Merge branch 'dt/gic' into next/dt

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

Documentation/devicetree/bindings/arm/gic.txt

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

arch/arm/Kconfig

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

arch/arm/Kconfig.debug

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

arch/arm/Makefile

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

arch/arm/boot/compressed/.gitignore

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

arch/arm/boot/compressed/Makefile

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

arch/arm/boot/compressed/atags_to_fdt.c

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

arch/arm/boot/compressed/head.S

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

arch/arm/boot/compressed/libfdt_env.h

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

arch/arm/boot/compressed/misc.c

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

arch/arm/boot/compressed/string.c

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

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

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

arch/arm/common/Kconfig

 config ARM_GIC
+	select IRQ_DOMAIN
 	bool
 
 config ARM_VIC

arch/arm/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->irq - gic_data->irq_offset;
+	return d->hwirq;
 }
 
 /*
@@ -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,
-	unsigned int irq_start)
+static void __init gic_dist_init(struct gic_chip_data *gic)
 {
-	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_set_chip_and_handler(i, &gic_chip, handle_fasteoi_irq);
-		irq_set_chip_data(i, gic);
-		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
+	irq_domain_for_each_irq(domain, i, irq) {
+		if (i < 32) {
+			irq_set_percpu_devid(irq);
+			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;
+
+	/*
+	 * 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_dist_init(gic, irq_start);
+	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

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

arch/arm/include/asm/hardirq.h

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

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

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