Merge branch 'depends/rmk/devel-stable' into imx/imx6q

arch/arm/Kconfig

@@ -29,6 +29,7 @@ config ARM
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_SPARSE_IRQ
 	select GENERIC_IRQ_SHOW
+	select CPU_PM if (SUSPEND || CPU_IDLE)
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -1832,6 +1833,38 @@ config ZBOOT_ROM_SH_MOBILE_SDHI
 
 endchoice
 
+config ARM_APPENDED_DTB
+	bool "Use appended device tree blob to zImage (EXPERIMENTAL)"
+	depends on OF && !ZBOOT_ROM && EXPERIMENTAL
+	help
+	  With this option, the boot code will look for a device tree binary
+	  (DTB) appended to zImage
+	  (e.g. cat zImage <filename>.dtb > zImage_w_dtb).
+
+	  This is meant as a backward compatibility convenience for those
+	  systems with a bootloader that can't be upgraded to accommodate
+	  the documented boot protocol using a device tree.
+
+	  Beware that there is very little in terms of protection against
+	  this option being confused by leftover garbage in memory that might
+	  look like a DTB header after a reboot if no actual DTB is appended
+	  to zImage.  Do not leave this option active in a production kernel
+	  if you don't intend to always append a DTB.  Proper passing of the
+	  location into r2 of a bootloader provided DTB is always preferable
+	  to this option.
+
+config ARM_ATAG_DTB_COMPAT
+	bool "Supplement the appended DTB with traditional ATAG information"
+	depends on ARM_APPENDED_DTB
+	help
+	  Some old bootloaders can't be updated to a DTB capable one, yet
+	  they provide ATAGs with memory configuration, the ramdisk address,
+	  the kernel cmdline string, etc.  Such information is dynamically
+	  provided by the bootloader and can't always be stored in a static
+	  DTB.  To allow a device tree enabled kernel to be used with such
+	  bootloaders, this option allows zImage to extract the information
+	  from the ATAG list and store it at run time into the appended DTB.
+
 config CMDLINE
 	string "Default kernel command string"
 	default ""

arch/arm/Kconfig.debug

@@ -158,4 +158,10 @@ config DEBUG_S3C_UART
 	  The uncompressor code port configuration is now handled
 	  by CONFIG_S3C_LOWLEVEL_UART_PORT.
 
+config ARM_KPROBES_TEST
+	tristate "Kprobes test module"
+	depends on KPROBES && MODULES
+	help
+	  Perform tests of kprobes API and instruction set simulation.
+
 endmenu

arch/arm/boot/compressed/.gitignore

@@ -5,3 +5,12 @@ piggy.lzo
 piggy.lzma
 vmlinux
 vmlinux.lds
+
+# borrowed libfdt files
+fdt.c
+fdt.h
+fdt_ro.c
+fdt_rw.c
+fdt_wip.c
+libfdt.h
+libfdt_internal.h

arch/arm/boot/compressed/Makefile

@@ -26,6 +26,10 @@ HEAD	= head.o
 OBJS	+= misc.o decompress.o
 FONTC	= $(srctree)/drivers/video/console/font_acorn_8x8.c
 
+# string library code (-Os is enforced to keep it much smaller)
+OBJS		+= string.o
+CFLAGS_string.o	:= -Os
+
 #
 # Architecture dependencies
 #
@@ -89,21 +93,41 @@ suffix_$(CONFIG_KERNEL_GZIP) = gzip
 suffix_$(CONFIG_KERNEL_LZO)  = lzo
 suffix_$(CONFIG_KERNEL_LZMA) = lzma
 
+# Borrowed libfdt files for the ATAG compatibility mode
+
+libfdt		:= fdt_rw.c fdt_ro.c fdt_wip.c fdt.c
+libfdt_hdrs	:= fdt.h libfdt.h libfdt_internal.h
+
+libfdt_objs	:= $(addsuffix .o, $(basename $(libfdt)))
+
+$(addprefix $(obj)/,$(libfdt) $(libfdt_hdrs)): $(obj)/%: $(srctree)/scripts/dtc/libfdt/%
+	$(call cmd,shipped)
+
+$(addprefix $(obj)/,$(libfdt_objs) atags_to_fdt.o): \
+	$(addprefix $(obj)/,$(libfdt_hdrs))
+
+ifeq ($(CONFIG_ARM_ATAG_DTB_COMPAT),y)
+OBJS	+= $(libfdt_objs) atags_to_fdt.o
+endif
+
 targets       := vmlinux vmlinux.lds \
 		 piggy.$(suffix_y) piggy.$(suffix_y).o \
-		 font.o font.c head.o misc.o $(OBJS)
+		 lib1funcs.o lib1funcs.S font.o font.c head.o misc.o $(OBJS)
 
 # Make sure files are removed during clean
-extra-y       += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S
+extra-y       += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S $(libfdt) $(libfdt_hdrs)
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
 endif
 
-ccflags-y := -fpic -fno-builtin
+ccflags-y := -fpic -fno-builtin -I$(obj)
 asflags-y := -Wa,-march=all
 
+# Supply kernel BSS size to the decompressor via a linker symbol.
+KBSS_SZ = $(shell size $(obj)/../../../../vmlinux | awk 'END{print $$3}')
+LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
 # Supply ZRELADDR to the decompressor via a linker symbol.
 ifneq ($(CONFIG_AUTO_ZRELADDR),y)
 LDFLAGS_vmlinux += --defsym zreladdr=$(ZRELADDR)
@@ -123,7 +147,7 @@ LDFLAGS_vmlinux += -T
 # For __aeabi_uidivmod
 lib1funcs = $(obj)/lib1funcs.o
 
-$(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S FORCE
+$(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S
 	$(call cmd,shipped)
 
 # We need to prevent any GOTOFF relocs being used with references

arch/arm/boot/compressed/atags_to_fdt.c

+#include <asm/setup.h>
+#include <libfdt.h>
+
+static int node_offset(void *fdt, const char *node_path)
+{
+	int offset = fdt_path_offset(fdt, node_path);
+	if (offset == -FDT_ERR_NOTFOUND)
+		offset = fdt_add_subnode(fdt, 0, node_path);
+	return offset;
+}
+
+static int setprop(void *fdt, const char *node_path, const char *property,
+		   uint32_t *val_array, int size)
+{
+	int offset = node_offset(fdt, node_path);
+	if (offset < 0)
+		return offset;
+	return fdt_setprop(fdt, offset, property, val_array, size);
+}
+
+static int setprop_string(void *fdt, const char *node_path,
+			  const char *property, const char *string)
+{
+	int offset = node_offset(fdt, node_path);
+	if (offset < 0)
+		return offset;
+	return fdt_setprop_string(fdt, offset, property, string);
+}
+
+static int setprop_cell(void *fdt, const char *node_path,
+			const char *property, uint32_t val)
+{
+	int offset = node_offset(fdt, node_path);
+	if (offset < 0)
+		return offset;
+	return fdt_setprop_cell(fdt, offset, property, val);
+}
+
+/*
+ * Convert and fold provided ATAGs into the provided FDT.
+ *
+ * REturn values:
+ *    = 0 -> pretend success
+ *    = 1 -> bad ATAG (may retry with another possible ATAG pointer)
+ *    < 0 -> error from libfdt
+ */
+int atags_to_fdt(void *atag_list, void *fdt, int total_space)
+{
+	struct tag *atag = atag_list;
+	uint32_t mem_reg_property[2 * NR_BANKS];
+	int memcount = 0;
+	int ret;
+
+	/* make sure we've got an aligned pointer */
+	if ((u32)atag_list & 0x3)
+		return 1;
+
+	/* if we get a DTB here we're done already */
+	if (*(u32 *)atag_list == fdt32_to_cpu(FDT_MAGIC))
+	       return 0;
+
+	/* validate the ATAG */
+	if (atag->hdr.tag != ATAG_CORE ||
+	    (atag->hdr.size != tag_size(tag_core) &&
+	     atag->hdr.size != 2))
+		return 1;
+
+	/* let's give it all the room it could need */
+	ret = fdt_open_into(fdt, fdt, total_space);
+	if (ret < 0)
+		return ret;
+
+	for_each_tag(atag, atag_list) {
+		if (atag->hdr.tag == ATAG_CMDLINE) {
+			setprop_string(fdt, "/chosen", "bootargs",
+					atag->u.cmdline.cmdline);
+		} else if (atag->hdr.tag == ATAG_MEM) {
+			if (memcount >= sizeof(mem_reg_property)/4)
+				continue;
+			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
+			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
+		} else if (atag->hdr.tag == ATAG_INITRD2) {
+			uint32_t initrd_start, initrd_size;
+			initrd_start = atag->u.initrd.start;
+			initrd_size = atag->u.initrd.size;
+			setprop_cell(fdt, "/chosen", "linux,initrd-start",
+					initrd_start);
+			setprop_cell(fdt, "/chosen", "linux,initrd-end",
+					initrd_start + initrd_size);
+		}
+	}
+
+	if (memcount)
+		setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount);
+
+	return fdt_pack(fdt);
+}

