Merge branch 'dt/gic' into next/dt

Conflicts:
	arch/arm/include/asm/localtimer.h
	arch/arm/mach-msm/board-msm8x60.c
	arch/arm/mach-omap2/board-generic.c

Documentation/devicetree/bindings/arm/gic.txt

+* ARM Generic Interrupt Controller
+
+ARM SMP cores are often associated with a GIC, providing per processor
+interrupts (PPI), shared processor interrupts (SPI) and software
+generated interrupts (SGI).
+
+Primary GIC is attached directly to the CPU and typically has PPIs and SGIs.
+Secondary GICs are cascaded into the upward interrupt controller and do not
+have PPIs or SGIs.
+
+Main node required properties:
+
+- compatible : should be one of:
+	"arm,cortex-a9-gic"
+	"arm,arm11mp-gic"
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt source.  The type shall be a <u32> and the value shall be 3.
+
+  The 1st cell is the interrupt type; 0 for SPI interrupts, 1 for PPI
+  interrupts.
+
+  The 2nd cell contains the interrupt number for the interrupt type.
+  SPI interrupts are in the range [0-987].  PPI interrupts are in the
+  range [0-15].
+
+  The 3rd cell is the flags, encoded as follows:
+	bits[3:0] trigger type and level flags.
+		1 = low-to-high edge triggered
+		2 = high-to-low edge triggered
+		4 = active high level-sensitive
+		8 = active low level-sensitive
+	bits[15:8] PPI interrupt cpu mask.  Each bit corresponds to each of
+	the 8 possible cpus attached to the GIC.  A bit set to '1' indicated
+	the interrupt is wired to that CPU.  Only valid for PPI interrupts.
+
+- reg : Specifies base physical address(s) and size of the GIC registers. The
+  first region is the GIC distributor register base and size. The 2nd region is
+  the GIC cpu interface register base and size.
+
+Optional
+- interrupts	: Interrupt source of the parent interrupt controller. Only
+  present on secondary GICs.
+
+Example:
+
+	intc: interrupt-controller@fff11000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <1>;
+		interrupt-controller;
+		reg = <0xfff11000 0x1000>,
+		      <0xfff10100 0x100>;
+	};
+

arch/arm/Kconfig

@@ -29,6 +29,7 @@ config ARM
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_SPARSE_IRQ
 	select GENERIC_IRQ_SHOW
+	select CPU_PM if (SUSPEND || CPU_IDLE)
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -195,7 +196,8 @@ config VECTORS_BASE
 	  The base address of exception vectors.
 
 config ARM_PATCH_PHYS_VIRT
-	bool "Patch physical to virtual translations at runtime"
+	bool "Patch physical to virtual translations at runtime" if EMBEDDED
+	default y
 	depends on !XIP_KERNEL && MMU
 	depends on !ARCH_REALVIEW || !SPARSEMEM
 	help
@@ -204,16 +206,25 @@ config ARM_PATCH_PHYS_VIRT
 	  kernel in system memory.
 
 	  This can only be used with non-XIP MMU kernels where the base
-	  of physical memory is at a 16MB boundary, or theoretically 64K
-	  for the MSM machine class.
+	  of physical memory is at a 16MB boundary.
 
-config ARM_PATCH_PHYS_VIRT_16BIT
-	def_bool y
-	depends on ARM_PATCH_PHYS_VIRT && ARCH_MSM
+	  Only disable this option if you know that you do not require
+	  this feature (eg, building a kernel for a single machine) and
+	  you need to shrink the kernel to the minimal size.
+
+config NEED_MACH_MEMORY_H
+	bool
 	help
-	  This option extends the physical to virtual translation patching
-	  to allow physical memory down to a theoretical minimum of 64K
-	  boundaries.
+	  Select this when mach/memory.h is required to provide special
+	  definitions for this platform.  The need for mach/memory.h should
+	  be avoided when possible.
+
+config PHYS_OFFSET
+	hex "Physical address of main memory"
+	depends on !ARM_PATCH_PHYS_VIRT && !NEED_MACH_MEMORY_H
+	help
+	  Please provide the physical address corresponding to the
+	  location of main memory in your system.
 
 source "init/Kconfig"
 
@@ -246,6 +257,7 @@ config ARCH_INTEGRATOR
 	select GENERIC_CLOCKEVENTS
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_FPGA_IRQ
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for ARM's Integrator platform.
 
@@ -261,6 +273,7 @@ config ARCH_REALVIEW
 	select PLAT_VERSATILE_CLCD
 	select ARM_TIMER_SP804
 	select GPIO_PL061 if GPIOLIB
+	select NEED_MACH_MEMORY_H
 	help
 	  This enables support for ARM Ltd RealView boards.
 
@@ -301,7 +314,6 @@ config ARCH_AT91
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_CLK
 	select CLKDEV_LOOKUP
-	select ARM_PATCH_PHYS_VIRT if MMU
 	help
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 and AT91CAP9 processors.
@@ -322,6 +334,7 @@ config ARCH_CLPS711X
 	bool "Cirrus Logic CLPS711x/EP721x-based"
 	select CPU_ARM720T
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for Cirrus Logic 711x/721x based boards.
 
