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

@@ -0,0 +1,55 @@
+* 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
+	  of physical memory is at a 16MB boundary.
-	  for the MSM machine class.
 
-config ARM_PATCH_PHYS_VIRT_16BIT
+	  Only disable this option if you know that you do not require
-	def_bool y
+	  this feature (eg, building a kernel for a single machine) and
-	depends on ARM_PATCH_PHYS_VIRT && ARCH_MSM
+	  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
+	  Select this when mach/memory.h is required to provide special
-	  to allow physical memory down to a theoretical minimum of 64K
+	  definitions for this platform.  The need for mach/memory.h should
-	  boundaries.
+	  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

@@ -0,0 +1,97 @@
+#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		)
+		adr	r9, wont_overwrite
- THUMB(		mov	lr, pc		)
+		cmp	r10, r9
- THUMB(		cmp	r10, lr		)
 		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
+		add	r1, r1, r0		@ This fixes up C references
-		str	r1, [r11], #4		@ 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

@@ -0,0 +1,15 @@
+#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/types.h>
-#include <linux/stddef.h>	/* for NULL */
 #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

@@ -0,0 +1,127 @@
+/*
+ * 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

@@ -1,4 +1,5 @@
 config ARM_GIC
+	select IRQ_DOMAIN
 	bool
 
 config ARM_VIC

arch/arm/common/gic.c

@@ -24,10 +24,20 @@
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/export.h>
 #include <linux/list.h>
 #include <linux/smp.h>
+#include <linux/cpu_pm.h>
 #include <linux/cpumask.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
 
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
@@ -71,8 +81,7 @@ static inline void __iomem *gic_cpu_base(struct irq_data *d)
 
 static inline unsigned int gic_irq(struct irq_data *d)
 {
-	struct gic_chip_data *gic_data = irq_data_get_irq_chip_data(d);
+	return d->hwirq;
-	return d->irq - gic_data->irq_offset;
 }
 
 /*
@@ -80,7 +89,7 @@ static inline unsigned int gic_irq(struct irq_data *d)
  */
 static void gic_mask_irq(struct irq_data *d)
 {
-	u32 mask = 1 << (d->irq % 32);
+	u32 mask = 1 << (gic_irq(d) % 32);
 
 	spin_lock(&irq_controller_lock);
 	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_CLEAR + (gic_irq(d) / 32) * 4);
@@ -91,7 +100,7 @@ static void gic_mask_irq(struct irq_data *d)
 
 static void gic_unmask_irq(struct irq_data *d)
 {
-	u32 mask = 1 << (d->irq % 32);
+	u32 mask = 1 << (gic_irq(d) % 32);
 
 	spin_lock(&irq_controller_lock);
 	if (gic_arch_extn.irq_unmask)
@@ -172,7 +181,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
 	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
-	unsigned int shift = (d->irq % 4) * 8;
+	unsigned int shift = (gic_irq(d) % 4) * 8;
 	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
 	u32 val, mask, bit;
 
@@ -180,7 +189,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 		return -EINVAL;
 
 	mask = 0xff << shift;
-	bit = 1 << (cpu + shift);
+	bit = 1 << (cpu_logical_map(cpu) + shift);
 
 	spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
@@ -223,7 +232,7 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 	if (gic_irq == 1023)
 		goto out;
 
-	cascade_irq = gic_irq + chip_data->irq_offset;
+	cascade_irq = irq_domain_to_irq(&chip_data->domain, gic_irq);
 	if (unlikely(gic_irq < 32 || gic_irq > 1020 || cascade_irq >= NR_IRQS))
 		do_bad_IRQ(cascade_irq, desc);
 	else
@@ -255,27 +264,25 @@ void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq)
 	irq_set_chained_handler(irq, gic_handle_cascade_irq);
 }
 
-static void __init gic_dist_init(struct gic_chip_data *gic,
+static void __init gic_dist_init(struct gic_chip_data *gic)
-	unsigned int irq_start)
 {
-	unsigned int gic_irqs, irq_limit, i;
+	unsigned int i, irq;
+	u32 cpumask;
+	unsigned int gic_irqs = gic->gic_irqs;
+	struct irq_domain *domain = &gic->domain;
 	void __iomem *base = gic->dist_base;
-	u32 cpumask = 1 << smp_processor_id();
+	u32 cpu = 0;
 
+#ifdef CONFIG_SMP
+	cpu = cpu_logical_map(smp_processor_id());
+#endif
+
+	cpumask = 1 << cpu;
 	cpumask |= cpumask << 8;
 	cpumask |= cpumask << 16;
 
 	writel_relaxed(0, base + GIC_DIST_CTRL);
 
-	/*
-	 * Find out how many interrupts are supported.
-	 * The GIC only supports up to 1020 interrupt sources.
-	 */
-	gic_irqs = readl_relaxed(base + GIC_DIST_CTR) & 0x1f;
-	gic_irqs = (gic_irqs + 1) * 32;
-	if (gic_irqs > 1020)
-		gic_irqs = 1020;
-
 	/*
 	 * Set all global interrupts to be level triggered, active low.
 	 */
@@ -301,20 +308,21 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	for (i = 32; i < gic_irqs; i += 32)
 		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
 
-	/*
-	 * Limit number of interrupts registered to the platform maximum
-	 */
-	irq_limit = gic->irq_offset + gic_irqs;
-	if (WARN_ON(irq_limit > NR_IRQS))
-		irq_limit = NR_IRQS;
-
 	/*
 	 * Setup the Linux IRQ subsystem.
 	 */
-	for (i = irq_start; i < irq_limit; i++) {
+	irq_domain_for_each_irq(domain, i, irq) {
-		irq_set_chip_and_handler(i, &gic_chip, handle_fasteoi_irq);
+		if (i < 32) {
-		irq_set_chip_data(i, gic);
+			irq_set_percpu_devid(irq);
-		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
+			irq_set_chip_and_handler(irq, &gic_chip,
+						 handle_percpu_devid_irq);
+			set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+		} else {
+			irq_set_chip_and_handler(irq, &gic_chip,
+						 handle_fasteoi_irq);
+			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		}
+		irq_set_chip_data(irq, gic);
 	}
 
 	writel_relaxed(1, base + GIC_DIST_CTRL);
@@ -343,23 +351,270 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
-void __init gic_init(unsigned int gic_nr, unsigned int irq_start,
+#ifdef CONFIG_CPU_PM
+/*
+ * Saves the GIC distributor registers during suspend or idle.  Must be called
+ * with interrupts disabled but before powering down the GIC.  After calling
+ * this function, no interrupts will be delivered by the GIC, and another
+ * platform-specific wakeup source must be enabled.
+ */
+static void gic_dist_save(unsigned int gic_nr)
+{
+	unsigned int gic_irqs;
+	void __iomem *dist_base;
+	int i;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+	dist_base = gic_data[gic_nr].dist_base;
+
+	if (!dist_base)
+		return;
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
+		gic_data[gic_nr].saved_spi_conf[i] =
+			readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		gic_data[gic_nr].saved_spi_target[i] =
+			readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		gic_data[gic_nr].saved_spi_enable[i] =
+			readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+}
+
+/*
+ * Restores the GIC distributor registers during resume or when coming out of
+ * idle.  Must be called before enabling interrupts.  If a level interrupt
+ * that occured while the GIC was suspended is still present, it will be
+ * handled normally, but any edge interrupts that occured will not be seen by
+ * the GIC and need to be handled by the platform-specific wakeup source.
+ */
+static void gic_dist_restore(unsigned int gic_nr)
+{
+	unsigned int gic_irqs;
+	unsigned int i;
+	void __iomem *dist_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+	dist_base = gic_data[gic_nr].dist_base;
+
+	if (!dist_base)
+		return;
+
+	writel_relaxed(0, dist_base + GIC_DIST_CTRL);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_conf[i],
+			dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		writel_relaxed(0xa0a0a0a0,
+			dist_base + GIC_DIST_PRI + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_target[i],
+			dist_base + GIC_DIST_TARGET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_enable[i],
+			dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	writel_relaxed(1, dist_base + GIC_DIST_CTRL);
+}
+
+static void gic_cpu_save(unsigned int gic_nr)
+{
+	int i;
+	u32 *ptr;
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data[gic_nr].dist_base;
+	cpu_base = gic_data[gic_nr].cpu_base;
+
+	if (!dist_base || !cpu_base)
+		return;
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
+
+}
+
+static void gic_cpu_restore(unsigned int gic_nr)
+{
+	int i;
+	u32 *ptr;
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data[gic_nr].dist_base;
+	cpu_base = gic_data[gic_nr].cpu_base;
+
+	if (!dist_base || !cpu_base)
+		return;
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(32, 4); i++)
+		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4);
+
+	writel_relaxed(0xf0, cpu_base + GIC_CPU_PRIMASK);
+	writel_relaxed(1, cpu_base + GIC_CPU_CTRL);
+}
+
+static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
+{
+	int i;
+
+	for (i = 0; i < MAX_GIC_NR; i++) {
+		switch (cmd) {
+		case CPU_PM_ENTER:
+			gic_cpu_save(i);
+			break;
+		case CPU_PM_ENTER_FAILED:
+		case CPU_PM_EXIT:
+			gic_cpu_restore(i);
+			break;
+		case CPU_CLUSTER_PM_ENTER:
+			gic_dist_save(i);
+			break;
+		case CPU_CLUSTER_PM_ENTER_FAILED:
+		case CPU_CLUSTER_PM_EXIT:
+			gic_dist_restore(i);
+			break;
+		}
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gic_notifier_block = {
+	.notifier_call = gic_notifier,
+};
+
+static void __init gic_pm_init(struct gic_chip_data *gic)
+{
+	gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_enable);
+
+	gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_conf);
+
+	cpu_pm_register_notifier(&gic_notifier_block);
+}
+#else
+static void __init gic_pm_init(struct gic_chip_data *gic)
+{
+}
+#endif
+
+#ifdef CONFIG_OF
+static int gic_irq_domain_dt_translate(struct irq_domain *d,
+				       struct device_node *controller,
+				       const u32 *intspec, unsigned int intsize,
+				       unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (d->of_node != controller)
+		return -EINVAL;
+	if (intsize < 3)
+		return -EINVAL;
+
+	/* Get the interrupt number and add 16 to skip over SGIs */
+	*out_hwirq = intspec[1] + 16;
+
+	/* For SPIs, we need to add 16 more to get the GIC irq ID number */
+	if (!intspec[0])
+		*out_hwirq += 16;
+
+	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
+	return 0;
+}
+#endif
+
+const struct irq_domain_ops gic_irq_domain_ops = {
+#ifdef CONFIG_OF
+	.dt_translate = gic_irq_domain_dt_translate,
+#endif
+};
+
+void __init gic_init(unsigned int gic_nr, int irq_start,
 	void __iomem *dist_base, void __iomem *cpu_base)
 {
 	struct gic_chip_data *gic;
+	struct irq_domain *domain;
+	int gic_irqs;
 
 	BUG_ON(gic_nr >= MAX_GIC_NR);
 
 	gic = &gic_data[gic_nr];
+	domain = &gic->domain;
 	gic->dist_base = dist_base;
 	gic->cpu_base = cpu_base;
-	gic->irq_offset = (irq_start - 1) & ~31;
 
-	if (gic_nr == 0)
+	/*
+	 * For primary GICs, skip over SGIs.
+	 * For secondary GICs, skip over PPIs, too.
+	 */
+	if (gic_nr == 0) {
 		gic_cpu_base_addr = cpu_base;
+		domain->hwirq_base = 16;
+		if (irq_start > 0)
+			irq_start = (irq_start & ~31) + 16;
+	} else
+		domain->hwirq_base = 32;
 
-	gic_dist_init(gic, irq_start);
+	/*
+	 * Find out how many interrupts are supported.
+	 * The GIC only supports up to 1020 interrupt sources.
+	 */
+	gic_irqs = readl_relaxed(dist_base + GIC_DIST_CTR) & 0x1f;
+	gic_irqs = (gic_irqs + 1) * 32;
+	if (gic_irqs > 1020)
+		gic_irqs = 1020;
+	gic->gic_irqs = gic_irqs;
+
+	domain->nr_irq = gic_irqs - domain->hwirq_base;
+	domain->irq_base = irq_alloc_descs(irq_start, 16, domain->nr_irq,
+					   numa_node_id());
+	if (IS_ERR_VALUE(domain->irq_base)) {
+		WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
+		     irq_start);
+		domain->irq_base = irq_start;
+	}
+	domain->priv = gic;
+	domain->ops = &gic_irq_domain_ops;
+	irq_domain_add(domain);
+
+	gic_chip.flags |= gic_arch_extn.flags;
+	gic_dist_init(gic);
 	gic_cpu_init(gic);
+	gic_pm_init(gic);
 }
 
 void __cpuinit gic_secondary_init(unsigned int gic_nr)
@@ -369,20 +624,15 @@ void __cpuinit gic_secondary_init(unsigned int gic_nr)
 	gic_cpu_init(&gic_data[gic_nr]);
 }
 
-void __cpuinit gic_enable_ppi(unsigned int irq)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	irq_set_status_flags(irq, IRQ_NOPROBE);
-	gic_unmask_irq(irq_get_irq_data(irq));
-	local_irq_restore(flags);
-}
-
 #ifdef CONFIG_SMP
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
-	unsigned long map = *cpus_addr(*mask);
+	int cpu;
+	unsigned long map = 0;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the
@@ -394,3 +644,35 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 	writel_relaxed(map << 16 | irq, gic_data[0].dist_base + GIC_DIST_SOFTINT);
 }
 #endif
+
+#ifdef CONFIG_OF
+static int gic_cnt __initdata = 0;
+
+int __init gic_of_init(struct device_node *node, struct device_node *parent)
+{
+	void __iomem *cpu_base;
+	void __iomem *dist_base;
+	int irq;
+	struct irq_domain *domain = &gic_data[gic_cnt].domain;
+
+	if (WARN_ON(!node))
+		return -ENODEV;
+
+	dist_base = of_iomap(node, 0);
+	WARN(!dist_base, "unable to map gic dist registers\n");
+
+	cpu_base = of_iomap(node, 1);
+	WARN(!cpu_base, "unable to map gic cpu registers\n");
+
+	domain->of_node = of_node_get(node);
+
+	gic_init(gic_cnt, -1, dist_base, cpu_base);
+
+	if (parent) {
+		irq = irq_of_parse_and_map(node, 0);
+		gic_cascade_irq(gic_cnt, irq);
+	}
+	gic_cnt++;
+	return 0;
+}
+#endif

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

@@ -0,0 +1,19 @@
+/*
+ * 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
+ * 16-31 are local.  We allow 30 to be used for the watchdog.
- * 29-31 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.
+ * Stop the local timer
- * Returns true if the local timer IRQ is to be processed.
  */
-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()
+ * Returns 0 on success or -EBUSY if the lock is already held.
- * encoded error on failure.
  */
-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 *
+static inline int
 reserve_pmu(enum arm_pmu_type type)
-{
-	return ERR_PTR(-ENODEV);
-}
-
-static inline int
-release_pmu(enum arm_pmu_type type)
 {
 	return -ENODEV;
 }
 
-static inline int
+static inline void
-init_pmu(enum arm_pmu_type type)
+release_pmu(enum arm_pmu_type type)	{ }
-{
-	return -ENODEV;
-}
 
 #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

@@ -1,22 +1,7 @@
 #ifndef __ASM_ARM_SUSPEND_H
 #define __ASM_ARM_SUSPEND_H
 
-#include <asm/memory.h>
-#include <asm/tlbflush.h>
-
 extern void cpu_resume(void);
-
+extern int cpu_suspend(unsigned long, int (*)(unsigned long));
-/*
- * 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/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