arch/arm/boot/compressed/head.S

@@ -216,6 +216,103 @@ restart:	adr	r0, LC0
 		mov	r10, r6
 #endif
 
+		mov	r5, #0			@ init dtb size to 0
+#ifdef CONFIG_ARM_APPENDED_DTB
+/*
+ *   r0  = delta
+ *   r2  = BSS start
+ *   r3  = BSS end
+ *   r4  = final kernel address
+ *   r5  = appended dtb size (still unknown)
+ *   r6  = _edata
+ *   r7  = architecture ID
+ *   r8  = atags/device tree pointer
+ *   r9  = size of decompressed image
+ *   r10 = end of this image, including  bss/stack/malloc space if non XIP
+ *   r11 = GOT start
+ *   r12 = GOT end
+ *   sp  = stack pointer
+ *
+ * if there are device trees (dtb) appended to zImage, advance r10 so that the
+ * dtb data will get relocated along with the kernel if necessary.
+ */
+
+		ldr	lr, [r6, #0]
+#ifndef __ARMEB__
+		ldr	r1, =0xedfe0dd0		@ sig is 0xd00dfeed big endian
+#else
+		ldr	r1, =0xd00dfeed
+#endif
+		cmp	lr, r1
+		bne	dtb_check_done		@ not found
+
+#ifdef CONFIG_ARM_ATAG_DTB_COMPAT
+		/*
+		 * OK... Let's do some funky business here.
+		 * If we do have a DTB appended to zImage, and we do have
+		 * an ATAG list around, we want the later to be translated
+		 * and folded into the former here.  To be on the safe side,
+		 * let's temporarily move  the stack away into the malloc
+		 * area.  No GOT fixup has occurred yet, but none of the
+		 * code we're about to call uses any global variable.
+		*/
+		add	sp, sp, #0x10000
+		stmfd	sp!, {r0-r3, ip, lr}
+		mov	r0, r8
+		mov	r1, r6
+		sub	r2, sp, r6
+		bl	atags_to_fdt
+
+		/*
+		 * If returned value is 1, there is no ATAG at the location
+		 * pointed by r8.  Try the typical 0x100 offset from start
+		 * of RAM and hope for the best.
+		 */
+		cmp	r0, #1
+		sub	r0, r4, #(TEXT_OFFSET - 0x100)
+		mov	r1, r6
+		sub	r2, sp, r6
+		blne	atags_to_fdt
+
+		ldmfd	sp!, {r0-r3, ip, lr}
+		sub	sp, sp, #0x10000
+#endif
+
+		mov	r8, r6			@ use the appended device tree
+
+		/*
+		 * Make sure that the DTB doesn't end up in the final
+		 * kernel's .bss area. To do so, we adjust the decompressed
+		 * kernel size to compensate if that .bss size is larger
+		 * than the relocated code.
+		 */
+		ldr	r5, =_kernel_bss_size
+		adr	r1, wont_overwrite
+		sub	r1, r6, r1
+		subs	r1, r5, r1
+		addhi	r9, r9, r1
+
+		/* Get the dtb's size */
+		ldr	r5, [r6, #4]
+#ifndef __ARMEB__
+		/* convert r5 (dtb size) to little endian */
+		eor	r1, r5, r5, ror #16
+		bic	r1, r1, #0x00ff0000
+		mov	r5, r5, ror #8
+		eor	r5, r5, r1, lsr #8
+#endif
+
+		/* preserve 64-bit alignment */
+		add	r5, r5, #7
+		bic	r5, r5, #7
+
+		/* relocate some pointers past the appended dtb */
+		add	r6, r6, r5
+		add	r10, r10, r5
+		add	sp, sp, r5
+dtb_check_done:
+#endif
+
 /*
  * Check to see if we will overwrite ourselves.
  *   r4  = final kernel address
@@ -223,15 +320,14 @@ restart:	adr	r0, LC0
  *   r10 = end of this image, including  bss/stack/malloc space if non XIP
  * We basically want:
  *   r4 - 16k page directory >= r10 -> OK
- *   r4 + image length <= current position (pc) -> OK
+ *   r4 + image length <= address of wont_overwrite -> OK
  */
 		add	r10, r10, #16384
 		cmp	r4, r10
 		bhs	wont_overwrite
 		add	r10, r4, r9
-   ARM(		cmp	r10, pc		)
- THUMB(		mov	lr, pc		)
- THUMB(		cmp	r10, lr		)
+		adr	r9, wont_overwrite
+		cmp	r10, r9
 		bls	wont_overwrite
 
 /*
@@ -285,14 +381,16 @@ wont_overwrite:
  *   r2  = BSS start
  *   r3  = BSS end
  *   r4  = kernel execution address
+ *   r5  = appended dtb size (0 if not present)
  *   r7  = architecture ID
  *   r8  = atags pointer
  *   r11 = GOT start
  *   r12 = GOT end
  *   sp  = stack pointer
  */
-		teq	r0, #0
+		orrs	r1, r0, r5
 		beq	not_relocated
+
 		add	r11, r11, r0
 		add	r12, r12, r0
 
@@ -307,12 +405,21 @@ wont_overwrite:
 
 		/*
 		 * Relocate all entries in the GOT table.
+		 * Bump bss entries to _edata + dtb size
 		 */
 1:		ldr	r1, [r11, #0]		@ relocate entries in the GOT
-		add	r1, r1, r0		@ table.  This fixes up the
-		str	r1, [r11], #4		@ C references.
+		add	r1, r1, r0		@ This fixes up C references
+		cmp	r1, r2			@ if entry >= bss_start &&
+		cmphs	r3, r1			@       bss_end > entry
+		addhi	r1, r1, r5		@    entry += dtb size
+		str	r1, [r11], #4		@ next entry
 		cmp	r11, r12
 		blo	1b
+
+		/* bump our bss pointers too */
+		add	r2, r2, r5
+		add	r3, r3, r5
+
 #else
 
 		/*

arch/arm/boot/compressed/libfdt_env.h

+#ifndef _ARM_LIBFDT_ENV_H
+#define _ARM_LIBFDT_ENV_H
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <asm/byteorder.h>
+
+#define fdt16_to_cpu(x)		be16_to_cpu(x)
+#define cpu_to_fdt16(x)		cpu_to_be16(x)
+#define fdt32_to_cpu(x)		be32_to_cpu(x)
+#define cpu_to_fdt32(x)		cpu_to_be32(x)
+#define fdt64_to_cpu(x)		be64_to_cpu(x)
+#define cpu_to_fdt64(x)		cpu_to_be64(x)
+
+#endif

arch/arm/boot/compressed/misc.c

@@ -18,14 +18,9 @@
 
 unsigned int __machine_arch_type;
 
-#define _LINUX_STRING_H_
-
 #include <linux/compiler.h>	/* for inline */
-#include <linux/types.h>	/* for size_t */
-#include <linux/stddef.h>	/* for NULL */
+#include <linux/types.h>
 #include <linux/linkage.h>
-#include <asm/string.h>
-
 
 static void putstr(const char *ptr);
 extern void error(char *x);
@@ -101,41 +96,6 @@ static void putstr(const char *ptr)
 	flush();
 }
 
-
-void *memcpy(void *__dest, __const void *__src, size_t __n)
-{
-	int i = 0;
-	unsigned char *d = (unsigned char *)__dest, *s = (unsigned char *)__src;
-
-	for (i = __n >> 3; i > 0; i--) {
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (__n & 1 << 2) {
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (__n & 1 << 1) {
-		*d++ = *s++;
-		*d++ = *s++;
-	}
-
-	if (__n & 1)
-		*d++ = *s++;
-
-	return __dest;
-}
-
 /*
  * gzip declarations
  */

