Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

43 files changed, 813 insertions, 2083 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 43b740d0e37..7b787d642af 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -7,6 +7,8 @@ AFLAGS_head.o        := -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+CFLAGS_REMOVE_patch.o = -pg
 endif
 
 CFLAGS_REMOVE_return_address.o = -pg
@@ -14,30 +16,29 @@ CFLAGS_REMOVE_return_address.o = -pg
 # Object file lists.
 
 obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
-		   process.o ptrace.o return_address.o setup.o signal.o \
-		   sys_arm.o stacktrace.o time.o traps.o
+		   process.o ptrace.o return_address.o sched_clock.o \
+		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += compat.o
 
 obj-$(CONFIG_LEDS)		+= leds.o
 obj-$(CONFIG_OC_ETM)		+= etm.o
-
+obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
-obj-$(CONFIG_ARCH_ACORN)	+= ecard.o 
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
 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-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
-obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
 obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
-obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o
+obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o patch.o
 ifdef CONFIG_THUMB2_KERNEL
 obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
 else
@@ -62,9 +63,6 @@ obj-$(CONFIG_SWP_EMULATE)	+= swp_emulate.o
 CFLAGS_swp_emulate.o		:= -Wa,-march=armv7-a
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 
-obj-$(CONFIG_CRUNCH)		+= crunch.o crunch-bits.o
-AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312
-
 obj-$(CONFIG_CPU_XSCALE)	+= xscale-cp0.o
 obj-$(CONFIG_CPU_XSC3)		+= xscale-cp0.o
 obj-$(CONFIG_CPU_MOHAWK)	+= xscale-cp0.o
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 5b0bce61eb6..b57c75e0b01 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -18,7 +18,6 @@
 #include <linux/io.h>
 
 #include <asm/checksum.h>
-#include <asm/system.h>
 #include <asm/ftrace.h>
 
 /*
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index f58ba358990..ede5f7741c4 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -16,7 +16,6 @@
 #include <asm/mach/pci.h>
 
 static int debug_pci;
-static int use_firmware;
 
 /*
  * We can't use pci_find_device() here since we are
@@ -295,34 +294,11 @@ static inline int pdev_bad_for_parity(struct pci_dev *dev)
 }
 
 /*
- * Adjust the device resources from bus-centric to Linux-centric.
- */
-static void __devinit
-pdev_fixup_device_resources(struct pci_sys_data *root, struct pci_dev *dev)
-{
-	resource_size_t offset;
-	int i;
-
-	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
-		if (dev->resource[i].start == 0)
-			continue;
-		if (dev->resource[i].flags & IORESOURCE_MEM)
-			offset = root->mem_offset;
-		else
-			offset = root->io_offset;
-
-		dev->resource[i].start += offset;
-		dev->resource[i].end   += offset;
-	}
-}
-
-/*
  * pcibios_fixup_bus - Called after each bus is probed,
  * but before its children are examined.
  */
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	struct pci_sys_data *root = bus->sysdata;
 	struct pci_dev *dev;
 	u16 features = PCI_COMMAND_SERR | PCI_COMMAND_PARITY | PCI_COMMAND_FAST_BACK;
 
@@ -333,8 +309,6 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		u16 status;
 
-		pdev_fixup_device_resources(root, dev);
-
 		pci_read_config_word(dev, PCI_STATUS, &status);
 
 		/*
@@ -400,43 +374,6 @@ EXPORT_SYMBOL(pcibios_fixup_bus);
 #endif
 
 /*
- * Convert from Linux-centric to bus-centric addresses for bridge devices.
- */
-void
-pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
-			 struct resource *res)
-{
-	struct pci_sys_data *root = dev->sysdata;
-	unsigned long offset = 0;
-
-	if (res->flags & IORESOURCE_IO)
-		offset = root->io_offset;
-	if (res->flags & IORESOURCE_MEM)
-		offset = root->mem_offset;
-
-	region->start = res->start - offset;
-	region->end   = res->end - offset;
-}
-EXPORT_SYMBOL(pcibios_resource_to_bus);
-
-void __devinit
-pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
-			struct pci_bus_region *region)
-{
-	struct pci_sys_data *root = dev->sysdata;
-	unsigned long offset = 0;
-
-	if (res->flags & IORESOURCE_IO)
-		offset = root->io_offset;
-	if (res->flags & IORESOURCE_MEM)
-		offset = root->mem_offset;
-
-	res->start = region->start + offset;
-	res->end   = region->end + offset;
-}
-EXPORT_SYMBOL(pcibios_bus_to_resource);
-
-/*
  * Swizzle the device pin each time we cross a bridge.
  * This might update pin and returns the slot number.
  */
@@ -497,10 +434,10 @@ static void __init pcibios_init_hw(struct hw_pci *hw)
 
 		if (ret > 0) {
 			if (list_empty(&sys->resources)) {
-				pci_add_resource(&sys->resources,
-						 &ioport_resource);
-				pci_add_resource(&sys->resources,
-						 &iomem_resource);
+				pci_add_resource_offset(&sys->resources,
+					 &ioport_resource, sys->io_offset);
+				pci_add_resource_offset(&sys->resources,
+					 &iomem_resource, sys->mem_offset);
 			}
 
 			sys->bus = hw->scan(nr, sys);
@@ -525,6 +462,7 @@ void __init pci_common_init(struct hw_pci *hw)
 
 	INIT_LIST_HEAD(&hw->buses);
 
+	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 	if (hw->preinit)
 		hw->preinit();
 	pcibios_init_hw(hw);
@@ -536,7 +474,7 @@ void __init pci_common_init(struct hw_pci *hw)
 	list_for_each_entry(sys, &hw->buses, node) {
 		struct pci_bus *bus = sys->bus;
 
-		if (!use_firmware) {
+		if (!pci_has_flag(PCI_PROBE_ONLY)) {
 			/*
 			 * Size the bridge windows.
 			 */
@@ -573,7 +511,7 @@ char * __init pcibios_setup(char *str)
 		debug_pci = 1;
 		return NULL;
 	} else if (!strcmp(str, "firmware")) {
-		use_firmware = 1;
+		pci_add_flags(PCI_PROBE_ONLY);
 		return NULL;
 	}
 	return str;
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
new file mode 100644
index 00000000000..89545f6c840
--- /dev/null
+++ b/arch/arm/kernel/cpuidle.c
@@ -0,0 +1,21 @@
+/*
+ * Copyright 2012 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/cpuidle.h>
+#include <asm/proc-fns.h>
+
+int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index)
+{
+	cpu_do_idle();
+
+	return index;
+}
diff --git a/arch/arm/kernel/crunch-bits.S b/arch/arm/kernel/crunch-bits.S
deleted file mode 100644
index 0ec9bb48fab..00000000000
--- a/arch/arm/kernel/crunch-bits.S
+++ /dev/null
@@ -1,305 +0,0 @@
-/*
- * arch/arm/kernel/crunch-bits.S
- * Cirrus MaverickCrunch context switching and handling
- *
- * Copyright (C) 2006 Lennert Buytenhek <buytenh@wantstofly.org>
- *
- * Shamelessly stolen from the iWMMXt code by Nicolas Pitre, which is
- * Copyright (c) 2003-2004, MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/linkage.h>
-#include <asm/ptrace.h>
-#include <asm/thread_info.h>
-#include <asm/asm-offsets.h>
-#include <mach/ep93xx-regs.h>
-
-/*
- * We can't use hex constants here due to a bug in gas.
- */
-#define CRUNCH_MVDX0		0
-#define CRUNCH_MVDX1		8
-#define CRUNCH_MVDX2		16
-#define CRUNCH_MVDX3		24
-#define CRUNCH_MVDX4		32
-#define CRUNCH_MVDX5		40
-#define CRUNCH_MVDX6		48
-#define CRUNCH_MVDX7		56
-#define CRUNCH_MVDX8		64
-#define CRUNCH_MVDX9		72
-#define CRUNCH_MVDX10		80
-#define CRUNCH_MVDX11		88
-#define CRUNCH_MVDX12		96
-#define CRUNCH_MVDX13		104
-#define CRUNCH_MVDX14		112
-#define CRUNCH_MVDX15		120
-#define CRUNCH_MVAX0L		128
-#define CRUNCH_MVAX0M		132
-#define CRUNCH_MVAX0H		136
-#define CRUNCH_MVAX1L		140
-#define CRUNCH_MVAX1M		144
-#define CRUNCH_MVAX1H		148
-#define CRUNCH_MVAX2L		152
-#define CRUNCH_MVAX2M		156
-#define CRUNCH_MVAX2H		160
-#define CRUNCH_MVAX3L		164
-#define CRUNCH_MVAX3M		168
-#define CRUNCH_MVAX3H		172
-#define CRUNCH_DSPSC		176
-
-#define CRUNCH_SIZE		184
-
-	.text
-
-/*
- * Lazy switching of crunch coprocessor context
- *
- * r10 = struct thread_info pointer
- * r9  = ret_from_exception
- * lr  = undefined instr exit
- *
- * called from prefetch exception handler with interrupts disabled
- */
-ENTRY(crunch_task_enable)
-	ldr	r8, =(EP93XX_APB_VIRT_BASE + 0x00130000)	@ syscon addr
-
-	ldr	r1, [r8, #0x80]
-	tst	r1, #0x00800000			@ access to crunch enabled?
-	movne	pc, lr				@ if so no business here
-	mov	r3, #0xaa			@ unlock syscon swlock
-	str	r3, [r8, #0xc0]
-	orr	r1, r1, #0x00800000		@ enable access to crunch
-	str	r1, [r8, #0x80]
-
-	ldr	r3, =crunch_owner
-	add	r0, r10, #TI_CRUNCH_STATE	@ get task crunch save area
-	ldr	r2, [sp, #60]			@ current task pc value
-	ldr	r1, [r3]			@ get current crunch owner
-	str	r0, [r3]			@ this task now owns crunch
-	sub	r2, r2, #4			@ adjust pc back
-	str	r2, [sp, #60]
-
-	ldr	r2, [r8, #0x80]
-	mov	r2, r2				@ flush out enable (@@@)
-
-	teq	r1, #0				@ test for last ownership
-	mov	lr, r9				@ normal exit from exception
-	beq	crunch_load			@ no owner, skip save
-
-crunch_save:
-	cfstr64		mvdx0, [r1, #CRUNCH_MVDX0]	@ save 64b registers
-	cfstr64		mvdx1, [r1, #CRUNCH_MVDX1]
-	cfstr64		mvdx2, [r1, #CRUNCH_MVDX2]
-	cfstr64		mvdx3, [r1, #CRUNCH_MVDX3]
-	cfstr64		mvdx4, [r1, #CRUNCH_MVDX4]
-	cfstr64		mvdx5, [r1, #CRUNCH_MVDX5]
-	cfstr64		mvdx6, [r1, #CRUNCH_MVDX6]
-	cfstr64		mvdx7, [r1, #CRUNCH_MVDX7]
-	cfstr64		mvdx8, [r1, #CRUNCH_MVDX8]
-	cfstr64		mvdx9, [r1, #CRUNCH_MVDX9]
-	cfstr64		mvdx10, [r1, #CRUNCH_MVDX10]
-	cfstr64		mvdx11, [r1, #CRUNCH_MVDX11]
-	cfstr64		mvdx12, [r1, #CRUNCH_MVDX12]
-	cfstr64		mvdx13, [r1, #CRUNCH_MVDX13]
-	cfstr64		mvdx14, [r1, #CRUNCH_MVDX14]
-	cfstr64		mvdx15, [r1, #CRUNCH_MVDX15]
-
-#ifdef __ARMEB__
-#error fix me for ARMEB
-#endif
-
-	cfmv32al	mvfx0, mvax0			@ save 72b accumulators
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX0L]
-	cfmv32am	mvfx0, mvax0
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX0M]
-	cfmv32ah	mvfx0, mvax0
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX0H]
-	cfmv32al	mvfx0, mvax1
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX1L]
-	cfmv32am	mvfx0, mvax1
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX1M]
-	cfmv32ah	mvfx0, mvax1
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX1H]
-	cfmv32al	mvfx0, mvax2
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX2L]
-	cfmv32am	mvfx0, mvax2
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX2M]
-	cfmv32ah	mvfx0, mvax2
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX2H]
-	cfmv32al	mvfx0, mvax3
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX3L]
-	cfmv32am	mvfx0, mvax3
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX3M]
-	cfmv32ah	mvfx0, mvax3
-	cfstr32		mvfx0, [r1, #CRUNCH_MVAX3H]
-
-	cfmv32sc	mvdx0, dspsc			@ save status word
-	cfstr64		mvdx0, [r1, #CRUNCH_DSPSC]
-
-	teq		r0, #0				@ anything to load?
-	cfldr64eq	mvdx0, [r1, #CRUNCH_MVDX0]	@ mvdx0 was clobbered
-	moveq		pc, lr
-
-crunch_load:
-	cfldr64		mvdx0, [r0, #CRUNCH_DSPSC]	@ load status word
-	cfmvsc32	dspsc, mvdx0
-
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX0L]	@ load 72b accumulators
-	cfmval32	mvax0, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX0M]
-	cfmvam32	mvax0, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX0H]
-	cfmvah32	mvax0, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX1L]
-	cfmval32	mvax1, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX1M]
-	cfmvam32	mvax1, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX1H]
-	cfmvah32	mvax1, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX2L]
-	cfmval32	mvax2, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX2M]
-	cfmvam32	mvax2, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX2H]
-	cfmvah32	mvax2, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX3L]
-	cfmval32	mvax3, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX3M]
-	cfmvam32	mvax3, mvfx0
-	cfldr32		mvfx0, [r0, #CRUNCH_MVAX3H]
-	cfmvah32	mvax3, mvfx0
-
-	cfldr64		mvdx0, [r0, #CRUNCH_MVDX0]	@ load 64b registers
-	cfldr64		mvdx1, [r0, #CRUNCH_MVDX1]
-	cfldr64		mvdx2, [r0, #CRUNCH_MVDX2]
-	cfldr64		mvdx3, [r0, #CRUNCH_MVDX3]
-	cfldr64		mvdx4, [r0, #CRUNCH_MVDX4]
-	cfldr64		mvdx5, [r0, #CRUNCH_MVDX5]
-	cfldr64		mvdx6, [r0, #CRUNCH_MVDX6]
-	cfldr64		mvdx7, [r0, #CRUNCH_MVDX7]
-	cfldr64		mvdx8, [r0, #CRUNCH_MVDX8]
-	cfldr64		mvdx9, [r0, #CRUNCH_MVDX9]
-	cfldr64		mvdx10, [r0, #CRUNCH_MVDX10]
-	cfldr64		mvdx11, [r0, #CRUNCH_MVDX11]
-	cfldr64		mvdx12, [r0, #CRUNCH_MVDX12]
-	cfldr64		mvdx13, [r0, #CRUNCH_MVDX13]
-	cfldr64		mvdx14, [r0, #CRUNCH_MVDX14]
-	cfldr64		mvdx15, [r0, #CRUNCH_MVDX15]
-
-	mov	pc, lr
-
-/*
- * Back up crunch regs to save area and disable access to them
- * (mainly for gdb or sleep mode usage)
- *
- * r0 = struct thread_info pointer of target task or NULL for any
- */
-ENTRY(crunch_task_disable)
-	stmfd	sp!, {r4, r5, lr}
-
-	mrs	ip, cpsr
-	orr	r2, ip, #PSR_I_BIT		@ disable interrupts
-	msr	cpsr_c, r2
-
-	ldr	r4, =(EP93XX_APB_VIRT_BASE + 0x00130000)	@ syscon addr
-
-	ldr	r3, =crunch_owner
-	add	r2, r0, #TI_CRUNCH_STATE	@ get task crunch save area
-	ldr	r1, [r3]			@ get current crunch owner
-	teq	r1, #0				@ any current owner?
-	beq	1f				@ no: quit
-	teq	r0, #0				@ any owner?
-	teqne	r1, r2				@ or specified one?
-	bne	1f				@ no: quit
-
-	ldr	r5, [r4, #0x80]			@ enable access to crunch
-	mov	r2, #0xaa
-	str	r2, [r4, #0xc0]
-	orr	r5, r5, #0x00800000
-	str	r5, [r4, #0x80]
-
-	mov	r0, #0				@ nothing to load
-	str	r0, [r3]			@ no more current owner
-	ldr	r2, [r4, #0x80]			@ flush out enable (@@@)
-	mov	r2, r2
-	bl	crunch_save
-
-	mov	r2, #0xaa			@ disable access to crunch
-	str	r2, [r4, #0xc0]
-	bic	r5, r5, #0x00800000
-	str	r5, [r4, #0x80]
-	ldr	r5, [r4, #0x80]			@ flush out enable (@@@)
-	mov	r5, r5
-
-1:	msr	cpsr_c, ip			@ restore interrupt mode
-	ldmfd	sp!, {r4, r5, pc}
-
-/*
- * Copy crunch state to given memory address
- *
- * r0 = struct thread_info pointer of target task
- * r1 = memory address where to store crunch state
- *
- * this is called mainly in the creation of signal stack frames
- */
-ENTRY(crunch_task_copy)
-	mrs	ip, cpsr
-	orr	r2, ip, #PSR_I_BIT		@ disable interrupts
-	msr	cpsr_c, r2
-
-	ldr	r3, =crunch_owner
-	add	r2, r0, #TI_CRUNCH_STATE	@ get task crunch save area
-	ldr	r3, [r3]			@ get current crunch owner
-	teq	r2, r3				@ does this task own it...
-	beq	1f
-
-	@ current crunch values are in the task save area
-	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	r0, r1
-	mov	r1, r2
-	mov	r2, #CRUNCH_SIZE
-	b	memcpy
-
-1:	@ this task owns crunch regs -- grab a copy from there
-	mov	r0, #0				@ nothing to load
-	mov	r3, lr				@ preserve return address
-	bl	crunch_save
-	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	pc, r3
-
-/*
- * Restore crunch state from given memory address
- *
- * r0 = struct thread_info pointer of target task
- * r1 = memory address where to get crunch state from
- *
- * this is used to restore crunch state when unwinding a signal stack frame
- */
-ENTRY(crunch_task_restore)
-	mrs	ip, cpsr
-	orr	r2, ip, #PSR_I_BIT		@ disable interrupts
-	msr	cpsr_c, r2
-
-	ldr	r3, =crunch_owner
-	add	r2, r0, #TI_CRUNCH_STATE	@ get task crunch save area
-	ldr	r3, [r3]			@ get current crunch owner
-	teq	r2, r3				@ does this task own it...
-	beq	1f
-
-	@ this task doesn't own crunch regs -- use its save area
-	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	r0, r2
-	mov	r2, #CRUNCH_SIZE
-	b	memcpy
-
-1:	@ this task owns crunch regs -- load them directly
-	mov	r0, r1
-	mov	r1, #0				@ nothing to save
-	mov	r3, lr				@ preserve return address
-	bl	crunch_load
-	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	pc, r3
diff --git a/arch/arm/kernel/crunch.c b/arch/arm/kernel/crunch.c
deleted file mode 100644
index 25ef223ba7f..00000000000
--- a/arch/arm/kernel/crunch.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * arch/arm/kernel/crunch.c
- * Cirrus MaverickCrunch context switching and handling
- *
- * Copyright (C) 2006 Lennert Buytenhek <buytenh@wantstofly.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <mach/ep93xx-regs.h>
-#include <asm/thread_notify.h>
-
-struct crunch_state *crunch_owner;
-
-void crunch_task_release(struct thread_info *thread)
-{
-	local_irq_disable();
-	if (crunch_owner == &thread->crunchstate)
-		crunch_owner = NULL;
-	local_irq_enable();
-}
-
-static int crunch_enabled(u32 devcfg)
-{
-	return !!(devcfg & EP93XX_SYSCON_DEVCFG_CPENA);
-}
-
-static int crunch_do(struct notifier_block *self, unsigned long cmd, void *t)
-{
-	struct thread_info *thread = (struct thread_info *)t;
-	struct crunch_state *crunch_state;
-	u32 devcfg;
-
-	crunch_state = &thread->crunchstate;
-
-	switch (cmd) {
-	case THREAD_NOTIFY_FLUSH:
-		memset(crunch_state, 0, sizeof(*crunch_state));
-
-		/*
-		 * FALLTHROUGH: Ensure we don't try to overwrite our newly
-		 * initialised state information on the first fault.
-		 */
-
-	case THREAD_NOTIFY_EXIT:
-		crunch_task_release(thread);
-		break;
-
-	case THREAD_NOTIFY_SWITCH:
-		devcfg = __raw_readl(EP93XX_SYSCON_DEVCFG);
-		if (crunch_enabled(devcfg) || crunch_owner == crunch_state) {
-			/*
-			 * We don't use ep93xx_syscon_swlocked_write() here
-			 * because we are on the context switch path and
-			 * preemption is already disabled.
-			 */
-			devcfg ^= EP93XX_SYSCON_DEVCFG_CPENA;
-			__raw_writel(0xaa, EP93XX_SYSCON_SWLOCK);
-			__raw_writel(devcfg, EP93XX_SYSCON_DEVCFG);
-		}
-		break;
-	}
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block crunch_notifier_block = {
-	.notifier_call	= crunch_do,
-};
-
-static int __init crunch_init(void)
-{
-	thread_register_notifier(&crunch_notifier_block);
-	elf_hwcap |= HWCAP_CRUNCH;
-
-	return 0;
-}
-
-late_initcall(crunch_init);
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 204e2160cfc..c45522c3678 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -10,6 +10,7 @@
  *  32-bit debugging code
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 		.text
 