@@ -1,6 +1,39 @@
 #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	r6, #24
-	lsls	r0, r6, #24
+	beq	2f
-	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
 	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
+	b	2f
-2:	@ at this point the C flag is always clear
+1:	add     r7, r3
-	add     r7, r3
+	ldrh	ip, [r7, #2]
-#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]
 	and	ip, 0x8f00
-	orrcc	ip, r6	@ mask in offset bits 31-24
+	orr	ip, r6	@ mask in offset bits 31-24
-	orrcs	ip, r0	@ mask in offset bits 23-16
 	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
+	b	2f
-	and	r0, r6, #255	@ offset bits 23-16
+1:	ldr	ip, [r7, r3]
-	mov	r6, r6, lsr #8	@ offset bits 31-24
-#else
-	mov	r0, #0		@ just in case...
-#endif
-	b	3f
-2:	ldr	ip, [r7, r3]
 	bic	ip, ip, #0x000000ff
-	tst	ip, #0x400	@ rotate shift tells us LS or MS byte
+	orr	ip, ip, r6	@ mask in offset bits 31-24
-	orrne	ip, ip, r6	@ mask in offset bits 31-24
-	orreq	ip, ip, r0	@ mask in offset bits 23-16
 	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/hw_breakpoint.c

@@ -45,7 +45,6 @@ static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
 
 /* Number of BRP/WRP registers on this CPU. */
 static int core_num_brps;
-static int core_num_reserved_brps;
 static int core_num_wrps;
 
 /* Debug architecture version. */
@@ -137,10 +136,11 @@ static u8 get_debug_arch(void)
 	u32 didr;
 
 	/* Do we implement the extended CPUID interface? */
-	if (WARN_ONCE((((read_cpuid_id() >> 16) & 0xf) != 0xf),
+	if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
-	    "CPUID feature registers not supported. "
+		pr_warning("CPUID feature registers not supported. "
-	    "Assuming v6 debug is present.\n"))
+			   "Assuming v6 debug is present.\n");
 		return ARM_DEBUG_ARCH_V6;
+	}
 
 	ARM_DBG_READ(c0, 0, didr);
 	return (didr >> 16) & 0xf;
@@ -154,10 +154,21 @@ u8 arch_get_debug_arch(void)
 static int debug_arch_supported(void)
 {
 	u8 arch = get_debug_arch();
-	return arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14;
+
+	/* We don't support the memory-mapped interface. */
+	return (arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14) ||
+		arch >= ARM_DEBUG_ARCH_V7_1;
 }
 
-/* Determine number of BRP register available. */
+/* Determine number of WRP registers available. */
+static int get_num_wrp_resources(void)
+{
+	u32 didr;
+	ARM_DBG_READ(c0, 0, didr);
+	return ((didr >> 28) & 0xf) + 1;
+}
+
+/* Determine number of BRP registers available. */
 static int get_num_brp_resources(void)
 {
 	u32 didr;
@@ -176,9 +187,10 @@ static int core_has_mismatch_brps(void)
 static int get_num_wrps(void)
 {
 	/*
-	 * FIXME: When a watchpoint fires, the only way to work out which
+	 * On debug architectures prior to 7.1, when a watchpoint fires, the
-	 * watchpoint it was is by disassembling the faulting instruction
+	 * only way to work out which watchpoint it was is by disassembling
-	 * and working out the address of the memory access.
+	 * the faulting instruction and working out the address of the memory
+	 * access.
 	 *
 	 * Furthermore, we can only do this if the watchpoint was precise
 	 * since imprecise watchpoints prevent us from calculating register
@@ -192,36 +204,17 @@ static int get_num_wrps(void)
 	 * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows
 	 * that it is set on some implementations].
 	 */
+	if (get_debug_arch() < ARM_DEBUG_ARCH_V7_1)
+		return 1;
 
-#if 0
+	return get_num_wrp_resources();
-	int wrps;
-	u32 didr;
-	ARM_DBG_READ(c0, 0, didr);
-	wrps = ((didr >> 28) & 0xf) + 1;
-#endif
-	int wrps = 1;
-
-	if (core_has_mismatch_brps() && wrps >= get_num_brp_resources())
-		wrps = get_num_brp_resources() - 1;
-
-	return wrps;
-}
-
-/* We reserve one breakpoint for each watchpoint. */
-static int get_num_reserved_brps(void)
-{
-	if (core_has_mismatch_brps())
-		return get_num_wrps();
-	return 0;
 }
 
 /* Determine number of usable BRPs available. */
 static int get_num_brps(void)
 {
 	int brps = get_num_brp_resources();
-	if (core_has_mismatch_brps())
+	return core_has_mismatch_brps() ? brps - 1 : brps;
-		brps -= get_num_reserved_brps();
-	return brps;
 }
 
 /*
@@ -255,6 +248,7 @@ static int enable_monitor_mode(void)
 		ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN));
 		break;
 	case ARM_DEBUG_ARCH_V7_ECP14:
+	case ARM_DEBUG_ARCH_V7_1:
 		ARM_DBG_WRITE(c2, 2, (dscr | ARM_DSCR_MDBGEN));
 		break;
 	default:
@@ -346,24 +340,10 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		val_base = ARM_BASE_BVR;
 		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
 		max_slots = core_num_brps;
-		if (info->step_ctrl.enabled) {
-			/* Override the breakpoint data with the step data. */
-			addr = info->trigger & ~0x3;
-			ctrl = encode_ctrl_reg(info->step_ctrl);
-		}
 	} else {
 		/* Watchpoint */
-		if (info->step_ctrl.enabled) {
-			/* Install into the reserved breakpoint region. */
-			ctrl_base = ARM_BASE_BCR + core_num_brps;
-			val_base = ARM_BASE_BVR + core_num_brps;
-			/* Override the watchpoint data with the step data. */
-			addr = info->trigger & ~0x3;
-			ctrl = encode_ctrl_reg(info->step_ctrl);
-		} else {
 		ctrl_base = ARM_BASE_WCR;
 		val_base = ARM_BASE_WVR;
-		}
 		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
@@ -382,6 +362,17 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		goto out;
 	}
 
+	/* Override the breakpoint data with the step data. */
+	if (info->step_ctrl.enabled) {
+		addr = info->trigger & ~0x3;
+		ctrl = encode_ctrl_reg(info->step_ctrl);
+		if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE) {
+			i = 0;
+			ctrl_base = ARM_BASE_BCR + core_num_brps;
+			val_base = ARM_BASE_BVR + core_num_brps;
+		}
+	}
+
 	/* Setup the address register. */
 	write_wb_reg(val_base + i, addr);
 
@@ -405,9 +396,6 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
-		if (info->step_ctrl.enabled)
-			base = ARM_BASE_BCR + core_num_brps;
-		else
 		base = ARM_BASE_WCR;
 		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 		max_slots = core_num_wrps;
@@ -426,6 +414,13 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot\n"))
 		return;
 
+	/* Ensure that we disable the mismatch breakpoint. */
+	if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE &&
+	    info->step_ctrl.enabled) {
+		i = 0;
+		base = ARM_BASE_BCR + core_num_brps;
+	}
+
 	/* Reset the control register. */
 	write_wb_reg(base + i, 0);
 }
@@ -632,10 +627,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * we can use the mismatch feature as a poor-man's hardware
 	 * single-step, but this only works for per-task breakpoints.
 	 */
-	if (WARN_ONCE(!bp->overflow_handler &&
+	if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) ||
-		(arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_brps()
+	    !core_has_mismatch_brps() || !bp->hw.bp_target)) {
-		 || !bp->hw.bp_target),
+		pr_warning("overflow handler required but none found\n");
-			"overflow handler required but none found\n")) {
 		ret = -EINVAL;
 	}
 out:
@@ -666,34 +660,62 @@ static void disable_single_step(struct perf_event *bp)
 	arch_install_hw_breakpoint(bp);
 }
 
-static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
+static void watchpoint_handler(unsigned long addr, unsigned int fsr,
+			       struct pt_regs *regs)
 {
-	int i;
+	int i, access;
+	u32 val, ctrl_reg, alignment_mask;
 	struct perf_event *wp, **slots;
 	struct arch_hw_breakpoint *info;
+	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
-	/* Without a disassembler, we can only handle 1 watchpoint. */
-	BUG_ON(core_num_wrps > 1);
-
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
 		wp = slots[i];
 
-		if (wp == NULL) {
+		if (wp == NULL)
-			rcu_read_unlock();
+			goto unlock;
-			continue;
+
+		info = counter_arch_bp(wp);
+		/*
+		 * The DFAR is an unknown value on debug architectures prior
+		 * to 7.1. Since we only allow a single watchpoint on these
+		 * older CPUs, we can set the trigger to the lowest possible
+		 * faulting address.
+		 */
+		if (debug_arch < ARM_DEBUG_ARCH_V7_1) {
+			BUG_ON(i > 0);
+			info->trigger = wp->attr.bp_addr;
+		} else {
+			if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+				alignment_mask = 0x7;
+			else
+				alignment_mask = 0x3;
+
+			/* Check if the watchpoint value matches. */
+			val = read_wb_reg(ARM_BASE_WVR + i);
+			if (val != (addr & ~alignment_mask))
+				goto unlock;
+
+			/* Possible match, check the byte address select. */
+			ctrl_reg = read_wb_reg(ARM_BASE_WCR + i);
+			decode_ctrl_reg(ctrl_reg, &ctrl);
+			if (!((1 << (addr & alignment_mask)) & ctrl.len))
+				goto unlock;
+
+			/* Check that the access type matches. */
+			access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W :
+				 HW_BREAKPOINT_R;
+			if (!(access & hw_breakpoint_type(wp)))
+				goto unlock;
+
+			/* We have a winner. */
+			info->trigger = addr;
 		}
 
-		/*
-		 * The DFAR is an unknown value. Since we only allow a
-		 * single watchpoint, we can set the trigger to the lowest
-		 * possible faulting address.
-		 */
-		info = counter_arch_bp(wp);
-		info->trigger = wp->attr.bp_addr;
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
 		perf_bp_event(wp, regs);
 
@@ -705,6 +727,7 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
 		if (!wp->overflow_handler)
 			enable_single_step(wp, instruction_pointer(regs));
 
+unlock:
 		rcu_read_unlock();
 	}
 }
@@ -717,7 +740,7 @@ static void watchpoint_single_step_handler(unsigned long pc)
 
 	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
 
-	for (i = 0; i < core_num_reserved_brps; ++i) {
+	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
 
 		wp = slots[i];
@@ -820,7 +843,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
 		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
 	case ARM_ENTRY_SYNC_WATCHPOINT:
-		watchpoint_handler(addr, regs);
+		watchpoint_handler(addr, fsr, regs);
 		break;
 	default:
 		ret = 1; /* Unhandled fault. */
@@ -834,11 +857,31 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 /*
  * One-time initialisation.
  */
-static void reset_ctrl_regs(void *info)
+static cpumask_t debug_err_mask;
+
+static int debug_reg_trap(struct pt_regs *regs, unsigned int instr)
 {
-	int i, cpu = smp_processor_id();
+	int cpu = smp_processor_id();
+
+	pr_warning("Debug register access (0x%x) caused undefined instruction on CPU %d\n",
+		   instr, cpu);
+
+	/* Set the error flag for this CPU and skip the faulting instruction. */
+	cpumask_set_cpu(cpu, &debug_err_mask);
+	instruction_pointer(regs) += 4;
+	return 0;
+}
+
+static struct undef_hook debug_reg_hook = {
+	.instr_mask	= 0x0fe80f10,
+	.instr_val	= 0x0e000e10,
+	.fn		= debug_reg_trap,
+};
+
+static void reset_ctrl_regs(void *unused)
+{
+	int i, raw_num_brps, err = 0, cpu = smp_processor_id();
 	u32 dbg_power;
-	cpumask_t *cpumask = info;
 
 	/*
 	 * v7 debug contains save and restore registers so that debug state
@@ -848,15 +891,33 @@ static void reset_ctrl_regs(void *info)
 	 * Access Register to avoid taking undefined instruction exceptions
 	 * later on.
 	 */
-	if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) {
+	switch (debug_arch) {
+	case ARM_DEBUG_ARCH_V6:
+	case ARM_DEBUG_ARCH_V6_1:
+		/* ARMv6 cores just need to reset the registers. */
+		goto reset_regs;
+	case ARM_DEBUG_ARCH_V7_ECP14:
 		/*
 		 * Ensure sticky power-down is clear (i.e. debug logic is
 		 * powered up).
 		 */
 		asm volatile("mrc p14, 0, %0, c1, c5, 4" : "=r" (dbg_power));
-		if ((dbg_power & 0x1) == 0) {
+		if ((dbg_power & 0x1) == 0)
+			err = -EPERM;
+		break;
+	case ARM_DEBUG_ARCH_V7_1:
+		/*
+		 * Ensure the OS double lock is clear.
+		 */
+		asm volatile("mrc p14, 0, %0, c1, c3, 4" : "=r" (dbg_power));
+		if ((dbg_power & 0x1) == 1)
+			err = -EPERM;
+		break;
+	}
+
+	if (err) {
 		pr_warning("CPU %d debug is powered down!\n", cpu);
-			cpumask_or(cpumask, cpumask, cpumask_of(cpu));
+		cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu));
 		return;
 	}
 
@@ -873,13 +934,14 @@ static void reset_ctrl_regs(void *info)
 	 */
 	asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0));
 	isb();
-	}
 
+reset_regs:
 	if (enable_monitor_mode())
 		return;
 
 	/* We must also reset any reserved registers. */
-	for (i = 0; i < core_num_brps + core_num_reserved_brps; ++i) {
+	raw_num_brps = get_num_brp_resources();
+	for (i = 0; i < raw_num_brps; ++i) {
 		write_wb_reg(ARM_BASE_BCR + i, 0UL);
 		write_wb_reg(ARM_BASE_BVR + i, 0UL);
 	}
@@ -895,6 +957,7 @@ static int __cpuinit dbg_reset_notify(struct notifier_block *self,
 {
 	if (action == CPU_ONLINE)
 		smp_call_function_single((int)cpu, reset_ctrl_regs, NULL, 1);
+
 	return NOTIFY_OK;
 }
 
@@ -905,7 +968,6 @@ static struct notifier_block __cpuinitdata dbg_reset_nb = {
 static int __init arch_hw_breakpoint_init(void)
 {
 	u32 dscr;
-	cpumask_t cpumask = { CPU_BITS_NONE };
 
 	debug_arch = get_debug_arch();
 
@@ -916,28 +978,31 @@ static int __init arch_hw_breakpoint_init(void)
 
 	/* Determine how many BRPs/WRPs are available. */
 	core_num_brps = get_num_brps();
-	core_num_reserved_brps = get_num_reserved_brps();
 	core_num_wrps = get_num_wrps();
 
-	pr_info("found %d breakpoint and %d watchpoint registers.\n",
+	/*
-		core_num_brps + core_num_reserved_brps, core_num_wrps);
+	 * We need to tread carefully here because DBGSWENABLE may be
-
+	 * driven low on this core and there isn't an architected way to
-	if (core_num_reserved_brps)
+	 * determine that.
-		pr_info("%d breakpoint(s) reserved for watchpoint "
+	 */
-				"single-step.\n", core_num_reserved_brps);
+	register_undef_hook(&debug_reg_hook);
 
 	/*
 	 * Reset the breakpoint resources. We assume that a halting
 	 * debugger will leave the world in a nice state for us.
 	 */
-	on_each_cpu(reset_ctrl_regs, &cpumask, 1);
+	on_each_cpu(reset_ctrl_regs, NULL, 1);
-	if (!cpumask_empty(&cpumask)) {
+	unregister_undef_hook(&debug_reg_hook);
+	if (!cpumask_empty(&debug_err_mask)) {
 		core_num_brps = 0;
-		core_num_reserved_brps = 0;
 		core_num_wrps = 0;
 		return 0;
 	}
 