arch/arm/boot/compressed/string.c

+/*
+ * arch/arm/boot/compressed/string.c
+ *
+ * Small subset of simple string routines
+ */
+
+#include <linux/string.h>
+
+void *memcpy(void *__dest, __const void *__src, size_t __n)
+{
+	int i = 0;
+	unsigned char *d = (unsigned char *)__dest, *s = (unsigned char *)__src;
+
+	for (i = __n >> 3; i > 0; i--) {
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+	}
+
+	if (__n & 1 << 2) {
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+		*d++ = *s++;
+	}
+
+	if (__n & 1 << 1) {
+		*d++ = *s++;
+		*d++ = *s++;
+	}
+
+	if (__n & 1)
+		*d++ = *s++;
+
+	return __dest;
+}
+
+void *memmove(void *__dest, __const void *__src, size_t count)
+{
+	unsigned char *d = __dest;
+	const unsigned char *s = __src;
+
+	if (__dest == __src)
+		return __dest;
+
+	if (__dest < __src)
+		return memcpy(__dest, __src, count);
+
+	while (count--)
+		d[count] = s[count];
+	return __dest;
+}
+
+size_t strlen(const char *s)
+{
+	const char *sc = s;
+
+	while (*sc != '\0')
+		sc++;
+	return sc - s;
+}
+
+int memcmp(const void *cs, const void *ct, size_t count)
+{
+	const unsigned char *su1 = cs, *su2 = ct, *end = su1 + count;
+	int res = 0;
+
+	while (su1 < end) {
+		res = *su1++ - *su2++;
+		if (res)
+			break;
+	}
+	return res;
+}
+
+int strcmp(const char *cs, const char *ct)
+{
+	unsigned char c1, c2;
+	int res = 0;
+
+	do {
+		c1 = *cs++;
+		c2 = *ct++;
+		res = c1 - c2;
+		if (res)
+			break;
+	} while (c1);
+	return res;
+}
+
+void *memchr(const void *s, int c, size_t count)
+{
+	const unsigned char *p = s;
+
+	while (count--)
+		if ((unsigned char)c == *p++)
+			return (void *)(p - 1);
+	return NULL;
+}
+
+char *strchr(const char *s, int c)
+{
+	while (*s != (char)c)
+		if (*s++ == '\0')
+			return NULL;
+	return (char *)s;
+}
+
+#undef memset
+
+void *memset(void *s, int c, size_t count)
+{
+	char *xs = s;
+	while (count--)
+		*xs++ = c;
+	return s;
+}
+
+void __memzero(void *s, size_t count)
+{
+	memset(s, 0, count);
+}

arch/arm/boot/compressed/vmlinux.lds.in

@@ -51,6 +51,10 @@ SECTIONS
   _got_start = .;
   .got			: { *(.got) }
   _got_end = .;
+
+  /* ensure the zImage file size is always a multiple of 64 bits */
+  /* (without a dummy byte, ld just ignores the empty section) */
+  .pad			: { BYTE(0); . = ALIGN(8); }
   _edata = .;
 
   . = BSS_START;

arch/arm/common/gic.c

@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/smp.h>
+#include <linux/cpu_pm.h>
 #include <linux/cpumask.h>
 #include <linux/io.h>
 
@@ -282,6 +283,8 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
 
+	gic->gic_irqs = gic_irqs;
+
 	/*
 	 * Set all global interrupts to be level triggered, active low.
 	 */
@@ -349,6 +352,189 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
+#ifdef CONFIG_CPU_PM
+/*
+ * Saves the GIC distributor registers during suspend or idle.  Must be called
+ * with interrupts disabled but before powering down the GIC.  After calling
+ * this function, no interrupts will be delivered by the GIC, and another
+ * platform-specific wakeup source must be enabled.
+ */
+static void gic_dist_save(unsigned int gic_nr)
+{
+	unsigned int gic_irqs;
+	void __iomem *dist_base;
+	int i;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+	dist_base = gic_data[gic_nr].dist_base;
+
+	if (!dist_base)
+		return;
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
+		gic_data[gic_nr].saved_spi_conf[i] =
+			readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		gic_data[gic_nr].saved_spi_target[i] =
+			readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		gic_data[gic_nr].saved_spi_enable[i] =
+			readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+}
+
+/*
+ * Restores the GIC distributor registers during resume or when coming out of
+ * idle.  Must be called before enabling interrupts.  If a level interrupt
+ * that occured while the GIC was suspended is still present, it will be
+ * handled normally, but any edge interrupts that occured will not be seen by
+ * the GIC and need to be handled by the platform-specific wakeup source.
+ */
+static void gic_dist_restore(unsigned int gic_nr)
+{
+	unsigned int gic_irqs;
+	unsigned int i;
+	void __iomem *dist_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+	dist_base = gic_data[gic_nr].dist_base;
+
+	if (!dist_base)
+		return;
+
+	writel_relaxed(0, dist_base + GIC_DIST_CTRL);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_conf[i],
+			dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		writel_relaxed(0xa0a0a0a0,
+			dist_base + GIC_DIST_PRI + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_target[i],
+			dist_base + GIC_DIST_TARGET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_enable[i],
+			dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	writel_relaxed(1, dist_base + GIC_DIST_CTRL);
+}
+
+static void gic_cpu_save(unsigned int gic_nr)
+{
+	int i;
+	u32 *ptr;
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data[gic_nr].dist_base;
+	cpu_base = gic_data[gic_nr].cpu_base;
+
+	if (!dist_base || !cpu_base)
+		return;
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
+
+}
+
+static void gic_cpu_restore(unsigned int gic_nr)
+{
+	int i;
+	u32 *ptr;
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data[gic_nr].dist_base;
+	cpu_base = gic_data[gic_nr].cpu_base;
+
+	if (!dist_base || !cpu_base)
+		return;
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(32, 4); i++)
+		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4);
+
+	writel_relaxed(0xf0, cpu_base + GIC_CPU_PRIMASK);
+	writel_relaxed(1, cpu_base + GIC_CPU_CTRL);
+}
+
+static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
+{
+	int i;
+
+	for (i = 0; i < MAX_GIC_NR; i++) {
+		switch (cmd) {
+		case CPU_PM_ENTER:
+			gic_cpu_save(i);
+			break;
+		case CPU_PM_ENTER_FAILED:
+		case CPU_PM_EXIT:
+			gic_cpu_restore(i);
+			break;
+		case CPU_CLUSTER_PM_ENTER:
+			gic_dist_save(i);
+			break;
+		case CPU_CLUSTER_PM_ENTER_FAILED:
+		case CPU_CLUSTER_PM_EXIT:
+			gic_dist_restore(i);
+			break;
+		}
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gic_notifier_block = {
+	.notifier_call = gic_notifier,
+};
+
+static void __init gic_pm_init(struct gic_chip_data *gic)
+{
+	gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_enable);
+
+	gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_conf);
+
+	cpu_pm_register_notifier(&gic_notifier_block);
+}
+#else
+static void __init gic_pm_init(struct gic_chip_data *gic)
+{
+}
+#endif
+
 void __init gic_init(unsigned int gic_nr, unsigned int irq_start,
 	void __iomem *dist_base, void __iomem *cpu_base)
 {
@@ -364,8 +550,10 @@ void __init gic_init(unsigned int gic_nr, unsigned int irq_start,
 	if (gic_nr == 0)
 		gic_cpu_base_addr = cpu_base;
 
+	gic_chip.flags |= gic_arch_extn.flags;
 	gic_dist_init(gic, irq_start);
 	gic_cpu_init(gic);
+	gic_pm_init(gic);
 }
 
 void __cpuinit gic_secondary_init(unsigned int gic_nr)

arch/arm/include/asm/dma-mapping.h

@@ -205,6 +205,13 @@ extern void *dma_alloc_writecombine(struct device *, size_t, dma_addr_t *,
 int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
 		void *, dma_addr_t, size_t);
 
+/*
+ * This can be called during boot to increase the size of the consistent
+ * DMA region above it's default value of 2MB. It must be called before the
+ * memory allocator is initialised, i.e. before any core_initcall.
+ */
+extern void __init init_consistent_dma_size(unsigned long size);
+
 
 #ifdef CONFIG_DMABOUNCE
 /*

arch/arm/include/asm/hardware/gic.h

@@ -46,6 +46,14 @@ struct gic_chip_data {
 	unsigned int irq_offset;
 	void __iomem *dist_base;
 	void __iomem *cpu_base;
+#ifdef CONFIG_CPU_PM
+	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
+	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
+	u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
+	u32 __percpu *saved_ppi_enable;
+	u32 __percpu *saved_ppi_conf;
+#endif
+	unsigned int gic_irqs;
 };
 #endif
 

arch/arm/include/asm/hw_breakpoint.h

@@ -50,6 +50,7 @@ static inline void decode_ctrl_reg(u32 reg,
 #define ARM_DEBUG_ARCH_V6_1	2
 #define ARM_DEBUG_ARCH_V7_ECP14	3
 #define ARM_DEBUG_ARCH_V7_MM	4
+#define ARM_DEBUG_ARCH_V7_1	5
 
 /* Breakpoint */
 #define ARM_BREAKPOINT_EXECUTE	0
@@ -57,6 +58,7 @@ static inline void decode_ctrl_reg(u32 reg,
 /* Watchpoints */
 #define ARM_BREAKPOINT_LOAD	1
 #define ARM_BREAKPOINT_STORE	2
+#define ARM_FSR_ACCESS_MASK	(1 << 11)
 
 /* Privilege Levels */
 #define ARM_BREAKPOINT_PRIV	1

arch/arm/include/asm/mach/arch.h

@@ -17,7 +17,7 @@ struct sys_timer;
 struct machine_desc {
 	unsigned int		nr;		/* architecture number	*/
 	const char		*name;		/* architecture name	*/
-	unsigned long		boot_params;	/* tagged list		*/
+	unsigned long		atag_offset;	/* tagged list (relative) */
 	const char		**dt_compat;	/* array of device tree
 						 * 'compatible' strings	*/
 

arch/arm/include/asm/mach/map.h

@@ -29,6 +29,7 @@ struct map_desc {
 #define MT_MEMORY_NONCACHED	11
 #define MT_MEMORY_DTCM		12
 #define MT_MEMORY_ITCM		13
+#define MT_MEMORY_SO		14
 
