Merge branch 'for-linus' of master.kernel.org:/home/rmk/linux-2.6-arm

* 'for-linus' of master.kernel.org:/home/rmk/linux-2.6-arm: (237 commits)
  ARM: 7004/1: fix traps.h compile warnings
  ARM: 6998/2: kernel: use proper memory barriers for bitops
  ARM: 6997/1: ep93xx: increase NR_BANKS to 16 for support of 128MB RAM
  ARM: Fix build errors caused by adding generic macros
  ARM: CPU hotplug: ensure we migrate all IRQs off a downed CPU
  ARM: CPU hotplug: pass in proper affinity mask on IRQ migration
  ARM: GIC: avoid routing interrupts to offline CPUs
  ARM: CPU hotplug: fix abuse of irqdesc->node
  ARM: 6981/2: mmci: adjust calculation of f_min
  ARM: 7000/1: LPAE: Use long long printk format for displaying the pud
  ARM: 6999/1: head, zImage: Always Enter the kernel in ARM state
  ARM: btc: avoid invalidating the branch target cache on kernel TLB maintanence
  ARM: ARM_DMA_ZONE_SIZE is no more
  ARM: mach-shark: move ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size
  ARM: mach-sa1100: move ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size
  ARM: mach-realview: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size
  ARM: mach-pxa: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size
  ARM: mach-ixp4xx: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size
  ARM: mach-h720x: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size
  ARM: mach-davinci: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size
  ...

Documentation/arm/Booting

@@ -164,3 +164,8 @@ In either case, the following conditions must be met:
 - The boot loader is expected to call the kernel image by jumping
   directly to the first instruction of the kernel image.
 
+  On CPUs supporting the ARM instruction set, the entry must be
+  made in ARM state, even for a Thumb-2 kernel.
+
+  On CPUs supporting only the Thumb instruction set such as
+  Cortex-M class CPUs, the entry must be made in Thumb state.

Documentation/arm/SH-Mobile/zboot-rom-sdhi.txt

+ROM-able zImage boot from eSD
+-----------------------------
+
+An ROM-able zImage compiled with ZBOOT_ROM_SDHI may be written to eSD and
+SuperH Mobile ARM will to boot directly from the SDHI hardware block.
+
+This is achieved by the mask ROM loading the first portion of the image into
+MERAM and then jumping to it. This portion contains loader code which
+copies the entire image to SDRAM and jumps to it. From there the zImage
+boot code proceeds as normal, uncompressing the image into its final
+location and then jumping to it.
+
+This code has been tested on an mackerel board using the developer 1A eSD
+boot mode which is configured using the following jumper settings.
+
+   8 7 6 5 4 3 2 1
+   x|x|x|x| |x|x|
+S4 -+-+-+-+-+-+-+-
+    | | | |x| | |x on
+
+The eSD card needs to be present in SDHI slot 1 (CN7).
+As such S1 and S33 also need to be configured as per
+the notes in arch/arm/mach-shmobile/board-mackerel.c.
+
+A partial zImage must be written to physical partition #1 (boot)
+of the eSD at sector 0 in vrl4 format. A utility vrl4 is supplied to
+accomplish this.
+
+e.g.
+	vrl4 < zImage | dd of=/dev/sdX bs=512 count=17
+
+A full copy of _the same_ zImage should be written to physical partition #1
+(boot) of the eSD at sector 0. This should _not_ be in vrl4 format.
+
+	vrl4 < zImage | dd of=/dev/sdX bs=512
+
+Note: The commands above assume that the physical partition has been
+switched. No such facility currently exists in the Linux Kernel.
+
+Physical partitions are described in the eSD specification.  At the time of
+writing they are not the same as partitions that are typically configured
+using fdisk and visible through /proc/partitions

Documentation/arm/kernel_user_helpers.txt

+Kernel-provided User Helpers
+============================
+
+These are segment of kernel provided user code reachable from user space
+at a fixed address in kernel memory.  This is used to provide user space
+with some operations which require kernel help because of unimplemented
+native feature and/or instructions in many ARM CPUs. The idea is for this
+code to be executed directly in user mode for best efficiency but which is
+too intimate with the kernel counter part to be left to user libraries.
+In fact this code might even differ from one CPU to another depending on
+the available instruction set, or whether it is a SMP systems. In other
+words, the kernel reserves the right to change this code as needed without
+warning. Only the entry points and their results as documented here are
+guaranteed to be stable.
+
+This is different from (but doesn't preclude) a full blown VDSO
+implementation, however a VDSO would prevent some assembly tricks with
+constants that allows for efficient branching to those code segments. And
+since those code segments only use a few cycles before returning to user
+code, the overhead of a VDSO indirect far call would add a measurable
+overhead to such minimalistic operations.
+
+User space is expected to bypass those helpers and implement those things
+inline (either in the code emitted directly by the compiler, or part of
+the implementation of a library call) when optimizing for a recent enough
+processor that has the necessary native support, but only if resulting
+binaries are already to be incompatible with earlier ARM processors due to
+useage of similar native instructions for other things.  In other words
+don't make binaries unable to run on earlier processors just for the sake
+of not using these kernel helpers if your compiled code is not going to
+use new instructions for other purpose.
+
+New helpers may be added over time, so an older kernel may be missing some
+helpers present in a newer kernel.  For this reason, programs must check
+the value of __kuser_helper_version (see below) before assuming that it is
+safe to call any particular helper.  This check should ideally be
+performed only once at process startup time, and execution aborted early
+if the required helpers are not provided by the kernel version that
+process is running on.
+
+kuser_helper_version
+--------------------
+
+Location:	0xffff0ffc
+
+Reference declaration:
+
+  extern int32_t __kuser_helper_version;
+
+Definition:
+
+  This field contains the number of helpers being implemented by the
+  running kernel.  User space may read this to determine the availability
+  of a particular helper.
+
+Usage example:
+
+#define __kuser_helper_version (*(int32_t *)0xffff0ffc)
+
+void check_kuser_version(void)
+{
+	if (__kuser_helper_version < 2) {
+		fprintf(stderr, "can't do atomic operations, kernel too old\n");
+		abort();
+	}
+}
+
+Notes:
+
+  User space may assume that the value of this field never changes
+  during the lifetime of any single process.  This means that this
+  field can be read once during the initialisation of a library or
+  startup phase of a program.
+
+kuser_get_tls
+-------------
+
+Location:	0xffff0fe0
+
+Reference prototype:
+
+  void * __kuser_get_tls(void);
+
+Input:
+
+  lr = return address
+
+Output:
+
+  r0 = TLS value
+
+Clobbered registers:
+
+  none
+
+Definition:
+
+  Get the TLS value as previously set via the __ARM_NR_set_tls syscall.
+
+Usage example:
+
+typedef void * (__kuser_get_tls_t)(void);
+#define __kuser_get_tls (*(__kuser_get_tls_t *)0xffff0fe0)
+
+void foo()
+{
+	void *tls = __kuser_get_tls();
+	printf("TLS = %p\n", tls);
+}
+
+Notes:
+
+  - Valid only if __kuser_helper_version >= 1 (from kernel version 2.6.12).
+
+kuser_cmpxchg
+-------------
+
+Location:	0xffff0fc0
+
+Reference prototype:
+
+  int __kuser_cmpxchg(int32_t oldval, int32_t newval, volatile int32_t *ptr);
+
+Input:
+
+  r0 = oldval
+  r1 = newval
+  r2 = ptr
+  lr = return address
+
+Output:
+
+  r0 = success code (zero or non-zero)
+  C flag = set if r0 == 0, clear if r0 != 0
+
+Clobbered registers:
+
+  r3, ip, flags
+
+Definition:
+
+  Atomically store newval in *ptr only if *ptr is equal to oldval.
+  Return zero if *ptr was changed or non-zero if no exchange happened.
+  The C flag is also set if *ptr was changed to allow for assembly
+  optimization in the calling code.
+
+Usage example:
+
+typedef int (__kuser_cmpxchg_t)(int oldval, int newval, volatile int *ptr);
+#define __kuser_cmpxchg (*(__kuser_cmpxchg_t *)0xffff0fc0)
+
+int atomic_add(volatile int *ptr, int val)
+{
+	int old, new;
+
+	do {
+		old = *ptr;
+		new = old + val;
+	} while(__kuser_cmpxchg(old, new, ptr));
+
+	return new;
+}
+
+Notes:
+
+  - This routine already includes memory barriers as needed.
+
+  - Valid only if __kuser_helper_version >= 2 (from kernel version 2.6.12).
+
+kuser_memory_barrier
+--------------------
+
+Location:	0xffff0fa0
+
+Reference prototype:
+
+  void __kuser_memory_barrier(void);
+
+Input:
+
+  lr = return address
+
+Output:
+
+  none
+
+Clobbered registers:
+
+  none
+
+Definition:
+
+  Apply any needed memory barrier to preserve consistency with data modified
+  manually and __kuser_cmpxchg usage.
+
+Usage example:
+
+typedef void (__kuser_dmb_t)(void);
+#define __kuser_dmb (*(__kuser_dmb_t *)0xffff0fa0)
+
+Notes:
+
+  - Valid only if __kuser_helper_version >= 3 (from kernel version 2.6.15).
+
+kuser_cmpxchg64
+---------------
+
+Location:	0xffff0f60
+
+Reference prototype:
+
+  int __kuser_cmpxchg64(const int64_t *oldval,
+                        const int64_t *newval,
+                        volatile int64_t *ptr);
+
+Input:
+
+  r0 = pointer to oldval
+  r1 = pointer to newval
+  r2 = pointer to target value
+  lr = return address
+
+Output:
+
+  r0 = success code (zero or non-zero)
+  C flag = set if r0 == 0, clear if r0 != 0
+
+Clobbered registers:
+
+  r3, lr, flags
+
+Definition:
+
+  Atomically store the 64-bit value pointed by *newval in *ptr only if *ptr
+  is equal to the 64-bit value pointed by *oldval.  Return zero if *ptr was
+  changed or non-zero if no exchange happened.
+
+  The C flag is also set if *ptr was changed to allow for assembly
+  optimization in the calling code.
+
+Usage example:
+
+typedef int (__kuser_cmpxchg64_t)(const int64_t *oldval,
+                                  const int64_t *newval,
+                                  volatile int64_t *ptr);
+#define __kuser_cmpxchg64 (*(__kuser_cmpxchg64_t *)0xffff0f60)
+
+int64_t atomic_add64(volatile int64_t *ptr, int64_t val)
+{
+	int64_t old, new;
+
+	do {
+		old = *ptr;
+		new = old + val;
+	} while(__kuser_cmpxchg64(&old, &new, ptr));
+
+	return new;
+}
+
+Notes:
+
+  - This routine already includes memory barriers as needed.
+
+  - Due to the length of this sequence, this spans 2 conventional kuser
+    "slots", therefore 0xffff0f80 is not used as a valid entry point.
+
+  - Valid only if __kuser_helper_version >= 5 (from kernel version 3.1).

Documentation/devicetree/bindings/arm/pmu.txt

+* ARM Performance Monitor Units
+
+ARM cores often have a PMU for counting cpu and cache events like cache misses
+and hits. The interface to the PMU is part of the ARM ARM. The ARM PMU
+representation in the device tree should be done as under:-
+
+Required properties:
+
+- compatible : should be one of
+	"arm,cortex-a9-pmu"
+	"arm,cortex-a8-pmu"
+	"arm,arm1176-pmu"
+	"arm,arm1136-pmu"
+- interrupts : 1 combined interrupt or 1 per core.
+
+Example:
+
+pmu {
+        compatible = "arm,cortex-a9-pmu";
+        interrupts = <100 101>;
+};

arch/arm/Kconfig

@@ -10,7 +10,7 @@ config ARM
 	select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI)
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_ARCH_KGDB
-	select HAVE_KPROBES if (!XIP_KERNEL && !THUMB2_KERNEL)
+	select HAVE_KPROBES if !XIP_KERNEL
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
 	select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
 	select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
@@ -37,6 +37,9 @@ config ARM
 	  Europe.  There is an ARM Linux project with a web page at
 	  <http://www.arm.linux.org.uk/>.
 
+config ARM_HAS_SG_CHAIN
+	bool
+
 config HAVE_PWM
 	bool
 
@@ -1347,7 +1350,6 @@ config SMP_ON_UP
 
 config HAVE_ARM_SCU
 	bool
-	depends on SMP
 	help
 	  This option enables support for the ARM system coherency unit
 
@@ -1716,17 +1718,34 @@ config ZBOOT_ROM
 	  Say Y here if you intend to execute your compressed kernel image
 	  (zImage) directly from ROM or flash.  If unsure, say N.
 
+choice
+	prompt "Include SD/MMC loader in zImage (EXPERIMENTAL)"
+	depends on ZBOOT_ROM && ARCH_SH7372 && EXPERIMENTAL
+	default ZBOOT_ROM_NONE
+	help
+	  Include experimental SD/MMC loading code in the ROM-able zImage.
+	  With this enabled it is possible to write the the ROM-able zImage
+	  kernel image to an MMC or SD card and boot the kernel straight
+	  from the reset vector. At reset the processor Mask ROM will load
+	  the first part of the the ROM-able zImage which in turn loads the
+	  rest the kernel image to RAM.
+
+config ZBOOT_ROM_NONE
+	bool "No SD/MMC loader in zImage (EXPERIMENTAL)"
+	help
+	  Do not load image from SD or MMC
+
 config ZBOOT_ROM_MMCIF
 	bool "Include MMCIF loader in zImage (EXPERIMENTAL)"
-	depends on ZBOOT_ROM && ARCH_SH7372 && EXPERIMENTAL
 	help
-	  Say Y here to include experimental MMCIF loading code in the
-	  ROM-able zImage. With this enabled it is possible to write the
-	  the ROM-able zImage kernel image to an MMC card and boot the
-	  kernel straight from the reset vector. At reset the processor
-	  Mask ROM will load the first part of the the ROM-able zImage
-	  which in turn loads the rest the kernel image to RAM using the
-	  MMCIF hardware block.
+	  Load image from MMCIF hardware block.
+
+config ZBOOT_ROM_SH_MOBILE_SDHI
+	bool "Include SuperH Mobile SDHI loader in zImage (EXPERIMENTAL)"
+	help
+	  Load image from SDHI hardware block
+
+endchoice
 
 config CMDLINE
 	string "Default kernel command string"

arch/arm/boot/compressed/Makefile

@@ -6,13 +6,19 @@
 
 OBJS		=
 
-# Ensure that mmcif loader code appears early in the image
+# Ensure that MMCIF loader code appears early in the image
 # to minimise that number of bocks that have to be read in
 # order to load it.
 ifeq ($(CONFIG_ZBOOT_ROM_MMCIF),y)
-ifeq ($(CONFIG_ARCH_SH7372),y)
 OBJS		+= mmcif-sh7372.o
 endif
+
+# Ensure that SDHI loader code appears early in the image
+# to minimise that number of bocks that have to be read in
+# order to load it.
+ifeq ($(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI),y)
+OBJS		+= sdhi-shmobile.o
+OBJS		+= sdhi-sh7372.o
 endif
 
 AFLAGS_head.o += -DTEXT_OFFSET=$(TEXT_OFFSET)

arch/arm/boot/compressed/head-shmobile.S

@@ -25,14 +25,14 @@
 	/* load board-specific initialization code */
 #include <mach/zboot.h>
 