+	pr_info("found %d " "%s" "breakpoint and %d watchpoint registers.\n",
+		core_num_brps, core_has_mismatch_brps() ? "(+1 reserved) " :
+		"", core_num_wrps);
+
 	ARM_DBG_READ(c1, 0, dscr);
 	if (dscr & ARM_DSCR_HDBGEN) {
 		max_watchpoint_len = 4;

arch/arm/kernel/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-test.h

@@ -0,0 +1,392 @@
+/*
+ * arch/arm/kernel/kprobes-test.h
+ *
+ * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define VERBOSE 0 /* Set to '1' for more logging of test cases */
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define NORMAL_ISA "16"
+#else
+#define NORMAL_ISA "32"
+#endif
+
+
+/* Flags used in kprobe_test_flags */
+#define TEST_FLAG_NO_ITBLOCK	(1<<0)
+#define TEST_FLAG_FULL_ITBLOCK	(1<<1)
+#define TEST_FLAG_NARROW_INSTR	(1<<2)
+
+extern int kprobe_test_flags;
+extern int kprobe_test_cc_position;
+
+
+#define TEST_MEMORY_SIZE 256
+
+
+/*
+ * Test case structures.
+ *
+ * The arguments given to test cases can be one of three types.
+ *
+ *   ARG_TYPE_REG
+ *	Load a register with the given value.
+ *
+ *   ARG_TYPE_PTR
+ *	Load a register with a pointer into the stack buffer (SP + given value).
+ *
+ *   ARG_TYPE_MEM
+ *	Store the given value into the stack buffer at [SP+index].
+ *
+ */
+
+#define	ARG_TYPE_END	0
+#define	ARG_TYPE_REG	1
+#define	ARG_TYPE_PTR	2
+#define	ARG_TYPE_MEM	3
+
+#define ARG_FLAG_UNSUPPORTED	0x01
+#define ARG_FLAG_SUPPORTED	0x02
+#define ARG_FLAG_THUMB		0x10	/* Must be 16 so TEST_ISA can be used */
+#define ARG_FLAG_ARM		0x20	/* Must be 32 so TEST_ISA can be used */
+
+struct test_arg {
+	u8	type;		/* ARG_TYPE_x */
+	u8	_padding[7];
+};
+
+struct test_arg_regptr {
+	u8	type;		/* ARG_TYPE_REG or ARG_TYPE_PTR */
+	u8	reg;
+	u8	_padding[2];
+	u32	val;
+};
+
+struct test_arg_mem {
+	u8	type;		/* ARG_TYPE_MEM */
+	u8	index;
+	u8	_padding[2];
+	u32	val;
+};
+
+struct test_arg_end {
+	u8	type;		/* ARG_TYPE_END */
+	u8	flags;		/* ARG_FLAG_x */
+	u16	code_offset;
+	u16	branch_offset;
+	u16	end_offset;
+};
+
+
+/*
+ * Building blocks for test cases.
+ *
+ * Each test case is wrapped between TESTCASE_START and TESTCASE_END.
+ *
+ * To specify arguments for a test case the TEST_ARG_{REG,PTR,MEM} macros are
+ * used followed by a terminating TEST_ARG_END.
+ *
+ * After this, the instruction to be tested is defined with TEST_INSTRUCTION.
+ * Or for branches, TEST_BRANCH_B and TEST_BRANCH_F (branch forwards/backwards).
+ *
+ * Some specific test cases may make use of other custom constructs.
+ */
+
+#if VERBOSE
+#define verbose(fmt, ...) pr_info(fmt, ##__VA_ARGS__)
+#else
+#define verbose(fmt, ...)
+#endif
+
+#define TEST_GROUP(title)					\
+	verbose("\n");						\
+	verbose(title"\n");					\
+	verbose("---------------------------------------------------------\n");
+
+#define TESTCASE_START(title)					\
+	__asm__ __volatile__ (					\
+	"bl	__kprobes_test_case_start		\n\t"	\
+	/* don't use .asciz here as 'title' may be */		\
+	/* multiple strings to be concatenated.  */		\
+	".ascii "#title"				\n\t"	\
+	".byte	0					\n\t"	\
+	".align	2					\n\t"
+
+#define	TEST_ARG_REG(reg, val)					\
+	".byte	"__stringify(ARG_TYPE_REG)"		\n\t"	\
+	".byte	"#reg"					\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_PTR(reg, val)					\
+	".byte	"__stringify(ARG_TYPE_PTR)"		\n\t"	\
+	".byte	"#reg"					\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_MEM(index, val)				\
+	".byte	"__stringify(ARG_TYPE_MEM)"		\n\t"	\
+	".byte	"#index"				\n\t"	\
+	".short	0					\n\t"	\
+	".word	"#val"					\n\t"
+
+#define	TEST_ARG_END(flags)					\
+	".byte	"__stringify(ARG_TYPE_END)"		\n\t"	\
+	".byte	"TEST_ISA flags"			\n\t"	\
+	".short	50f-0f					\n\t"	\
+	".short	2f-0f					\n\t"	\
+	".short	99f-0f					\n\t"	\
+	".code "TEST_ISA"				\n\t"	\
+	"0:						\n\t"
+
+#define TEST_INSTRUCTION(instruction)				\
+	"50:	nop					\n\t"	\
+	"1:	"instruction"				\n\t"	\
+	"	nop					\n\t"
+
+#define TEST_BRANCH_F(instruction, xtra_dist)			\
+	TEST_INSTRUCTION(instruction)				\
+	".if "#xtra_dist"				\n\t"	\
+	"	b	99f				\n\t"	\
+	".space "#xtra_dist"				\n\t"	\
+	".endif						\n\t"	\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"
+
+#define TEST_BRANCH_B(instruction, xtra_dist)			\
+	"	b	50f				\n\t"	\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"	\
+	"	b	99f				\n\t"	\
+	".if "#xtra_dist"				\n\t"	\
+	".space "#xtra_dist"				\n\t"	\
+	".endif						\n\t"	\
+	TEST_INSTRUCTION(instruction)
+
+#define TESTCASE_END						\
+	"2:						\n\t"	\
+	"99:						\n\t"	\
+	"	bl __kprobes_test_case_end_"TEST_ISA"	\n\t"	\
+	".code "NORMAL_ISA"				\n\t"	\
+	: :							\
+	: "r0", "r1", "r2", "r3", "ip", "lr", "memory", "cc"	\
+	);
+
+
+/*
+ * Macros to define test cases.
+ *
+ * Those of the form TEST_{R,P,M}* can be used to define test cases
+ * which take combinations of the three basic types of arguments. E.g.
+ *
+ *   TEST_R	One register argument
+ *   TEST_RR	Two register arguments
+ *   TEST_RPR	A register, a pointer, then a register argument
+ *
+ * For testing instructions which may branch, there are macros TEST_BF_*
+ * and TEST_BB_* for branching forwards and backwards.
+ *
+ * TEST_SUPPORTED and TEST_UNSUPPORTED don't cause the code to be executed,
+ * the just verify that a kprobe is or is not allowed on the given instruction.
+ */
+
+#define TEST(code)				\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code)			\
+	TESTCASE_END
+
+#define TEST_UNSUPPORTED(code)					\
+	TESTCASE_START(code)					\
+	TEST_ARG_END("|"__stringify(ARG_FLAG_UNSUPPORTED))	\
+	TEST_INSTRUCTION(code)					\
+	TESTCASE_END
+
+#define TEST_SUPPORTED(code)					\
+	TESTCASE_START(code)					\
+	TEST_ARG_END("|"__stringify(ARG_FLAG_SUPPORTED))	\
+	TEST_INSTRUCTION(code)					\
+	TESTCASE_END
+
+#define TEST_R(code1, reg, val, code2)			\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_INSTRUCTION(code1 #reg code2)		\
+	TESTCASE_END
+
+#define TEST_RR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_RRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RRRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4, reg4, val4)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4 #reg4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_REG(reg4, val4)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4 #reg4)	\
+	TESTCASE_END
+
+#define TEST_P(code1, reg1, val1, code2)	\
+	TESTCASE_START(code1 #reg1 code2)	\
+	TEST_ARG_PTR(reg1, val1)		\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code1 #reg1 code2)	\
+	TESTCASE_END
+
+#define TEST_PR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_PTR(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_RP(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_PTR(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_PRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_PTR(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RPR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_PTR(reg2, val2)						\
+	TEST_ARG_REG(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_RRP(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_PTR(reg3, val3)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4)		\
+	TESTCASE_END
+
+#define TEST_BF_P(code1, reg1, val1, code2)	\
+	TESTCASE_START(code1 #reg1 code2)	\
+	TEST_ARG_PTR(reg1, val1)		\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_F(code1 #reg1 code2, 0)	\
+	TESTCASE_END
+
+#define TEST_BF_X(code, xtra_dist)		\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_F(code, xtra_dist)		\
+	TESTCASE_END
+
+#define TEST_BB_X(code, xtra_dist)		\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_B(code, xtra_dist)		\
+	TESTCASE_END
+
+#define TEST_BF_RX(code1, reg, val, code2, xtra_dist)	\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_BRANCH_F(code1 #reg code2, xtra_dist)	\
+	TESTCASE_END
+
+#define TEST_BB_RX(code1, reg, val, code2, xtra_dist)	\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_BRANCH_B(code1 #reg code2, xtra_dist)	\
+	TESTCASE_END
+
+#define TEST_BF(code)	TEST_BF_X(code, 0)
+#define TEST_BB(code)	TEST_BB_X(code, 0)
+
+#define TEST_BF_R(code1, reg, val, code2) TEST_BF_RX(code1, reg, val, code2, 0)
+#define TEST_BB_R(code1, reg, val, code2) TEST_BB_RX(code1, reg, val, code2, 0)
+
+#define TEST_BF_RR(code1, reg1, val1, code2, reg2, val2, code3)	\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
+	TEST_ARG_REG(reg1, val1)				\
+	TEST_ARG_REG(reg2, val2)				\
+	TEST_ARG_END("")					\
+	TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3, 0)		\
+	TESTCASE_END
+
+#define TEST_X(code, codex)			\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_INSTRUCTION(code)			\
+	"	b	99f		\n\t"	\
+	"	"codex"			\n\t"	\
+	TESTCASE_END
+
+#define TEST_RX(code1, reg, val, code2, codex)		\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_INSTRUCTION(code1 __stringify(reg) code2)	\
+	"	b	99f		\n\t"		\
+	"	"codex"			\n\t"		\
+	TESTCASE_END
+
+#define TEST_RRX(code1, reg1, val1, code2, reg2, val2, code3, codex)		\
+	TESTCASE_START(code1 #reg1 code2 #reg2 code3)				\
+	TEST_ARG_REG(reg1, val1)						\
+	TEST_ARG_REG(reg2, val2)						\
+	TEST_ARG_END("")							\
+	TEST_INSTRUCTION(code1 __stringify(reg1) code2 __stringify(reg2) code3)	\
+	"	b	99f		\n\t"					\
+	"	"codex"			\n\t"					\
+	TESTCASE_END
+
+
+/* Various values used in test cases... */
+#define N(val)	(val ^ 0xffffffff)
+#define VAL1	0x12345678
+#define VAL2	N(VAL1)
+#define VAL3	0xa5f801
+#define VAL4	N(VAL3)
+#define VALM	0x456789ab
+#define VALR	0xdeaddead
+#define HH1	0x0123fecb
+#define HH2	0xa9874567
+
+
+#ifdef CONFIG_THUMB2_KERNEL
+void kprobe_thumb16_test_cases(void);
+void kprobe_thumb32_test_cases(void);
+#else
+void kprobe_arm_test_cases(void);
+#endif

arch/arm/kernel/kprobes-thumb.c

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

arch/arm/kernel/kprobes.h

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

arch/arm/kernel/perf_event.c

@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/bitmap.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -26,16 +27,8 @@
 #include <asm/pmu.h>
 #include <asm/stacktrace.h>
 
-static struct platform_device *pmu_device;
-
 /*
- * Hardware lock to serialize accesses to PMU registers. Needed for the
+ * ARMv6 supports a maximum of 3 events, starting from index 0. If we add
- * read/modify/write sequences.
- */
-static DEFINE_RAW_SPINLOCK(pmu_lock);
-
-/*
- * ARMv6 supports a maximum of 3 events, starting from index 1. If we add
  * another platform that supports more, we need to increase this to be the
  * largest of all platforms.
  *
@@ -43,62 +36,24 @@ static DEFINE_RAW_SPINLOCK(pmu_lock);
  *  cycle counter CCNT + 31 events counters CNT0..30.
  *  Cortex-A8 has 1+4 counters, Cortex-A9 has 1+6 counters.
  */
-#define ARMPMU_MAX_HWEVENTS		33
+#define ARMPMU_MAX_HWEVENTS		32
 
-/* The events for a given CPU. */
+static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
-struct cpu_hw_events {
+static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
-	/*
+static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
-	 * The events that are active on the CPU for the given index. Index 0
-	 * is reserved.
-	 */
-	struct perf_event	*events[ARMPMU_MAX_HWEVENTS];
 
-	/*
+#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
-	 * 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[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
-
-	/*
-	 * A 1 bit for an index indicates that the counter is actively being
-	 * used.
-	 */
-	unsigned long		active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
-};
-static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
-
-struct arm_pmu {
-	enum arm_perf_pmu_ids id;
-	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 cpu_hw_events *cpuc,
-					 struct hw_perf_event *hwc);
-	u32		(*read_counter)(int idx);
-	void		(*write_counter)(int idx, u32 val);
-	void		(*start)(void);
-	void		(*stop)(void);
-	void		(*reset)(void *);
-	const unsigned	(*cache_map)[PERF_COUNT_HW_CACHE_MAX]
-				    [PERF_COUNT_HW_CACHE_OP_MAX]
-				    [PERF_COUNT_HW_CACHE_RESULT_MAX];
-	const unsigned	(*event_map)[PERF_COUNT_HW_MAX];
-	u32		raw_event_mask;
-	int		num_events;
-	u64		max_period;
-};
 
 /* Set at runtime when we know what CPU type we are. */
-static const struct arm_pmu *armpmu;
+static struct arm_pmu *cpu_pmu;
 
 enum arm_perf_pmu_ids
 armpmu_get_pmu_id(void)
 {
 	int id = -ENODEV;
 
-	if (armpmu != NULL)
+	if (cpu_pmu != NULL)
-		id = armpmu->id;
+		id = cpu_pmu->id;
 
 	return id;
 }
@@ -109,8 +64,8 @@ armpmu_get_max_events(void)
 {
 	int max_events = 0;
 
-	if (armpmu != NULL)
+	if (cpu_pmu != NULL)
-		max_events = armpmu->num_events;
+		max_events = cpu_pmu->num_events;
 
 	return max_events;
 }
@@ -130,7 +85,11 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 #define CACHE_OP_UNSUPPORTED		0xFFFF
 
 static int
-armpmu_map_cache_event(u64 config)
+armpmu_map_cache_event(const unsigned (*cache_map)
+				      [PERF_COUNT_HW_CACHE_MAX]
+				      [PERF_COUNT_HW_CACHE_OP_MAX]
+				      [PERF_COUNT_HW_CACHE_RESULT_MAX],
+		       u64 config)
 {
 	unsigned int cache_type, cache_op, cache_result, ret;
 
@@ -146,7 +105,7 @@ armpmu_map_cache_event(u64 config)
 	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
 		return -EINVAL;
 
-	ret = (int)(*armpmu->cache_map)[cache_type][cache_op][cache_result];
+	ret = (int)(*cache_map)[cache_type][cache_op][cache_result];
 
 	if (ret == CACHE_OP_UNSUPPORTED)
 		return -ENOENT;
@@ -155,23 +114,46 @@ armpmu_map_cache_event(u64 config)
 }
 
 static int
-armpmu_map_event(u64 config)
+armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-	int mapping = (*armpmu->event_map)[config];
+	int mapping = (*event_map)[config];
-	return mapping == HW_OP_UNSUPPORTED ? -EOPNOTSUPP : mapping;
+	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
 static int
-armpmu_map_raw_event(u64 config)
+armpmu_map_raw_event(u32 raw_event_mask, u64 config)
 {
-	return (int)(config & armpmu->raw_event_mask);
+	return (int)(config & raw_event_mask);
 }
 