 #ifdef CONFIG_MMU
 extern void iotable_init(struct map_desc *, int);

arch/arm/include/asm/memory.h

@@ -77,16 +77,7 @@
  */
 #define IOREMAP_MAX_ORDER	24
 
-/*
- * Size of DMA-consistent memory region.  Must be multiple of 2M,
- * between 2MB and 14MB inclusive.
- */
-#ifndef CONSISTENT_DMA_SIZE
-#define CONSISTENT_DMA_SIZE 	SZ_2M
-#endif
-
 #define CONSISTENT_END		(0xffe00000UL)
-#define CONSISTENT_BASE		(CONSISTENT_END - CONSISTENT_DMA_SIZE)
 
 #else /* CONFIG_MMU */
 

arch/arm/include/asm/pgtable.h

@@ -232,6 +232,9 @@ extern pgprot_t		pgprot_kernel;
 #define pgprot_writecombine(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE)
 
+#define pgprot_stronglyordered(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
+
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN)

arch/arm/include/asm/pmu.h

@@ -13,7 +13,12 @@
 #define __ARM_PMU_H__
 
 #include <linux/interrupt.h>
+#include <linux/perf_event.h>
 
+/*
+ * Types of PMUs that can be accessed directly and require mutual
+ * exclusion between profiling tools.
+ */
 enum arm_pmu_type {
 	ARM_PMU_DEVICE_CPU	= 0,
 	ARM_NUM_PMU_DEVICES,
@@ -37,21 +42,17 @@ struct arm_pmu_platdata {
  * reserve_pmu() - reserve the hardware performance counters
  *
  * Reserve the hardware performance counters in the system for exclusive use.
- * The platform_device for the system is returned on success, ERR_PTR()
- * encoded error on failure.
+ * Returns 0 on success or -EBUSY if the lock is already held.
  */
-extern struct platform_device *
+extern int
 reserve_pmu(enum arm_pmu_type type);
 
 /**
  * release_pmu() - Relinquish control of the performance counters
  *
  * Release the performance counters and allow someone else to use them.
- * Callers must have disabled the counters and released IRQs before calling
- * this. The platform_device returned from reserve_pmu() must be passed as
- * a cookie.
  */
-extern int
+extern void
 release_pmu(enum arm_pmu_type type);
 
 /**
@@ -68,24 +69,78 @@ init_pmu(enum arm_pmu_type type);
 
 #include <linux/err.h>
 
-static inline struct platform_device *
-reserve_pmu(enum arm_pmu_type type)
-{
-	return ERR_PTR(-ENODEV);
-}
-
 static inline int
-release_pmu(enum arm_pmu_type type)
+reserve_pmu(enum arm_pmu_type type)
 {
 	return -ENODEV;
 }
 
-static inline int
-init_pmu(enum arm_pmu_type type)
-{
-	return -ENODEV;
-}
+static inline void
+release_pmu(enum arm_pmu_type type)	{ }
 
 #endif /* CONFIG_CPU_HAS_PMU */
 
+#ifdef CONFIG_HW_PERF_EVENTS
+
+/* The events for a given PMU register set. */
+struct pmu_hw_events {
+	/*
+	 * The events that are active on the PMU for the given index.
+	 */
+	struct perf_event	**events;
+
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	unsigned long           *used_mask;
+
+	/*
+	 * Hardware lock to serialize accesses to PMU registers. Needed for the
+	 * read/modify/write sequences.
+	 */
+	raw_spinlock_t		pmu_lock;
+};
+
+struct arm_pmu {
+	struct pmu	pmu;
+	enum arm_perf_pmu_ids id;
+	enum arm_pmu_type type;
+	cpumask_t	active_irqs;
+	const char	*name;
+	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
+	void		(*enable)(struct hw_perf_event *evt, int idx);
+	void		(*disable)(struct hw_perf_event *evt, int idx);
+	int		(*get_event_idx)(struct pmu_hw_events *hw_events,
+					 struct hw_perf_event *hwc);
+	int		(*set_event_filter)(struct hw_perf_event *evt,
+					    struct perf_event_attr *attr);
+	u32		(*read_counter)(int idx);
+	void		(*write_counter)(int idx, u32 val);
+	void		(*start)(void);
+	void		(*stop)(void);
+	void		(*reset)(void *);
+	int		(*map_event)(struct perf_event *event);
+	int		num_events;
+	atomic_t	active_events;
+	struct mutex	reserve_mutex;
+	u64		max_period;
+	struct platform_device	*plat_device;
+	struct pmu_hw_events	*(*get_hw_events)(void);
+};
+
+#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
+
+int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type);
+
+u64 armpmu_event_update(struct perf_event *event,
+			struct hw_perf_event *hwc,
+			int idx, int overflow);
+
+int armpmu_event_set_period(struct perf_event *event,
+			    struct hw_perf_event *hwc,
+			    int idx);
+
+#endif /* CONFIG_HW_PERF_EVENTS */
+
 #endif /* __ARM_PMU_H__ */

arch/arm/include/asm/proc-fns.h

@@ -81,6 +81,10 @@ extern void cpu_dcache_clean_area(void *, int);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+
+/* These three are private to arch/arm/kernel/suspend.c */
+extern void cpu_do_suspend(void *);
+extern void cpu_do_resume(void *);
 #else
 #define cpu_proc_init			processor._proc_init
 #define cpu_proc_fin			processor._proc_fin
@@ -89,6 +93,10 @@ extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 #define cpu_dcache_clean_area		processor.dcache_clean_area
 #define cpu_set_pte_ext			processor.set_pte_ext
 #define cpu_do_switch_mm		processor.switch_mm
+
+/* These three are private to arch/arm/kernel/suspend.c */
+#define cpu_do_suspend			processor.do_suspend
+#define cpu_do_resume			processor.do_resume
 #endif
 
 extern void cpu_resume(void);

arch/arm/include/asm/suspend.h

 #ifndef __ASM_ARM_SUSPEND_H
 #define __ASM_ARM_SUSPEND_H
 
-#include <asm/memory.h>
-#include <asm/tlbflush.h>
-
 extern void cpu_resume(void);
-
-/*
- * Hide the first two arguments to __cpu_suspend - these are an implementation
- * detail which platform code shouldn't have to know about.
- */
-static inline int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
-{
-	extern int __cpu_suspend(int, long, unsigned long,
-				 int (*)(unsigned long));
-	int ret = __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn);
-	flush_tlb_all();
-	return ret;
-}
+extern int cpu_suspend(unsigned long, int (*)(unsigned long));
 
 #endif

arch/arm/kernel/Makefile

@@ -29,7 +29,7 @@ obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
-obj-$(CONFIG_PM_SLEEP)		+= sleep.o
+obj-$(CONFIG_PM_SLEEP)		+= sleep.o suspend.o
 obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
@@ -43,6 +43,13 @@ obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
 else
 obj-$(CONFIG_KPROBES)		+= kprobes-arm.o
 endif
+obj-$(CONFIG_ARM_KPROBES_TEST)	+= test-kprobes.o
+test-kprobes-objs		:= kprobes-test.o
+ifdef CONFIG_THUMB2_KERNEL
+test-kprobes-objs		+= kprobes-test-thumb.o
+else
+test-kprobes-objs		+= kprobes-test-arm.o
+endif
 obj-$(CONFIG_ATAGS_PROC)	+= atags.o
 obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o

arch/arm/kernel/hw_breakpoint.c

@@ -45,7 +45,6 @@ static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
 
 /* Number of BRP/WRP registers on this CPU. */
 static int core_num_brps;
-static int core_num_reserved_brps;
 static int core_num_wrps;
 
 /* Debug architecture version. */
@@ -137,10 +136,11 @@ static u8 get_debug_arch(void)
 	u32 didr;
 
 	/* Do we implement the extended CPUID interface? */
-	if (WARN_ONCE((((read_cpuid_id() >> 16) & 0xf) != 0xf),
-	    "CPUID feature registers not supported. "
-	    "Assuming v6 debug is present.\n"))
+	if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
+		pr_warning("CPUID feature registers not supported. "
+			   "Assuming v6 debug is present.\n");
 		return ARM_DEBUG_ARCH_V6;
+	}
 
 	ARM_DBG_READ(c0, 0, didr);
 	return (didr >> 16) & 0xf;
@@ -154,10 +154,21 @@ u8 arch_get_debug_arch(void)
 static int debug_arch_supported(void)
 {
 	u8 arch = get_debug_arch();
-	return arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14;
+
+	/* We don't support the memory-mapped interface. */
+	return (arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14) ||
+		arch >= ARM_DEBUG_ARCH_V7_1;
+}
+
+/* Determine number of WRP registers available. */
+static int get_num_wrp_resources(void)
+{
+	u32 didr;
+	ARM_DBG_READ(c0, 0, didr);
+	return ((didr >> 28) & 0xf) + 1;
 }
 