-#ifdef CONFIG_ZBOOT_ROM_MMCIF
-	/* Load image from MMC */
-	adr	sp, __tmp_stack + 128
+#if defined(CONFIG_ZBOOT_ROM_MMCIF) || defined(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI)
+	/* Load image from MMC/SD */
+	adr	sp, __tmp_stack + 256
 	ldr	r0, __image_start
 	ldr	r1, __image_end
 	subs	r1, r1, r0
 	ldr	r0, __load_base
-	bl	mmcif_loader
+	bl	mmc_loader
 
 	/* Jump to loaded code */
 	ldr	r0, __loaded
@@ -51,9 +51,9 @@ __loaded:
 	.long	__continue
 	.align
 __tmp_stack:
-	.space	128
+	.space	256
 __continue:
-#endif /* CONFIG_ZBOOT_ROM_MMCIF */
+#endif /* CONFIG_ZBOOT_ROM_MMC || CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI */
 
 	b	1f
 __atags:@ tag #1

arch/arm/boot/compressed/head.S

@@ -353,7 +353,8 @@ not_relocated:	mov	r0, #0
 		mov	r0, #0			@ must be zero
 		mov	r1, r7			@ restore architecture number
 		mov	r2, r8			@ restore atags pointer
-		mov	pc, r4			@ call kernel
+ ARM(		mov	pc, r4	)		@ call kernel
+ THUMB(		bx	r4	)		@ entry point is always ARM
 
 		.align	2
 		.type	LC0, #object

arch/arm/boot/compressed/mmcif-sh7372.c

@@ -40,7 +40,7 @@
  * to an MMC card
  * # dd if=vrl4.out of=/dev/sdx bs=512 seek=1
  */
-asmlinkage void mmcif_loader(unsigned char *buf, unsigned long len)
+asmlinkage void mmc_loader(unsigned char *buf, unsigned long len)
 {
 	mmc_init_progress();
 	mmc_update_progress(MMC_PROGRESS_ENTER);

arch/arm/boot/compressed/sdhi-sh7372.c

+/*
+ * SuperH Mobile SDHI
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Kuninori Morimoto
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Parts inspired by u-boot
+ */
+
+#include <linux/io.h>
+#include <mach/mmc.h>
+#include <linux/mmc/boot.h>
+#include <linux/mmc/tmio.h>
+
+#include "sdhi-shmobile.h"
+
+#define PORT179CR       0xe60520b3
+#define PORT180CR       0xe60520b4
+#define PORT181CR       0xe60520b5
+#define PORT182CR       0xe60520b6
+#define PORT183CR       0xe60520b7
+#define PORT184CR       0xe60520b8
+
+#define SMSTPCR3        0xe615013c
+
+#define CR_INPUT_ENABLE 0x10
+#define CR_FUNCTION1    0x01
+
+#define SDHI1_BASE	(void __iomem *)0xe6860000
+#define SDHI_BASE	SDHI1_BASE
+
+/*  SuperH Mobile SDHI loader
+ *
+ * loads the zImage from an SD card starting from block 0
+ * on physical partition 1
+ *
+ * The image must be start with a vrl4 header and
+ * the zImage must start at offset 512 of the image. That is,
+ * at block 1 (=byte 512) of physical partition 1
+ *
+ * Use the following line to write the vrl4 formated zImage
+ * to an SD card
+ * # dd if=vrl4.out of=/dev/sdx bs=512
+ */
+asmlinkage void mmc_loader(unsigned short *buf, unsigned long len)
+{
+	int high_capacity;
+
+	mmc_init_progress();
+
+	mmc_update_progress(MMC_PROGRESS_ENTER);
+        /* Initialise SDHI1 */
+        /* PORT184CR: GPIO_FN_SDHICMD1 Control */
+        __raw_writeb(CR_FUNCTION1, PORT184CR);
+        /* PORT179CR: GPIO_FN_SDHICLK1 Control */
+        __raw_writeb(CR_INPUT_ENABLE|CR_FUNCTION1, PORT179CR);
+        /* PORT181CR: GPIO_FN_SDHID1_3 Control */
+        __raw_writeb(CR_FUNCTION1, PORT183CR);
+        /* PORT182CR: GPIO_FN_SDHID1_2 Control */
+        __raw_writeb(CR_FUNCTION1, PORT182CR);
+        /* PORT183CR: GPIO_FN_SDHID1_1 Control */
+        __raw_writeb(CR_FUNCTION1, PORT181CR);
+        /* PORT180CR: GPIO_FN_SDHID1_0 Control */
+        __raw_writeb(CR_FUNCTION1, PORT180CR);
+
+        /* Enable clock to SDHI1 hardware block */
+        __raw_writel(__raw_readl(SMSTPCR3) & ~(1 << 13), SMSTPCR3);
+
+	/* setup SDHI hardware */
+	mmc_update_progress(MMC_PROGRESS_INIT);
+	high_capacity = sdhi_boot_init(SDHI_BASE);
+	if (high_capacity < 0)
+		goto err;
+
+	mmc_update_progress(MMC_PROGRESS_LOAD);
+	/* load kernel */
+	if (sdhi_boot_do_read(SDHI_BASE, high_capacity,
+			      0, /* Kernel is at block 1 */
+			      (len + TMIO_BBS - 1) / TMIO_BBS, buf))
+		goto err;
+
+        /* Disable clock to SDHI1 hardware block */
+        __raw_writel(__raw_readl(SMSTPCR3) & (1 << 13), SMSTPCR3);
+
+	mmc_update_progress(MMC_PROGRESS_DONE);
+
+	return;
+err:
+	for(;;);
+}

arch/arm/boot/compressed/sdhi-shmobile.c

+/*
+ * SuperH Mobile SDHI
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Kuninori Morimoto
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Parts inspired by u-boot
+ */
+
+#include <linux/io.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/core.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
+#include <linux/mmc/tmio.h>
+#include <mach/sdhi.h>
+
+#define OCR_FASTBOOT		(1<<29)
+#define OCR_HCS			(1<<30)
+#define OCR_BUSY		(1<<31)
+
+#define RESP_CMD12		0x00000030
+
+static inline u16 sd_ctrl_read16(void __iomem *base, int addr)
+{
+        return __raw_readw(base + addr);
+}
+
+static inline u32 sd_ctrl_read32(void __iomem *base, int addr)
+{
+	return __raw_readw(base + addr) |
+	       __raw_readw(base + addr + 2) << 16;
+}
+
+static inline void sd_ctrl_write16(void __iomem *base, int addr, u16 val)
+{
+	__raw_writew(val, base + addr);
+}
+
+static inline void sd_ctrl_write32(void __iomem *base, int addr, u32 val)
+{
+	__raw_writew(val, base + addr);
+	__raw_writew(val >> 16, base + addr + 2);
+}
+
+#define ALL_ERROR (TMIO_STAT_CMD_IDX_ERR | TMIO_STAT_CRCFAIL |		\
+		   TMIO_STAT_STOPBIT_ERR | TMIO_STAT_DATATIMEOUT |	\
+		   TMIO_STAT_RXOVERFLOW | TMIO_STAT_TXUNDERRUN |	\
+		   TMIO_STAT_CMDTIMEOUT | TMIO_STAT_ILL_ACCESS |	\
+		   TMIO_STAT_ILL_FUNC)
+
+static int sdhi_intr(void __iomem *base)
+{
+	unsigned long state = sd_ctrl_read32(base, CTL_STATUS);
+
+	if (state & ALL_ERROR) {
+		sd_ctrl_write32(base, CTL_STATUS, ~ALL_ERROR);
+		sd_ctrl_write32(base, CTL_IRQ_MASK,
+				ALL_ERROR |
+				sd_ctrl_read32(base, CTL_IRQ_MASK));
+		return -EINVAL;
+	}
+	if (state & TMIO_STAT_CMDRESPEND) {
+		sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND);
+		sd_ctrl_write32(base, CTL_IRQ_MASK,
+				TMIO_STAT_CMDRESPEND |
+				sd_ctrl_read32(base, CTL_IRQ_MASK));
+		return 0;
+	}
+	if (state & TMIO_STAT_RXRDY) {
+		sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_RXRDY);
+		sd_ctrl_write32(base, CTL_IRQ_MASK,
+				TMIO_STAT_RXRDY | TMIO_STAT_TXUNDERRUN |
+				sd_ctrl_read32(base, CTL_IRQ_MASK));
+		return 0;
+	}
+	if (state & TMIO_STAT_DATAEND) {
+		sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_DATAEND);
+		sd_ctrl_write32(base, CTL_IRQ_MASK,
+				TMIO_STAT_DATAEND |
+				sd_ctrl_read32(base, CTL_IRQ_MASK));
+		return 0;
+	}
+
+	return -EAGAIN;
+}
+
+static int sdhi_boot_wait_resp_end(void __iomem *base)
+{
+	int err = -EAGAIN, timeout = 10000000;
+
+	while (timeout--) {
+		err = sdhi_intr(base);
+		if (err != -EAGAIN)
+			break;
+		udelay(1);
+	}
+
+	return err;
+}
+
+/* SDHI_CLK_CTRL */
+#define CLK_MMC_ENABLE                 (1 << 8)
+#define CLK_MMC_INIT                   (1 << 6)        /* clk / 256 */
+
+static void sdhi_boot_mmc_clk_stop(void __iomem *base)
+{
+	sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, 0x0000);
+	msleep(10);
+	sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, ~CLK_MMC_ENABLE &
+		sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL));
+	msleep(10);
+}
+
+static void sdhi_boot_mmc_clk_start(void __iomem *base)
+{
+	sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, CLK_MMC_ENABLE |
+		sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL));
+	msleep(10);
+	sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, CLK_MMC_ENABLE);
+	msleep(10);
+}
+
+static void sdhi_boot_reset(void __iomem *base)
+{
+	sd_ctrl_write16(base, CTL_RESET_SD, 0x0000);
+	msleep(10);
+	sd_ctrl_write16(base, CTL_RESET_SD, 0x0001);
+	msleep(10);
+}
+
+/* Set MMC clock / power.
+ * Note: This controller uses a simple divider scheme therefore it cannot
+ * run a MMC card at full speed (20MHz). The max clock is 24MHz on SD, but as
+ * MMC wont run that fast, it has to be clocked at 12MHz which is the next
+ * slowest setting.
+ */
+static int sdhi_boot_mmc_set_ios(void __iomem *base, struct mmc_ios *ios)
+{
+	if (sd_ctrl_read32(base, CTL_STATUS) & TMIO_STAT_CMD_BUSY)
+		return -EBUSY;
+
+	if (ios->clock)
+		sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL,
+				ios->clock | CLK_MMC_ENABLE);
+
+	/* Power sequence - OFF -> ON -> UP */
+	switch (ios->power_mode) {
+	case MMC_POWER_OFF: /* power down SD bus */
+		sdhi_boot_mmc_clk_stop(base);
+		break;
+	case MMC_POWER_ON: /* power up SD bus */
+		break;
+	case MMC_POWER_UP: /* start bus clock */
+		sdhi_boot_mmc_clk_start(base);
+		break;
+	}
+
+	switch (ios->bus_width) {
+	case MMC_BUS_WIDTH_1:
+		sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x80e0);
+	break;
+	case MMC_BUS_WIDTH_4:
+		sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x00e0);
+	break;
+	}
+
+	/* Let things settle. delay taken from winCE driver */
+	udelay(140);
+
+	return 0;
+}
+
+/* These are the bitmasks the tmio chip requires to implement the MMC response
+ * types. Note that R1 and R6 are the same in this scheme. */
+#define RESP_NONE      0x0300
+#define RESP_R1        0x0400
+#define RESP_R1B       0x0500
+#define RESP_R2        0x0600
+#define RESP_R3        0x0700
+#define DATA_PRESENT   0x0800
+#define TRANSFER_READ  0x1000
+
+static int sdhi_boot_request(void __iomem *base, struct mmc_command *cmd)
+{
+	int err, c = cmd->opcode;
+
+	switch (mmc_resp_type(cmd)) {
+	case MMC_RSP_NONE: c |= RESP_NONE; break;
+	case MMC_RSP_R1:   c |= RESP_R1;   break;
+	case MMC_RSP_R1B:  c |= RESP_R1B;  break;
+	case MMC_RSP_R2:   c |= RESP_R2;   break;
+	case MMC_RSP_R3:   c |= RESP_R3;   break;
+	default:
+		return -EINVAL;
+	}
+
+	/* No interrupts so this may not be cleared */
+	sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND);
+
+	sd_ctrl_write32(base, CTL_IRQ_MASK, TMIO_STAT_CMDRESPEND |
+			sd_ctrl_read32(base, CTL_IRQ_MASK));
+	sd_ctrl_write32(base, CTL_ARG_REG, cmd->arg);
+	sd_ctrl_write16(base, CTL_SD_CMD, c);
+
+
+	sd_ctrl_write32(base, CTL_IRQ_MASK,
+			~(TMIO_STAT_CMDRESPEND | ALL_ERROR) &
+			sd_ctrl_read32(base, CTL_IRQ_MASK));
+
+	err = sdhi_boot_wait_resp_end(base);
+	if (err)
+		return err;
+
+	cmd->resp[0] = sd_ctrl_read32(base, CTL_RESPONSE);
+
+	return 0;
+}
+
+static int sdhi_boot_do_read_single(void __iomem *base, int high_capacity,
+				    unsigned long block, unsigned short *buf)
+{
+	int err, i;
+
+	/* CMD17 - Read */
+	{
+		struct mmc_command cmd;
+
+		cmd.opcode = MMC_READ_SINGLE_BLOCK | \
+			     TRANSFER_READ | DATA_PRESENT;
+		if (high_capacity)
+			cmd.arg = block;
+		else
+			cmd.arg = block * TMIO_BBS;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	sd_ctrl_write32(base, CTL_IRQ_MASK,
+			~(TMIO_STAT_DATAEND | TMIO_STAT_RXRDY |
+			  TMIO_STAT_TXUNDERRUN) &
+			sd_ctrl_read32(base, CTL_IRQ_MASK));
+	err = sdhi_boot_wait_resp_end(base);
+	if (err)
+		return err;
+
+	sd_ctrl_write16(base, CTL_SD_XFER_LEN, TMIO_BBS);
+	for (i = 0; i < TMIO_BBS / sizeof(*buf); i++)
+		*buf++ = sd_ctrl_read16(base, RESP_CMD12);
+
+	err = sdhi_boot_wait_resp_end(base);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int sdhi_boot_do_read(void __iomem *base, int high_capacity,
+		      unsigned long offset, unsigned short count,
+		      unsigned short *buf)
+{
+	unsigned long i;
+	int err = 0;
+
+	for (i = 0; i < count; i++) {
+		err = sdhi_boot_do_read_single(base, high_capacity, offset + i,
+					       buf + (i * TMIO_BBS /
+						      sizeof(*buf)));
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+#define VOLTAGES (MMC_VDD_32_33 | MMC_VDD_33_34)
+
+int sdhi_boot_init(void __iomem *base)
+{
+	bool sd_v2 = false, sd_v1_0 = false;
+	unsigned short cid;
+	int err, high_capacity = 0;
+
+	sdhi_boot_mmc_clk_stop(base);
+	sdhi_boot_reset(base);
+
+	/* mmc0: clock 400000Hz busmode 1 powermode 2 cs 0 Vdd 21 width 0 timing 0 */
+	{
+		struct mmc_ios ios;
+		ios.power_mode = MMC_POWER_ON;
+		ios.bus_width = MMC_BUS_WIDTH_1;
+		ios.clock = CLK_MMC_INIT;
+		err = sdhi_boot_mmc_set_ios(base, &ios);
+		if (err)
+			return err;
+	}
+
+	/* CMD0 */
+	{
+		struct mmc_command cmd;
+		msleep(1);
+		cmd.opcode = MMC_GO_IDLE_STATE;
+		cmd.arg = 0;
+		cmd.flags = MMC_RSP_NONE;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+		msleep(2);
+	}
+
+	/* CMD8 - Test for SD version 2 */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = SD_SEND_IF_COND;
+		cmd.arg = (VOLTAGES != 0) << 8 | 0xaa;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd); /* Ignore error */
+		if ((cmd.resp[0] & 0xff) == 0xaa)
+			sd_v2 = true;
+	}
+
+	/* CMD55 - Get OCR (SD) */
+	{
+		int timeout = 1000;
+		struct mmc_command cmd;
+
+		cmd.arg = 0;
+
+		do {
+			cmd.opcode = MMC_APP_CMD;
+			cmd.flags = MMC_RSP_R1;
+			cmd.arg = 0;
+			err = sdhi_boot_request(base, &cmd);
+			if (err)
+				break;
+
+			cmd.opcode = SD_APP_OP_COND;
+			cmd.flags = MMC_RSP_R3;
+			cmd.arg = (VOLTAGES & 0xff8000);
+			if (sd_v2)
+				cmd.arg |= OCR_HCS;
+			cmd.arg |= OCR_FASTBOOT;
+			err = sdhi_boot_request(base, &cmd);
+			if (err)
+				break;
+
+			msleep(1);
+		} while((!(cmd.resp[0] & OCR_BUSY)) && --timeout);
+
+		if (!err && timeout) {
+			if (!sd_v2)
+				sd_v1_0 = true;
+			high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS;
+		}
+	}
+
+	/* CMD1 - Get OCR (MMC) */
+	if (!sd_v2 && !sd_v1_0) {
+		int timeout = 1000;
+		struct mmc_command cmd;
+
+		do {
+			cmd.opcode = MMC_SEND_OP_COND;
+			cmd.arg = VOLTAGES | OCR_HCS;
+			cmd.flags = MMC_RSP_R3;
+			err = sdhi_boot_request(base, &cmd);
+			if (err)
+				return err;
+
+			msleep(1);
+		} while((!(cmd.resp[0] & OCR_BUSY)) && --timeout);
+
+		if (!timeout)
+			return -EAGAIN;
+
+		high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS;
+	}
+
+	/* CMD2 - Get CID */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_ALL_SEND_CID;
+		cmd.arg = 0;
+		cmd.flags = MMC_RSP_R2;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	/* CMD3
+	 * MMC: Set the relative address
+	 * SD:  Get the relative address
+	 * Also puts the card into the standby state
+	 */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_SET_RELATIVE_ADDR;
+		cmd.arg = 0;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+		cid = cmd.resp[0] >> 16;
+	}
+
+	/* CMD9 - Get CSD */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_SEND_CSD;
+		cmd.arg = cid << 16;
+		cmd.flags = MMC_RSP_R2;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	/* CMD7 - Select the card */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_SELECT_CARD;
+		//cmd.arg = rca << 16;
+		cmd.arg = cid << 16;
+		//cmd.flags = MMC_RSP_R1B;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	/* CMD16 - Set the block size */
+	{
+		struct mmc_command cmd;
+		cmd.opcode = MMC_SET_BLOCKLEN;
+		cmd.arg = TMIO_BBS;
+		cmd.flags = MMC_RSP_R1;
+		err = sdhi_boot_request(base, &cmd);
+		if (err)
+			return err;
+	}
+
+	return high_capacity;
+}