-static int
+static int map_cpu_event(struct perf_event *event,
+			 const unsigned (*event_map)[PERF_COUNT_HW_MAX],
+			 const unsigned (*cache_map)
+					[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX],
+			 u32 raw_event_mask)
+{
+	u64 config = event->attr.config;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		return armpmu_map_event(event_map, config);
+	case PERF_TYPE_HW_CACHE:
+		return armpmu_map_cache_event(cache_map, config);
+	case PERF_TYPE_RAW:
+		return armpmu_map_raw_event(raw_event_mask, config);
+	}
+
+	return -ENOENT;
+}
+
+int
 armpmu_event_set_period(struct perf_event *event,
 			struct hw_perf_event *hwc,
 			int idx)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
 	int ret = 0;
@@ -202,11 +184,12 @@ armpmu_event_set_period(struct perf_event *event,
 	return ret;
 }
 
-static u64
+u64
 armpmu_event_update(struct perf_event *event,
 		    struct hw_perf_event *hwc,
 		    int idx, int overflow)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	u64 delta, prev_raw_count, new_raw_count;
 
 again:
@@ -246,11 +229,9 @@ armpmu_read(struct perf_event *event)
 static void
 armpmu_stop(struct perf_event *event, int flags)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!armpmu)
-		return;
-
 	/*
 	 * ARM pmu always has to update the counter, so ignore
 	 * PERF_EF_UPDATE, see comments in armpmu_start().
@@ -266,11 +247,9 @@ armpmu_stop(struct perf_event *event, int flags)
 static void
 armpmu_start(struct perf_event *event, int flags)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!armpmu)
-		return;
-
 	/*
 	 * ARM pmu always has to reprogram the period, so ignore
 	 * PERF_EF_RELOAD, see the comment below.
@@ -293,16 +272,16 @@ armpmu_start(struct perf_event *event, int flags)
 static void
 armpmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
 	WARN_ON(idx < 0);
 
-	clear_bit(idx, cpuc->active_mask);
 	armpmu_stop(event, PERF_EF_UPDATE);
-	cpuc->events[idx] = NULL;
+	hw_events->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
+	clear_bit(idx, hw_events->used_mask);
 
 	perf_event_update_userpage(event);
 }
@@ -310,7 +289,8 @@ armpmu_del(struct perf_event *event, int flags)
 static int
 armpmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
@@ -318,7 +298,7 @@ armpmu_add(struct perf_event *event, int flags)
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
-	idx = armpmu->get_event_idx(cpuc, hwc);
+	idx = armpmu->get_event_idx(hw_events, hwc);
 	if (idx < 0) {
 		err = idx;
 		goto out;
@@ -330,8 +310,7 @@ armpmu_add(struct perf_event *event, int flags)
 	 */
 	event->hw.idx = idx;
 	armpmu->disable(hwc, idx);
-	cpuc->events[idx] = event;
+	hw_events->events[idx] = event;
-	set_bit(idx, cpuc->active_mask);
 
 	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
 	if (flags & PERF_EF_START)
@@ -345,25 +324,25 @@ armpmu_add(struct perf_event *event, int flags)
 	return err;
 }
 
-static struct pmu pmu;
-
 static int
-validate_event(struct cpu_hw_events *cpuc,
+validate_event(struct pmu_hw_events *hw_events,
 	       struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event fake_event = event->hw;
+	struct pmu *leader_pmu = event->group_leader->pmu;
 
-	if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
 		return 1;
 
-	return armpmu->get_event_idx(cpuc, &fake_event) >= 0;
+	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
 }
 
 static int
 validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
-	struct cpu_hw_events fake_pmu;
+	struct pmu_hw_events fake_pmu;
 
 	memset(&fake_pmu, 0, sizeof(fake_pmu));
 
@@ -383,110 +362,119 @@ validate_group(struct perf_event *event)
 
 static irqreturn_t armpmu_platform_irq(int irq, void *dev)
 {
-	struct arm_pmu_platdata *plat = dev_get_platdata(&pmu_device->dev);
+	struct arm_pmu *armpmu = (struct arm_pmu *) dev;
+	struct platform_device *plat_device = armpmu->plat_device;
+	struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev);
 
 	return plat->handle_irq(irq, dev, armpmu->handle_irq);
 }
 
+static void
+armpmu_release_hardware(struct arm_pmu *armpmu)
+{
+	int i, irq, irqs;
+	struct platform_device *pmu_device = armpmu->plat_device;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+
+	for (i = 0; i < irqs; ++i) {
+		if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
+			continue;
+		irq = platform_get_irq(pmu_device, i);
+		if (irq >= 0)
+			free_irq(irq, armpmu);
+	}
+
+	release_pmu(armpmu->type);
+}
+
 static int
-armpmu_reserve_hardware(void)
+armpmu_reserve_hardware(struct arm_pmu *armpmu)
 {
 	struct arm_pmu_platdata *plat;
 	irq_handler_t handle_irq;
-	int i, err = -ENODEV, irq;
+	int i, err, irq, irqs;
+	struct platform_device *pmu_device = armpmu->plat_device;
 
-	pmu_device = reserve_pmu(ARM_PMU_DEVICE_CPU);
+	err = reserve_pmu(armpmu->type);
-	if (IS_ERR(pmu_device)) {
+	if (err) {
 		pr_warning("unable to reserve pmu\n");
-		return PTR_ERR(pmu_device);
+		return err;
 	}
 
-	init_pmu(ARM_PMU_DEVICE_CPU);
-
 	plat = dev_get_platdata(&pmu_device->dev);
 	if (plat && plat->handle_irq)
 		handle_irq = armpmu_platform_irq;
 	else
 		handle_irq = armpmu->handle_irq;
 
-	if (pmu_device->num_resources < 1) {
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (irqs < 1) {
 		pr_err("no irqs for PMUs defined\n");
 		return -ENODEV;
 	}
 
-	for (i = 0; i < pmu_device->num_resources; ++i) {
+	for (i = 0; i < irqs; ++i) {
+		err = 0;
 		irq = platform_get_irq(pmu_device, i);
 		if (irq < 0)
 			continue;
 
+		/*
+		 * If we have a single PMU interrupt that we can't shift,
+		 * assume that we're running on a uniprocessor machine and
+		 * continue. Otherwise, continue without this interrupt.
+		 */
+		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+				    irq, i);
+			continue;
+		}
+
 		err = request_irq(irq, handle_irq,
 				  IRQF_DISABLED | IRQF_NOBALANCING,
-				  "armpmu", NULL);
+				  "arm-pmu", armpmu);
 		if (err) {
-			pr_warning("unable to request IRQ%d for ARM perf "
+			pr_err("unable to request IRQ%d for ARM PMU counters\n",
-				"counters\n", irq);
+				irq);
-			break;
+			armpmu_release_hardware(armpmu);
-		}
-	}
-
-	if (err) {
-		for (i = i - 1; i >= 0; --i) {
-			irq = platform_get_irq(pmu_device, i);
-			if (irq >= 0)
-				free_irq(irq, NULL);
-		}
-		release_pmu(ARM_PMU_DEVICE_CPU);
-		pmu_device = NULL;
-	}
-
 			return err;
 		}
 
-static void
+		cpumask_set_cpu(i, &armpmu->active_irqs);
-armpmu_release_hardware(void)
-{
-	int i, irq;
-
-	for (i = pmu_device->num_resources - 1; i >= 0; --i) {
-		irq = platform_get_irq(pmu_device, i);
-		if (irq >= 0)
-			free_irq(irq, NULL);
-	}
-	armpmu->stop();
-
-	release_pmu(ARM_PMU_DEVICE_CPU);
-	pmu_device = NULL;
 	}
 
-static atomic_t active_events = ATOMIC_INIT(0);
+	return 0;
-static DEFINE_MUTEX(pmu_reserve_mutex);
+}
 
 static void
 hw_perf_event_destroy(struct perf_event *event)
 {
-	if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-		armpmu_release_hardware();
+	atomic_t *active_events	 = &armpmu->active_events;
-		mutex_unlock(&pmu_reserve_mutex);
+	struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;
+
+	if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
+		armpmu_release_hardware(armpmu);
+		mutex_unlock(pmu_reserve_mutex);
 	}
 }
 
+static int
+event_requires_mode_exclusion(struct perf_event_attr *attr)
+{
+	return attr->exclude_idle || attr->exclude_user ||
+	       attr->exclude_kernel || attr->exclude_hv;
+}
+
 static int
 __hw_perf_event_init(struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	int mapping, err;
 
-	/* Decode the generic type into an ARM event identifier. */
+	mapping = armpmu->map_event(event);
-	if (PERF_TYPE_HARDWARE == event->attr.type) {
-		mapping = armpmu_map_event(event->attr.config);
-	} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
-		mapping = armpmu_map_cache_event(event->attr.config);
-	} else if (PERF_TYPE_RAW == event->attr.type) {
-		mapping = armpmu_map_raw_event(event->attr.config);
-	} else {
-		pr_debug("event type %x not supported\n", event->attr.type);
-		return -EOPNOTSUPP;
-	}
 
 	if (mapping < 0) {
 		pr_debug("event %x:%llx not supported\n", event->attr.type,
@@ -494,18 +482,6 @@ __hw_perf_event_init(struct perf_event *event)
 		return mapping;
 	}
 
-	/*
-	 * Check whether we need to exclude the counter from certain modes.
-	 * The ARM performance counters are on all of the time so if someone
-	 * has asked us for some excludes then we have to fail.
-	 */
-	if (event->attr.exclude_kernel || event->attr.exclude_user ||
-	    event->attr.exclude_hv || event->attr.exclude_idle) {
-		pr_debug("ARM performance counters do not support "
-			 "mode exclusion\n");
-		return -EPERM;
-	}
-
 	/*
 	 * We don't assign an index until we actually place the event onto
 	 * hardware. Use -1 to signify that we haven't decided where to put it
@@ -513,17 +489,26 @@ __hw_perf_event_init(struct perf_event *event)
 	 * clever allocation or constraints checking at this point.
 	 */
 	hwc->idx		= -1;
-
+	hwc->config_base	= 0;
-	/*
-	 * Store the event encoding into the config_base field. config and
-	 * event_base are unused as the only 2 things we need to know are
-	 * the event mapping and the counter to use. The counter to use is
-	 * also the indx and the config_base is the event type.
-	 */
-	hwc->config_base	    = (unsigned long)mapping;
 	hwc->config		= 0;
 	hwc->event_base		= 0;
 
+	/*
+	 * Check whether we need to exclude the counter from certain modes.
+	 */
+	if ((!armpmu->set_event_filter ||
+	     armpmu->set_event_filter(hwc, &event->attr)) &&
+	     event_requires_mode_exclusion(&event->attr)) {
+		pr_debug("ARM performance counters do not support "
+			 "mode exclusion\n");
+		return -EPERM;
+	}
+
+	/*
+	 * Store the event encoding into the config_base field.
+	 */
+	hwc->config_base	    |= (unsigned long)mapping;
+
 	if (!hwc->sample_period) {
 		hwc->sample_period  = armpmu->max_period;
 		hwc->last_period    = hwc->sample_period;
@@ -542,32 +527,23 @@ __hw_perf_event_init(struct perf_event *event)
 
 static int armpmu_event_init(struct perf_event *event)
 {
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	int err = 0;
+	atomic_t *active_events = &armpmu->active_events;
 
-	switch (event->attr.type) {
+	if (armpmu->map_event(event) == -ENOENT)
-	case PERF_TYPE_RAW:
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-		break;
-
-	default:
 		return -ENOENT;
-	}
-
-	if (!armpmu)
-		return -ENODEV;
 
 	event->destroy = hw_perf_event_destroy;
 
-	if (!atomic_inc_not_zero(&active_events)) {
+	if (!atomic_inc_not_zero(active_events)) {
-		mutex_lock(&pmu_reserve_mutex);
+		mutex_lock(&armpmu->reserve_mutex);
-		if (atomic_read(&active_events) == 0) {
+		if (atomic_read(active_events) == 0)
-			err = armpmu_reserve_hardware();
+			err = armpmu_reserve_hardware(armpmu);
-		}
 
 		if (!err)
-			atomic_inc(&active_events);
+			atomic_inc(active_events);
-		mutex_unlock(&pmu_reserve_mutex);
+		mutex_unlock(&armpmu->reserve_mutex);
 	}
 
 	if (err)
@@ -582,22 +558,9 @@ static int armpmu_event_init(struct perf_event *event)
 
 static void armpmu_enable(struct pmu *pmu)
 {
-	/* Enable all of the perf events on hardware. */
+	struct arm_pmu *armpmu = to_arm_pmu(pmu);
-	int idx, enabled = 0;
+	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
-
-	if (!armpmu)
-		return;
-
-	for (idx = 0; idx <= armpmu->num_events; ++idx) {
-		struct perf_event *event = cpuc->events[idx];
-
-		if (!event)
-			continue;
-
-		armpmu->enable(&event->hw, idx);
-		enabled = 1;
-	}
 
 	if (enabled)
 		armpmu->start();
@@ -605,11 +568,16 @@ static void armpmu_enable(struct pmu *pmu)
 
 static void armpmu_disable(struct pmu *pmu)
 {
-	if (armpmu)
+	struct arm_pmu *armpmu = to_arm_pmu(pmu);
 	armpmu->stop();
 }
 
-static struct pmu pmu = {
+static void __init armpmu_init(struct arm_pmu *armpmu)
+{
+	atomic_set(&armpmu->active_events, 0);
+	mutex_init(&armpmu->reserve_mutex);
+
+	armpmu->pmu = (struct pmu) {
 		.pmu_enable	= armpmu_enable,
 		.pmu_disable	= armpmu_disable,
 		.event_init	= armpmu_event_init,
@@ -619,6 +587,13 @@ static struct pmu pmu = {
 		.stop		= armpmu_stop,
 		.read		= armpmu_read,
 	};
+}
+
+int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type)
+{
+	armpmu_init(armpmu);
+	return perf_pmu_register(&armpmu->pmu, name, type);
+}
 
 /* Include the PMU-specific implementations. */
 #include "perf_event_xscale.c"
@@ -630,14 +605,72 @@ static struct pmu pmu = {
  * This requires SMP to be available, so exists as a separate initcall.
  */
 static int __init
-armpmu_reset(void)
+cpu_pmu_reset(void)
 {
-	if (armpmu && armpmu->reset)
+	if (cpu_pmu && cpu_pmu->reset)
-		return on_each_cpu(armpmu->reset, NULL, 1);
+		return on_each_cpu(cpu_pmu->reset, NULL, 1);
 	return 0;
 }
-arch_initcall(armpmu_reset);
+arch_initcall(cpu_pmu_reset);
 
