diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2e86b8f..32cbf3e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -2,6 +2,7 @@
 	bool
 	default y
 	select HAVE_AOUT
+	select HAVE_DMA_API_DEBUG
 	select HAVE_IDE
 	select HAVE_MEMBLOCK
 	select RTC_LIB
@@ -36,6 +37,9 @@
 config HAVE_PWM
 	bool
 
+config MIGHT_HAVE_PCI
+	bool
+
 config SYS_SUPPORTS_APM_EMULATION
 	bool
 
@@ -226,7 +230,7 @@
 	bool "ARM Ltd. Integrator family"
 	select ARM_AMBA
 	select ARCH_HAS_CPUFREQ
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select ICST
 	select GENERIC_CLOCKEVENTS
 	select PLAT_VERSATILE
@@ -236,7 +240,7 @@
 config ARCH_REALVIEW
 	bool "ARM Ltd. RealView family"
 	select ARM_AMBA
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select HAVE_SCHED_CLOCK
 	select ICST
 	select GENERIC_CLOCKEVENTS
@@ -251,7 +255,7 @@
 	bool "ARM Ltd. Versatile family"
 	select ARM_AMBA
 	select ARM_VIC
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select HAVE_SCHED_CLOCK
 	select ICST
 	select GENERIC_CLOCKEVENTS
@@ -266,7 +270,7 @@
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_AMBA
 	select ARM_TIMER_SP804
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
 	select HAVE_SCHED_CLOCK
@@ -288,7 +292,7 @@
 	depends on MMU
 	select CPU_V6
 	select ARM_AMBA
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	help
@@ -306,6 +310,7 @@
 	select CPU_V6
 	select GENERIC_CLOCKEVENTS
 	select ARM_GIC
+	select MIGHT_HAVE_PCI
 	select PCI_DOMAINS if PCI
 	help
 	  Support for Cavium Networks CNS3XXX platform.
@@ -335,7 +340,7 @@
 	select CPU_ARM920T
 	select ARM_AMBA
 	select ARM_VIC
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_USES_GETTIMEOFFSET
@@ -355,14 +360,14 @@
 	bool "Freescale MXC/iMX-based"
 	select GENERIC_CLOCKEVENTS
 	select ARCH_REQUIRE_GPIOLIB
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	help
 	  Support for Freescale MXC/iMX-based family of processors
 
 config ARCH_STMP3XXX
 	bool "Freescale STMP3xxx"
 	select CPU_ARM926T
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
 	select USB_ARCH_HAS_EHCI
@@ -442,6 +447,7 @@
 	select GENERIC_GPIO
 	select GENERIC_CLOCKEVENTS
 	select HAVE_SCHED_CLOCK
+	select MIGHT_HAVE_PCI
 	select DMABOUNCE if PCI
 	help
 	  Support for Intel's IXP4XX (XScale) family of processors.
@@ -481,7 +487,7 @@
 	select HAVE_IDE
 	select ARM_AMBA
 	select USB_ARCH_HAS_OHCI
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	help
@@ -515,7 +521,7 @@
 	bool "Marvell PXA168/910/MMP2"
 	depends on MMU
 	select ARCH_REQUIRE_GPIOLIB
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
@@ -549,7 +555,7 @@
 	bool "Nuvoton W90X900 CPU"
 	select CPU_ARM926T
 	select ARCH_REQUIRE_GPIOLIB
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	help
 	  Support for Nuvoton (Winbond logic dept.) ARM9 processor,
@@ -563,19 +569,19 @@
 config ARCH_NUC93X
 	bool "Nuvoton NUC93X CPU"
 	select CPU_ARM926T
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	help
 	  Support for Nuvoton (Winbond logic dept.) NUC93X MCU,The NUC93X is a
 	  low-power and high performance MPEG-4/JPEG multimedia controller chip.
 
 config ARCH_TEGRA
 	bool "NVIDIA Tegra"
+	select CLKDEV_LOOKUP
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
 	select HAVE_CLK
 	select HAVE_SCHED_CLOCK
-	select COMMON_CLKDEV
 	select ARCH_HAS_BARRIERS if CACHE_L2X0
 	select ARCH_HAS_CPUFREQ
 	help
@@ -585,7 +591,7 @@
 config ARCH_PNX4008
 	bool "Philips Nexperia PNX4008 Mobile"
 	select CPU_ARM926T
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select ARCH_USES_GETTIMEOFFSET
 	help
 	  This enables support for Philips PNX4008 mobile platform.
@@ -595,7 +601,7 @@
 	depends on MMU
 	select ARCH_MTD_XIP
 	select ARCH_HAS_CPUFREQ
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
 	select HAVE_SCHED_CLOCK
@@ -774,7 +780,7 @@
 	bool "Telechips TCC ARM926-based systems"
 	select CPU_ARM926T
 	select HAVE_CLK
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	help
 	  Support for Telechips TCC ARM926-based systems.
@@ -799,7 +805,7 @@
 	select ARM_AMBA
 	select ARM_VIC
 	select GENERIC_CLOCKEVENTS
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_GPIO
 	help
 	  Support for ST-Ericsson U300 series mobile platforms.
@@ -809,7 +815,7 @@
 	select CPU_V7
 	select ARM_AMBA
 	select GENERIC_CLOCKEVENTS
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select ARCH_REQUIRE_GPIOLIB
 	help
 	  Support for ST-Ericsson's Ux500 architecture
@@ -819,7 +825,7 @@
 	select ARM_AMBA
 	select ARM_VIC
 	select CPU_ARM926T
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select ARCH_REQUIRE_GPIOLIB
 	help
@@ -831,7 +837,7 @@
 	select ARCH_REQUIRE_GPIOLIB
 	select ZONE_DMA
 	select HAVE_IDE
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_ALLOCATOR
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	help
@@ -852,7 +858,7 @@
 	bool "ST SPEAr"
 	select ARM_AMBA
 	select ARCH_REQUIRE_GPIOLIB
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
 	help
@@ -1034,6 +1040,11 @@
 	default y
 	bool
 
+config MULTI_IRQ_HANDLER
+	bool
+	help
+	  Allow each machine to specify it's own IRQ handler at run time.
+
 if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
@@ -1181,7 +1192,7 @@
 	bool
 
 config PCI
-	bool "PCI support" if ARCH_INTEGRATOR_AP || ARCH_VERSATILE_PB || ARCH_IXP4XX || ARCH_KS8695 || MACH_ARMCORE || ARCH_CNS3XXX || SA1100_NANOENGINE
+	bool "PCI support" if MIGHT_HAVE_PCI
 	help
 	  Find out whether you have a PCI motherboard. PCI is the name of a
 	  bus system, i.e. the way the CPU talks to the other stuff inside
@@ -1253,7 +1264,7 @@
 config SMP_ON_UP
 	bool "Allow booting SMP kernel on uniprocessor systems (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
-	depends on SMP && !XIP && !THUMB2_KERNEL
+	depends on SMP && !XIP
 	default y
 	help
 	  SMP kernels contain instructions which fail on non-SMP processors.
@@ -1272,6 +1283,7 @@
 config HAVE_ARM_TWD
 	bool
 	depends on SMP
+	select TICK_ONESHOT
 	help
 	  This options enables support for the ARM timer and watchdog unit
 
@@ -1335,7 +1347,7 @@
 	default 100
 
 config THUMB2_KERNEL
-	bool "Compile the kernel in Thumb-2 mode"
+	bool "Compile the kernel in Thumb-2 mode (EXPERIMENTAL)"
 	depends on CPU_V7 && !CPU_V6 && EXPERIMENTAL
 	select AEABI
 	select ARM_ASM_UNIFIED
@@ -1549,6 +1561,7 @@
 
 config CC_STACKPROTECTOR
 	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
 	help
 	  This option turns on the -fstack-protector GCC feature. This
 	  feature puts, at the beginning of functions, a canary value on
@@ -1745,7 +1758,7 @@
 	  Internal configuration node for common cpufreq on Samsung SoC
 
 config CPU_FREQ_S3C24XX
-	bool "CPUfreq driver for Samsung S3C24XX series CPUs"
+	bool "CPUfreq driver for Samsung S3C24XX series CPUs (EXPERIMENTAL)"
 	depends on ARCH_S3C2410 && CPU_FREQ && EXPERIMENTAL
 	select CPU_FREQ_S3C
 	help
@@ -1757,7 +1770,7 @@
 	  If in doubt, say N.
 
 config CPU_FREQ_S3C24XX_PLL
-	bool "Support CPUfreq changing of PLL frequency"
+	bool "Support CPUfreq changing of PLL frequency (EXPERIMENTAL)"
 	depends on CPU_FREQ_S3C24XX && EXPERIMENTAL
 	help
 	  Compile in support for changing the PLL frequency from the
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index eac6208..494224a 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -31,7 +31,7 @@
 	  reported is severely limited.
 
 config ARM_UNWIND
-	bool "Enable stack unwinding support"
+	bool "Enable stack unwinding support (EXPERIMENTAL)"
 	depends on AEABI && EXPERIMENTAL
 	default y
 	help
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index 0a34c81..778655f 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -37,7 +37,3 @@
 
 config SHARP_SCOOP
 	bool
-
-config COMMON_CLKDEV
-	bool
-	select HAVE_CLK
diff --git a/arch/arm/common/clkdev.c b/arch/arm/common/clkdev.c
deleted file mode 100644
index e2b2bb6..0000000
--- a/arch/arm/common/clkdev.c
+++ /dev/null
@@ -1,179 +0,0 @@
-/*
- *  arch/arm/common/clkdev.c
- *
- *  Copyright (C) 2008 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.
- *
- * Helper for the clk API to assist looking up a struct clk.
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/list.h>
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/string.h>
-#include <linux/mutex.h>
-#include <linux/clk.h>
-#include <linux/slab.h>
-
-#include <asm/clkdev.h>
-#include <mach/clkdev.h>
-
-static LIST_HEAD(clocks);
-static DEFINE_MUTEX(clocks_mutex);
-
-/*
- * Find the correct struct clk for the device and connection ID.
- * We do slightly fuzzy matching here:
- *  An entry with a NULL ID is assumed to be a wildcard.
- *  If an entry has a device ID, it must match
- *  If an entry has a connection ID, it must match
- * Then we take the most specific entry - with the following
- * order of precedence: dev+con > dev only > con only.
- */
-static struct clk *clk_find(const char *dev_id, const char *con_id)
-{
-	struct clk_lookup *p;
-	struct clk *clk = NULL;
-	int match, best = 0;
-
-	list_for_each_entry(p, &clocks, node) {
-		match = 0;
-		if (p->dev_id) {
-			if (!dev_id || strcmp(p->dev_id, dev_id))
-				continue;
-			match += 2;
-		}
-		if (p->con_id) {
-			if (!con_id || strcmp(p->con_id, con_id))
-				continue;
-			match += 1;
-		}
-
-		if (match > best) {
-			clk = p->clk;
-			if (match != 3)
-				best = match;
-			else
-				break;
-		}
-	}
-	return clk;
-}
-
-struct clk *clk_get_sys(const char *dev_id, const char *con_id)
-{
-	struct clk *clk;
-
-	mutex_lock(&clocks_mutex);
-	clk = clk_find(dev_id, con_id);
-	if (clk && !__clk_get(clk))
-		clk = NULL;
-	mutex_unlock(&clocks_mutex);
-
-	return clk ? clk : ERR_PTR(-ENOENT);
-}
-EXPORT_SYMBOL(clk_get_sys);
-
-struct clk *clk_get(struct device *dev, const char *con_id)
-{
-	const char *dev_id = dev ? dev_name(dev) : NULL;
-
-	return clk_get_sys(dev_id, con_id);
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-	__clk_put(clk);
-}
-EXPORT_SYMBOL(clk_put);
-
-void clkdev_add(struct clk_lookup *cl)
-{
-	mutex_lock(&clocks_mutex);
-	list_add_tail(&cl->node, &clocks);
-	mutex_unlock(&clocks_mutex);
-}
-EXPORT_SYMBOL(clkdev_add);
-
-void __init clkdev_add_table(struct clk_lookup *cl, size_t num)
-{
-	mutex_lock(&clocks_mutex);
-	while (num--) {
-		list_add_tail(&cl->node, &clocks);
-		cl++;
-	}
-	mutex_unlock(&clocks_mutex);
-}
-
-#define MAX_DEV_ID	20
-#define MAX_CON_ID	16
-
-struct clk_lookup_alloc {
-	struct clk_lookup cl;
-	char	dev_id[MAX_DEV_ID];
-	char	con_id[MAX_CON_ID];
-};
-
-struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
-	const char *dev_fmt, ...)
-{
-	struct clk_lookup_alloc *cla;
-
-	cla = kzalloc(sizeof(*cla), GFP_KERNEL);
-	if (!cla)
-		return NULL;
-
-	cla->cl.clk = clk;
-	if (con_id) {
-		strlcpy(cla->con_id, con_id, sizeof(cla->con_id));
-		cla->cl.con_id = cla->con_id;
-	}
-
-	if (dev_fmt) {
-		va_list ap;
-
-		va_start(ap, dev_fmt);
-		vscnprintf(cla->dev_id, sizeof(cla->dev_id), dev_fmt, ap);
-		cla->cl.dev_id = cla->dev_id;
-		va_end(ap);
-	}
-
-	return &cla->cl;
-}
-EXPORT_SYMBOL(clkdev_alloc);
-
-int clk_add_alias(const char *alias, const char *alias_dev_name, char *id,
-	struct device *dev)
-{
-	struct clk *r = clk_get(dev, id);
-	struct clk_lookup *l;
-
-	if (IS_ERR(r))
-		return PTR_ERR(r);
-
-	l = clkdev_alloc(r, alias, alias_dev_name);
-	clk_put(r);
-	if (!l)
-		return -ENODEV;
-	clkdev_add(l);
-	return 0;
-}
-EXPORT_SYMBOL(clk_add_alias);
-
-/*
- * clkdev_drop - remove a clock dynamically allocated
- */
-void clkdev_drop(struct clk_lookup *cl)
-{
-	mutex_lock(&clocks_mutex);
-	list_del(&cl->node);
-	mutex_unlock(&clocks_mutex);
-	kfree(cl);
-}
-EXPORT_SYMBOL(clkdev_drop);
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index cc0a932..e568163 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -328,7 +328,7 @@
  * substitute the safe buffer for the unsafe one.
  * (basically move the buffer from an unsafe area to a safe one)
  */
-dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
+dma_addr_t __dma_map_single(struct device *dev, void *ptr, size_t size,
 		enum dma_data_direction dir)
 {
 	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
@@ -338,7 +338,7 @@
 
 	return map_single(dev, ptr, size, dir);
 }
-EXPORT_SYMBOL(dma_map_single);
+EXPORT_SYMBOL(__dma_map_single);
 
 /*
  * see if a mapped address was really a "safe" buffer and if so, copy
@@ -346,7 +346,7 @@
  * the safe buffer.  (basically return things back to the way they
  * should be)
  */
-void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+void __dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 		enum dma_data_direction dir)
 {
 	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
@@ -354,9 +354,9 @@
 
 	unmap_single(dev, dma_addr, size, dir);
 }
-EXPORT_SYMBOL(dma_unmap_single);
+EXPORT_SYMBOL(__dma_unmap_single);
 
-dma_addr_t dma_map_page(struct device *dev, struct page *page,
+dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir)
 {
 	dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n",
@@ -372,7 +372,7 @@
 
 	return map_single(dev, page_address(page) + offset, size, dir);
 }
-EXPORT_SYMBOL(dma_map_page);
+EXPORT_SYMBOL(__dma_map_page);
 
 /*
  * see if a mapped address was really a "safe" buffer and if so, copy
@@ -380,7 +380,7 @@
  * the safe buffer.  (basically return things back to the way they
  * should be)
  */
-void dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
+void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 		enum dma_data_direction dir)
 {
 	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
@@ -388,7 +388,7 @@
 
 	unmap_single(dev, dma_addr, size, dir);
 }
-EXPORT_SYMBOL(dma_unmap_page);
+EXPORT_SYMBOL(__dma_unmap_page);
 
 int dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
 		unsigned long off, size_t sz, enum dma_data_direction dir)
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 749bb66..bc2d2d7 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -18,6 +18,7 @@
 #endif
 
 #include <asm/ptrace.h>
+#include <asm/domain.h>
 
 /*
  * Endian independent macros for shifting bytes within registers.
@@ -157,16 +158,24 @@
 #ifdef CONFIG_SMP
 #define ALT_SMP(instr...)					\
 9998:	instr
+/*
+ * Note: if you get assembler errors from ALT_UP() when building with
+ * CONFIG_THUMB2_KERNEL, you almost certainly need to use
+ * ALT_SMP( W(instr) ... )
+ */
 #define ALT_UP(instr...)					\
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
-	instr							;\
+9997:	instr							;\
+	.if . - 9997b != 4					;\
+		.error "ALT_UP() content must assemble to exactly 4 bytes";\
+	.endif							;\
 	.popsection
 #define ALT_UP_B(label)					\
 	.equ	up_b_offset, label - 9998b			;\
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
-	b	. + up_b_offset					;\
+	W(b)	. + up_b_offset					;\
 	.popsection
 #else
 #define ALT_SMP(instr...)
@@ -177,16 +186,24 @@
 /*
  * SMP data memory barrier
  */
-	.macro	smp_dmb
+	.macro	smp_dmb mode
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
+	.ifeqs "\mode","arm"
 	ALT_SMP(dmb)
+	.else
+	ALT_SMP(W(dmb))
+	.endif
 #elif __LINUX_ARM_ARCH__ == 6
 	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
 #else
 #error Incompatible SMP platform
 #endif
+	.ifeqs "\mode","arm"
 	ALT_UP(nop)
+	.else
+	ALT_UP(W(nop))
+	.endif
 #endif
 	.endm
 
@@ -206,12 +223,12 @@
  */
 #ifdef CONFIG_THUMB2_KERNEL
 
-	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort
+	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=T()
 9999:
 	.if	\inc == 1
-	\instr\cond\()bt \reg, [\ptr, #\off]
+	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
 	.elseif	\inc == 4
-	\instr\cond\()t \reg, [\ptr, #\off]
+	\instr\cond\()\t\().w \reg, [\ptr, #\off]
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -246,13 +263,13 @@
 
 #else	/* !CONFIG_THUMB2_KERNEL */
 
-	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort
+	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort, t=T()
 	.rept	\rept
 9999:
 	.if	\inc == 1
-	\instr\cond\()bt \reg, [\ptr], #\inc
+	\instr\cond\()b\()\t \reg, [\ptr], #\inc
 	.elseif	\inc == 4
-	\instr\cond\()t \reg, [\ptr], #\inc
+	\instr\cond\()\t \reg, [\ptr], #\inc
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index 9d61220..75fe66b 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -23,4 +23,6 @@
 #define ARCH_SLAB_MINALIGN 8
 #endif
 
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
 #endif
diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h
index b56c138..765d332 100644
--- a/arch/arm/include/asm/clkdev.h
+++ b/arch/arm/include/asm/clkdev.h
@@ -12,23 +12,13 @@
 #ifndef __ASM_CLKDEV_H
 #define __ASM_CLKDEV_H
 
-struct clk;
-struct device;
+#include <linux/slab.h>
 
-struct clk_lookup {
-	struct list_head	node;
-	const char		*dev_id;
-	const char		*con_id;
-	struct clk		*clk;
-};
+#include <mach/clkdev.h>
 
-struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
-	const char *dev_fmt, ...);
-
-void clkdev_add(struct clk_lookup *cl);
-void clkdev_drop(struct clk_lookup *cl);
-
-void clkdev_add_table(struct clk_lookup *, size_t);
-int clk_add_alias(const char *, const char *, char *, struct device *);
+static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
+{
+	return kzalloc(size, GFP_KERNEL);
+}
 
 #endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index c568da7..4fff837 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -5,24 +5,29 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
 