@@ -362,6 +375,7 @@ config ARCH_EBSA110
 	select ISA
 	select NO_IOPORT
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_MEMORY_H
 	help
 	  This is an evaluation board for the StrongARM processor available
 	  from Digital. It has limited hardware on-board, including an
@@ -377,6 +391,7 @@ config ARCH_EP93XX
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MEMORY_H
 	help
 	  This enables support for the Cirrus EP93xx series of CPUs.
 
@@ -385,6 +400,7 @@ config ARCH_FOOTBRIDGE
 	select CPU_SA110
 	select FOOTBRIDGE
 	select GENERIC_CLOCKEVENTS
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for systems based on the DC21285 companion chip
 	  ("FootBridge"), such as the Simtec CATS and the Rebel NetWinder.
@@ -434,6 +450,7 @@ config ARCH_IOP13XX
 	select PCI
 	select ARCH_SUPPORTS_MSI
 	select VMSPLIT_1G
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for Intel's IOP13XX (XScale) family of processors.
 
@@ -464,6 +481,7 @@ config ARCH_IXP23XX
 	select CPU_XSC3
  	select PCI
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for Intel's IXP23xx (XScale) family of processors.
 
@@ -473,6 +491,7 @@ config ARCH_IXP2000
 	select CPU_XSCALE
 	select PCI
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for Intel's IXP2400/2800 (XScale) family of processors.
 
@@ -566,6 +585,7 @@ config ARCH_KS8695
 	select CPU_ARM922T
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for Micrel/Kendin KS8695 "Centaur" (ARM922T) based
 	  System-on-Chip devices.
@@ -657,6 +677,7 @@ config ARCH_SHMOBILE
 	select SPARSE_IRQ
 	select MULTI_IRQ_HANDLER
 	select PM_GENERIC_DOMAINS if PM
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for Renesas's SH-Mobile and R-Mobile ARM platforms.
 
@@ -671,6 +692,7 @@ config ARCH_RPC
 	select NO_IOPORT
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_MEMORY_H
 	help
 	  On the Acorn Risc-PC, Linux can support the internal IDE disk and
 	  CD-ROM interface, serial and parallel port, and the floppy drive.
@@ -689,6 +711,7 @@ config ARCH_SA1100
 	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select ARCH_REQUIRE_GPIOLIB
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for StrongARM 11x0 based boards.
 
@@ -781,6 +804,7 @@ config ARCH_S5PV210
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C_RTC if RTC_CLASS
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
+	select NEED_MACH_MEMORY_H
 	help
 	  Samsung S5PV210/S5PC110 series based systems
 
@@ -797,6 +821,7 @@ config ARCH_EXYNOS4
 	select HAVE_S3C_RTC if RTC_CLASS
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
+	select NEED_MACH_MEMORY_H
 	help
 	  Samsung EXYNOS4 series based systems
 
@@ -808,6 +833,7 @@ config ARCH_SHARK
 	select ZONE_DMA
 	select PCI
 	select ARCH_USES_GETTIMEOFFSET
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for the StrongARM based Digital DNARD machine, also known
 	  as "Shark" (<http://www.shark-linux.de/shark.html>).
@@ -835,6 +861,7 @@ config ARCH_U300
 	select CLKDEV_LOOKUP
 	select HAVE_MACH_CLKDEV
 	select GENERIC_GPIO
+	select NEED_MACH_MEMORY_H
 	help
 	  Support for ST-Ericsson U300 series mobile platforms.
 
@@ -1407,6 +1434,31 @@ config SMP_ON_UP
 
 	  If you don't know what to do here, say Y.
 
+config ARM_CPU_TOPOLOGY
+	bool "Support cpu topology definition"
+	depends on SMP && CPU_V7
+	default y
+	help
+	  Support ARM cpu topology definition. The MPIDR register defines
+	  affinity between processors which is then used to describe the cpu
+	  topology of an ARM System.
+
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
 config HAVE_ARM_SCU
 	bool
 	help
@@ -1807,6 +1859,38 @@ config ZBOOT_ROM_SH_MOBILE_SDHI
 
 endchoice
 
+config ARM_APPENDED_DTB
+	bool "Use appended device tree blob to zImage (EXPERIMENTAL)"
+	depends on OF && !ZBOOT_ROM && EXPERIMENTAL
+	help
+	  With this option, the boot code will look for a device tree binary
+	  (DTB) appended to zImage
+	  (e.g. cat zImage <filename>.dtb > zImage_w_dtb).
+
+	  This is meant as a backward compatibility convenience for those
+	  systems with a bootloader that can't be upgraded to accommodate
+	  the documented boot protocol using a device tree.
+
+	  Beware that there is very little in terms of protection against
+	  this option being confused by leftover garbage in memory that might
+	  look like a DTB header after a reboot if no actual DTB is appended
+	  to zImage.  Do not leave this option active in a production kernel
+	  if you don't intend to always append a DTB.  Proper passing of the
+	  location into r2 of a bootloader provided DTB is always preferable
+	  to this option.
+
+config ARM_ATAG_DTB_COMPAT
+	bool "Supplement the appended DTB with traditional ATAG information"
+	depends on ARM_APPENDED_DTB
+	help
+	  Some old bootloaders can't be updated to a DTB capable one, yet
+	  they provide ATAGs with memory configuration, the ramdisk address,
+	  the kernel cmdline string, etc.  Such information is dynamically
+	  provided by the bootloader and can't always be stored in a static
+	  DTB.  To allow a device tree enabled kernel to be used with such
+	  bootloaders, this option allows zImage to extract the information
+	  from the ATAG list and store it at run time into the appended DTB.
+
 config CMDLINE
 	string "Default kernel command string"
 	default ""

