185 files changed, 2403 insertions, 1863 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9adc278a22ab..84fda2bebd7a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -37,6 +37,9 @@ config ARM
           Europe.  There is an ARM Linux project with a web page at
           <http://www.arm.linux.org.uk/>.
 
+config ARM_HAS_SG_CHAIN
+        bool
+
 config HAVE_PWM
         bool
 
@@ -1346,7 +1349,6 @@ config SMP_ON_UP
 
 config HAVE_ARM_SCU
         bool
-        depends on SMP
         help
           This option enables support for the ARM system coherency unit
 
@@ -1715,17 +1717,34 @@ config ZBOOT_ROM
           Say Y here if you intend to execute your compressed kernel image
           (zImage) directly from ROM or flash.  If unsure, say N.
 
+choice
+        prompt "Include SD/MMC loader in zImage (EXPERIMENTAL)"
+        depends on ZBOOT_ROM && ARCH_SH7372 && EXPERIMENTAL
+        default ZBOOT_ROM_NONE
+        help
+          Include experimental SD/MMC loading code in the ROM-able zImage.
+          With this enabled it is possible to write the the ROM-able zImage
+          kernel image to an MMC or SD card and boot the kernel straight
+          from the reset vector. At reset the processor Mask ROM will load
+          the first part of the the ROM-able zImage which in turn loads the
+          rest the kernel image to RAM.
+
+config ZBOOT_ROM_NONE
+        bool "No SD/MMC loader in zImage (EXPERIMENTAL)"
+        help
+          Do not load image from SD or MMC
+
 config ZBOOT_ROM_MMCIF
         bool "Include MMCIF loader in zImage (EXPERIMENTAL)"
-        depends on ZBOOT_ROM && ARCH_SH7372 && EXPERIMENTAL
         help
-          Say Y here to include experimental MMCIF loading code in the
-          ROM-able zImage. With this enabled it is possible to write the
-          the ROM-able zImage kernel image to an MMC card and boot the
-          kernel straight from the reset vector. At reset the processor
-          Mask ROM will load the first part of the the ROM-able zImage
-          which in turn loads the rest the kernel image to RAM using the
-          MMCIF hardware block.
+          Load image from MMCIF hardware block.
+
+config ZBOOT_ROM_SH_MOBILE_SDHI
+        bool "Include SuperH Mobile SDHI loader in zImage (EXPERIMENTAL)"
+        help
+          Load image from SDHI hardware block
+
+endchoice
 
 config CMDLINE
         string "Default kernel command string"
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 23aad0722303..0c74a6fab952 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -6,13 +6,19 @@
 
 OBJS            =
 
-# Ensure that mmcif loader code appears early in the image
+# Ensure that MMCIF loader code appears early in the image
 # to minimise that number of bocks that have to be read in
 # order to load it.
 ifeq ($(CONFIG_ZBOOT_ROM_MMCIF),y)
-ifeq ($(CONFIG_ARCH_SH7372),y)
 OBJS            += mmcif-sh7372.o
 endif
+
+# Ensure that SDHI loader code appears early in the image
+# to minimise that number of bocks that have to be read in
+# order to load it.
+ifeq ($(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI),y)
+OBJS            += sdhi-shmobile.o
+OBJS            += sdhi-sh7372.o
 endif
 
 AFLAGS_head.o += -DTEXT_OFFSET=$(TEXT_OFFSET)
diff --git a/arch/arm/boot/compressed/head-shmobile.S b/arch/arm/boot/compressed/head-shmobile.S
index c943d2e7da9d..fe3719b516fd 100644
--- a/arch/arm/boot/compressed/head-shmobile.S
+++ b/arch/arm/boot/compressed/head-shmobile.S
@@ -25,14 +25,14 @@
         /* load board-specific initialization code */
 #include <mach/zboot.h>
 
-#ifdef CONFIG_ZBOOT_ROM_MMCIF
-        /* Load image from MMC */
-        adr     sp, __tmp_stack + 128
+#if defined(CONFIG_ZBOOT_ROM_MMCIF) || defined(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI)
+        /* Load image from MMC/SD */
+        adr     sp, __tmp_stack + 256
         ldr     r0, __image_start
         ldr     r1, __image_end
         subs    r1, r1, r0
         ldr     r0, __load_base
-        bl      mmcif_loader
+        bl      mmc_loader
 