arch/arm/boot/compressed/sdhi-shmobile.h

+#ifndef SDHI_MOBILE_H
+#define SDHI_MOBILE_H
+
+#include <linux/compiler.h>
+
+int sdhi_boot_do_read(void __iomem *base, int high_capacity,
+		      unsigned long offset, unsigned short count,
+		      unsigned short *buf);
+int sdhi_boot_init(void __iomem *base);
+
+#endif

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

@@ -33,20 +33,24 @@ SECTIONS
     *(.text.*)
     *(.fixup)
     *(.gnu.warning)
+    *(.glue_7t)
+    *(.glue_7)
+  }
+  .rodata : {
     *(.rodata)
     *(.rodata.*)
-    *(.glue_7)
-    *(.glue_7t)
+  }
+  .piggydata : {
     *(.piggydata)
-    . = ALIGN(4);
   }
 
+  . = ALIGN(4);
   _etext = .;
 
+  .got.plt		: { *(.got.plt) }
   _got_start = .;
   .got			: { *(.got) }
   _got_end = .;
-  .got.plt		: { *(.got.plt) }
   _edata = .;
 
   . = BSS_START;

arch/arm/common/dmabounce.c

@@ -79,6 +79,8 @@ struct dmabounce_device_info {
 	struct dmabounce_pool	large;
 
 	rwlock_t lock;
+
+	int (*needs_bounce)(struct device *, dma_addr_t, size_t);
 };
 
 #ifdef STATS
@@ -210,114 +212,91 @@ static struct safe_buffer *find_safe_buffer_dev(struct device *dev,
 	if (!dev || !dev->archdata.dmabounce)
 		return NULL;
 	if (dma_mapping_error(dev, dma_addr)) {
-		if (dev)
-			dev_err(dev, "Trying to %s invalid mapping\n", where);
-		else
-			pr_err("unknown device: Trying to %s invalid mapping\n", where);
+		dev_err(dev, "Trying to %s invalid mapping\n", where);
 		return NULL;
 	}
 	return find_safe_buffer(dev->archdata.dmabounce, dma_addr);
 }
 
-static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
-		enum dma_data_direction dir)
+static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
-	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-	dma_addr_t dma_addr;
-	int needs_bounce = 0;
-
-	if (device_info)
-		DO_STATS ( device_info->map_op_count++ );
-
-	dma_addr = virt_to_dma(dev, ptr);
+	if (!dev || !dev->archdata.dmabounce)
+		return 0;
 
 	if (dev->dma_mask) {
-		unsigned long mask = *dev->dma_mask;
-		unsigned long limit;
+		unsigned long limit, mask = *dev->dma_mask;
 
 		limit = (mask + 1) & ~mask;
 		if (limit && size > limit) {
 			dev_err(dev, "DMA mapping too big (requested %#x "
 				"mask %#Lx)\n", size, *dev->dma_mask);
-			return ~0;
+			return -E2BIG;
 		}
 
-		/*
-		 * Figure out if we need to bounce from the DMA mask.
-		 */
-		needs_bounce = (dma_addr | (dma_addr + size - 1)) & ~mask;
+		/* Figure out if we need to bounce from the DMA mask. */
+		if ((dma_addr | (dma_addr + size - 1)) & ~mask)
+			return 1;
 	}
 
-	if (device_info && (needs_bounce || dma_needs_bounce(dev, dma_addr, size))) {
-		struct safe_buffer *buf;
+	return !!dev->archdata.dmabounce->needs_bounce(dev, dma_addr, size);
+}
 
-		buf = alloc_safe_buffer(device_info, ptr, size, dir);
-		if (buf == 0) {
-			dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
-			       __func__, ptr);
-			return ~0;
-		}
+static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
+		enum dma_data_direction dir)
+{
+	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
+	struct safe_buffer *buf;
 
-		dev_dbg(dev,
-			"%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-			__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-			buf->safe, buf->safe_dma_addr);
+	if (device_info)
+		DO_STATS ( device_info->map_op_count++ );
 
-		if ((dir == DMA_TO_DEVICE) ||
-		    (dir == DMA_BIDIRECTIONAL)) {
-			dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
-				__func__, ptr, buf->safe, size);
-			memcpy(buf->safe, ptr, size);
-		}
-		ptr = buf->safe;
+	buf = alloc_safe_buffer(device_info, ptr, size, dir);
+	if (buf == NULL) {
+		dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
+		       __func__, ptr);
+		return ~0;
+	}
 
-		dma_addr = buf->safe_dma_addr;
-	} else {
-		/*
-		 * We don't need to sync the DMA buffer since
-		 * it was allocated via the coherent allocators.
-		 */
-		__dma_single_cpu_to_dev(ptr, size, dir);
+	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+		buf->safe, buf->safe_dma_addr);
+
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
+		dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
+			__func__, ptr, buf->safe, size);
+		memcpy(buf->safe, ptr, size);
 	}
 
-	return dma_addr;
+	return buf->safe_dma_addr;
 }
 
-static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
+static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
 		size_t size, enum dma_data_direction dir)
 {
-	struct safe_buffer *buf = find_safe_buffer_dev(dev, dma_addr, "unmap");
-
-	if (buf) {
-		BUG_ON(buf->size != size);
-		BUG_ON(buf->direction != dir);
+	BUG_ON(buf->size != size);
+	BUG_ON(buf->direction != dir);
 
-		dev_dbg(dev,
-			"%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-			__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-			buf->safe, buf->safe_dma_addr);
+	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+		buf->safe, buf->safe_dma_addr);
 
-		DO_STATS(dev->archdata.dmabounce->bounce_count++);
+	DO_STATS(dev->archdata.dmabounce->bounce_count++);
 
-		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
-			void *ptr = buf->ptr;
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
+		void *ptr = buf->ptr;
 
-			dev_dbg(dev,
-				"%s: copy back safe %p to unsafe %p size %d\n",
-				__func__, buf->safe, ptr, size);
-			memcpy(ptr, buf->safe, size);
+		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
+			__func__, buf->safe, ptr, size);
+		memcpy(ptr, buf->safe, size);
 
-			/*
-			 * Since we may have written to a page cache page,
-			 * we need to ensure that the data will be coherent
-			 * with user mappings.
-			 */
-			__cpuc_flush_dcache_area(ptr, size);
-		}
-		free_safe_buffer(dev->archdata.dmabounce, buf);
-	} else {
-		__dma_single_dev_to_cpu(dma_to_virt(dev, dma_addr), size, dir);
+		/*
+		 * Since we may have written to a page cache page,
+		 * we need to ensure that the data will be coherent
+		 * with user mappings.
+		 */
+		__cpuc_flush_dcache_area(ptr, size);
 	}
+	free_safe_buffer(dev->archdata.dmabounce, buf);
 }
 
 /* ************************************************** */
@@ -328,45 +307,28 @@ static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
  * substitute the safe buffer for the unsafe one.
  * (basically move the buffer from an unsafe area to a safe one)
  */
-dma_addr_t __dma_map_single(struct device *dev, void *ptr, size_t size,
-		enum dma_data_direction dir)
-{
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, ptr, size, dir);
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	return map_single(dev, ptr, size, dir);
-}
-EXPORT_SYMBOL(__dma_map_single);
-
-/*
- * see if a mapped address was really a "safe" buffer and if so, copy
- * the data from the safe buffer back to the unsafe buffer and free up
- * the safe buffer.  (basically return things back to the way they
- * should be)
- */
-void __dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		enum dma_data_direction dir)
-{
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, (void *) dma_addr, size, dir);
-
-	unmap_single(dev, dma_addr, size, dir);
-}
-EXPORT_SYMBOL(__dma_unmap_single);
-
 dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir)
 {
+	dma_addr_t dma_addr;
+	int ret;
+
 	dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n",
 		__func__, page, offset, size, dir);
 
-	BUG_ON(!valid_dma_direction(dir));
+	dma_addr = pfn_to_dma(dev, page_to_pfn(page)) + offset;
+
+	ret = needs_bounce(dev, dma_addr, size);
+	if (ret < 0)
+		return ~0;
+
+	if (ret == 0) {
+		__dma_page_cpu_to_dev(page, offset, size, dir);
+		return dma_addr;
+	}
 
 	if (PageHighMem(page)) {
-		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages "
-			     "is not supported\n");
+		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
 		return ~0;
 	}
 
@@ -383,10 +345,19 @@ EXPORT_SYMBOL(__dma_map_page);
 void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 		enum dma_data_direction dir)
 {
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, (void *) dma_addr, size, dir);
+	struct safe_buffer *buf;
+
+	dev_dbg(dev, "%s(dma=%#x,size=%d,dir=%x)\n",
+		__func__, dma_addr, size, dir);
+
+	buf = find_safe_buffer_dev(dev, dma_addr, __func__);
+	if (!buf) {
+		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, dma_addr)),
+			dma_addr & ~PAGE_MASK, size, dir);
+		return;
+	}
 
-	unmap_single(dev, dma_addr, size, dir);
+	unmap_single(dev, buf, size, dir);
 }
 EXPORT_SYMBOL(__dma_unmap_page);
 
@@ -461,7 +432,8 @@ static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
 }
 
 int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
-		unsigned long large_buffer_size)
+		unsigned long large_buffer_size,
+		int (*needs_bounce_fn)(struct device *, dma_addr_t, size_t))
 {
 	struct dmabounce_device_info *device_info;
 	int ret;
@@ -497,6 +469,7 @@ int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
 	device_info->dev = dev;
 	INIT_LIST_HEAD(&device_info->safe_buffers);
 	rwlock_init(&device_info->lock);
+	device_info->needs_bounce = needs_bounce_fn;
 
 #ifdef STATS
 	device_info->total_allocs = 0;

arch/arm/common/gic.c

@@ -179,22 +179,21 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 {
 	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
 	unsigned int shift = (d->irq % 4) * 8;
-	unsigned int cpu = cpumask_first(mask_val);
+	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
 	u32 val, mask, bit;
 
-	if (cpu >= 8)
+	if (cpu >= 8 || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
 	mask = 0xff << shift;
 	bit = 1 << (cpu + shift);
 
 	spin_lock(&irq_controller_lock);
-	d->node = cpu;
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
 	spin_unlock(&irq_controller_lock);
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 #endif
 

arch/arm/common/it8152.c

@@ -243,6 +243,12 @@ static struct resource it8152_mem = {
  * ITE8152 chip can address up to 64MByte, so all the devices
  * connected to ITE8152 (PCI and USB) should have limited DMA window
  */
+static int it8152_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
+{
+	dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
+		__func__, dma_addr, size);
+	return (dma_addr + size - PHYS_OFFSET) >= SZ_64M;
+}
 
 /*
  * Setup DMA mask to 64MB on devices connected to ITE8152. Ignore all
@@ -254,7 +260,7 @@ static int it8152_pci_platform_notify(struct device *dev)
 		if (dev->dma_mask)
 			*dev->dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
 		dev->coherent_dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
-		dmabounce_register_dev(dev, 2048, 4096);
+		dmabounce_register_dev(dev, 2048, 4096, it8152_needs_bounce);
 	}
 	return 0;
 }
@@ -267,14 +273,6 @@ static int it8152_pci_platform_notify_remove(struct device *dev)
 	return 0;
 }
 