-/* Determine number of BRP register available. */
+/* Determine number of BRP registers available. */
 static int get_num_brp_resources(void)
 {
 	u32 didr;
@@ -176,9 +187,10 @@ static int core_has_mismatch_brps(void)
 static int get_num_wrps(void)
 {
 	/*
-	 * FIXME: When a watchpoint fires, the only way to work out which
-	 * watchpoint it was is by disassembling the faulting instruction
-	 * and working out the address of the memory access.
+	 * On debug architectures prior to 7.1, when a watchpoint fires, the
+	 * only way to work out which watchpoint it was is by disassembling
+	 * the faulting instruction and working out the address of the memory
+	 * access.
 	 *
 	 * Furthermore, we can only do this if the watchpoint was precise
 	 * since imprecise watchpoints prevent us from calculating register
@@ -192,36 +204,17 @@ static int get_num_wrps(void)
 	 * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows
 	 * that it is set on some implementations].
 	 */
+	if (get_debug_arch() < ARM_DEBUG_ARCH_V7_1)
+		return 1;
 
-#if 0
-	int wrps;
-	u32 didr;
-	ARM_DBG_READ(c0, 0, didr);
-	wrps = ((didr >> 28) & 0xf) + 1;
-#endif
-	int wrps = 1;
-
-	if (core_has_mismatch_brps() && wrps >= get_num_brp_resources())
-		wrps = get_num_brp_resources() - 1;
-
-	return wrps;
-}
-
-/* We reserve one breakpoint for each watchpoint. */
-static int get_num_reserved_brps(void)
-{
-	if (core_has_mismatch_brps())
-		return get_num_wrps();
-	return 0;
+	return get_num_wrp_resources();
 }
 
 /* Determine number of usable BRPs available. */
 static int get_num_brps(void)
 {
 	int brps = get_num_brp_resources();
-	if (core_has_mismatch_brps())
-		brps -= get_num_reserved_brps();
-	return brps;
+	return core_has_mismatch_brps() ? brps - 1 : brps;
 }
 
 /*
@@ -239,7 +232,7 @@ static int enable_monitor_mode(void)
 
 	/* Ensure that halting mode is disabled. */
 	if (WARN_ONCE(dscr & ARM_DSCR_HDBGEN,
-			"halting debug mode enabled. Unable to access hardware resources.\n")) {
+		"halting debug mode enabled. Unable to access hardware resources.\n")) {
 		ret = -EPERM;
 		goto out;
 	}
@@ -255,6 +248,7 @@ static int enable_monitor_mode(void)
 		ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN));
 		break;
 	case ARM_DEBUG_ARCH_V7_ECP14:
+	case ARM_DEBUG_ARCH_V7_1:
 		ARM_DBG_WRITE(c2, 2, (dscr | ARM_DSCR_MDBGEN));
 		break;
 	default:
@@ -346,24 +340,10 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		val_base = ARM_BASE_BVR;
 		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
 		max_slots = core_num_brps;
-		if (info->step_ctrl.enabled) {
-			/* Override the breakpoint data with the step data. */
-			addr = info->trigger & ~0x3;
-			ctrl = encode_ctrl_reg(info->step_ctrl);
-		}
 	} else {
 		/* Watchpoint */
-		if (info->step_ctrl.enabled) {
-			/* Install into the reserved breakpoint region. */
-			ctrl_base = ARM_BASE_BCR + core_num_brps;
-			val_base = ARM_BASE_BVR + core_num_brps;
-			/* Override the watchpoint data with the step data. */
-			addr = info->trigger & ~0x3;
-			ctrl = encode_ctrl_reg(info->step_ctrl);
-		} else {
-			ctrl_base = ARM_BASE_WCR;
-			val_base = ARM_BASE_WVR;
-		}
+		ctrl_base = ARM_BASE_WCR;
+		val_base = ARM_BASE_WVR;
 		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
@@ -382,6 +362,17 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		goto out;
 	}
 
+	/* Override the breakpoint data with the step data. */
+	if (info->step_ctrl.enabled) {
+		addr = info->trigger & ~0x3;
+		ctrl = encode_ctrl_reg(info->step_ctrl);
+		if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE) {
+			i = 0;
+			ctrl_base = ARM_BASE_BCR + core_num_brps;
+			val_base = ARM_BASE_BVR + core_num_brps;
+		}
+	}
+
 	/* Setup the address register. */
 	write_wb_reg(val_base + i, addr);
 
@@ -405,10 +396,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
-		if (info->step_ctrl.enabled)
-			base = ARM_BASE_BCR + core_num_brps;
-		else
-			base = ARM_BASE_WCR;
+		base = ARM_BASE_WCR;
 		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
@@ -426,6 +414,13 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot\n"))
 		return;
 
+	/* Ensure that we disable the mismatch breakpoint. */
+	if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE &&
+	    info->step_ctrl.enabled) {
+		i = 0;
+		base = ARM_BASE_BCR + core_num_brps;
+	}
+
 	/* Reset the control register. */
 	write_wb_reg(base + i, 0);
 }
@@ -632,10 +627,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * we can use the mismatch feature as a poor-man's hardware
 	 * single-step, but this only works for per-task breakpoints.
 	 */
-	if (WARN_ONCE(!bp->overflow_handler &&
-		(arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_brps()
-		 || !bp->hw.bp_target),
-			"overflow handler required but none found\n")) {
+	if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) ||
+	    !core_has_mismatch_brps() || !bp->hw.bp_target)) {
+		pr_warning("overflow handler required but none found\n");
 		ret = -EINVAL;
 	}
 out:
@@ -666,34 +660,62 @@ static void disable_single_step(struct perf_event *bp)
 	arch_install_hw_breakpoint(bp);
 }
 
-static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
+static void watchpoint_handler(unsigned long addr, unsigned int fsr,
+			       struct pt_regs *regs)
 {
-	int i;
+	int i, access;
+	u32 val, ctrl_reg, alignment_mask;
 	struct perf_event *wp, **slots;
 	struct arch_hw_breakpoint *info;
+	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
-	/* Without a disassembler, we can only handle 1 watchpoint. */
-	BUG_ON(core_num_wrps > 1);
-
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
 		wp = slots[i];
 
-		if (wp == NULL) {
-			rcu_read_unlock();
-			continue;
-		}
+		if (wp == NULL)
+			goto unlock;
 
+		info = counter_arch_bp(wp);
 		/*
-		 * The DFAR is an unknown value. Since we only allow a
-		 * single watchpoint, we can set the trigger to the lowest
-		 * possible faulting address.
+		 * The DFAR is an unknown value on debug architectures prior
+		 * to 7.1. Since we only allow a single watchpoint on these
+		 * older CPUs, we can set the trigger to the lowest possible
+		 * faulting address.
 		 */
-		info = counter_arch_bp(wp);
-		info->trigger = wp->attr.bp_addr;
+		if (debug_arch < ARM_DEBUG_ARCH_V7_1) {
+			BUG_ON(i > 0);
+			info->trigger = wp->attr.bp_addr;
+		} else {
+			if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+				alignment_mask = 0x7;
+			else
+				alignment_mask = 0x3;
+
+			/* Check if the watchpoint value matches. */
+			val = read_wb_reg(ARM_BASE_WVR + i);
+			if (val != (addr & ~alignment_mask))
+				goto unlock;
+
+			/* Possible match, check the byte address select. */
+			ctrl_reg = read_wb_reg(ARM_BASE_WCR + i);
+			decode_ctrl_reg(ctrl_reg, &ctrl);
+			if (!((1 << (addr & alignment_mask)) & ctrl.len))
+				goto unlock;
+
+			/* Check that the access type matches. */
+			access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W :
+				 HW_BREAKPOINT_R;
+			if (!(access & hw_breakpoint_type(wp)))
+				goto unlock;
+
+			/* We have a winner. */
+			info->trigger = addr;
+		}
+
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
 		perf_bp_event(wp, regs);
 
@@ -705,6 +727,7 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 		if (!wp->overflow_handler)
 			enable_single_step(wp, instruction_pointer(regs));
 
+unlock:
 		rcu_read_unlock();
 	}
 }
@@ -717,7 +740,7 @@ static void watchpoint_single_step_handler(unsigned long pc)
 
 	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
-	for (i = 0; i < core_num_reserved_brps; ++i) {
+	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
 		wp = slots[i];
@@ -820,7 +843,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
 		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
 	case ARM_ENTRY_SYNC_WATCHPOINT:
-		watchpoint_handler(addr, regs);
+		watchpoint_handler(addr, fsr, regs);
 		break;
 	default:
 		ret = 1; /* Unhandled fault. */
@@ -834,11 +857,31 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 /*
  * One-time initialisation.
  */
-static void reset_ctrl_regs(void *info)
+static cpumask_t debug_err_mask;
+
+static int debug_reg_trap(struct pt_regs *regs, unsigned int instr)
 {
-	int i, cpu = smp_processor_id();
+	int cpu = smp_processor_id();
+
+	pr_warning("Debug register access (0x%x) caused undefined instruction on CPU %d\n",
+		   instr, cpu);
+
+	/* Set the error flag for this CPU and skip the faulting instruction. */
+	cpumask_set_cpu(cpu, &debug_err_mask);
+	instruction_pointer(regs) += 4;
+	return 0;
+}
+
+static struct undef_hook debug_reg_hook = {
+	.instr_mask	= 0x0fe80f10,
+	.instr_val	= 0x0e000e10,
+	.fn		= debug_reg_trap,
+};
+
+static void reset_ctrl_regs(void *unused)
+{
+	int i, raw_num_brps, err = 0, cpu = smp_processor_id();
 	u32 dbg_power;
-	cpumask_t *cpumask = info;
 