         /* Jump to loaded code */
         ldr     r0, __loaded
@@ -51,9 +51,9 @@ __loaded:
         .long   __continue
         .align
 __tmp_stack:
-        .space  128
+        .space  256
 __continue:
-#endif /* CONFIG_ZBOOT_ROM_MMCIF */
+#endif /* CONFIG_ZBOOT_ROM_MMC || CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI */
 
         b       1f
 __atags:@ tag #1
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 942fad97e447..e95a5989602a 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -353,7 +353,8 @@ not_relocated:	mov	r0, #0
                 mov     r0, #0                  @ must be zero
                 mov     r1, r7                  @ restore architecture number
                 mov     r2, r8                  @ restore atags pointer
-                mov     pc, r4                  @ call kernel
+ ARM(           mov     pc, r4  )               @ call kernel
+ THUMB(         bx      r4      )               @ entry point is always ARM
 
                 .align  2
                 .type   LC0, #object
@@ -597,6 +598,8 @@ __common_mmu_cache_on:
                 sub     pc, lr, r0, lsr #32     @ properly flush pipeline
 #endif
 
+#define PROC_ENTRY_SIZE (4*5)
+
 /*
  * Here follow the relocatable cache support functions for the
  * various processors.  This is a generic hook for locating an
@@ -624,7 +627,7 @@ call_cache_fn:	adr	r12, proc_types
  ARM(           addeq   pc, r12, r3             ) @ call cache function
  THUMB(         addeq   r12, r3                 )
  THUMB(         moveq   pc, r12                 ) @ call cache function
-                add     r12, r12, #4*5
+                add     r12, r12, #PROC_ENTRY_SIZE
                 b       1b
 
 /*
@@ -794,6 +797,16 @@ proc_types:
 