-int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-	dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
-		__func__, dma_addr, size);
-	return (dev->bus == &pci_bus_type) &&
-		((dma_addr + size - PHYS_OFFSET) >= SZ_64M);
-}
-
 int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
 	if (mask >= PHYS_OFFSET + SZ_64M - 1)

arch/arm/common/sa1111.c

@@ -579,7 +579,36 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac,
 
 	sachip->dev->coherent_dma_mask &= sa1111_dma_mask[drac >> 2];
 }
+#endif
 
+#ifdef CONFIG_DMABOUNCE
+/*
+ * According to the "Intel StrongARM SA-1111 Microprocessor Companion
+ * Chip Specification Update" (June 2000), erratum #7, there is a
+ * significant bug in the SA1111 SDRAM shared memory controller.  If
+ * an access to a region of memory above 1MB relative to the bank base,
+ * it is important that address bit 10 _NOT_ be asserted. Depending
+ * on the configuration of the RAM, bit 10 may correspond to one
+ * of several different (processor-relative) address bits.
+ *
+ * This routine only identifies whether or not a given DMA address
+ * is susceptible to the bug.
+ *
+ * This should only get called for sa1111_device types due to the
+ * way we configure our device dma_masks.
+ */
+static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
+{
+	/*
+	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
+	 * User's Guide" mentions that jumpers R51 and R52 control the
+	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
+	 * SDRAM bank 1 on Neponset). The default configuration selects
+	 * Assabet, so any address in bank 1 is necessarily invalid.
+	 */
+	return (machine_is_assabet() || machine_is_pfs168()) &&
+		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000);
+}
 #endif
 
 static void sa1111_dev_release(struct device *_dev)
@@ -644,7 +673,8 @@ sa1111_init_one_child(struct sa1111 *sachip, struct resource *parent,
 		dev->dev.dma_mask = &dev->dma_mask;
 
 		if (dev->dma_mask != 0xffffffffUL) {
-			ret = dmabounce_register_dev(&dev->dev, 1024, 4096);
+			ret = dmabounce_register_dev(&dev->dev, 1024, 4096,
+					sa1111_needs_bounce);
 			if (ret) {
 				dev_err(&dev->dev, "SA1111: Failed to register"
 					" with dmabounce\n");
@@ -818,34 +848,6 @@ static void __sa1111_remove(struct sa1111 *sachip)
 	kfree(sachip);
 }
 
-/*
- * According to the "Intel StrongARM SA-1111 Microprocessor Companion
- * Chip Specification Update" (June 2000), erratum #7, there is a
- * significant bug in the SA1111 SDRAM shared memory controller.  If
- * an access to a region of memory above 1MB relative to the bank base,
- * it is important that address bit 10 _NOT_ be asserted. Depending
- * on the configuration of the RAM, bit 10 may correspond to one
- * of several different (processor-relative) address bits.
- *
- * This routine only identifies whether or not a given DMA address
- * is susceptible to the bug.
- *
- * This should only get called for sa1111_device types due to the
- * way we configure our device dma_masks.
- */
-int dma_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
-{
-	/*
-	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
-	 * User's Guide" mentions that jumpers R51 and R52 control the
-	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
-	 * SDRAM bank 1 on Neponset). The default configuration selects
-	 * Assabet, so any address in bank 1 is necessarily invalid.
-	 */
-	return ((machine_is_assabet() || machine_is_pfs168()) &&
-		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000));
-}
-
 struct sa1111_save_data {
 	unsigned int	skcr;
 	unsigned int	skpcr;

arch/arm/include/asm/assembler.h

@@ -293,4 +293,13 @@
 	.macro	ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f
 	usracc	ldr, \reg, \ptr, \inc, \cond, \rept, \abort
 	.endm
+
+/* Utility macro for declaring string literals */
+	.macro	string name:req, string
+	.type \name , #object
+\name:
+	.asciz "\string"
+	.size \name , . - \name
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */

arch/arm/include/asm/bitops.h

@@ -26,8 +26,8 @@
 #include <linux/compiler.h>
 #include <asm/system.h>
 
-#define smp_mb__before_clear_bit()	mb()
-#define smp_mb__after_clear_bit()	mb()
+#define smp_mb__before_clear_bit()	smp_mb()
+#define smp_mb__after_clear_bit()	smp_mb()
 
 /*
  * These functions are the basis of our bit ops.

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

@@ -115,39 +115,8 @@ static inline void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 		___dma_page_dev_to_cpu(page, off, size, dir);
 }
 
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- *
- * FIXME: This should really be a platform specific issue - we should
- * return false if GFP_DMA allocations may not satisfy the supplied 'mask'.
- */
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	if (mask < ISA_DMA_THRESHOLD)
-		return 0;
-	return 1;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-#ifdef CONFIG_DMABOUNCE
-	if (dev->archdata.dmabounce) {
-		if (dma_mask >= ISA_DMA_THRESHOLD)
-			return 0;
-		else
-			return -EIO;
-	}
-#endif
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-
-	return 0;
-}
+extern int dma_supported(struct device *, u64);
+extern int dma_set_mask(struct device *, u64);
 
 /*
  * DMA errors are defined by all-bits-set in the DMA address.
@@ -256,14 +225,14 @@ int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
  * @dev: valid struct device pointer
  * @small_buf_size: size of buffers to use with small buffer pool
  * @large_buf_size: size of buffers to use with large buffer pool (can be 0)
+ * @needs_bounce_fn: called to determine whether buffer needs bouncing
  *
  * This function should be called by low-level platform code to register
  * a device as requireing DMA buffer bouncing. The function will allocate
  * appropriate DMA pools for the device.
- *
  */
 extern int dmabounce_register_dev(struct device *, unsigned long,
-		unsigned long);
+		unsigned long, int (*)(struct device *, dma_addr_t, size_t));
 
 /**
  * dmabounce_unregister_dev
@@ -277,31 +246,9 @@ extern int dmabounce_register_dev(struct device *, unsigned long,
  */
 extern void dmabounce_unregister_dev(struct device *);
 
-/**
- * dma_needs_bounce
- *
- * @dev: valid struct device pointer
- * @dma_handle: dma_handle of unbounced buffer
- * @size: size of region being mapped
- *
- * Platforms that utilize the dmabounce mechanism must implement
- * this function.
- *
- * The dmabounce routines call this function whenever a dma-mapping
- * is requested to determine whether a given buffer needs to be bounced
- * or not. The function must return 0 if the buffer is OK for
- * DMA access and 1 if the buffer needs to be bounced.
- *
- */
-extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
-
 /*
  * The DMA API, implemented by dmabounce.c.  See below for descriptions.
  */
-extern dma_addr_t __dma_map_single(struct device *, void *, size_t,
-		enum dma_data_direction);
-extern void __dma_unmap_single(struct device *, dma_addr_t, size_t,
-		enum dma_data_direction);
 extern dma_addr_t __dma_map_page(struct device *, struct page *,
 		unsigned long, size_t, enum dma_data_direction);
 extern void __dma_unmap_page(struct device *, dma_addr_t, size_t,
@@ -328,13 +275,6 @@ static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
 }
 
 
-static inline dma_addr_t __dma_map_single(struct device *dev, void *cpu_addr,
-		size_t size, enum dma_data_direction dir)
-{
-	__dma_single_cpu_to_dev(cpu_addr, size, dir);
-	return virt_to_dma(dev, cpu_addr);
-}
-
 static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir)
 {
@@ -342,12 +282,6 @@ static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
 }
 
-static inline void __dma_unmap_single(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	__dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir);
-}
-
 static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
@@ -373,14 +307,18 @@ static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle,
 static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
 		size_t size, enum dma_data_direction dir)
 {
+	unsigned long offset;
+	struct page *page;
 	dma_addr_t addr;
 
+	BUG_ON(!virt_addr_valid(cpu_addr));
+	BUG_ON(!virt_addr_valid(cpu_addr + size - 1));
 	BUG_ON(!valid_dma_direction(dir));
 
-	addr = __dma_map_single(dev, cpu_addr, size, dir);
-	debug_dma_map_page(dev, virt_to_page(cpu_addr),
-			(unsigned long)cpu_addr & ~PAGE_MASK, size,
-			dir, addr, true);
+	page = virt_to_page(cpu_addr);
+	offset = (unsigned long)cpu_addr & ~PAGE_MASK;
+	addr = __dma_map_page(dev, page, offset, size, dir);
+	debug_dma_map_page(dev, page, offset, size, dir, addr, true);
 
 	return addr;
 }
@@ -430,7 +368,7 @@ static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
 	debug_dma_unmap_page(dev, handle, size, dir, true);
-	__dma_unmap_single(dev, handle, size, dir);
+	__dma_unmap_page(dev, handle, size, dir);
 }
 
 /**

arch/arm/include/asm/dma.h

 #ifndef __ASM_ARM_DMA_H
 #define __ASM_ARM_DMA_H
 
-#include <asm/memory.h>
-
 /*
  * This is the maximum virtual address which can be DMA'd from.
  */
-#ifndef ARM_DMA_ZONE_SIZE
-#define MAX_DMA_ADDRESS	0xffffffff
+#ifndef CONFIG_ZONE_DMA
+#define MAX_DMA_ADDRESS	0xffffffffUL
 #else
-#define MAX_DMA_ADDRESS	(PAGE_OFFSET + ARM_DMA_ZONE_SIZE)
+#define MAX_DMA_ADDRESS	({ \
+	extern unsigned long arm_dma_zone_size; \
+	arm_dma_zone_size ? \
+		(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
 #endif
 
 #ifdef CONFIG_ISA_DMA_API

arch/arm/include/asm/entry-macro-multi.S

@@ -4,8 +4,8 @@
  * Interrupt handling.  Preserves r7, r8, r9
  */
 	.macro	arch_irq_handler_default
-	get_irqnr_preamble r5, lr
-1:	get_irqnr_and_base r0, r6, r5, lr
+	get_irqnr_preamble r6, lr
+1:	get_irqnr_and_base r0, r2, r6, lr
 	movne	r1, sp
 	@
 	@ routine called with r0 = irq number, r1 = struct pt_regs *
@@ -17,17 +17,17 @@
 	/*
 	 * XXX
 	 *
-	 * this macro assumes that irqstat (r6) and base (r5) are
+	 * this macro assumes that irqstat (r2) and base (r6) are
 	 * preserved from get_irqnr_and_base above
 	 */
-	ALT_SMP(test_for_ipi r0, r6, r5, lr)
+	ALT_SMP(test_for_ipi r0, r2, r6, lr)
 	ALT_UP_B(9997f)
 	movne	r1, sp
 	adrne	lr, BSYM(1b)
 	bne	do_IPI
 
 #ifdef CONFIG_LOCAL_TIMERS
-	test_for_ltirq r0, r6, r5, lr
+	test_for_ltirq r0, r2, r6, lr
 	movne	r0, sp
 	adrne	lr, BSYM(1b)
 	bne	do_local_timer
@@ -40,7 +40,7 @@
 	.align	5
 	.global \symbol_name
 \symbol_name:
-	mov	r4, lr
+	mov	r8, lr
 	arch_irq_handler_default
-	mov     pc, r4
+	mov     pc, r8
 	.endm

arch/arm/include/asm/hwcap.h

@@ -4,22 +4,26 @@
 /*
  * HWCAP flags - for elf_hwcap (in kernel) and AT_HWCAP
  */
-#define HWCAP_SWP	1
-#define HWCAP_HALF	2
-#define HWCAP_THUMB	4
-#define HWCAP_26BIT	8	/* Play it safe */
-#define HWCAP_FAST_MULT	16
-#define HWCAP_FPA	32
-#define HWCAP_VFP	64
-#define HWCAP_EDSP	128
-#define HWCAP_JAVA	256
-#define HWCAP_IWMMXT	512
-#define HWCAP_CRUNCH	1024
-#define HWCAP_THUMBEE	2048
-#define HWCAP_NEON	4096
-#define HWCAP_VFPv3	8192
-#define HWCAP_VFPv3D16	16384
-#define HWCAP_TLS	32768
+#define HWCAP_SWP	(1 << 0)
+#define HWCAP_HALF	(1 << 1)
+#define HWCAP_THUMB	(1 << 2)
+#define HWCAP_26BIT	(1 << 3)	/* Play it safe */
+#define HWCAP_FAST_MULT	(1 << 4)
+#define HWCAP_FPA	(1 << 5)
+#define HWCAP_VFP	(1 << 6)
+#define HWCAP_EDSP	(1 << 7)
+#define HWCAP_JAVA	(1 << 8)
+#define HWCAP_IWMMXT	(1 << 9)
+#define HWCAP_CRUNCH	(1 << 10)
+#define HWCAP_THUMBEE	(1 << 11)
+#define HWCAP_NEON	(1 << 12)
+#define HWCAP_VFPv3	(1 << 13)
+#define HWCAP_VFPv3D16	(1 << 14)
+#define HWCAP_TLS	(1 << 15)
+#define HWCAP_VFPv4	(1 << 16)
+#define HWCAP_IDIVA	(1 << 17)
+#define HWCAP_IDIVT	(1 << 18)
+#define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 /*

arch/arm/include/asm/kprobes.h

@@ -24,12 +24,6 @@
 #define MAX_INSN_SIZE			2
 #define MAX_STACK_SIZE			64	/* 32 would probably be OK */
 
-/*
- * This undefined instruction must be unique and
- * reserved solely for kprobes' use.
- */
-#define KPROBE_BREAKPOINT_INSTRUCTION	0xe7f001f8
-
 #define regs_return_value(regs)		((regs)->ARM_r0)
 #define flush_insn_slot(p)		do { } while (0)
 #define kretprobe_blacklist_size	0
@@ -38,14 +32,17 @@ 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);
 
 /* 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_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;
 };
 
 struct prev_kprobe {
@@ -62,20 +59,9 @@ struct kprobe_ctlblk {
 };
 
 void arch_remove_kprobe(struct kprobe *);
-void kretprobe_trampoline(void);
-
 int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 			     unsigned long val, void *data);
 
-enum kprobe_insn {
-	INSN_REJECTED,
-	INSN_GOOD,
-	INSN_GOOD_NO_SLOT
-};
-
-enum kprobe_insn arm_kprobe_decode_insn(kprobe_opcode_t,
-					struct arch_specific_insn *);
-void __init arm_kprobe_decode_init(void);
 
 #endif /* _ARM_KPROBES_H */

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

@@ -23,6 +23,10 @@ struct machine_desc {
 
 	unsigned int		nr_irqs;	/* number of IRQs */
 
+#ifdef CONFIG_ZONE_DMA
+	unsigned long		dma_zone_size;	/* size of DMA-able area */
+#endif
+
 	unsigned int		video_start;	/* start of video RAM	*/
 	unsigned int		video_end;	/* end of video RAM	*/
 

arch/arm/include/asm/memory.h

@@ -203,18 +203,6 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 #define PHYS_OFFSET	PLAT_PHYS_OFFSET
 #endif
 
-/*
- * The DMA mask corresponding to the maximum bus address allocatable
- * using GFP_DMA.  The default here places no restriction on DMA
- * allocations.  This must be the smallest DMA mask in the system,
- * so a successful GFP_DMA allocation will always satisfy this.
- */
-#ifndef ARM_DMA_ZONE_SIZE
-#define ISA_DMA_THRESHOLD	(0xffffffffULL)
-#else
-#define ISA_DMA_THRESHOLD	(PHYS_OFFSET + ARM_DMA_ZONE_SIZE - 1)
-#endif
-
 /*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.

arch/arm/include/asm/perf_event.h

@@ -24,6 +24,8 @@ enum arm_perf_pmu_ids {
 	ARM_PERF_PMU_ID_V6MP,
 	ARM_PERF_PMU_ID_CA8,
 	ARM_PERF_PMU_ID_CA9,
+	ARM_PERF_PMU_ID_CA5,
+	ARM_PERF_PMU_ID_CA15,
 	ARM_NUM_PMU_IDS,
 };
 

arch/arm/include/asm/pmu.h

@@ -52,7 +52,7 @@ reserve_pmu(enum arm_pmu_type device);
  * a cookie.
  */
 extern int
-release_pmu(struct platform_device *pdev);
+release_pmu(enum arm_pmu_type type);
 
 /**
  * init_pmu() - Initialise the PMU.