 #include <asm-generic/dma-coherent.h>
 #include <asm/memory.h>
 
+#ifdef __arch_page_to_dma
+#error Please update to __arch_pfn_to_dma
+#endif
+
 /*
- * page_to_dma/dma_to_virt/virt_to_dma are architecture private functions
- * used internally by the DMA-mapping API to provide DMA addresses. They
- * must not be used by drivers.
+ * dma_to_pfn/pfn_to_dma/dma_to_virt/virt_to_dma are architecture private
+ * functions used internally by the DMA-mapping API to provide DMA
+ * addresses. They must not be used by drivers.
  */
-#ifndef __arch_page_to_dma
-static inline dma_addr_t page_to_dma(struct device *dev, struct page *page)
+#ifndef __arch_pfn_to_dma
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-	return (dma_addr_t)__pfn_to_bus(page_to_pfn(page));
+	return (dma_addr_t)__pfn_to_bus(pfn);
 }
 
-static inline struct page *dma_to_page(struct device *dev, dma_addr_t addr)
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
-	return pfn_to_page(__bus_to_pfn(addr));
+	return __bus_to_pfn(addr);
 }
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
@@ -35,14 +40,14 @@
 	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
 }
 #else
-static inline dma_addr_t page_to_dma(struct device *dev, struct page *page)
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-	return __arch_page_to_dma(dev, page);
+	return __arch_pfn_to_dma(dev, pfn);
 }
 
-static inline struct page *dma_to_page(struct device *dev, dma_addr_t addr)
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
-	return __arch_dma_to_page(dev, addr);
+	return __arch_dma_to_pfn(dev, addr);
 }
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
@@ -293,13 +298,13 @@
 /*
  * The DMA API, implemented by dmabounce.c.  See below for descriptions.
  */
-extern dma_addr_t dma_map_single(struct device *, void *, size_t,
+extern dma_addr_t __dma_map_single(struct device *, void *, size_t,
 		enum dma_data_direction);
-extern void dma_unmap_single(struct device *, dma_addr_t, size_t,
+extern void __dma_unmap_single(struct device *, dma_addr_t, size_t,
 		enum dma_data_direction);
-extern dma_addr_t dma_map_page(struct device *, struct page *,
+extern dma_addr_t __dma_map_page(struct device *, struct page *,
 		unsigned long, size_t, enum dma_data_direction);
-extern void dma_unmap_page(struct device *, dma_addr_t, size_t,
+extern void __dma_unmap_page(struct device *, dma_addr_t, size_t,
 		enum dma_data_direction);
 
 /*
@@ -323,6 +328,34 @@
 }
 
 
+static inline dma_addr_t __dma_map_single(struct device *dev, void *cpu_addr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_single_cpu_to_dev(cpu_addr, size, dir);
+	return virt_to_dma(dev, cpu_addr);
+}
+
+static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir)
+{
+	__dma_page_cpu_to_dev(page, offset, size, dir);
+	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
+}
+
+static inline void __dma_unmap_single(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir);
+}
+
+static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
+		handle & ~PAGE_MASK, size, dir);
+}
+#endif /* CONFIG_DMABOUNCE */
+
 /**
  * dma_map_single - map a single buffer for streaming DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
@@ -340,11 +373,16 @@
 static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
 		size_t size, enum dma_data_direction dir)
 {
+	dma_addr_t addr;
+
 	BUG_ON(!valid_dma_direction(dir));
 
-	__dma_single_cpu_to_dev(cpu_addr, size, dir);
+	addr = __dma_map_single(dev, cpu_addr, size, dir);
+	debug_dma_map_page(dev, virt_to_page(cpu_addr),
+			(unsigned long)cpu_addr & ~PAGE_MASK, size,
+			dir, addr, true);
 
-	return virt_to_dma(dev, cpu_addr);
+	return addr;
 }
 
 /**
@@ -364,11 +402,14 @@
 static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir)
 {
+	dma_addr_t addr;
+
 	BUG_ON(!valid_dma_direction(dir));
 
-	__dma_page_cpu_to_dev(page, offset, size, dir);
+	addr = __dma_map_page(dev, page, offset, size, dir);
+	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
 
-	return page_to_dma(dev, page) + offset;
+	return addr;
 }
 
 /**
@@ -388,7 +429,8 @@
 static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
-	__dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir);
+	debug_dma_unmap_page(dev, handle, size, dir, true);
+	__dma_unmap_single(dev, handle, size, dir);
 }
 
 /**
@@ -408,10 +450,9 @@
 static inline void dma_unmap_page(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
-	__dma_page_dev_to_cpu(dma_to_page(dev, handle), handle & ~PAGE_MASK,
-		size, dir);
+	debug_dma_unmap_page(dev, handle, size, dir, false);
+	__dma_unmap_page(dev, handle, size, dir);
 }
-#endif /* CONFIG_DMABOUNCE */
 
 /**
  * dma_sync_single_range_for_cpu
@@ -437,6 +478,8 @@
 {
 	BUG_ON(!valid_dma_direction(dir));
 
+	debug_dma_sync_single_for_cpu(dev, handle + offset, size, dir);
+
 	if (!dmabounce_sync_for_cpu(dev, handle, offset, size, dir))
 		return;
 
@@ -449,6 +492,8 @@
 {
 	BUG_ON(!valid_dma_direction(dir));
 
+	debug_dma_sync_single_for_device(dev, handle + offset, size, dir);
+
 	if (!dmabounce_sync_for_device(dev, handle, offset, size, dir))
 		return;
 
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index cc7ef40..af18cea 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -45,13 +45,17 @@
  */
 #define DOMAIN_NOACCESS	0
 #define DOMAIN_CLIENT	1
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define DOMAIN_MANAGER	3
+#else
+#define DOMAIN_MANAGER	1
+#endif
 
 #define domain_val(dom,type)	((type) << (2*(dom)))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define set_domain(x)					\
 	do {						\
 	__asm__ __volatile__(				\
@@ -74,5 +78,28 @@
 #define modify_domain(dom,type)	do { } while (0)
 #endif
 
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions (inline assembly)
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)	#instr "t"
+#else
+#define T(instr)	#instr
 #endif
-#endif /* !__ASSEMBLY__ */
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)	instr ## t
+#else
+#define T(instr)	instr
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* !__ASM_PROC_DOMAIN_H */
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
new file mode 100644
index 0000000..ec0bbf7
--- /dev/null
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -0,0 +1,44 @@
+/*
+ * Interrupt handling.  Preserves r7, r8, r9
+ */
+	.macro	arch_irq_handler_default
+	get_irqnr_preamble r5, lr
+1:	get_irqnr_and_base r0, r6, r5, lr
+	movne	r1, sp
+	@
+	@ routine called with r0 = irq number, r1 = struct pt_regs *
+	@
+	adrne	lr, BSYM(1b)
+	bne	asm_do_IRQ
+
+#ifdef CONFIG_SMP
+	/*
+	 * XXX
+	 *
+	 * this macro assumes that irqstat (r6) and base (r5) are
+	 * preserved from get_irqnr_and_base above
+	 */
+	ALT_SMP(test_for_ipi r0, r6, r5, lr)
+	ALT_UP_B(9997f)
+	movne	r1, sp
+	adrne	lr, BSYM(1b)
+	bne	do_IPI
+
+#ifdef CONFIG_LOCAL_TIMERS
+	test_for_ltirq r0, r6, r5, lr
+	movne	r0, sp
+	adrne	lr, BSYM(1b)
+	bne	do_local_timer
+#endif
+#endif
+9997:
+	.endm
+
+	.macro	arch_irq_handler, symbol_name
+	.align	5
+	.global \symbol_name
+\symbol_name:
+	mov	r4, lr
+	arch_irq_handler_default
+	mov     pc, r4
+	.endm
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 540a044..b33fe70 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -13,12 +13,13 @@
 #include <linux/preempt.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1, [%2]\n"				\
+	"1:	" T(ldr) "	%1, [%2]\n"			\
 	"	" insn "\n"					\
-	"2:	strt	%0, [%2]\n"				\
+	"2:	" T(str) "	%0, [%2]\n"			\
 	"	mov	%0, #0\n"				\
 	"3:\n"							\
 	"	.pushsection __ex_table,\"a\"\n"		\
@@ -97,10 +98,10 @@
 	pagefault_disable();	/* implies preempt_disable() */
 
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	ldrt	%0, [%3]\n"
+	"1:	" T(ldr) "	%0, [%3]\n"
 	"	teq	%0, %1\n"
 	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	streqt	%2, [%3]\n"
+	"2:	" T(streq) "	%2, [%3]\n"
 	"3:\n"
 	"	.pushsection __ex_table,\"a\"\n"
 	"	.align	3\n"
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 6d7485a..89ad180 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,13 +5,31 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
+#define NR_IPI	5
+
 typedef struct {
 	unsigned int __softirq_pending;
+#ifdef CONFIG_LOCAL_TIMERS
 	unsigned int local_timer_irqs;
+#endif
+#ifdef CONFIG_SMP
+	unsigned int ipi_irqs[NR_IPI];
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
 
+#define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
+#define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
+
+#ifdef CONFIG_SMP
+u64 smp_irq_stat_cpu(unsigned int cpu);
+#else
+#define smp_irq_stat_cpu(cpu)	0
+#endif
+
+#define arch_irq_stat_cpu	smp_irq_stat_cpu
+
 #if NR_IRQS > 512
 #define HARDIRQ_BITS	10
 #elif NR_IRQS > 256
diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h
index 50c7e7c..6bc63ab 100644
--- a/arch/arm/include/asm/localtimer.h
+++ b/arch/arm/include/asm/localtimer.h
@@ -30,7 +30,6 @@
 #include "smp_twd.h"
 
 #define local_timer_ack()	twd_timer_ack()
-#define local_timer_stop()	twd_timer_stop()
 
 #else
 
@@ -40,11 +39,6 @@
  */
 int local_timer_ack(void);
 
-/*
- * Stop a local timer interrupt.
- */
-void local_timer_stop(void);
-
 #endif
 
 /*
@@ -52,12 +46,6 @@
  */
 void local_timer_setup(struct clock_event_device *);
 
-#else
-
-static inline void local_timer_stop(void)
-{
-}
-
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index d97a964..3a0893a 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -37,12 +37,21 @@
 					 struct meminfo *);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
+	void			(*init_early)(void);
 	void			(*init_irq)(void);
 	struct sys_timer	*timer;		/* system tick timer	*/
 	void			(*init_machine)(void);
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+	void			(*handle_irq)(struct pt_regs *);
+#endif
 };
 
 /*
+ * Current machine - only accessible during boot.
+ */
+extern struct machine_desc *machine_desc;
+
+/*
  * Set of macros to define architecture features.  This is built into
  * a table by the linker.
  */
diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h
index ce3eee9f..22ac140 100644
--- a/arch/arm/include/asm/mach/irq.h
+++ b/arch/arm/include/asm/mach/irq.h
@@ -17,10 +17,12 @@
 /*
  * This is internal.  Do not use it.
  */
-extern unsigned int arch_nr_irqs;
-extern void (*init_arch_irq)(void);
 extern void init_FIQ(void);
-extern int show_fiq_list(struct seq_file *, void *);
+extern int show_fiq_list(struct seq_file *, int);
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+extern void (*handle_arch_irq)(struct pt_regs *);
+#endif
 
 /*
  * This is for easy migration, but should be changed in the source
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index 35d408f..883f6be 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -43,7 +43,6 @@
 #endif
 };
 
-extern struct sys_timer *system_timer;
 extern void timer_tick(void);
 
 #endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 3d05190..96ed521 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -33,27 +33,23 @@
 /*
  * generate IPI list text
  */
-extern void show_ipi_list(struct seq_file *p);
+extern void show_ipi_list(struct seq_file *, int);
 
 /*
  * Called from assembly code, this handles an IPI.
  */
-asmlinkage void do_IPI(struct pt_regs *regs);
+asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
 
 /*
  * Setup the set of possible CPUs (via set_cpu_possible)
  */
 extern void smp_init_cpus(void);
 
-/*
- * Move global data into per-processor storage.
- */
-extern void smp_store_cpu_info(unsigned int cpuid);
 
 /*
  * Raise an IPI cross call on CPUs in callmap.
  */
-extern void smp_cross_call(const struct cpumask *mask);
+extern void smp_cross_call(const struct cpumask *mask, int ipi);
 
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
@@ -73,6 +69,11 @@
 extern void platform_secondary_init(unsigned int cpu);
 
 /*
+ * Initialize cpu_possible map, and enable coherency
+ */
+extern void platform_smp_prepare_cpus(unsigned int);
+
+/*
  * Initial data for bringing up a secondary CPU.
  */
 struct secondary_data {
@@ -97,6 +98,6 @@
 /*
  * show local interrupt info
  */
-extern void show_local_irqs(struct seq_file *);
+extern void show_local_irqs(struct seq_file *, int);
 
 #endif /* ifndef __ASM_ARM_SMP_H */
diff --git a/arch/arm/include/asm/smp_mpidr.h b/arch/arm/include/asm/smp_mpidr.h
deleted file mode 100644
index 6a9307d..0000000
--- a/arch/arm/include/asm/smp_mpidr.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef ASMARM_SMP_MIDR_H
-#define ASMARM_SMP_MIDR_H
-
-#define hard_smp_processor_id()						\
-	({								\
-		unsigned int cpunum;					\
-		__asm__("\n"						\
-			"1:	mrc p15, 0, %0, c0, c0, 5\n"		\
-			"	.pushsection \".alt.smp.init\", \"a\"\n"\
-			"	.long	1b\n"				\
-			"	mov	%0, #0\n"			\
-			"	.popsection"				\
-			: "=r" (cpunum));				\
-		cpunum &= 0x0F;						\
-	})
-
-#endif
diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h
index 634f357..fed9981 100644
--- a/arch/arm/include/asm/smp_twd.h
+++ b/arch/arm/include/asm/smp_twd.h
@@ -22,7 +22,6 @@
 
 extern void __iomem *twd_base;
 
-void twd_timer_stop(void);
 int twd_timer_ack(void);
 void twd_timer_setup(struct clock_event_device *);
 
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 3222ab8..97f6d60 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -124,6 +124,13 @@
 #define vectors_high()	(0)
 #endif
 
+#if __LINUX_ARM_ARCH__ >= 7 ||		\
+	(__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K))
+#define sev()	__asm__ __volatile__ ("sev" : : : "memory")
+#define wfe()	__asm__ __volatile__ ("wfe" : : : "memory")
+#define wfi()	__asm__ __volatile__ ("wfi" : : : "memory")
+#endif
+
 #if __LINUX_ARM_ARCH__ >= 7
 #define isb() __asm__ __volatile__ ("isb" : : : "memory")
 #define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 124475a..1b960d5 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -46,4 +46,6 @@
 extern void __init early_trap_init(void);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 
+extern void *vectors_page;
+
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 33e4a48..b293616 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -227,7 +227,7 @@
 
 #define __get_user_asm_byte(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrbt	%1,[%2]\n"				\
+	"1:	" T(ldrb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -263,7 +263,7 @@
 
 #define __get_user_asm_word(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1,[%2]\n"				\
+	"1:	" T(ldr) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -308,7 +308,7 @@
 
 #define __put_user_asm_byte(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strbt	%1,[%2]\n"				\
+	"1:	" T(strb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -341,7 +341,7 @@
 
 #define __put_user_asm_word(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strt	%1,[%2]\n"				\
+	"1:	" T(str) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -366,10 +366,10 @@
 
 #define __put_user_asm_dword(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
- ARM(	"1:	strt	" __reg_oper1 ", [%1], #4\n"	)	\
- ARM(	"2:	strt	" __reg_oper0 ", [%1]\n"	)	\
- THUMB(	"1:	strt	" __reg_oper1 ", [%1]\n"	)	\
- THUMB(	"2:	strt	" __reg_oper0 ", [%1, #4]\n"	)	\
+ ARM(	"1:	" T(str) "	" __reg_oper1 ", [%1], #4\n"	)	\
+ ARM(	"2:	" T(str) "	" __reg_oper0 ", [%1]\n"	)	\
+ THUMB(	"1:	" T(str) "	" __reg_oper1 ", [%1]\n"	)	\
+ THUMB(	"2:	" T(str) "	" __reg_oper0 ", [%1, #4]\n"	)	\
 	"3:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index fd3ec49..7c33e6f 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -30,7 +30,7 @@
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
-obj-$(CONFIG_SMP)		+= smp.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
@@ -44,6 +44,8 @@
 obj-$(CONFIG_ARM_UNWIND)	+= unwind.o
 obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(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
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index bb96a7d..27f6448 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -25,42 +25,22 @@
 #include <asm/tls.h>
 
 #include "entry-header.S"
+#include <asm/entry-macro-multi.S>
 
 /*
  * Interrupt handling.  Preserves r7, r8, r9
  */
 	.macro	irq_handler
-	get_irqnr_preamble r5, lr
-1:	get_irqnr_and_base r0, r6, r5, lr
-	movne	r1, sp
-	@
-	@ routine called with r0 = irq number, r1 = struct pt_regs *
-	@
-	adrne	lr, BSYM(1b)
-	bne	asm_do_IRQ
-
-#ifdef CONFIG_SMP
-	/*
-	 * XXX
-	 *
-	 * this macro assumes that irqstat (r6) and base (r5) are
-	 * preserved from get_irqnr_and_base above
-	 */
-	ALT_SMP(test_for_ipi r0, r6, r5, lr)
-	ALT_UP_B(9997f)
-	movne	r0, sp
-	adrne	lr, BSYM(1b)
-	bne	do_IPI
-
-#ifdef CONFIG_LOCAL_TIMERS
-	test_for_ltirq r0, r6, r5, lr
-	movne	r0, sp
-	adrne	lr, BSYM(1b)
-	bne	do_local_timer
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+	ldr	r5, =handle_arch_irq
+	mov	r0, sp
+	ldr	r5, [r5]
+	adr	lr, BSYM(9997f)
+	teq	r5, #0
+	movne	pc, r5
 #endif
+	arch_irq_handler_default
 9997:
-#endif
-
 	.endm
 
 #ifdef CONFIG_KPROBES
@@ -735,7 +715,7 @@
  THUMB(	stmia	ip!, {r4 - sl, fp}	   )	@ Store most regs on stack
  THUMB(	str	sp, [ip], #4		   )
  THUMB(	str	lr, [ip], #4		   )
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	set_tls	r3, r4, r5
@@ -744,7 +724,7 @@
 	ldr	r8, =__stack_chk_guard
 	ldr	r7, [r7, #TSK_STACK_CANARY]
 #endif
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 	mcr	p15, 0, r6, c3, c0, 0		@ Set domain register
 #endif
 	mov	r5, r0
@@ -842,7 +822,7 @@
  */
 
 __kuser_memory_barrier:				@ 0xffff0fa0
-	smp_dmb
+	smp_dmb	arm
 	usr_ret	lr
 
 	.align	5
@@ -959,7 +939,7 @@
 
 #else
 
-	smp_dmb
+	smp_dmb	arm
 1:	ldrex	r3, [r2]
 	subs	r3, r3, r0
 	strexeq	r3, r1, [r2]
@@ -1245,3 +1225,9 @@
 	.space	4
 cr_no_alignment:
 	.space	4
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+	.globl	handle_arch_irq
+handle_arch_irq:
+	.space	4
+#endif
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 6ff7919..e72dc34 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -45,6 +45,7 @@
 #include <asm/fiq.h>
 #include <asm/irq.h>
 #include <asm/system.h>
+#include <asm/traps.h>
 
 static unsigned long no_fiq_insn;
 
@@ -67,17 +68,22 @@
 
 static struct fiq_handler *current_fiq = &default_owner;
 
-int show_fiq_list(struct seq_file *p, void *v)
+int show_fiq_list(struct seq_file *p, int prec)
 {
 	if (current_fiq != &default_owner)
-		seq_printf(p, "FIQ:              %s\n", current_fiq->name);
+		seq_printf(p, "%*s:              %s\n", prec, "FIQ",
+			current_fiq->name);
 
 	return 0;
 }
 
 void set_fiq_handler(void *start, unsigned int length)
 {
+#if defined(CONFIG_CPU_USE_DOMAINS)
 	memcpy((void *)0xffff001c, start, length);
+#else
+	memcpy(vectors_page + 0x1c, start, length);
+#endif
 	flush_icache_range(0xffff001c, 0xffff001c + length);
 	if (!vectors_high())
 		flush_icache_range(0x1c, 0x1c + length);
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 6bd82d2..f17d9a0 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -91,6 +91,11 @@
 	movs	r8, r5				@ invalid machine (r5=0)?
  THUMB( it	eq )		@ force fixup-able long branch encoding
 	beq	__error_a			@ yes, error 'a'
+
+	/*
+	 * r1 = machine no, r2 = atags,
+	 * r8 = machinfo, r9 = cpuid, r10 = procinfo
+	 */
 	bl	__vet_atags
 #ifdef CONFIG_SMP_ON_UP
 	bl	__fixup_smp
@@ -387,19 +392,19 @@
 