                 .size   proc_types, . - proc_types
 
+                /*
+                 * If you get a "non-constant expression in ".if" statement"
+                 * error from the assembler on this line, check that you have
+                 * not accidentally written a "b" instruction where you should
+                 * have written W(b).
+                 */
+                .if (. - proc_types) % PROC_ENTRY_SIZE != 0
+                .error "The size of one or more proc_types entries is wrong."
+                .endif
+
 /*
  * Turn off the Cache and MMU.  ARMv3 does not support
  * reading the control register, but ARMv4 does.
diff --git a/arch/arm/boot/compressed/mmcif-sh7372.c b/arch/arm/boot/compressed/mmcif-sh7372.c
index 7453c8337b83..b6f61d9a5a1b 100644
--- a/arch/arm/boot/compressed/mmcif-sh7372.c
+++ b/arch/arm/boot/compressed/mmcif-sh7372.c
@@ -40,7 +40,7 @@
  * to an MMC card
  * # dd if=vrl4.out of=/dev/sdx bs=512 seek=1
  */
-asmlinkage void mmcif_loader(unsigned char *buf, unsigned long len)
+asmlinkage void mmc_loader(unsigned char *buf, unsigned long len)
 {
         mmc_init_progress();
         mmc_update_progress(MMC_PROGRESS_ENTER);
diff --git a/arch/arm/boot/compressed/sdhi-sh7372.c b/arch/arm/boot/compressed/sdhi-sh7372.c
new file mode 100644
index 000000000000..d403a8b24d7f
--- /dev/null
+++ b/arch/arm/boot/compressed/sdhi-sh7372.c
@@ -0,0 +1,95 @@
+/*
+ * SuperH Mobile SDHI
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Kuninori Morimoto
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Parts inspired by u-boot
+ */
+
+#include <linux/io.h>
+#include <mach/mmc.h>
+#include <linux/mmc/boot.h>
+#include <linux/mmc/tmio.h>
+
+#include "sdhi-shmobile.h"
+
+#define PORT179CR       0xe60520b3
+#define PORT180CR       0xe60520b4
+#define PORT181CR       0xe60520b5
+#define PORT182CR       0xe60520b6
+#define PORT183CR       0xe60520b7
+#define PORT184CR       0xe60520b8
+
+#define SMSTPCR3        0xe615013c
+
+#define CR_INPUT_ENABLE 0x10
+#define CR_FUNCTION1    0x01
+
+#define SDHI1_BASE      (void __iomem *)0xe6860000
+#define SDHI_BASE       SDHI1_BASE
+
+/*  SuperH Mobile SDHI loader
+ *
+ * loads the zImage from an SD card starting from block 0
+ * on physical partition 1
+ *
+ * The image must be start with a vrl4 header and
+ * the zImage must start at offset 512 of the image. That is,
+ * at block 1 (=byte 512) of physical partition 1
+ *
+ * Use the following line to write the vrl4 formated zImage
+ * to an SD card
+ * # dd if=vrl4.out of=/dev/sdx bs=512
+ */
+asmlinkage void mmc_loader(unsigned short *buf, unsigned long len)
+{
+        int high_capacity;
+
+        mmc_init_progress();
+
+        mmc_update_progress(MMC_PROGRESS_ENTER);
+        /* Initialise SDHI1 */
+        /* PORT184CR: GPIO_FN_SDHICMD1 Control */
+        __raw_writeb(CR_FUNCTION1, PORT184CR);
+        /* PORT179CR: GPIO_FN_SDHICLK1 Control */
+        __raw_writeb(CR_INPUT_ENABLE|CR_FUNCTION1, PORT179CR);
+        /* PORT181CR: GPIO_FN_SDHID1_3 Control */
+        __raw_writeb(CR_FUNCTION1, PORT183CR);
+        /* PORT182CR: GPIO_FN_SDHID1_2 Control */
+        __raw_writeb(CR_FUNCTION1, PORT182CR);
+        /* PORT183CR: GPIO_FN_SDHID1_1 Control */
+        __raw_writeb(CR_FUNCTION1, PORT181CR);
+        /* PORT180CR: GPIO_FN_SDHID1_0 Control */
+        __raw_writeb(CR_FUNCTION1, PORT180CR);
+
+        /* Enable clock to SDHI1 hardware block */
+        __raw_writel(__raw_readl(SMSTPCR3) & ~(1 << 13), SMSTPCR3);
+
+        /* setup SDHI hardware */
+        mmc_update_progress(MMC_PROGRESS_INIT);
+        high_capacity = sdhi_boot_init(SDHI_BASE);
+        if (high_capacity < 0)
+                goto err;
+
+        mmc_update_progress(MMC_PROGRESS_LOAD);
+        /* load kernel */
+        if (sdhi_boot_do_read(SDHI_BASE, high_capacity,
+                              0, /* Kernel is at block 1 */
+                              (len + TMIO_BBS - 1) / TMIO_BBS, buf))
+                goto err;
+
+        /* Disable clock to SDHI1 hardware block */
+        __raw_writel(__raw_readl(SMSTPCR3) & (1 << 13), SMSTPCR3);
+
+        mmc_update_progress(MMC_PROGRESS_DONE);
+
+        return;
+err:
+        for(;;);
+}
diff --git a/arch/arm/boot/compressed/sdhi-shmobile.c b/arch/arm/boot/compressed/sdhi-shmobile.c
new file mode 100644
index 000000000000..bd3d46980955
--- /dev/null
+++ b/arch/arm/boot/compressed/sdhi-shmobile.c
@@ -0,0 +1,449 @@
+/*
+ * SuperH Mobile SDHI
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Kuninori Morimoto
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Parts inspired by u-boot
+ */
+
+#include <linux/io.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/core.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
+#include <linux/mmc/tmio.h>
+#include <mach/sdhi.h>
+
+#define OCR_FASTBOOT            (1<<29)
+#define OCR_HCS                 (1<<30)
+#define OCR_BUSY                (1<<31)
+
+#define RESP_CMD12              0x00000030
+
+static inline u16 sd_ctrl_read16(void __iomem *base, int addr)