 	/*
 	 * v7 debug contains save and restore registers so that debug state
@@ -848,38 +891,57 @@ static void reset_ctrl_regs(void *info)
 	 * Access Register to avoid taking undefined instruction exceptions
 	 * later on.
 	 */
-	if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) {
+	switch (debug_arch) {
+	case ARM_DEBUG_ARCH_V6:
+	case ARM_DEBUG_ARCH_V6_1:
+		/* ARMv6 cores just need to reset the registers. */
+		goto reset_regs;
+	case ARM_DEBUG_ARCH_V7_ECP14:
 		/*
 		 * Ensure sticky power-down is clear (i.e. debug logic is
 		 * powered up).
 		 */
 		asm volatile("mrc p14, 0, %0, c1, c5, 4" : "=r" (dbg_power));
-		if ((dbg_power & 0x1) == 0) {
-			pr_warning("CPU %d debug is powered down!\n", cpu);
-			cpumask_or(cpumask, cpumask, cpumask_of(cpu));
-			return;
-		}
-
+		if ((dbg_power & 0x1) == 0)
+			err = -EPERM;
+		break;
+	case ARM_DEBUG_ARCH_V7_1:
 		/*
-		 * Unconditionally clear the lock by writing a value
-		 * other than 0xC5ACCE55 to the access register.
+		 * Ensure the OS double lock is clear.
 		 */
-		asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
-		isb();
+		asm volatile("mrc p14, 0, %0, c1, c3, 4" : "=r" (dbg_power));
+		if ((dbg_power & 0x1) == 1)
+			err = -EPERM;
+		break;
+	}
 
-		/*
-		 * Clear any configured vector-catch events before
-		 * enabling monitor mode.
-		 */
-		asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0));
-		isb();
+	if (err) {
+		pr_warning("CPU %d debug is powered down!\n", cpu);
+		cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu));
+		return;
 	}
 
+	/*
+	 * Unconditionally clear the lock by writing a value
+	 * other than 0xC5ACCE55 to the access register.
+	 */
+	asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
+	isb();
+
+	/*
+	 * Clear any configured vector-catch events before
+	 * enabling monitor mode.
+	 */
+	asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0));
+	isb();
+
+reset_regs:
 	if (enable_monitor_mode())
 		return;
 
 	/* We must also reset any reserved registers. */
-	for (i = 0; i < core_num_brps + core_num_reserved_brps; ++i) {
+	raw_num_brps = get_num_brp_resources();
+	for (i = 0; i < raw_num_brps; ++i) {
 		write_wb_reg(ARM_BASE_BCR + i, 0UL);
 		write_wb_reg(ARM_BASE_BVR + i, 0UL);
 	}
@@ -895,6 +957,7 @@ static int __cpuinit dbg_reset_notify(struct notifier_block *self,
 {
 	if (action == CPU_ONLINE)
 		smp_call_function_single((int)cpu, reset_ctrl_regs, NULL, 1);
+
 	return NOTIFY_OK;
 }
 
@@ -905,7 +968,6 @@ static struct notifier_block __cpuinitdata dbg_reset_nb = {
 static int __init arch_hw_breakpoint_init(void)
 {
 	u32 dscr;
-	cpumask_t cpumask = { CPU_BITS_NONE };
 
 	debug_arch = get_debug_arch();
 
@@ -916,28 +978,31 @@ static int __init arch_hw_breakpoint_init(void)
 
 	/* Determine how many BRPs/WRPs are available. */
 	core_num_brps = get_num_brps();
-	core_num_reserved_brps = get_num_reserved_brps();
 	core_num_wrps = get_num_wrps();
 
-	pr_info("found %d breakpoint and %d watchpoint registers.\n",
-		core_num_brps + core_num_reserved_brps, core_num_wrps);
-
-	if (core_num_reserved_brps)
-		pr_info("%d breakpoint(s) reserved for watchpoint "
-				"single-step.\n", core_num_reserved_brps);
+	/*
+	 * We need to tread carefully here because DBGSWENABLE may be
+	 * driven low on this core and there isn't an architected way to
+	 * determine that.
+	 */
+	register_undef_hook(&debug_reg_hook);
 
 	/*
 	 * Reset the breakpoint resources. We assume that a halting
 	 * debugger will leave the world in a nice state for us.
 	 */
-	on_each_cpu(reset_ctrl_regs, &cpumask, 1);
-	if (!cpumask_empty(&cpumask)) {
+	on_each_cpu(reset_ctrl_regs, NULL, 1);
+	unregister_undef_hook(&debug_reg_hook);
+	if (!cpumask_empty(&debug_err_mask)) {
 		core_num_brps = 0;
-		core_num_reserved_brps = 0;
 		core_num_wrps = 0;
 		return 0;
 	}
 
+	pr_info("found %d " "%s" "breakpoint and %d watchpoint registers.\n",
+		core_num_brps, core_has_mismatch_brps() ? "(+1 reserved) " :
+		"", core_num_wrps);
+
 	ARM_DBG_READ(c1, 0, dscr);
 	if (dscr & ARM_DSCR_HDBGEN) {
 		max_watchpoint_len = 4;

arch/arm/kernel/kprobes-arm.c

@@ -60,6 +60,7 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <linux/module.h>
 
 #include "kprobes.h"
 