+/*
+ * PMU platform driver and devicetree bindings.
+ */
+static struct of_device_id armpmu_of_device_ids[] = {
+	{.compatible = "arm,cortex-a9-pmu"},
+	{.compatible = "arm,cortex-a8-pmu"},
+	{.compatible = "arm,arm1136-pmu"},
+	{.compatible = "arm,arm1176-pmu"},
+	{},
+};
+
+static struct platform_device_id armpmu_plat_device_ids[] = {
+	{.name = "arm-pmu"},
+	{},
+};
+
+static int __devinit armpmu_device_probe(struct platform_device *pdev)
+{
+	cpu_pmu->plat_device = pdev;
+	return 0;
+}
+
+static struct platform_driver armpmu_driver = {
+	.driver		= {
+		.name	= "arm-pmu",
+		.of_match_table = armpmu_of_device_ids,
+	},
+	.probe		= armpmu_device_probe,
+	.id_table	= armpmu_plat_device_ids,
+};
+
+static int __init register_pmu_driver(void)
+{
+	return platform_driver_register(&armpmu_driver);
+}
+device_initcall(register_pmu_driver);
+
+static struct pmu_hw_events *armpmu_get_cpu_events(void)
+{
+	return &__get_cpu_var(cpu_hw_events);
+}
+
+static void __init cpu_pmu_init(struct arm_pmu *armpmu)
+{
+	int cpu;
+	for_each_possible_cpu(cpu) {
+		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
+		events->events = per_cpu(hw_events, cpu);
+		events->used_mask = per_cpu(used_mask, cpu);
+		raw_spin_lock_init(&events->pmu_lock);
+	}
+	armpmu->get_hw_events = armpmu_get_cpu_events;
+	armpmu->type = ARM_PMU_DEVICE_CPU;
+}
+
+/*
+ * CPU PMU identification and registration.
+ */
 static int __init
 init_hw_perf_events(void)
 {
@@ -651,22 +684,22 @@ init_hw_perf_events(void)
 		case 0xB360:	/* ARM1136 */
 		case 0xB560:	/* ARM1156 */
 		case 0xB760:	/* ARM1176 */
-			armpmu = armv6pmu_init();
+			cpu_pmu = armv6pmu_init();
 			break;
 		case 0xB020:	/* ARM11mpcore */
-			armpmu = armv6mpcore_pmu_init();
+			cpu_pmu = armv6mpcore_pmu_init();
 			break;
 		case 0xC080:	/* Cortex-A8 */
-			armpmu = armv7_a8_pmu_init();
+			cpu_pmu = armv7_a8_pmu_init();
 			break;
 		case 0xC090:	/* Cortex-A9 */
-			armpmu = armv7_a9_pmu_init();
+			cpu_pmu = armv7_a9_pmu_init();
 			break;
 		case 0xC050:	/* Cortex-A5 */
-			armpmu = armv7_a5_pmu_init();
+			cpu_pmu = armv7_a5_pmu_init();
 			break;
 		case 0xC0F0:	/* Cortex-A15 */
-			armpmu = armv7_a15_pmu_init();
+			cpu_pmu = armv7_a15_pmu_init();
 			break;
 		}
 	/* Intel CPUs [xscale]. */
@@ -674,23 +707,23 @@ init_hw_perf_events(void)
 		part_number = (cpuid >> 13) & 0x7;
 		switch (part_number) {
 		case 1:
-			armpmu = xscale1pmu_init();
+			cpu_pmu = xscale1pmu_init();
 			break;
 		case 2:
-			armpmu = xscale2pmu_init();
+			cpu_pmu = xscale2pmu_init();
 			break;
 		}
 	}
 
-	if (armpmu) {
+	if (cpu_pmu) {
 		pr_info("enabled with %s PMU driver, %d counters available\n",
-			armpmu->name, armpmu->num_events);
+			cpu_pmu->name, cpu_pmu->num_events);
+		cpu_pmu_init(cpu_pmu);
+		armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
 	} else {
 		pr_info("no hardware support available\n");
 	}
 
-	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
-
 	return 0;
 }
 early_initcall(init_hw_perf_events);

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 const struct arm_pmu armv6pmu = {
+static int armv6_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv6_perf_map,
+				&armv6_perf_cache_map, 0xFF);
+}
+
+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,
+	.map_event		= armv6_map_event,
-	.event_map		= &armv6_perf_map,
-	.raw_event_mask		= 0xFF,
 	.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,
+	.map_event		= armv6mpcore_map_event,
-	.event_map		= &armv6mpcore_perf_map,
-	.raw_event_mask		= 0xFF,
 	.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_v7.c

@@ -17,6 +17,9 @@
  */
 
 #ifdef CONFIG_CPU_V7
+
+static struct arm_pmu armv7pmu;
+
 /*
  * Common ARMv7 event types
  *
@@ -676,24 +679,25 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 };
 
 /*
- * Perf Events counters
+ * Perf Events' indices
  */
-enum armv7_counters {
+#define	ARMV7_IDX_CYCLE_COUNTER	0
-	ARMV7_CYCLE_COUNTER		= 1,	/* Cycle counter */
+#define	ARMV7_IDX_COUNTER0	1
-	ARMV7_COUNTER0			= 2,	/* First event counter */
+#define	ARMV7_IDX_COUNTER_LAST	(ARMV7_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
-};
 
-/*
+#define	ARMV7_MAX_COUNTERS	32
- * The cycle counter is ARMV7_CYCLE_COUNTER.
+#define	ARMV7_COUNTER_MASK	(ARMV7_MAX_COUNTERS - 1)
- * The first event counter is ARMV7_COUNTER0.
- * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
- */
-#define	ARMV7_COUNTER_LAST	(ARMV7_COUNTER0 + armpmu->num_events - 1)
 
 /*
  * ARMv7 low level PMNC access
  */
 
+/*
+ * Perf Event to low level counters mapping
+ */
+#define	ARMV7_IDX_TO_COUNTER(x)	\
+	(((x) - ARMV7_IDX_COUNTER0) & ARMV7_COUNTER_MASK)
+
 /*
  * Per-CPU PMNC: config reg
  */
@@ -707,104 +711,77 @@ enum armv7_counters {
 #define	ARMV7_PMNC_N_MASK	0x1f
 #define	ARMV7_PMNC_MASK		0x3f	 /* Mask for writable bits */
 
-/*
- * Available counters
- */
-#define ARMV7_CNT0		0	/* First event counter */
-#define ARMV7_CCNT		31	/* Cycle counter */
-
-/* Perf Event to low level counters mapping */
-#define ARMV7_EVENT_CNT_TO_CNTx	(ARMV7_COUNTER0 - ARMV7_CNT0)
-
-/*
- * CNTENS: counters enable reg
- */
-#define ARMV7_CNTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENS_C		(1 << ARMV7_CCNT)
-
-/*
- * CNTENC: counters disable reg
- */
-#define ARMV7_CNTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENC_C		(1 << ARMV7_CCNT)
-
-/*
- * INTENS: counters overflow interrupt enable reg
- */
-#define ARMV7_INTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENS_C		(1 << ARMV7_CCNT)
-
-/*
- * INTENC: counters overflow interrupt disable reg
- */
-#define ARMV7_INTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENC_C		(1 << ARMV7_CCNT)
-
-/*
- * EVTSEL: Event selection reg
- */
-#define	ARMV7_EVTSEL_MASK	0xff		/* Mask for writable bits */
-
-/*
- * SELECT: Counter selection reg
- */
-#define	ARMV7_SELECT_MASK	0x1f		/* Mask for writable bits */
-
 /*
  * FLAG: counters overflow flag status reg
  */
-#define ARMV7_FLAG_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_FLAG_C		(1 << ARMV7_CCNT)
 #define	ARMV7_FLAG_MASK		0xffffffff	/* Mask for writable bits */
 #define	ARMV7_OVERFLOWED_MASK	ARMV7_FLAG_MASK
 
-static inline unsigned long armv7_pmnc_read(void)
+/*
+ * PMXEVTYPER: Event selection reg
+ */
+#define	ARMV7_EVTYPE_MASK	0xc00000ff	/* Mask for writable bits */
+#define	ARMV7_EVTYPE_EVENT	0xff		/* Mask for EVENT bits */
+
+/*
+ * Event filters for PMUv2
+ */
+#define	ARMV7_EXCLUDE_PL1	(1 << 31)
+#define	ARMV7_EXCLUDE_USER	(1 << 30)
+#define	ARMV7_INCLUDE_HYP	(1 << 27)
+
+static inline u32 armv7_pmnc_read(void)
 {
 	u32 val;
 	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
 	return val;
 }
 
-static inline void armv7_pmnc_write(unsigned long val)
+static inline void armv7_pmnc_write(u32 val)
 {
 	val &= ARMV7_PMNC_MASK;
 	isb();
 	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
 }
 
-static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
+static inline int armv7_pmnc_has_overflowed(u32 pmnc)
 {
 	return pmnc & ARMV7_OVERFLOWED_MASK;
 }
 
-static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
+static inline int armv7_pmnc_counter_valid(int idx)
-					enum armv7_counters counter)
+{
+	return idx >= ARMV7_IDX_CYCLE_COUNTER && idx <= ARMV7_IDX_COUNTER_LAST;
+}
+
+static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx)
 {
 	int ret = 0;
+	u32 counter;
 
-	if (counter == ARMV7_CYCLE_COUNTER)
+	if (!armv7_pmnc_counter_valid(idx)) {
-		ret = pmnc & ARMV7_FLAG_C;
-	else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
-		ret = pmnc & ARMV7_FLAG_P(counter);
-	else
 		pr_err("CPU%u checking wrong counter %d overflow status\n",
-			smp_processor_id(), counter);
+			smp_processor_id(), idx);
+	} else {
+		counter = ARMV7_IDX_TO_COUNTER(idx);
+		ret = pmnc & BIT(counter);
+	}
 
 	return ret;
 }
 
-static inline int armv7_pmnc_select_counter(unsigned int idx)
+static inline int armv7_pmnc_select_counter(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
+	if (!armv7_pmnc_counter_valid(idx)) {
-		pr_err("CPU%u selecting wrong PMNC counter"
+		pr_err("CPU%u selecting wrong PMNC counter %d\n",
-			" %d\n", smp_processor_id(), idx);
+			smp_processor_id(), idx);
-		return -1;
+		return -EINVAL;
 	}
 
-	val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
+	counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter));
 	isb();
 
 	return idx;
@@ -812,124 +789,95 @@ static inline int armv7_pmnc_select_counter(unsigned int idx)
 
 static inline u32 armv7pmu_read_counter(int idx)
 {
-	unsigned long value = 0;
+	u32 value = 0;
 
-	if (idx == ARMV7_CYCLE_COUNTER)
+	if (!armv7_pmnc_counter_valid(idx))
-		asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
-	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
-		if (armv7_pmnc_select_counter(idx) == idx)
-			asm volatile("mrc p15, 0, %0, c9, c13, 2"
-				     : "=r" (value));
-	} else
 		pr_err("CPU%u reading wrong counter %d\n",
 			smp_processor_id(), idx);
+	else if (idx == ARMV7_IDX_CYCLE_COUNTER)
+		asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
+	else if (armv7_pmnc_select_counter(idx) == idx)
+		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (value));
 
 	return value;
 }
 
 static inline void armv7pmu_write_counter(int idx, u32 value)
 {
-	if (idx == ARMV7_CYCLE_COUNTER)
+	if (!armv7_pmnc_counter_valid(idx))
-		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
-	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
-		if (armv7_pmnc_select_counter(idx) == idx)
-			asm volatile("mcr p15, 0, %0, c9, c13, 2"
-				     : : "r" (value));
-	} else
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
+	else if (idx == ARMV7_IDX_CYCLE_COUNTER)
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+	else if (armv7_pmnc_select_counter(idx) == idx)
+		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value));
 }
 
-static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
+static inline void armv7_pmnc_write_evtsel(int idx, u32 val)
 {
 	if (armv7_pmnc_select_counter(idx) == idx) {
-		val &= ARMV7_EVTSEL_MASK;
+		val &= ARMV7_EVTYPE_MASK;
 		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
 	}
 }
 
-static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
+static inline int armv7_pmnc_enable_counter(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
+	if (!armv7_pmnc_counter_valid(idx)) {
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+		pr_err("CPU%u enabling wrong PMNC counter %d\n",
-		pr_err("CPU%u enabling wrong PMNC counter"
+			smp_processor_id(), idx);
-			" %d\n", smp_processor_id(), idx);
+		return -EINVAL;
-		return -1;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
+	counter = ARMV7_IDX_TO_COUNTER(idx);
-		val = ARMV7_CNTENS_C;
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter)));
-	else
-		val = ARMV7_CNTENS_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
-
 	return idx;
 }
 
-static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
+static inline int armv7_pmnc_disable_counter(int idx)
 {
-	u32 val;
+	u32 counter;
 
-
+	if (!armv7_pmnc_counter_valid(idx)) {
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
+		pr_err("CPU%u disabling wrong PMNC counter %d\n",
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+			smp_processor_id(), idx);
-		pr_err("CPU%u disabling wrong PMNC counter"
+		return -EINVAL;
-			" %d\n", smp_processor_id(), idx);
-		return -1;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
+	counter = ARMV7_IDX_TO_COUNTER(idx);
-		val = ARMV7_CNTENC_C;
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter)));
-	else
-		val = ARMV7_CNTENC_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
-
 	return idx;
 }
 
-static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
+static inline int armv7_pmnc_enable_intens(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
+	if (!armv7_pmnc_counter_valid(idx)) {
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+		pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n",
-		pr_err("CPU%u enabling wrong PMNC counter"
+			smp_processor_id(), idx);
-			" interrupt enable %d\n", smp_processor_id(), idx);
+		return -EINVAL;
-		return -1;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
+	counter = ARMV7_IDX_TO_COUNTER(idx);
-		val = ARMV7_INTENS_C;
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter)));
-	else
-		val = ARMV7_INTENS_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
-
 	return idx;
 }
 
-static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
+static inline int armv7_pmnc_disable_intens(int idx)
 {
-	u32 val;
+	u32 counter;
 
-	if ((idx != ARMV7_CYCLE_COUNTER) &&
+	if (!armv7_pmnc_counter_valid(idx)) {
-	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+		pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n",
-		pr_err("CPU%u disabling wrong PMNC counter"
+			smp_processor_id(), idx);
-			" interrupt enable %d\n", smp_processor_id(), idx);
+		return -EINVAL;
-		return -1;
 	}
 
-	if (idx == ARMV7_CYCLE_COUNTER)
+	counter = ARMV7_IDX_TO_COUNTER(idx);
-		val = ARMV7_INTENC_C;
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter)));
-	else
-		val = ARMV7_INTENC_P(idx);
-
-	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
-
 	return idx;
 }
 
@@ -973,14 +921,14 @@ static void armv7_pmnc_dump_regs(void)
 	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
 	printk(KERN_INFO "CCNT  =0x%08x\n", val);
 
-	for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
+	for (cnt = ARMV7_IDX_COUNTER0; cnt <= ARMV7_IDX_COUNTER_LAST; cnt++) {
 		armv7_pmnc_select_counter(cnt);
 		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
 		printk(KERN_INFO "CNT[%d] count =0x%08x\n",
-			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+			ARMV7_IDX_TO_COUNTER(cnt), val);
 		asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
 		printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
-			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+			ARMV7_IDX_TO_COUNTER(cnt), val);
 	}
 }
 #endif
@@ -988,12 +936,13 @@ static void armv7_pmnc_dump_regs(void)
 static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -1002,9 +951,10 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 
 	/*
 	 * Set event (if destined for PMNx counters)
-	 * We don't need to set the event if it's a cycle count
+	 * We only need to set the event for the cycle counter if we
+	 * have the ability to perform event filtering.
 	 */
-	if (idx != ARMV7_CYCLE_COUNTER)
+	if (armv7pmu.set_event_filter || idx != ARMV7_IDX_CYCLE_COUNTER)
 		armv7_pmnc_write_evtsel(idx, hwc->config_base);
 
 	/*
@@ -1017,17 +967,18 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
 	 */
 	armv7_pmnc_enable_counter(idx);
 
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
 	unsigned long flags;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/*
 	 * Disable counter and interrupt
 	 */
-	raw_spin_lock_irqsave(&pmu_lock, flags);
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -1039,14 +990,14 @@ static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
 	 */
 	armv7_pmnc_disable_intens(idx);
 
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 {
-	unsigned long pmnc;
+	u32 pmnc;
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
+	struct pmu_hw_events *cpuc;
 	struct pt_regs *regs;
 	int idx;
 
@@ -1069,13 +1020,10 @@ static irqreturn_t armv7pmu_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;
-
 		/*
 		 * We have a single interrupt for all counters. Check that
 		 * each counter has overflowed before we process it.
@@ -1090,7 +1038,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		if (perf_event_overflow(event, &data, regs))
-			armpmu->disable(hwc, idx);
+			cpu_pmu->disable(hwc, idx);
 	}
 