+{
+        return __raw_readw(base + addr);
+}
+
+static inline u32 sd_ctrl_read32(void __iomem *base, int addr)
+{
+        return __raw_readw(base + addr) |
+               __raw_readw(base + addr + 2) << 16;
+}
+
+static inline void sd_ctrl_write16(void __iomem *base, int addr, u16 val)
+{
+        __raw_writew(val, base + addr);
+}
+
+static inline void sd_ctrl_write32(void __iomem *base, int addr, u32 val)
+{
+        __raw_writew(val, base + addr);
+        __raw_writew(val >> 16, base + addr + 2);
+}
+
+#define ALL_ERROR (TMIO_STAT_CMD_IDX_ERR | TMIO_STAT_CRCFAIL |          \
+                   TMIO_STAT_STOPBIT_ERR | TMIO_STAT_DATATIMEOUT |      \
+                   TMIO_STAT_RXOVERFLOW | TMIO_STAT_TXUNDERRUN |        \
+                   TMIO_STAT_CMDTIMEOUT | TMIO_STAT_ILL_ACCESS |        \
+                   TMIO_STAT_ILL_FUNC)
+
+static int sdhi_intr(void __iomem *base)
+{
+        unsigned long state = sd_ctrl_read32(base, CTL_STATUS);
+
+        if (state & ALL_ERROR) {
+                sd_ctrl_write32(base, CTL_STATUS, ~ALL_ERROR);
+                sd_ctrl_write32(base, CTL_IRQ_MASK,
+                                ALL_ERROR |
+                                sd_ctrl_read32(base, CTL_IRQ_MASK));
+                return -EINVAL;
+        }
+        if (state & TMIO_STAT_CMDRESPEND) {
+                sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND);
+                sd_ctrl_write32(base, CTL_IRQ_MASK,
+                                TMIO_STAT_CMDRESPEND |
+                                sd_ctrl_read32(base, CTL_IRQ_MASK));
+                return 0;
+        }
+        if (state & TMIO_STAT_RXRDY) {
+                sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_RXRDY);
+                sd_ctrl_write32(base, CTL_IRQ_MASK,
+                                TMIO_STAT_RXRDY | TMIO_STAT_TXUNDERRUN |
+                                sd_ctrl_read32(base, CTL_IRQ_MASK));
+                return 0;
+        }
+        if (state & TMIO_STAT_DATAEND) {
+                sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_DATAEND);
+                sd_ctrl_write32(base, CTL_IRQ_MASK,
+                                TMIO_STAT_DATAEND |
+                                sd_ctrl_read32(base, CTL_IRQ_MASK));
+                return 0;
+        }
+
+        return -EAGAIN;
+}
+
+static int sdhi_boot_wait_resp_end(void __iomem *base)
+{
+        int err = -EAGAIN, timeout = 10000000;
+
+        while (timeout--) {
+                err = sdhi_intr(base);
+                if (err != -EAGAIN)
+                        break;
+                udelay(1);
+        }
+
+        return err;
+}
+
+/* SDHI_CLK_CTRL */
+#define CLK_MMC_ENABLE                 (1 << 8)
+#define CLK_MMC_INIT                   (1 << 6)        /* clk / 256 */
+
+static void sdhi_boot_mmc_clk_stop(void __iomem *base)
+{
+        sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, 0x0000);
+        msleep(10);
+        sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, ~CLK_MMC_ENABLE &
+                sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL));
+        msleep(10);
+}
+
+static void sdhi_boot_mmc_clk_start(void __iomem *base)
+{
+        sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, CLK_MMC_ENABLE |
+                sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL));
+        msleep(10);
+        sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, CLK_MMC_ENABLE);
+        msleep(10);
+}
+
+static void sdhi_boot_reset(void __iomem *base)
+{
+        sd_ctrl_write16(base, CTL_RESET_SD, 0x0000);
+        msleep(10);
+        sd_ctrl_write16(base, CTL_RESET_SD, 0x0001);
+        msleep(10);
+}
+
+/* Set MMC clock / power.
+ * Note: This controller uses a simple divider scheme therefore it cannot
+ * run a MMC card at full speed (20MHz). The max clock is 24MHz on SD, but as
+ * MMC wont run that fast, it has to be clocked at 12MHz which is the next
+ * slowest setting.
+ */
+static int sdhi_boot_mmc_set_ios(void __iomem *base, struct mmc_ios *ios)
+{
+        if (sd_ctrl_read32(base, CTL_STATUS) & TMIO_STAT_CMD_BUSY)
+                return -EBUSY;
+
+        if (ios->clock)
+                sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL,
+                                ios->clock | CLK_MMC_ENABLE);
+
+        /* Power sequence - OFF -> ON -> UP */
+        switch (ios->power_mode) {
+        case MMC_POWER_OFF: /* power down SD bus */
+                sdhi_boot_mmc_clk_stop(base);
+                break;
+        case MMC_POWER_ON: /* power up SD bus */
+                break;
+        case MMC_POWER_UP: /* start bus clock */
+                sdhi_boot_mmc_clk_start(base);
+                break;
+        }
+
+        switch (ios->bus_width) {
+        case MMC_BUS_WIDTH_1:
+                sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x80e0);
+        break;
+        case MMC_BUS_WIDTH_4:
+                sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x00e0);
