Merge branch 'misc' into devel

Conflicts:
	arch/arm/Kconfig
	arch/arm/common/Makefile
	arch/arm/kernel/Makefile
	arch/arm/kernel/smp.c

119 files changed, 1514 insertions, 1263 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2e86b8f62104..32cbf3e888ff 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -2,6 +2,7 @@ config ARM
         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 ARM
 config HAVE_PWM
         bool
 
+config MIGHT_HAVE_PCI
+        bool
+
 config SYS_SUPPORTS_APM_EMULATION
         bool
 
@@ -226,7 +230,7 @@ config ARCH_INTEGRATOR
         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_INTEGRATOR
 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 @@ config ARCH_VERSATILE
         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 @@ config ARCH_VEXPRESS
         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 @@ config ARCH_BCMRING
         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 @@ config ARCH_CNS3XXX
         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 @@ config ARCH_EP93XX
         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 @@ config ARCH_MXC
         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 @@ config ARCH_IXP4XX
         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 @@ config ARCH_LPC32XX
         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 @@ config ARCH_MMP
         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 @@ config ARCH_W90X900
         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_W90X900
 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_TEGRA
 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 @@ config ARCH_PXA
         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 @@ config ARCH_TCC_926
         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 @@ config ARCH_U300
         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 @@ config ARCH_U8500
         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 @@ config ARCH_NOMADIK
         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 @@ config ARCH_DAVINCI
         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 @@ config PLAT_SPEAR
         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 @@ config CPU_HAS_PMU
         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 @@ config ISA_DMA_API
         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
 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_SCU
 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 @@ config HZ
         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 SECCOMP
 
 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 @@ config CPU_FREQ_S3C
           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 @@ config CPU_FREQ_S3C24XX
           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 eac62085f5b2..494224a9b459 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -31,7 +31,7 @@ config FRAME_POINTER
           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 0a34c8186924..778655f0257a 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -37,7 +37,3 @@ config SHARP_PARAM
 
 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 e2b2bb66e094..000000000000
--- 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 cc0a932bbea9..e5681636626f 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -328,7 +328,7 @@ static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
  * 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 @@ dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
 
         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 @@ EXPORT_SYMBOL(dma_map_single);
  * 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 @@ void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 
         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 @@ dma_addr_t dma_map_page(struct device *dev, struct page *page,
 
         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 @@ EXPORT_SYMBOL(dma_map_page);
  * 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 @@ void dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 
         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 749bb6622404..bc2d2d75f706 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 9d6122096fbe..75fe66bc02b4 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 b56c1389b6fa..765d33222369 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 c568da7dcae4..4fff837363ed 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 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
         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 @@ extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
 /*
  * 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 int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
 }
 
 
+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 int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
 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_single(struct device *dev, void *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_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 dma_addr_t dma_map_page(struct device *dev, struct page *page,
 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_single(struct device *dev, dma_addr_t handle,
 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 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
 {
         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 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 {
         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 cc7ef4080711..af18ceaacf5d 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 000000000000..ec0bbf79c71f
--- /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 540a044153a5..b33fe7065b38 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 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
         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 6d7485aff955..89ad1805e579 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 50c7e7cfd670..6bc63ab498ce 100644
--- a/arch/arm/include/asm/localtimer.h
+++ b/arch/arm/include/asm/localtimer.h
@@ -30,7 +30,6 @@ asmlinkage void do_local_timer(struct pt_regs *);
 #include "smp_twd.h"
 
 #define local_timer_ack()       twd_timer_ack()
-#define local_timer_stop()      twd_timer_stop()
 
 #else
 
@@ -40,11 +39,6 @@ asmlinkage void do_local_timer(struct pt_regs *);
  */
 int local_timer_ack(void);
 
-/*
- * Stop a local timer interrupt.
- */
-void local_timer_stop(void);
-
 #endif
 