arch/arm/Kconfig.debug

@@ -129,4 +129,10 @@ config DEBUG_S3C_UART
 	  The uncompressor code port configuration is now handled
 	  by CONFIG_S3C_LOWLEVEL_UART_PORT.
 
+config ARM_KPROBES_TEST
+	tristate "Kprobes test module"
+	depends on KPROBES && MODULES
+	help
+	  Perform tests of kprobes API and instruction set simulation.
+
 endmenu

arch/arm/Makefile

@@ -128,6 +128,9 @@ textofs-$(CONFIG_PM_H1940)      := 0x00108000
 ifeq ($(CONFIG_ARCH_SA1100),y)
 textofs-$(CONFIG_SA1111) := 0x00208000
 endif
+textofs-$(CONFIG_ARCH_MSM7X30) := 0x00208000
+textofs-$(CONFIG_ARCH_MSM8X60) := 0x00208000
+textofs-$(CONFIG_ARCH_MSM8960) := 0x00208000
 
 # Machine directory name.  This list is sorted alphanumerically
 # by CONFIG_* macro name.

arch/arm/boot/compressed/.gitignore

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

arch/arm/boot/compressed/Makefile

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

arch/arm/boot/compressed/atags_to_fdt.c

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

arch/arm/boot/compressed/head.S

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

arch/arm/boot/compressed/libfdt_env.h

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

arch/arm/boot/compressed/misc.c

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

arch/arm/boot/compressed/string.c

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

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

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

arch/arm/common/Kconfig

 config ARM_GIC
+	select IRQ_DOMAIN
 	bool
 
 config ARM_VIC

arch/arm/include/asm/cputype.h

@@ -8,6 +8,7 @@
 #define CPUID_CACHETYPE	1
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
+#define CPUID_MPIDR	5
 
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
@@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
 	return read_cpuid(CPUID_TCM);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
+{
+	return read_cpuid(CPUID_MPIDR);
+}
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For

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

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

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

@@ -25,13 +25,6 @@
 	movne	r1, sp
 	adrne	lr, BSYM(1b)
 	bne	do_IPI
-
-#ifdef CONFIG_LOCAL_TIMERS
-	test_for_ltirq r0, r2, r6, lr
-	movne	r0, sp
-	adrne	lr, BSYM(1b)
-	bne	do_local_timer
-#endif
 #endif
 9997:
 	.endm

arch/arm/include/asm/exception.h

+/*
+ * Annotations for marking C functions as exception handlers.
+ *
+ * These should only be used for C functions that are called from the low
+ * level exception entry code and not any intervening C code.
+ */
+#ifndef __ASM_ARM_EXCEPTION_H
+#define __ASM_ARM_EXCEPTION_H
+
+#include <linux/ftrace.h>
+
+#define __exception	__attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
+#define __exception_irq_entry	__exception
+#endif
+
+#endif /* __ASM_ARM_EXCEPTION_H */

arch/arm/include/asm/hardirq.h

@@ -9,9 +9,6 @@
 
 typedef struct {
 	unsigned int __softirq_pending;
-#ifdef CONFIG_LOCAL_TIMERS
-	unsigned int local_timer_irqs;
-#endif
 #ifdef CONFIG_SMP
 	unsigned int ipi_irqs[NR_IPI];
 #endif

arch/arm/include/asm/hardware/entry-macro-gic.S

@@ -22,15 +22,11 @@
  * interrupt controller spec.  To wit:
  *
  * Interrupts 0-15 are IPI
- * 16-28 are reserved
- * 29-31 are local.  We allow 30 to be used for the watchdog.
+ * 16-31 are local.  We allow 30 to be used for the watchdog.
  * 32-1020 are global
  * 1021-1022 are reserved
  * 1023 is "spurious" (no interrupt)
  *
- * For now, we ignore all local interrupts so only return an interrupt if it's
- * between 30 and 1020.  The test_for_ipi routine below will pick up on IPIs.
- *
  * A simple read from the controller will tell us the number of the highest
  * priority enabled interrupt.  We then just need to check whether it is in the
  * valid range for an IRQ (30-1020 inclusive).
@@ -43,7 +39,7 @@
 