@@ -971,6 +972,9 @@ const union decode_item kprobe_decode_arm_table[] = {
 
 	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)
 {

arch/arm/kernel/kprobes-test.h

+/*
+ * arch/arm/kernel/kprobes-test.h
+ *
+ * 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.
+ */
+
+#define VERBOSE 0 /* Set to '1' for more logging of test cases */
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define NORMAL_ISA "16"
+#else
+#define NORMAL_ISA "32"
+#endif
+
+
+/* Flags used in kprobe_test_flags */
+#define TEST_FLAG_NO_ITBLOCK	(1<<0)
+#define TEST_FLAG_FULL_ITBLOCK	(1<<1)
+#define TEST_FLAG_NARROW_INSTR	(1<<2)
+
+extern int kprobe_test_flags;
+extern int kprobe_test_cc_position;
+
+
+#define TEST_MEMORY_SIZE 256
+
+
+/*
+ * Test case structures.
+ *
+ * The arguments given to test cases can be one of three types.
+ *
+ *   ARG_TYPE_REG
+ *	Load a register with the given value.
+ *
+ *   ARG_TYPE_PTR
+ *	Load a register with a pointer into the stack buffer (SP + given value).
+ *
+ *   ARG_TYPE_MEM
+ *	Store the given value into the stack buffer at [SP+index].
+ *
+ */
+
+#define	ARG_TYPE_END	0
+#define	ARG_TYPE_REG	1
+#define	ARG_TYPE_PTR	2
+#define	ARG_TYPE_MEM	3
+
+#define ARG_FLAG_UNSUPPORTED	0x01
+#define ARG_FLAG_SUPPORTED	0x02
+#define ARG_FLAG_THUMB		0x10	/* Must be 16 so TEST_ISA can be used */
+#define ARG_FLAG_ARM		0x20	/* Must be 32 so TEST_ISA can be used */
+
+struct test_arg {
+	u8	type;		/* ARG_TYPE_x */
+	u8	_padding[7];
+};
+
+struct test_arg_regptr {
+	u8	type;		/* ARG_TYPE_REG or ARG_TYPE_PTR */
+	u8	reg;
+	u8	_padding[2];
+	u32	val;
+};
+
+struct test_arg_mem {
+	u8	type;		/* ARG_TYPE_MEM */
+	u8	index;
+	u8	_padding[2];
+	u32	val;
+};
+
+struct test_arg_end {
+	u8	type;		/* ARG_TYPE_END */
+	u8	flags;		/* ARG_FLAG_x */
+	u16	code_offset;
+	u16	branch_offset;
+	u16	end_offset;
+};
+
+
+/*
+ * Building blocks for test cases.
+ *
+ * Each test case is wrapped between TESTCASE_START and TESTCASE_END.
+ *
+ * To specify arguments for a test case the TEST_ARG_{REG,PTR,MEM} macros are
+ * used followed by a terminating TEST_ARG_END.
+ *
+ * After this, the instruction to be tested is defined with TEST_INSTRUCTION.
+ * Or for branches, TEST_BRANCH_B and TEST_BRANCH_F (branch forwards/backwards).
+ *
+ * Some specific test cases may make use of other custom constructs.
+ */
+
+#if VERBOSE
+#define verbose(fmt, ...) pr_info(fmt, ##__VA_ARGS__)
+#else
+#define verbose(fmt, ...)
+#endif
+
+#define TEST_GROUP(title)					\
+	verbose("\n");						\
+	verbose(title"\n");					\
+	verbose("---------------------------------------------------------\n");
+
+#define TESTCASE_START(title)					\
+	__asm__ __volatile__ (					\
+	"bl	__kprobes_test_case_start		\n\t"	\
+	/* don't use .asciz here as 'title' may be */		\
+	/* multiple strings to be concatenated.  */		\
+	".ascii "#title"				\n\t"	\
+	".byte	0					\n\t"	\
+	".align	2					\n\t"
+
+#define	TEST_ARG_REG(reg, val)					\
+	".byte	"__stringify(ARG_TYPE_REG)"		\n\t"	\
+	".byte	"#reg"					\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_PTR(reg, val)					\
+	".byte	"__stringify(ARG_TYPE_PTR)"		\n\t"	\
+	".byte	"#reg"					\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_MEM(index, val)				\
+	".byte	"__stringify(ARG_TYPE_MEM)"		\n\t"	\
+	".byte	"#index"				\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_END(flags)					\
+	".byte	"__stringify(ARG_TYPE_END)"		\n\t"	\
+	".byte	"TEST_ISA flags"			\n\t"	\
+	".short	50f-0f					\n\t"	\
+	".short	2f-0f					\n\t"	\
+	".short	99f-0f					\n\t"	\
+	".code "TEST_ISA"				\n\t"	\
+	"0:						\n\t"
+
+#define TEST_INSTRUCTION(instruction)				\
+	"50:	nop					\n\t"	\
+	"1:	"instruction"				\n\t"	\
+	"	nop					\n\t"
+
+#define TEST_BRANCH_F(instruction, xtra_dist)			\
+	TEST_INSTRUCTION(instruction)				\
+	".if "#xtra_dist"				\n\t"	\
+	"	b	99f				\n\t"	\
+	".space "#xtra_dist"				\n\t"	\
+	".endif						\n\t"	\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"
+
+#define TEST_BRANCH_B(instruction, xtra_dist)			\
+	"	b	50f				\n\t"	\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"	\
+	"	b	99f				\n\t"	\
+	".if "#xtra_dist"				\n\t"	\
+	".space "#xtra_dist"				\n\t"	\
+	".endif						\n\t"	\
+	TEST_INSTRUCTION(instruction)
+
+#define TESTCASE_END						\
+	"2:						\n\t"	\
+	"99:						\n\t"	\
+	"	bl __kprobes_test_case_end_"TEST_ISA"	\n\t"	\
+	".code "NORMAL_ISA"				\n\t"	\
+	: :							\
+	: "r0", "r1", "r2", "r3", "ip", "lr", "memory", "cc"	\
+	);
+
+
+/*
+ * Macros to define test cases.
+ *
+ * Those of the form TEST_{R,P,M}* can be used to define test cases
+ * which take combinations of the three basic types of arguments. E.g.
+ *
+ *   TEST_R	One register argument
+ *   TEST_RR	Two register arguments
+ *   TEST_RPR	A register, a pointer, then a register argument
+ *
+ * For testing instructions which may branch, there are macros TEST_BF_*
+ * and TEST_BB_* for branching forwards and backwards.
+ *
+ * TEST_SUPPORTED and TEST_UNSUPPORTED don't cause the code to be executed,
+ * the just verify that a kprobe is or is not allowed on the given instruction.
+ */
+
+#define TEST(code)				\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code)			\
+	TESTCASE_END
+
+#define TEST_UNSUPPORTED(code)					\
+	TESTCASE_START(code)					\
+	TEST_ARG_END("|"__stringify(ARG_FLAG_UNSUPPORTED))	\
+	TEST_INSTRUCTION(code)					\
+	TESTCASE_END
+
+#define TEST_SUPPORTED(code)					\
+	TESTCASE_START(code)					\
+	TEST_ARG_END("|"__stringify(ARG_FLAG_SUPPORTED))	\
+	TEST_INSTRUCTION(code)					\
+	TESTCASE_END
+
+#define TEST_R(code1, reg, val, code2)			\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_INSTRUCTION(code1 #reg code2)		\
+	TESTCASE_END
+
+#define TEST_RR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_RRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RRRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4, reg4, val4)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4 #reg4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_REG(reg4, val4)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4 #reg4)	\
+	TESTCASE_END
+
+#define TEST_P(code1, reg1, val1, code2)	\
+	TESTCASE_START(code1 #reg1 code2)	\
+	TEST_ARG_PTR(reg1, val1)		\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code1 #reg1 code2)	\
+	TESTCASE_END
+
+#define TEST_PR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_PTR(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_RP(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_PTR(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_PRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_PTR(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RPR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_PTR(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RRP(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_PTR(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_BF_P(code1, reg1, val1, code2)	\
+	TESTCASE_START(code1 #reg1 code2)	\
+	TEST_ARG_PTR(reg1, val1)		\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_F(code1 #reg1 code2, 0)	\
+	TESTCASE_END
+
+#define TEST_BF_X(code, xtra_dist)		\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_F(code, xtra_dist)		\
+	TESTCASE_END
+
+#define TEST_BB_X(code, xtra_dist)		\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_B(code, xtra_dist)		\
+	TESTCASE_END
+
+#define TEST_BF_RX(code1, reg, val, code2, xtra_dist)	\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_BRANCH_F(code1 #reg code2, xtra_dist)	\
+	TESTCASE_END
+
+#define TEST_BB_RX(code1, reg, val, code2, xtra_dist)	\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_BRANCH_B(code1 #reg code2, xtra_dist)	\
+	TESTCASE_END
+
+#define TEST_BF(code)	TEST_BF_X(code, 0)
+#define TEST_BB(code)	TEST_BB_X(code, 0)
+
+#define TEST_BF_R(code1, reg, val, code2) TEST_BF_RX(code1, reg, val, code2, 0)
+#define TEST_BB_R(code1, reg, val, code2) TEST_BB_RX(code1, reg, val, code2, 0)
+
+#define TEST_BF_RR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3, 0)		\
+	TESTCASE_END
+
+#define TEST_X(code, codex)			\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code)			\
+	"	b	99f		\n\t"	\
+	"	"codex"			\n\t"	\
+	TESTCASE_END
+
+#define TEST_RX(code1, reg, val, code2, codex)		\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_INSTRUCTION(code1 __stringify(reg) code2)	\
+	"	b	99f		\n\t"		\
+	"	"codex"			\n\t"		\
+	TESTCASE_END
+
+#define TEST_RRX(code1, reg1, val1, code2, reg2, val2, code3, codex)		\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)				\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 __stringify(reg1) code2 __stringify(reg2) code3)	\
+	"	b	99f		\n\t"					\
+	"	"codex"			\n\t"					\
+	TESTCASE_END
+
+
+/* Various values used in test cases... */
+#define N(val)	(val ^ 0xffffffff)
+#define VAL1	0x12345678
+#define VAL2	N(VAL1)
+#define VAL3	0xa5f801
+#define VAL4	N(VAL3)
+#define VALM	0x456789ab
+#define VALR	0xdeaddead
+#define HH1	0x0123fecb
+#define HH2	0xa9874567
+
+
+#ifdef CONFIG_THUMB2_KERNEL
+void kprobe_thumb16_test_cases(void);
+void kprobe_thumb32_test_cases(void);
+#else
+void kprobe_arm_test_cases(void);
+#endif

arch/arm/kernel/kprobes-thumb.c

@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <linux/module.h>
 
 #include "kprobes.h"
 
@@ -943,6 +944,9 @@ const union decode_item kprobe_decode_thumb32_table[] = {
 	 */
 	DECODE_END
 };
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(kprobe_decode_thumb32_table);
+#endif
 
 static void __kprobes
 t16_simulate_bxblx(struct kprobe *p, struct pt_regs *regs)
@@ -1423,6 +1427,9 @@ const union decode_item kprobe_decode_thumb16_table[] = {
 