 #ifdef CONFIG_SMP_ON_UP
 __fixup_smp:
-	mov	r7, #0x00070000
-	orr	r6, r7, #0xff000000	@ mask 0xff070000
-	orr	r7, r7, #0x41000000	@ val 0x41070000
-	and	r0, r9, r6
-	teq	r0, r7			@ ARM CPU and ARMv6/v7?
+	mov	r4, #0x00070000
+	orr	r3, r4, #0xff000000	@ mask 0xff070000
+	orr	r4, r4, #0x41000000	@ val 0x41070000
+	and	r0, r9, r3
+	teq	r0, r4			@ ARM CPU and ARMv6/v7?
 	bne	__fixup_smp_on_up	@ no, assume UP
 
-	orr	r6, r6, #0x0000ff00
-	orr	r6, r6, #0x000000f0	@ mask 0xff07fff0
-	orr	r7, r7, #0x0000b000
-	orr	r7, r7, #0x00000020	@ val 0x4107b020
-	and	r0, r9, r6
-	teq	r0, r7			@ ARM 11MPCore?
+	orr	r3, r3, #0x0000ff00
+	orr	r3, r3, #0x000000f0	@ mask 0xff07fff0
+	orr	r4, r4, #0x0000b000
+	orr	r4, r4, #0x00000020	@ val 0x4107b020
+	and	r0, r9, r3
+	teq	r0, r4			@ ARM 11MPCore?
 	moveq	pc, lr			@ yes, assume SMP
 
 	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
@@ -408,15 +413,22 @@
 
 __fixup_smp_on_up:
 	adr	r0, 1f
-	ldmia	r0, {r3, r6, r7}
+	ldmia	r0, {r3 - r5}
 	sub	r3, r0, r3
-	add	r6, r6, r3
-	add	r7, r7, r3
-2:	cmp	r6, r7
-	ldmia	r6!, {r0, r4}
-	strlo	r4, [r0, r3]
-	blo	2b
-	mov	pc, lr
+	add	r4, r4, r3
+	add	r5, r5, r3
+2:	cmp	r4, r5
+	movhs	pc, lr
+	ldmia	r4!, {r0, r6}
+ ARM(	str	r6, [r0, r3]	)
+ THUMB(	add	r0, r0, r3	)
+#ifdef __ARMEB__
+ THUMB(	mov	r6, r6, ror #16	)	@ Convert word order for big-endian.
+#endif
+ THUMB(	strh	r6, [r0], #2	)	@ For Thumb-2, store as two halfwords
+ THUMB(	mov	r6, r6, lsr #16	)	@ to be robust against misaligned r3.
+ THUMB(	strh	r6, [r0]	)
+	b	2b
 ENDPROC(__fixup_smp)
 
 	.align
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 6d61633..8135438 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -38,6 +38,7 @@
 #include <linux/ftrace.h>
 
 #include <asm/system.h>
+#include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 
@@ -48,8 +49,6 @@
 #define irq_finish(irq) do { } while (0)
 #endif
 
-unsigned int arch_nr_irqs;
-void (*init_arch_irq)(void) __initdata = NULL;
 unsigned long irq_err_count;
 
 int show_interrupts(struct seq_file *p, void *v)
@@ -58,11 +57,20 @@
 	struct irq_desc *desc;
 	struct irqaction * action;
 	unsigned long flags;
+	int prec, n;
+
+	for (prec = 3, n = 1000; prec < 10 && n <= nr_irqs; prec++)
+		n *= 10;
+
+#ifdef CONFIG_SMP
+	if (prec < 4)
+		prec = 4;
+#endif
 
 	if (i == 0) {
 		char cpuname[12];
 
-		seq_printf(p, "    ");
+		seq_printf(p, "%*s ", prec, "");
 		for_each_present_cpu(cpu) {
 			sprintf(cpuname, "CPU%d", cpu);
 			seq_printf(p, " %10s", cpuname);
@@ -77,7 +85,7 @@
 		if (!action)
 			goto unlock;
 
-		seq_printf(p, "%3d: ", i);
+		seq_printf(p, "%*d: ", prec, i);
 		for_each_present_cpu(cpu)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 		seq_printf(p, " %10s", desc->chip->name ? : "-");
@@ -90,13 +98,15 @@
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	} else if (i == nr_irqs) {
 #ifdef CONFIG_FIQ
-		show_fiq_list(p, v);
+		show_fiq_list(p, prec);
 #endif
 #ifdef CONFIG_SMP
-		show_ipi_list(p);
-		show_local_irqs(p);
+		show_ipi_list(p, prec);
 #endif
-		seq_printf(p, "Err: %10lu\n", irq_err_count);
+#ifdef CONFIG_LOCAL_TIMERS
+		show_local_irqs(p, prec);
+#endif
+		seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	}
 	return 0;
 }
@@ -156,13 +166,13 @@
 
 void __init init_IRQ(void)
 {
-	init_arch_irq();
+	machine_desc->init_irq();
 }
 
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {
-	nr_irqs = arch_nr_irqs ? arch_nr_irqs : NR_IRQS;
+	nr_irqs = machine_desc->nr_irqs ? machine_desc->nr_irqs : NR_IRQS;
 	return nr_irqs;
 }
 #endif
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 336f14e..3455ad3 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -75,9 +75,9 @@
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
-unsigned int __machine_arch_type;
+unsigned int __machine_arch_type __read_mostly;
 EXPORT_SYMBOL(__machine_arch_type);
-unsigned int cacheid;
+unsigned int cacheid __read_mostly;
 EXPORT_SYMBOL(cacheid);
 
 unsigned int __atags_pointer __initdata;
@@ -91,24 +91,24 @@
 unsigned int system_serial_high;
 EXPORT_SYMBOL(system_serial_high);
 
-unsigned int elf_hwcap;
+unsigned int elf_hwcap __read_mostly;
 EXPORT_SYMBOL(elf_hwcap);
 
 
 #ifdef MULTI_CPU
-struct processor processor;
+struct processor processor __read_mostly;
 #endif
 #ifdef MULTI_TLB
-struct cpu_tlb_fns cpu_tlb;
+struct cpu_tlb_fns cpu_tlb __read_mostly;
 #endif
 #ifdef MULTI_USER
-struct cpu_user_fns cpu_user;
+struct cpu_user_fns cpu_user __read_mostly;
 #endif
 #ifdef MULTI_CACHE
-struct cpu_cache_fns cpu_cache;
+struct cpu_cache_fns cpu_cache __read_mostly;
 #endif
 #ifdef CONFIG_OUTER_CACHE
-struct outer_cache_fns outer_cache;
+struct outer_cache_fns outer_cache __read_mostly;
 EXPORT_SYMBOL(outer_cache);
 #endif
 
@@ -126,6 +126,7 @@
 static const char *cpu_name;
 static const char *machine_name;
 static char __initdata cmd_line[COMMAND_LINE_SIZE];
+struct machine_desc *machine_desc __initdata;
 
 static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE;
 static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } };
@@ -708,13 +709,11 @@
 	{ 0, ATAG_NONE }
 };
 
-static void (*init_machine)(void) __initdata;
-
 static int __init customize_machine(void)
 {
 	/* customizes platform devices, or adds new ones */
-	if (init_machine)
-		init_machine();
+	if (machine_desc->init_machine)
+		machine_desc->init_machine();
 	return 0;
 }
 arch_initcall(customize_machine);
@@ -809,6 +808,7 @@
 
 	setup_processor();
 	mdesc = setup_machine(machine_arch_type);
+	machine_desc = mdesc;
 	machine_name = mdesc->name;
 
 	if (mdesc->soft_reboot)
@@ -868,13 +868,9 @@
 	cpu_init();
 	tcm_init();
 
-	/*
-	 * Set up various architecture-specific pointers
-	 */
-	arch_nr_irqs = mdesc->nr_irqs;
-	init_arch_irq = mdesc->init_irq;
-	system_timer = mdesc->timer;
-	init_machine = mdesc->init_machine;
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+	handle_arch_irq = mdesc->handle_irq;
+#endif
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
@@ -884,6 +880,9 @@
 #endif
 #endif
 	early_trap_init();
+
+	if (mdesc->init_early)
+		mdesc->init_early();
 }
 
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b6b78b2..5ec79b4 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -25,6 +25,7 @@
 #include <linux/irq.h>
 #include <linux/percpu.h>
 #include <linux/clockchips.h>
+#include <linux/completion.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
@@ -38,7 +39,6 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
-#include <asm/smp_plat.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -47,22 +47,8 @@
  */
 struct secondary_data secondary_data;
 
-/*
- * structures for inter-processor calls
- * - A collection of single bit ipi messages.
- */
-struct ipi_data {
-	spinlock_t lock;
-	unsigned long ipi_count;
-	unsigned long bits;
-};
-
-static DEFINE_PER_CPU(struct ipi_data, ipi_data) = {
-	.lock	= SPIN_LOCK_UNLOCKED,
-};
-
 enum ipi_msg_type {
-	IPI_TIMER,
+	IPI_TIMER = 2,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
@@ -178,8 +164,12 @@
 			barrier();
 		}
 
-		if (!cpu_online(cpu))
+		if (!cpu_online(cpu)) {
+			pr_crit("CPU%u: failed to come online\n", cpu);
 			ret = -EIO;
+		}
+	} else {
+		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
 	}
 
 	secondary_data.stack = NULL;
@@ -195,18 +185,12 @@
 
 	pgd_free(&init_mm, pgd);
 
-	if (ret) {
-		printk(KERN_CRIT "CPU%u: processor failed to boot\n", cpu);
-
-		/*
-		 * FIXME: We need to clean up the new idle thread. --rmk
-		 */
-	}
-
 	return ret;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static void percpu_timer_stop(void);
+
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
@@ -234,7 +218,7 @@
 	/*
 	 * Stop the local timer for this CPU.
 	 */
-	local_timer_stop();
+	percpu_timer_stop();
 
 	/*
 	 * Flush user cache and TLB mappings, and then remove this CPU
@@ -253,12 +237,20 @@
 	return 0;
 }
 
+static DECLARE_COMPLETION(cpu_died);
+
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
+	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+		pr_err("CPU%u: cpu didn't die\n", cpu);
+		return;
+	}
+	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
+
 	if (!platform_cpu_kill(cpu))
 		printk("CPU%u: unable to kill\n", cpu);
 }
@@ -275,12 +267,17 @@
 {
 	unsigned int cpu = smp_processor_id();
 
-	local_irq_disable();
 	idle_task_exit();
 
+	local_irq_disable();
+	mb();
+
+	/* Tell __cpu_die() that this CPU is now safe to dispose of */
+	complete(&cpu_died);
+
 	/*
 	 * actual CPU shutdown procedure is at least platform (if not
-	 * CPU) specific
+	 * CPU) specific.
 	 */
 	platform_cpu_die(cpu);
 
@@ -290,6 +287,7 @@
 	 * to be repeated to undo the effects of taking the CPU offline.
 	 */
 	__asm__("mov	sp, %0\n"
+	"	mov	fp, #0\n"
 	"	b	secondary_start_kernel"
 		:
 		: "r" (task_stack_page(current) + THREAD_SIZE - 8));
@@ -297,6 +295,17 @@
 #endif /* CONFIG_HOTPLUG_CPU */
 
 /*
+ * Called by both boot and secondaries to move global data into
+ * per-processor storage.
+ */
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
+
+	cpu_info->loops_per_jiffy = loops_per_jiffy;
+}
+
+/*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
  */
@@ -320,6 +329,7 @@
 
 	cpu_init();
 	preempt_disable();
+	trace_hardirqs_off();
 
 	/*
 	 * Give the platform a chance to do its own initialisation.
@@ -353,17 +363,6 @@
 	cpu_idle();
 }
 
-/*
- * Called by both boot and secondaries to move global data into
- * per-processor storage.
- */
-void __cpuinit smp_store_cpu_info(unsigned int cpuid)
-{
-	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
-
-	cpu_info->loops_per_jiffy = loops_per_jiffy;
-}
-
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	int cpu;
@@ -386,61 +385,80 @@
 	per_cpu(cpu_data, cpu).idle = current;
 }
 
-static void send_ipi_message(const struct cpumask *mask, enum ipi_msg_type msg)
+void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned long flags;
-	unsigned int cpu;
+	unsigned int ncores = num_possible_cpus();
 
-	local_irq_save(flags);
-
-	for_each_cpu(cpu, mask) {
-		struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
-
-		spin_lock(&ipi->lock);
-		ipi->bits |= 1 << msg;
-		spin_unlock(&ipi->lock);
-	}
+	smp_store_cpu_info(smp_processor_id());
 
 	/*
-	 * Call the platform specific cross-CPU call function.
+	 * are we trying to boot more cores than exist?
 	 */
-	smp_cross_call(mask);
+	if (max_cpus > ncores)
+		max_cpus = ncores;
 
-	local_irq_restore(flags);
+	if (max_cpus > 1) {
+		/*
+		 * Enable the local timer or broadcast device for the
+		 * boot CPU, but only if we have more than one CPU.
+		 */
+		percpu_timer_setup();
+
+		/*
+		 * Initialise the SCU if there are more than one CPU
+		 * and let them know where to start.
+		 */
+		platform_smp_prepare_cpus(max_cpus);
+	}
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	send_ipi_message(mask, IPI_CALL_FUNC);
+	smp_cross_call(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
-void show_ipi_list(struct seq_file *p)
+static const char *ipi_types[NR_IPI] = {
+#define S(x,s)	[x - IPI_TIMER] = s
+	S(IPI_TIMER, "Timer broadcast interrupts"),
+	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
+	S(IPI_CALL_FUNC, "Function call interrupts"),
+	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
+	S(IPI_CPU_STOP, "CPU stop interrupts"),
+};
+
+void show_ipi_list(struct seq_file *p, int prec)
 {
-	unsigned int cpu;
+	unsigned int cpu, i;
 
-	seq_puts(p, "IPI:");
+	for (i = 0; i < NR_IPI; i++) {
+		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
-	for_each_present_cpu(cpu)
-		seq_printf(p, " %10lu", per_cpu(ipi_data, cpu).ipi_count);
+		for_each_present_cpu(cpu)
+			seq_printf(p, "%10u ",
+				   __get_irq_stat(cpu, ipi_irqs[i]));
 
-	seq_putc(p, '\n');
+		seq_printf(p, " %s\n", ipi_types[i]);
+	}
 }
 
-void show_local_irqs(struct seq_file *p)
+u64 smp_irq_stat_cpu(unsigned int cpu)
 {
-	unsigned int cpu;
+	u64 sum = 0;
+	int i;
 
-	seq_printf(p, "LOC: ");
+	for (i = 0; i < NR_IPI; i++)
+		sum += __get_irq_stat(cpu, ipi_irqs[i]);
 
-	for_each_present_cpu(cpu)
-		seq_printf(p, "%10u ", irq_stat[cpu].local_timer_irqs);
+#ifdef CONFIG_LOCAL_TIMERS
+	sum += __get_irq_stat(cpu, local_timer_irqs);
+#endif
 
-	seq_putc(p, '\n');
+	return sum;
 }
 
 /*
@@ -463,18 +481,30 @@
 	int cpu = smp_processor_id();
 
 	if (local_timer_ack()) {
-		irq_stat[cpu].local_timer_irqs++;
+		__inc_irq_stat(cpu, local_timer_irqs);
 		ipi_timer();
 	}
 
 	set_irq_regs(old_regs);
 }
+
+void show_local_irqs(struct seq_file *p, int prec)
+{
+	unsigned int cpu;
+
+	seq_printf(p, "%*s: ", prec, "LOC");
+
+	for_each_present_cpu(cpu)
+		seq_printf(p, "%10u ", __get_irq_stat(cpu, local_timer_irqs));
+
+	seq_printf(p, " Local timer interrupts\n");
+}
 #endif
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 static void smp_timer_broadcast(const struct cpumask *mask)
 {
-	send_ipi_message(mask, IPI_TIMER);
+	smp_cross_call(mask, IPI_TIMER);
 }
 #else
 #define smp_timer_broadcast	NULL
@@ -511,6 +541,21 @@
 	local_timer_setup(evt);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The generic clock events code purposely does not stop the local timer
+ * on CPU_DEAD/CPU_DEAD_FROZEN hotplug events, so we have to do it
+ * manually here.
+ */
+static void percpu_timer_stop(void)
+{
+	unsigned int cpu = smp_processor_id();
+	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
+
+	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+}
+#endif
+
 static DEFINE_SPINLOCK(stop_lock);
 
 /*
@@ -537,85 +582,70 @@
 
 /*
  * Main handler for inter-processor interrupts
- *
- * For ARM, the ipimask now only identifies a single
- * category of IPI (Bit 1 IPIs have been replaced by a
- * different mechanism):
- *
- *  Bit 0 - Inter-processor function call
  */
-asmlinkage void __exception_irq_entry do_IPI(struct pt_regs *regs)
+asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
 {
 	unsigned int cpu = smp_processor_id();
-	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	ipi->ipi_count++;
+	if (ipinr >= IPI_TIMER && ipinr < IPI_TIMER + NR_IPI)
+		__inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_TIMER]);
 
-	for (;;) {
-		unsigned long msgs;
+	switch (ipinr) {
+	case IPI_TIMER:
+		ipi_timer();
+		break;
 
-		spin_lock(&ipi->lock);
-		msgs = ipi->bits;
-		ipi->bits = 0;
-		spin_unlock(&ipi->lock);
+	case IPI_RESCHEDULE:
+		/*
+		 * nothing more to do - eveything is
+		 * done on the interrupt return path
+		 */
+		break;
 
-		if (!msgs)
-			break;
+	case IPI_CALL_FUNC:
+		generic_smp_call_function_interrupt();
+		break;
 
-		do {
-			unsigned nextmsg;
+	case IPI_CALL_FUNC_SINGLE:
+		generic_smp_call_function_single_interrupt();
+		break;
 
-			nextmsg = msgs & -msgs;
-			msgs &= ~nextmsg;
-			nextmsg = ffz(~nextmsg);
+	case IPI_CPU_STOP:
+		ipi_cpu_stop(cpu);
+		break;
 
-			switch (nextmsg) {
-			case IPI_TIMER:
-				ipi_timer();
-				break;
-
-			case IPI_RESCHEDULE:
-				/*
-				 * nothing more to do - eveything is
-				 * done on the interrupt return path
-				 */
-				break;
-
-			case IPI_CALL_FUNC:
-				generic_smp_call_function_interrupt();
-				break;
-
-			case IPI_CALL_FUNC_SINGLE:
-				generic_smp_call_function_single_interrupt();
-				break;
-
-			case IPI_CPU_STOP:
-				ipi_cpu_stop(cpu);
-				break;
-
-			default:
-				printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
-				       cpu, nextmsg);
-				break;
-			}
-		} while (msgs);
+	default:
+		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
+		       cpu, ipinr);
+		break;
 	}
-
 	set_irq_regs(old_regs);
 }
 
 void smp_send_reschedule(int cpu)
 {
-	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
 void smp_send_stop(void)
 {
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-	if (!cpus_empty(mask))
-		send_ipi_message(&mask, IPI_CPU_STOP);
+	unsigned long timeout;
+
+	if (num_online_cpus() > 1) {
+		cpumask_t mask = cpu_online_map;
+		cpu_clear(smp_processor_id(), mask);
+
+		smp_cross_call(&mask, IPI_CPU_STOP);
+	}
+
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while (num_online_cpus() > 1 && timeout--)
+		udelay(1);
+
+	if (num_online_cpus() > 1)
+		pr_warning("SMP: failed to stop secondary CPUs\n");
 }
 