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

@@ -82,13 +82,13 @@ 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));
 #else
-#define cpu_proc_init()			processor._proc_init()
-#define cpu_proc_fin()			processor._proc_fin()
-#define cpu_reset(addr)			processor.reset(addr)
-#define cpu_do_idle()			processor._do_idle()
-#define cpu_dcache_clean_area(addr,sz)	processor.dcache_clean_area(addr,sz)
-#define cpu_set_pte_ext(ptep,pte,ext)	processor.set_pte_ext(ptep,pte,ext)
-#define cpu_do_switch_mm(pgd,mm)	processor.switch_mm(pgd,mm)
+#define cpu_proc_init			processor._proc_init
+#define cpu_proc_fin			processor._proc_fin
+#define cpu_reset			processor.reset
+#define cpu_do_idle			processor._do_idle
+#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
 #endif
 
 extern void cpu_resume(void);

arch/arm/include/asm/ptrace.h

@@ -69,8 +69,9 @@
 #define PSR_c		0x000000ff	/* Control		*/
 
 /*
- * ARMv7 groups of APSR bits
+ * ARMv7 groups of PSR bits
  */
+#define APSR_MASK	0xf80f0000	/* N, Z, C, V, Q and GE flags */
 #define PSR_ISET_MASK	0x01000010	/* ISA state (J, T) mask */
 #define PSR_IT_MASK	0x0600fc00	/* If-Then execution state mask */
 #define PSR_ENDIAN_MASK	0x00000200	/* Endianness state mask */
@@ -199,6 +200,14 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 #define predicate(x)		((x) & 0xf0000000)
 #define PREDICATE_ALWAYS	0xe0000000
 
+/*
+ * True if instr is a 32-bit thumb instruction. This works if instr
+ * is the first or only half-word of a thumb instruction. It also works
+ * when instr holds all 32-bits of a wide thumb instruction if stored
+ * in the form (first_half<<16)|(second_half)
+ */
+#define is_wide_instruction(instr)	((unsigned)(instr) >= 0xe800)
+
 /*
  * kprobe-based event tracer support
  */

arch/arm/include/asm/scatterlist.h

 #ifndef _ASMARM_SCATTERLIST_H
 #define _ASMARM_SCATTERLIST_H
 
+#ifdef CONFIG_ARM_HAS_SG_CHAIN
+#define ARCH_HAS_SG_CHAIN
+#endif
+
 #include <asm/memory.h>
 #include <asm/types.h>
 #include <asm-generic/scatterlist.h>

arch/arm/include/asm/setup.h

@@ -187,12 +187,16 @@ struct tagtable {
 
 #define __tag __used __attribute__((__section__(".taglist.init")))
 #define __tagtable(tag, fn) \
-static struct tagtable __tagtable_##fn __tag = { tag, fn }
+static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 
 /*
  * Memory map description
  */
-#define NR_BANKS 8
+#ifdef CONFIG_ARCH_EP93XX
+# define NR_BANKS 16
+#else
+# define NR_BANKS 8
+#endif
 
 struct membank {
 	phys_addr_t start;

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;
+}
+
+#endif

arch/arm/include/asm/tcm.h

@@ -27,5 +27,7 @@
 
 void *tcm_alloc(size_t len);
 void tcm_free(void *addr, size_t len);
+bool tcm_dtcm_present(void);
+bool tcm_itcm_present(void);
 
 #endif

arch/arm/include/asm/tlbflush.h

@@ -34,16 +34,12 @@
 #define TLB_V6_D_ASID	(1 << 17)
 #define TLB_V6_I_ASID	(1 << 18)
 
-#define TLB_BTB		(1 << 28)
-
 /* Unified Inner Shareable TLB operations (ARMv7 MP extensions) */
 #define TLB_V7_UIS_PAGE	(1 << 19)
 #define TLB_V7_UIS_FULL (1 << 20)
 #define TLB_V7_UIS_ASID (1 << 21)
 
-/* Inner Shareable BTB operation (ARMv7 MP extensions) */
-#define TLB_V7_IS_BTB	(1 << 22)
-
+#define TLB_BARRIER	(1 << 28)
 #define TLB_L2CLEAN_FR	(1 << 29)		/* Feroceon */
 #define TLB_DCLEAN	(1 << 30)
 #define TLB_WB		(1 << 31)
@@ -58,7 +54,7 @@
  *	  v4wb  - ARMv4 with write buffer without I TLB flush entry instruction
  *	  v4wbi - ARMv4 with write buffer with I TLB flush entry instruction
  *	  fr    - Feroceon (v4wbi with non-outer-cacheable page table walks)
- *	  fa    - Faraday (v4 with write buffer with UTLB and branch target buffer (BTB))
+ *	  fa    - Faraday (v4 with write buffer with UTLB)
  *	  v6wbi - ARMv6 with write buffer with I TLB flush entry instruction
  *	  v7wbi - identical to v6wbi
  */
@@ -99,7 +95,7 @@
 # define v4_always_flags	(-1UL)
 #endif
 
-#define fa_tlb_flags	(TLB_WB | TLB_BTB | TLB_DCLEAN | \
+#define fa_tlb_flags	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
 			 TLB_V4_U_FULL | TLB_V4_U_PAGE)
 
 #ifdef CONFIG_CPU_TLB_FA
@@ -166,7 +162,7 @@
 # define v4wb_always_flags	(-1UL)
 #endif
 
-#define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \
+#define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
 			 TLB_V6_I_FULL | TLB_V6_D_FULL | \
 			 TLB_V6_I_PAGE | TLB_V6_D_PAGE | \
 			 TLB_V6_I_ASID | TLB_V6_D_ASID)
@@ -184,9 +180,9 @@
 # define v6wbi_always_flags	(-1UL)
 #endif
 
-#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \
+#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
 			 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID)
-#define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BTB | \
+#define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
 			 TLB_V6_U_FULL | TLB_V6_U_PAGE | TLB_V6_U_ASID)
 
 #ifdef CONFIG_CPU_TLB_V7
@@ -341,15 +337,7 @@ static inline void local_flush_tlb_all(void)
 	if (tlb_flag(TLB_V7_UIS_FULL))
 		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
 
-	if (tlb_flag(TLB_BTB)) {
-		/* flush the branch target cache */
-		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
-		dsb();
-		isb();
-	}
-	if (tlb_flag(TLB_V7_IS_BTB)) {
-		/* flush the branch target cache */
-		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc");
+	if (tlb_flag(TLB_BARRIER)) {
 		dsb();
 		isb();
 	}
@@ -389,17 +377,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 		asm("mcr p15, 0, %0, c8, c3, 2" : : "r" (asid) : "cc");
 #endif
 
-	if (tlb_flag(TLB_BTB)) {
-		/* flush the branch target cache */
-		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
-		dsb();
-	}
-	if (tlb_flag(TLB_V7_IS_BTB)) {
-		/* flush the branch target cache */
-		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc");
+	if (tlb_flag(TLB_BARRIER))
 		dsb();
-		isb();
-	}
 }
 
 static inline void
@@ -439,17 +418,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (uaddr) : "cc");
 #endif
 
-	if (tlb_flag(TLB_BTB)) {
-		/* flush the branch target cache */
-		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
-		dsb();
-	}
-	if (tlb_flag(TLB_V7_IS_BTB)) {
-		/* flush the branch target cache */
-		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc");
+	if (tlb_flag(TLB_BARRIER))
 		dsb();
-		isb();
-	}
 }
 
 static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
@@ -482,15 +452,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	if (tlb_flag(TLB_V7_UIS_PAGE))
 		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (kaddr) : "cc");
 
-	if (tlb_flag(TLB_BTB)) {
-		/* flush the branch target cache */
-		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc");
-		dsb();
-		isb();
-	}
-	if (tlb_flag(TLB_V7_IS_BTB)) {
-		/* flush the branch target cache */
-		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc");
+	if (tlb_flag(TLB_BARRIER)) {
 		dsb();
 		isb();
 	}

arch/arm/include/asm/traps.h

@@ -3,6 +3,9 @@
 
 #include <linux/list.h>
 
+struct pt_regs;
+struct task_struct;
+
 struct undef_hook {
 	struct list_head node;
 	u32 instr_mask;

arch/arm/kernel/Makefile

@@ -37,7 +37,12 @@ obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-decode.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o
+ifdef CONFIG_THUMB2_KERNEL
+obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
+else
+obj-$(CONFIG_KPROBES)		+= kprobes-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/asm-offsets.c

@@ -59,6 +59,9 @@ int main(void)
   DEFINE(TI_TP_VALUE,		offsetof(struct thread_info, tp_value));
   DEFINE(TI_FPSTATE,		offsetof(struct thread_info, fpstate));
   DEFINE(TI_VFPSTATE,		offsetof(struct thread_info, vfpstate));
+#ifdef CONFIG_SMP
+  DEFINE(VFP_CPU,		offsetof(union vfp_state, hard.cpu));
+#endif
 #ifdef CONFIG_ARM_THUMBEE
   DEFINE(TI_THUMBEE_STATE,	offsetof(struct thread_info, thumbee_state));
 #endif

arch/arm/kernel/entry-armv.S

@@ -29,21 +29,53 @@
 #include <asm/entry-macro-multi.S>
 
 /*
- * Interrupt handling.  Preserves r7, r8, r9
+ * Interrupt handling.
  */
 	.macro	irq_handler
 #ifdef CONFIG_MULTI_IRQ_HANDLER
-	ldr	r5, =handle_arch_irq
+	ldr	r1, =handle_arch_irq
 	mov	r0, sp
-	ldr	r5, [r5]
+	ldr	r1, [r1]
 	adr	lr, BSYM(9997f)
-	teq	r5, #0
-	movne	pc, r5
+	teq	r1, #0
+	movne	pc, r1
 #endif
 	arch_irq_handler_default
 9997:
 	.endm
 
+	.macro	pabt_helper
+	@ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5
+#ifdef MULTI_PABORT
+	ldr	ip, .LCprocfns
+	mov	lr, pc
+	ldr	pc, [ip, #PROCESSOR_PABT_FUNC]
+#else
+	bl	CPU_PABORT_HANDLER
+#endif
+	.endm
+
+	.macro	dabt_helper
+
+	@
+	@ Call the processor-specific abort handler:
+	@
+	@  r2 - pt_regs
+	@  r4 - aborted context pc
+	@  r5 - aborted context psr
+	@
+	@ The abort handler must return the aborted address in r0, and
+	@ the fault status register in r1.  r9 must be preserved.
+	@
+#ifdef MULTI_DABORT
+	ldr	ip, .LCprocfns
+	mov	lr, pc
+	ldr	pc, [ip, #PROCESSOR_DABT_FUNC]
+#else
+	bl	CPU_DABORT_HANDLER
+#endif
+	.endm
+
 #ifdef CONFIG_KPROBES
 	.section	.kprobes.text,"ax",%progbits
 #else
@@ -126,106 +158,74 @@ ENDPROC(__und_invalid)
  SPFIX(	subeq	sp, sp, #4	)
 	stmia	sp, {r1 - r12}
 
-	ldmia	r0, {r1 - r3}
-	add	r5, sp, #S_SP - 4	@ here for interlock avoidance
-	mov	r4, #-1			@  ""  ""      ""       ""
-	add	r0, sp, #(S_FRAME_SIZE + \stack_hole - 4)
- SPFIX(	addeq	r0, r0, #4	)
-	str	r1, [sp, #-4]!		@ save the "real" r0 copied
+	ldmia	r0, {r3 - r5}
+	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
+	mov	r6, #-1			@  ""  ""      ""       ""
+	add	r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+ SPFIX(	addeq	r2, r2, #4	)
+	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
 
-	mov	r1, lr
+	mov	r3, lr
 
 	@
 	@ We are now ready to fill in the remaining blanks on the stack:
 	@
-	@  r0 - sp_svc
-	@  r1 - lr_svc
-	@  r2 - lr_<exception>, already fixed up for correct return/restart
-	@  r3 - spsr_<exception>
-	@  r4 - orig_r0 (see pt_regs definition in ptrace.h)
+	@  r2 - sp_svc
+	@  r3 - lr_svc
+	@  r4 - lr_<exception>, already fixed up for correct return/restart
+	@  r5 - spsr_<exception>
+	@  r6 - orig_r0 (see pt_regs definition in ptrace.h)
 	@
-	stmia	r5, {r0 - r4}
+	stmia	r7, {r2 - r6}
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off
+#endif
 	.endm
 
 	.align	5
 __dabt_svc:
 	svc_entry
-
-	@
-	@ get ready to re-enable interrupts if appropriate
-	@
-	mrs	r9, cpsr
-	tst	r3, #PSR_I_BIT
-	biceq	r9, r9, #PSR_I_BIT
-
-	@
-	@ Call the processor-specific abort handler:
-	@
-	@  r2 - aborted context pc
-	@  r3 - aborted context cpsr
-	@
-	@ The abort handler must return the aborted address in r0, and
-	@ the fault status register in r1.  r9 must be preserved.
-	@
-#ifdef MULTI_DABORT
-	ldr	r4, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [r4, #PROCESSOR_DABT_FUNC]
-#else
-	bl	CPU_DABORT_HANDLER
-#endif
-
-	@
-	@ set desired IRQ state, then call main handler
-	@
-	debug_entry r1
-	msr	cpsr_c, r9
 	mov	r2, sp
-	bl	do_DataAbort
+	dabt_helper
 
 	@
 	@ IRQs off again before pulling preserved data off the stack
 	@
 	disable_irq_notrace
 
-	@
-	@ restore SPSR and restart the instruction
-	@
-	ldr	r2, [sp, #S_PSR]
-	svc_exit r2				@ return from exception
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	r5, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	r5, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_svc)
 
 	.align	5
 __irq_svc:
 	svc_entry
+	irq_handler
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
-#endif
 #ifdef CONFIG_PREEMPT
 	get_thread_info tsk
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
-	add	r7, r8, #1			@ increment it
-	str	r7, [tsk, #TI_PREEMPT]
-#endif
-
-	irq_handler
-#ifdef CONFIG_PREEMPT
-	str	r8, [tsk, #TI_PREEMPT]		@ restore preempt count
 	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
 	teq	r8, #0				@ if preempt count != 0
 	movne	r0, #0				@ force flags to 0
 	tst	r0, #_TIF_NEED_RESCHED
 	blne	svc_preempt
 #endif
-	ldr	r4, [sp, #S_PSR]		@ irqs are already disabled
+
 #ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r4, #PSR_I_BIT
-	bleq	trace_hardirqs_on
+	@ The parent context IRQs must have been enabled to get here in
+	@ the first place, so there's no point checking the PSR I bit.
+	bl	trace_hardirqs_on
 #endif
-	svc_exit r4				@ return from exception
+	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__irq_svc)
 