@@ -100,7 +101,7 @@
 
 #endif	/* CONFIG_CPU_V6 */
 
-#else
+#elif !defined(CONFIG_DEBUG_SEMIHOSTING)
 #include <mach/debug-macro.S>
 #endif	/* CONFIG_DEBUG_ICEDCC */
 
@@ -155,6 +156,8 @@ hexbuf:		.space 16
 
 		.ltorg
 
+#ifndef CONFIG_DEBUG_SEMIHOSTING
+
 ENTRY(printascii)
 		addruart_current r3, r1, r2
 		b	2f
@@ -177,3 +180,24 @@ ENTRY(printch)
 		mov	r0, #0
 		b	1b
 ENDPROC(printch)
+
+#else
+
+ENTRY(printascii)
+		mov	r1, r0
+		mov	r0, #0x04		@ SYS_WRITE0
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xab		)
+		mov	pc, lr
+ENDPROC(printascii)
+
+ENTRY(printch)
+		adr	r1, hexbuf
+		strb	r0, [r1]
+		mov	r0, #0x03		@ SYS_WRITEC
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xab		)
+		mov	pc, lr
+ENDPROC(printch)
+
+#endif
diff --git a/arch/arm/kernel/ecard.c b/arch/arm/kernel/ecard.c
deleted file mode 100644
index 4dd0edab6a6..00000000000
--- a/arch/arm/kernel/ecard.c
+++ /dev/null
@@ -1,1231 +0,0 @@
-/*
- *  linux/arch/arm/kernel/ecard.c
- *
- *  Copyright 1995-2001 Russell King
- *
- * 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.
- *
- *  Find all installed expansion cards, and handle interrupts from them.
- *
- *  Created from information from Acorns RiscOS3 PRMs
- *
- *  08-Dec-1996	RMK	Added code for the 9'th expansion card - the ether
- *			podule slot.
- *  06-May-1997	RMK	Added blacklist for cards whose loader doesn't work.
- *  12-Sep-1997	RMK	Created new handling of interrupt enables/disables
- *			- cards can now register their own routine to control
- *			interrupts (recommended).
- *  29-Sep-1997	RMK	Expansion card interrupt hardware not being re-enabled
- *			on reset from Linux. (Caused cards not to respond
- *			under RiscOS without hard reset).
- *  15-Feb-1998	RMK	Added DMA support
- *  12-Sep-1998	RMK	Added EASI support
- *  10-Jan-1999	RMK	Run loaders in a simulated RISC OS environment.
- *  17-Apr-1999	RMK	Support for EASI Type C cycles.
- */
-#define ECARD_C
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/sched.h>
-#include <linux/interrupt.h>
-#include <linux/completion.h>
-#include <linux/reboot.h>
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/device.h>
-#include <linux/init.h>
-#include <linux/mutex.h>
-#include <linux/kthread.h>
-#include <linux/io.h>
-
-#include <asm/dma.h>
-#include <asm/ecard.h>
-#include <mach/hardware.h>
-#include <asm/irq.h>
-#include <asm/mmu_context.h>
-#include <asm/mach/irq.h>
-#include <asm/tlbflush.h>
-
-#include "ecard.h"
-
-#ifndef CONFIG_ARCH_RPC
-#define HAVE_EXPMASK
-#endif
-
-struct ecard_request {
-	void		(*fn)(struct ecard_request *);
-	ecard_t		*ec;
-	unsigned int	address;
-	unsigned int	length;
-	unsigned int	use_loader;
-	void		*buffer;
-	struct completion *complete;
-};
-
-struct expcard_blacklist {
-	unsigned short	 manufacturer;
-	unsigned short	 product;
-	const char	*type;
-};
-
-static ecard_t *cards;
-static ecard_t *slot_to_expcard[MAX_ECARDS];
-static unsigned int ectcr;
-#ifdef HAS_EXPMASK
-static unsigned int have_expmask;
-#endif
-
-/* List of descriptions of cards which don't have an extended
- * identification, or chunk directories containing a description.
- */
-static struct expcard_blacklist __initdata blacklist[] = {
-	{ MANU_ACORN, PROD_ACORN_ETHER1, "Acorn Ether1" }
-};
-
-asmlinkage extern int
-ecard_loader_reset(unsigned long base, loader_t loader);
-asmlinkage extern int
-ecard_loader_read(int off, unsigned long base, loader_t loader);
-
-static inline unsigned short ecard_getu16(unsigned char *v)
-{
-	return v[0] | v[1] << 8;
-}
-
-static inline signed long ecard_gets24(unsigned char *v)
-{
-	return v[0] | v[1] << 8 | v[2] << 16 | ((v[2] & 0x80) ? 0xff000000 : 0);
-}
-
-static inline ecard_t *slot_to_ecard(unsigned int slot)
-{
-	return slot < MAX_ECARDS ? slot_to_expcard[slot] : NULL;
-}
-
-/* ===================== Expansion card daemon ======================== */
-/*
- * Since the loader programs on the expansion cards need to be run
- * in a specific environment, create a separate task with this
- * environment up, and pass requests to this task as and when we
- * need to.
- *
- * This should allow 99% of loaders to be called from Linux.
- *
- * From a security standpoint, we trust the card vendors.  This
- * may be a misplaced trust.
- */
-static void ecard_task_reset(struct ecard_request *req)
-{
-	struct expansion_card *ec = req->ec;
-	struct resource *res;
-
-	res = ec->slot_no == 8
-		? &ec->resource[ECARD_RES_MEMC]
-		: ec->easi
-		  ? &ec->resource[ECARD_RES_EASI]
-		  : &ec->resource[ECARD_RES_IOCSYNC];
-
-	ecard_loader_reset(res->start, ec->loader);
-}
-
-static void ecard_task_readbytes(struct ecard_request *req)
-{
-	struct expansion_card *ec = req->ec;
-	unsigned char *buf = req->buffer;
-	unsigned int len = req->length;
-	unsigned int off = req->address;
-
-	if (ec->slot_no == 8) {
-		void __iomem *base = (void __iomem *)
-				ec->resource[ECARD_RES_MEMC].start;
-
-		/*
-		 * The card maintains an index which increments the address
-		 * into a 4096-byte page on each access.  We need to keep
-		 * track of the counter.
-		 */
-		static unsigned int index;
-		unsigned int page;
-
-		page = (off >> 12) * 4;
-		if (page > 256 * 4)
-			return;
-
-		off &= 4095;
-
-		/*
-		 * If we are reading offset 0, or our current index is
-		 * greater than the offset, reset the hardware index counter.
-		 */
-		if (off == 0 || index > off) {
-			writeb(0, base);
-			index = 0;
-		}
-
-		/*
-		 * Increment the hardware index counter until we get to the
-		 * required offset.  The read bytes are discarded.
-		 */
-		while (index < off) {
-			readb(base + page);
-			index += 1;
-		}
-
-		while (len--) {
-			*buf++ = readb(base + page);
-			index += 1;
-		}
-	} else {
-		unsigned long base = (ec->easi
-			 ? &ec->resource[ECARD_RES_EASI]
-			 : &ec->resource[ECARD_RES_IOCSYNC])->start;
-		void __iomem *pbase = (void __iomem *)base;
-
-		if (!req->use_loader || !ec->loader) {
-			off *= 4;
-			while (len--) {
-				*buf++ = readb(pbase + off);
-				off += 4;
-			}
-		} else {
-			while(len--) {
-				/*
-				 * The following is required by some
-				 * expansion card loader programs.
-				 */
-				*(unsigned long *)0x108 = 0;
-				*buf++ = ecard_loader_read(off++, base,
-							   ec->loader);
-			}
-		}
-	}
-
-}
-
-static DECLARE_WAIT_QUEUE_HEAD(ecard_wait);
-static struct ecard_request *ecard_req;
-static DEFINE_MUTEX(ecard_mutex);
-
-/*
- * Set up the expansion card daemon's page tables.
- */
-static void ecard_init_pgtables(struct mm_struct *mm)
-{
-	struct vm_area_struct vma;
-
-	/* We want to set up the page tables for the following mapping:
-	 *  Virtual	Physical
-	 *  0x03000000	0x03000000
-	 *  0x03010000	unmapped
-	 *  0x03210000	0x03210000
-	 *  0x03400000	unmapped
-	 *  0x08000000	0x08000000
-	 *  0x10000000	unmapped
-	 *
-	 * FIXME: we don't follow this 100% yet.
-	 */
-	pgd_t *src_pgd, *dst_pgd;
-
-	src_pgd = pgd_offset(mm, (unsigned long)IO_BASE);
-	dst_pgd = pgd_offset(mm, IO_START);
-
-	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (IO_SIZE / PGDIR_SIZE));
-
-	src_pgd = pgd_offset(mm, (unsigned long)EASI_BASE);
-	dst_pgd = pgd_offset(mm, EASI_START);
-
-	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE));
-
-	vma.vm_mm = mm;
-
-	flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE);
-	flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE);
-}
-
-static int ecard_init_mm(void)
-{
-	struct mm_struct * mm = mm_alloc();
-	struct mm_struct *active_mm = current->active_mm;
-
-	if (!mm)
-		return -ENOMEM;
-
-	current->mm = mm;
-	current->active_mm = mm;
-	activate_mm(active_mm, mm);
-	mmdrop(active_mm);
-	ecard_init_pgtables(mm);
-	return 0;
-}
-
-static int
-ecard_task(void * unused)
-{
-	/*
-	 * Allocate a mm.  We're not a lazy-TLB kernel task since we need
-	 * to set page table entries where the user space would be.  Note
-	 * that this also creates the page tables.  Failure is not an
-	 * option here.
-	 */
-	if (ecard_init_mm())
-		panic("kecardd: unable to alloc mm\n");
-
-	while (1) {
-		struct ecard_request *req;
-
-		wait_event_interruptible(ecard_wait, ecard_req != NULL);
-
-		req = xchg(&ecard_req, NULL);
-		if (req != NULL) {
-			req->fn(req);
-			complete(req->complete);
-		}
-	}
-}
-
-/*
- * Wake the expansion card daemon to action our request.
- *
- * FIXME: The test here is not sufficient to detect if the
- * kcardd is running.
- */
-static void ecard_call(struct ecard_request *req)
-{
-	DECLARE_COMPLETION_ONSTACK(completion);
-
-	req->complete = &completion;
-
-	mutex_lock(&ecard_mutex);
-	ecard_req = req;
-	wake_up(&ecard_wait);
-
-	/*
-	 * Now wait for kecardd to run.
-	 */
-	wait_for_completion(&completion);
-	mutex_unlock(&ecard_mutex);
-}
-
-/* ======================= Mid-level card control ===================== */
-
-static void
-ecard_readbytes(void *addr, ecard_t *ec, int off, int len, int useld)
-{
-	struct ecard_request req;
-
-	req.fn		= ecard_task_readbytes;
-	req.ec		= ec;
-	req.address	= off;
-	req.length	= len;
-	req.use_loader	= useld;
-	req.buffer	= addr;
-
-	ecard_call(&req);
-}
-
-int ecard_readchunk(struct in_chunk_dir *cd, ecard_t *ec, int id, int num)
-{
-	struct ex_chunk_dir excd;
-	int index = 16;
-	int useld = 0;
-
-	if (!ec->cid.cd)
-		return 0;
-
-	while(1) {
-		ecard_readbytes(&excd, ec, index, 8, useld);
-		index += 8;
-		if (c_id(&excd) == 0) {
-			if (!useld && ec->loader) {
-				useld = 1;
-				index = 0;
-				continue;
-			}
-			return 0;
-		}
-		if (c_id(&excd) == 0xf0) { /* link */
-			index = c_start(&excd);
-			continue;
-		}
-		if (c_id(&excd) == 0x80) { /* loader */
-			if (!ec->loader) {
-				ec->loader = kmalloc(c_len(&excd),
-							       GFP_KERNEL);
-				if (ec->loader)
-					ecard_readbytes(ec->loader, ec,
-							(int)c_start(&excd),
-							c_len(&excd), useld);
-				else
-					return 0;
-			}
-			continue;
-		}
-		if (c_id(&excd) == id && num-- == 0)
-			break;
-	}
-
-	if (c_id(&excd) & 0x80) {
-		switch (c_id(&excd) & 0x70) {
-		case 0x70:
-			ecard_readbytes((unsigned char *)excd.d.string, ec,
-					(int)c_start(&excd), c_len(&excd),
-					useld);
-			break;
-		case 0x00:
-			break;
-		}
-	}
-	cd->start_offset = c_start(&excd);
-	memcpy(cd->d.string, excd.d.string, 256);
-	return 1;
-}
-
-/* ======================= Interrupt control ============================ */
-
-static void ecard_def_irq_enable(ecard_t *ec, int irqnr)
-{
-#ifdef HAS_EXPMASK
-	if (irqnr < 4 && have_expmask) {
-		have_expmask |= 1 << irqnr;
-		__raw_writeb(have_expmask, EXPMASK_ENABLE);
-	}