 /*
@@ -625,128 +655,3 @@
 {
 	return -EINVAL;
 }
-
-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();
-}
-
-/**********************************************************************/
-
-/*
- * TLB operations
- */
-struct tlb_args {
-	struct vm_area_struct *ta_vma;
-	unsigned long ta_start;
-	unsigned long ta_end;
-};
-
-static inline void ipi_flush_tlb_all(void *ignored)
-{
-	local_flush_tlb_all();
-}
-
-static inline void ipi_flush_tlb_mm(void *arg)
-{
-	struct mm_struct *mm = (struct mm_struct *)arg;
-
-	local_flush_tlb_mm(mm);
-}
-
-static inline void ipi_flush_tlb_page(void *arg)
-{
-	struct tlb_args *ta = (struct tlb_args *)arg;
-
-	local_flush_tlb_page(ta->ta_vma, ta->ta_start);
-}
-
-static inline void ipi_flush_tlb_kernel_page(void *arg)
-{
-	struct tlb_args *ta = (struct tlb_args *)arg;
-
-	local_flush_tlb_kernel_page(ta->ta_start);
-}
-
-static inline void ipi_flush_tlb_range(void *arg)
-{
-	struct tlb_args *ta = (struct tlb_args *)arg;
-
-	local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
-}
-
-static inline void ipi_flush_tlb_kernel_range(void *arg)
-{
-	struct tlb_args *ta = (struct tlb_args *)arg;
-
-	local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end);
-}
-
-void flush_tlb_all(void)
-{
-	if (tlb_ops_need_broadcast())
-		on_each_cpu(ipi_flush_tlb_all, NULL, 1);
-	else
-		local_flush_tlb_all();
-}
-
-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));
-	else
-		local_flush_tlb_mm(mm);
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
-{
-	if (tlb_ops_need_broadcast()) {
-		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));
-	} else
-		local_flush_tlb_page(vma, uaddr);
-}
-
-void flush_tlb_kernel_page(unsigned long kaddr)
-{
-	if (tlb_ops_need_broadcast()) {
-		struct tlb_args ta;
-		ta.ta_start = kaddr;
-		on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
-	} else
-		local_flush_tlb_kernel_page(kaddr);
-}
-
-void flush_tlb_range(struct vm_area_struct *vma,
-                     unsigned long start, unsigned long end)
-{
-	if (tlb_ops_need_broadcast()) {
-		struct tlb_args ta;
-		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));
-	} else
-		local_flush_tlb_range(vma, start, end);
-}
-
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
-{
-	if (tlb_ops_need_broadcast()) {
-		struct tlb_args ta;
-		ta.ta_start = start;
-		ta.ta_end = end;
-		on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
-	} else
-		local_flush_tlb_kernel_range(start, end);
-}
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
new file mode 100644
index 0000000..7dcb352
--- /dev/null
+++ b/arch/arm/kernel/smp_tlb.c
@@ -0,0 +1,139 @@
+/*
+ *  linux/arch/arm/kernel/smp_tlb.c
+ *
+ *  Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * 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/preempt.h>
+#include <linux/smp.h>
+
+#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();
+}
+
+/**********************************************************************/
+
+/*
+ * TLB operations
+ */
+struct tlb_args {
+	struct vm_area_struct *ta_vma;
+	unsigned long ta_start;
+	unsigned long ta_end;
+};
+
+static inline void ipi_flush_tlb_all(void *ignored)
+{
+	local_flush_tlb_all();
+}
+
+static inline void ipi_flush_tlb_mm(void *arg)
+{
+	struct mm_struct *mm = (struct mm_struct *)arg;
+
+	local_flush_tlb_mm(mm);
+}
+
+static inline void ipi_flush_tlb_page(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+}
+
+static inline void ipi_flush_tlb_kernel_page(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_kernel_page(ta->ta_start);
+}
+
+static inline void ipi_flush_tlb_range(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+}
+
+static inline void ipi_flush_tlb_kernel_range(void *arg)
+{
+	struct tlb_args *ta = (struct tlb_args *)arg;
+
+	local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end);
+}
+
+void flush_tlb_all(void)
+{
+	if (tlb_ops_need_broadcast())
+		on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+	else
+		local_flush_tlb_all();
+}
+
+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));
+	else
+		local_flush_tlb_mm(mm);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	if (tlb_ops_need_broadcast()) {
+		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));
+	} else
+		local_flush_tlb_page(vma, uaddr);
+}
+
+void flush_tlb_kernel_page(unsigned long kaddr)
+{
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_start = kaddr;
+		on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
+	} else
+		local_flush_tlb_kernel_page(kaddr);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma,
+                     unsigned long start, unsigned long end)
+{
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		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));
+	} else
+		local_flush_tlb_range(vma, start, end);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_start = start;
+		ta.ta_end = end;
+		on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
+	} else
+		local_flush_tlb_kernel_range(start, end);
+}
+
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 67f933e..dd79074 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -145,13 +145,3 @@
 
 	clockevents_register_device(clk);
 }
-
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * take a local timer down
- */
-void twd_timer_stop(void)
-{
-	__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
-}
-#endif
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
new file mode 100644
index 0000000..7a57609
--- /dev/null
+++ b/arch/arm/kernel/swp_emulate.c
@@ -0,0 +1,267 @@
+/*
+ *  linux/arch/arm/kernel/swp_emulate.c
+ *
+ *  Copyright (C) 2009 ARM Limited
+ *  __user_* functions adapted from include/asm/uaccess.h
+ *
+ * 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.
+ *
+ *  Implements emulation of the SWP/SWPB instructions using load-exclusive and
+ *  store-exclusive for processors that have them disabled (or future ones that
+ *  might not implement them).
+ *
+ *  Syntax of SWP{B} instruction: SWP{B}<c> <Rt>, <Rt2>, [<Rn>]
+ *  Where: Rt  = destination
+ *	   Rt2 = source
+ *	   Rn  = address
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+#include <linux/perf_event.h>
+
+#include <asm/traps.h>
+#include <asm/uaccess.h>
+
+/*
+ * Error-checking SWP macros implemented using ldrex{b}/strex{b}
+ */
+#define __user_swpX_asm(data, addr, res, temp, B)		\
+	__asm__ __volatile__(					\
+	"	mov		%2, %1\n"			\
+	"0:	ldrex"B"	%1, [%3]\n"			\
+	"1:	strex"B"	%0, %2, [%3]\n"			\
+	"	cmp		%0, #0\n"			\
+	"	movne		%0, %4\n"			\
+	"2:\n"							\
+	"	.section	 .fixup,\"ax\"\n"		\
+	"	.align		2\n"				\
+	"3:	mov		%0, %5\n"			\
+	"	b		2b\n"				\
+	"	.previous\n"					\
+	"	.section	 __ex_table,\"a\"\n"		\
+	"	.align		3\n"				\
+	"	.long		0b, 3b\n"			\
+	"	.long		1b, 3b\n"			\
+	"	.previous"					\
+	: "=&r" (res), "+r" (data), "=&r" (temp)		\
+	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "cc", "memory")
+
+#define __user_swp_asm(data, addr, res, temp) \
+	__user_swpX_asm(data, addr, res, temp, "")
+#define __user_swpb_asm(data, addr, res, temp) \
+	__user_swpX_asm(data, addr, res, temp, "b")
+
+/*
+ * Macros/defines for extracting register numbers from instruction.
+ */
+#define EXTRACT_REG_NUM(instruction, offset) \
+	(((instruction) & (0xf << (offset))) >> (offset))
+#define RN_OFFSET  16
+#define RT_OFFSET  12
+#define RT2_OFFSET  0
+/*
+ * Bit 22 of the instruction encoding distinguishes between
+ * the SWP and SWPB variants (bit set means SWPB).
+ */
+#define TYPE_SWPB (1 << 22)
+
+static unsigned long swpcounter;
+static unsigned long swpbcounter;
+static unsigned long abtcounter;
+static pid_t         previous_pid;
+
+#ifdef CONFIG_PROC_FS
+static int proc_read_status(char *page, char **start, off_t off, int count,
+			    int *eof, void *data)
+{
+	char *p = page;
+	int len;
+
+	p += sprintf(p, "Emulated SWP:\t\t%lu\n", swpcounter);
+	p += sprintf(p, "Emulated SWPB:\t\t%lu\n", swpbcounter);
+	p += sprintf(p, "Aborted SWP{B}:\t\t%lu\n", abtcounter);
+	if (previous_pid != 0)
+		p += sprintf(p, "Last process:\t\t%d\n", previous_pid);
+
+	len = (p - page) - off;
+	if (len < 0)
+		len = 0;
+
+	*eof = (len <= count) ? 1 : 0;
+	*start = page + off;
+
+	return len;
+}
+#endif
+
+/*
+ * Set up process info to signal segmentation fault - called on access error.
+ */
+static void set_segfault(struct pt_regs *regs, unsigned long addr)
+{
+	siginfo_t info;
+
+	if (find_vma(current->mm, addr) == NULL)
+		info.si_code = SEGV_MAPERR;
+	else
+		info.si_code = SEGV_ACCERR;
+
+	info.si_signo = SIGSEGV;
+	info.si_errno = 0;
+	info.si_addr  = (void *) instruction_pointer(regs);
+
+	pr_debug("SWP{B} emulation: access caused memory abort!\n");
+	arm_notify_die("Illegal memory access", regs, &info, 0, 0);
+
+	abtcounter++;
+}
+
+static int emulate_swpX(unsigned int address, unsigned int *data,
+			unsigned int type)
+{
+	unsigned int res = 0;
+
+	if ((type != TYPE_SWPB) && (address & 0x3)) {
+		/* SWP to unaligned address not permitted */
+		pr_debug("SWP instruction on unaligned pointer!\n");
+		return -EFAULT;
+	}
+
+	while (1) {
+		unsigned long temp;
+
+		/*
+		 * Barrier required between accessing protected resource and
+		 * releasing a lock for it. Legacy code might not have done
+		 * this, and we cannot determine that this is not the case
+		 * being emulated, so insert always.
+		 */
+		smp_mb();
+
+		if (type == TYPE_SWPB)
+			__user_swpb_asm(*data, address, res, temp);
+		else
+			__user_swp_asm(*data, address, res, temp);
+
+		if (likely(res != -EAGAIN) || signal_pending(current))
+			break;
+
+		cond_resched();
+	}
+
+	if (res == 0) {
+		/*
+		 * Barrier also required between aquiring a lock for a
+		 * protected resource and accessing the resource. Inserted for
+		 * same reason as above.
+		 */
+		smp_mb();
+
+		if (type == TYPE_SWPB)
+			swpbcounter++;
+		else
+			swpcounter++;
+	}
+
+	return res;
+}
+
+/*
+ * swp_handler logs the id of calling process, dissects the instruction, sanity
+ * checks the memory location, calls emulate_swpX for the actual operation and
+ * deals with fixup/error handling before returning
+ */
+static int swp_handler(struct pt_regs *regs, unsigned int instr)
+{
+	unsigned int address, destreg, data, type;
+	unsigned int res = 0;
+
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, regs->ARM_pc);
+
+	if (current->pid != previous_pid) {
+		pr_debug("\"%s\" (%ld) uses deprecated SWP{B} instruction\n",
+			 current->comm, (unsigned long)current->pid);
+		previous_pid = current->pid;
+	}
+
+	address = regs->uregs[EXTRACT_REG_NUM(instr, RN_OFFSET)];
+	data	= regs->uregs[EXTRACT_REG_NUM(instr, RT2_OFFSET)];
+	destreg = EXTRACT_REG_NUM(instr, RT_OFFSET);
+
+	type = instr & TYPE_SWPB;
+
+	pr_debug("addr in r%d->0x%08x, dest is r%d, source in r%d->0x%08x)\n",
+		 EXTRACT_REG_NUM(instr, RN_OFFSET), address,
+		 destreg, EXTRACT_REG_NUM(instr, RT2_OFFSET), data);
+
+	/* Check access in reasonable access range for both SWP and SWPB */
+	if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+		pr_debug("SWP{B} emulation: access to %p not allowed!\n",
+			 (void *)address);
+		res = -EFAULT;
+	} else {
+		res = emulate_swpX(address, &data, type);
+	}
+
+	if (res == 0) {
+		/*
+		 * On successful emulation, revert the adjustment to the PC
+		 * made in kernel/traps.c in order to resume execution at the
+		 * instruction following the SWP{B}.
+		 */
+		regs->ARM_pc += 4;
+		regs->uregs[destreg] = data;
+	} else if (res == -EFAULT) {
+		/*
+		 * Memory errors do not mean emulation failed.
+		 * Set up signal info to return SEGV, then return OK
+		 */
+		set_segfault(regs, address);
+	}
+
+	return 0;
+}
+
+/*
+ * Only emulate SWP/SWPB executed in ARM state/User mode.
+ * The kernel must be SWP free and SWP{B} does not exist in Thumb/ThumbEE.
+ */
+static struct undef_hook swp_hook = {
+	.instr_mask = 0x0fb00ff0,
+	.instr_val  = 0x01000090,
+	.cpsr_mask  = MODE_MASK | PSR_T_BIT | PSR_J_BIT,
+	.cpsr_val   = USR_MODE,
+	.fn	    = swp_handler
+};
+
+/*
+ * Register handler and create status file in /proc/cpu
+ * Invoked as late_initcall, since not needed before init spawned.
+ */
+static int __init swp_emulation_init(void)
+{
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry *res;
+
+	res = create_proc_entry("cpu/swp_emulation", S_IRUGO, NULL);
+
+	if (!res)
+		return -ENOMEM;
+
+	res->read_proc = proc_read_status;
+#endif /* CONFIG_PROC_FS */
+
+	printk(KERN_NOTICE "Registering SWP/SWPB emulation handler\n");
+	register_undef_hook(&swp_hook);
+
+	return 0;
+}
+
+late_initcall(swp_emulation_init);
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 38c261f..f1e2eb1 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -30,12 +30,13 @@
 #include <asm/leds.h>
 #include <asm/thread_info.h>
 #include <asm/stacktrace.h>
+#include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 
 /*
  * Our system timer.
  */
-struct sys_timer *system_timer;
+static struct sys_timer *system_timer;
 
 #if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE)
 /* this needs a better home */
@@ -160,6 +161,7 @@
 
 void __init time_init(void)
 {
+	system_timer = machine_desc->timer;
 	system_timer->init();
 }
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 446aee9..e02f4f7 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -37,6 +37,8 @@
 
 static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
 
+void *vectors_page;
+
 #ifdef CONFIG_DEBUG_USER
 unsigned int user_debug;
 
@@ -756,7 +758,11 @@
 
 void __init early_trap_init(void)
 {
+#if defined(CONFIG_CPU_USE_DOMAINS)
 	unsigned long vectors = CONFIG_VECTORS_BASE;
+#else
+	unsigned long vectors = (unsigned long)vectors_page;
+#endif
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	extern char __kuser_helper_start[], __kuser_helper_end[];
@@ -780,10 +786,10 @@
 	 * Copy signal return handlers into the vector page, and
 	 * set sigreturn to be a pointer to these.
 	 */
-	memcpy((void *)KERN_SIGRETURN_CODE, sigreturn_codes,
-	       sizeof(sigreturn_codes));
-	memcpy((void *)KERN_RESTART_CODE, syscall_restart_code,
-	       sizeof(syscall_restart_code));
+	memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE),
+	       sigreturn_codes, sizeof(sigreturn_codes));
+	memcpy((void *)(vectors + KERN_RESTART_CODE - CONFIG_VECTORS_BASE),
+	       syscall_restart_code, sizeof(syscall_restart_code));
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE);
 	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 897c1a8..86b66f3 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -168,6 +168,7 @@
 
 		NOSAVE_DATA
 		CACHELINE_ALIGNED_DATA(32)
+		READ_MOSTLY_DATA(32)
 
 		/*
 		 * The exception fixup table (might need resorting at runtime)
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index b1631a7..1b049cd 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -28,20 +28,21 @@
  */
 #include <linux/linkage.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 ENTRY(__get_user_1)
-1:	ldrbt	r2, [r0]
+1:	T(ldrb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
 #ifdef CONFIG_THUMB2_KERNEL
-2:	ldrbt	r2, [r0]
-3:	ldrbt	r3, [r0, #1]
+2:	T(ldrb)	r2, [r0]
+3:	T(ldrb)	r3, [r0, #1]
 #else
-2:	ldrbt	r2, [r0], #1
-3:	ldrbt	r3, [r0]
+2:	T(ldrb)	r2, [r0], #1
+3:	T(ldrb)	r3, [r0]
 #endif
 #ifndef __ARMEB__
 	orr	r2, r2, r3, lsl #8
@@ -53,7 +54,7 @@
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
-4:	ldrt	r2, [r0]
+4:	T(ldr)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_4)
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 5a01a23..c023fc1 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -28,9 +28,10 @@
  */
 #include <linux/linkage.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 ENTRY(__put_user_1)
-1:	strbt	r2, [r0]
+1:	T(strb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_1)
@@ -39,19 +40,19 @@
 	mov	ip, r2, lsr #8
 #ifdef CONFIG_THUMB2_KERNEL
 #ifndef __ARMEB__
-2:	strbt	r2, [r0]
-3:	strbt	ip, [r0, #1]
+2:	T(strb)	r2, [r0]
+3:	T(strb)	ip, [r0, #1]
 #else
-2:	strbt	ip, [r0]
-3:	strbt	r2, [r0, #1]
+2:	T(strb)	ip, [r0]
+3:	T(strb)	r2, [r0, #1]
 #endif
 #else	/* !CONFIG_THUMB2_KERNEL */
 #ifndef __ARMEB__
-2:	strbt	r2, [r0], #1
-3:	strbt	ip, [r0]
+2:	T(strb)	r2, [r0], #1
+3:	T(strb)	ip, [r0]
 #else
-2:	strbt	ip, [r0], #1
-3:	strbt	r2, [r0]
+2:	T(strb)	ip, [r0], #1
+3:	T(strb)	r2, [r0]
 #endif
 #endif	/* CONFIG_THUMB2_KERNEL */
 	mov	r0, #0
@@ -59,18 +60,18 @@
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
-4:	strt	r2, [r0]
+4:	T(str)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
 #ifdef CONFIG_THUMB2_KERNEL
-5:	strt	r2, [r0]
-6:	strt	r3, [r0, #4]
+5:	T(str)	r2, [r0]
+6:	T(str)	r3, [r0, #4]
 #else
-5:	strt	r2, [r0], #4
-6:	strt	r3, [r0]
+5:	T(str)	r2, [r0], #4
+6:	T(str)	r3, [r0]
 #endif
 	mov	r0, #0
 	mov	pc, lr
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index fee9f6f..d0ece2a 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -14,6 +14,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 		.text
 
@@ -31,11 +32,11 @@
 		rsb	ip, ip, #4
 		cmp	ip, #2
 		ldrb	r3, [r1], #1
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #1
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		sub	r2, r2, ip
 		b	.Lc2u_dest_aligned
 
@@ -58,7 +59,7 @@
 		addmi	ip, r2, #4
 		bmi	.Lc2u_0nowords
 		ldr	r3, [r1], #4
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -87,18 +88,18 @@
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
 		ldrne	r3, [r1], #4
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_0fupi
 .Lc2u_0nowords:	teq	ip, #0
 		beq	.Lc2u_finished
 .Lc2u_nowords:	cmp	ip, #2
 		ldrb	r3, [r1], #1
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #1
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_not_enough:
@@ -119,7 +120,7 @@
 		mov	r3, r7, pull #8
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #24
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -154,18 +155,18 @@
 		movne	r3, r7, pull #8
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #24
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_1fupi
 .Lc2u_1nowords:	mov	r3, r7, get_byte_1
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		movge	r3, r7, get_byte_2
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		movgt	r3, r7, get_byte_3
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_2fupi:	subs	r2, r2, #4
@@ -174,7 +175,7 @@
 		mov	r3, r7, pull #16
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #16
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -209,18 +210,18 @@
 		movne	r3, r7, pull #16
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #16
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_2fupi
 .Lc2u_2nowords:	mov	r3, r7, get_byte_2
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		movge	r3, r7, get_byte_3
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_3fupi:	subs	r2, r2, #4
@@ -229,7 +230,7 @@
 		mov	r3, r7, pull #24
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #8
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -264,18 +265,18 @@
 		movne	r3, r7, pull #24
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #8
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_3fupi
 .Lc2u_3nowords:	mov	r3, r7, get_byte_3
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 ENDPROC(__copy_to_user)
 