+        break;
+        }
+
+        /* Let things settle. delay taken from winCE driver */
+        udelay(140);
+
+        return 0;
+}
+
+/* These are the bitmasks the tmio chip requires to implement the MMC response
+ * types. Note that R1 and R6 are the same in this scheme. */
+#define RESP_NONE      0x0300
+#define RESP_R1        0x0400
+#define RESP_R1B       0x0500
+#define RESP_R2        0x0600
+#define RESP_R3        0x0700
+#define DATA_PRESENT   0x0800
+#define TRANSFER_READ  0x1000
+
+static int sdhi_boot_request(void __iomem *base, struct mmc_command *cmd)
+{
+        int err, c = cmd->opcode;
+
+        switch (mmc_resp_type(cmd)) {
+        case MMC_RSP_NONE: c |= RESP_NONE; break;
+        case MMC_RSP_R1:   c |= RESP_R1;   break;
+        case MMC_RSP_R1B:  c |= RESP_R1B;  break;
+        case MMC_RSP_R2:   c |= RESP_R2;   break;
+        case MMC_RSP_R3:   c |= RESP_R3;   break;
+        default:
+                return -EINVAL;
+        }
+
+        /* No interrupts so this may not be cleared */
+        sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND);
+
+        sd_ctrl_write32(base, CTL_IRQ_MASK, TMIO_STAT_CMDRESPEND |
+                        sd_ctrl_read32(base, CTL_IRQ_MASK));
+        sd_ctrl_write32(base, CTL_ARG_REG, cmd->arg);
+        sd_ctrl_write16(base, CTL_SD_CMD, c);
+
+
+        sd_ctrl_write32(base, CTL_IRQ_MASK,
+                        ~(TMIO_STAT_CMDRESPEND | ALL_ERROR) &
+                        sd_ctrl_read32(base, CTL_IRQ_MASK));
+
+        err = sdhi_boot_wait_resp_end(base);
+        if (err)
+                return err;
+
+        cmd->resp[0] = sd_ctrl_read32(base, CTL_RESPONSE);
+
+        return 0;
+}
+
+static int sdhi_boot_do_read_single(void __iomem *base, int high_capacity,
+                                    unsigned long block, unsigned short *buf)
+{
+        int err, i;
+
+        /* CMD17 - Read */
+        {
+                struct mmc_command cmd;
+
+                cmd.opcode = MMC_READ_SINGLE_BLOCK | \
+                             TRANSFER_READ | DATA_PRESENT;
+                if (high_capacity)
+                        cmd.arg = block;
+                else
+                        cmd.arg = block * TMIO_BBS;
+                cmd.flags = MMC_RSP_R1;
+                err = sdhi_boot_request(base, &cmd);
+                if (err)
+                        return err;
+        }
+
+        sd_ctrl_write32(base, CTL_IRQ_MASK,
+                        ~(TMIO_STAT_DATAEND | TMIO_STAT_RXRDY |
+                          TMIO_STAT_TXUNDERRUN) &
+                        sd_ctrl_read32(base, CTL_IRQ_MASK));
+        err = sdhi_boot_wait_resp_end(base);
+        if (err)
+                return err;
+
+        sd_ctrl_write16(base, CTL_SD_XFER_LEN, TMIO_BBS);
+        for (i = 0; i < TMIO_BBS / sizeof(*buf); i++)
+                *buf++ = sd_ctrl_read16(base, RESP_CMD12);
+
+        err = sdhi_boot_wait_resp_end(base);
+        if (err)
+                return err;
+
+        return 0;
+}
+
+int sdhi_boot_do_read(void __iomem *base, int high_capacity,
+                      unsigned long offset, unsigned short count,
+                      unsigned short *buf)
+{
+        unsigned long i;
+        int err = 0;
+
+        for (i = 0; i < count; i++) {
+                err = sdhi_boot_do_read_single(base, high_capacity, offset + i,
+                                               buf + (i * TMIO_BBS /
+                                                      sizeof(*buf)));
+                if (err)
+                        return err;
+        }
+
+        return 0;
+}
+
+#define VOLTAGES (MMC_VDD_32_33 | MMC_VDD_33_34)
+
+int sdhi_boot_init(void __iomem *base)
+{
+        bool sd_v2 = false, sd_v1_0 = false;
+        unsigned short cid;
+        int err, high_capacity = 0;
+
+        sdhi_boot_mmc_clk_stop(base);
+        sdhi_boot_reset(base);
+
+        /* mmc0: clock 400000Hz busmode 1 powermode 2 cs 0 Vdd 21 width 0 timing 0 */
+        {
+                struct mmc_ios ios;
+                ios.power_mode = MMC_POWER_ON;
+                ios.bus_width = MMC_BUS_WIDTH_1;
+                ios.clock = CLK_MMC_INIT;
+                err = sdhi_boot_mmc_set_ios(base, &ios);
+                if (err)
+                        return err;
+        }
+
+        /* CMD0 */
+        {
+                struct mmc_command cmd;
+                msleep(1);
+                cmd.opcode = MMC_GO_IDLE_STATE;
+                cmd.arg = 0;
+                cmd.flags = MMC_RSP_NONE;
+                err = sdhi_boot_request(base, &cmd);
+                if (err)
+                        return err;
+                msleep(2);
+        }
+
+        /* CMD8 - Test for SD version 2 */
+        {
+                struct mmc_command cmd;
+                cmd.opcode = SD_SEND_IF_COND;
+                cmd.arg = (VOLTAGES != 0) << 8 | 0xaa;
+                cmd.flags = MMC_RSP_R1;
+                err = sdhi_boot_request(base, &cmd); /* Ignore error */
+                if ((cmd.resp[0] & 0xff) == 0xaa)