 /*
@@ -52,12 +46,6 @@ void local_timer_stop(void);
  */
 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 d97a964207fa..3a0893a76a3b 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -37,12 +37,21 @@ struct machine_desc {
                                          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 ce3eee9fe26c..22ac140edd9e 100644
--- a/arch/arm/include/asm/mach/irq.h
+++ b/arch/arm/include/asm/mach/irq.h
@@ -17,10 +17,12 @@ struct seq_file;
 /*
  * 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 35d408f6dccf..883f6be5117a 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -43,7 +43,6 @@ struct sys_timer {
 #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 3d05190797cb..96ed521f2408 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -33,27 +33,23 @@ struct seq_file;
 /*
  * 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 @@ asmlinkage void secondary_start_kernel(void);
 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 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 /*
  * 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 6a9307d64900..000000000000
--- 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 634f357be6bb..fed9981fba08 100644
--- a/arch/arm/include/asm/smp_twd.h
+++ b/arch/arm/include/asm/smp_twd.h
@@ -22,7 +22,6 @@ struct clock_event_device;
 
 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 3222ab8b3447..97f6d60297d5 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -124,6 +124,13 @@ extern unsigned int user_debug;
 #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 124475afb007..1b960d5ef6a5 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -46,4 +46,6 @@ static inline int in_exception_text(unsigned long ptr)
 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 33e4a48fe103..b293616a1a1a 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -227,7 +227,7 @@ do {									\
 
 #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 @@ do {									\
 
 #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 @@ do {									\
 
 #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 @@ do {									\
 
 #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 @@ do {									\
 
 #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 fd3ec49bfba6..7c33e6f29bcc 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -30,7 +30,7 @@ obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(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_KGDB)		+= kgdb.o
 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 bb96a7d4bbf5..27f64489c1cb 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 @@ ENTRY(__switch_to)
  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 @@ ENTRY(__switch_to)
         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_helper_start:
  */
 
 __kuser_memory_barrier:                         @ 0xffff0fa0
-        smp_dmb
+        smp_dmb arm
         usr_ret lr
 
         .align  5
@@ -959,7 +939,7 @@ kuser_cmpxchg_fixup:
 
 #else
 
-        smp_dmb
+        smp_dmb arm
 1:      ldrex   r3, [r2]
         subs    r3, r3, r0
         strexeq r3, r1, [r2]
@@ -1245,3 +1225,9 @@ cr_alignment:
         .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 6ff7919613d7..e72dc34eea1c 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 default_owner = {
 
 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 6bd82d25683c..f17d9a09e8fb 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -91,6 +91,11 @@ ENTRY(stext)
         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 @@ ENDPROC(__turn_mmu_on)
 
 #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:
 
 __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 6d616333340f..8135438b8818 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 @@ int show_interrupts(struct seq_file *p, void *v)
         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 @@ int show_interrupts(struct seq_file *p, void *v)
                 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 @@ unlock:
                 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
+#ifdef CONFIG_LOCAL_TIMERS
+                show_local_irqs(p, prec);
 #endif
-                seq_printf(p, "Err: %10lu\n", irq_err_count);
+                seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
         }
         return 0;
 }
@@ -156,13 +166,13 @@ void set_irq_flags(unsigned int irq, unsigned int iflags)
 
 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 336f14e0e5c2..3455ad33de4c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -75,9 +75,9 @@ extern void reboot_setup(char *str);
 
 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 @@ EXPORT_SYMBOL(system_serial_low);
 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 @@ EXPORT_SYMBOL(elf_platform);
 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 @@ static struct init_tags {
         { 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 @@ void __init setup_arch(char **cmdline_p)
 
         setup_processor();
         mdesc = setup_machine(machine_arch_type);
+        machine_desc = mdesc;
         machine_name = mdesc->name;
 
         if (mdesc->soft_reboot)
@@ -868,13 +868,9 @@ void __init setup_arch(char **cmdline_p)
         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 @@ void __init setup_arch(char **cmdline_p)
 #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 b6b78b22031b..5ec79b4ff950 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 @@ int __cpuinit __cpu_up(unsigned int cpu)
                         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 @@ int __cpuinit __cpu_up(unsigned int cpu)
 