 	ldr	\tmp, =1021
 	bic     \irqnr, \irqstat, #0x1c00
-	cmp     \irqnr, #29
+	cmp     \irqnr, #15
 	cmpcc	\irqnr, \irqnr
 	cmpne	\irqnr, \tmp
 	cmpcs	\irqnr, \irqnr
@@ -62,14 +58,3 @@
 	strcc	\irqstat, [\base, #GIC_CPU_EOI]
 	cmpcs	\irqnr, \irqnr
 	.endm
-
-/* As above, this assumes that irqstat and base are preserved.. */
-
-	.macro test_for_ltirq, irqnr, irqstat, base, tmp
-	bic	\irqnr, \irqstat, #0x1c00
-	mov 	\tmp, #0
-	cmp	\irqnr, #29
-	moveq	\tmp, #1
-	streq	\irqstat, [\base, #GIC_CPU_EOI]
-	cmp	\tmp, #0
-	.endm

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

@@ -33,19 +33,32 @@
 #define GIC_DIST_SOFTINT		0xf00
 
 #ifndef __ASSEMBLY__
+#include <linux/irqdomain.h>
+struct device_node;
+
 extern void __iomem *gic_cpu_base_addr;
 extern struct irq_chip gic_arch_extn;
 
-void gic_init(unsigned int, unsigned int, void __iomem *, void __iomem *);
+void gic_init(unsigned int, int, void __iomem *, void __iomem *);
+int gic_of_init(struct device_node *node, struct device_node *parent);
 void gic_secondary_init(unsigned int);
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq);
-void gic_enable_ppi(unsigned int);
 
 struct gic_chip_data {
-	unsigned int irq_offset;
 	void __iomem *dist_base;
 	void __iomem *cpu_base;
+#ifdef CONFIG_CPU_PM
+	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
+	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
+	u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
+	u32 __percpu *saved_ppi_enable;
+	u32 __percpu *saved_ppi_conf;
+#endif
+#ifdef CONFIG_IRQ_DOMAIN
+	struct irq_domain domain;
+#endif
+	unsigned int gic_irqs;
 };
 #endif
 

arch/arm/include/asm/hw_breakpoint.h

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

arch/arm/include/asm/localtimer.h

@@ -11,6 +11,7 @@
 #define __ASM_ARM_LOCALTIMER_H
 
 #include <linux/errno.h>
+#include <linux/interrupt.h>
 
 struct clock_event_device;
 
@@ -19,27 +20,20 @@ struct clock_event_device;
  */
 void percpu_timer_setup(void);
 
-/*
- * Called from assembly, this is the local timer IRQ handler
- */
-asmlinkage void do_local_timer(struct pt_regs *);
-
-
 #ifdef CONFIG_LOCAL_TIMERS
 
 #ifdef CONFIG_HAVE_ARM_TWD
 
 #include "smp_twd.h"
 
-#define local_timer_ack()	twd_timer_ack()
+#define local_timer_stop(c)	twd_timer_stop((c))
 
 #else
 
 /*
- * Platform provides this to acknowledge a local timer IRQ.
- * Returns true if the local timer IRQ is to be processed.
+ * Stop the local timer
  */
-int local_timer_ack(void);
+void local_timer_stop(struct clock_event_device *);
 
 #endif
 
@@ -54,6 +48,10 @@ static inline int local_timer_setup(struct clock_event_device *evt)
 {
 	return -ENXIO;
 }
+
+static inline void local_timer_stop(struct clock_event_device *evt)
+{
+}
 #endif
 
 #endif

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

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

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

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

arch/arm/include/asm/memory.h

@@ -16,9 +16,12 @@
 #include <linux/compiler.h>
 #include <linux/const.h>
 #include <linux/types.h>
-#include <mach/memory.h>
 #include <asm/sizes.h>
 
+#ifdef CONFIG_NEED_MACH_MEMORY_H
+#include <mach/memory.h>
+#endif
+
 /*
  * Allow for constants defined here to be used from assembly code
  * by prepending the UL suffix only with actual C code compilation.
@@ -77,16 +80,7 @@
  */
 #define IOREMAP_MAX_ORDER	24
 
-/*
- * Size of DMA-consistent memory region.  Must be multiple of 2M,
- * between 2MB and 14MB inclusive.
- */
-#ifndef CONSISTENT_DMA_SIZE
-#define CONSISTENT_DMA_SIZE 	SZ_2M
-#endif
-
 #define CONSISTENT_END		(0xffe00000UL)
-#define CONSISTENT_BASE		(CONSISTENT_END - CONSISTENT_DMA_SIZE)
 
 #else /* CONFIG_MMU */
 
@@ -160,7 +154,6 @@
  * so that all we need to do is modify the 8-bit constant field.
  */
 #define __PV_BITS_31_24	0x81000000
-#define __PV_BITS_23_16	0x00810000
 
 extern unsigned long __pv_phys_offset;
 #define PHYS_OFFSET __pv_phys_offset
@@ -178,9 +171,6 @@ static inline unsigned long __virt_to_phys(unsigned long x)
 {
 	unsigned long t;
 	__pv_stub(x, t, "add", __PV_BITS_31_24);
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	__pv_stub(t, t, "add", __PV_BITS_23_16);
-#endif
 	return t;
 }
 