@@ -294,11 +295,11 @@
 .Lcfu_dest_not_aligned:
 		rsb	ip, ip, #4
 		cmp	ip, #2
-USER(		ldrbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrb)	r3, [r1], #1)			@ May fault
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		sub	r2, r2, ip
 		b	.Lcfu_dest_aligned
@@ -321,7 +322,7 @@
 .Lcfu_0fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_0nowords
-USER(		ldrt	r3, [r1], #4)
+USER(		T(ldr)	r3, [r1], #4)
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
 		rsb	ip, ip, #0
@@ -350,18 +351,18 @@
 		ldmneia	r1!, {r3 - r4}			@ Shouldnt fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		ldrnet	r3, [r1], #4			@ Shouldnt fault
+		T(ldrne) r3, [r1], #4			@ Shouldnt fault
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_0fupi
 .Lcfu_0nowords:	teq	ip, #0
 		beq	.Lcfu_finished
 .Lcfu_nowords:	cmp	ip, #2
-USER(		ldrbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrb)	r3, [r1], #1)			@ May fault
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 
@@ -374,7 +375,7 @@
 
 .Lcfu_src_not_aligned:
 		bic	r1, r1, #3
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		cmp	ip, #2
 		bgt	.Lcfu_3fupi
 		beq	.Lcfu_2fupi
@@ -382,7 +383,7 @@
 		addmi	ip, r2, #4
 		bmi	.Lcfu_1nowords
 		mov	r3, r7, pull #8
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #24
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -417,7 +418,7 @@
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #8
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #24
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -437,7 +438,7 @@
 		addmi	ip, r2, #4
 		bmi	.Lcfu_2nowords
 		mov	r3, r7, pull #16
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #16
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -473,7 +474,7 @@
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #16
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #16
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -485,7 +486,7 @@
 		strb	r3, [r0], #1
 		movge	r3, r7, get_byte_3
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #0)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #0)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 
@@ -493,7 +494,7 @@
 		addmi	ip, r2, #4
 		bmi	.Lcfu_3nowords
 		mov	r3, r7, pull #24
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #8
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -528,7 +529,7 @@
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #24
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #8
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -538,9 +539,9 @@
 		beq	.Lcfu_finished
 		cmp	ip, #2
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 ENDPROC(__copy_from_user)
diff --git a/arch/arm/mach-bcmring/clock.c b/arch/arm/mach-bcmring/clock.c
index 14bafc3..ad237a4 100644
--- a/arch/arm/mach-bcmring/clock.c
+++ b/arch/arm/mach-bcmring/clock.c
@@ -21,13 +21,12 @@
 #include <linux/string.h>
 #include <linux/clk.h>
 #include <linux/spinlock.h>
+#include <linux/clkdev.h>
 #include <mach/csp/hw_cfg.h>
 #include <mach/csp/chipcHw_def.h>
 #include <mach/csp/chipcHw_reg.h>
 #include <mach/csp/chipcHw_inline.h>
 
-#include <asm/clkdev.h>
-
 #include "clock.h"
 
 #define clk_is_primary(x)       ((x)->type & CLK_TYPE_PRIMARY)
diff --git a/arch/arm/mach-bcmring/core.c b/arch/arm/mach-bcmring/core.c
index b91b1b0..8fc2035 100644
--- a/arch/arm/mach-bcmring/core.c
+++ b/arch/arm/mach-bcmring/core.c
@@ -30,10 +30,10 @@
 #include <linux/amba/bus.h>
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/clkdev.h>
 
 #include <mach/csp/mm_addr.h>
 #include <mach/hardware.h>
-#include <asm/clkdev.h>
 #include <linux/io.h>
 #include <asm/irq.h>
 #include <asm/hardware/arm_timer.h>
diff --git a/arch/arm/mach-cns3xxx/Kconfig b/arch/arm/mach-cns3xxx/Kconfig
index 9ebfcc4..29b13f2 100644
--- a/arch/arm/mach-cns3xxx/Kconfig
+++ b/arch/arm/mach-cns3xxx/Kconfig
@@ -3,6 +3,7 @@
 
 config MACH_CNS3420VB
 	bool "Support for CNS3420 Validation Board"
+	select MIGHT_HAVE_PCI
 	help
 	  Include support for the Cavium Networks CNS3420 MPCore Platform
 	  Baseboard.
diff --git a/arch/arm/mach-davinci/clock.h b/arch/arm/mach-davinci/clock.h
index 1109998..0dd2203 100644
--- a/arch/arm/mach-davinci/clock.h
+++ b/arch/arm/mach-davinci/clock.h
@@ -68,7 +68,7 @@
 #ifndef __ASSEMBLER__
 
 #include <linux/list.h>
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #define PLLSTAT_GOSTAT	BIT(0)
 #define PLLCMD_GOSET	BIT(0)
diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c
index ef06c66..ca4de71 100644
--- a/arch/arm/mach-ep93xx/clock.c
+++ b/arch/arm/mach-ep93xx/clock.c
@@ -19,10 +19,10 @@
 #include <linux/string.h>
 #include <linux/io.h>
 #include <linux/spinlock.h>
+#include <linux/clkdev.h>
 
 #include <mach/hardware.h>
 
-#include <asm/clkdev.h>
 #include <asm/div64.h>
 
 
diff --git a/arch/arm/mach-imx/clock-imx1.c b/arch/arm/mach-imx/clock-imx1.c
index daca30b..3938a56 100644
--- a/arch/arm/mach-imx/clock-imx1.c
+++ b/arch/arm/mach-imx/clock-imx1.c
@@ -22,8 +22,7 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
-
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #include <mach/clock.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-imx/clock-imx21.c b/arch/arm/mach-imx/clock-imx21.c
index cf15ea5..d705655 100644
--- a/arch/arm/mach-imx/clock-imx21.c
+++ b/arch/arm/mach-imx/clock-imx21.c
@@ -21,11 +21,11 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/clkdev.h>
 
 #include <mach/clock.h>
 #include <mach/hardware.h>
 #include <mach/common.h>
-#include <asm/clkdev.h>
 #include <asm/div64.h>
 
 #define IO_ADDR_CCM(off)	(MX21_IO_ADDRESS(MX21_CCM_BASE_ADDR + (off)))
diff --git a/arch/arm/mach-imx/clock-imx27.c b/arch/arm/mach-imx/clock-imx27.c
index 98a25ba..ca1017b 100644
--- a/arch/arm/mach-imx/clock-imx27.c
+++ b/arch/arm/mach-imx/clock-imx27.c
@@ -21,8 +21,8 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <asm/div64.h>
 
 #include <mach/clock.h>
diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig
index 27db275..769b0f1 100644
--- a/arch/arm/mach-integrator/Kconfig
+++ b/arch/arm/mach-integrator/Kconfig
@@ -4,6 +4,7 @@
 
 config ARCH_INTEGRATOR_AP
 	bool "Support Integrator/AP and Integrator/PP2 platforms"
+	select MIGHT_HAVE_PCI
 	help
 	  Include support for the ARM(R) Integrator/AP and
 	  Integrator/PP2 platforms.
diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c
index 8f4fb6d..b8e884b 100644
--- a/arch/arm/mach-integrator/core.c
+++ b/arch/arm/mach-integrator/core.c
@@ -21,9 +21,8 @@
 #include <linux/amba/bus.h>
 #include <linux/amba/serial.h>
 #include <linux/io.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
-#include <mach/clkdev.h>
 #include <mach/hardware.h>
 #include <mach/platform.h>
 #include <asm/irq.h>
diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c
index fd684bf..5db574f 100644
--- a/arch/arm/mach-integrator/impd1.c
+++ b/arch/arm/mach-integrator/impd1.c
@@ -22,9 +22,8 @@
 #include <linux/amba/clcd.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
-#include <mach/clkdev.h>
 #include <asm/hardware/icst.h>
 #include <mach/lm.h>
 #include <mach/impd1.h>
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 1713ecf..85e48a5 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -21,9 +21,8 @@
 #include <linux/amba/mmci.h>
 #include <linux/io.h>
 #include <linux/gfp.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
-#include <mach/clkdev.h>
 #include <mach/hardware.h>
 #include <mach/platform.h>
 #include <asm/irq.h>
diff --git a/arch/arm/mach-iop13xx/include/mach/memory.h b/arch/arm/mach-iop13xx/include/mach/memory.h
index 7415e43..3ad4553 100644
--- a/arch/arm/mach-iop13xx/include/mach/memory.h
+++ b/arch/arm/mach-iop13xx/include/mach/memory.h
@@ -58,13 +58,13 @@
 		__dma;							\
 	})
 
-#define __arch_page_to_dma(dev, page)					\
+#define __arch_pfn_to_dma(dev, pfn)					\
 	({								\
 		/* __is_lbus_virt() can never be true for RAM pages */	\
-		(dma_addr_t)page_to_phys(page);				\
+		(dma_addr_t)__pfn_to_phys(pfn);				\
 	})
 
-#define __arch_dma_to_page(dev, addr)	phys_to_page(addr)
+#define __arch_dma_to_pfn(dev, addr)	__phys_to_pfn(addr)
 
 #endif /* CONFIG_ARCH_IOP13XX */
 #endif /* !ASSEMBLY */
diff --git a/arch/arm/mach-ks8695/Kconfig b/arch/arm/mach-ks8695/Kconfig
index fe0c82e..f5c39a8 100644
--- a/arch/arm/mach-ks8695/Kconfig
+++ b/arch/arm/mach-ks8695/Kconfig
@@ -4,6 +4,7 @@
 
 config MACH_KS8695
 	bool "KS8695 development board"
+	select MIGHT_HAVE_PCI
 	help
 	  Say 'Y' here if you want your kernel to run on the original
 	  Kendin-Micrel KS8695 development board.
diff --git a/arch/arm/mach-ks8695/include/mach/memory.h b/arch/arm/mach-ks8695/include/mach/memory.h
index ffa19aa..bace9a6 100644
--- a/arch/arm/mach-ks8695/include/mach/memory.h
+++ b/arch/arm/mach-ks8695/include/mach/memory.h
@@ -35,17 +35,17 @@
 					__phys_to_virt(x) : __bus_to_virt(x)); })
 #define __arch_virt_to_dma(dev, x)	({ is_lbus_device(dev) ? \
 					(dma_addr_t)__virt_to_phys(x) : (dma_addr_t)__virt_to_bus(x); })
-#define __arch_page_to_dma(dev, x)	\
-	({ dma_addr_t __dma = page_to_phys(page); \
+#define __arch_pfn_to_dma(dev, pfn)	\
+	({ dma_addr_t __dma = __pfn_to_phys(pfn); \
 	   if (!is_lbus_device(dev)) \
 		__dma = __dma - PHYS_OFFSET + KS8695_PCIMEM_PA; \
 	   __dma; })
 
-#define __arch_dma_to_page(dev, x)	\
+#define __arch_dma_to_pfn(dev, x)	\
 	({ dma_addr_t __dma = x;				\
 	   if (!is_lbus_device(dev))				\
 		__dma += PHYS_OFFSET - KS8695_PCIMEM_PA;	\
-	   phys_to_page(__dma);					\
+	   __phys_to_pfn(__dma);				\
 	})
 
 #endif
diff --git a/arch/arm/mach-lpc32xx/clock.c b/arch/arm/mach-lpc32xx/clock.c
index 32d6379..da0e649 100644
--- a/arch/arm/mach-lpc32xx/clock.c
+++ b/arch/arm/mach-lpc32xx/clock.c
@@ -90,10 +90,9 @@
 #include <linux/clk.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/clcd.h>
+#include <linux/clkdev.h>
 
 #include <mach/hardware.h>
-#include <asm/clkdev.h>
-#include <mach/clkdev.h>
 #include <mach/platform.h>
 #include "clock.h"
 #include "common.h"
diff --git a/arch/arm/mach-mmp/clock.h b/arch/arm/mach-mmp/clock.h
index 016ae94..9b027d7 100644
--- a/arch/arm/mach-mmp/clock.h
+++ b/arch/arm/mach-mmp/clock.h
@@ -6,7 +6,7 @@
  *  published by the Free Software Foundation.
  */
 
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 struct clkops {
 	void			(*enable)(struct clk *);
diff --git a/arch/arm/mach-msm/include/mach/smp.h b/arch/arm/mach-msm/include/mach/smp.h
index 3ff7bf5..a95f7b9 100644
--- a/arch/arm/mach-msm/include/mach/smp.h
+++ b/arch/arm/mach-msm/include/mach/smp.h
@@ -31,9 +31,9 @@
 
 #include <asm/hardware/gic.h>
 
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-mx25/clock.c b/arch/arm/mach-mx25/clock.c
index 9e4a557..00dcb08 100644
--- a/arch/arm/mach-mx25/clock.c
+++ b/arch/arm/mach-mx25/clock.c
@@ -21,8 +21,7 @@
 #include <linux/list.h>
 #include <linux/clk.h>
 #include <linux/io.h>
-
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #include <mach/clock.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-mx3/clock-imx31.c b/arch/arm/mach-mx3/clock-imx31.c
index 109e98f..1cd8b40 100644
--- a/arch/arm/mach-mx3/clock-imx31.c
+++ b/arch/arm/mach-mx3/clock-imx31.c
@@ -23,8 +23,8 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <asm/div64.h>
 
 #include <mach/clock.h>
diff --git a/arch/arm/mach-mx3/clock-imx35.c b/arch/arm/mach-mx3/clock-imx35.c
index 61e4a31..819dd80 100644
--- a/arch/arm/mach-mx3/clock-imx35.c
+++ b/arch/arm/mach-mx3/clock-imx35.c
@@ -21,8 +21,7 @@
 #include <linux/list.h>
 #include <linux/clk.h>
 #include <linux/io.h>
-
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #include <mach/clock.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-mx5/clock-mx51.c b/arch/arm/mach-mx5/clock-mx51.c
index 8ac36d8..5975edb 100644
--- a/arch/arm/mach-mx5/clock-mx51.c
+++ b/arch/arm/mach-mx5/clock-mx51.c
@@ -14,8 +14,8 @@
 #include <linux/delay.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <asm/div64.h>
 
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-mxc91231/clock.c b/arch/arm/mach-mxc91231/clock.c
index 5c85075..9fab505 100644
--- a/arch/arm/mach-mxc91231/clock.c
+++ b/arch/arm/mach-mxc91231/clock.c
@@ -2,12 +2,12 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/clkdev.h>
 
 #include <mach/clock.h>
 #include <mach/hardware.h>
 #include <mach/common.h>
 
-#include <asm/clkdev.h>
 #include <asm/bug.h>
 #include <asm/div64.h>
 
diff --git a/arch/arm/mach-nomadik/clock.c b/arch/arm/mach-nomadik/clock.c
index 89f793a..48a59f2 100644
--- a/arch/arm/mach-nomadik/clock.c
+++ b/arch/arm/mach-nomadik/clock.c
@@ -7,7 +7,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/clk.h>
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 #include "clock.h"
 
 /*
diff --git a/arch/arm/mach-nuc93x/clock.h b/arch/arm/mach-nuc93x/clock.h
index 18e51be..4de1f1d 100644
--- a/arch/arm/mach-nuc93x/clock.h
+++ b/arch/arm/mach-nuc93x/clock.h
@@ -10,7 +10,7 @@
  * the Free Software Foundation; either version 2 of the License.
  */
 
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 void nuc93x_clk_enable(struct clk *clk, int enable);
 void clks_register(struct clk_lookup *clks, size_t num);
diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c
index b8c7fb9..84ef704 100644
--- a/arch/arm/mach-omap1/clock.c
+++ b/arch/arm/mach-omap1/clock.c
@@ -17,9 +17,9 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/clkdev.h>
 
 #include <asm/mach-types.h>
-#include <asm/clkdev.h>
 
 #include <plat/cpu.h>
 #include <plat/usb.h>
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index ed8d330..ebb888f 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -26,10 +26,10 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/bitops.h>
+#include <linux/clkdev.h>
 
 #include <plat/cpu.h>
 #include <plat/clock.h>
-#include <asm/clkdev.h>
 
 #include "clock.h"
 #include "prm.h"
diff --git a/arch/arm/mach-omap2/omap-hotplug.c b/arch/arm/mach-omap2/omap-hotplug.c
index 6cee456..4976b93 100644
--- a/arch/arm/mach-omap2/omap-hotplug.c
+++ b/arch/arm/mach-omap2/omap-hotplug.c
@@ -17,16 +17,13 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
-#include <linux/completion.h>
 
 #include <asm/cacheflush.h>
 #include <mach/omap4-common.h>
 
-static DECLARE_COMPLETION(cpu_killed);
-
 int platform_cpu_kill(unsigned int cpu)
 {
-	return wait_for_completion_timeout(&cpu_killed, 5000);
+	return 1;
 }
 
 /*
@@ -35,15 +32,6 @@
  */
 void platform_cpu_die(unsigned int cpu)
 {
-	unsigned int this_cpu = hard_smp_processor_id();
-
-	if (cpu != this_cpu) {
-		pr_crit("platform_cpu_die running on %u, should be %u\n",
-			   this_cpu, cpu);
-		BUG();
-	}
-	pr_notice("CPU%u: shutdown\n", cpu);
-	complete(&cpu_killed);
 	flush_cache_all();
 	dsb();
 
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 9fbac2c..b66cfe8 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -21,7 +21,6 @@
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
-#include <asm/localtimer.h>
 #include <asm/smp_scu.h>
 #include <mach/hardware.h>
 #include <mach/omap4-common.h>
@@ -29,22 +28,10 @@
 /* SCU base address */
 static void __iomem *scu_base;
 
-/*
- * Use SCU config register to count number of cores
- */
-static inline unsigned int get_core_count(void)
-{
-	if (scu_base)
-		return scu_get_core_count(scu_base);
-	return 1;
-}
-
 static DEFINE_SPINLOCK(boot_lock);
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
-	trace_hardirqs_off();
-
 	/*
 	 * If any interrupts are already enabled for the primary
 	 * core (e.g. timer irq), then they will not have been enabled
@@ -76,7 +63,7 @@
 	omap_modify_auxcoreboot0(0x200, 0xfffffdff);
 	flush_cache_all();
 	smp_wmb();
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	/*
 	 * Now the secondary core is starting up let it run its
@@ -118,25 +105,9 @@
 	scu_base = ioremap(OMAP44XX_SCU_BASE, SZ_256);
 	BUG_ON(!scu_base);
 
-	ncores = get_core_count();
-
-	for (i = 0; i < ncores; i++)
-		set_cpu_possible(i, true);
-}
-
-void __init smp_prepare_cpus(unsigned int max_cpus)
-{
-	unsigned int ncores = get_core_count();
-	unsigned int cpu = smp_processor_id();
-	int i;
+	ncores = scu_get_core_count(scu_base);
 
 	/* sanity check */
-	if (ncores == 0) {
-		printk(KERN_ERR
-		       "OMAP4: strange core count of 0? Default to 1\n");
-		ncores = 1;
-	}
-
 	if (ncores > NR_CPUS) {
 		printk(KERN_WARNING
 		       "OMAP4: no. of cores (%d) greater than configured "
@@ -144,13 +115,14 @@
 		       ncores, NR_CPUS);
 		ncores = NR_CPUS;
 	}
-	smp_store_cpu_info(cpu);
 
-	/*
-	 * are we trying to boot more cores than exist?
-	 */
-	if (max_cpus > ncores)
-		max_cpus = ncores;
+	for (i = 0; i < ncores; i++)
+		set_cpu_possible(i, true);
+}
+
+void __init platform_smp_prepare_cpus(unsigned int max_cpus)
+{
+	int i;
 
 	/*
 	 * Initialise the present map, which describes the set of CPUs
@@ -159,18 +131,10 @@
 	for (i = 0; i < max_cpus; i++)
 		set_cpu_present(i, true);
 