+                        sd_v2 = true;
+        }
+
+        /* CMD55 - Get OCR (SD) */
+        {
+                int timeout = 1000;
+                struct mmc_command cmd;
+
+                cmd.arg = 0;
+
+                do {
+                        cmd.opcode = MMC_APP_CMD;
+                        cmd.flags = MMC_RSP_R1;
+                        cmd.arg = 0;
+                        err = sdhi_boot_request(base, &cmd);
+                        if (err)
+                                break;
+
+                        cmd.opcode = SD_APP_OP_COND;
+                        cmd.flags = MMC_RSP_R3;
+                        cmd.arg = (VOLTAGES & 0xff8000);
+                        if (sd_v2)
+                                cmd.arg |= OCR_HCS;
+                        cmd.arg |= OCR_FASTBOOT;
+                        err = sdhi_boot_request(base, &cmd);
+                        if (err)
+                                break;
+
+                        msleep(1);
+                } while((!(cmd.resp[0] & OCR_BUSY)) && --timeout);
+
+                if (!err && timeout) {
+                        if (!sd_v2)
+                                sd_v1_0 = true;
+                        high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS;
+                }
+        }
+
+        /* CMD1 - Get OCR (MMC) */
+        if (!sd_v2 && !sd_v1_0) {
+                int timeout = 1000;
+                struct mmc_command cmd;
+
+                do {
+                        cmd.opcode = MMC_SEND_OP_COND;
+                        cmd.arg = VOLTAGES | OCR_HCS;
+                        cmd.flags = MMC_RSP_R3;
+                        err = sdhi_boot_request(base, &cmd);
+                        if (err)
+                                return err;
+
+                        msleep(1);
+                } while((!(cmd.resp[0] & OCR_BUSY)) && --timeout);
+
+                if (!timeout)
+                        return -EAGAIN;
+
+                high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS;
+        }
+
+        /* CMD2 - Get CID */
+        {
+                struct mmc_command cmd;
+                cmd.opcode = MMC_ALL_SEND_CID;
+                cmd.arg = 0;
+                cmd.flags = MMC_RSP_R2;
+                err = sdhi_boot_request(base, &cmd);
+                if (err)
+                        return err;
+        }
+
+        /* CMD3
+         * MMC: Set the relative address
+         * SD:  Get the relative address
+         * Also puts the card into the standby state
+         */
+        {
+                struct mmc_command cmd;
+                cmd.opcode = MMC_SET_RELATIVE_ADDR;
+                cmd.arg = 0;
+                cmd.flags = MMC_RSP_R1;
+                err = sdhi_boot_request(base, &cmd);
+                if (err)
+                        return err;
+                cid = cmd.resp[0] >> 16;
+        }
+
+        /* CMD9 - Get CSD */
+        {
+                struct mmc_command cmd;
+                cmd.opcode = MMC_SEND_CSD;
+                cmd.arg = cid << 16;
+                cmd.flags = MMC_RSP_R2;
+                err = sdhi_boot_request(base, &cmd);
+                if (err)
+                        return err;
+        }
+
+        /* CMD7 - Select the card */
+        {
+                struct mmc_command cmd;
+                cmd.opcode = MMC_SELECT_CARD;
+                //cmd.arg = rca << 16;
+                cmd.arg = cid << 16;
+                //cmd.flags = MMC_RSP_R1B;
+                cmd.flags = MMC_RSP_R1;
+                err = sdhi_boot_request(base, &cmd);
+                if (err)
+                        return err;
+        }
+
+        /* CMD16 - Set the block size */
+        {
+                struct mmc_command cmd;
+                cmd.opcode = MMC_SET_BLOCKLEN;
+                cmd.arg = TMIO_BBS;
+                cmd.flags = MMC_RSP_R1;
+                err = sdhi_boot_request(base, &cmd);
+                if (err)
+                        return err;
+        }
+
+        return high_capacity;
+}
diff --git a/arch/arm/boot/compressed/sdhi-shmobile.h b/arch/arm/boot/compressed/sdhi-shmobile.h
new file mode 100644
index 000000000000..92eaa09f985e
--- /dev/null
+++ b/arch/arm/boot/compressed/sdhi-shmobile.h
@@ -0,0 +1,11 @@
+#ifndef SDHI_MOBILE_H
+#define SDHI_MOBILE_H
+
+#include <linux/compiler.h>
+
+int sdhi_boot_do_read(void __iomem *base, int high_capacity,
+                      unsigned long offset, unsigned short count,
+                      unsigned short *buf);
+int sdhi_boot_init(void __iomem *base);
+
+#endif
diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in
index ea80abe78844..4e728834a1b9 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.in
+++ b/arch/arm/boot/compressed/vmlinux.lds.in
@@ -33,20 +33,24 @@ SECTIONS
     *(.text.*)
     *(.fixup)
     *(.gnu.warning)
+    *(.glue_7t)
+    *(.glue_7)
+  }
+  .rodata : {
     *(.rodata)
     *(.rodata.*)
-    *(.glue_7)
-    *(.glue_7t)
+  }
+  .piggydata : {
     *(.piggydata)
-    . = ALIGN(4);
   }
 