@@ -251,7 +251,6 @@ __und_svc:
 #else
 	svc_entry
 #endif
-
 	@
 	@ call emulation code, which returns using r9 if it has emulated
 	@ the instruction, or the more conventional lr if we are to treat
@@ -260,15 +259,16 @@ __und_svc:
 	@  r0 - instruction
 	@
 #ifndef	CONFIG_THUMB2_KERNEL
-	ldr	r0, [r2, #-4]
+	ldr	r0, [r4, #-4]
 #else
-	ldrh	r0, [r2, #-2]			@ Thumb instruction at LR - 2
+	ldrh	r0, [r4, #-2]			@ Thumb instruction at LR - 2
 	and	r9, r0, #0xf800
 	cmp	r9, #0xe800			@ 32-bit instruction if xx >= 0
-	ldrhhs	r9, [r2]			@ bottom 16 bits
+	ldrhhs	r9, [r4]			@ bottom 16 bits
 	orrhs	r0, r9, r0, lsl #16
 #endif
 	adr	r9, BSYM(1f)
+	mov	r2, r4
 	bl	call_fpe
 
 	mov	r0, sp				@ struct pt_regs *regs
@@ -282,45 +282,35 @@ __und_svc:
 	@
 	@ restore SPSR and restart the instruction
 	@
-	ldr	r2, [sp, #S_PSR]		@ Get SVC cpsr
-	svc_exit r2				@ return from exception
+	ldr	r5, [sp, #S_PSR]		@ Get SVC cpsr
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	r5, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	r5, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__und_svc)
 
 	.align	5
 __pabt_svc:
 	svc_entry
-
-	@
-	@ re-enable interrupts if appropriate
-	@
-	mrs	r9, cpsr
-	tst	r3, #PSR_I_BIT
-	biceq	r9, r9, #PSR_I_BIT
-
-	mov	r0, r2			@ pass address of aborted instruction.
-#ifdef MULTI_PABORT
-	ldr	r4, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [r4, #PROCESSOR_PABT_FUNC]
-#else
-	bl	CPU_PABORT_HANDLER
-#endif
-	debug_entry r1
-	msr	cpsr_c, r9			@ Maybe enable interrupts
 	mov	r2, sp				@ regs
-	bl	do_PrefetchAbort		@ call abort handler
+	pabt_helper
 
 	@
 	@ IRQs off again before pulling preserved data off the stack
 	@
 	disable_irq_notrace
 
-	@
-	@ restore SPSR and restart the instruction
-	@
-	ldr	r2, [sp, #S_PSR]
-	svc_exit r2				@ return from exception
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	r5, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	r5, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__pabt_svc)
 
@@ -351,23 +341,23 @@ ENDPROC(__pabt_svc)
  ARM(	stmib	sp, {r1 - r12}	)
  THUMB(	stmia	sp, {r0 - r12}	)
 
-	ldmia	r0, {r1 - r3}
+	ldmia	r0, {r3 - r5}
 	add	r0, sp, #S_PC		@ here for interlock avoidance
-	mov	r4, #-1			@  ""  ""     ""        ""
+	mov	r6, #-1			@  ""  ""     ""        ""
 
-	str	r1, [sp]		@ save the "real" r0 copied
+	str	r3, [sp]		@ save the "real" r0 copied
 					@ from the exception stack
 
 	@
 	@ We are now ready to fill in the remaining blanks on the stack:
 	@
-	@  r2 - lr_<exception>, already fixed up for correct return/restart
-	@  r3 - spsr_<exception>
-	@  r4 - orig_r0 (see pt_regs definition in ptrace.h)
+	@  r4 - lr_<exception>, already fixed up for correct return/restart
+	@  r5 - spsr_<exception>
+	@  r6 - orig_r0 (see pt_regs definition in ptrace.h)
 	@
 	@ Also, separately save sp_usr and lr_usr
 	@
-	stmia	r0, {r2 - r4}
+	stmia	r0, {r4 - r6}
  ARM(	stmdb	r0, {sp, lr}^			)
  THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
@@ -380,10 +370,14 @@ ENDPROC(__pabt_svc)
 	@ Clear FP to mark the first stack frame
 	@
 	zero_fp
+
+#ifdef CONFIG_IRQSOFF_TRACER
+	bl	trace_hardirqs_off
+#endif
 	.endm
 
 	.macro	kuser_cmpxchg_check
-#if __LINUX_ARM_ARCH__ < 6 && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+#if !defined(CONFIG_CPU_32v6K) && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
 #ifndef CONFIG_MMU
 #warning "NPTL on non MMU needs fixing"
 #else
@@ -391,8 +385,8 @@ ENDPROC(__pabt_svc)
 	@ if it was interrupted in a critical region.  Here we
 	@ perform a quick test inline since it should be false
 	@ 99.9999% of the time.  The rest is done out of line.
-	cmp	r2, #TASK_SIZE
-	blhs	kuser_cmpxchg_fixup
+	cmp	r4, #TASK_SIZE
+	blhs	kuser_cmpxchg64_fixup
 #endif
 #endif
 	.endm
@@ -401,32 +395,9 @@ ENDPROC(__pabt_svc)
 __dabt_usr:
 	usr_entry
 	kuser_cmpxchg_check
-
-	@
-	@ Call the processor-specific abort handler:
-	@
-	@  r2 - aborted context pc
-	@  r3 - aborted context cpsr
-	@
-	@ The abort handler must return the aborted address in r0, and
-	@ the fault status register in r1.
-	@
-#ifdef MULTI_DABORT
-	ldr	r4, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [r4, #PROCESSOR_DABT_FUNC]
-#else
-	bl	CPU_DABORT_HANDLER
-#endif
-
-	@
-	@ IRQs on, then call the main handler
-	@
-	debug_entry r1
-	enable_irq
 	mov	r2, sp
-	adr	lr, BSYM(ret_from_exception)
-	b	do_DataAbort
+	dabt_helper
+	b	ret_from_exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_usr)
 
@@ -434,28 +405,8 @@ ENDPROC(__dabt_usr)
 __irq_usr:
 	usr_entry
 	kuser_cmpxchg_check
-
-#ifdef CONFIG_IRQSOFF_TRACER
-	bl	trace_hardirqs_off
-#endif
-
-	get_thread_info tsk
-#ifdef CONFIG_PREEMPT
-	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
-	add	r7, r8, #1			@ increment it
-	str	r7, [tsk, #TI_PREEMPT]
-#endif
-
 	irq_handler
-#ifdef CONFIG_PREEMPT
-	ldr	r0, [tsk, #TI_PREEMPT]
-	str	r8, [tsk, #TI_PREEMPT]
-	teq	r0, r7
- ARM(	strne	r0, [r0, -r0]	)
- THUMB(	movne	r0, #0		)
- THUMB(	strne	r0, [r0]	)
-#endif
-
+	get_thread_info tsk
 	mov	why, #0
 	b	ret_to_user_from_irq
  UNWIND(.fnend		)
@@ -467,6 +418,9 @@ ENDPROC(__irq_usr)
 __und_usr:
 	usr_entry
 
+	mov	r2, r4
+	mov	r3, r5
+
 	@
 	@ fall through to the emulation code, which returns using r9 if
 	@ it has emulated the instruction, or the more conventional lr
@@ -682,19 +636,8 @@ ENDPROC(__und_usr_unknown)
 	.align	5
 __pabt_usr:
 	usr_entry
-
-	mov	r0, r2			@ pass address of aborted instruction.
-#ifdef MULTI_PABORT
-	ldr	r4, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [r4, #PROCESSOR_PABT_FUNC]
-#else
-	bl	CPU_PABORT_HANDLER
-#endif
-	debug_entry r1
-	enable_irq				@ Enable interrupts
 	mov	r2, sp				@ regs
-	bl	do_PrefetchAbort		@ call abort handler
+	pabt_helper
  UNWIND(.fnend		)
 	/* fall through */
 /*
@@ -758,31 +701,12 @@ ENDPROC(__switch_to)
 /*
  * User helpers.
  *
- * These are segment of kernel provided user code reachable from user space
- * at a fixed address in kernel memory.  This is used to provide user space
- * with some operations which require kernel help because of unimplemented
- * native feature and/or instructions in many ARM CPUs. The idea is for
- * this code to be executed directly in user mode for best efficiency but
- * which is too intimate with the kernel counter part to be left to user
- * libraries.  In fact this code might even differ from one CPU to another
- * depending on the available  instruction set and restrictions like on
- * SMP systems.  In other words, the kernel reserves the right to change
- * this code as needed without warning. Only the entry points and their
- * results are guaranteed to be stable.
- *
  * Each segment is 32-byte aligned and will be moved to the top of the high
  * vector page.  New segments (if ever needed) must be added in front of
  * existing ones.  This mechanism should be used only for things that are
  * really small and justified, and not be abused freely.
  *
- * User space is expected to implement those things inline when optimizing
- * for a processor that has the necessary native support, but only if such
- * resulting binaries are already to be incompatible with earlier ARM
- * processors due to the use of unsupported instructions other than what
- * is provided here.  In other words don't make binaries unable to run on
- * earlier processors just for the sake of not using these kernel helpers
- * if your compiled code is not going to use the new instructions for other
- * purpose.
+ * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
  */
  THUMB(	.arm	)
 
@@ -799,96 +723,103 @@ ENDPROC(__switch_to)
 __kuser_helper_start:
 
 /*
- * Reference prototype:
- *
- *	void __kernel_memory_barrier(void)
- *
- * Input:
- *
- *	lr = return address
- *
- * Output:
- *
- *	none
- *
- * Clobbered:
- *
- *	none
- *
- * Definition and user space usage example:
- *
- *	typedef void (__kernel_dmb_t)(void);
- *	#define __kernel_dmb (*(__kernel_dmb_t *)0xffff0fa0)
- *
- * Apply any needed memory barrier to preserve consistency with data modified
- * manually and __kuser_cmpxchg usage.
- *
- * This could be used as follows:
- *
- * #define __kernel_dmb() \
- *         asm volatile ( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #95" \
- *	        : : : "r0", "lr","cc" )
+ * Due to the length of some sequences, __kuser_cmpxchg64 spans 2 regular
+ * kuser "slots", therefore 0xffff0f80 is not used as a valid entry point.
  */
 
-__kuser_memory_barrier:				@ 0xffff0fa0
+__kuser_cmpxchg64:				@ 0xffff0f60
+
+#if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+
+	/*
+	 * Poor you.  No fast solution possible...
+	 * The kernel itself must perform the operation.
+	 * A special ghost syscall is used for that (see traps.c).
+	 */
+	stmfd	sp!, {r7, lr}
+	ldr	r7, 1f			@ it's 20 bits
+	swi	__ARM_NR_cmpxchg64
+	ldmfd	sp!, {r7, pc}
+1:	.word	__ARM_NR_cmpxchg64
+
+#elif defined(CONFIG_CPU_32v6K)
+
+	stmfd	sp!, {r4, r5, r6, r7}
+	ldrd	r4, r5, [r0]			@ load old val
+	ldrd	r6, r7, [r1]			@ load new val
+	smp_dmb	arm
+1:	ldrexd	r0, r1, [r2]			@ load current val
+	eors	r3, r0, r4			@ compare with oldval (1)
+	eoreqs	r3, r1, r5			@ compare with oldval (2)
+	strexdeq r3, r6, r7, [r2]		@ store newval if eq
+	teqeq	r3, #1				@ success?
+	beq	1b				@ if no then retry
 	smp_dmb	arm
+	rsbs	r0, r3, #0			@ set returned val and C flag
+	ldmfd	sp!, {r4, r5, r6, r7}
+	bx	lr
+
+#elif !defined(CONFIG_SMP)
+
+#ifdef CONFIG_MMU
+
+	/*
+	 * The only thing that can break atomicity in this cmpxchg64
+	 * implementation is either an IRQ or a data abort exception
+	 * causing another process/thread to be scheduled in the middle of
+	 * the critical sequence.  The same strategy as for cmpxchg is used.
+	 */
+	stmfd	sp!, {r4, r5, r6, lr}
+	ldmia	r0, {r4, r5}			@ load old val
+	ldmia	r1, {r6, lr}			@ load new val
+1:	ldmia	r2, {r0, r1}			@ load current val
+	eors	r3, r0, r4			@ compare with oldval (1)
+	eoreqs	r3, r1, r5			@ compare with oldval (2)
+2:	stmeqia	r2, {r6, lr}			@ store newval if eq
+	rsbs	r0, r3, #0			@ set return val and C flag
+	ldmfd	sp!, {r4, r5, r6, pc}
+
+	.text
+kuser_cmpxchg64_fixup:
+	@ Called from kuser_cmpxchg_fixup.
+	@ r4 = address of interrupted insn (must be preserved).
+	@ sp = saved regs. r7 and r8 are clobbered.
+	@ 1b = first critical insn, 2b = last critical insn.
+	@ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b.
+	mov	r7, #0xffff0fff
+	sub	r7, r7, #(0xffff0fff - (0xffff0f60 + (1b - __kuser_cmpxchg64)))
+	subs	r8, r4, r7
+	rsbcss	r8, r8, #(2b - 1b)
+	strcs	r7, [sp, #S_PC]
+#if __LINUX_ARM_ARCH__ < 6
+	bcc	kuser_cmpxchg32_fixup
+#endif
+	mov	pc, lr
+	.previous
+
+#else
+#warning "NPTL on non MMU needs fixing"
+	mov	r0, #-1
+	adds	r0, r0, #0
 	usr_ret	lr
+#endif
+
+#else
+#error "incoherent kernel configuration"
+#endif
+
+	/* pad to next slot */
+	.rept	(16 - (. - __kuser_cmpxchg64)/4)
+	.word	0
+	.endr
 
 	.align	5
 
-/*
- * Reference prototype:
- *
- *	int __kernel_cmpxchg(int oldval, int newval, int *ptr)
- *
- * Input:
- *
- *	r0 = oldval
- *	r1 = newval
- *	r2 = ptr
- *	lr = return address
- *
- * Output:
- *
- *	r0 = returned value (zero or non-zero)
- *	C flag = set if r0 == 0, clear if r0 != 0
- *
- * Clobbered:
- *
- *	r3, ip, flags
- *
- * Definition and user space usage example:
- *
- *	typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr);
- *	#define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0)
- *
- * Atomically store newval in *ptr if *ptr is equal to oldval for user space.
- * Return zero if *ptr was changed or non-zero if no exchange happened.
- * The C flag is also set if *ptr was changed to allow for assembly
- * optimization in the calling code.
- *
- * Notes:
- *
- *    - This routine already includes memory barriers as needed.
- *
- * For example, a user space atomic_add implementation could look like this:
- *
- * #define atomic_add(ptr, val) \
- *	({ register unsigned int *__ptr asm("r2") = (ptr); \
- *	   register unsigned int __result asm("r1"); \
- *	   asm volatile ( \
- *	       "1: @ atomic_add\n\t" \
- *	       "ldr	r0, [r2]\n\t" \
- *	       "mov	r3, #0xffff0fff\n\t" \
- *	       "add	lr, pc, #4\n\t" \
- *	       "add	r1, r0, %2\n\t" \
- *	       "add	pc, r3, #(0xffff0fc0 - 0xffff0fff)\n\t" \
- *	       "bcc	1b" \
- *	       : "=&r" (__result) \
- *	       : "r" (__ptr), "rIL" (val) \
- *	       : "r0","r3","ip","lr","cc","memory" ); \
- *	   __result; })
- */
+__kuser_memory_barrier:				@ 0xffff0fa0
+	smp_dmb	arm
+	usr_ret	lr
+
+	.align	5
 