@@ -188,9 +178,6 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 {
 	unsigned long t;
 	__pv_stub(x, t, "sub", __PV_BITS_31_24);
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	__pv_stub(t, t, "sub", __PV_BITS_23_16);
-#endif
 	return t;
 }
 #else
@@ -200,7 +187,11 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 #endif
 
 #ifndef PHYS_OFFSET
+#ifdef PLAT_PHYS_OFFSET
 #define PHYS_OFFSET	PLAT_PHYS_OFFSET
+#else
+#define PHYS_OFFSET	UL(CONFIG_PHYS_OFFSET)
+#endif
 #endif
 
 /*

arch/arm/include/asm/module.h

@@ -31,11 +31,7 @@ struct mod_arch_specific {
 
 /* Add __virt_to_phys patching state as well */
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-#define MODULE_ARCH_VERMAGIC_P2V "p2v16 "
-#else
 #define MODULE_ARCH_VERMAGIC_P2V "p2v8 "
-#endif
 #else
 #define MODULE_ARCH_VERMAGIC_P2V ""
 #endif

arch/arm/include/asm/pgtable.h

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

arch/arm/include/asm/pmu.h

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

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

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

arch/arm/include/asm/smp.h

@@ -32,6 +32,11 @@ extern void show_ipi_list(struct seq_file *, int);
  */
 asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
 
+/*
+ * Called from C code, this handles an IPI.
+ */
+void handle_IPI(int ipinr, struct pt_regs *regs);
+
 /*
  * Setup the set of possible CPUs (via set_cpu_possible)
  */
@@ -65,6 +70,12 @@ extern void platform_secondary_init(unsigned int cpu);
  */
 extern void platform_smp_prepare_cpus(unsigned int);
 
+/*
+ * Logical CPU mapping.
+ */
+extern int __cpu_logical_map[NR_CPUS];
+#define cpu_logical_map(cpu)	__cpu_logical_map[cpu]
+
 /*
  * Initial data for bringing up a secondary CPU.
  */
@@ -88,9 +99,4 @@ extern void platform_cpu_enable(unsigned int cpu);
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
-/*
- * show local interrupt info
- */
-extern void show_local_irqs(struct seq_file *, int);
-
 #endif /* ifndef __ASM_ARM_SMP_H */

arch/arm/include/asm/smp_twd.h

@@ -22,7 +22,7 @@ struct clock_event_device;
 
 extern void __iomem *twd_base;
 
-int twd_timer_ack(void);
 void twd_timer_setup(struct clock_event_device *);
+void twd_timer_stop(struct clock_event_device *);
 
 #endif

arch/arm/include/asm/suspend.h

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

arch/arm/include/asm/system.h

@@ -62,13 +62,6 @@
 
 #include <asm/outercache.h>
 
-#define __exception	__attribute__((section(".exception.text")))
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-#define __exception_irq_entry	__irq_entry
-#else
-#define __exception_irq_entry	__exception
-#endif
-
 struct thread_info;
 struct task_struct;
 

arch/arm/include/asm/topology.h

 #ifndef _ASM_ARM_TOPOLOGY_H
 #define _ASM_ARM_TOPOLOGY_H
 
+#ifdef CONFIG_ARM_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cputopo_arm {
+	int thread_id;
+	int core_id;
+	int socket_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cputopo_arm cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].socket_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */

arch/arm/kernel/Makefile

@@ -29,7 +29,7 @@ obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
-obj-$(CONFIG_PM_SLEEP)		+= sleep.o
+obj-$(CONFIG_PM_SLEEP)		+= sleep.o suspend.o
 obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
@@ -43,6 +43,13 @@ obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
 else
 obj-$(CONFIG_KPROBES)		+= kprobes-arm.o
 endif
+obj-$(CONFIG_ARM_KPROBES_TEST)	+= test-kprobes.o
+test-kprobes-objs		:= kprobes-test.o
+ifdef CONFIG_THUMB2_KERNEL
+test-kprobes-objs		+= kprobes-test-thumb.o
+else
+test-kprobes-objs		+= kprobes-test-arm.o
+endif
 obj-$(CONFIG_ATAGS_PROC)	+= atags.o
 obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
@@ -66,6 +73,7 @@ obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_CPU_HAS_PMU)	+= pmu.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
+obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)
   obj-y		+= io.o

arch/arm/kernel/debug.S

@@ -22,7 +22,7 @@
 #if defined(CONFIG_DEBUG_ICEDCC)
 		@@ debug using ARM EmbeddedICE DCC channel
 