         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 @@ int __cpu_disable(void)
         /*
          * 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 @@ int __cpu_disable(void)
         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 @@ void __ref cpu_die(void)
 {
         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 @@ void __ref cpu_die(void)
          * 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 @@ void __ref cpu_die(void)
 #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 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 
         cpu_init();
         preempt_disable();
+        trace_hardirqs_off();
 
         /*
          * Give the platform a chance to do its own initialisation.
@@ -353,17 +363,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
         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 @@ void __init smp_prepare_boot_cpu(void)
         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;
-
-        local_irq_save(flags);
+        unsigned int ncores = num_possible_cpus();
 
-        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;
+
+        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();
 
-        local_irq_restore(flags);
+                /*
+                 * 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 @@ asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs)
         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 @@ void __cpuinit percpu_timer_setup(void)
         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);
 
 /*
@@ -537,216 +582,76 @@ static void ipi_cpu_stop(unsigned int cpu)
 
 /*
  * 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++;
-
-        for (;;) {
-                unsigned long msgs;
+        if (ipinr >= IPI_TIMER && ipinr < IPI_TIMER + NR_IPI)
+                __inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_TIMER]);
 
-                spin_lock(&ipi->lock);
-                msgs = ipi->bits;
-                ipi->bits = 0;
-                spin_unlock(&ipi->lock);
-
-                if (!msgs)
-                        break;
-
-                do {
-                        unsigned nextmsg;
-
-                        nextmsg = msgs & -msgs;
-                        msgs &= ~nextmsg;
-                        nextmsg = ffz(~nextmsg);
-
-                        switch (nextmsg) {
-                        case IPI_TIMER:
-                                ipi_timer();
-                                break;
+        switch (ipinr) {
+        case IPI_TIMER:
+                ipi_timer();
+                break;
 
-                        case IPI_RESCHEDULE:
-                                /*
-                                 * nothing more to do - eveything is
-                                 * done on the interrupt return path
-                                 */
-                                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:
+                generic_smp_call_function_interrupt();
+                break;
 
-                        case IPI_CALL_FUNC_SINGLE:
-                                generic_smp_call_function_single_interrupt();
-                                break;
+        case IPI_CALL_FUNC_SINGLE:
+                generic_smp_call_function_single_interrupt();
+                break;
 
-                        case IPI_CPU_STOP:
-                                ipi_cpu_stop(cpu);
-                                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;
 
-/*
- * not supported here
- */
-int setup_profiling_timer(unsigned int multiplier)
-{
-        return -EINVAL;
-}
+        if (num_online_cpus() > 1) {
+                cpumask_t mask = cpu_online_map;
+                cpu_clear(smp_processor_id(), mask);
 
-static void
-on_each_cpu_mask(void (*func)(void *), void *info, int wait,
-                const struct cpumask *mask)
-{
-        preempt_disable();
+                smp_cross_call(&mask, IPI_CPU_STOP);
+        }
 
-        smp_call_function_many(mask, func, info, wait);
-        if (cpumask_test_cpu(smp_processor_id(), mask))
-                func(info);
+        /* Wait up to one second for other CPUs to stop */
+        timeout = USEC_PER_SEC;
+        while (num_online_cpus() > 1 && timeout--)
+                udelay(1);
 
-        preempt_enable();
+        if (num_online_cpus() > 1)
+                pr_warning("SMP: failed to stop secondary CPUs\n");
 }
 
-/**********************************************************************/
-
 /*
- * TLB operations
+ * not supported here
  */
-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)
+int setup_profiling_timer(unsigned int multiplier)
 {
-        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);
+        return -EINVAL;
 }
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
new file mode 100644
index 000000000000..7dcb35285be7
--- /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 67f933ec4177..dd790745b3ef 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -145,13 +145,3 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 
         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 000000000000..7a5760922914
--- /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 38c261f9951c..f1e2eb19a67d 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 @@ device_initcall(timer_init_sysfs);
 