+  . = ALIGN(4);
   _etext = .;
 
+  .got.plt              : { *(.got.plt) }
   _got_start = .;
   .got                  : { *(.got) }
   _got_end = .;
-  .got.plt              : { *(.got.plt) }
   _edata = .;
 
   . = BSS_START;
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index e5681636626f..595ecd290ebf 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -79,6 +79,8 @@ struct dmabounce_device_info {
         struct dmabounce_pool   large;
 
         rwlock_t lock;
+
+        int (*needs_bounce)(struct device *, dma_addr_t, size_t);
 };
 
 #ifdef STATS
@@ -210,114 +212,91 @@ static struct safe_buffer *find_safe_buffer_dev(struct device *dev,
         if (!dev || !dev->archdata.dmabounce)
                 return NULL;
         if (dma_mapping_error(dev, dma_addr)) {
-                if (dev)
-                        dev_err(dev, "Trying to %s invalid mapping\n", where);
-                else
-                        pr_err("unknown device: Trying to %s invalid mapping\n", where);
+                dev_err(dev, "Trying to %s invalid mapping\n", where);
                 return NULL;
         }
         return find_safe_buffer(dev->archdata.dmabounce, dma_addr);
 }
 
-static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
-                enum dma_data_direction dir)
+static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
-        struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-        dma_addr_t dma_addr;
-        int needs_bounce = 0;
-
-        if (device_info)
-                DO_STATS ( device_info->map_op_count++ );
-
-        dma_addr = virt_to_dma(dev, ptr);
+        if (!dev || !dev->archdata.dmabounce)
+                return 0;
 
         if (dev->dma_mask) {
-                unsigned long mask = *dev->dma_mask;
-                unsigned long limit;
+                unsigned long limit, mask = *dev->dma_mask;
 
                 limit = (mask + 1) & ~mask;
                 if (limit && size > limit) {
                         dev_err(dev, "DMA mapping too big (requested %#x "
                                 "mask %#Lx)\n", size, *dev->dma_mask);
-                        return ~0;
+                        return -E2BIG;
                 }
 
-                /*
-                 * Figure out if we need to bounce from the DMA mask.
-                 */
-                needs_bounce = (dma_addr | (dma_addr + size - 1)) & ~mask;
+                /* Figure out if we need to bounce from the DMA mask. */
+                if ((dma_addr | (dma_addr + size - 1)) & ~mask)
+                        return 1;
         }
 
-        if (device_info && (needs_bounce || dma_needs_bounce(dev, dma_addr, size))) {
-                struct safe_buffer *buf;
+        return !!dev->archdata.dmabounce->needs_bounce(dev, dma_addr, size);
+}
 
-                buf = alloc_safe_buffer(device_info, ptr, size, dir);
-                if (buf == 0) {
-                        dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
-                               __func__, ptr);
-                        return 0;
-                }
+static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
+                enum dma_data_direction dir)
+{
+        struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
+        struct safe_buffer *buf;
 
-                dev_dbg(dev,
-                        "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-                        __func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-                        buf->safe, buf->safe_dma_addr);
+        if (device_info)
+                DO_STATS ( device_info->map_op_count++ );
 
-                if ((dir == DMA_TO_DEVICE) ||
-                    (dir == DMA_BIDIRECTIONAL)) {
-                        dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
-                                __func__, ptr, buf->safe, size);
-                        memcpy(buf->safe, ptr, size);
-                }
-                ptr = buf->safe;
+        buf = alloc_safe_buffer(device_info, ptr, size, dir);
+        if (buf == NULL) {
+                dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
+                       __func__, ptr);
+                return ~0;
+        }
 
-                dma_addr = buf->safe_dma_addr;
-        } else {
-                /*
-                 * We don't need to sync the DMA buffer since
-                 * it was allocated via the coherent allocators.
-                 */
-                __dma_single_cpu_to_dev(ptr, size, dir);
+        dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+                __func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+                buf->safe, buf->safe_dma_addr);
+
+        if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
+                dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
+                        __func__, ptr, buf->safe, size);
+                memcpy(buf->safe, ptr, size);
         }
 
-        return dma_addr;
+        return buf->safe_dma_addr;
 }
 
-static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
+static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
                 size_t size, enum dma_data_direction dir)
 {
-        struct safe_buffer *buf = find_safe_buffer_dev(dev, dma_addr, "unmap");
-
-        if (buf) {
-                BUG_ON(buf->size != size);
-                BUG_ON(buf->direction != dir);
+        BUG_ON(buf->size != size);
+        BUG_ON(buf->direction != dir);
 