-		.macro	addruart, rp, rv
+		.macro	addruart, rp, rv, tmp
 		.endm
 
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7)
@@ -106,7 +106,7 @@
 
 #ifdef CONFIG_MMU
 		.macro	addruart_current, rx, tmp1, tmp2
-		addruart	\tmp1, \tmp2
+		addruart	\tmp1, \tmp2, \rx
 		mrc		p15, 0, \rx, c1, c0
 		tst		\rx, #1
 		moveq		\rx, \tmp1

arch/arm/kernel/head.S

@@ -95,7 +95,7 @@ ENTRY(stext)
 	sub	r4, r3, r4			@ (PHYS_OFFSET - PAGE_OFFSET)
 	add	r8, r8, r4			@ PHYS_OFFSET
 #else
-	ldr	r8, =PLAT_PHYS_OFFSET
+	ldr	r8, =PHYS_OFFSET		@ always constant in this case
 #endif
 
 	/*
@@ -234,7 +234,7 @@ __create_page_tables:
 	 * This allows debug messages to be output
 	 * via a serial console before paging_init.
 	 */
-	addruart r7, r3
+	addruart r7, r3, r0
 
 	mov	r3, r3, lsr #20
 	mov	r3, r3, lsl #2
@@ -488,13 +488,8 @@ __fixup_pv_table:
 	add	r5, r5, r3	@ adjust table end address
 	add	r7, r7, r3	@ adjust __pv_phys_offset address
 	str	r8, [r7]	@ save computed PHYS_OFFSET to __pv_phys_offset
-#ifndef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
 	mov	r6, r3, lsr #24	@ constant for add/sub instructions
 	teq	r3, r6, lsl #24 @ must be 16MiB aligned
-#else
-	mov	r6, r3, lsr #16	@ constant for add/sub instructions
-	teq	r3, r6, lsl #16	@ must be 64kiB aligned
-#endif
 THUMB(	it	ne		@ cross section branch )
 	bne	__error
 	str	r6, [r7, #4]	@ save to __pv_offset
@@ -510,20 +505,8 @@ ENDPROC(__fixup_pv_table)
 	.text
 __fixup_a_pv_table:
 #ifdef CONFIG_THUMB2_KERNEL
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	lsls	r0, r6, #24
-	lsr	r6, #8
-	beq	1f
-	clz	r7, r0
-	lsr	r0, #24
-	lsl	r0, r7
-	bic	r0, 0x0080
-	lsrs	r7, #1
-	orrcs   r0, #0x0080
-	orr	r0, r0, r7, lsl #12
-#endif
-1:	lsls	r6, #24
-	beq	4f
+	lsls	r6, #24
+	beq	2f
 	clz	r7, r6
 	lsr	r6, #24
 	lsl	r6, r7
@@ -532,43 +515,25 @@ __fixup_a_pv_table:
 	orrcs	r6, #0x0080
 	orr	r6, r6, r7, lsl #12
 	orr	r6, #0x4000
-	b	4f
-2:	@ at this point the C flag is always clear
-	add     r7, r3
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	ldrh	ip, [r7]
-	tst	ip, 0x0400	@ the i bit tells us LS or MS byte
-	beq	3f
-	cmp	r0, #0		@ set C flag, and ...
-	biceq	ip, 0x0400	@ immediate zero value has a special encoding
-	streqh	ip, [r7]	@ that requires the i bit cleared
-#endif
-3:	ldrh	ip, [r7, #2]
+	b	2f
+1:	add     r7, r3
+	ldrh	ip, [r7, #2]
 	and	ip, 0x8f00
-	orrcc	ip, r6	@ mask in offset bits 31-24
-	orrcs	ip, r0	@ mask in offset bits 23-16
+	orr	ip, r6	@ mask in offset bits 31-24
 	strh	ip, [r7, #2]
-4:	cmp	r4, r5
+2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
-	bcc	2b
+	bcc	1b
 	bx	lr
 #else
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
-	and	r0, r6, #255	@ offset bits 23-16
-	mov	r6, r6, lsr #8	@ offset bits 31-24
-#else
-	mov	r0, #0		@ just in case...
-#endif
-	b	3f
-2:	ldr	ip, [r7, r3]
+	b	2f
+1:	ldr	ip, [r7, r3]
 	bic	ip, ip, #0x000000ff
-	tst	ip, #0x400	@ rotate shift tells us LS or MS byte
-	orrne	ip, ip, r6	@ mask in offset bits 31-24
-	orreq	ip, ip, r0	@ mask in offset bits 23-16
+	orr	ip, ip, r6	@ mask in offset bits 31-24
 	str	ip, [r7, r3]
-3:	cmp	r4, r5
+2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
-	bcc	2b
+	bcc	1b
 	mov	pc, lr
 #endif
 ENDPROC(__fixup_a_pv_table)

arch/arm/kernel/irq.c

@@ -35,8 +35,8 @@
 #include <linux/list.h>
 #include <linux/kallsyms.h>
 #include <linux/proc_fs.h>
-#include <linux/ftrace.h>
 
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -58,9 +58,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 #endif
 #ifdef CONFIG_SMP
 	show_ipi_list(p, prec);
-#endif
-#ifdef CONFIG_LOCAL_TIMERS
-	show_local_irqs(p, prec);
 #endif
 	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	return 0;

arch/arm/kernel/kprobes-arm.c

@@ -60,6 +60,7 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <linux/module.h>
 