 	/*
@@ -1108,40 +1056,44 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 static void armv7pmu_start(void)
 {
 	unsigned long flags;
+	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);
 	/* Enable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_stop(void)
 {
 	unsigned long flags;
+	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);
 	/* Disable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&pmu_lock, flags);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
+static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
 				  struct hw_perf_event *event)
 {
 	int idx;
+	unsigned long evtype = event->config_base & ARMV7_EVTYPE_EVENT;
 
 	/* Always place a cycle counter into the cycle counter. */
-	if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
+	if (evtype == ARMV7_PERFCTR_CPU_CYCLES) {
-		if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
+		if (test_and_set_bit(ARMV7_IDX_CYCLE_COUNTER, cpuc->used_mask))
 			return -EAGAIN;
 
-		return ARMV7_CYCLE_COUNTER;
+		return ARMV7_IDX_CYCLE_COUNTER;
-	} else {
+	}
+
 	/*
 	 * For anything other than a cycle counter, try and use
 	 * the events counters
 	 */
-		for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
+	for (idx = ARMV7_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
 		if (!test_and_set_bit(idx, cpuc->used_mask))
 			return idx;
 	}
@@ -1149,20 +1101,69 @@ static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
 	/* The counters are all in use. */
 	return -EAGAIN;
 }
+
+/*
+ * Add an event filter to a given event. This will only work for PMUv2 PMUs.
+ */
+static int armv7pmu_set_event_filter(struct hw_perf_event *event,
+				     struct perf_event_attr *attr)
+{
+	unsigned long config_base = 0;
+
+	if (attr->exclude_idle)
+		return -EPERM;
+	if (attr->exclude_user)
+		config_base |= ARMV7_EXCLUDE_USER;
+	if (attr->exclude_kernel)
+		config_base |= ARMV7_EXCLUDE_PL1;
+	if (!attr->exclude_hv)
+		config_base |= ARMV7_INCLUDE_HYP;
+
+	/*
+	 * Install the filter into config_base as this is used to
+	 * construct the event type.
+	 */
+	event->config_base = config_base;
+
+	return 0;
 }
 
 static void armv7pmu_reset(void *info)
 {
-	u32 idx, nb_cnt = armpmu->num_events;
+	u32 idx, nb_cnt = cpu_pmu->num_events;
 
 	/* The counter and interrupt enable registers are unknown at reset. */
-	for (idx = 1; idx < nb_cnt; ++idx)
+	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx)
 		armv7pmu_disable_event(NULL, idx);
 
 	/* Initialize & Reset PMNC: C and P bits */
 	armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);
 }
 
+static int armv7_a8_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a8_perf_map,
+				&armv7_a8_perf_cache_map, 0xFF);
+}
+
+static int armv7_a9_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a9_perf_map,
+				&armv7_a9_perf_cache_map, 0xFF);
+}
+
+static int armv7_a5_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a5_perf_map,
+				&armv7_a5_perf_cache_map, 0xFF);
+}
+
+static int armv7_a15_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a15_perf_map,
+				&armv7_a15_perf_cache_map, 0xFF);
+}
+
 static struct arm_pmu armv7pmu = {
 	.handle_irq		= armv7pmu_handle_irq,
 	.enable			= armv7pmu_enable_event,
@@ -1173,7 +1174,6 @@ static struct arm_pmu armv7pmu = {
 	.start			= armv7pmu_start,
 	.stop			= armv7pmu_stop,
 	.reset			= armv7pmu_reset,
-	.raw_event_mask		= 0xFF,
 	.max_period		= (1LLU << 32) - 1,
 };
 
@@ -1188,62 +1188,59 @@ static u32 __init armv7_read_num_pmnc_events(void)
 	return nb_cnt + 1;
 }
 
-static const struct arm_pmu *__init armv7_a8_pmu_init(void)
+static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA8;
 	armv7pmu.name		= "ARMv7 Cortex-A8";
-	armv7pmu.cache_map	= &armv7_a8_perf_cache_map;
+	armv7pmu.map_event	= armv7_a8_map_event;
-	armv7pmu.event_map	= &armv7_a8_perf_map;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a9_pmu_init(void)
+static struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA9;
 	armv7pmu.name		= "ARMv7 Cortex-A9";
-	armv7pmu.cache_map	= &armv7_a9_perf_cache_map;
+	armv7pmu.map_event	= armv7_a9_map_event;
-	armv7pmu.event_map	= &armv7_a9_perf_map;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a5_pmu_init(void)
+static struct arm_pmu *__init armv7_a5_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA5;
 	armv7pmu.name		= "ARMv7 Cortex-A5";
-	armv7pmu.cache_map	= &armv7_a5_perf_cache_map;
+	armv7pmu.map_event	= armv7_a5_map_event;
-	armv7pmu.event_map	= &armv7_a5_perf_map;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
 	return &armv7pmu;
 }
 
-static const struct arm_pmu *__init armv7_a15_pmu_init(void)
+static struct arm_pmu *__init armv7_a15_pmu_init(void)
 {
 	armv7pmu.id		= ARM_PERF_PMU_ID_CA15;
 	armv7pmu.name		= "ARMv7 Cortex-A15";
-	armv7pmu.cache_map	= &armv7_a15_perf_cache_map;
+	armv7pmu.map_event	= armv7_a15_map_event;
-	armv7pmu.event_map	= &armv7_a15_perf_map;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
+	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
 	return &armv7pmu;
 }
 #else
-static const struct arm_pmu *__init armv7_a8_pmu_init(void)
+static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a9_pmu_init(void)
+static struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a5_pmu_init(void)
+static struct arm_pmu *__init armv7_a5_pmu_init(void)
 {
 	return NULL;
 }
 
-static const struct arm_pmu *__init armv7_a15_pmu_init(void)
+static struct arm_pmu *__init armv7_a15_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,
+	.map_event	= xscale_map_event,
-	.event_map	= &xscale_perf_map,
-	.raw_event_mask	= 0xFF,
 	.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,
+	.map_event	= xscale_map_event,
-	.event_map	= &xscale_perf_map,
-	.raw_event_mask	= 0xFF,
 	.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/pmu.c

@@ -10,192 +10,26 @@
  *
  */
 
-#define pr_fmt(fmt) "PMU: " fmt
-
-#include <linux/cpumask.h>
 #include <linux/err.h>
-#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
 
 #include <asm/pmu.h>
 
-static volatile long pmu_lock;
+/*
+ * PMU locking to ensure mutual exclusion between different subsystems.
+ */
+static unsigned long pmu_lock[BITS_TO_LONGS(ARM_NUM_PMU_DEVICES)];
 
-static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES];
+int
-
-static int __devinit pmu_register(struct platform_device *pdev,
-					enum arm_pmu_type type)
-{
-	if (type < 0 || type >= ARM_NUM_PMU_DEVICES) {
-		pr_warning("received registration request for unknown "
-				"PMU device type %d\n", type);
-		return -EINVAL;
-	}
-
-	if (pmu_devices[type]) {
-		pr_warning("rejecting duplicate registration of PMU device "
-			"type %d.", type);
-		return -ENOSPC;
-	}
-
-	pr_info("registered new PMU device of type %d\n", type);
-	pmu_devices[type] = pdev;
-	return 0;
-}
-
-#define OF_MATCH_PMU(_name, _type) {	\
-	.compatible = _name,		\
-	.data = (void *)_type,		\
-}
-
-#define OF_MATCH_CPU(name)	OF_MATCH_PMU(name, ARM_PMU_DEVICE_CPU)
-
-static struct of_device_id armpmu_of_device_ids[] = {
-	OF_MATCH_CPU("arm,cortex-a9-pmu"),
-	OF_MATCH_CPU("arm,cortex-a8-pmu"),
-	OF_MATCH_CPU("arm,arm1136-pmu"),
-	OF_MATCH_CPU("arm,arm1176-pmu"),
-	{},
-};
-
-#define PLAT_MATCH_PMU(_name, _type) {	\
-	.name		= _name,	\
-	.driver_data	= _type,	\
-}
-
-#define PLAT_MATCH_CPU(_name)	PLAT_MATCH_PMU(_name, ARM_PMU_DEVICE_CPU)
-
-static struct platform_device_id armpmu_plat_device_ids[] = {
-	PLAT_MATCH_CPU("arm-pmu"),
-	{},
-};
-
-enum arm_pmu_type armpmu_device_type(struct platform_device *pdev)
-{
-	const struct of_device_id	*of_id;
-	const struct platform_device_id *pdev_id;
-
-	/* provided by of_device_id table */
-	if (pdev->dev.of_node) {
-		of_id = of_match_device(armpmu_of_device_ids, &pdev->dev);
-		BUG_ON(!of_id);
-		return (enum arm_pmu_type)of_id->data;
-	}
-
-	/* Provided by platform_device_id table */
-	pdev_id = platform_get_device_id(pdev);
-	BUG_ON(!pdev_id);
-	return pdev_id->driver_data;
-}
-
-static int __devinit armpmu_device_probe(struct platform_device *pdev)
-{
-	return pmu_register(pdev, armpmu_device_type(pdev));
-}
-
-static struct platform_driver armpmu_driver = {
-	.driver		= {
-		.name	= "arm-pmu",
-		.of_match_table = armpmu_of_device_ids,
-	},
-	.probe		= armpmu_device_probe,
-	.id_table	= armpmu_plat_device_ids,
-};
-
-static int __init register_pmu_driver(void)
-{
-	return platform_driver_register(&armpmu_driver);
-}
-device_initcall(register_pmu_driver);
-
-struct platform_device *
 reserve_pmu(enum arm_pmu_type type)
 {
-	struct platform_device *pdev;
+	return test_and_set_bit_lock(type, pmu_lock) ? -EBUSY : 0;
-
-	if (test_and_set_bit_lock(type, &pmu_lock)) {
-		pdev = ERR_PTR(-EBUSY);
-	} else if (pmu_devices[type] == NULL) {
-		clear_bit_unlock(type, &pmu_lock);
-		pdev = ERR_PTR(-ENODEV);
-	} else {
-		pdev = pmu_devices[type];
-	}
-
-	return pdev;
 }
 EXPORT_SYMBOL_GPL(reserve_pmu);
 
-int
+void
 release_pmu(enum arm_pmu_type type)
 {
-	if (WARN_ON(!pmu_devices[type]))
+	clear_bit_unlock(type, pmu_lock);
-		return -EINVAL;
-	clear_bit_unlock(type, &pmu_lock);
-	return 0;
 }
-EXPORT_SYMBOL_GPL(release_pmu);
-
-static int
-set_irq_affinity(int irq,
-		 unsigned int cpu)
-{
-#ifdef CONFIG_SMP
-	int err = irq_set_affinity(irq, cpumask_of(cpu));
-	if (err)
-		pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
-			   irq, cpu);
-	return err;
-#else
-	return -EINVAL;
-#endif
-}
-
-static int
-init_cpu_pmu(void)
-{
-	int i, irqs, err = 0;
-	struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU];
-
-	if (!pdev)
-		return -ENODEV;
-
-	irqs = pdev->num_resources;
-
-	/*
-	 * If we have a single PMU interrupt that we can't shift, assume that
-	 * we're running on a uniprocessor machine and continue.
-	 */
-	if (irqs == 1 && !irq_can_set_affinity(platform_get_irq(pdev, 0)))
-		return 0;
-
-	for (i = 0; i < irqs; ++i) {
-		err = set_irq_affinity(platform_get_irq(pdev, i), i);
-		if (err)
-			break;
-	}
-
-	return err;
-}
-
-int
-init_pmu(enum arm_pmu_type type)
-{
-	int err = 0;
-
-	switch (type) {
-	case ARM_PMU_DEVICE_CPU:
-		err = init_cpu_pmu();
-		break;
-	default:
-		pr_warning("attempt to initialise PMU of unknown "
-			   "type %d\n", type);
-		err = -EINVAL;
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(init_pmu);

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) {
+	else if (mdesc->atag_offset)
-#ifdef CONFIG_MMU
+		tags = (void *)(PAGE_OFFSET + mdesc->atag_offset);
-		/*
-		 * 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);
-		}
-	}
 
 #if defined(CONFIG_DEPRECATED_PARAM_STRUCT)
 	/*

arch/arm/kernel/sleep.S

@@ -8,92 +8,61 @@
 	.text
 
 /*
- * Save CPU state for a suspend
+ * Save CPU state for a suspend.  This saves the CPU general purpose
- *  r1 = v:p offset
+ * registers, and allocates space on the kernel stack to save the CPU
- *  r2 = suspend function arg0
+ * specific registers and some other data for resume.
- *  r3 = suspend function
+ *  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	r4, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
-	ldr	ip, [r10, #CPU_DO_RESUME] @ virtual resume function
 #else
-	ldr	r5, =cpu_suspend_size
+	ldr	r4, =cpu_suspend_size
-	ldr	ip, =cpu_do_resume
 #endif
-	mov	r6, sp			@ current virtual SP
+	mov	r5, sp			@ current virtual SP
-	sub	sp, sp, r5		@ allocate CPU state on stack
+	add	r4, r4, #12		@ Space for pgd, virt sp, phys resume fn
-	mov	r0, sp			@ save pointer to CPU save block
+	sub	sp, sp, r4		@ allocate CPU state on stack
-	add	ip, ip, r1		@ convert resume fn to phys
+	stmfd	sp!, {r0, r1}		@ save suspend func arg and pointer
-	stmfd	sp!, {r1, r6, ip}	@ save v:p, virt SP, phys resume fn
+	add	r0, sp, #8		@ save pointer to save block
-	ldr	r5, =sleep_save_sp
+	mov	r1, r4			@ size of save block
-	add	r6, sp, r1		@ convert SP to phys
+	mov	r2, r5			@ virtual SP
-	stmfd	sp!, {r2, r3}		@ save suspend func arg and pointer
+	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
+	add	r3, r3, lr, lsl #2
-#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
 #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
  */
-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:
+ENTRY(cpu_resume_mmu)
-	mcr	p15, 0, r1, c1, c0, 0	@ turn on MMU, I-cache, etc
+	ldr	r3, =cpu_resume_after_mmu
-	mrc	p15, 0, r1, c0, c0, 0	@ read id reg
+	mcr	p15, 0, r0, c1, c0, 0	@ turn on MMU, I-cache, etc
-	mov	r1, r1
+	mrc	p15, 0, r0, c0, c0, 0	@ read id reg
-	mov	r1, r1
+	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.c

@@ -16,7 +16,6 @@
 #include <linux/cache.h>
 #include <linux/profile.h>
 #include <linux/errno.h>
-#include <linux/ftrace.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/cpu.h>
@@ -31,6 +30,8 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/topology.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -39,6 +40,7 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
+#include <asm/smp_plat.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -259,6 +261,20 @@ void __ref cpu_die(void)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
+int __cpu_logical_map[NR_CPUS];
+
+void __init smp_setup_processor_id(void)
+{
+	int i;
+	u32 cpu = is_smp() ? read_cpuid_mpidr() & 0xff : 0;
+
+	cpu_logical_map(0) = cpu;
+	for (i = 1; i < NR_CPUS; ++i)
+		cpu_logical_map(i) = i == cpu ? 0 : i;
+
+	printk(KERN_INFO "Booting Linux on physical CPU %d\n", cpu);
+}
+
 /*
  * Called by both boot and secondaries to move global data into
  * per-processor storage.
@@ -268,6 +284,8 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
 	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
 
 	cpu_info->loops_per_jiffy = loops_per_jiffy;
+
+	store_cpu_topology(cpuid);
 }
 
 /*
@@ -358,6 +376,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned int ncores = num_possible_cpus();
 
+	init_cpu_topology();
+
 	smp_store_cpu_info(smp_processor_id());
 