-	if (max_cpus > 1) {
-		/*
-		 * Enable the local timer or broadcast device for the
-		 * boot CPU, but only if we have more than one CPU.
-		 */
-		percpu_timer_setup();
-
-		/*
-		 * Initialise the SCU and wake up the secondary core using
-		 * wakeup_secondary().
-		 */
-		scu_enable(scu_base);
-		wakeup_secondary();
-	}
+	/*
+	 * Initialise the SCU and wake up the secondary core using
+	 * wakeup_secondary().
+	 */
+	scu_enable(scu_base);
+	wakeup_secondary();
 }
diff --git a/arch/arm/mach-pnx4008/clock.c b/arch/arm/mach-pnx4008/clock.c
index 9d1975f..a4a3819 100644
--- a/arch/arm/mach-pnx4008/clock.c
+++ b/arch/arm/mach-pnx4008/clock.c
@@ -21,8 +21,7 @@
 #include <linux/err.h>
 #include <linux/delay.h>
 #include <linux/io.h>
-
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #include <mach/hardware.h>
 #include <mach/clock.h>
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index c93e73d..c98d81f 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -94,6 +94,7 @@
 	select PXA27x
 	select IWMMXT
 	select PXA25x
+	select MIGHT_HAVE_PCI
 
 config MACH_EM_X270
 	bool "CompuLab EM-x270 platform"
diff --git a/arch/arm/mach-pxa/clock.c b/arch/arm/mach-pxa/clock.c
index abba008..4e4a84b 100644
--- a/arch/arm/mach-pxa/clock.c
+++ b/arch/arm/mach-pxa/clock.c
@@ -11,8 +11,8 @@
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <mach/pxa2xx-regs.h>
 #include <mach/hardware.h>
 
diff --git a/arch/arm/mach-pxa/clock.h b/arch/arm/mach-pxa/clock.h
index d848874..12cc0e8 100644
--- a/arch/arm/mach-pxa/clock.h
+++ b/arch/arm/mach-pxa/clock.h
@@ -1,4 +1,4 @@
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 struct clkops {
 	void			(*enable)(struct clk *);
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index aad806c..1c6602c 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -30,8 +30,8 @@
 #include <linux/ata_platform.h>
 #include <linux/amba/mmci.h>
 #include <linux/gfp.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
@@ -47,7 +47,6 @@
 
 #include <asm/hardware/gic.h>
 
-#include <mach/clkdev.h>
 #include <mach/platform.h>
 #include <mach/irqs.h>
 #include <asm/hardware/timer-sp.h>
diff --git a/arch/arm/mach-realview/hotplug.c b/arch/arm/mach-realview/hotplug.c
index f95521a..a87523d 100644
--- a/arch/arm/mach-realview/hotplug.c
+++ b/arch/arm/mach-realview/hotplug.c
@@ -11,14 +11,11 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
-#include <linux/completion.h>
 
 #include <asm/cacheflush.h>
 
 extern volatile int pen_release;
 
-static DECLARE_COMPLETION(cpu_killed);
-
 static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
@@ -34,10 +31,10 @@
 	"	bic	%0, %0, #0x20\n"
 	"	mcr	p15, 0, %0, c1, c0, 1\n"
 	"	mrc	p15, 0, %0, c1, c0, 0\n"
-	"	bic	%0, %0, #0x04\n"
+	"	bic	%0, %0, %2\n"
 	"	mcr	p15, 0, %0, c1, c0, 0\n"
 	  : "=&r" (v)
-	  : "r" (0)
+	  : "r" (0), "Ir" (CR_C)
 	  : "cc");
 }
 
@@ -46,17 +43,17 @@
 	unsigned int v;
 
 	asm volatile(	"mrc	p15, 0, %0, c1, c0, 0\n"
-	"	orr	%0, %0, #0x04\n"
+	"	orr	%0, %0, %1\n"
 	"	mcr	p15, 0, %0, c1, c0, 0\n"
 	"	mrc	p15, 0, %0, c1, c0, 1\n"
 	"	orr	%0, %0, #0x20\n"
 	"	mcr	p15, 0, %0, c1, c0, 1\n"
 	  : "=&r" (v)
-	  :
+	  : "Ir" (CR_C)
 	  : "cc");
 }
 
-static inline void platform_do_lowpower(unsigned int cpu)
+static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 {
 	/*
 	 * there is no power-control hardware on this platform, so all
@@ -80,22 +77,19 @@
 		}
 
 		/*
-		 * getting here, means that we have come out of WFI without
+		 * Getting here, means that we have come out of WFI without
 		 * having been woken up - this shouldn't happen
 		 *
-		 * The trouble is, letting people know about this is not really
-		 * possible, since we are currently running incoherently, and
-		 * therefore cannot safely call printk() or anything else
+		 * Just note it happening - when we're woken, we can report
+		 * its occurrence.
 		 */
-#ifdef DEBUG
-		printk("CPU%u: spurious wakeup call\n", cpu);
-#endif
+		(*spurious)++;
 	}
 }
 
 int platform_cpu_kill(unsigned int cpu)
 {
-	return wait_for_completion_timeout(&cpu_killed, 5000);
+	return 1;
 }
 
 /*
@@ -105,30 +99,22 @@
  */
 void platform_cpu_die(unsigned int cpu)
 {
-#ifdef DEBUG
-	unsigned int this_cpu = hard_smp_processor_id();
-
-	if (cpu != this_cpu) {
-		printk(KERN_CRIT "Eek! platform_cpu_die running on %u, should be %u\n",
-			   this_cpu, cpu);
-		BUG();
-	}
-#endif
-
-	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
-	complete(&cpu_killed);
+	int spurious = 0;
 
 	/*
 	 * we're ready for shutdown now, so do it
 	 */
 	cpu_enter_lowpower();
-	platform_do_lowpower(cpu);
+	platform_do_lowpower(cpu, &spurious);
 
 	/*
 	 * bring this CPU back into the world of cache
 	 * coherency, and then restore interrupts
 	 */
 	cpu_leave_lowpower();
+
+	if (spurious)
+		pr_warn("CPU%u: %u spurious wakeup calls\n", cpu, spurious);
 }
 
 int platform_cpu_disable(unsigned int cpu)
diff --git a/arch/arm/mach-realview/include/mach/smp.h b/arch/arm/mach-realview/include/mach/smp.h
index d3cd265..c8221b3 100644
--- a/arch/arm/mach-realview/include/mach/smp.h
+++ b/arch/arm/mach-realview/include/mach/smp.h
@@ -2,14 +2,13 @@
 #define ASMARM_ARCH_SMP_H
 
 #include <asm/hardware/gic.h>
-#include <asm/smp_mpidr.h>
 
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c
index 6da8a2e..a22bf67 100644
--- a/arch/arm/mach-realview/platsmp.c
+++ b/arch/arm/mach-realview/platsmp.c
@@ -19,7 +19,6 @@
 #include <asm/cacheflush.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/localtimer.h>
 #include <asm/unified.h>
 
 #include <mach/board-eb.h>
@@ -37,6 +36,19 @@
  */
 volatile int __cpuinitdata pen_release = -1;
 
+/*
+ * Write pen_release in a way that is guaranteed to be visible to all
+ * observers, irrespective of whether they're taking part in coherency
+ * or not.  This is necessary for the hotplug code to work reliably.
+ */
+static void write_pen_release(int val)
+{
+	pen_release = val;
+	smp_wmb();
+	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
+	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
+}
+
 static void __iomem *scu_base_addr(void)
 {
 	if (machine_is_realview_eb_mp())
@@ -50,20 +62,10 @@
 		return (void __iomem *)0;
 }
 
-static inline unsigned int get_core_count(void)
-{
-	void __iomem *scu_base = scu_base_addr();
-	if (scu_base)
-		return scu_get_core_count(scu_base);
-	return 1;
-}
-
 static DEFINE_SPINLOCK(boot_lock);
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
-	trace_hardirqs_off();
-
 	/*
 	 * if any interrupts are already enabled for the primary
 	 * core (e.g. timer irq), then they will not have been enabled
@@ -75,8 +77,7 @@
 	 * let the primary processor know we're out of the
 	 * pen, then head off into the C entry point
 	 */
-	pen_release = -1;
-	smp_wmb();
+	write_pen_release(-1);
 
 	/*
 	 * Synchronise with the boot thread.
@@ -103,20 +104,14 @@
 	 * Note that "pen_release" is the hardware CPU ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	pen_release = cpu;
-	flush_cache_all();
+	write_pen_release(cpu);
 
 	/*
-	 * XXX
-	 *
-	 * This is a later addition to the booting protocol: the
-	 * bootMonitor now puts secondary cores into WFI, so
-	 * poke_milo() no longer gets the cores moving; we need
-	 * to send a soft interrupt to wake the secondary core.
-	 * Use smp_cross_call() for this, since there's little
-	 * point duplicating the code here
+	 * Send the secondary CPU a soft interrupt, thereby causing
+	 * the boot monitor to read the system wide flags register,
+	 * and branch to the address found there.
 	 */
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
@@ -136,48 +131,18 @@
 	return pen_release != -1 ? -ENOSYS : 0;
 }
 
-static void __init poke_milo(void)
-{
-	/* nobody is to be released from the pen yet */
-	pen_release = -1;
-
-	/*
-	 * Write the address of secondary startup into the system-wide flags
-	 * register. The BootMonitor waits for this register to become
-	 * non-zero.
-	 */
-	__raw_writel(BSYM(virt_to_phys(realview_secondary_startup)),
-		     __io_address(REALVIEW_SYS_FLAGSSET));
-
-	mb();
-}
-
 /*
  * Initialise the CPU possible map early - this describes the CPUs
  * which may be present or become present in the system.
  */
 void __init smp_init_cpus(void)
 {
-	unsigned int i, ncores = get_core_count();
+	void __iomem *scu_base = scu_base_addr();
+	unsigned int i, ncores;
 
-	for (i = 0; i < ncores; i++)
-		set_cpu_possible(i, true);
-}
-
-void __init smp_prepare_cpus(unsigned int max_cpus)
-{
-	unsigned int ncores = get_core_count();
-	unsigned int cpu = smp_processor_id();
-	int i;
+	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores == 0) {
-		printk(KERN_ERR
-		       "Realview: strange CM count of 0? Default to 1\n");
-
-		ncores = 1;
-	}
-
 	if (ncores > NR_CPUS) {
 		printk(KERN_WARNING
 		       "Realview: no. of cores (%d) greater than configured "
@@ -186,13 +151,13 @@
 		ncores = NR_CPUS;
 	}
 
-	smp_store_cpu_info(cpu);
+	for (i = 0; i < ncores; i++)
+		set_cpu_possible(i, true);
+}
 
-	/*
-	 * are we trying to boot more cores than exist?
-	 */
-	if (max_cpus > ncores)
-		max_cpus = ncores;
+void __init platform_smp_prepare_cpus(unsigned int max_cpus)
+{
+	int i;
 
 	/*
 	 * Initialise the present map, which describes the set of CPUs
@@ -201,21 +166,14 @@
 	for (i = 0; i < max_cpus; i++)
 		set_cpu_present(i, true);
 
-	/*
-	 * Initialise the SCU if there are more than one CPU and let
-	 * them know where to start. Note that, on modern versions of
-	 * MILO, the "poke" doesn't actually do anything until each
-	 * individual core is sent a soft interrupt to get it out of
-	 * WFI
-	 */
-	if (max_cpus > 1) {
-		/*
-		 * Enable the local timer or broadcast device for the
-		 * boot CPU, but only if we have more than one CPU.
-		 */
-		percpu_timer_setup();
+	scu_enable(scu_base_addr());
 
-		scu_enable(scu_base_addr());
-		poke_milo();
-	}
+	/*
+	 * Write the address of secondary startup into the
+	 * system-wide flags register. The BootMonitor waits
+	 * until it receives a soft interrupt, and then the
+	 * secondary CPU branches to this address.
+	 */
+	__raw_writel(BSYM(virt_to_phys(realview_secondary_startup)),
+		     __io_address(REALVIEW_SYS_FLAGSSET));
 }
diff --git a/arch/arm/mach-s3c2412/Kconfig b/arch/arm/mach-s3c2412/Kconfig
index 6983cb4..e82ab4a 100644
--- a/arch/arm/mach-s3c2412/Kconfig
+++ b/arch/arm/mach-s3c2412/Kconfig
@@ -59,7 +59,7 @@
 	  Say Y here if you are using the Logitech Jive.
 
 config MACH_JIVE_SHOW_BOOTLOADER
-	bool "Allow access to bootloader partitions in MTD"
+	bool "Allow access to bootloader partitions in MTD (EXPERIMENTAL)"
 	depends on MACH_JIVE && EXPERIMENTAL
 
 config MACH_SMDK2413
diff --git a/arch/arm/mach-s5pv310/hotplug.c b/arch/arm/mach-s5pv310/hotplug.c
index 03652c3..afa5392 100644
--- a/arch/arm/mach-s5pv310/hotplug.c
+++ b/arch/arm/mach-s5pv310/hotplug.c
@@ -13,14 +13,11 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
-#include <linux/completion.h>
 
 #include <asm/cacheflush.h>
 
 extern volatile int pen_release;
 
-static DECLARE_COMPLETION(cpu_killed);
-
 static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
@@ -33,13 +30,13 @@
 	 * Turn off coherency
 	 */
 	"	mrc	p15, 0, %0, c1, c0, 1\n"
-	"	bic	%0, %0, #0x20\n"
+	"	bic	%0, %0, %2\n"
 	"	mcr	p15, 0, %0, c1, c0, 1\n"
 	"	mrc	p15, 0, %0, c1, c0, 0\n"
 	"	bic	%0, %0, #0x04\n"
 	"	mcr	p15, 0, %0, c1, c0, 0\n"
 	  : "=&r" (v)
-	  : "r" (0)
+	  : "r" (0), "Ir" (CR_C)
 	  : "cc");
 }
 
@@ -49,17 +46,17 @@
 
 	asm volatile(
 	"mrc	p15, 0, %0, c1, c0, 0\n"
-	"	orr	%0, %0, #0x04\n"
+	"	orr	%0, %0, %1\n"
 	"	mcr	p15, 0, %0, c1, c0, 0\n"
 	"	mrc	p15, 0, %0, c1, c0, 1\n"
 	"	orr	%0, %0, #0x20\n"
 	"	mcr	p15, 0, %0, c1, c0, 1\n"
 	  : "=&r" (v)
-	  :
+	  : "Ir" (CR_C)
 	  : "cc");
 }
 
-static inline void platform_do_lowpower(unsigned int cpu)
+static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 {
 	/*
 	 * there is no power-control hardware on this platform, so all
@@ -83,22 +80,19 @@
 		}
 
 		/*
-		 * getting here, means that we have come out of WFI without
+		 * Getting here, means that we have come out of WFI without
 		 * having been woken up - this shouldn't happen
 		 *
-		 * The trouble is, letting people know about this is not really
-		 * possible, since we are currently running incoherently, and
-		 * therefore cannot safely call printk() or anything else
+		 * Just note it happening - when we're woken, we can report
+		 * its occurrence.
 		 */
-#ifdef DEBUG
-		printk(KERN_WARN "CPU%u: spurious wakeup call\n", cpu);
-#endif
+		(*spurious)++;
 	}
 }
 
 int platform_cpu_kill(unsigned int cpu)
 {
-	return wait_for_completion_timeout(&cpu_killed, 5000);
+	return 1;
 }
 
 /*
@@ -108,30 +102,22 @@
  */
 void platform_cpu_die(unsigned int cpu)
 {
-#ifdef DEBUG
-	unsigned int this_cpu = hard_smp_processor_id();
-
-	if (cpu != this_cpu) {
-		printk(KERN_CRIT "Eek! platform_cpu_die running on %u, should be %u\n",
-			   this_cpu, cpu);
-		BUG();
-	}
-#endif
-
-	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
-	complete(&cpu_killed);
+	int spurious = 0;
 
 	/*
 	 * we're ready for shutdown now, so do it
 	 */
 	cpu_enter_lowpower();
-	platform_do_lowpower(cpu);
+	platform_do_lowpower(cpu, &spurious);
 
 	/*
 	 * bring this CPU back into the world of cache
 	 * coherency, and then restore interrupts
 	 */
 	cpu_leave_lowpower();
+
+	if (spurious)
+		pr_warn("CPU%u: %u spurious wakeup calls\n", cpu, spurious);
 }
 
 int platform_cpu_disable(unsigned int cpu)
diff --git a/arch/arm/mach-s5pv310/include/mach/smp.h b/arch/arm/mach-s5pv310/include/mach/smp.h
index e1cc6a2..393ccbd 100644
--- a/arch/arm/mach-s5pv310/include/mach/smp.h
+++ b/arch/arm/mach-s5pv310/include/mach/smp.h
@@ -7,14 +7,13 @@
 #define ASM_ARCH_SMP_H __FILE__
 
 #include <asm/hardware/gic.h>
-#include <asm/smp_mpidr.h>
 
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-s5pv310/platsmp.c b/arch/arm/mach-s5pv310/platsmp.c
index 15929c1..34093b0 100644
--- a/arch/arm/mach-s5pv310/platsmp.c
+++ b/arch/arm/mach-s5pv310/platsmp.c
@@ -22,7 +22,6 @@
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
-#include <asm/localtimer.h>
 #include <asm/smp_scu.h>
 #include <asm/unified.h>
 
@@ -38,6 +37,19 @@
 
 volatile int __cpuinitdata pen_release = -1;
 
+/*
+ * Write pen_release in a way that is guaranteed to be visible to all
+ * observers, irrespective of whether they're taking part in coherency
+ * or not.  This is necessary for the hotplug code to work reliably.
+ */
+static void write_pen_release(int val)
+{
+	pen_release = val;
+	smp_wmb();
+	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
+	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
+}
+
 static void __iomem *scu_base_addr(void)
 {
 	return (void __iomem *)(S5P_VA_SCU);
@@ -47,8 +59,6 @@
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
-	trace_hardirqs_off();
-
 	/*
 	 * if any interrupts are already enabled for the primary
 	 * core (e.g. timer irq), then they will not have been enabled
@@ -60,8 +70,7 @@
 	 * let the primary processor know we're out of the
 	 * pen, then head off into the C entry point
 	 */
-	pen_release = -1;
-	smp_wmb();
+	write_pen_release(-1);
 
 	/*
 	 * Synchronise with the boot thread.
@@ -88,16 +97,14 @@
 	 * Note that "pen_release" is the hardware CPU ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	pen_release = cpu;
-	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
-	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
+	write_pen_release(cpu);
 
 	/*
 	 * Send the secondary CPU a soft interrupt, thereby causing
 	 * the boot monitor to read the system wide flags register,
 	 * and branch to the address found there.
 	 */
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
@@ -130,13 +137,6 @@
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores == 0) {
-		printk(KERN_ERR
-		       "S5PV310: strange CM count of 0? Default to 1\n");
-
-		ncores = 1;
-	}
-
 	if (ncores > NR_CPUS) {
 		printk(KERN_WARNING
 		       "S5PV310: no. of cores (%d) greater than configured "
@@ -149,18 +149,10 @@
 		set_cpu_possible(i, true);
 }
 
-void __init smp_prepare_cpus(unsigned int max_cpus)
+void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned int ncores = num_possible_cpus();
-	unsigned int cpu = smp_processor_id();
 	int i;
 
-	smp_store_cpu_info(cpu);
-
-	/* are we trying to boot more cores than exist? */
-	if (max_cpus > ncores)
-		max_cpus = ncores;
-
 	/*
 	 * Initialise the present map, which describes the set of CPUs
 	 * actually populated at the present time.
@@ -168,25 +160,13 @@
 	for (i = 0; i < max_cpus; i++)
 		set_cpu_present(i, true);
 
+	scu_enable(scu_base_addr());
+
 	/*
-	 * Initialise the SCU if there are more than one CPU and let
-	 * them know where to start.
+	 * Write the address of secondary startup into the
+	 * system-wide flags register. The boot monitor waits
+	 * until it receives a soft interrupt, and then the
+	 * secondary CPU branches to this address.
 	 */
-	if (max_cpus > 1) {
-		/*
-		 * Enable the local timer or broadcast device for the
-		 * boot CPU, but only if we have more than one CPU.
-		 */
-		percpu_timer_setup();
-
-		scu_enable(scu_base_addr());
-
-		/*
-		 * Write the address of secondary startup into the
-		 * system-wide flags register. The boot monitor waits
-		 * until it receives a soft interrupt, and then the
-		 * secondary CPU branches to this address.
-		 */
 	__raw_writel(BSYM(virt_to_phys(s5pv310_secondary_startup)), S5P_VA_SYSRAM);
-	}
 }
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 51dcd59..6329333 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -6,7 +6,7 @@
 	bool "SH-Mobile G3 (SH7367)"
 	select CPU_V6
 	select HAVE_CLK
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select SH_CLK_CPG
 	select GENERIC_CLOCKEVENTS
 