 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 446aee97436f..e02f4f7537c5 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 @@ static void __init kuser_get_tls_init(unsigned long vectors)
 
 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 @@ void __init early_trap_init(void)
          * 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 897c1a8f1694..86b66f3f2031 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -168,6 +168,7 @@ SECTIONS
 
                 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 b1631a7dbe75..1b049cd7a49a 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 @@ ENTRY(__get_user_2)
 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 5a01a23c6c06..c023fc11e86c 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 @@ ENTRY(__put_user_2)
         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 @@ ENTRY(__put_user_2)
 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 fee9f6f88adb..d0ece2aeb70d 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 @@ ENTRY(__copy_to_user)
                 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 @@ USER(		strt	r3, [r0], #4)			@ May fault
                 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 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
                 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 @@ USER(		strt	r3, [r0], #4)			@ May fault
                 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 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
                 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 @@ USER(		strt	r3, [r0], #4)			@ May fault
                 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 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
                 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 @@ USER(		strt	r3, [r0], #4)			@ May fault
                 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 @@ ENDPROC(__copy_to_user)
 .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 @@ ENTRY(__copy_from_user)
 .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 @@ USER(		ldrt	r3, [r1], #4)
                 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 @@ USER(		ldrgtbt	r3, [r1], #1)			@ May fault
 
 .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 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
                 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 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
                 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 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
                 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 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
                 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 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
                 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 @@ USER(		ldrgtbt	r3, [r1], #0)			@ May fault
                 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 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
                 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 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
                 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 14bafc38f2dc..ad237a42d265 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 b91b1b0fdff3..8fc2035759fb 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 9ebfcc46feb1..29b13f249aa9 100644
--- a/arch/arm/mach-cns3xxx/Kconfig
+++ b/arch/arm/mach-cns3xxx/Kconfig
@@ -3,6 +3,7 @@ menu "CNS3XXX platform type"
 
 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 11099980b58b..0dd22031ec62 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 ef06c66a6f16..ca4de7105097 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 daca30b2d5b1..3938a563b280 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 cf15ea516a72..d7056559715a 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 98a25bada783..ca1017b9028d 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 27db275b367c..769b0f10c834 100644
--- a/arch/arm/mach-integrator/Kconfig
+++ b/arch/arm/mach-integrator/Kconfig
@@ -4,6 +4,7 @@ menu "Integrator Options"
 
 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 8f4fb6d638f7..b8e884b450da 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 fd684bf205e5..5db574f8ae3f 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 1713ecf0c95f..85e48a5f77b9 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 7415e4338651..3ad455318868 100644
--- a/arch/arm/mach-iop13xx/include/mach/memory.h
+++ b/arch/arm/mach-iop13xx/include/mach/memory.h
@@ -58,13 +58,13 @@ static inline unsigned long __lbus_to_virt(dma_addr_t x)
                 __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 fe0c82e30b2d..f5c39a8c2b00 100644
--- a/arch/arm/mach-ks8695/Kconfig
+++ b/arch/arm/mach-ks8695/Kconfig
@@ -4,6 +4,7 @@ menu "Kendin/Micrel KS8695 Implementations"
 