-#endif
-}
-
-static void ecard_def_irq_disable(ecard_t *ec, int irqnr)
-{
-#ifdef HAS_EXPMASK
-	if (irqnr < 4 && have_expmask) {
-		have_expmask &= ~(1 << irqnr);
-		__raw_writeb(have_expmask, EXPMASK_ENABLE);
-	}
-#endif
-}
-
-static int ecard_def_irq_pending(ecard_t *ec)
-{
-	return !ec->irqmask || readb(ec->irqaddr) & ec->irqmask;
-}
-
-static void ecard_def_fiq_enable(ecard_t *ec, int fiqnr)
-{
-	panic("ecard_def_fiq_enable called - impossible");
-}
-
-static void ecard_def_fiq_disable(ecard_t *ec, int fiqnr)
-{
-	panic("ecard_def_fiq_disable called - impossible");
-}
-
-static int ecard_def_fiq_pending(ecard_t *ec)
-{
-	return !ec->fiqmask || readb(ec->fiqaddr) & ec->fiqmask;
-}
-
-static expansioncard_ops_t ecard_default_ops = {
-	ecard_def_irq_enable,
-	ecard_def_irq_disable,
-	ecard_def_irq_pending,
-	ecard_def_fiq_enable,
-	ecard_def_fiq_disable,
-	ecard_def_fiq_pending
-};
-
-/*
- * Enable and disable interrupts from expansion cards.
- * (interrupts are disabled for these functions).
- *
- * They are not meant to be called directly, but via enable/disable_irq.
- */
-static void ecard_irq_unmask(struct irq_data *d)
-{
-	ecard_t *ec = slot_to_ecard(d->irq - 32);
-
-	if (ec) {
-		if (!ec->ops)
-			ec->ops = &ecard_default_ops;
-
-		if (ec->claimed && ec->ops->irqenable)
-			ec->ops->irqenable(ec, d->irq);
-		else
-			printk(KERN_ERR "ecard: rejecting request to "
-				"enable IRQs for %d\n", d->irq);
-	}
-}
-
-static void ecard_irq_mask(struct irq_data *d)
-{
-	ecard_t *ec = slot_to_ecard(d->irq - 32);
-
-	if (ec) {
-		if (!ec->ops)
-			ec->ops = &ecard_default_ops;
-
-		if (ec->ops && ec->ops->irqdisable)
-			ec->ops->irqdisable(ec, d->irq);
-	}
-}
-
-static struct irq_chip ecard_chip = {
-	.name		= "ECARD",
-	.irq_ack	= ecard_irq_mask,
-	.irq_mask	= ecard_irq_mask,
-	.irq_unmask	= ecard_irq_unmask,
-};
-
-void ecard_enablefiq(unsigned int fiqnr)
-{
-	ecard_t *ec = slot_to_ecard(fiqnr);
-
-	if (ec) {
-		if (!ec->ops)
-			ec->ops = &ecard_default_ops;
-
-		if (ec->claimed && ec->ops->fiqenable)
-			ec->ops->fiqenable(ec, fiqnr);
-		else
-			printk(KERN_ERR "ecard: rejecting request to "
-				"enable FIQs for %d\n", fiqnr);
-	}
-}
-
-void ecard_disablefiq(unsigned int fiqnr)
-{
-	ecard_t *ec = slot_to_ecard(fiqnr);
-
-	if (ec) {
-		if (!ec->ops)
-			ec->ops = &ecard_default_ops;
-
-		if (ec->ops->fiqdisable)
-			ec->ops->fiqdisable(ec, fiqnr);
-	}
-}
-
-static void ecard_dump_irq_state(void)
-{
-	ecard_t *ec;
-
-	printk("Expansion card IRQ state:\n");
-
-	for (ec = cards; ec; ec = ec->next) {
-		if (ec->slot_no == 8)
-			continue;
-
-		printk("  %d: %sclaimed, ",
-		       ec->slot_no, ec->claimed ? "" : "not ");
-
-		if (ec->ops && ec->ops->irqpending &&
-		    ec->ops != &ecard_default_ops)
-			printk("irq %spending\n",
-			       ec->ops->irqpending(ec) ? "" : "not ");
-		else
-			printk("irqaddr %p, mask = %02X, status = %02X\n",
-			       ec->irqaddr, ec->irqmask, readb(ec->irqaddr));
-	}
-}
-
-static void ecard_check_lockup(struct irq_desc *desc)
-{
-	static unsigned long last;
-	static int lockup;
-
-	/*
-	 * If the timer interrupt has not run since the last million
-	 * unrecognised expansion card interrupts, then there is
-	 * something seriously wrong.  Disable the expansion card
-	 * interrupts so at least we can continue.
-	 *
-	 * Maybe we ought to start a timer to re-enable them some time
-	 * later?
-	 */
-	if (last == jiffies) {
-		lockup += 1;
-		if (lockup > 1000000) {
-			printk(KERN_ERR "\nInterrupt lockup detected - "
-			       "disabling all expansion card interrupts\n");
-
-			desc->irq_data.chip->irq_mask(&desc->irq_data);
-			ecard_dump_irq_state();
-		}
-	} else
-		lockup = 0;
-
-	/*
-	 * If we did not recognise the source of this interrupt,
-	 * warn the user, but don't flood the user with these messages.
-	 */
-	if (!last || time_after(jiffies, last + 5*HZ)) {
-		last = jiffies;
-		printk(KERN_WARNING "Unrecognised interrupt from backplane\n");
-		ecard_dump_irq_state();
-	}
-}
-
-static void
-ecard_irq_handler(unsigned int irq, struct irq_desc *desc)
-{
-	ecard_t *ec;
-	int called = 0;
-
-	desc->irq_data.chip->irq_mask(&desc->irq_data);
-	for (ec = cards; ec; ec = ec->next) {
-		int pending;
-
-		if (!ec->claimed || ec->irq == NO_IRQ || ec->slot_no == 8)
-			continue;
-
-		if (ec->ops && ec->ops->irqpending)
-			pending = ec->ops->irqpending(ec);
-		else
-			pending = ecard_default_ops.irqpending(ec);
-
-		if (pending) {
-			generic_handle_irq(ec->irq);
-			called ++;
-		}
-	}
-	desc->irq_data.chip->irq_unmask(&desc->irq_data);
-
-	if (called == 0)
-		ecard_check_lockup(desc);
-}
-
-#ifdef HAS_EXPMASK
-static unsigned char priority_masks[] =
-{
-	0xf0, 0xf1, 0xf3, 0xf7, 0xff, 0xff, 0xff, 0xff
-};
-
-static unsigned char first_set[] =
-{
-	0x00, 0x00, 0x01, 0x00, 0x02, 0x00, 0x01, 0x00,
-	0x03, 0x00, 0x01, 0x00, 0x02, 0x00, 0x01, 0x00
-};
-
-static void
-ecard_irqexp_handler(unsigned int irq, struct irq_desc *desc)
-{
-	const unsigned int statusmask = 15;
-	unsigned int status;
-
-	status = __raw_readb(EXPMASK_STATUS) & statusmask;
-	if (status) {
-		unsigned int slot = first_set[status];
-		ecard_t *ec = slot_to_ecard(slot);
-
-		if (ec->claimed) {
-			/*
-			 * this ugly code is so that we can operate a
-			 * prioritorising system:
-			 *
-			 * Card 0 	highest priority
-			 * Card 1
-			 * Card 2
-			 * Card 3	lowest priority
-			 *
-			 * Serial cards should go in 0/1, ethernet/scsi in 2/3
-			 * otherwise you will lose serial data at high speeds!
-			 */
-			generic_handle_irq(ec->irq);
-		} else {
-			printk(KERN_WARNING "card%d: interrupt from unclaimed "
-			       "card???\n", slot);
-			have_expmask &= ~(1 << slot);
-			__raw_writeb(have_expmask, EXPMASK_ENABLE);
-		}
-	} else
-		printk(KERN_WARNING "Wild interrupt from backplane (masks)\n");
-}
-
-static int __init ecard_probeirqhw(void)
-{
-	ecard_t *ec;
-	int found;
-
-	__raw_writeb(0x00, EXPMASK_ENABLE);
-	__raw_writeb(0xff, EXPMASK_STATUS);
-	found = (__raw_readb(EXPMASK_STATUS) & 15) == 0;
-	__raw_writeb(0xff, EXPMASK_ENABLE);
-
-	if (found) {
-		printk(KERN_DEBUG "Expansion card interrupt "
-		       "management hardware found\n");
-
-		/* for each card present, set a bit to '1' */
-		have_expmask = 0x80000000;
-
-		for (ec = cards; ec; ec = ec->next)
-			have_expmask |= 1 << ec->slot_no;
-
-		__raw_writeb(have_expmask, EXPMASK_ENABLE);
-	}
-
-	return found;
-}
-#else
-#define ecard_irqexp_handler NULL
-#define ecard_probeirqhw() (0)
-#endif
-
-static void __iomem *__ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed)
-{
-	void __iomem *address = NULL;
-	int slot = ec->slot_no;
-
-	if (ec->slot_no == 8)
-		return ECARD_MEMC8_BASE;
-
-	ectcr &= ~(1 << slot);
-
-	switch (type) {
-	case ECARD_MEMC:
-		if (slot < 4)
-			address = ECARD_MEMC_BASE + (slot << 14);
-		break;
-
-	case ECARD_IOC:
-		if (slot < 4)
-			address = ECARD_IOC_BASE + (slot << 14);
-		else
-			address = ECARD_IOC4_BASE + ((slot - 4) << 14);
-		if (address)
-			address += speed << 19;
-		break;
-
-	case ECARD_EASI:
-		address = ECARD_EASI_BASE + (slot << 24);
-		if (speed == ECARD_FAST)
-			ectcr |= 1 << slot;
-		break;
-
-	default:
-		break;
-	}
-
-#ifdef IOMD_ECTCR
-	iomd_writeb(ectcr, IOMD_ECTCR);
-#endif
-	return address;
-}
-
-static int ecard_prints(struct seq_file *m, ecard_t *ec)
-{
-	seq_printf(m, "  %d: %s ", ec->slot_no, ec->easi ? "EASI" : "    ");
-
-	if (ec->cid.id == 0) {
-		struct in_chunk_dir incd;
-
-		seq_printf(m, "[%04X:%04X] ",
-			ec->cid.manufacturer, ec->cid.product);
-
-		if (!ec->card_desc && ec->cid.cd &&
-		    ecard_readchunk(&incd, ec, 0xf5, 0)) {
-			ec->card_desc = kmalloc(strlen(incd.d.string)+1, GFP_KERNEL);
-
-			if (ec->card_desc)
-				strcpy((char *)ec->card_desc, incd.d.string);
-		}
-
-		seq_printf(m, "%s\n", ec->card_desc ? ec->card_desc : "*unknown*");
-	} else
-		seq_printf(m, "Simple card %d\n", ec->cid.id);
-
-	return 0;
-}
-
-static int ecard_devices_proc_show(struct seq_file *m, void *v)
-{
-	ecard_t *ec = cards;
-
-	while (ec) {
-		ecard_prints(m, ec);
-		ec = ec->next;
-	}
-	return 0;
-}
-
-static int ecard_devices_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ecard_devices_proc_show, NULL);
-}
-
-static const struct file_operations bus_ecard_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ecard_devices_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static struct proc_dir_entry *proc_bus_ecard_dir = NULL;
-
-static void ecard_proc_init(void)
-{
-	proc_bus_ecard_dir = proc_mkdir("bus/ecard", NULL);
-	proc_create("devices", 0, proc_bus_ecard_dir, &bus_ecard_proc_fops);
-}
-
-#define ec_set_resource(ec,nr,st,sz)				\
-	do {							\
-		(ec)->resource[nr].name = dev_name(&ec->dev);	\
-		(ec)->resource[nr].start = st;			\
-		(ec)->resource[nr].end = (st) + (sz) - 1;	\
-		(ec)->resource[nr].flags = IORESOURCE_MEM;	\
-	} while (0)
-
-static void __init ecard_free_card(struct expansion_card *ec)
-{
-	int i;
-
-	for (i = 0; i < ECARD_NUM_RESOURCES; i++)
-		if (ec->resource[i].flags)
-			release_resource(&ec->resource[i]);
-
-	kfree(ec);
-}
-
-static struct expansion_card *__init ecard_alloc_card(int type, int slot)
-{
-	struct expansion_card *ec;
-	unsigned long base;
-	int i;
-
-	ec = kzalloc(sizeof(ecard_t), GFP_KERNEL);
-	if (!ec) {
-		ec = ERR_PTR(-ENOMEM);
-		goto nomem;
-	}
-
-	ec->slot_no = slot;
-	ec->easi = type == ECARD_EASI;
-	ec->irq = NO_IRQ;
-	ec->fiq = NO_IRQ;
-	ec->dma = NO_DMA;
-	ec->ops = &ecard_default_ops;
-
-	dev_set_name(&ec->dev, "ecard%d", slot);
-	ec->dev.parent = NULL;
-	ec->dev.bus = &ecard_bus_type;
-	ec->dev.dma_mask = &ec->dma_mask;
-	ec->dma_mask = (u64)0xffffffff;
-	ec->dev.coherent_dma_mask = ec->dma_mask;
-
-	if (slot < 4) {
-		ec_set_resource(ec, ECARD_RES_MEMC,
-				PODSLOT_MEMC_BASE + (slot << 14),
-				PODSLOT_MEMC_SIZE);
-		base = PODSLOT_IOC0_BASE + (slot << 14);
-	} else
-		base = PODSLOT_IOC4_BASE + ((slot - 4) << 14);
-
-#ifdef CONFIG_ARCH_RPC
-	if (slot < 8) {
-		ec_set_resource(ec, ECARD_RES_EASI,
-				PODSLOT_EASI_BASE + (slot << 24),
-				PODSLOT_EASI_SIZE);
-	}
-
-	if (slot == 8) {
-		ec_set_resource(ec, ECARD_RES_MEMC, NETSLOT_BASE, NETSLOT_SIZE);
-	} else
-#endif
-
-	for (i = 0; i <= ECARD_RES_IOCSYNC - ECARD_RES_IOCSLOW; i++)
-		ec_set_resource(ec, i + ECARD_RES_IOCSLOW,
-				base + (i << 19), PODSLOT_IOC_SIZE);
-
-	for (i = 0; i < ECARD_NUM_RESOURCES; i++) {
-		if (ec->resource[i].flags &&
-		    request_resource(&iomem_resource, &ec->resource[i])) {
-			dev_err(&ec->dev, "resource(s) not available\n");