 	/*
@@ -437,10 +457,6 @@ u64 smp_irq_stat_cpu(unsigned int cpu)
 	for (i = 0; i < NR_IPI; i++)
 		sum += __get_irq_stat(cpu, ipi_irqs[i]);
 
-#ifdef CONFIG_LOCAL_TIMERS
-	sum += __get_irq_stat(cpu, local_timer_irqs);
-#endif
-
 	return sum;
 }
 
@@ -457,33 +473,6 @@ static void ipi_timer(void)
 	irq_exit();
 }
 
-#ifdef CONFIG_LOCAL_TIMERS
-asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-	int cpu = smp_processor_id();
-
-	if (local_timer_ack()) {
-		__inc_irq_stat(cpu, local_timer_irqs);
-		ipi_timer();
-	}
-
-	set_irq_regs(old_regs);
-}
-
-void show_local_irqs(struct seq_file *p, int prec)
-{
-	unsigned int cpu;
-
-	seq_printf(p, "%*s: ", prec, "LOC");
-
-	for_each_present_cpu(cpu)
-		seq_printf(p, "%10u ", __get_irq_stat(cpu, local_timer_irqs));
-
-	seq_printf(p, " Local timer interrupts\n");
-}
-#endif
-
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 static void smp_timer_broadcast(const struct cpumask *mask)
 {
@@ -534,7 +523,7 @@ static void percpu_timer_stop(void)
 	unsigned int cpu = smp_processor_id();
 	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
 
-	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+	local_timer_stop(evt);
 }
 #endif
 
@@ -566,6 +555,11 @@ static void ipi_cpu_stop(unsigned int cpu)
  * Main handler for inter-processor interrupts
  */
 asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
+{
+	handle_IPI(ipinr, regs);
+}
+
+void handle_IPI(int ipinr, struct pt_regs *regs)
 {
 	unsigned int cpu = smp_processor_id();
 	struct pt_regs *old_regs = set_irq_regs(regs);

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/smp_twd.c

@@ -19,6 +19,7 @@
 #include <linux/io.h>
 
 #include <asm/smp_twd.h>
+#include <asm/localtimer.h>
 #include <asm/hardware/gic.h>
 
 /* set up by the platform code */
@@ -26,6 +27,8 @@ void __iomem *twd_base;
 
 static unsigned long twd_timer_rate;
 
+static struct clock_event_device __percpu **twd_evt;
+
 static void twd_set_mode(enum clock_event_mode mode,
 			struct clock_event_device *clk)
 {
@@ -80,6 +83,12 @@ int twd_timer_ack(void)
 	return 0;
 }
 
+void twd_timer_stop(struct clock_event_device *clk)
+{
+	twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
+	disable_percpu_irq(clk->irq);
+}
+
 static void __cpuinit twd_calibrate_rate(void)
 {
 	unsigned long count;
@@ -119,11 +128,43 @@ static void __cpuinit twd_calibrate_rate(void)
 	}
 }
 
+static irqreturn_t twd_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
+
+	if (twd_timer_ack()) {
+		evt->event_handler(evt);
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
 /*
  * Setup the local clock events for a CPU.
  */
 void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 {
+	struct clock_event_device **this_cpu_clk;
+
+	if (!twd_evt) {
+		int err;
+
+		twd_evt = alloc_percpu(struct clock_event_device *);
+		if (!twd_evt) {
+			pr_err("twd: can't allocate memory\n");
+			return;
+		}
+
+		err = request_percpu_irq(clk->irq, twd_handler,
+					 "twd", twd_evt);
+		if (err) {
+			pr_err("twd: can't register interrupt %d (%d)\n",
+			       clk->irq, err);
+			return;
+		}
+	}
+
 	twd_calibrate_rate();
 
 	clk->name = "local_timer";
@@ -137,8 +178,10 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	clk->max_delta_ns = clockevent_delta2ns(0xffffffff, clk);
 	clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
 
+	this_cpu_clk = __this_cpu_ptr(twd_evt);
+	*this_cpu_clk = clk;
+
 	clockevents_register_device(clk);
 
-	/* Make sure our local interrupt controller has this enabled */
+	enable_percpu_irq(clk->irq, 0);
-	gic_enable_ppi(clk->irq);
 }

arch/arm/kernel/suspend.c

@@ -0,0 +1,72 @@
+#include <linux/init.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/memory.h>
+#include <asm/suspend.h>
+#include <asm/tlbflush.h>
+
+static pgd_t *suspend_pgd;
+
+extern int __cpu_suspend(unsigned long, int (*)(unsigned long));
+extern void cpu_resume_mmu(void);
+
+/*
+ * This is called by __cpu_suspend() to save the state, and do whatever
+ * flushing is required to ensure that when the CPU goes to sleep we have
+ * the necessary data available when the caches are not searched.
+ */
+void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr)
+{
+	*save_ptr = virt_to_phys(ptr);
+
+	/* This must correspond to the LDM in cpu_resume() assembly */
+	*ptr++ = virt_to_phys(suspend_pgd);
+	*ptr++ = sp;
+	*ptr++ = virt_to_phys(cpu_do_resume);
+
+	cpu_do_suspend(ptr);
+
+	flush_cache_all();
+	outer_clean_range(*save_ptr, *save_ptr + ptrsz);
+	outer_clean_range(virt_to_phys(save_ptr),
+			  virt_to_phys(save_ptr) + sizeof(*save_ptr));
+}
+
+/*
+ * Hide the first two arguments to __cpu_suspend - these are an implementation
+ * detail which platform code shouldn't have to know about.
+ */
+int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret;
+
+	if (!suspend_pgd)
+		return -EINVAL;
+
+	/*
+	 * Provide a temporary page table with an identity mapping for
+	 * the MMU-enable code, required for resuming.  On successful
+	 * resume (indicated by a zero return code), we need to switch
+	 * back to the correct page tables.
+	 */
+	ret = __cpu_suspend(arg, fn);
+	if (ret == 0) {
+		cpu_switch_mm(mm->pgd, mm);
+		local_flush_tlb_all();
+	}
+
+	return ret;
+}
+
+static int __init cpu_suspend_init(void)
+{
+	suspend_pgd = pgd_alloc(&init_mm);
+	if (suspend_pgd) {
+		unsigned long addr = virt_to_phys(cpu_resume_mmu);
+		identity_mapping_add(suspend_pgd, addr, addr + SECTION_SIZE);
+	}
+	return suspend_pgd ? 0 : -ENOMEM;
+}
+core_initcall(cpu_suspend_init);

arch/arm/kernel/topology.c

@@ -0,0 +1,148 @@
+/*
+ * arch/arm/kernel/topology.c
+ *
+ * Copyright (C) 2011 Linaro Limited.
+ * Written by: Vincent Guittot
+ *
+ * based on arch/sh/kernel/topology.c
+ *
+ * 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.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+
+#include <asm/cputype.h>
+#include <asm/topology.h>
+
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+/*
+ * These masks reflect the current use of the affinity levels.
+ * The affinity level can be up to 16 bits according to ARM ARM
+ */
+
+#define MPIDR_LEVEL0_MASK 0x3
+#define MPIDR_LEVEL0_SHIFT 0
+
+#define MPIDR_LEVEL1_MASK 0xF
+#define MPIDR_LEVEL1_SHIFT 8
+
+#define MPIDR_LEVEL2_MASK 0xFF
+#define MPIDR_LEVEL2_SHIFT 16
+
+struct cputopo_arm cpu_topology[NR_CPUS];
+
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+/*
+ * store_cpu_topology is called at boot when only one cpu is running
+ * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
+ * which prevents simultaneous write access to cpu_topology array
+ */
+void store_cpu_topology(unsigned int cpuid)
+{
+	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+	unsigned int mpidr;
+	unsigned int cpu;
+
+	/* If the cpu topology has been already set, just return */
+	if (cpuid_topo->core_id != -1)
+		return;
+
+	mpidr = read_cpuid_mpidr();
+
+	/* create cpu topology mapping */
+	if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) {
+		/*
+		 * This is a multiprocessor system
+		 * multiprocessor format & multiprocessor mode field are set
+		 */
+
+		if (mpidr & MPIDR_MT_BITMASK) {
+			/* core performance interdependency */
+			cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
+				& MPIDR_LEVEL0_MASK;
+			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
+				& MPIDR_LEVEL1_MASK;
+			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT)
+				& MPIDR_LEVEL2_MASK;
+		} else {
+			/* largely independent cores */
+			cpuid_topo->thread_id = -1;
+			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
+				& MPIDR_LEVEL0_MASK;
+			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
+				& MPIDR_LEVEL1_MASK;
+		}
+	} else {
+		/*
+		 * This is an uniprocessor system
+		 * we are in multiprocessor format but uniprocessor system
+		 * or in the old uniprocessor format
+		 */
+		cpuid_topo->thread_id = -1;
+		cpuid_topo->core_id = 0;
+		cpuid_topo->socket_id = -1;
+	}
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->socket_id == cpu_topo->socket_id) {
+			cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+			if (cpu != cpuid)
+				cpumask_set_cpu(cpu,
+					&cpuid_topo->core_sibling);
+
+			if (cpuid_topo->core_id == cpu_topo->core_id) {
+				cpumask_set_cpu(cpuid,
+					&cpu_topo->thread_sibling);
+				if (cpu != cpuid)
+					cpumask_set_cpu(cpu,
+						&cpuid_topo->thread_sibling);
+			}
+		}
+	}
+	smp_wmb();
+
+	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
+		cpuid, cpu_topology[cpuid].thread_id,
+		cpu_topology[cpuid].core_id,
+		cpu_topology[cpuid].socket_id, mpidr);
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void init_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	/* init core mask */
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->socket_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+	}
+	smp_wmb();
+}

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

arch/arm/mach-bcmring/include/mach/hardware.h

@@ -22,7 +22,6 @@
 #define __ASM_ARCH_HARDWARE_H
 
 #include <asm/sizes.h>
-#include <mach/memory.h>
 #include <cfg_global.h>
 #include <mach/csp/mm_io.h>
 
@@ -31,7 +30,7 @@
  *  *_SIZE  is the size of the region
  *  *_BASE  is the virtual address
  */
-#define RAM_START               PLAT_PHYS_OFFSET
+#define RAM_START               PHYS_OFFSET
 
 #define RAM_SIZE                (CFG_GLOBAL_RAM_SIZE-CFG_GLOBAL_RAM_SIZE_RESERVED)
 #define RAM_BASE                PAGE_OFFSET

arch/arm/mach-bcmring/include/mach/memory.h

@@ -1,33 +0,0 @@
-/*****************************************************************************
-* Copyright 2005 - 2008 Broadcom Corporation.  All rights reserved.
-*
-* Unless you and Broadcom execute a separate written software license
-* agreement governing use of this software, this software is licensed to you
-* under the terms of the GNU General Public License version 2, available at
-* http://www.broadcom.com/licenses/GPLv2.php (the "GPL").
-*
-* Notwithstanding the above, under no circumstances may you combine this
-* software in any way with any other Broadcom software provided under a
-* license other than the GPL, without Broadcom's express prior written
-* consent.
-*****************************************************************************/
-
-#ifndef __ASM_ARCH_MEMORY_H
-#define __ASM_ARCH_MEMORY_H
-
-#include <cfg_global.h>
-
-/*
- * Physical vs virtual RAM address space conversion.  These are
- * private definitions which should NOT be used outside memory.h
- * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
- */
-
-#define PLAT_PHYS_OFFSET CFG_GLOBAL_RAM_BASE
-
-/*
- * Maximum DMA memory allowed is 14M
- */
-#define CONSISTENT_DMA_SIZE (SZ_16M - SZ_2M)
-
-#endif

arch/arm/mach-bcmring/mm.c

@@ -13,6 +13,7 @@
 *****************************************************************************/
 
 #include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
 #include <asm/mach/map.h>
 
 #include <mach/hardware.h>
@@ -53,4 +54,6 @@ void __init bcmring_map_io(void)
 {
 
 	iotable_init(bcmring_io_desc, ARRAY_SIZE(bcmring_io_desc));
+	/* Maximum DMA memory allowed is 14M */
+	init_consistent_dma_size(14 << 20);
 }

arch/arm/mach-clps711x/autcpu12.c

@@ -64,7 +64,7 @@ void __init autcpu12_map_io(void)
 
 MACHINE_START(AUTCPU12, "autronix autcpu12")
 	/* Maintainer: Thomas Gleixner */
-	.boot_params	= 0xc0020000,
+	.atag_offset	= 0x20000,
 	.map_io		= autcpu12_map_io,
 	.init_irq	= clps711x_init_irq,
 	.timer		= &clps711x_timer,

arch/arm/mach-clps711x/cdb89712.c

@@ -55,7 +55,7 @@ static void __init cdb89712_map_io(void)
 
 MACHINE_START(CDB89712, "Cirrus-CDB89712")
 	/* Maintainer: Ray Lehtiniemi */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= cdb89712_map_io,
 	.init_irq	= clps711x_init_irq,
 	.timer		= &clps711x_timer,

arch/arm/mach-clps711x/ceiva.c

@@ -56,7 +56,7 @@ static void __init ceiva_map_io(void)
 
 MACHINE_START(CEIVA, "CEIVA/Polaroid Photo MAX Digital Picture Frame")
 	/* Maintainer: Rob Scott */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.map_io		= ceiva_map_io,
 	.init_irq	= clps711x_init_irq,
 	.timer		= &clps711x_timer,

arch/arm/mach-clps711x/clep7312.c

@@ -37,7 +37,7 @@ fixup_clep7312(struct machine_desc *desc, struct tag *tags,
 
 MACHINE_START(CLEP7212, "Cirrus Logic 7212/7312")
 	/* Maintainer: Nobody */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x0100,
 	.fixup		= fixup_clep7312,
 	.map_io		= clps711x_map_io,
 	.init_irq	= clps711x_init_irq,

arch/arm/mach-clps711x/edb7211-arch.c

@@ -57,7 +57,7 @@ fixup_edb7211(struct machine_desc *desc, struct tag *tags,
 
 MACHINE_START(EDB7211, "CL-EDB7211 (EP7211 eval board)")
 	/* Maintainer: Jon McClintock */
-	.boot_params	= 0xc0020100,	/* 0xc0000000 - 0xc001ffff can be video RAM */
+	.atag_offset	= 0x20100,	/* 0xc0000000 - 0xc001ffff can be video RAM */
 	.fixup		= fixup_edb7211,
 	.map_io		= edb7211_map_io,
 	.reserve	= edb7211_reserve,

arch/arm/mach-clps711x/fortunet.c

@@ -75,7 +75,6 @@ fortunet_fixup(struct machine_desc *desc, struct tag *tags,
 
 MACHINE_START(FORTUNET, "ARM-FortuNet")
 	/* Maintainer: FortuNet Inc. */
-	.boot_params	= 0x00000000,
 	.fixup		= fortunet_fixup,
 	.map_io		= clps711x_map_io,
 	.init_irq	= clps711x_init_irq,

arch/arm/mach-clps711x/include/mach/debug-macro.S

@@ -14,7 +14,7 @@
 #include <mach/hardware.h>
 #include <asm/hardware/clps7111.h>
 
-		.macro	addruart, rp, rv
+		.macro	addruart, rp, rv, tmp
 #ifndef CONFIG_DEBUG_CLPS711X_UART2
 		mov	\rp, #0x0000	@ UART1
 #else

arch/arm/mach-clps711x/p720t.c

@@ -89,7 +89,7 @@ static void __init p720t_map_io(void)
 