@@ -14,7 +14,7 @@
 	bool "SH-Mobile G4 (SH7377)"
 	select CPU_V7
 	select HAVE_CLK
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select SH_CLK_CPG
 	select GENERIC_CLOCKEVENTS
 
@@ -22,7 +22,7 @@
 	bool "SH-Mobile AP4 (SH7372)"
 	select CPU_V7
 	select HAVE_CLK
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	select SH_CLK_CPG
 	select GENERIC_CLOCKEVENTS
 
diff --git a/arch/arm/mach-shmobile/clock-sh7367.c b/arch/arm/mach-shmobile/clock-sh7367.c
index 9f78729..6b186ae 100644
--- a/arch/arm/mach-shmobile/clock-sh7367.c
+++ b/arch/arm/mach-shmobile/clock-sh7367.c
@@ -20,8 +20,8 @@
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/sh_clk.h>
+#include <linux/clkdev.h>
 #include <mach/common.h>
-#include <asm/clkdev.h>
 
 /* SH7367 registers */
 #define RTFRQCR    0xe6150000
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index 3aa0260..d98deb4 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -20,8 +20,8 @@
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/sh_clk.h>
+#include <linux/clkdev.h>
 #include <mach/common.h>
-#include <asm/clkdev.h>
 
 /* SH7372 registers */
 #define FRQCRA		0xe6150000
diff --git a/arch/arm/mach-shmobile/clock-sh7377.c b/arch/arm/mach-shmobile/clock-sh7377.c
index f91395a..9594246 100644
--- a/arch/arm/mach-shmobile/clock-sh7377.c
+++ b/arch/arm/mach-shmobile/clock-sh7377.c
@@ -20,8 +20,8 @@
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/sh_clk.h>
+#include <linux/clkdev.h>
 #include <mach/common.h>
-#include <asm/clkdev.h>
 
 /* SH7377 registers */
 #define RTFRQCR    0xe6150000
diff --git a/arch/arm/mach-tcc8k/clock.c b/arch/arm/mach-tcc8k/clock.c
index ba32a15..3970a9c 100644
--- a/arch/arm/mach-tcc8k/clock.c
+++ b/arch/arm/mach-tcc8k/clock.c
@@ -12,8 +12,7 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
-
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #include <mach/clock.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-tegra/clock.c b/arch/arm/mach-tegra/clock.c
index ae19f95..77948e0 100644
--- a/arch/arm/mach-tegra/clock.c
+++ b/arch/arm/mach-tegra/clock.c
@@ -25,7 +25,7 @@
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/regulator/consumer.h>
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #include "clock.h"
 #include "board.h"
diff --git a/arch/arm/mach-tegra/clock.h b/arch/arm/mach-tegra/clock.h
index 94fd859..083a4cf 100644
--- a/arch/arm/mach-tegra/clock.h
+++ b/arch/arm/mach-tegra/clock.h
@@ -21,7 +21,7 @@
 #define __MACH_TEGRA_CLOCK_H
 
 #include <linux/list.h>
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #define DIV_BUS			(1 << 0)
 #define DIV_U71			(1 << 1)
diff --git a/arch/arm/mach-tegra/hotplug.c b/arch/arm/mach-tegra/hotplug.c
index 8e7f115..a5cb1ce 100644
--- a/arch/arm/mach-tegra/hotplug.c
+++ b/arch/arm/mach-tegra/hotplug.c
@@ -11,12 +11,9 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
-#include <linux/completion.h>
 
 #include <asm/cacheflush.h>
 
-static DECLARE_COMPLETION(cpu_killed);
-
 static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
@@ -29,13 +26,13 @@
 	 * Turn off coherency
 	 */
 	"	mrc	p15, 0, %0, c1, c0, 1\n"
-	"	bic	%0, %0, #0x20\n"
+	"	bic	%0, %0, %2\n"
 	"	mcr	p15, 0, %0, c1, c0, 1\n"
 	"	mrc	p15, 0, %0, c1, c0, 0\n"
 	"	bic	%0, %0, #0x04\n"
 	"	mcr	p15, 0, %0, c1, c0, 0\n"
 	  : "=&r" (v)
-	  : "r" (0)
+	  : "r" (0), "Ir" (CR_C)
 	  : "cc");
 }
 
@@ -45,17 +42,17 @@
 
 	asm volatile(
 	"mrc	p15, 0, %0, c1, c0, 0\n"
-	"	orr	%0, %0, #0x04\n"
+	"	orr	%0, %0, %1\n"
 	"	mcr	p15, 0, %0, c1, c0, 0\n"
 	"	mrc	p15, 0, %0, c1, c0, 1\n"
 	"	orr	%0, %0, #0x20\n"
 	"	mcr	p15, 0, %0, c1, c0, 1\n"
 	  : "=&r" (v)
-	  :
+	  : "Ir" (CR_C)
 	  : "cc");
 }
 
-static inline void platform_do_lowpower(unsigned int cpu)
+static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 {
 	/*
 	 * there is no power-control hardware on this platform, so all
@@ -79,22 +76,19 @@
 		/*}*/
 
 		/*
-		 * getting here, means that we have come out of WFI without
+		 * Getting here, means that we have come out of WFI without
 		 * having been woken up - this shouldn't happen
 		 *
-		 * The trouble is, letting people know about this is not really
-		 * possible, since we are currently running incoherently, and
-		 * therefore cannot safely call printk() or anything else
+		 * Just note it happening - when we're woken, we can report
+		 * its occurrence.
 		 */
-#ifdef DEBUG
-		printk(KERN_WARN "CPU%u: spurious wakeup call\n", cpu);
-#endif
+		(*spurious)++;
 	}
 }
 
 int platform_cpu_kill(unsigned int cpu)
 {
-	return wait_for_completion_timeout(&cpu_killed, 5000);
+	return 1;
 }
 
 /*
@@ -104,30 +98,22 @@
  */
 void platform_cpu_die(unsigned int cpu)
 {
-#ifdef DEBUG
-	unsigned int this_cpu = hard_smp_processor_id();
-
-	if (cpu != this_cpu) {
-		printk(KERN_CRIT "Eek! platform_cpu_die running on %u, should be %u\n",
-			   this_cpu, cpu);
-		BUG();
-	}
-#endif
-
-	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
-	complete(&cpu_killed);
+	int spurious = 0;
 
 	/*
 	 * we're ready for shutdown now, so do it
 	 */
 	cpu_enter_lowpower();
-	platform_do_lowpower(cpu);
+	platform_do_lowpower(cpu, &spurious);
 
 	/*
 	 * bring this CPU back into the world of cache
 	 * coherency, and then restore interrupts
 	 */
 	cpu_leave_lowpower();
+
+	if (spurious)
+		pr_warn("CPU%u: %u spurious wakeup calls\n", cpu, spurious);
 }
 
 int platform_cpu_disable(unsigned int cpu)
diff --git a/arch/arm/mach-tegra/include/mach/smp.h b/arch/arm/mach-tegra/include/mach/smp.h
index e4a34a3..c8221b3 100644
--- a/arch/arm/mach-tegra/include/mach/smp.h
+++ b/arch/arm/mach-tegra/include/mach/smp.h
@@ -2,21 +2,13 @@
 #define ASMARM_ARCH_SMP_H
 
 #include <asm/hardware/gic.h>
-#include <asm/smp_mpidr.h>
 
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
-}
-
-/*
- * Do nothing on MPcore.
- */
-static inline void smp_cross_call_done(cpumask_t callmap)
-{
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c
index 3b7376c..ec1f689 100644
--- a/arch/arm/mach-tegra/platsmp.c
+++ b/arch/arm/mach-tegra/platsmp.c
@@ -22,7 +22,6 @@
 #include <asm/cacheflush.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/localtimer.h>
 #include <asm/smp_scu.h>
 
 #include <mach/iomap.h>
@@ -41,8 +40,6 @@
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
-	trace_hardirqs_off();
-
 	/*
 	 * if any interrupts are already enabled for the primary
 	 * core (e.g. timer irq), then they will not have been enabled
@@ -117,24 +114,20 @@
 {
 	unsigned int i, ncores = scu_get_core_count(scu_base);
 
+	if (ncores > NR_CPUS) {
+		printk(KERN_ERR "Tegra: no. of cores (%u) greater than configured (%u), clipping\n",
+			ncores, NR_CPUS);
+		ncores = NR_CPUS;
+	}
+
 	for (i = 0; i < ncores; i++)
 		cpu_set(i, cpu_possible_map);
 }
 
-void __init smp_prepare_cpus(unsigned int max_cpus)
+void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned int ncores = scu_get_core_count(scu_base);
-	unsigned int cpu = smp_processor_id();
 	int i;
 
-	smp_store_cpu_info(cpu);
-
-	/*
-	 * are we trying to boot more cores than exist?
-	 */
-	if (max_cpus > ncores)
-		max_cpus = ncores;
-
 	/*
 	 * Initialise the present map, which describes the set of CPUs
 	 * actually populated at the present time.
@@ -142,15 +135,5 @@
 	for (i = 0; i < max_cpus; i++)
 		set_cpu_present(i, true);
 
-	/*
-	 * Initialise the SCU if there are more than one CPU and let
-	 * them know where to start. Note that, on modern versions of
-	 * MILO, the "poke" doesn't actually do anything until each
-	 * individual core is sent a soft interrupt to get it out of
-	 * WFI
-	 */
-	if (max_cpus > 1) {
-		percpu_timer_setup();
-		scu_enable(scu_base);
-	}
+	scu_enable(scu_base);
 }
diff --git a/arch/arm/mach-tegra/tegra2_clocks.c b/arch/arm/mach-tegra/tegra2_clocks.c
index ae3b308..f0dae6d 100644
--- a/arch/arm/mach-tegra/tegra2_clocks.c
+++ b/arch/arm/mach-tegra/tegra2_clocks.c
@@ -24,8 +24,7 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/hrtimer.h>
-
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #include <mach/iomap.h>
 
diff --git a/arch/arm/mach-u300/clock.c b/arch/arm/mach-u300/clock.c
index 7458fc6..fabcc49 100644
--- a/arch/arm/mach-u300/clock.c
+++ b/arch/arm/mach-u300/clock.c
@@ -25,8 +25,8 @@
 #include <linux/timer.h>
 #include <linux/io.h>
 #include <linux/seq_file.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <mach/hardware.h>
 #include <mach/syscon.h>
 
diff --git a/arch/arm/mach-ux500/clock.c b/arch/arm/mach-ux500/clock.c
index 1675047..531de5c 100644
--- a/arch/arm/mach-ux500/clock.c
+++ b/arch/arm/mach-ux500/clock.c
@@ -13,8 +13,7 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
-
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 #include <plat/mtu.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-ux500/headsmp.S b/arch/arm/mach-ux500/headsmp.S
index a6be2cd..64fa451 100644
--- a/arch/arm/mach-ux500/headsmp.S
+++ b/arch/arm/mach-ux500/headsmp.S
@@ -23,7 +23,6 @@
 	ldmia	r4, {r5, r6}
 	sub	r4, r4, r5
 	add	r6, r6, r4
-	dsb
 pen:	ldr	r7, [r6]
 	cmp	r7, r0
 	bne	pen
diff --git a/arch/arm/mach-ux500/hotplug.c b/arch/arm/mach-ux500/hotplug.c
index b782a03..dd8037e 100644
--- a/arch/arm/mach-ux500/hotplug.c
+++ b/arch/arm/mach-ux500/hotplug.c
@@ -11,14 +11,11 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
-#include <linux/completion.h>
 
 #include <asm/cacheflush.h>
 
 extern volatile int pen_release;
 
-static DECLARE_COMPLETION(cpu_killed);
-
 static inline void platform_do_lowpower(unsigned int cpu)
 {
 	flush_cache_all();
@@ -38,7 +35,7 @@
 
 int platform_cpu_kill(unsigned int cpu)
 {
-	return wait_for_completion_timeout(&cpu_killed, 5000);
+	return 1;
 }
 
 /*
@@ -48,19 +45,6 @@
  */
 void platform_cpu_die(unsigned int cpu)
 {
-#ifdef DEBUG
-	unsigned int this_cpu = hard_smp_processor_id();
-
-	if (cpu != this_cpu) {
-		printk(KERN_CRIT "Eek! platform_cpu_die running on %u, should be %u\n",
-			   this_cpu, cpu);
-		BUG();
-	}
-#endif
-
-	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
-	complete(&cpu_killed);
-
 	/* directly enter low power state, skipping secure registers */
 	platform_do_lowpower(cpu);
 }
diff --git a/arch/arm/mach-ux500/include/mach/smp.h b/arch/arm/mach-ux500/include/mach/smp.h
index 197e841..ca2b15b 100644
--- a/arch/arm/mach-ux500/include/mach/smp.h
+++ b/arch/arm/mach-ux500/include/mach/smp.h
@@ -10,7 +10,6 @@
 #define ASMARM_ARCH_SMP_H
 
 #include <asm/hardware/gic.h>
-#include <asm/smp_mpidr.h>
 
 /* This is required to wakeup the secondary core */
 extern void u8500_secondary_startup(void);
@@ -18,8 +17,8 @@
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 #endif
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index b5077b4..2115a0c 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -18,7 +18,6 @@
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
-#include <asm/localtimer.h>
 #include <asm/smp_scu.h>
 #include <mach/hardware.h>
 
@@ -28,17 +27,23 @@
  */
 volatile int __cpuinitdata pen_release = -1;
 
-static unsigned int __init get_core_count(void)
+/*
+ * Write pen_release in a way that is guaranteed to be visible to all
+ * observers, irrespective of whether they're taking part in coherency
+ * or not.  This is necessary for the hotplug code to work reliably.
+ */
+static void write_pen_release(int val)
 {
-	return scu_get_core_count(__io_address(UX500_SCU_BASE));
+	pen_release = val;
+	smp_wmb();
+	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
+	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
 }
 
 static DEFINE_SPINLOCK(boot_lock);
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
-	trace_hardirqs_off();
-
 	/*
 	 * if any interrupts are already enabled for the primary
 	 * core (e.g. timer irq), then they will not have been enabled
@@ -50,7 +55,7 @@
 	 * let the primary processor know we're out of the
 	 * pen, then head off into the C entry point
 	 */
-	pen_release = -1;
+	write_pen_release(-1);
 
 	/*
 	 * Synchronise with the boot thread.
@@ -74,11 +79,9 @@
 	 * the holding pen - release it, then wait for it to flag
 	 * that it has been released by resetting pen_release.
 	 */
-	pen_release = cpu;
-	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
-	outer_clean_range(__pa(&pen_release), __pa(&pen_release) + 1);
+	write_pen_release(cpu);
 
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
@@ -97,9 +100,6 @@
 
 static void __init wakeup_secondary(void)
 {
-	/* nobody is to be released from the pen yet */
-	pen_release = -1;
-
 	/*
 	 * write the address of secondary startup into the backup ram register
 	 * at offset 0x1FF4, then write the magic number 0xA1FEED01 to the
@@ -126,41 +126,27 @@
  */
 void __init smp_init_cpus(void)
 {
-	unsigned int i, ncores = get_core_count();
+	unsigned int i, ncores;
+
+	ncores = scu_get_core_count(__io_address(UX500_SCU_BASE));
+
+	/* sanity check */
+	if (ncores > NR_CPUS) {
+		printk(KERN_WARNING
+		       "U8500: no. of cores (%d) greater than configured "
+		       "maximum of %d - clipping\n",
+		       ncores, NR_CPUS);
+		ncores = NR_CPUS;
+	}
 
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
 }
 
-void __init smp_prepare_cpus(unsigned int max_cpus)
+void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned int ncores = get_core_count();
-	unsigned int cpu = smp_processor_id();
 	int i;
 
-	/* sanity check */
-	if (ncores == 0) {
-		printk(KERN_ERR
-		       "U8500: strange CM count of 0? Default to 1\n");
-		ncores = 1;
-	}
-
-	if (ncores > num_possible_cpus())	{
-		printk(KERN_WARNING
-		       "U8500: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, num_possible_cpus());
-		ncores = num_possible_cpus();
-	}
-
-	smp_store_cpu_info(cpu);
-
-	/*
-	 * are we trying to boot more cores than exist?
-	 */
-	if (max_cpus > ncores)
-		max_cpus = ncores;
-
 	/*
 	 * Initialise the present map, which describes the set of CPUs
 	 * actually populated at the present time.
@@ -168,13 +154,6 @@
 	for (i = 0; i < max_cpus; i++)
 		set_cpu_present(i, true);
 
-	if (max_cpus > 1) {
-		/*
-		 * Enable the local timer or broadcast device for the
-		 * boot CPU, but only if we have more than one CPU.
-		 */
-		percpu_timer_setup();
-		scu_enable(__io_address(UX500_SCU_BASE));
-		wakeup_secondary();
-	}
+	scu_enable(__io_address(UX500_SCU_BASE));
+	wakeup_secondary();
 }
diff --git a/arch/arm/mach-versatile/Kconfig b/arch/arm/mach-versatile/Kconfig
index c781f30..3f7b5e9 100644
--- a/arch/arm/mach-versatile/Kconfig
+++ b/arch/arm/mach-versatile/Kconfig
@@ -4,6 +4,7 @@
 config ARCH_VERSATILE_PB
 	bool "Support Versatile/PB platform"
 	select CPU_ARM926T
+	select MIGHT_HAVE_PCI
 	default y
 	help
 	  Include support for the ARM(R) Versatile/PB platform.
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index 40a024c..13a83e4 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -31,8 +31,8 @@
 #include <linux/amba/pl022.h>
 #include <linux/io.h>
 #include <linux/gfp.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <asm/system.h>
 #include <asm/irq.h>
 #include <asm/leds.h>
@@ -46,7 +46,6 @@
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 #include <asm/mach/map.h>
-#include <mach/clkdev.h>
 #include <mach/hardware.h>
 #include <mach/platform.h>
 #include <asm/hardware/timer-sp.h>
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 1b71b77..2c0ac7d 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -5,4 +5,5 @@
 obj-y					:= v2m.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
 obj-$(CONFIG_SMP)			+= platsmp.o headsmp.o
+obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
 obj-$(CONFIG_LOCAL_TIMERS)		+= localtimer.o
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index cb5793e..e628402 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -8,8 +8,8 @@
 #include <linux/platform_device.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/clcd.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <asm/pgtable.h>
 #include <asm/hardware/arm_timer.h>
 #include <asm/hardware/cache-l2x0.h>
@@ -18,7 +18,6 @@
 #include <asm/pmu.h>
 #include <asm/smp_twd.h>
 