-			ec->resource[i].end -= ec->resource[i].start;
-			ec->resource[i].start = 0;
-			ec->resource[i].flags = 0;
-		}
-	}
-
- nomem:
-	return ec;
-}
-
-static ssize_t ecard_show_irq(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	return sprintf(buf, "%u\n", ec->irq);
-}
-
-static ssize_t ecard_show_dma(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	return sprintf(buf, "%u\n", ec->dma);
-}
-
-static ssize_t ecard_show_resources(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	char *str = buf;
-	int i;
-
-	for (i = 0; i < ECARD_NUM_RESOURCES; i++)
-		str += sprintf(str, "%08x %08x %08lx\n",
-				ec->resource[i].start,
-				ec->resource[i].end,
-				ec->resource[i].flags);
-
-	return str - buf;
-}
-
-static ssize_t ecard_show_vendor(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	return sprintf(buf, "%u\n", ec->cid.manufacturer);
-}
-
-static ssize_t ecard_show_device(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	return sprintf(buf, "%u\n", ec->cid.product);
-}
-
-static ssize_t ecard_show_type(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	return sprintf(buf, "%s\n", ec->easi ? "EASI" : "IOC");
-}
-
-static struct device_attribute ecard_dev_attrs[] = {
-	__ATTR(device,   S_IRUGO, ecard_show_device,    NULL),
-	__ATTR(dma,      S_IRUGO, ecard_show_dma,       NULL),
-	__ATTR(irq,      S_IRUGO, ecard_show_irq,       NULL),
-	__ATTR(resource, S_IRUGO, ecard_show_resources, NULL),
-	__ATTR(type,     S_IRUGO, ecard_show_type,      NULL),
-	__ATTR(vendor,   S_IRUGO, ecard_show_vendor,    NULL),
-	__ATTR_NULL,
-};
-
-
-int ecard_request_resources(struct expansion_card *ec)
-{
-	int i, err = 0;
-
-	for (i = 0; i < ECARD_NUM_RESOURCES; i++) {
-		if (ecard_resource_end(ec, i) &&
-		    !request_mem_region(ecard_resource_start(ec, i),
-					ecard_resource_len(ec, i),
-					ec->dev.driver->name)) {
-			err = -EBUSY;
-			break;
-		}
-	}
-
-	if (err) {
-		while (i--)
-			if (ecard_resource_end(ec, i))
-				release_mem_region(ecard_resource_start(ec, i),
-						   ecard_resource_len(ec, i));
-	}
-	return err;
-}
-EXPORT_SYMBOL(ecard_request_resources);
-
-void ecard_release_resources(struct expansion_card *ec)
-{
-	int i;
-
-	for (i = 0; i < ECARD_NUM_RESOURCES; i++)
-		if (ecard_resource_end(ec, i))
-			release_mem_region(ecard_resource_start(ec, i),
-					   ecard_resource_len(ec, i));
-}
-EXPORT_SYMBOL(ecard_release_resources);
-
-void ecard_setirq(struct expansion_card *ec, const struct expansion_card_ops *ops, void *irq_data)
-{
-	ec->irq_data = irq_data;
-	barrier();
-	ec->ops = ops;
-}
-EXPORT_SYMBOL(ecard_setirq);
-
-void __iomem *ecardm_iomap(struct expansion_card *ec, unsigned int res,
-			   unsigned long offset, unsigned long maxsize)
-{
-	unsigned long start = ecard_resource_start(ec, res);
-	unsigned long end = ecard_resource_end(ec, res);
-
-	if (offset > (end - start))
-		return NULL;
-
-	start += offset;
-	if (maxsize && end - start > maxsize)
-		end = start + maxsize;
-	
-	return devm_ioremap(&ec->dev, start, end - start);
-}
-EXPORT_SYMBOL(ecardm_iomap);
-
-/*
- * Probe for an expansion card.
- *
- * If bit 1 of the first byte of the card is set, then the
- * card does not exist.
- */
-static int __init
-ecard_probe(int slot, card_type_t type)
-{
-	ecard_t **ecp;
-	ecard_t *ec;
-	struct ex_ecid cid;
-	void __iomem *addr;
-	int i, rc;
-
-	ec = ecard_alloc_card(type, slot);
-	if (IS_ERR(ec)) {
-		rc = PTR_ERR(ec);
-		goto nomem;
-	}
-
-	rc = -ENODEV;
-	if ((addr = __ecard_address(ec, type, ECARD_SYNC)) == NULL)
-		goto nodev;
-
-	cid.r_zero = 1;
-	ecard_readbytes(&cid, ec, 0, 16, 0);
-	if (cid.r_zero)
-		goto nodev;
-
-	ec->cid.id	= cid.r_id;
-	ec->cid.cd	= cid.r_cd;
-	ec->cid.is	= cid.r_is;
-	ec->cid.w	= cid.r_w;
-	ec->cid.manufacturer = ecard_getu16(cid.r_manu);
-	ec->cid.product = ecard_getu16(cid.r_prod);
-	ec->cid.country = cid.r_country;
-	ec->cid.irqmask = cid.r_irqmask;
-	ec->cid.irqoff  = ecard_gets24(cid.r_irqoff);
-	ec->cid.fiqmask = cid.r_fiqmask;
-	ec->cid.fiqoff  = ecard_gets24(cid.r_fiqoff);
-	ec->fiqaddr	=
-	ec->irqaddr	= addr;
-
-	if (ec->cid.is) {
-		ec->irqmask = ec->cid.irqmask;
-		ec->irqaddr += ec->cid.irqoff;
-		ec->fiqmask = ec->cid.fiqmask;
-		ec->fiqaddr += ec->cid.fiqoff;
-	} else {
-		ec->irqmask = 1;
-		ec->fiqmask = 4;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(blacklist); i++)
-		if (blacklist[i].manufacturer == ec->cid.manufacturer &&
-		    blacklist[i].product == ec->cid.product) {
-			ec->card_desc = blacklist[i].type;
-			break;
-		}
-
-	/*
-	 * hook the interrupt handlers
-	 */
-	if (slot < 8) {
-		ec->irq = 32 + slot;
-		irq_set_chip_and_handler(ec->irq, &ecard_chip,
-					 handle_level_irq);
-		set_irq_flags(ec->irq, IRQF_VALID);
-	}
-
-	if (slot == 8)
-		ec->irq = 11;
-#ifdef CONFIG_ARCH_RPC
-	/* On RiscPC, only first two slots have DMA capability */
-	if (slot < 2)
-		ec->dma = 2 + slot;
-#endif
-
-	for (ecp = &cards; *ecp; ecp = &(*ecp)->next);
-
-	*ecp = ec;
-	slot_to_expcard[slot] = ec;
-
-	device_register(&ec->dev);
-
-	return 0;
-
- nodev:
-	ecard_free_card(ec);
- nomem:
-	return rc;
-}
-
-/*
- * Initialise the expansion card system.
- * Locate all hardware - interrupt management and
- * actual cards.
- */
-static int __init ecard_init(void)
-{
-	struct task_struct *task;
-	int slot, irqhw;
-
-	task = kthread_run(ecard_task, NULL, "kecardd");
-	if (IS_ERR(task)) {
-		printk(KERN_ERR "Ecard: unable to create kernel thread: %ld\n",
-		       PTR_ERR(task));
-		return PTR_ERR(task);
-	}
-
-	printk("Probing expansion cards\n");
-
-	for (slot = 0; slot < 8; slot ++) {
-		if (ecard_probe(slot, ECARD_EASI) == -ENODEV)
-			ecard_probe(slot, ECARD_IOC);
-	}
-
-	ecard_probe(8, ECARD_IOC);
-
-	irqhw = ecard_probeirqhw();
-
-	irq_set_chained_handler(IRQ_EXPANSIONCARD,
-				irqhw ? ecard_irqexp_handler : ecard_irq_handler);
-
-	ecard_proc_init();
-
-	return 0;
-}
-
-subsys_initcall(ecard_init);
-
-/*
- *	ECARD "bus"
- */
-static const struct ecard_id *
-ecard_match_device(const struct ecard_id *ids, struct expansion_card *ec)
-{
-	int i;
-
-	for (i = 0; ids[i].manufacturer != 65535; i++)
-		if (ec->cid.manufacturer == ids[i].manufacturer &&
-		    ec->cid.product == ids[i].product)
-			return ids + i;
-
-	return NULL;
-}
-
-static int ecard_drv_probe(struct device *dev)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	struct ecard_driver *drv = ECARD_DRV(dev->driver);
-	const struct ecard_id *id;
-	int ret;
-
-	id = ecard_match_device(drv->id_table, ec);
-
-	ec->claimed = 1;
-	ret = drv->probe(ec, id);
-	if (ret)
-		ec->claimed = 0;
-	return ret;
-}
-
-static int ecard_drv_remove(struct device *dev)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	struct ecard_driver *drv = ECARD_DRV(dev->driver);
-
-	drv->remove(ec);
-	ec->claimed = 0;
-
-	/*
-	 * Restore the default operations.  We ensure that the
-	 * ops are set before we change the data.
-	 */
-	ec->ops = &ecard_default_ops;
-	barrier();
-	ec->irq_data = NULL;
-
-	return 0;
-}
-
-/*
- * Before rebooting, we must make sure that the expansion card is in a
- * sensible state, so it can be re-detected.  This means that the first
- * page of the ROM must be visible.  We call the expansion cards reset
- * handler, if any.
- */
-static void ecard_drv_shutdown(struct device *dev)
-{
-	struct expansion_card *ec = ECARD_DEV(dev);
-	struct ecard_driver *drv = ECARD_DRV(dev->driver);
-	struct ecard_request req;
-
-	if (dev->driver) {
-		if (drv->shutdown)
-			drv->shutdown(ec);
-		ec->claimed = 0;
-	}
-
-	/*
-	 * If this card has a loader, call the reset handler.
-	 */
-	if (ec->loader) {
-		req.fn = ecard_task_reset;
-		req.ec = ec;
-		ecard_call(&req);
-	}
-}
-
-int ecard_register_driver(struct ecard_driver *drv)
-{
-	drv->drv.bus = &ecard_bus_type;
-
-	return driver_register(&drv->drv);
-}
-
-void ecard_remove_driver(struct ecard_driver *drv)
-{
-	driver_unregister(&drv->drv);
-}
-
-static int ecard_match(struct device *_dev, struct device_driver *_drv)
-{
-	struct expansion_card *ec = ECARD_DEV(_dev);
-	struct ecard_driver *drv = ECARD_DRV(_drv);
-	int ret;
-
-	if (drv->id_table) {
-		ret = ecard_match_device(drv->id_table, ec) != NULL;
-	} else {
-		ret = ec->cid.id == drv->id;
-	}
-
-	return ret;
-}
-
-struct bus_type ecard_bus_type = {
-	.name		= "ecard",
-	.dev_attrs	= ecard_dev_attrs,
-	.match		= ecard_match,
-	.probe		= ecard_drv_probe,
-	.remove		= ecard_drv_remove,
-	.shutdown	= ecard_drv_shutdown,
-};
-
-static int ecard_bus_init(void)
-{
-	return bus_register(&ecard_bus_type);
-}
-
-postcore_initcall(ecard_bus_init);
-
-EXPORT_SYMBOL(ecard_readchunk);
-EXPORT_SYMBOL(ecard_register_driver);
-EXPORT_SYMBOL(ecard_remove_driver);
-EXPORT_SYMBOL(ecard_bus_type);
diff --git a/arch/arm/kernel/ecard.h b/arch/arm/kernel/ecard.h
deleted file mode 100644
index 4642d436be2..00000000000
--- a/arch/arm/kernel/ecard.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- *  ecard.h
- *
- *  Copyright 2007 Russell King
- *
- * 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.
- */
-
-/* Definitions internal to ecard.c - for it's use only!!
- *
- * External expansion card header as read from the card
- */
-struct ex_ecid {
-	unsigned char	r_irq:1;
-	unsigned char	r_zero:1;
-	unsigned char	r_fiq:1;
-	unsigned char	r_id:4;
-	unsigned char	r_a:1;
-
-	unsigned char	r_cd:1;
-	unsigned char	r_is:1;
-	unsigned char	r_w:2;
-	unsigned char	r_r1:4;
-
-	unsigned char	r_r2:8;
-
-	unsigned char	r_prod[2];
-
-	unsigned char	r_manu[2];
-
-	unsigned char	r_country;
-
-	unsigned char	r_fiqmask;
-	unsigned char	r_fiqoff[3];
-
-	unsigned char	r_irqmask;
-	unsigned char	r_irqoff[3];
-};
-
-/*
- * Chunk directory entry as read from the card
- */
-struct ex_chunk_dir {
-	unsigned char r_id;
-	unsigned char r_len[3];
-	unsigned long r_start;
-	union {
-		char string[256];
-		char data[1];
-	} d;
-#define c_id(x)		((x)->r_id)
-#define c_len(x)	((x)->r_len[0]|((x)->r_len[1]<<8)|((x)->r_len[2]<<16))
-#define c_start(x)	((x)->r_start)
-};
-
-typedef enum ecard_type {		/* Cards address space		*/
-	ECARD_IOC,
-	ECARD_MEMC,
-	ECARD_EASI
-} card_type_t;
-
-typedef enum {				/* Speed for ECARD_IOC space	*/
-	ECARD_SLOW	 = 0,
-	ECARD_MEDIUM	 = 1,
-	ECARD_FAST	 = 2,
-	ECARD_SYNC	 = 3
-} card_speed_t;
diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c
index ddba41d1fcf..d0d1e83150c 100644
--- a/arch/arm/kernel/elf.c
+++ b/arch/arm/kernel/elf.c
@@ -3,6 +3,7 @@
 #include <linux/personality.h>
 #include <linux/binfmts.h>
 #include <linux/elf.h>
+#include <asm/system_info.h>
 