 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 ffa19aae6e05..bace9a681adc 100644
--- a/arch/arm/mach-ks8695/include/mach/memory.h
+++ b/arch/arm/mach-ks8695/include/mach/memory.h
@@ -35,17 +35,17 @@ extern struct bus_type platform_bus_type;
                                         __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 32d63796430a..da0e6498110a 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 016ae94691c0..9b027d7491f5 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 3ff7bf5e679e..a95f7b9efe31 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 9e4a5578c2fb..00dcb08019e9 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 109e98f323e0..1cd8b40b7676 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 61e4a318980a..819dd809615a 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 8ac36d882927..5975edb47de8 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 5c85075d8a56..9fab505f1eb1 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 89f793adf776..48a59f24e10c 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 18e51be4816f..4de1f1da9dc5 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 b8c7fb9d7921..84ef70476b51 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 ed8d330522f1..ebb888f59365 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 6cee456ca542..4976b9393e49 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 @@ int platform_cpu_kill(unsigned int cpu)
  */
 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 9fbac2c39104..b66cfe8bc464 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 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
         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 @@ void __init smp_init_cpus(void)
         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 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
                        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 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         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 9d1975fa4d9f..a4a3819c96cb 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 c93e73d54dd1..c98d81ff250c 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -94,6 +94,7 @@ config MACH_ARMCORE
         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 abba0089a2ae..4e4a84be96ba 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 d8488742b807..12cc0e87e6c4 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 aad806c5cb12..1c6602cf50e4 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 f95521a5e5ce..a87523d095e6 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 @@ static inline void cpu_enter_lowpower(void)
         "       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 @@ static inline void cpu_leave_lowpower(void)
         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 @@ static inline void platform_do_lowpower(unsigned int cpu)
                 }
 
                 /*
-                 * 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 @@ int platform_cpu_kill(unsigned int cpu)
  */
 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 d3cd265cb058..c8221b38ee7c 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 6da8a2e53c44..a22bf67f2f78 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 @@ extern void realview_secondary_startup(void);
  */
 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 @@ static void __iomem *scu_base_addr(void)
                 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 @@ void __cpuinit platform_secondary_init(unsigned int cpu)
          * 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 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
          * 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 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
         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 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
                 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 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         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. 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
+         * 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.
          */
-        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());
-                poke_milo();
-        }
+        __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 6983cb4d4cae..e82ab4aa7ab9 100644
--- a/arch/arm/mach-s3c2412/Kconfig
+++ b/arch/arm/mach-s3c2412/Kconfig
@@ -59,7 +59,7 @@ config MACH_JIVE
           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 03652c3605f6..afa5392d9fc0 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 @@ static inline void cpu_enter_lowpower(void)
          * 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 @@ static inline void cpu_leave_lowpower(void)
 
         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 @@ static inline void platform_do_lowpower(unsigned int cpu)
                 }
 
                 /*
-                 * 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 @@ int platform_cpu_kill(unsigned int cpu)
  */
 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 e1cc6a251c6a..393ccbd52c4a 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 15929c169f81..34093b069f67 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 @@ extern void s5pv310_secondary_startup(void);
 
 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 @@ 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
@@ -60,8 +70,7 @@ void __cpuinit platform_secondary_init(unsigned int cpu)
          * 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 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
          * 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 @@ void __init smp_init_cpus(void)
         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 @@ void __init smp_init_cpus(void)
                 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 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         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 51dcd59eda6a..632933357242 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -6,7 +6,7 @@ config ARCH_SH7367
         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 @@ config ARCH_SH7377
         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 @@ config ARCH_SH7372
         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 9f78729098f2..6b186aefcbd6 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 3aa026069435..d98deb497c2f 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 f91395aeb9ab..95942466e63f 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 ba32a15127ab..3970a9cdce26 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 ae19f95585be..77948e0f4909 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 94fd859770f1..083a4cfc6cf0 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 8e7f115aa21e..a5cb1ce76ff2 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 @@ static inline void cpu_enter_lowpower(void)
          * 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 @@ static inline void cpu_leave_lowpower(void)
 
         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 @@ static inline void platform_do_lowpower(unsigned int cpu)
                 /*}*/
 
                 /*
-                 * 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 @@ int platform_cpu_kill(unsigned int cpu)
  */
 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 e4a34a35a544..c8221b38ee7c 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)
-{
-        gic_raise_softirq(mask, 1);
-}
-
-/*
- * Do nothing on MPcore.
- */
-static inline void smp_cross_call_done(cpumask_t callmap)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
+        gic_raise_softirq(mask, ipi);
 }
 
 #endif
diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c
index 3b7376c4f356..ec1f68924edf 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 @@ static void __iomem *scu_base = IO_ADDRESS(TEGRA_ARM_PERIF_BASE);
 