 __kuser_cmpxchg:				@ 0xffff0fc0
 
@@ -925,15 +856,15 @@ __kuser_cmpxchg:				@ 0xffff0fc0
 	usr_ret	lr
 
 	.text
-kuser_cmpxchg_fixup:
+kuser_cmpxchg32_fixup:
 	@ Called from kuser_cmpxchg_check macro.
-	@ r2 = address of interrupted insn (must be preserved).
+	@ r4 = address of interrupted insn (must be preserved).
 	@ sp = saved regs. r7 and r8 are clobbered.
 	@ 1b = first critical insn, 2b = last critical insn.
-	@ If r2 >= 1b and r2 <= 2b then saved pc_usr is set to 1b.
+	@ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b.
 	mov	r7, #0xffff0fff
 	sub	r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg)))
-	subs	r8, r2, r7
+	subs	r8, r4, r7
 	rsbcss	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
 	mov	pc, lr
@@ -963,39 +894,6 @@ kuser_cmpxchg_fixup:
 
 	.align	5
 
-/*
- * Reference prototype:
- *
- *	int __kernel_get_tls(void)
- *
- * Input:
- *
- *	lr = return address
- *
- * Output:
- *
- *	r0 = TLS value
- *
- * Clobbered:
- *
- *	none
- *
- * Definition and user space usage example:
- *
- *	typedef int (__kernel_get_tls_t)(void);
- *	#define __kernel_get_tls (*(__kernel_get_tls_t *)0xffff0fe0)
- *
- * Get the TLS value as previously set via the __ARM_NR_set_tls syscall.
- *
- * This could be used as follows:
- *
- * #define __kernel_get_tls() \
- *	({ register unsigned int __val asm("r0"); \
- *         asm( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #31" \
- *	        : "=r" (__val) : : "lr","cc" ); \
- *	   __val; })
- */
-
 __kuser_get_tls:				@ 0xffff0fe0
 	ldr	r0, [pc, #(16 - 8)]	@ read TLS, set in kuser_get_tls_init
 	usr_ret	lr
@@ -1004,19 +902,6 @@ __kuser_get_tls:				@ 0xffff0fe0
 	.word	0			@ 0xffff0ff0 software TLS value, then
 	.endr				@ pad up to __kuser_helper_version
 
-/*
- * Reference declaration:
- *
- *	extern unsigned int __kernel_helper_version;
- *
- * Definition and user space usage example:
- *
- *	#define __kernel_helper_version (*(unsigned int *)0xffff0ffc)
- *
- * User space may read this to determine the curent number of helpers
- * available.
- */
-
 __kuser_helper_version:				@ 0xffff0ffc
 	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)
 

arch/arm/kernel/entry-header.S

@@ -121,15 +121,13 @@
 	.endm
 #else	/* CONFIG_THUMB2_KERNEL */
 	.macro	svc_exit, rpsr
+	ldr	lr, [sp, #S_SP]			@ top of the stack
+	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
 	clrex					@ clear the exclusive monitor
-	ldr	r0, [sp, #S_SP]			@ top of the stack
-	ldr	r1, [sp, #S_PC]			@ return address
-	tst	r0, #4				@ orig stack 8-byte aligned?
-	stmdb	r0, {r1, \rpsr}			@ rfe context
+	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
 	ldmia	sp, {r0 - r12}
-	ldr	lr, [sp, #S_LR]
-	addeq	sp, sp, #S_FRAME_SIZE - 8	@ aligned
-	addne	sp, sp, #S_FRAME_SIZE - 4	@ not aligned
+	mov	sp, lr
+	ldr	lr, [sp], #4
 	rfeia	sp!
 	.endm
 
@@ -165,25 +163,6 @@
 	.endm
 #endif	/* !CONFIG_THUMB2_KERNEL */
 
-	@
-	@ Debug exceptions are taken as prefetch or data aborts.
-	@ We must disable preemption during the handler so that
-	@ we can access the debug registers safely.
-	@
-	.macro	debug_entry, fsr
-#if defined(CONFIG_HAVE_HW_BREAKPOINT) && defined(CONFIG_PREEMPT)
-	ldr	r4, =0x40f		@ mask out fsr.fs
-	and	r5, r4, \fsr
-	cmp	r5, #2			@ debug exception
-	bne	1f
-	get_thread_info r10
-	ldr	r6, [r10, #TI_PREEMPT]	@ get preempt count
-	add	r11, r6, #1		@ increment it
-	str	r11, [r10, #TI_PREEMPT]
-1:
-#endif
-	.endm
-
 /*
  * These are the registers used in the syscall handler, and allow us to
  * have in theory up to 7 arguments to a function - r0 to r6.

arch/arm/kernel/head-nommu.S

@@ -32,8 +32,16 @@
  * numbers for r1.
  *
  */
+	.arm
+
 	__HEAD
 ENTRY(stext)
+
+ THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
+ THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
+ THUMB(	.thumb			)	@ switch to Thumb now.
+ THUMB(1:			)
+
 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
 #ifndef CONFIG_CPU_CP15

arch/arm/kernel/head.S

@@ -71,8 +71,16 @@
  * crap here - that's what the boot loader (or in extreme, well justified
  * circumstances, zImage) is for.
  */
+	.arm
+
 	__HEAD
 ENTRY(stext)
+
+ THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
+ THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
+ THUMB(	.thumb			)	@ switch to Thumb now.
+ THUMB(1:			)
+
 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
 	mrc	p15, 0, r9, c0, c0		@ get processor id

arch/arm/kernel/hw_breakpoint.c

@@ -796,7 +796,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs)
 
 /*
  * Called from either the Data Abort Handler [watchpoint] or the
- * Prefetch Abort Handler [breakpoint] with preemption disabled.
+ * Prefetch Abort Handler [breakpoint] with interrupts disabled.
  */
 static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 				 struct pt_regs *regs)
@@ -804,8 +804,10 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 	int ret = 0;
 	u32 dscr;
 
-	/* We must be called with preemption disabled. */
-	WARN_ON(preemptible());
+	preempt_disable();
+
+	if (interrupts_enabled(regs))
+		local_irq_enable();
 
 	/* We only handle watchpoints and hardware breakpoints. */
 	ARM_DBG_READ(c1, 0, dscr);
@@ -824,10 +826,6 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 		ret = 1; /* Unhandled fault. */
 	}
 
-	/*
-	 * Re-enable preemption after it was disabled in the
-	 * low-level exception handling code.
-	 */
 	preempt_enable();
 
 	return ret;

arch/arm/kernel/irq.c

@@ -131,54 +131,63 @@ int __init arch_probe_nr_irqs(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static bool migrate_one_irq(struct irq_data *d)
+static bool migrate_one_irq(struct irq_desc *desc)
 {
-	unsigned int cpu = cpumask_any_and(d->affinity, cpu_online_mask);
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+	const struct cpumask *affinity = d->affinity;
+	struct irq_chip *c;
 	bool ret = false;
 
-	if (cpu >= nr_cpu_ids) {
-		cpu = cpumask_any(cpu_online_mask);
+	/*
+	 * If this is a per-CPU interrupt, or the affinity does not
+	 * include this CPU, then we have nothing to do.
+	 */
+	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
+		return false;
+
+	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+		affinity = cpu_online_mask;
 		ret = true;
 	}
 
-	pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", d->irq, d->node, cpu);
-
-	d->chip->irq_set_affinity(d, cpumask_of(cpu), true);
+	c = irq_data_get_irq_chip(d);
+	if (c->irq_set_affinity)
+		c->irq_set_affinity(d, affinity, true);
+	else
+		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
 
 	return ret;
 }
 
 /*
- * The CPU has been marked offline.  Migrate IRQs off this CPU.  If
- * the affinity settings do not allow other CPUs, force them onto any
+ * The current CPU has been marked offline.  Migrate IRQs off this CPU.
+ * If the affinity settings do not allow other CPUs, force them onto any
  * available CPU.
+ *
+ * Note: we must iterate over all IRQs, whether they have an attached
+ * action structure or not, as we need to get chained interrupts too.
  */
 void migrate_irqs(void)
 {
-	unsigned int i, cpu = smp_processor_id();
+	unsigned int i;
 	struct irq_desc *desc;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
 	for_each_irq_desc(i, desc) {
-		struct irq_data *d = &desc->irq_data;
 		bool affinity_broken = false;
 
-		raw_spin_lock(&desc->lock);
-		do {
-			if (desc->action == NULL)
-				break;
-
-			if (d->node != cpu)
-				break;
+		if (!desc)
+			continue;
 
-			affinity_broken = migrate_one_irq(d);
-		} while (0);
+		raw_spin_lock(&desc->lock);
+		affinity_broken = migrate_one_irq(desc);
 		raw_spin_unlock(&desc->lock);
 
 		if (affinity_broken && printk_ratelimit())
-			pr_warning("IRQ%u no longer affine to CPU%u\n", i, cpu);
+			pr_warning("IRQ%u no longer affine to CPU%u\n", i,
+				smp_processor_id());
 	}
 
 	local_irq_restore(flags);

arch/arm/kernel/kprobes-common.c

+/*
+ * arch/arm/kernel/kprobes-common.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/kprobes.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)
+{
+	kprobe_opcode_t insn = p->opcode;
+	int rn = (insn >> 16) & 0xf;
+	int lbit = insn & (1 << 20);
+	int wbit = insn & (1 << 21);
+	int ubit = insn & (1 << 23);
+	int pbit = insn & (1 << 24);
+	long *addr = (long *)regs->uregs[rn];
+	int reg_bit_vector;
+	int reg_count;
+
+	reg_count = 0;
+	reg_bit_vector = insn & 0xffff;
+	while (reg_bit_vector) {
+		reg_bit_vector &= (reg_bit_vector - 1);
+		++reg_count;
+	}
+
+	if (!ubit)
+		addr -= reg_count;
+	addr += (!pbit == !ubit);
+
+	reg_bit_vector = insn & 0xffff;
+	while (reg_bit_vector) {
+		int reg = __ffs(reg_bit_vector);
+		reg_bit_vector &= (reg_bit_vector - 1);
+		if (lbit)
+			regs->uregs[reg] = *addr++;
+		else
+			*addr++ = regs->uregs[reg];
+	}
+
+	if (wbit) {
+		if (!ubit)
+			addr -= reg_count;
+		addr -= (!pbit == !ubit);
+		regs->uregs[rn] = (long)addr;
+	}
+}
+
+static void __kprobes simulate_stm1_pc(struct kprobe *p, struct pt_regs *regs)
+{
+	regs->ARM_pc = (long)p->addr + str_pc_offset;
+	simulate_ldm1stm1(p, regs);
+	regs->ARM_pc = (long)p->addr + 4;
+}
+
+static void __kprobes simulate_ldm1_pc(struct kprobe *p, struct pt_regs *regs)
+{
+	simulate_ldm1stm1(p, regs);
+	load_write_pc(regs->ARM_pc, regs);
+}
+
+static void __kprobes
+emulate_generic_r0_12_noflags(struct kprobe *p, struct pt_regs *regs)
+{
+	register void *rregs asm("r1") = regs;
+	register void *rfn asm("lr") = p->ainsn.insn_fn;
+
+	__asm__ __volatile__ (
+		"stmdb	sp!, {%[regs], r11}	\n\t"
+		"ldmia	%[regs], {r0-r12}	\n\t"
+#if __LINUX_ARM_ARCH__ >= 6
+		"blx	%[fn]			\n\t"
+#else
+		"str	%[fn], [sp, #-4]!	\n\t"
+		"adr	lr, 1f			\n\t"
+		"ldr	pc, [sp], #4		\n\t"
+		"1:				\n\t"
+#endif
+		"ldr	lr, [sp], #4		\n\t" /* lr = regs */
+		"stmia	lr, {r0-r12}		\n\t"
+		"ldr	r11, [sp], #4		\n\t"
+		: [regs] "=r" (rregs), [fn] "=r" (rfn)
+		: "0" (rregs), "1" (rfn)
+		: "r0", "r2", "r3", "r4", "r5", "r6", "r7",
+		  "r8", "r9", "r10", "r12", "memory", "cc"
+		);
+}
+
+static void __kprobes
+emulate_generic_r2_14_noflags(struct kprobe *p, struct pt_regs *regs)
+{
+	emulate_generic_r0_12_noflags(p, (struct pt_regs *)(regs->uregs+2));
+}
+
+static void __kprobes
+emulate_ldm_r3_15(struct kprobe *p, struct pt_regs *regs)
+{
+	emulate_generic_r0_12_noflags(p, (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)
+{
+	kprobe_insn_handler_t *handler = 0;
+	unsigned reglist = insn & 0xffff;
+	int is_ldm = insn & 0x100000;
+	int rn = (insn >> 16) & 0xf;
+
+	if (rn <= 12 && (reglist & 0xe000) == 0) {
+		/* Instruction only uses registers in the range R0..R12 */
+		handler = emulate_generic_r0_12_noflags;
+
+	} else if (rn >= 2 && (reglist & 0x8003) == 0) {
+		/* Instruction only uses registers in the range R2..R14 */
+		rn -= 2;
+		reglist >>= 2;
+		handler = emulate_generic_r2_14_noflags;
+
+	} else if (rn >= 3 && (reglist & 0x0007) == 0) {
+		/* Instruction only uses registers in the range R3..R15 */
+		if (is_ldm && (reglist & 0x8000)) {
+			rn -= 3;
+			reglist >>= 3;
+			handler = emulate_ldm_r3_15;
+		}
+	}
+
+	if (handler) {
+		/* We can emulate the instruction in (possibly) modified form */
+		asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist;
+		asi->insn_handler = handler;
+		return INSN_GOOD;
+	}
+
+	/* Fallback to slower simulation... */
+	if (reglist & 0x8000)
+		handler = is_ldm ? simulate_ldm1_pc : simulate_stm1_pc;
+	else
+		handler = simulate_ldm1stm1;
+	asi->insn_handler = handler;
+	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.c

@@ -28,14 +28,16 @@
 #include <asm/traps.h>
 #include <asm/cacheflush.h>
 
+#include "kprobes.h"
+
 #define MIN_STACK_SIZE(addr) 				\
 	min((unsigned long)MAX_STACK_SIZE,		\
 	    (unsigned long)current_thread_info() + THREAD_START_SP - (addr))
 
-#define flush_insns(addr, cnt) 				\
+#define flush_insns(addr, size)				\
 	flush_icache_range((unsigned long)(addr),	\
 			   (unsigned long)(addr) +	\
-			   sizeof(kprobe_opcode_t) * (cnt))
+			   (size))
 
 /* Used as a marker in ARM_pc to note when we're in a jprobe. */
 #define JPROBE_MAGIC_ADDR		0xffffffff
@@ -49,16 +51,35 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	kprobe_opcode_t insn;
 	kprobe_opcode_t tmp_insn[MAX_INSN_SIZE];
 	unsigned long addr = (unsigned long)p->addr;
+	bool thumb;
+	kprobe_decode_insn_t *decode_insn;
 	int is;
 
-	if (addr & 0x3 || in_exception_text(addr))
+	if (in_exception_text(addr))
 		return -EINVAL;
 