 int elf_check_arch(const struct elf32_hdr *x)
 {
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index be16a48007b..7fd3ad048da 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -15,16 +15,19 @@
  *  that causes it to save wrong values...  Be aware!
  */
 
+#include <asm/assembler.h>
 #include <asm/memory.h>
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
 #include <asm/vfpmacros.h>
+#ifndef CONFIG_MULTI_IRQ_HANDLER
 #include <mach/entry-macro.S>
+#endif
 #include <asm/thread_notify.h>
 #include <asm/unwind.h>
 #include <asm/unistd.h>
 #include <asm/tls.h>
-#include <asm/system.h>
+#include <asm/system_info.h>
 
 #include "entry-header.S"
 #include <asm/entry-macro-multi.S>
@@ -1101,7 +1104,6 @@ __stubs_start:
  * get out of that mode without clobbering one register.
  */
 vector_fiq:
-	disable_fiq
 	subs	pc, lr, #4
 
 /*=============================================================================
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 9fd0ba90c1d..54ee265dd81 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -10,9 +10,15 @@
 
 #include <asm/unistd.h>
 #include <asm/ftrace.h>
-#include <mach/entry-macro.S>
 #include <asm/unwind.h>
 
+#ifdef CONFIG_NEED_RET_TO_USER
+#include <mach/entry-macro.S>
+#else
+	.macro  arch_ret_to_user, tmp1, tmp2
+	.endm
+#endif
+
 #include "entry-header.S"
 
 
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 4c164ece589..c32f8456aa0 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -42,9 +42,9 @@
 #include <linux/seq_file.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
 #include <asm/fiq.h>
 #include <asm/irq.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 static unsigned long no_fiq_insn;
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index c0062ad1e84..df0bf0c8cb7 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -16,10 +16,13 @@
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
+#include <asm/opcodes.h>
 #include <asm/ftrace.h>
 
+#include "insn.h"
+
 #ifdef CONFIG_THUMB2_KERNEL
-#define	NOP		0xeb04f85d	/* pop.w {lr} */
+#define	NOP		0xf85deb04	/* pop.w {lr} */
 #else
 #define	NOP		0xe8bd4000	/* pop {lr} */
 #endif
@@ -60,76 +63,31 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
 }
 #endif
 
-#ifdef CONFIG_THUMB2_KERNEL
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
-				       bool link)
-{
-	unsigned long s, j1, j2, i1, i2, imm10, imm11;
-	unsigned long first, second;
-	long offset;
-
-	offset = (long)addr - (long)(pc + 4);
-	if (offset < -16777216 || offset > 16777214) {
-		WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	s	= (offset >> 24) & 0x1;
-	i1	= (offset >> 23) & 0x1;
-	i2	= (offset >> 22) & 0x1;
-	imm10	= (offset >> 12) & 0x3ff;
-	imm11	= (offset >>  1) & 0x7ff;
-
-	j1 = (!i1) ^ s;
-	j2 = (!i2) ^ s;
-
-	first = 0xf000 | (s << 10) | imm10;
-	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
-	if (link)
-		second |= 1 << 14;
-
-	return (second << 16) | first;
-}
-#else
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
-				       bool link)
-{
-	unsigned long opcode = 0xea000000;
-	long offset;
-
-	if (link)
-		opcode |= 1 << 24;
-
-	offset = (long)addr - (long)(pc + 8);
-	if (unlikely(offset < -33554432 || offset > 33554428)) {
-		/* Can't generate branches that far (from ARM ARM). Ftrace
-		 * doesn't generate branches outside of kernel text.
-		 */
-		WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	offset = (offset >> 2) & 0x00ffffff;
-
-	return opcode | offset;
-}
-#endif
-
 static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 {
-	return ftrace_gen_branch(pc, addr, true);
+	return arm_gen_branch_link(pc, addr);
 }
 
 static int ftrace_modify_code(unsigned long pc, unsigned long old,
-			      unsigned long new)
+			      unsigned long new, bool validate)
 {
 	unsigned long replaced;
 
-	if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		old = __opcode_to_mem_thumb32(old);
+		new = __opcode_to_mem_thumb32(new);
+	} else {
+		old = __opcode_to_mem_arm(old);
+		new = __opcode_to_mem_arm(new);
+	}
 
-	if (replaced != old)
-		return -EINVAL;
+	if (validate) {
+		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+			return -EFAULT;
+
+		if (replaced != old)
+			return -EINVAL;
+	}
 
 	if (probe_kernel_write((void *)pc, &new, MCOUNT_INSN_SIZE))
 		return -EPERM;
@@ -141,23 +99,21 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old,
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
-	unsigned long pc, old;
+	unsigned long pc;
 	unsigned long new;
 	int ret;
 
 	pc = (unsigned long)&ftrace_call;
-	memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE);
 	new = ftrace_call_replace(pc, (unsigned long)func);
 
-	ret = ftrace_modify_code(pc, old, new);
+	ret = ftrace_modify_code(pc, 0, new, false);
 
 #ifdef CONFIG_OLD_MCOUNT
 	if (!ret) {
 		pc = (unsigned long)&ftrace_call_old;
-		memcpy(&old, &ftrace_call_old, MCOUNT_INSN_SIZE);
 		new = ftrace_call_replace(pc, (unsigned long)func);
 
-		ret = ftrace_modify_code(pc, old, new);
+		ret = ftrace_modify_code(pc, 0, new, false);
 	}
 #endif
 
@@ -172,7 +128,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	old = ftrace_nop_replace(rec);
 	new = ftrace_call_replace(ip, adjust_address(rec, addr));
 
-	return ftrace_modify_code(rec->ip, old, new);
+	return ftrace_modify_code(rec->ip, old, new, true);
 }
 
 int ftrace_make_nop(struct module *mod,
@@ -185,7 +141,7 @@ int ftrace_make_nop(struct module *mod,
 
 	old = ftrace_call_replace(ip, adjust_address(rec, addr));
 	new = ftrace_nop_replace(rec);
-	ret = ftrace_modify_code(ip, old, new);
+	ret = ftrace_modify_code(ip, old, new, true);
 
 #ifdef CONFIG_OLD_MCOUNT
 	if (ret == -EINVAL && addr == MCOUNT_ADDR) {
@@ -193,7 +149,7 @@ int ftrace_make_nop(struct module *mod,
 
 		old = ftrace_call_replace(ip, adjust_address(rec, addr));
 		new = ftrace_nop_replace(rec);
-		ret = ftrace_modify_code(ip, old, new);
+		ret = ftrace_modify_code(ip, old, new, true);
 	}
 #endif
 