 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 @@ void __init smp_init_cpus(void)
 {
         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 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         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 ae3b308e22a4..f0dae6d8ba52 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 7458fc6df5c6..fabcc49abe80 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 1675047daf20..531de5c63641 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 a6be2cdf2b2f..64fa451edcfd 100644
--- a/arch/arm/mach-ux500/headsmp.S
+++ b/arch/arm/mach-ux500/headsmp.S
@@ -23,7 +23,6 @@ ENTRY(u8500_secondary_startup)
         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 b782a03024be..dd8037ebccf8 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 @@ static inline void platform_do_lowpower(unsigned int cpu)
 
 int platform_cpu_kill(unsigned int cpu)
 {
-        return wait_for_completion_timeout(&cpu_killed, 5000);
+        return 1;
 }
 
 /*
@@ -48,19 +45,6 @@ int platform_cpu_kill(unsigned int cpu)
  */
 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 197e8417375e..ca2b15b1b3b1 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 @@ extern void u8500_secondary_startup(void);
 /*
  * 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 b5077b4c419f..2115a0cf07b0 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 @@ void __cpuinit platform_secondary_init(unsigned int cpu)
          * 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 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
          * 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 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 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
@@ -126,40 +126,26 @@ static void __init wakeup_secondary(void)
  */
 void __init smp_init_cpus(void)
 {
-        unsigned int i, ncores = get_core_count();
+        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_get_core_count(__io_address(UX500_SCU_BASE));
 
         /* 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())       {
+        if (ncores > NR_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();
+                       ncores, NR_CPUS);
+                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
@@ -168,13 +154,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         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 c781f30c8368..3f7b5e9d83c5 100644
--- a/arch/arm/mach-versatile/Kconfig
+++ b/arch/arm/mach-versatile/Kconfig
@@ -4,6 +4,7 @@ menu "Versatile platform type"
 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 40a024c71e4b..13a83e45a33b 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 1b71b77ade22..2c0ac7de2814 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 cb5793ef3ee0..e628402b754c 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 000000000000..ea4cbfb90a66
--- /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 5a6da4fd247e..4c05e4a9713a 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 dfb591031d17..b1687b6abe63 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 @@ extern void vexpress_secondary_startup(void);
  */
 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 @@ 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
@@ -57,8 +67,7 @@ void __cpuinit platform_secondary_init(unsigned int cpu)
          * 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 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
          * 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 @@ void __init smp_init_cpus(void)
         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 @@ void __init smp_init_cpus(void)
                 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 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         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 de13603dc028..a9ed3428a2fa 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 c56ddab3d912..b88a1b16b2e9 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 4414a01e1e8a..8493ed04797a 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -599,6 +599,14 @@ config CPU_CP15_MPU
         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 @@ config ARM_THUMBEE
           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 809f1bf9fa29..6b48e0a3d7aa 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -312,7 +312,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
                 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 @@ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr
         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 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
         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 @@ void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
         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 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
                 __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 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
                 __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 55c17a6fb22f..ab506272b2d3 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -204,12 +204,8 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
         /*
          * 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 72ad3e1f56cf..79c01f540cbe 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 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 {
         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 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
          * 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 b795afd0a2c6..f8f777df8d72 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 9b9ff5d949fd..7401f4d7e676 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -148,8 +148,11 @@ ENTRY(cpu_v7_set_pte_ext)
 
         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 @@ __v7_setup:
         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 @@ __v7_setup:
 #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 92c5bb7909f5..c9408434a855 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -11,13 +11,13 @@ choice
 
 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 bb937f3fabed..4b2028ab4d2b 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 d5306bee44b2..f8d922fb5584 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 ecd6a488c497..7a10257909ef 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 @@ extern u32 omap_read_auxcoreboot0(void);
 /*
  * 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 298bafc0a52f..2572260f990f 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 e593a2a801c6..2e712e17ce72 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 8063a322c790..0797cb528b46 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 @@ void vfp_flush_hwstate(struct thread_info *thread)
         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 @@ static int __init vfp_init(void)
         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 */