+#ifdef CONFIG_THUMB2_KERNEL
+	thumb = true;
+	addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */
+	insn = ((u16 *)addr)[0];
+	if (is_wide_instruction(insn)) {
+		insn <<= 16;
+		insn |= ((u16 *)addr)[1];
+		decode_insn = thumb32_kprobe_decode_insn;
+	} else
+		decode_insn = thumb16_kprobe_decode_insn;
+#else /* !CONFIG_THUMB2_KERNEL */
+	thumb = false;
+	if (addr & 0x3)
+		return -EINVAL;
 	insn = *p->addr;
+	decode_insn = arm_kprobe_decode_insn;
+#endif
+
 	p->opcode = insn;
 	p->ainsn.insn = tmp_insn;
 
-	switch (arm_kprobe_decode_insn(insn, &p->ainsn)) {
+	switch ((*decode_insn)(insn, &p->ainsn)) {
 	case INSN_REJECTED:	/* not supported */
 		return -EINVAL;
 
@@ -68,7 +89,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 			return -ENOMEM;
 		for (is = 0; is < MAX_INSN_SIZE; ++is)
 			p->ainsn.insn[is] = tmp_insn[is];
-		flush_insns(p->ainsn.insn, MAX_INSN_SIZE);
+		flush_insns(p->ainsn.insn,
+				sizeof(p->ainsn.insn[0]) * MAX_INSN_SIZE);
+		p->ainsn.insn_fn = (kprobe_insn_fn_t *)
+					((uintptr_t)p->ainsn.insn | thumb);
 		break;
 
 	case INSN_GOOD_NO_SLOT:	/* instruction doesn't need insn slot */
@@ -79,24 +103,88 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	return 0;
 }
 
+#ifdef CONFIG_THUMB2_KERNEL
+
+/*
+ * For a 32-bit Thumb breakpoint spanning two memory words we need to take
+ * special precautions to insert the breakpoint atomically, especially on SMP
+ * systems. This is achieved by calling this arming function using stop_machine.
+ */
+static int __kprobes set_t32_breakpoint(void *addr)
+{
+	((u16 *)addr)[0] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION >> 16;
+	((u16 *)addr)[1] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION & 0xffff;
+	flush_insns(addr, 2*sizeof(u16));
+	return 0;
+}
+
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+	uintptr_t addr = (uintptr_t)p->addr & ~1; /* Remove any Thumb flag */
+
+	if (!is_wide_instruction(p->opcode)) {
+		*(u16 *)addr = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
+		flush_insns(addr, sizeof(u16));
+	} else if (addr & 2) {
+		/* A 32-bit instruction spanning two words needs special care */
+		stop_machine(set_t32_breakpoint, (void *)addr, &cpu_online_map);
+	} else {
+		/* Word aligned 32-bit instruction can be written atomically */
+		u32 bkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
+#ifndef __ARMEB__ /* Swap halfwords for little-endian */
+		bkp = (bkp >> 16) | (bkp << 16);
+#endif
+		*(u32 *)addr = bkp;
+		flush_insns(addr, sizeof(u32));
+	}
+}
+
+#else /* !CONFIG_THUMB2_KERNEL */
+
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-	*p->addr = KPROBE_BREAKPOINT_INSTRUCTION;
-	flush_insns(p->addr, 1);
+	kprobe_opcode_t insn = p->opcode;
+	kprobe_opcode_t brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
+	if (insn >= 0xe0000000)
+		brkp |= 0xe0000000;  /* Unconditional instruction */
+	else
+		brkp |= insn & 0xf0000000;  /* Copy condition from insn */
+	*p->addr = brkp;
+	flush_insns(p->addr, sizeof(p->addr[0]));
 }
 
+#endif /* !CONFIG_THUMB2_KERNEL */
+
 /*
  * The actual disarming is done here on each CPU and synchronized using
  * stop_machine. This synchronization is necessary on SMP to avoid removing
  * a probe between the moment the 'Undefined Instruction' exception is raised
  * and the moment the exception handler reads the faulting instruction from
- * memory.
+ * memory. It is also needed to atomically set the two half-words of a 32-bit
+ * Thumb breakpoint.
  */
 int __kprobes __arch_disarm_kprobe(void *p)
 {
 	struct kprobe *kp = p;
+#ifdef CONFIG_THUMB2_KERNEL
+	u16 *addr = (u16 *)((uintptr_t)kp->addr & ~1);
+	kprobe_opcode_t insn = kp->opcode;
+	unsigned int len;
+
+	if (is_wide_instruction(insn)) {
+		((u16 *)addr)[0] = insn>>16;
+		((u16 *)addr)[1] = insn;
+		len = 2*sizeof(u16);
+	} else {
+		((u16 *)addr)[0] = insn;
+		len = sizeof(u16);
+	}
+	flush_insns(addr, len);
+
+#else /* !CONFIG_THUMB2_KERNEL */
 	*kp->addr = kp->opcode;
-	flush_insns(kp->addr, 1);
+	flush_insns(kp->addr, sizeof(kp->addr[0]));
+#endif
 	return 0;
 }
 
@@ -130,12 +218,24 @@ static void __kprobes set_current_kprobe(struct kprobe *p)
 	__get_cpu_var(current_kprobe) = p;
 }
 
-static void __kprobes singlestep(struct kprobe *p, struct pt_regs *regs,
-				 struct kprobe_ctlblk *kcb)
+static void __kprobes
+singlestep_skip(struct kprobe *p, struct pt_regs *regs)
 {
+#ifdef CONFIG_THUMB2_KERNEL
+	regs->ARM_cpsr = it_advance(regs->ARM_cpsr);
+	if (is_wide_instruction(p->opcode))
+		regs->ARM_pc += 4;
+	else
+		regs->ARM_pc += 2;
+#else
 	regs->ARM_pc += 4;
-	if (p->ainsn.insn_check_cc(regs->ARM_cpsr))
-		p->ainsn.insn_handler(p, regs);
+#endif
+}
+
+static inline void __kprobes
+singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
+{
+	p->ainsn.insn_singlestep(p, regs);
 }
 
 /*
@@ -149,11 +249,23 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 {
 	struct kprobe *p, *cur;
 	struct kprobe_ctlblk *kcb;
-	kprobe_opcode_t	*addr = (kprobe_opcode_t *)regs->ARM_pc;
 
 	kcb = get_kprobe_ctlblk();
 	cur = kprobe_running();
-	p = get_kprobe(addr);
+
+#ifdef CONFIG_THUMB2_KERNEL
+	/*
+	 * First look for a probe which was registered using an address with
+	 * bit 0 set, this is the usual situation for pointers to Thumb code.
+	 * If not found, fallback to looking for one with bit 0 clear.
+	 */
+	p = get_kprobe((kprobe_opcode_t *)(regs->ARM_pc | 1));
+	if (!p)
+		p = get_kprobe((kprobe_opcode_t *)regs->ARM_pc);
+
+#else /* ! CONFIG_THUMB2_KERNEL */
+	p = get_kprobe((kprobe_opcode_t *)regs->ARM_pc);
+#endif
 
 	if (p) {
 		if (cur) {
@@ -173,7 +285,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				/* impossible cases */
 				BUG();
 			}
-		} else {
+		} else if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+			/* Probe hit and conditional execution check ok. */
 			set_current_kprobe(p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
@@ -193,6 +306,13 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				}
 				reset_current_kprobe();
 			}
+		} else {
+			/*
+			 * Probe hit but conditional execution check failed,
+			 * so just skip the instruction and continue as if
+			 * nothing had happened.
+			 */
+			singlestep_skip(p, regs);
 		}
 	} else if (cur) {
 		/* We probably hit a jprobe.  Call its break handler. */
@@ -300,7 +420,11 @@ void __naked __kprobes kretprobe_trampoline(void)
 		"bl	trampoline_handler	\n\t"
 		"mov	lr, r0			\n\t"
 		"ldmia	sp!, {r0 - r11}		\n\t"
+#ifdef CONFIG_THUMB2_KERNEL
+		"bx	lr			\n\t"
+#else
 		"mov	pc, lr			\n\t"
+#endif
 		: : : "memory");
 }
 
@@ -378,11 +502,22 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	long sp_addr = regs->ARM_sp;
+	long cpsr;
 
 	kcb->jprobe_saved_regs = *regs;
 	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
 	regs->ARM_pc = (long)jp->entry;
-	regs->ARM_cpsr |= PSR_I_BIT;
+
+	cpsr = regs->ARM_cpsr | PSR_I_BIT;
+#ifdef CONFIG_THUMB2_KERNEL
+	/* Set correct Thumb state in cpsr */
+	if (regs->ARM_pc & 1)
+		cpsr |= PSR_T_BIT;
+	else
+		cpsr &= ~PSR_T_BIT;
+#endif
+	regs->ARM_cpsr = cpsr;
+
 	preempt_disable();
 	return 1;
 }
@@ -404,7 +539,12 @@ void __kprobes jprobe_return(void)
 		 * This is to prevent any simulated instruction from writing
 		 * over the regs when they are accessing the stack.
 		 */
+#ifdef CONFIG_THUMB2_KERNEL
+		"sub    r0, %0, %1		\n\t"
+		"mov    sp, r0			\n\t"
+#else
 		"sub    sp, %0, %1		\n\t"
+#endif
 		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
 		"str    %0, [sp, %2]		\n\t"
 		"str    r0, [sp, %3]		\n\t"
@@ -415,15 +555,28 @@ void __kprobes jprobe_return(void)
 		 * Return to the context saved by setjmp_pre_handler
 		 * and restored by longjmp_break_handler.
 		 */
+#ifdef CONFIG_THUMB2_KERNEL
+		"ldr	lr, [sp, %2]		\n\t" /* lr = saved sp */
+		"ldrd	r0, r1, [sp, %5]	\n\t" /* r0,r1 = saved lr,pc */
+		"ldr	r2, [sp, %4]		\n\t" /* r2 = saved psr */
+		"stmdb	lr!, {r0, r1, r2}	\n\t" /* push saved lr and */
+						      /* rfe context */
+		"ldmia	sp, {r0 - r12}		\n\t"
+		"mov	sp, lr			\n\t"
+		"ldr	lr, [sp], #4		\n\t"
+		"rfeia	sp!			\n\t"
+#else
 		"ldr	r0, [sp, %4]		\n\t"
 		"msr	cpsr_cxsf, r0		\n\t"
 		"ldmia	sp, {r0 - pc}		\n\t"
+#endif
 		:
 		: "r" (kcb->jprobe_saved_regs.ARM_sp),
 		  "I" (sizeof(struct pt_regs) * 2),
 		  "J" (offsetof(struct pt_regs, ARM_sp)),
 		  "J" (offsetof(struct pt_regs, ARM_pc)),
-		  "J" (offsetof(struct pt_regs, ARM_cpsr))
+		  "J" (offsetof(struct pt_regs, ARM_cpsr)),
+		  "J" (offsetof(struct pt_regs, ARM_lr))
 		: "memory", "cc");
 }
 
@@ -460,17 +613,44 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p)
 	return 0;
 }
 
-static struct undef_hook kprobes_break_hook = {
+#ifdef CONFIG_THUMB2_KERNEL
+
+static struct undef_hook kprobes_thumb16_break_hook = {
+	.instr_mask	= 0xffff,
+	.instr_val	= KPROBE_THUMB16_BREAKPOINT_INSTRUCTION,
+	.cpsr_mask	= MODE_MASK,
+	.cpsr_val	= SVC_MODE,
+	.fn		= kprobe_trap_handler,
+};
+
+static struct undef_hook kprobes_thumb32_break_hook = {
 	.instr_mask	= 0xffffffff,
-	.instr_val	= KPROBE_BREAKPOINT_INSTRUCTION,
+	.instr_val	= KPROBE_THUMB32_BREAKPOINT_INSTRUCTION,
 	.cpsr_mask	= MODE_MASK,
 	.cpsr_val	= SVC_MODE,
 	.fn		= kprobe_trap_handler,
 };
 
+#else  /* !CONFIG_THUMB2_KERNEL */
+
+static struct undef_hook kprobes_arm_break_hook = {
+	.instr_mask	= 0x0fffffff,
+	.instr_val	= KPROBE_ARM_BREAKPOINT_INSTRUCTION,
+	.cpsr_mask	= MODE_MASK,
+	.cpsr_val	= SVC_MODE,
+	.fn		= kprobe_trap_handler,
+};
+
+#endif /* !CONFIG_THUMB2_KERNEL */
+
 int __init arch_init_kprobes()
 {
 	arm_kprobe_decode_init();
-	register_undef_hook(&kprobes_break_hook);
+#ifdef CONFIG_THUMB2_KERNEL
+	register_undef_hook(&kprobes_thumb16_break_hook);
+	register_undef_hook(&kprobes_thumb32_break_hook);
+#else
+	register_undef_hook(&kprobes_arm_break_hook);
+#endif
 	return 0;
 }

arch/arm/kernel/perf_event.c

@@ -435,7 +435,7 @@ armpmu_reserve_hardware(void)
 			if (irq >= 0)
 				free_irq(irq, NULL);
 		}
-		release_pmu(pmu_device);
+		release_pmu(ARM_PMU_DEVICE_CPU);
 		pmu_device = NULL;
 	}
 
@@ -454,7 +454,7 @@ armpmu_release_hardware(void)
 	}
 	armpmu->stop();
 
-	release_pmu(pmu_device);
+	release_pmu(ARM_PMU_DEVICE_CPU);
 	pmu_device = NULL;
 }
 
@@ -662,6 +662,12 @@ init_hw_perf_events(void)
 		case 0xC090:	/* Cortex-A9 */
 			armpmu = armv7_a9_pmu_init();
 			break;
+		case 0xC050:	/* Cortex-A5 */
+			armpmu = armv7_a5_pmu_init();
+			break;
+		case 0xC0F0:	/* Cortex-A15 */
+			armpmu = armv7_a15_pmu_init();
+			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (0x69 == implementor) {

arch/arm/kernel/ptrace.c

@@ -228,34 +228,12 @@ static struct undef_hook thumb_break_hook = {
 	.fn		= break_trap,
 };
 
-static int thumb2_break_trap(struct pt_regs *regs, unsigned int instr)
-{
-	unsigned int instr2;
-	void __user *pc;
-
-	/* Check the second half of the instruction.  */
-	pc = (void __user *)(instruction_pointer(regs) + 2);
-
-	if (processor_mode(regs) == SVC_MODE) {
-		instr2 = *(u16 *) pc;
-	} else {
-		get_user(instr2, (u16 __user *)pc);
-	}
-
-	if (instr2 == 0xa000) {
-		ptrace_break(current, regs);
-		return 0;
-	} else {
-		return 1;
-	}
-}
-
 static struct undef_hook thumb2_break_hook = {
-	.instr_mask	= 0xffff,
-	.instr_val	= 0xf7f0,
+	.instr_mask	= 0xffffffff,
+	.instr_val	= 0xf7f0a000,
 	.cpsr_mask	= PSR_T_BIT,
 	.cpsr_val	= PSR_T_BIT,
-	.fn		= thumb2_break_trap,
+	.fn		= break_trap,
 };
 
 static int __init ptrace_break_init(void)

arch/arm/mach-bcmring/include/mach/entry-macro.S

@@ -80,7 +80,3 @@
 
 		.macro  arch_ret_to_user, tmp1, tmp2
 		.endm
-
-		.macro	irq_prio_table
-		.endm
-