 #include "kprobes.h"
 
@@ -971,6 +972,9 @@ const union decode_item kprobe_decode_arm_table[] = {
 
 	DECODE_END
 };
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(kprobe_decode_arm_table);
+#endif
 
 static void __kprobes arm_singlestep(struct kprobe *p, struct pt_regs *regs)
 {

arch/arm/kernel/kprobes-thumb.c

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

arch/arm/kernel/kprobes.h

@@ -413,6 +413,14 @@ struct decode_reject {
 	DECODE_HEADER(DECODE_TYPE_REJECT, _mask, _value, 0)
 
 
+#ifdef CONFIG_THUMB2_KERNEL
+extern const union decode_item kprobe_decode_thumb16_table[];
+extern const union decode_item kprobe_decode_thumb32_table[];
+#else
+extern const union decode_item kprobe_decode_arm_table[];
+#endif
+
+
 int kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
 			const union decode_item *table, bool thumb16);
 

arch/arm/kernel/perf_event_v6.c

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

arch/arm/kernel/perf_event_xscale.c

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

arch/arm/kernel/setup.c

@@ -820,25 +820,8 @@ static struct machine_desc * __init setup_machine_tags(unsigned int nr)
 
 	if (__atags_pointer)
 		tags = phys_to_virt(__atags_pointer);
-	else if (mdesc->boot_params) {
-#ifdef CONFIG_MMU
-		/*
-		 * We still are executing with a minimal MMU mapping created
-		 * with the presumption that the machine default for this
-		 * is located in the first MB of RAM.  Anything else will
-		 * fault and silently hang the kernel at this point.
-		 */
-		if (mdesc->boot_params < PHYS_OFFSET ||
-		    mdesc->boot_params >= PHYS_OFFSET + SZ_1M) {
-			printk(KERN_WARNING
-			       "Default boot params at physical 0x%08lx out of reach\n",
-			       mdesc->boot_params);
-		} else
-#endif
-		{
-			tags = phys_to_virt(mdesc->boot_params);
-		}
-	}
+	else if (mdesc->atag_offset)
+		tags = (void *)(PAGE_OFFSET + mdesc->atag_offset);
 
 #if defined(CONFIG_DEPRECATED_PARAM_STRUCT)
 	/*

arch/arm/kernel/sleep.S

@@ -8,92 +8,61 @@
 	.text
 
 /*
- * Save CPU state for a suspend
- *  r1 = v:p offset
- *  r2 = suspend function arg0
- *  r3 = suspend function
+ * Save CPU state for a suspend.  This saves the CPU general purpose
+ * registers, and allocates space on the kernel stack to save the CPU
+ * specific registers and some other data for resume.
+ *  r0 = suspend function arg0
+ *  r1 = suspend function
  */
 ENTRY(__cpu_suspend)
 	stmfd	sp!, {r4 - r11, lr}
 #ifdef MULTI_CPU
 	ldr	r10, =processor
-	ldr	r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
-	ldr	ip, [r10, #CPU_DO_RESUME] @ virtual resume function
+	ldr	r4, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
 #else
-	ldr	r5, =cpu_suspend_size
-	ldr	ip, =cpu_do_resume
+	ldr	r4, =cpu_suspend_size
 #endif
-	mov	r6, sp			@ current virtual SP
-	sub	sp, sp, r5		@ allocate CPU state on stack
-	mov	r0, sp			@ save pointer to CPU save block
-	add	ip, ip, r1		@ convert resume fn to phys
-	stmfd	sp!, {r1, r6, ip}	@ save v:p, virt SP, phys resume fn
-	ldr	r5, =sleep_save_sp
-	add	r6, sp, r1		@ convert SP to phys
-	stmfd	sp!, {r2, r3}		@ save suspend func arg and pointer
+	mov	r5, sp			@ current virtual SP
+	add	r4, r4, #12		@ Space for pgd, virt sp, phys resume fn
+	sub	sp, sp, r4		@ allocate CPU state on stack
+	stmfd	sp!, {r0, r1}		@ save suspend func arg and pointer
+	add	r0, sp, #8		@ save pointer to save block
+	mov	r1, r4			@ size of save block
+	mov	r2, r5			@ virtual SP
+	ldr	r3, =sleep_save_sp
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
 	ALT_UP(mov lr, #0)
 	and	lr, lr, #15
-	str	r6, [r5, lr, lsl #2]	@ save phys SP
-#else
-	str	r6, [r5]		@ save phys SP
-#endif
-#ifdef MULTI_CPU
-	mov	lr, pc
-	ldr	pc, [r10, #CPU_DO_SUSPEND] @ save CPU state
-#else
-	bl	cpu_do_suspend
-#endif
-
-	@ flush data cache
-#ifdef MULTI_CACHE
-	ldr	r10, =cpu_cache
-	mov	lr, pc
-	ldr	pc, [r10, #CACHE_FLUSH_KERN_ALL]
-#else
-	bl	__cpuc_flush_kern_all
+	add	r3, r3, lr, lsl #2
 #endif
+	bl	__cpu_suspend_save
 	adr	lr, BSYM(cpu_suspend_abort)
 	ldmfd	sp!, {r0, pc}		@ call suspend fn
 ENDPROC(__cpu_suspend)
 	.ltorg
 
 cpu_suspend_abort:
-	ldmia	sp!, {r1 - r3}		@ pop v:p, virt SP, phys resume fn
+	ldmia	sp!, {r1 - r3}		@ pop phys pgd, virt SP, phys resume fn
+	teq	r0, #0
+	moveq	r0, #1			@ force non-zero value
 	mov	sp, r2
 	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_suspend_abort)
 