 	DECODE_END
 };
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(kprobe_decode_thumb16_table);
+#endif
 
 static unsigned long __kprobes thumb_check_cc(unsigned long cpsr)
 {

arch/arm/kernel/kprobes.h

@@ -413,6 +413,14 @@ struct decode_reject {
 	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);
 

arch/arm/kernel/perf_event_v6.c

@@ -54,7 +54,7 @@ enum armv6_perf_types {
 };
 
 enum armv6_counters {
-	ARMV6_CYCLE_COUNTER = 1,
+	ARMV6_CYCLE_COUNTER = 0,
 	ARMV6_COUNTER0,
 	ARMV6_COUNTER1,
 };
@@ -433,6 +433,7 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
 		      int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= 0;
@@ -454,12 +455,29 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
 	 * Mask out the current event and set the counter to count the event
 	 * that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static int counter_is_active(unsigned long pmcr, int idx)
+{
+	unsigned long mask = 0;
+	if (idx == ARMV6_CYCLE_COUNTER)
+		mask = ARMV6_PMCR_CCOUNT_IEN;
+	else if (idx == ARMV6_COUNTER0)
+		mask = ARMV6_PMCR_COUNT0_IEN;
+	else if (idx == ARMV6_COUNTER1)
+		mask = ARMV6_PMCR_COUNT1_IEN;
+
+	if (mask)
+		return pmcr & mask;
+
+	WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+	return 0;
 }
 
 static irqreturn_t
@@ -468,7 +486,7 @@ armv6pmu_handle_irq(int irq_num,
 {
 	unsigned long pmcr = armv6_pmcr_read();
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -487,11 +505,11 @@ armv6pmu_handle_irq(int irq_num,
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!counter_is_active(pmcr, idx))
 			continue;
 
 		/*
@@ -508,7 +526,7 @@ armv6pmu_handle_irq(int irq_num,
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	/*
@@ -527,28 +545,30 @@ static void
 armv6pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val |= ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 armv6pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
+armv6pmu_get_event_idx(struct pmu_hw_events *cpuc,
 		       struct hw_perf_event *event)
 {
 	/* Always place a cycle counter into the cycle counter. */
@@ -578,6 +598,7 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
 		       int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= ARMV6_PMCR_CCOUNT_IEN;
@@ -598,12 +619,12 @@ armv6pmu_disable_event(struct hw_perf_event *hwc,
 	 * of ETM bus signal assertion cycles. The external reporting should
 	 * be disabled and so this should never increment.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
@@ -611,6 +632,7 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
 			      int idx)
 {
 	unsigned long val, mask, flags, evt = 0;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
 		mask	= ARMV6_PMCR_CCOUNT_IEN;
@@ -627,15 +649,21 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
 	 * Unlike UP ARMv6, we don't have a way of stopping the counters. We
 	 * simply disable the interrupt reporting.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static int armv6_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv6_perf_map,
+				&armv6_perf_cache_map, 0xFF);
 }
 
-static const struct arm_pmu armv6pmu = {
+static struct arm_pmu armv6pmu = {
 	.id			= ARM_PERF_PMU_ID_V6,
 	.name			= "v6",
 	.handle_irq		= armv6pmu_handle_irq,
@@ -646,14 +674,12 @@ static const struct arm_pmu armv6pmu = {
 	.get_event_idx		= armv6pmu_get_event_idx,
 	.start			= armv6pmu_start,
 	.stop			= armv6pmu_stop,
-	.cache_map		= &armv6_perf_cache_map,
-	.event_map		= &armv6_perf_map,
-	.raw_event_mask		= 0xFF,
+	.map_event		= armv6_map_event,
 	.num_events		= 3,
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init armv6pmu_init(void)
+static struct arm_pmu *__init armv6pmu_init(void)
 {
 	return &armv6pmu;
 }
@@ -665,7 +691,14 @@ static const struct arm_pmu *__init armv6pmu_init(void)
  * disable the interrupt reporting and update the event. When unthrottling we
  * reset the period and enable the interrupt reporting.
  */
-static const struct arm_pmu armv6mpcore_pmu = {
+
+static int armv6mpcore_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv6mpcore_perf_map,
+				&armv6mpcore_perf_cache_map, 0xFF);
+}
+
+static struct arm_pmu armv6mpcore_pmu = {
 	.id			= ARM_PERF_PMU_ID_V6MP,
 	.name			= "v6mpcore",
 	.handle_irq		= armv6pmu_handle_irq,
@@ -676,24 +709,22 @@ static const struct arm_pmu armv6mpcore_pmu = {
 	.get_event_idx		= armv6pmu_get_event_idx,
 	.start			= armv6pmu_start,
 	.stop			= armv6pmu_stop,
-	.cache_map		= &armv6mpcore_perf_cache_map,
-	.event_map		= &armv6mpcore_perf_map,
-	.raw_event_mask		= 0xFF,
+	.map_event		= armv6mpcore_map_event,
 	.num_events		= 3,
 	.max_period		= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
 	return &armv6mpcore_pmu;
 }
 #else
-static const struct arm_pmu *__init armv6pmu_init(void)
+static struct arm_pmu *__init armv6pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
+static struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
 	return NULL;
 }

arch/arm/kernel/perf_event_xscale.c

@@ -40,7 +40,7 @@ enum xscale_perf_types {
 };
 
 enum xscale_counters {
-	XSCALE_CYCLE_COUNTER	= 1,
+	XSCALE_CYCLE_COUNTER	= 0,
 	XSCALE_COUNTER0,
 	XSCALE_COUNTER1,
 	XSCALE_COUNTER2,
@@ -222,7 +222,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 {
 	unsigned long pmnc;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -249,13 +249,10 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
 		if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
 			continue;
 
@@ -266,7 +263,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	irq_work_run();
@@ -284,6 +281,7 @@ static void
 xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	switch (idx) {
 	case XSCALE_CYCLE_COUNTER:
@@ -305,18 +303,19 @@ xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long val, mask, evt, flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	switch (idx) {
 	case XSCALE_CYCLE_COUNTER:
@@ -336,16 +335,16 @@ xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
+xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc,
 			struct hw_perf_event *event)
 {
 	if (XSCALE_PERFCTR_CCNT == event->config_base) {
@@ -368,24 +367,26 @@ static void
 xscale1pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val |= XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale1pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u32
@@ -424,7 +425,13 @@ xscale1pmu_write_counter(int counter, u32 val)
 	}
 }
 
-static const struct arm_pmu xscale1pmu = {
+static int xscale_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &xscale_perf_map,
+				&xscale_perf_cache_map, 0xFF);
+}
+
+static struct arm_pmu xscale1pmu = {
 	.id		= ARM_PERF_PMU_ID_XSCALE1,
 	.name		= "xscale1",
 	.handle_irq	= xscale1pmu_handle_irq,
@@ -435,14 +442,12 @@ static const struct arm_pmu xscale1pmu = {
 	.get_event_idx	= xscale1pmu_get_event_idx,
 	.start		= xscale1pmu_start,
 	.stop		= xscale1pmu_stop,
-	.cache_map	= &xscale_perf_cache_map,
-	.event_map	= &xscale_perf_map,
-	.raw_event_mask	= 0xFF,
+	.map_event	= xscale_map_event,
 	.num_events	= 3,
 	.max_period	= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init xscale1pmu_init(void)
+static struct arm_pmu *__init xscale1pmu_init(void)
 {
 	return &xscale1pmu;
 }
@@ -560,7 +565,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 {
 	unsigned long pmnc, of_flags;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -581,13 +586,10 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
 		if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
 			continue;
 
@@ -598,7 +600,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	irq_work_run();
@@ -616,6 +618,7 @@ static void
 xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags, ien, evtsel;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	ien = xscale2pmu_read_int_enable();
 	evtsel = xscale2pmu_read_event_select();
@@ -649,16 +652,17 @@ xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags, ien, evtsel;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	ien = xscale2pmu_read_int_enable();
 	evtsel = xscale2pmu_read_event_select();
@@ -692,14 +696,14 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
-xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
+xscale2pmu_get_event_idx(struct pmu_hw_events *cpuc,
 			struct hw_perf_event *event)
 {
 	int idx = xscale1pmu_get_event_idx(cpuc, event);
@@ -718,24 +722,26 @@ static void
 xscale2pmu_start(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
 	val |= XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void
 xscale2pmu_stop(void)
 {
 	unsigned long flags, val;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u32
@@ -786,7 +792,7 @@ xscale2pmu_write_counter(int counter, u32 val)
 	}
 }
 
-static const struct arm_pmu xscale2pmu = {
+static struct arm_pmu xscale2pmu = {
 	.id		= ARM_PERF_PMU_ID_XSCALE2,
 	.name		= "xscale2",
 	.handle_irq	= xscale2pmu_handle_irq,
@@ -797,24 +803,22 @@ static const struct arm_pmu xscale2pmu = {
 	.get_event_idx	= xscale2pmu_get_event_idx,
 	.start		= xscale2pmu_start,
 	.stop		= xscale2pmu_stop,
-	.cache_map	= &xscale_perf_cache_map,
-	.event_map	= &xscale_perf_map,
-	.raw_event_mask	= 0xFF,
+	.map_event	= xscale_map_event,
 	.num_events	= 5,
 	.max_period	= (1LLU << 32) - 1,
 };
 
-static const struct arm_pmu *__init xscale2pmu_init(void)
+static struct arm_pmu *__init xscale2pmu_init(void)
 {
 	return &xscale2pmu;
 }
 #else
-static const struct arm_pmu *__init xscale1pmu_init(void)
+static struct arm_pmu *__init xscale1pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init xscale2pmu_init(void)
+static struct arm_pmu *__init xscale2pmu_init(void)
 {
 	return NULL;
 }