@@ -249,12 +205,12 @@ static int __ftrace_modify_caller(unsigned long *callsite,
 {
 	unsigned long caller_fn = (unsigned long) func;
 	unsigned long pc = (unsigned long) callsite;
-	unsigned long branch = ftrace_gen_branch(pc, caller_fn, false);
+	unsigned long branch = arm_gen_branch(pc, caller_fn);
 	unsigned long nop = 0xe1a00000;	/* mov r0, r0 */
 	unsigned long old = enable ? nop : branch;
 	unsigned long new = enable ? branch : nop;
 
-	return ftrace_modify_code(pc, old, new);
+	return ftrace_modify_code(pc, old, new, true);
 }
 
 static int ftrace_modify_graph_caller(bool enable)
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index d46f25968be..278cfc144f4 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -17,8 +17,8 @@
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/cp15.h>
 #include <asm/thread_info.h>
-#include <asm/system.h>
 
 /*
  * Kernel startup entry point.
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 6d579114406..3bf0c7f8b04 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -15,12 +15,12 @@
 #include <linux/init.h>
 
 #include <asm/assembler.h>
+#include <asm/cp15.h>
 #include <asm/domain.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
 #include <asm/memory.h>
 #include <asm/thread_info.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 
 #ifdef CONFIG_DEBUG_LL
@@ -265,7 +265,7 @@ __create_page_tables:
 	str	r6, [r3]
 
 #ifdef CONFIG_DEBUG_LL
-#ifndef CONFIG_DEBUG_ICEDCC
+#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING)
 	/*
 	 * Map in IO space for serial debugging.
 	 * This allows debug messages to be output
@@ -297,10 +297,10 @@ __create_page_tables:
 	cmp	r0, r6
 	blo	1b
 
-#else /* CONFIG_DEBUG_ICEDCC */
-	/* we don't need any serial debugging mappings for ICEDCC */
+#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */
+	/* we don't need any serial debugging mappings */
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
-#endif /* !CONFIG_DEBUG_ICEDCC */
+#endif
 
 #if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)
 	/*
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index d6a95ef9131..ba386bd9410 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -34,7 +34,6 @@
 #include <asm/current.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/kdebug.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 /* Breakpoint currently in use for each BRP. */
diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c
new file mode 100644
index 00000000000..b760340b701
--- /dev/null
+++ b/arch/arm/kernel/insn.c
@@ -0,0 +1,62 @@
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <asm/opcodes.h>
+
+static unsigned long
+__arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link)
+{
+	unsigned long s, j1, j2, i1, i2, imm10, imm11;
+	unsigned long first, second;
+	long offset;
+
+	offset = (long)addr - (long)(pc + 4);
+	if (offset < -16777216 || offset > 16777214) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	s	= (offset >> 24) & 0x1;
+	i1	= (offset >> 23) & 0x1;
+	i2	= (offset >> 22) & 0x1;
+	imm10	= (offset >> 12) & 0x3ff;
+	imm11	= (offset >>  1) & 0x7ff;
+
+	j1 = (!i1) ^ s;
+	j2 = (!i2) ^ s;
+
+	first = 0xf000 | (s << 10) | imm10;
+	second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
+	if (link)
+		second |= 1 << 14;
+
+	return __opcode_thumb32_compose(first, second);
+}
+
+static unsigned long
+__arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link)
+{
+	unsigned long opcode = 0xea000000;
+	long offset;
+
+	if (link)
+		opcode |= 1 << 24;
+
+	offset = (long)addr - (long)(pc + 8);
+	if (unlikely(offset < -33554432 || offset > 33554428)) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	offset = (offset >> 2) & 0x00ffffff;
+
+	return opcode | offset;
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
+		return __arm_gen_branch_thumb2(pc, addr, link);
+	else
+		return __arm_gen_branch_arm(pc, addr, link);
+}
diff --git a/arch/arm/kernel/insn.h b/arch/arm/kernel/insn.h
new file mode 100644
index 00000000000..e96065da4da
--- /dev/null
+++ b/arch/arm/kernel/insn.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_INSN_H
+#define __ASM_ARM_INSN_H
+
+static inline unsigned long
+arm_gen_nop(void)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+	return 0xf3af8000; /* nop.w */
+#else
+	return 0xe1a00000; /* mov r0, r0 */
+#endif
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link);
+
+static inline unsigned long
+arm_gen_branch(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, false);
+}
+
+static inline unsigned long
+arm_gen_branch_link(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, true);
+}
+
+#endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 3efd82cc95f..71ccdbfed66 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -36,7 +36,6 @@
 #include <linux/proc_fs.h>
 
 #include <asm/exception.h>
-#include <asm/system.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
@@ -181,10 +180,7 @@ void migrate_irqs(void)
 	local_irq_save(flags);
 
 	for_each_irq_desc(i, desc) {
-		bool affinity_broken = false;
-
-		if (!desc)
-			continue;
+		bool affinity_broken;
 
 		raw_spin_lock(&desc->lock);
 		affinity_broken = migrate_one_irq(desc);
diff --git a/arch/arm/kernel/jump_label.c b/arch/arm/kernel/jump_label.c
new file mode 100644
index 00000000000..4ce4f789446
--- /dev/null
+++ b/arch/arm/kernel/jump_label.c
@@ -0,0 +1,39 @@
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+
+#include "insn.h"
+#include "patch.h"
+
+#ifdef HAVE_JUMP_LABEL
+
+static void __arch_jump_label_transform(struct jump_entry *entry,
+					enum jump_label_type type,
+					bool is_static)
+{
+	void *addr = (void *)entry->code;
+	unsigned int insn;
+
+	if (type == JUMP_LABEL_ENABLE)
+		insn = arm_gen_branch(entry->code, entry->target);
+	else
+		insn = arm_gen_nop();
+
+	if (is_static)
+		__patch_text(addr, insn);
+	else
+		patch_text(addr, insn);
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, false);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type)
+{
+	__arch_jump_label_transform(entry, type, true);
+}
+
+#endif
diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c
index a5394fb4e4e..18a76282970 100644
--- a/arch/arm/kernel/kprobes-common.c
+++ b/arch/arm/kernel/kprobes-common.c
@@ -13,6 +13,7 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <asm/system_info.h>
 
 #include "kprobes.h"
 
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 129c1163248..4dd41fc9e23 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -29,6 +29,7 @@
 #include <asm/cacheflush.h>
 
 #include "kprobes.h"
+#include "patch.h"
 
 #define MIN_STACK_SIZE(addr) 				\
 	min((unsigned long)MAX_STACK_SIZE,		\
@@ -103,57 +104,33 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	return 0;
 }
 
-#ifdef CONFIG_THUMB2_KERNEL
-
-/*
- * For a 32-bit Thumb breakpoint spanning two memory words we need to take
- * special precautions to insert the breakpoint atomically, especially on SMP
- * systems. This is achieved by calling this arming function using stop_machine.
- */
-static int __kprobes set_t32_breakpoint(void *addr)
-{
-	((u16 *)addr)[0] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION >> 16;
-	((u16 *)addr)[1] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION & 0xffff;
-	flush_insns(addr, 2*sizeof(u16));
-	return 0;
-}
-
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-	uintptr_t addr = (uintptr_t)p->addr & ~1; /* Remove any Thumb flag */
-
-	if (!is_wide_instruction(p->opcode)) {
-		*(u16 *)addr = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
-		flush_insns(addr, sizeof(u16));
-	} else if (addr & 2) {
-		/* A 32-bit instruction spanning two words needs special care */
-		stop_machine(set_t32_breakpoint, (void *)addr, &cpu_online_map);
+	unsigned int brkp;
+	void *addr;
+
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* Remove any Thumb flag */
+		addr = (void *)((uintptr_t)p->addr & ~1);
+
+		if (is_wide_instruction(p->opcode))
+			brkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
+		else
+			brkp = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
 	} else {
-		/* Word aligned 32-bit instruction can be written atomically */
-		u32 bkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
-#ifndef __ARMEB__ /* Swap halfwords for little-endian */
-		bkp = (bkp >> 16) | (bkp << 16);
-#endif
-		*(u32 *)addr = bkp;
-		flush_insns(addr, sizeof(u32));
-	}
-}
+		kprobe_opcode_t insn = p->opcode;
 
-#else /* !CONFIG_THUMB2_KERNEL */
+		addr = p->addr;
+		brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
 
-void __kprobes arch_arm_kprobe(struct kprobe *p)
-{
-	kprobe_opcode_t insn = p->opcode;
-	kprobe_opcode_t brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
-	if (insn >= 0xe0000000)
-		brkp |= 0xe0000000;  /* Unconditional instruction */
-	else
-		brkp |= insn & 0xf0000000;  /* Copy condition from insn */
-	*p->addr = brkp;
-	flush_insns(p->addr, sizeof(p->addr[0]));
-}
+		if (insn >= 0xe0000000)
+			brkp |= 0xe0000000;  /* Unconditional instruction */
+		else
+			brkp |= insn & 0xf0000000;  /* Copy condition from insn */
+	}
 
-#endif /* !CONFIG_THUMB2_KERNEL */
+	patch_text(addr, brkp);
+}
 
 /*
  * The actual disarming is done here on each CPU and synchronized using
@@ -166,31 +143,16 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
 int __kprobes __arch_disarm_kprobe(void *p)
 {
 	struct kprobe *kp = p;
-#ifdef CONFIG_THUMB2_KERNEL
-	u16 *addr = (u16 *)((uintptr_t)kp->addr & ~1);
-	kprobe_opcode_t insn = kp->opcode;
-	unsigned int len;
+	void *addr = (void *)((uintptr_t)kp->addr & ~1);
 
-	if (is_wide_instruction(insn)) {
-		((u16 *)addr)[0] = insn>>16;
-		((u16 *)addr)[1] = insn;
-		len = 2*sizeof(u16);
-	} else {
-		((u16 *)addr)[0] = insn;
-		len = sizeof(u16);
-	}
-	flush_insns(addr, len);
+	__patch_text(addr, kp->opcode);
 
-#else /* !CONFIG_THUMB2_KERNEL */
-	*kp->addr = kp->opcode;
-	flush_insns(kp->addr, sizeof(kp->addr[0]));
-#endif
 	return 0;
 }
 
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-	stop_machine(__arch_disarm_kprobe, p, &cpu_online_map);
+	stop_machine(__arch_disarm_kprobe, p, cpu_online_mask);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 764bd456d84..dfcdb9f7c12 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -7,12 +7,13 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
-#include <asm/system.h>
+#include <asm/system_misc.h>
 
 extern const unsigned char relocate_new_kernel[];
 extern const unsigned int relocate_new_kernel_size;
@@ -53,6 +54,29 @@ void machine_crash_nonpanic_core(void *unused)
 		cpu_relax();
 }
 
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
+			chip->irq_eoi(&desc->irq_data);
+
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
+}
+
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	unsigned long msecs;
@@ -70,6 +94,7 @@ void machine_crash_shutdown(struct pt_regs *regs)
 		printk(KERN_WARNING "Non-crashing CPUs did not react to IPI\n");
 
 	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
 
 	printk(KERN_INFO "Loading crashdump kernel...\n");
 }
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
new file mode 100644
index 00000000000..07314af4773
--- /dev/null
+++ b/arch/arm/kernel/patch.c
@@ -0,0 +1,75 @@
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/stop_machine.h>
+
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include <asm/opcodes.h>
+
+#include "patch.h"
+
+struct patch {
+	void *addr;
+	unsigned int insn;
+};
+
+void __kprobes __patch_text(void *addr, unsigned int insn)
+{
+	bool thumb2 = IS_ENABLED(CONFIG_THUMB2_KERNEL);
+	int size;
+
+	if (thumb2 && __opcode_is_thumb16(insn)) {
+		*(u16 *)addr = __opcode_to_mem_thumb16(insn);
+		size = sizeof(u16);
+	} else if (thumb2 && ((uintptr_t)addr & 2)) {
+		u16 first = __opcode_thumb32_first(insn);
+		u16 second = __opcode_thumb32_second(insn);
+		u16 *addrh = addr;
+
+		addrh[0] = __opcode_to_mem_thumb16(first);
+		addrh[1] = __opcode_to_mem_thumb16(second);
+
+		size = sizeof(u32);
+	} else {
+		if (thumb2)
+			insn = __opcode_to_mem_thumb32(insn);
+		else
+			insn = __opcode_to_mem_arm(insn);
+
+		*(u32 *)addr = insn;
+		size = sizeof(u32);
+	}
+
+	flush_icache_range((uintptr_t)(addr),
+			   (uintptr_t)(addr) + size);
+}
+
+static int __kprobes patch_text_stop_machine(void *data)
+{
+	struct patch *patch = data;
+
+	__patch_text(patch->addr, patch->insn);
+
+	return 0;
+}
+
+void __kprobes patch_text(void *addr, unsigned int insn)
+{
+	struct patch patch = {
+		.addr = addr,
+		.insn = insn,
+	};
+
+	if (cache_ops_need_broadcast()) {
+		stop_machine(patch_text_stop_machine, &patch, cpu_online_mask);
+	} else {
+		bool straddles_word = IS_ENABLED(CONFIG_THUMB2_KERNEL)
+				      && __opcode_is_thumb32(insn)
+				      && ((uintptr_t)addr & 2);
+
+		if (straddles_word)
+			stop_machine(patch_text_stop_machine, &patch, NULL);
+		else
+			__patch_text(addr, insn);
+	}
+}
diff --git a/arch/arm/kernel/patch.h b/arch/arm/kernel/patch.h
new file mode 100644
index 00000000000..b4731f2dac3
--- /dev/null
+++ b/arch/arm/kernel/patch.h
@@ -0,0 +1,7 @@
+#ifndef _ARM_KERNEL_PATCH_H
+#define _ARM_KERNEL_PATCH_H
+
+void patch_text(void *addr, unsigned int insn);
+void __patch_text(void *addr, unsigned int insn);
+
+#endif
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 5bb91bf3d47..186c8cb982c 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -180,7 +180,7 @@ armpmu_event_set_period(struct perf_event *event,
 u64
 armpmu_event_update(struct perf_event *event,
 		    struct hw_perf_event *hwc,
-		    int idx, int overflow)
+		    int idx)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	u64 delta, prev_raw_count, new_raw_count;
@@ -193,13 +193,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	new_raw_count &= armpmu->max_period;
-	prev_raw_count &= armpmu->max_period;
-
-	if (overflow)
-		delta = armpmu->max_period - prev_raw_count + new_raw_count + 1;
-	else
-		delta = new_raw_count - prev_raw_count;
+	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
 
 	local64_add(delta, &event->count);
 	local64_sub(delta, &hwc->period_left);
@@ -216,7 +210,7 @@ armpmu_read(struct perf_event *event)
 	if (hwc->idx < 0)
 		return;
 