 /*
  * r0 = control register value
- * r1 = v:p offset (preserved by cpu_do_resume)
- * r2 = phys page table base
- * r3 = L1 section flags
  */
+	.align	5
 ENTRY(cpu_resume_mmu)
-	adr	r4, cpu_resume_turn_mmu_on
-	mov	r4, r4, lsr #20
-	orr	r3, r3, r4, lsl #20
-	ldr	r5, [r2, r4, lsl #2]	@ save old mapping
-	str	r3, [r2, r4, lsl #2]	@ setup 1:1 mapping for mmu code
-	sub	r2, r2, r1
 	ldr	r3, =cpu_resume_after_mmu
-	bic	r1, r0, #CR_C		@ ensure D-cache is disabled
-	b	cpu_resume_turn_mmu_on
-ENDPROC(cpu_resume_mmu)
-	.ltorg
-	.align	5
-cpu_resume_turn_mmu_on:
-	mcr	p15, 0, r1, c1, c0, 0	@ turn on MMU, I-cache, etc
-	mrc	p15, 0, r1, c0, c0, 0	@ read id reg
-	mov	r1, r1
-	mov	r1, r1
+	mcr	p15, 0, r0, c1, c0, 0	@ turn on MMU, I-cache, etc
+	mrc	p15, 0, r0, c0, c0, 0	@ read id reg
+	mov	r0, r0
+	mov	r0, r0
 	mov	pc, r3			@ jump to virtual address
-ENDPROC(cpu_resume_turn_mmu_on)
+ENDPROC(cpu_resume_mmu)
 cpu_resume_after_mmu:
-	str	r5, [r2, r4, lsl #2]	@ restore old mapping
-	mcr	p15, 0, r0, c1, c0, 0	@ turn on D-cache
 	bl	cpu_init		@ restore the und/abt/irq banked regs
 	mov	r0, #0			@ return zero on success
 	ldmfd	sp!, {r4 - r11, pc}
@@ -119,7 +88,7 @@ ENTRY(cpu_resume)
 	ldr	r0, sleep_save_sp	@ stack phys addr
 #endif
 	setmode	PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1  @ set SVC, irqs off
-	@ load v:p, stack, resume fn
+	@ load phys pgd, stack, resume fn
   ARM(	ldmia	r0!, {r1, sp, pc}	)
 THUMB(	ldmia	r0!, {r1, r2, r3}	)
 THUMB(	mov	sp, r2			)

arch/arm/kernel/smp_scu.c

@@ -34,7 +34,7 @@ unsigned int __init scu_get_core_count(void __iomem *scu_base)
 /*
  * Enable the SCU
  */
-void __init scu_enable(void __iomem *scu_base)
+void scu_enable(void __iomem *scu_base)
 {
 	u32 scu_ctrl;
 

arch/arm/kernel/traps.c

@@ -27,6 +27,7 @@
 
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>

arch/arm/mach-at91/at91sam9g45.c

@@ -12,6 +12,7 @@
 
 #include <linux/module.h>
 #include <linux/pm.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
@@ -325,6 +326,7 @@ static void at91sam9g45_poweroff(void)
 static void __init at91sam9g45_map_io(void)
 {
 	at91_init_sram(0, AT91SAM9G45_SRAM_BASE, AT91SAM9G45_SRAM_SIZE);
+	init_consistent_dma_size(SZ_4M);
 }
 
 static void __init at91sam9g45_initialize(void)

arch/arm/mach-at91/include/mach/at91sam9g45.h

@@ -128,8 +128,6 @@
 #define AT91SAM9G45_EHCI_BASE	0x00800000	/* USB Host controller (EHCI) */
 #define AT91SAM9G45_VDEC_BASE	0x00900000	/* Video Decoder Controller */
 
-#define CONSISTENT_DMA_SIZE	SZ_4M
-
 /*
  * DMA peripheral identifiers
  * for hardware handshaking interface

arch/arm/mach-at91/include/mach/debug-macro.S

@@ -14,7 +14,7 @@
 #include <mach/hardware.h>
 #include <mach/at91_dbgu.h>
 
-	.macro	addruart, rp, rv
+	.macro	addruart, rp, rv, tmp
 	ldr	\rp, =(AT91_BASE_SYS + AT91_DBGU)	@ System peripherals (phys address)
 	ldr	\rv, =(AT91_VA_BASE_SYS	+ AT91_DBGU)	@ System peripherals (virt address)
 	.endm