-#include <mach/clkdev.h>
 #include <mach/ct-ca9x4.h>
 
 #include <asm/hardware/timer-sp.h>
diff --git a/arch/arm/mach-vexpress/hotplug.c b/arch/arm/mach-vexpress/hotplug.c
new file mode 100644
index 0000000..ea4cbfb
--- /dev/null
+++ b/arch/arm/mach-vexpress/hotplug.c
@@ -0,0 +1,128 @@
+/*
+ *  linux/arch/arm/mach-realview/hotplug.c
+ *
+ *  Copyright (C) 2002 ARM Ltd.
+ *  All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/smp.h>
+
+#include <asm/cacheflush.h>
+
+extern volatile int pen_release;
+
+static inline void cpu_enter_lowpower(void)
+{
+	unsigned int v;
+
+	flush_cache_all();
+	asm volatile(
+		"mcr	p15, 0, %1, c7, c5, 0\n"
+	"	mcr	p15, 0, %1, c7, c10, 4\n"
+	/*
+	 * Turn off coherency
+	 */
+	"	mrc	p15, 0, %0, c1, c0, 1\n"
+	"	bic	%0, %0, %3\n"
+	"	mcr	p15, 0, %0, c1, c0, 1\n"
+	"	mrc	p15, 0, %0, c1, c0, 0\n"
+	"	bic	%0, %0, %2\n"
+	"	mcr	p15, 0, %0, c1, c0, 0\n"
+	  : "=&r" (v)
+	  : "r" (0), "Ir" (CR_C), "Ir" (0x40)
+	  : "cc");
+}
+
+static inline void cpu_leave_lowpower(void)
+{
+	unsigned int v;
+
+	asm volatile(
+		"mrc	p15, 0, %0, c1, c0, 0\n"
+	"	orr	%0, %0, %1\n"
+	"	mcr	p15, 0, %0, c1, c0, 0\n"
+	"	mrc	p15, 0, %0, c1, c0, 1\n"
+	"	orr	%0, %0, %2\n"
+	"	mcr	p15, 0, %0, c1, c0, 1\n"
+	  : "=&r" (v)
+	  : "Ir" (CR_C), "Ir" (0x40)
+	  : "cc");
+}
+
+static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
+{
+	/*
+	 * there is no power-control hardware on this platform, so all
+	 * we can do is put the core into WFI; this is safe as the calling
+	 * code will have already disabled interrupts
+	 */
+	for (;;) {
+		/*
+		 * here's the WFI
+		 */
+		asm(".word	0xe320f003\n"
+		    :
+		    :
+		    : "memory", "cc");
+
+		if (pen_release == cpu) {
+			/*
+			 * OK, proper wakeup, we're done
+			 */
+			break;
+		}
+
+		/*
+		 * Getting here, means that we have come out of WFI without
+		 * having been woken up - this shouldn't happen
+		 *
+		 * Just note it happening - when we're woken, we can report
+		 * its occurrence.
+		 */
+		(*spurious)++;
+	}
+}
+
+int platform_cpu_kill(unsigned int cpu)
+{
+	return 1;
+}
+
+/*
+ * platform-specific code to shutdown a CPU
+ *
+ * Called with IRQs disabled
+ */
+void platform_cpu_die(unsigned int cpu)
+{
+	int spurious = 0;
+
+	/*
+	 * we're ready for shutdown now, so do it
+	 */
+	cpu_enter_lowpower();
+	platform_do_lowpower(cpu, &spurious);
+
+	/*
+	 * bring this CPU back into the world of cache
+	 * coherency, and then restore interrupts
+	 */
+	cpu_leave_lowpower();
+
+	if (spurious)
+		pr_warn("CPU%u: %u spurious wakeup calls\n", cpu, spurious);
+}
+
+int platform_cpu_disable(unsigned int cpu)
+{
+	/*
+	 * we don't allow CPU 0 to be shutdown (it is still too special
+	 * e.g. clock tick interrupts)
+	 */
+	return cpu == 0 ? -EPERM : 0;
+}
diff --git a/arch/arm/mach-vexpress/include/mach/smp.h b/arch/arm/mach-vexpress/include/mach/smp.h
index 5a6da4f..4c05e4a 100644
--- a/arch/arm/mach-vexpress/include/mach/smp.h
+++ b/arch/arm/mach-vexpress/include/mach/smp.h
@@ -2,13 +2,12 @@
 #define __MACH_SMP_H
 
 #include <asm/hardware/gic.h>
-#include <asm/smp_mpidr.h>
 
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 #endif
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index dfb5910..b1687b6 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -17,7 +17,6 @@
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
-#include <asm/localtimer.h>
 #include <asm/smp_scu.h>
 #include <asm/unified.h>
 
@@ -35,6 +34,19 @@
  */
 volatile int __cpuinitdata pen_release = -1;
 
+/*
+ * Write pen_release in a way that is guaranteed to be visible to all
+ * observers, irrespective of whether they're taking part in coherency
+ * or not.  This is necessary for the hotplug code to work reliably.
+ */
+static void write_pen_release(int val)
+{
+	pen_release = val;
+	smp_wmb();
+	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
+	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
+}
+
 static void __iomem *scu_base_addr(void)
 {
 	return MMIO_P2V(A9_MPCORE_SCU);
@@ -44,8 +56,6 @@
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
-	trace_hardirqs_off();
-
 	/*
 	 * if any interrupts are already enabled for the primary
 	 * core (e.g. timer irq), then they will not have been enabled
@@ -57,8 +67,7 @@
 	 * let the primary processor know we're out of the
 	 * pen, then head off into the C entry point
 	 */
-	pen_release = -1;
-	smp_wmb();
+	write_pen_release(-1);
 
 	/*
 	 * Synchronise with the boot thread.
@@ -83,16 +92,14 @@
 	 * since we haven't sent them a soft interrupt, they shouldn't
 	 * be there.
 	 */
-	pen_release = cpu;
-	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
-	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
+	write_pen_release(cpu);
 
 	/*
 	 * Send the secondary CPU a soft interrupt, thereby causing
 	 * the boot monitor to read the system wide flags register,
 	 * and branch to the address found there.
 	 */
-	smp_cross_call(cpumask_of(cpu));
+	smp_cross_call(cpumask_of(cpu), 1);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
@@ -124,13 +131,6 @@
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores == 0) {
-		printk(KERN_ERR
-		       "vexpress: strange CM count of 0? Default to 1\n");
-
-		ncores = 1;
-	}
-
 	if (ncores > NR_CPUS) {
 		printk(KERN_WARNING
 		       "vexpress: no. of cores (%d) greater than configured "
@@ -143,20 +143,10 @@
 		set_cpu_possible(i, true);
 }
 
-void __init smp_prepare_cpus(unsigned int max_cpus)
+void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned int ncores = num_possible_cpus();
-	unsigned int cpu = smp_processor_id();
 	int i;
 
-	smp_store_cpu_info(cpu);
-
-	/*
-	 * are we trying to boot more cores than exist?
-	 */
-	if (max_cpus > ncores)
-		max_cpus = ncores;
-
 	/*
 	 * Initialise the present map, which describes the set of CPUs
 	 * actually populated at the present time.
@@ -164,27 +154,15 @@
 	for (i = 0; i < max_cpus; i++)
 		set_cpu_present(i, true);
 
+	scu_enable(scu_base_addr());
+
 	/*
-	 * Initialise the SCU if there are more than one CPU and let
-	 * them know where to start.
+	 * Write the address of secondary startup into the
+	 * system-wide flags register. The boot monitor waits
+	 * until it receives a soft interrupt, and then the
+	 * secondary CPU branches to this address.
 	 */
-	if (max_cpus > 1) {
-		/*
-		 * Enable the local timer or broadcast device for the
-		 * boot CPU, but only if we have more than one CPU.
-		 */
-		percpu_timer_setup();
-
-		scu_enable(scu_base_addr());
-
-		/*
-		 * Write the address of secondary startup into the
-		 * system-wide flags register. The boot monitor waits
-		 * until it receives a soft interrupt, and then the
-		 * secondary CPU branches to this address.
-		 */
-		writel(~0, MMIO_P2V(V2M_SYS_FLAGSCLR));
-		writel(BSYM(virt_to_phys(vexpress_secondary_startup)),
-			MMIO_P2V(V2M_SYS_FLAGSSET));
-	}
+	writel(~0, MMIO_P2V(V2M_SYS_FLAGSCLR));
+	writel(BSYM(virt_to_phys(vexpress_secondary_startup)),
+		MMIO_P2V(V2M_SYS_FLAGSSET));
 }
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index de13603..a9ed342 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -11,8 +11,8 @@
 #include <linux/spinlock.h>
 #include <linux/sysdev.h>
 #include <linux/usb/isp1760.h>
+#include <linux/clkdev.h>
 
-#include <asm/clkdev.h>
 #include <asm/sizes.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
@@ -20,7 +20,6 @@
 #include <asm/hardware/arm_timer.h>
 #include <asm/hardware/timer-sp.h>
 
-#include <mach/clkdev.h>
 #include <mach/motherboard.h>
 
 #include <plat/sched_clock.h>
diff --git a/arch/arm/mach-w90x900/clock.h b/arch/arm/mach-w90x900/clock.h
index c56ddab..b88a1b1 100644
--- a/arch/arm/mach-w90x900/clock.h
+++ b/arch/arm/mach-w90x900/clock.h
@@ -10,7 +10,7 @@
  * the Free Software Foundation; either version 2 of the License.
  */
 
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 void nuc900_clk_enable(struct clk *clk, int enable);
 void nuc900_subclk_enable(struct clk *clk, int enable);
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 4414a01..8493ed0 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -599,6 +599,14 @@
 	help
 	  Processor has the CP15 register, which has MPU related registers.
 
+config CPU_USE_DOMAINS
+	bool
+	depends on MMU
+	default y if !CPU_32v6K
+	help
+	  This option enables or disables the use of domain switching
+	  via the set_fs() function.
+
 #
 # CPU supports 36-bit I/O
 #
@@ -628,6 +636,33 @@
 	  Say Y here if you have a CPU with the ThumbEE extension and code to
 	  make use of it. Say N for code that can run on CPUs without ThumbEE.
 
+config SWP_EMULATE
+	bool "Emulate SWP/SWPB instructions"
+	depends on CPU_V7
+	select HAVE_PROC_CPU if PROC_FS
+	default y if SMP
+	help
+	  ARMv6 architecture deprecates use of the SWP/SWPB instructions.
+	  ARMv7 multiprocessing extensions introduce the ability to disable
+	  these instructions, triggering an undefined instruction exception
+	  when executed. Say Y here to enable software emulation of these
+	  instructions for userspace (not kernel) using LDREX/STREX.
+	  Also creates /proc/cpu/swp_emulation for statistics.
+
+	  In some older versions of glibc [<=2.8] SWP is used during futex
+	  trylock() operations with the assumption that the code will not
+	  be preempted. This invalid assumption may be more likely to fail
+	  with SWP emulation enabled, leading to deadlock of the user
+	  application.
+
+	  NOTE: when accessing uncached shared regions, LDREX/STREX rely
+	  on an external transaction monitoring block called a global
+	  monitor to maintain update atomicity. If your system does not
+	  implement a global monitor, this option can cause programs that
+	  perform SWP operations to uncached memory to deadlock.
+
+	  If unsure, say Y.
+
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
 	depends on ARCH_SUPPORTS_BIG_ENDIAN
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 809f1bf..6b48e0a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -312,7 +312,7 @@
 		addr = page_address(page);
 
 	if (addr)
-		*handle = page_to_dma(dev, page);
+		*handle = pfn_to_dma(dev, page_to_pfn(page));
 
 	return addr;
 }
@@ -407,7 +407,7 @@
 	if (!arch_is_coherent())
 		__dma_free_remap(cpu_addr, size);
 
-	__dma_free_buffer(dma_to_page(dev, handle), size);
+	__dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
 }
 EXPORT_SYMBOL(dma_free_coherent);
 
@@ -555,17 +555,20 @@
 	struct scatterlist *s;
 	int i, j;
 
+	BUG_ON(!valid_dma_direction(dir));
+
 	for_each_sg(sg, s, nents, i) {
-		s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
+		s->dma_address = __dma_map_page(dev, sg_page(s), s->offset,
 						s->length, dir);
 		if (dma_mapping_error(dev, s->dma_address))
 			goto bad_mapping;
 	}
+	debug_dma_map_sg(dev, sg, nents, nents, dir);
 	return nents;
 
  bad_mapping:
 	for_each_sg(sg, s, i, j)
-		dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+		__dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
 	return 0;
 }
 EXPORT_SYMBOL(dma_map_sg);
@@ -586,8 +589,10 @@
 	struct scatterlist *s;
 	int i;
 
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+
 	for_each_sg(sg, s, nents, i)
-		dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+		__dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
 }
 EXPORT_SYMBOL(dma_unmap_sg);
 
@@ -612,6 +617,8 @@
 		__dma_page_dev_to_cpu(sg_page(s), s->offset,
 				      s->length, dir);
 	}
+
+	debug_dma_sync_sg_for_cpu(dev, sg, nents, dir);
 }
 EXPORT_SYMBOL(dma_sync_sg_for_cpu);
 
@@ -636,5 +643,16 @@
 		__dma_page_cpu_to_dev(sg_page(s), s->offset,
 				      s->length, dir);
 	}
+
+	debug_dma_sync_sg_for_device(dev, sg, nents, dir);
 }
 EXPORT_SYMBOL(dma_sync_sg_for_device);
+
+#define PREALLOC_DMA_DEBUG_ENTRIES	4096
+
+static int __init dma_debug_do_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	return 0;
+}
+fs_initcall(dma_debug_do_init);
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 55c17a6..ab50627 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -204,12 +204,8 @@
 	/*
 	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
 	 */
-	if (pfn_valid(pfn)) {
-		printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory.  This leads\n"
-		       "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n"
-		       "will fail in the next kernel release.  Please fix your driver.\n");
-		WARN_ON(1);
-	}
+	if (WARN_ON(pfn_valid(pfn)))
+		return NULL;
 
 	type = get_mem_type(mtype);
 	if (!type)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 72ad3e1..79c01f5 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -24,6 +24,7 @@
 #include <asm/smp_plat.h>
 #include <asm/tlb.h>
 #include <asm/highmem.h>
+#include <asm/traps.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -914,12 +915,11 @@
 {
 	struct map_desc map;
 	unsigned long addr;
-	void *vectors;
 
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors = early_alloc(PAGE_SIZE);
+	vectors_page = early_alloc(PAGE_SIZE);
 
 	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -959,7 +959,7 @@
 	 * location (0xffff0000).  If we aren't using high-vectors, also
 	 * create a mapping at the low-vectors virtual address.
 	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
+	map.pfn = __phys_to_pfn(virt_to_phys(vectors_page));
 	map.virtual = 0xffff0000;
 	map.length = PAGE_SIZE;
 	map.type = MT_HIGH_VECTORS;
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index b795afd..f8f777d 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -109,6 +109,10 @@
  *  110x   0   1   0	r/w	r/o
  *  11x0   0   1   0	r/w	r/o
  *  1111   0   1   1	r/w	r/w
+ *
+ * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
+ *  110x   1   1   1	r/o	r/o
+ *  11x0   1   1   1	r/o	r/o
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:
@@ -148,8 +152,11 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
 	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
 	tst	r1, #L_PTE_EXEC
 	orreq	r3, r3, #PTE_EXT_XN
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 9b9ff5d..7401f4d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -148,8 +148,11 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
 	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
 	tst	r1, #L_PTE_EXEC
 	orreq	r3, r3, #PTE_EXT_XN
@@ -273,8 +276,6 @@
 	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
-	mov	r10, #0x1f			@ domains 0, 1 = manager
-	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
 	/*
 	 * Memory region attributes with SCTLR.TRE=1
 	 *
@@ -313,6 +314,10 @@
 #ifdef CONFIG_CPU_ENDIAN_BE8
 	orr	r6, r6, #1 << 25		@ big-endian page tables
 #endif
+#ifdef CONFIG_SWP_EMULATE
+	orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
+	bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"
+#endif
    	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig
index 92c5bb7..c940843 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -11,13 +11,13 @@
 
 config ARCH_OMAP1
 	bool "TI OMAP1"
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	help
 	  "Systems based on omap7xx, omap15xx or omap16xx"
 
 config ARCH_OMAP2PLUS
 	bool "TI OMAP2/3/4"
-	select COMMON_CLKDEV
+	select CLKDEV_LOOKUP
 	help
 	  "Systems based on OMAP2, OMAP3 or OMAP4"
 
diff --git a/arch/arm/plat-omap/include/plat/clkdev_omap.h b/arch/arm/plat-omap/include/plat/clkdev_omap.h
index bb937f3..4b2028a 100644
--- a/arch/arm/plat-omap/include/plat/clkdev_omap.h
+++ b/arch/arm/plat-omap/include/plat/clkdev_omap.h
@@ -8,7 +8,7 @@
 #ifndef __ARCH_ARM_PLAT_OMAP_INCLUDE_PLAT_CLKDEV_OMAP_H
 #define __ARCH_ARM_PLAT_OMAP_INCLUDE_PLAT_CLKDEV_OMAP_H
 
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 
 struct omap_clk {
 	u16				cpu;
diff --git a/arch/arm/plat-omap/include/plat/memory.h b/arch/arm/plat-omap/include/plat/memory.h
index d5306be..f8d922f 100644
--- a/arch/arm/plat-omap/include/plat/memory.h
+++ b/arch/arm/plat-omap/include/plat/memory.h
@@ -61,17 +61,17 @@
 #define lbus_to_virt(x)		((x) - OMAP1510_LB_OFFSET + PAGE_OFFSET)
 #define is_lbus_device(dev)	(cpu_is_omap15xx() && dev && (strncmp(dev_name(dev), "ohci", 4) == 0))
 
-#define __arch_page_to_dma(dev, page)	\
-	({ dma_addr_t __dma = page_to_phys(page); \
+#define __arch_pfn_to_dma(dev, pfn)	\
+	({ dma_addr_t __dma = __pfn_to_phys(pfn); \
 	   if (is_lbus_device(dev)) \
 		__dma = __dma - PHYS_OFFSET + OMAP1510_LB_OFFSET; \
 	   __dma; })
 
-#define __arch_dma_to_page(dev, addr)	\
+#define __arch_dma_to_pfn(dev, addr)	\
 	({ dma_addr_t __dma = addr;				\
 	   if (is_lbus_device(dev))				\
 		__dma += PHYS_OFFSET - OMAP1510_LB_OFFSET;	\
-	   phys_to_page(__dma);					\
+	   __phys_to_pfn(__dma);				\
 	})
 
 #define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
diff --git a/arch/arm/plat-omap/include/plat/smp.h b/arch/arm/plat-omap/include/plat/smp.h
index ecd6a48..7a10257 100644
--- a/arch/arm/plat-omap/include/plat/smp.h
+++ b/arch/arm/plat-omap/include/plat/smp.h
@@ -18,7 +18,6 @@
 #define OMAP_ARCH_SMP_H
 
 #include <asm/hardware/gic.h>
-#include <asm/smp_mpidr.h>
 
 /* Needed for secondary core boot */
 extern void omap_secondary_startup(void);
@@ -29,9 +28,9 @@
 /*
  * We use Soft IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/plat-spear/include/plat/clock.h b/arch/arm/plat-spear/include/plat/clock.h
index 298bafc..2572260 100644
--- a/arch/arm/plat-spear/include/plat/clock.h
+++ b/arch/arm/plat-spear/include/plat/clock.h
@@ -15,7 +15,7 @@
 #define __PLAT_CLOCK_H
 
 #include <linux/list.h>
-#include <asm/clkdev.h>
+#include <linux/clkdev.h>
 #include <linux/types.h>
 
 /* clk structure flags */
diff --git a/arch/arm/plat-stmp3xxx/clock.c b/arch/arm/plat-stmp3xxx/clock.c
index e593a2a..2e712e1 100644
--- a/arch/arm/plat-stmp3xxx/clock.c
+++ b/arch/arm/plat-stmp3xxx/clock.c
@@ -25,9 +25,9 @@
 #include <linux/err.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/clkdev.h>
 
 #include <asm/mach-types.h>
-#include <asm/clkdev.h>
 #include <mach/platform.h>
 #include <mach/regs-clkctrl.h>
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 8063a32..0797cb5 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -10,9 +10,12 @@
  */
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/cpu.h>
 #include <linux/kernel.h>
+#include <linux/notifier.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/init.h>
 
 #include <asm/cputype.h>
@@ -484,7 +487,24 @@
 	put_cpu();
 }
 
-#include <linux/smp.h>
+/*
+ * VFP hardware can lose all context when a CPU goes offline.
+ * Safely clear our held state when a CPU has been killed, and
+ * re-enable access to VFP when the CPU comes back online.
+ *
+ * Both CPU_DYING and CPU_STARTING are called on the CPU which
+ * is being offlined/onlined.
+ */
+static int vfp_hotplug(struct notifier_block *b, unsigned long action,
+	void *hcpu)
+{
+	if (action == CPU_DYING || action == CPU_DYING_FROZEN) {
+		unsigned int cpu = (long)hcpu;
+		last_VFP_context[cpu] = NULL;
+	} else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+		vfp_enable(NULL);
+	return NOTIFY_OK;
+}
 
 /*
  * VFP support code initialisation.
@@ -514,6 +534,8 @@
 	else if (vfpsid & FPSID_NODOUBLE) {
 		printk("no double precision support\n");
 	} else {
+		hotcpu_notifier(vfp_hotplug, 0);
+
 		smp_call_function(vfp_enable, NULL, 1);
 
 		VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT;  /* Extract the architecture version */