-	armpmu_event_update(event, hwc, hwc->idx, 0);
+	armpmu_event_update(event, hwc, hwc->idx);
 }
 
 static void
@@ -232,7 +226,7 @@ armpmu_stop(struct perf_event *event, int flags)
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		armpmu->disable(hwc, hwc->idx);
 		barrier(); /* why? */
-		armpmu_event_update(event, hwc, hwc->idx, 0);
+		armpmu_event_update(event, hwc, hwc->idx);
 		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
 	}
 }
@@ -518,7 +512,13 @@ __hw_perf_event_init(struct perf_event *event)
 	hwc->config_base	    |= (unsigned long)mapping;
 
 	if (!hwc->sample_period) {
-		hwc->sample_period  = armpmu->max_period;
+		/*
+		 * For non-sampling runs, limit the sample_period to half
+		 * of the counter width. That way, the new counter value
+		 * is far less likely to overtake the previous one unless
+		 * you have some serious IRQ latency issues.
+		 */
+		hwc->sample_period  = armpmu->max_period >> 1;
 		hwc->last_period    = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
@@ -539,6 +539,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (armpmu->map_event(event) == -ENOENT)
 		return -ENOENT;
 
@@ -680,6 +684,28 @@ static void __init cpu_pmu_init(struct arm_pmu *armpmu)
 }
 
 /*
+ * PMU hardware loses all context when a CPU goes offline.
+ * When a CPU is hotplugged back in, since some hardware registers are
+ * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
+ * junk values out of them.
+ */
+static int __cpuinit pmu_cpu_notify(struct notifier_block *b,
+					unsigned long action, void *hcpu)
+{
+	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
+		return NOTIFY_DONE;
+
+	if (cpu_pmu && cpu_pmu->reset)
+		cpu_pmu->reset(NULL);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata pmu_cpu_notifier = {
+	.notifier_call = pmu_cpu_notify,
+};
+
+/*
  * CPU PMU identification and registration.
  */
 static int __init
@@ -712,6 +738,9 @@ init_hw_perf_events(void)
 		case 0xC0F0:	/* Cortex-A15 */
 			cpu_pmu = armv7_a15_pmu_init();
 			break;
+		case 0xC070:	/* Cortex-A7 */
+			cpu_pmu = armv7_a7_pmu_init();
+			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (0x69 == implementor) {
@@ -730,6 +759,7 @@ init_hw_perf_events(void)
 		pr_info("enabled with %s PMU driver, %d counters available\n",
 			cpu_pmu->name, cpu_pmu->num_events);
 		cpu_pmu_init(cpu_pmu);
+		register_cpu_notifier(&pmu_cpu_notifier);
 		armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
 	} else {
 		pr_info("no hardware support available\n");
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 533be9930ec..b78af0cc6ef 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -467,23 +467,6 @@ armv6pmu_enable_event(struct hw_perf_event *hwc,
 	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
 armv6pmu_handle_irq(int irq_num,
 		    void *dev)
@@ -513,7 +496,8 @@ armv6pmu_handle_irq(int irq_num,
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!counter_is_active(pmcr, idx))
+		/* Ignore if we don't have an event. */
+		if (!event)
 			continue;
 
 		/*
@@ -524,7 +508,7 @@ armv6pmu_handle_irq(int irq_num,
 			continue;
 
 		hwc = &event->hw;
-		armpmu_event_update(event, hwc, idx, 1);
+		armpmu_event_update(event, hwc, idx);
 		data.period = event->hw.last_period;
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 6933244c68f..00755d82e2f 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -610,6 +610,130 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 };
 
 /*
+ * Cortex-A7 HW events mapping
+ */
+static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
  * Perf Events' indices
  */
 #define	ARMV7_IDX_CYCLE_COUNTER	0
@@ -809,6 +933,11 @@ static inline int armv7_pmnc_disable_intens(int idx)
 
 	counter = ARMV7_IDX_TO_COUNTER(idx);
 	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter)));
+	isb();
+	/* Clear the overflow flag in case an interrupt is pending. */
+	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(counter)));
+	isb();
+
 	return idx;
 }
 
@@ -955,6 +1084,10 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
+		/* Ignore if we don't have an event. */
+		if (!event)
+			continue;
+
 		/*
 		 * We have a single interrupt for all counters. Check that
 		 * each counter has overflowed before we process it.
@@ -963,7 +1096,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 			continue;
 
 		hwc = &event->hw;
-		armpmu_event_update(event, hwc, idx, 1);
+		armpmu_event_update(event, hwc, idx);
 		data.period = event->hw.last_period;
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
@@ -1095,6 +1228,12 @@ static int armv7_a15_map_event(struct perf_event *event)
 				&armv7_a15_perf_cache_map, 0xFF);
 }
 
+static int armv7_a7_map_event(struct perf_event *event)
+{
+	return map_cpu_event(event, &armv7_a7_perf_map,
+				&armv7_a7_perf_cache_map, 0xFF);
+}
+
 static struct arm_pmu armv7pmu = {
 	.handle_irq		= armv7pmu_handle_irq,
 	.enable			= armv7pmu_enable_event,
@@ -1155,6 +1294,16 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void)
 	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
 	return &armv7pmu;
 }
+
+static struct arm_pmu *__init armv7_a7_pmu_init(void)
+{
+	armv7pmu.id		= ARM_PERF_PMU_ID_CA7;
+	armv7pmu.name		= "ARMv7 Cortex-A7";
+	armv7pmu.map_event	= armv7_a7_map_event;
+	armv7pmu.num_events	= armv7_read_num_pmnc_events();
+	armv7pmu.set_event_filter = armv7pmu_set_event_filter;
+	return &armv7pmu;
+}
 #else
 static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
@@ -1175,4 +1324,9 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void)
 {
 	return NULL;
 }
+
+static struct arm_pmu *__init armv7_a7_pmu_init(void)
+{
+	return NULL;
+}
 #endif	/* CONFIG_CPU_V7 */
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 3b99d826982..71a21e6712f 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -255,11 +255,14 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
+		if (!event)
+			continue;
+
 		if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
 			continue;
 
 		hwc = &event->hw;
-		armpmu_event_update(event, hwc, idx, 1);
+		armpmu_event_update(event, hwc, idx);
 		data.period = event->hw.last_period;
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
@@ -592,11 +595,14 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
-		if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
+		if (!event)
+			continue;
+
+		if (!xscale2_pmnc_counter_has_overflowed(of_flags, idx))
 			continue;
 
 		hwc = &event->hw;
-		armpmu_event_update(event, hwc, idx, 1);
+		armpmu_event_update(event, hwc, idx);
 		data.period = event->hw.last_period;
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
@@ -663,7 +669,7 @@ xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
 static void
 xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
-	unsigned long flags, ien, evtsel;
+	unsigned long flags, ien, evtsel, of_flags;
 	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	ien = xscale2pmu_read_int_enable();
@@ -672,26 +678,31 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 	switch (idx) {
 	case XSCALE_CYCLE_COUNTER:
 		ien &= ~XSCALE2_CCOUNT_INT_EN;
+		of_flags = XSCALE2_CCOUNT_OVERFLOW;
 		break;
 	case XSCALE_COUNTER0:
 		ien &= ~XSCALE2_COUNT0_INT_EN;
 		evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
 		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT;
+		of_flags = XSCALE2_COUNT0_OVERFLOW;
 		break;
 	case XSCALE_COUNTER1:
 		ien &= ~XSCALE2_COUNT1_INT_EN;
 		evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
 		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT;
+		of_flags = XSCALE2_COUNT1_OVERFLOW;
 		break;
 	case XSCALE_COUNTER2:
 		ien &= ~XSCALE2_COUNT2_INT_EN;
 		evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
 		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT;
+		of_flags = XSCALE2_COUNT2_OVERFLOW;
 		break;
 	case XSCALE_COUNTER3:
 		ien &= ~XSCALE2_COUNT3_INT_EN;
 		evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
 		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT;
+		of_flags = XSCALE2_COUNT3_OVERFLOW;
 		break;
 	default:
 		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
@@ -701,6 +712,7 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
+	xscale2pmu_write_overflow_flags(of_flags);
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 971d65c253a..2b7b017a20c 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -35,7 +35,6 @@
 #include <asm/cacheflush.h>
 #include <asm/leds.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/thread_notify.h>
 #include <asm/stacktrace.h>
 #include <asm/mach/time.h>
@@ -61,8 +60,6 @@ extern void setup_mm_for_reboot(void);
 
 static volatile int hlt_counter;
 
-#include <mach/system.h>
-
 void disable_hlt(void)
 {
 	hlt_counter++;
@@ -181,13 +178,17 @@ void cpu_idle_wait(void)
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
 /*
- * This is our default idle handler.  We need to disable
- * interrupts here to ensure we don't miss a wakeup call.
+ * This is our default idle handler.
  */
+
+void (*arm_pm_idle)(void);
+
 static void default_idle(void)
 {
-	if (!need_resched())
-		arch_idle();
+	if (arm_pm_idle)
+		arm_pm_idle();
+	else
+		cpu_do_idle();
 	local_irq_enable();
 }
 
@@ -215,6 +216,10 @@ void cpu_idle(void)
 				cpu_die();
 #endif
 
+			/*
+			 * We need to disable interrupts here
+			 * to ensure we don't miss a wakeup call.
+			 */
 			local_irq_disable();
 #ifdef CONFIG_PL310_ERRATA_769419
 			wmb();
@@ -222,26 +227,23 @@ void cpu_idle(void)
 			if (hlt_counter) {
 				local_irq_enable();
 				cpu_relax();
-			} else {
+			} else if (!need_resched()) {
 				stop_critical_timings();
 				if (cpuidle_idle_call())
 					pm_idle();
 				start_critical_timings();
 				/*
-				 * This will eventually be removed - pm_idle
-				 * functions should always return with IRQs
-				 * enabled.
+				 * pm_idle functions must always
+				 * return with IRQs enabled.
 				 */
 				WARN_ON(irqs_disabled());
+			} else
 				local_irq_enable();
-			}
 		}
 		leds_event(led_idle_end);
 		rcu_idle_exit();
 		tick_nohz_idle_exit();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
@@ -526,22 +528,39 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 #ifdef CONFIG_MMU
 /*
  * The vectors page is always readable from user space for the
- * atomic helpers and the signal restart code.  Let's declare a mapping
- * for it so it is visible through ptrace and /proc/<pid>/mem.
+ * atomic helpers and the signal restart code. Insert it into the
+ * gate_vma so that it is visible through ptrace and /proc/<pid>/mem.
  */
+static struct vm_area_struct gate_vma;
+
+static int __init gate_vma_init(void)
+{
+	gate_vma.vm_start	= 0xffff0000;
+	gate_vma.vm_end		= 0xffff0000 + PAGE_SIZE;
+	gate_vma.vm_page_prot	= PAGE_READONLY_EXEC;
+	gate_vma.vm_flags	= VM_READ | VM_EXEC |
+				  VM_MAYREAD | VM_MAYEXEC;
+	return 0;
+}
+arch_initcall(gate_vma_init);
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+	return &gate_vma;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+	return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end);
+}
 
-int vectors_user_mapping(void)
+int in_gate_area_no_mm(unsigned long addr)
 {
-	struct mm_struct *mm = current->mm;
-	return install_special_mapping(mm, 0xffff0000, PAGE_SIZE,
-				       VM_READ | VM_EXEC |
-				       VM_MAYREAD | VM_MAYEXEC |
-				       VM_ALWAYSDUMP | VM_RESERVED,
-				       NULL);
+	return in_gate_area(NULL, addr);
 }
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
-	return (vma->vm_start == 0xffff0000) ? "[vectors]" : NULL;
+	return (vma == &gate_vma) ? "[vectors]" : NULL;
 }
 #endif
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ede6443c34d..80abafb9bf3 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -26,7 +26,6 @@
 #include <linux/audit.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 
 #define REG_PC	15
@@ -257,7 +256,7 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
 {
 	unsigned long tmp;
 
-	if (off & 3 || off >= sizeof(struct user))
+	if (off & 3)
 		return -EIO;
 
 	tmp = 0;
@@ -269,6 +268,8 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
 		tmp = tsk->mm->end_code;
 	else if (off < sizeof(struct pt_regs))
 		tmp = get_user_reg(tsk, off >> 2);
+	else if (off >= sizeof(struct user))
+		return -EIO;
 
 	return put_user(tmp, ret);
 }
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 5416c7c1252..27d186abbc0 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -10,6 +10,7 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/syscore_ops.h>
 #include <linux/timer.h>
 