 MACHINE_START(P720T, "ARM-Prospector720T")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.boot_params	= 0xc0000100,
+	.atag_offset	= 0x100,
 	.fixup		= fixup_p720t,
 	.map_io		= p720t_map_io,
 	.init_irq	= clps711x_init_irq,

arch/arm/mach-cns3xxx/cns3420vb.c

@@ -197,7 +197,7 @@ static void __init cns3420_map_io(void)
 }
 
 MACHINE_START(CNS3420VB, "Cavium Networks CNS3420 Validation Board")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.map_io		= cns3420_map_io,
 	.init_irq	= cns3xxx_init_irq,
 	.timer		= &cns3xxx_timer,

arch/arm/mach-cns3xxx/include/mach/debug-macro.S

@@ -10,7 +10,7 @@
  * published by the Free Software Foundation.
  */
 
-		.macro	addruart,rp,rv
+		.macro	addruart,rp,rv,tmp
 		mov	\rp, #0x00009000
 		orr	\rv, \rp, #0xf0000000	@ virtual base
 		orr	\rp, \rp, #0x10000000

arch/arm/mach-cns3xxx/include/mach/memory.h

@@ -1,26 +0,0 @@
-/*
- * Copyright 2003 ARM Limited
- * Copyright 2008 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- */
-
-#ifndef __MACH_MEMORY_H
-#define __MACH_MEMORY_H
-
-/*
- * Physical DRAM offset.
- */
-#define PLAT_PHYS_OFFSET		UL(0x00000000)
-
-#define __phys_to_bus(x)	((x) + PHYS_OFFSET)
-#define __bus_to_phys(x)	((x) - PHYS_OFFSET)
-
-#define __virt_to_bus(v)	__phys_to_bus(__virt_to_phys(v))
-#define __bus_to_virt(b)	__phys_to_virt(__bus_to_phys(b))
-#define __pfn_to_bus(p)		__phys_to_bus(__pfn_to_phys(p))
-#define __bus_to_pfn(b)		__phys_to_pfn(__bus_to_phys(b))
-
-#endif

arch/arm/mach-davinci/board-da830-evm.c

@@ -676,7 +676,7 @@ static void __init da830_evm_map_io(void)
 }
 
 MACHINE_START(DAVINCI_DA830_EVM, "DaVinci DA830/OMAP-L137/AM17x EVM")
-	.boot_params	= (DA8XX_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= da830_evm_map_io,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,

arch/arm/mach-davinci/board-da850-evm.c

@@ -1291,7 +1291,7 @@ static void __init da850_evm_map_io(void)
 }
 
 MACHINE_START(DAVINCI_DA850_EVM, "DaVinci DA850/OMAP-L138/AM18x EVM")
-	.boot_params	= (DA8XX_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= da850_evm_map_io,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,

arch/arm/mach-davinci/board-dm355-evm.c

@@ -351,7 +351,7 @@ static __init void dm355_evm_init(void)
 }
 
 MACHINE_START(DAVINCI_DM355_EVM, "DaVinci DM355 EVM")
-	.boot_params  = (0x80000100),
+	.atag_offset  = 0x100,
 	.map_io	      = dm355_evm_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer	      = &davinci_timer,

arch/arm/mach-davinci/board-dm355-leopard.c

@@ -270,7 +270,7 @@ static __init void dm355_leopard_init(void)
 }
 
 MACHINE_START(DM355_LEOPARD, "DaVinci DM355 leopard")
-	.boot_params  = (0x80000100),
+	.atag_offset  = 0x100,
 	.map_io	      = dm355_leopard_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer	      = &davinci_timer,

arch/arm/mach-davinci/board-dm365-evm.c

@@ -612,7 +612,7 @@ static __init void dm365_evm_init(void)
 }
 
 MACHINE_START(DAVINCI_DM365_EVM, "DaVinci DM365 EVM")
-	.boot_params	= (0x80000100),
+	.atag_offset	= 0x100,
 	.map_io		= dm365_evm_map_io,
 	.init_irq	= davinci_irq_init,
 	.timer		= &davinci_timer,

arch/arm/mach-davinci/board-dm644x-evm.c

@@ -712,7 +712,7 @@ static __init void davinci_evm_init(void)
 
 MACHINE_START(DAVINCI_EVM, "DaVinci DM644x EVM")
 	/* Maintainer: MontaVista Software <source@mvista.com> */
-	.boot_params  = (DAVINCI_DDR_BASE + 0x100),
+	.atag_offset  = 0x100,
 	.map_io	      = davinci_evm_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer	      = &davinci_timer,

arch/arm/mach-davinci/board-dm646x-evm.c

@@ -792,7 +792,7 @@ static __init void evm_init(void)
 }
 
 MACHINE_START(DAVINCI_DM6467_EVM, "DaVinci DM646x EVM")
-	.boot_params  = (0x80000100),
+	.atag_offset  = 0x100,
 	.map_io       = davinci_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer        = &davinci_timer,
@@ -801,7 +801,7 @@ MACHINE_START(DAVINCI_DM6467_EVM, "DaVinci DM646x EVM")
 MACHINE_END
 
 MACHINE_START(DAVINCI_DM6467TEVM, "DaVinci DM6467T EVM")
-	.boot_params  = (0x80000100),
+	.atag_offset  = 0x100,
 	.map_io       = davinci_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer        = &davinci_timer,

arch/arm/mach-davinci/board-mityomapl138.c

@@ -566,7 +566,7 @@ static void __init mityomapl138_map_io(void)
 }
 
 MACHINE_START(MITYOMAPL138, "MityDSP-L138/MityARM-1808")
-	.boot_params	= (DA8XX_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= mityomapl138_map_io,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,

arch/arm/mach-davinci/board-neuros-osd2.c

@@ -272,7 +272,7 @@ static __init void davinci_ntosd2_init(void)
 
 MACHINE_START(NEUROS_OSD2, "Neuros OSD2")
 	/* Maintainer: Neuros Technologies <neuros@groups.google.com> */
-	.boot_params	= (DAVINCI_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		 = davinci_ntosd2_map_io,
 	.init_irq	= davinci_irq_init,
 	.timer		= &davinci_timer,

arch/arm/mach-davinci/board-omapl138-hawk.c

@@ -338,7 +338,7 @@ static void __init omapl138_hawk_map_io(void)
 }
 
 MACHINE_START(OMAPL138_HAWKBOARD, "AM18x/OMAP-L138 Hawkboard")
-	.boot_params	= (DA8XX_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= omapl138_hawk_map_io,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,

arch/arm/mach-davinci/board-sffsdr.c

@@ -151,7 +151,7 @@ static __init void davinci_sffsdr_init(void)
 
 MACHINE_START(SFFSDR, "Lyrtech SFFSDR")
 	/* Maintainer: Hugo Villeneuve hugo.villeneuve@lyrtech.com */
-	.boot_params  = (DAVINCI_DDR_BASE + 0x100),
+	.atag_offset  = 0x100,
 	.map_io	      = davinci_sffsdr_map_io,
 	.init_irq     = davinci_irq_init,
 	.timer	      = &davinci_timer,

arch/arm/mach-davinci/board-tnetv107x-evm.c

@@ -277,7 +277,7 @@ console_initcall(tnetv107x_evm_console_init);
 #endif
 
 MACHINE_START(TNETV107X, "TNETV107X EVM")
-	.boot_params	= (TNETV107X_DDR_BASE + 0x100),
+	.atag_offset	= 0x100,
 	.map_io		= tnetv107x_init,
 	.init_irq	= cp_intc_init,
 	.timer		= &davinci_timer,

arch/arm/mach-davinci/common.c

@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/etherdevice.h>
 #include <linux/davinci_emac.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/tlb.h>
 #include <asm/mach/map.h>
@@ -86,6 +87,8 @@ void __init davinci_common_init(struct davinci_soc_info *soc_info)
 		iotable_init(davinci_soc_info.io_desc,
 				davinci_soc_info.io_desc_num);
 
+	init_consistent_dma_size(14 << 20);
+
 	/*
 	 * Normally devicemaps_init() would flush caches and tlb after
 	 * mdesc->map_io(), but we must also do it here because of the CPU

arch/arm/mach-davinci/cpuidle.c

@@ -19,7 +19,7 @@
 #include <asm/proc-fns.h>
 
 #include <mach/cpuidle.h>
-#include <mach/memory.h>
+#include <mach/ddr2.h>
 
 #define DAVINCI_CPUIDLE_MAX_STATES	2
 

arch/arm/mach-davinci/include/mach/ddr2.h

@@ -0,0 +1,4 @@
+#define DDR2_SDRCR_OFFSET	0xc
+#define DDR2_SRPD_BIT		(1 << 23)
+#define DDR2_MCLKSTOPEN_BIT	(1 << 30)
+#define DDR2_LPMODEN_BIT	(1 << 31)

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

@@ -18,56 +18,50 @@
 
 #include <linux/serial_reg.h>
 
-#include <asm/memory.h>
-
 #include <mach/serial.h>
 
 #define UART_SHIFT	2
 
-#define davinci_uart_v2p(x)	((x) - PAGE_OFFSET + PLAT_PHYS_OFFSET)
-#define davinci_uart_p2v(x)	((x) - PLAT_PHYS_OFFSET + PAGE_OFFSET)
-
 		.pushsection .data
 davinci_uart_phys:	.word	0
 davinci_uart_virt:	.word	0
 		.popsection
 
-		.macro addruart, rp, rv
+		.macro addruart, rp, rv, tmp
 
 		/* Use davinci_uart_phys/virt if already configured */
-10:		mrc	p15, 0, \rp, c1, c0
+10:		adr	\rp, 99f		@ get effective addr of 99f
-		tst	\rp, #1			@ MMU enabled?
+		ldr	\rv, [\rp]		@ get absolute addr of 99f
-		ldreq	\rp, =davinci_uart_v2p(davinci_uart_phys)
+		sub	\rv, \rv, \rp		@ offset between the two
-		ldrne	\rp, =davinci_uart_phys
+		ldr	\rp, [\rp, #4]		@ abs addr of omap_uart_phys
-		add	\rv, \rp, #4		@ davinci_uart_virt
+		sub	\tmp, \rp, \rv		@ make it effective
-		ldr	\rp, [\rp, #0]
+		ldr	\rp, [\tmp, #0]		@ davinci_uart_phys
-		ldr	\rv, [\rv, #0]
+		ldr	\rv, [\tmp, #4]		@ davinci_uart_virt
 		cmp	\rp, #0			@ is port configured?
 		cmpne	\rv, #0
-		bne	99f			@ already configured
+		bne	100f			@ already configured
 
 		/* Check the debug UART address set in uncompress.h */
-		mrc	p15, 0, \rp, c1, c0
+		and	\rp, pc, #0xff000000
-		tst	\rp, #1			@ MMU enabled?
+		ldr	\rv, =DAVINCI_UART_INFO_OFS
+		add	\rp, \rp, \rv
 
 		/* Copy uart phys address from decompressor uart info */
-		ldreq	\rv, =davinci_uart_v2p(davinci_uart_phys)
+		ldr	\rv, [\rp, #0]
-		ldrne	\rv, =davinci_uart_phys
+		str	\rv, [\tmp, #0]
-		ldreq	\rp, =DAVINCI_UART_INFO
-		ldrne	\rp, =davinci_uart_p2v(DAVINCI_UART_INFO)
-		ldr	\rp, [\rp, #0]
-		str	\rp, [\rv]
 
 		/* Copy uart virt address from decompressor uart info */
-		ldreq	\rv, =davinci_uart_v2p(davinci_uart_virt)
+		ldr	\rv, [\rp, #4]
-		ldrne	\rv, =davinci_uart_virt
+		str	\rv, [\tmp, #4]
-		ldreq	\rp, =DAVINCI_UART_INFO
-		ldrne	\rp, =davinci_uart_p2v(DAVINCI_UART_INFO)
-		ldr	\rp, [\rp, #4]
-		str	\rp, [\rv]
 
 		b	10b
-99:
+
+		.align
+99:		.word	.
+		.word	davinci_uart_phys
+		.ltorg
+
+100:
 		.endm
 
 		.macro	senduart,rd,rx

arch/arm/mach-davinci/include/mach/memory.h

@@ -1,44 +0,0 @@
-/*
- * DaVinci memory space definitions
- *
- * Author: Kevin Hilman, MontaVista Software, Inc. <source@mvista.com>
- *
- * 2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-#ifndef __ASM_ARCH_MEMORY_H
-#define __ASM_ARCH_MEMORY_H
-
-/**************************************************************************
- * Included Files
- **************************************************************************/
-#include <asm/page.h>
-#include <asm/sizes.h>
-
-/**************************************************************************
- * Definitions
- **************************************************************************/
-#define DAVINCI_DDR_BASE	0x80000000
-#define DA8XX_DDR_BASE		0xc0000000
-
-#if defined(CONFIG_ARCH_DAVINCI_DA8XX) && defined(CONFIG_ARCH_DAVINCI_DMx)
-#error Cannot enable DaVinci and DA8XX platforms concurrently
-#elif defined(CONFIG_ARCH_DAVINCI_DA8XX)
-#define PLAT_PHYS_OFFSET DA8XX_DDR_BASE
-#else
-#define PLAT_PHYS_OFFSET DAVINCI_DDR_BASE
-#endif
-
-#define DDR2_SDRCR_OFFSET	0xc
-#define DDR2_SRPD_BIT		BIT(23)
-#define DDR2_MCLKSTOPEN_BIT	BIT(30)
-#define DDR2_LPMODEN_BIT	BIT(31)
-
-/*
- * Increase size of DMA-consistent memory region
- */
-#define CONSISTENT_DMA_SIZE (14<<20)
-
-#endif /* __ASM_ARCH_MEMORY_H */

arch/arm/mach-davinci/include/mach/serial.h

@@ -21,8 +21,9 @@
  * macros in debug-macro.S.
  *
  * This area sits just below the page tables (see arch/arm/kernel/head.S).
+ * We define it as a relative offset from start of usable RAM.
  */
-#define DAVINCI_UART_INFO	(PLAT_PHYS_OFFSET + 0x3ff8)
+#define DAVINCI_UART_INFO_OFS	0x3ff8
 
 #define DAVINCI_UART0_BASE	(IO_PHYS + 0x20000)
 #define DAVINCI_UART1_BASE	(IO_PHYS + 0x20400)

arch/arm/mach-davinci/include/mach/uncompress.h

@@ -43,7 +43,12 @@ static inline void flush(void)
 
 static inline void set_uart_info(u32 phys, void * __iomem virt)
 {
-	u32 *uart_info = (u32 *)(DAVINCI_UART_INFO);
+	/*
+	 * Get address of some.bss variable and round it down
+	 * a la CONFIG_AUTO_ZRELADDR.
+	 */
+	u32 ram_start = (u32)&uart & 0xf8000000;
+	u32 *uart_info = (u32 *)(ram_start + DAVINCI_UART_INFO_OFS);
 
 	uart = (u32 *)phys;
 	uart_info[0] = phys;

arch/arm/mach-davinci/sleep.S

@@ -22,7 +22,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <mach/psc.h>
-#include <mach/memory.h>
+#include <mach/ddr2.h>
 
 #include "clock.h"
 

arch/arm/mach-dove/cm-a510.c

@@ -87,7 +87,7 @@ static void __init cm_a510_init(void)
 }
 
 MACHINE_START(CM_A510, "Compulab CM-A510 Board")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= cm_a510_init,
 	.map_io		= dove_map_io,
 	.init_early	= dove_init_early,

arch/arm/mach-dove/dove-db-setup.c

@@ -94,7 +94,7 @@ static void __init dove_db_init(void)
 }
 
 MACHINE_START(DOVE_DB, "Marvell DB-MV88AP510-BP Development Board")
-	.boot_params	= 0x00000100,
+	.atag_offset	= 0x100,
 	.init_machine	= dove_db_init,
 	.map_io		= dove_map_io,
 	.init_early	= dove_init_early,

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

@@ -8,7 +8,7 @@
 
 #include <mach/bridge-regs.h>
 
-	.macro	addruart, rp, rv
+	.macro	addruart, rp, rv, tmp
 	ldr	\rp, =DOVE_SB_REGS_PHYS_BASE
 	ldr	\rv, =DOVE_SB_REGS_VIRT_BASE
 	orr	\rp, \rp, #0x00012000