 #include <asm/sched_clock.h>
@@ -164,3 +165,20 @@ void __init sched_clock_postinit(void)
 
 	sched_clock_poll(sched_clock_timer.data);
 }
+
+static int sched_clock_suspend(void)
+{
+	sched_clock_poll(sched_clock_timer.data);
+	return 0;
+}
+
+static struct syscore_ops sched_clock_ops = {
+	.suspend = sched_clock_suspend,
+};
+
+static int __init sched_clock_syscore_init(void)
+{
+	register_syscore_ops(&sched_clock_ops);
+	return 0;
+}
+device_initcall(sched_clock_syscore_init);
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index a255c39612c..b91411371ae 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -33,6 +33,7 @@
 #include <linux/sort.h>
 
 #include <asm/unified.h>
+#include <asm/cp15.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
@@ -44,12 +45,13 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/tlbflush.h>
-#include <asm/system.h>
 
 #include <asm/prom.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
+#include <asm/system_info.h>
+#include <asm/system_misc.h>
 #include <asm/traps.h>
 #include <asm/unwind.h>
 #include <asm/memblock.h>
@@ -974,7 +976,6 @@ void __init setup_arch(char **cmdline_p)
 	conswitchp = &dummy_con;
 #endif
 #endif
-	early_trap_init();
 
 	if (mdesc->init_early)
 		mdesc->init_early();
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 9e617bd4a14..7cb532fc8aa 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -66,12 +66,13 @@ const unsigned long syscall_restart_code[2] = {
  */
 asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask)
 {
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
+	sigset_t blocked;
+
 	current->saved_sigmask = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -280,10 +281,7 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0) {
 		sigdelsetmask(&set, ~_BLOCKABLE);
-		spin_lock_irq(&current->sighand->siglock);
-		current->blocked = set;
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
+		set_current_blocked(&set);
 	}
 
 	__get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
@@ -636,13 +634,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka,
 	/*
 	 * Block the signal if we were successful.
 	 */
-	spin_lock_irq(&tsk->sighand->siglock);
-	sigorsets(&tsk->blocked, &tsk->blocked,
-		  &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&tsk->blocked, sig);
-	recalc_sigpending();
-	spin_unlock_irq(&tsk->sighand->siglock);
+	block_sigmask(ka, sig);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 1f268bda455..987dcf33415 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -4,7 +4,6 @@
 #include <asm/assembler.h>
 #include <asm/glue-cache.h>
 #include <asm/glue-proc.h>
-#include <asm/system.h>
 	.text
 
 /*
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index cdeb727527d..addbbe8028c 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -58,6 +58,8 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 };
 
+static DECLARE_COMPLETION(cpu_running);
+
 int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
@@ -98,20 +100,12 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	 */
 	ret = boot_secondary(cpu, idle);
 	if (ret == 0) {
-		unsigned long timeout;
-
 		/*
 		 * CPU was successfully started, wait for it
 		 * to come online or time out.
 		 */
-		timeout = jiffies + HZ;
-		while (time_before(jiffies, timeout)) {
-			if (cpu_online(cpu))
-				break;
-
-			udelay(10);
-			barrier();
-		}
+		wait_for_completion_timeout(&cpu_running,
+						 msecs_to_jiffies(1000));
 
 		if (!cpu_online(cpu)) {
 			pr_crit("CPU%u: failed to come online\n", cpu);
@@ -246,6 +240,8 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
 	store_cpu_topology(cpuid);
 }
 
+static void percpu_timer_setup(void);
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -286,22 +282,16 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
-	 * before we continue.
+	 * before we continue - which happens after __cpu_up returns.
 	 */
 	set_cpu_online(cpu, true);
+	complete(&cpu_running);
 
 	/*
 	 * Setup the percpu timer for this CPU.
 	 */
 	percpu_timer_setup();
 
-	while (!cpu_active(cpu))
-		cpu_relax();
-
-	/*
-	 * cpu_active bit is set, so it's safe to enalbe interrupts
-	 * now.
-	 */
 	local_irq_enable();
 	local_fiq_enable();
 
@@ -359,7 +349,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		 * re-initialize the map in platform_smp_prepare_cpus() if
 		 * present != possible (e.g. physical hotplug).
 		 */
-		init_cpu_present(&cpu_possible_map);
+		init_cpu_present(cpu_possible_mask);
 
 		/*
 		 * Initialise the SCU if there are more than one CPU
@@ -459,7 +449,20 @@ static void __cpuinit broadcast_timer_setup(struct clock_event_device *evt)
 	clockevents_register_device(evt);
 }
 
-void __cpuinit percpu_timer_setup(void)
+static struct local_timer_ops *lt_ops;
+
+#ifdef CONFIG_LOCAL_TIMERS
+int local_timer_register(struct local_timer_ops *ops)
+{
+	if (lt_ops)
+		return -EBUSY;
+
+	lt_ops = ops;
+	return 0;
+}
+#endif
+
+static void __cpuinit percpu_timer_setup(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
@@ -467,7 +470,7 @@ void __cpuinit percpu_timer_setup(void)
 	evt->cpumask = cpumask_of(cpu);
 	evt->broadcast = smp_timer_broadcast;
 
-	if (local_timer_setup(evt))
+	if (!lt_ops || lt_ops->setup(evt))
 		broadcast_timer_setup(evt);
 }
 
@@ -482,7 +485,8 @@ static void percpu_timer_stop(void)
 	unsigned int cpu = smp_processor_id();
 	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
 
-	local_timer_stop(evt);
+	if (lt_ops)
+		lt_ops->stop(evt);
 }
 #endif
 
@@ -577,8 +581,9 @@ void smp_send_stop(void)
 	unsigned long timeout;
 
 	if (num_online_cpus() > 1) {
-		cpumask_t mask = cpu_online_map;
-		cpu_clear(smp_processor_id(), mask);
+		struct cpumask mask;
+		cpumask_copy(&mask, cpu_online_mask);
+		cpumask_clear_cpu(smp_processor_id(), &mask);
 
 		smp_cross_call(&mask, IPI_CPU_STOP);
 	}
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 7dcb35285be..02c5d2ce23b 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -13,18 +13,6 @@
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
 
-static void on_each_cpu_mask(void (*func)(void *), void *info, int wait,
-	const struct cpumask *mask)
-{
-	preempt_disable();
-
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(smp_processor_id(), mask))
-		func(info);
-
-	preempt_enable();
-}
-
 /**********************************************************************/
 
 /*
@@ -87,7 +75,7 @@ void flush_tlb_all(void)
 void flush_tlb_mm(struct mm_struct *mm)
 {
 	if (tlb_ops_need_broadcast())
-		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
+		on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
 	else
 		local_flush_tlb_mm(mm);
 }
@@ -98,7 +86,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		struct tlb_args ta;
 		ta.ta_vma = vma;
 		ta.ta_start = uaddr;
-		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page,
+					&ta, 1);
 	} else
 		local_flush_tlb_page(vma, uaddr);
 }
@@ -121,7 +110,8 @@ void flush_tlb_range(struct vm_area_struct *vma,
 		ta.ta_vma = vma;
 		ta.ta_start = start;
 		ta.ta_end = end;
-		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range,
+					&ta, 1);
 	} else
 		local_flush_tlb_range(vma, start, end);
 }
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 7a79b24597b..fef42b21cec 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -18,20 +18,23 @@
 #include <linux/smp.h>
 #include <linux/jiffies.h>
 #include <linux/clockchips.h>
-#include <linux/irq.h>
+#include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
 
 #include <asm/smp_twd.h>
 #include <asm/localtimer.h>
 #include <asm/hardware/gic.h>
 
 /* set up by the platform code */
-void __iomem *twd_base;
+static void __iomem *twd_base;
 
 static struct clk *twd_clk;
 static unsigned long twd_timer_rate;
 
 static struct clock_event_device __percpu **twd_evt;
+static int twd_ppi;
 
 static void twd_set_mode(enum clock_event_mode mode,
 			struct clock_event_device *clk)
@@ -77,7 +80,7 @@ static int twd_set_next_event(unsigned long evt,
  * If a local timer interrupt has occurred, acknowledge and return 1.
  * Otherwise, return 0.
  */
-int twd_timer_ack(void)
+static int twd_timer_ack(void)
 {
 	if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) {
 		__raw_writel(1, twd_base + TWD_TIMER_INTSTAT);
@@ -87,7 +90,7 @@ int twd_timer_ack(void)
 	return 0;
 }
 
-void twd_timer_stop(struct clock_event_device *clk)
+static void twd_timer_stop(struct clock_event_device *clk)
 {
 	twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
 	disable_percpu_irq(clk->irq);
@@ -222,28 +225,10 @@ static struct clk *twd_get_clock(void)
 /*
  * Setup the local clock events for a CPU.
  */
-void __cpuinit twd_timer_setup(struct clock_event_device *clk)
+static int __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;
-		}
-	}
-
 	if (!twd_clk)
 		twd_clk = twd_get_clock();
 
@@ -260,6 +245,7 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	clk->rating = 350;
 	clk->set_mode = twd_set_mode;
 	clk->set_next_event = twd_set_next_event;
+	clk->irq = twd_ppi;
 
 	this_cpu_clk = __this_cpu_ptr(twd_evt);
 	*this_cpu_clk = clk;
@@ -267,4 +253,95 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	clockevents_config_and_register(clk, twd_timer_rate,
 					0xf, 0xffffffff);
 	enable_percpu_irq(clk->irq, 0);
+
+	return 0;
+}
+
+static struct local_timer_ops twd_lt_ops __cpuinitdata = {
+	.setup	= twd_timer_setup,
+	.stop	= twd_timer_stop,
+};
+
+static int __init twd_local_timer_common_register(void)
+{
+	int err;
+
+	twd_evt = alloc_percpu(struct clock_event_device *);
+	if (!twd_evt) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	err = request_percpu_irq(twd_ppi, twd_handler, "twd", twd_evt);
+	if (err) {
+		pr_err("twd: can't register interrupt %d (%d)\n", twd_ppi, err);
+		goto out_free;
+	}
+
+	err = local_timer_register(&twd_lt_ops);
+	if (err)
+		goto out_irq;
+
+	return 0;
+
+out_irq:
+	free_percpu_irq(twd_ppi, twd_evt);
+out_free:
+	iounmap(twd_base);
+	twd_base = NULL;
+	free_percpu(twd_evt);
+
+	return err;
 }
+
+int __init twd_local_timer_register(struct twd_local_timer *tlt)
+{
+	if (twd_base || twd_evt)
+		return -EBUSY;
+
+	twd_ppi	= tlt->res[1].start;
+
+	twd_base = ioremap(tlt->res[0].start, resource_size(&tlt->res[0]));
+	if (!twd_base)
+		return -ENOMEM;
+
+	return twd_local_timer_common_register();
+}
+
+#ifdef CONFIG_OF
+const static struct of_device_id twd_of_match[] __initconst = {
+	{ .compatible = "arm,cortex-a9-twd-timer",	},
+	{ .compatible = "arm,cortex-a5-twd-timer",	},
+	{ .compatible = "arm,arm11mp-twd-timer",	},
+	{ },
+};
+
+void __init twd_local_timer_of_register(void)
+{
+	struct device_node *np;
+	int err;
+
+	np = of_find_matching_node(NULL, twd_of_match);
+	if (!np) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	twd_ppi = irq_of_parse_and_map(np, 0);
+	if (!twd_ppi) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	twd_base = of_iomap(np, 0);
+	if (!twd_base) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = twd_local_timer_common_register();
+
+out:
+	WARN(err, "twd_local_timer_of_register failed (%d)\n", err);
+}
+#endif
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 01ec453bb92..30ae6bb4a31 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -16,6 +16,7 @@
 #include <asm/cputype.h>
 #include <asm/mach/map.h>
 #include <asm/memory.h>
+#include <asm/system_info.h>
 #include "tcm.h"
 
 static struct gen_pool *tcm_pool;
diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c
index 9cb7aaca159..aab89976405 100644
--- a/arch/arm/kernel/thumbee.c
+++ b/arch/arm/kernel/thumbee.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
+#include <asm/system_info.h>
 #include <asm/thread_notify.h>
 
 /*
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 8c57dd3680e..fe31b22f18f 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -25,8 +25,6 @@
 #include <linux/timer.h>
 #include <linux/irq.h>
 
-#include <linux/mc146818rtc.h>
-
 #include <asm/leds.h>
 #include <asm/thread_info.h>
 #include <asm/sched_clock.h>
@@ -149,8 +147,6 @@ void __init time_init(void)
 {
 	system_timer = machine_desc->timer;
 	system_timer->init();
-#ifdef CONFIG_HAVE_SCHED_CLOCK
 	sched_clock_postinit();
-#endif
 }
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index f84dfe67724..778454750a6 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -29,11 +29,11 @@
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/exception.h>
-#include <asm/system.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
 #include <asm/unwind.h>
 #include <asm/tls.h>
+#include <asm/system_misc.h>
 
 #include "signal.h"
 
@@ -227,6 +227,11 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 #else
 #define S_SMP ""
 #endif
+#ifdef CONFIG_THUMB2_KERNEL
+#define S_ISA " THUMB2"
+#else
+#define S_ISA " ARM"
+#endif
 
 static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs)
 {
@@ -234,8 +239,8 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt
 	static int die_counter;
 	int ret;
 
-	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n",
-	       str, err, ++die_counter);
+	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP
+	       S_ISA "\n", str, err, ++die_counter);
 
 	/* trap and error numbers are mostly meaningless on ARM */
 	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV);
@@ -784,18 +789,16 @@ static void __init kuser_get_tls_init(unsigned long vectors)
 		memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4);
 }
 
-void __init early_trap_init(void)
+void __init early_trap_init(void *vectors_base)
 {
-#if defined(CONFIG_CPU_USE_DOMAINS)
-	unsigned long vectors = CONFIG_VECTORS_BASE;
-#else
-	unsigned long vectors = (unsigned long)vectors_page;
-#endif
+	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	extern char __kuser_helper_start[], __kuser_helper_end[];
 	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
 
+	vectors_page = vectors_base;
+
 	/*
 	 * Copy the vectors, stubs and kuser helpers (in entry-armv.S)
 	 * into the vector page, mapped at 0xffff0000, and ensure these