-                dev_dbg(dev,
-                        "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-                        __func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-                        buf->safe, buf->safe_dma_addr);
+        dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+                __func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+                buf->safe, buf->safe_dma_addr);
 
-                DO_STATS(dev->archdata.dmabounce->bounce_count++);
+        DO_STATS(dev->archdata.dmabounce->bounce_count++);
 
-                if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
-                        void *ptr = buf->ptr;
+        if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
+                void *ptr = buf->ptr;
 
-                        dev_dbg(dev,
-                                "%s: copy back safe %p to unsafe %p size %d\n",
-                                __func__, buf->safe, ptr, size);
-                        memcpy(ptr, buf->safe, size);
+                dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
+                        __func__, buf->safe, ptr, size);
+                memcpy(ptr, buf->safe, size);
 
-                        /*
-                         * Since we may have written to a page cache page,
-                         * we need to ensure that the data will be coherent
-                         * with user mappings.
-                         */
-                        __cpuc_flush_dcache_area(ptr, size);
-                }
-                free_safe_buffer(dev->archdata.dmabounce, buf);
-        } else {
-                __dma_single_dev_to_cpu(dma_to_virt(dev, dma_addr), size, dir);
+                /*
+                 * Since we may have written to a page cache page,
+                 * we need to ensure that the data will be coherent
+                 * with user mappings.
+                 */
+                __cpuc_flush_dcache_area(ptr, size);
         }
+        free_safe_buffer(dev->archdata.dmabounce, buf);
 }
 
 /* ************************************************** */
@@ -328,45 +307,28 @@ 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,
-                enum dma_data_direction dir)
-{
-        dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-                __func__, ptr, size, dir);
-
-        BUG_ON(!valid_dma_direction(dir));
-
-        return map_single(dev, ptr, size, dir);
-}
-EXPORT_SYMBOL(__dma_map_single);
-
-/*
- * see if a mapped address was really a "safe" buffer and if so, copy
- * the data from the safe buffer back to the unsafe buffer and free up
- * 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,
-                enum dma_data_direction dir)
-{
-        dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-                __func__, (void *) dma_addr, size, dir);
-
-        unmap_single(dev, dma_addr, size, dir);
-}
-EXPORT_SYMBOL(__dma_unmap_single);
-
 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 dma_addr;
+        int ret;
+
         dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n",
                 __func__, page, offset, size, dir);
 
-        BUG_ON(!valid_dma_direction(dir));
+        dma_addr = pfn_to_dma(dev, page_to_pfn(page)) + offset;
+
+        ret = needs_bounce(dev, dma_addr, size);
+        if (ret < 0)
+                return ~0;
+
+        if (ret == 0) {
+                __dma_page_cpu_to_dev(page, offset, size, dir);
+                return dma_addr;
+        }
 
         if (PageHighMem(page)) {
-                dev_err(dev, "DMA buffer bouncing of HIGHMEM pages "
-                             "is not supported\n");
+                dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
                 return ~0;
         }
 
@@ -383,10 +345,19 @@ EXPORT_SYMBOL(__dma_map_page);
 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",
-                __func__, (void *) dma_addr, size, dir);
+        struct safe_buffer *buf;
+
+        dev_dbg(dev, "%s(dma=%#x,size=%d,dir=%x)\n",
+                __func__, dma_addr, size, dir);
+
+        buf = find_safe_buffer_dev(dev, dma_addr, __func__);
+        if (!buf) {
+                __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, dma_addr)),
+                        dma_addr & ~PAGE_MASK, size, dir);
+                return;
+        }
 
-        unmap_single(dev, dma_addr, size, dir);
+        unmap_single(dev, buf, size, dir);
 }
 EXPORT_SYMBOL(__dma_unmap_page);
 
@@ -461,7 +432,8 @@ static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
 }
 
 int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
-                unsigned long large_buffer_size)
+                unsigned long large_buffer_size,
+                int (*needs_bounce_fn)(struct device *, dma_addr_t, size_t))
 {
         struct dmabounce_device_info *device_info;
         int ret;
@@ -497,6 +469,7 @@ int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
         device_info->dev = dev;
         INIT_LIST_HEAD(&device_info->safe_buffers);
         rwlock_init(&device_info->lock);
+        device_info->needs_bounce = needs_bounce_fn;
 
 #ifdef STATS
         device_info->total_allocs = 0;
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 4ddd0a6ac7ff..7bdd91766d65 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -179,22 +179,21 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 {
         void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
         unsigned int shift = (d->irq % 4) * 8;
-        unsigned int cpu = cpumask_first(mask_val);
+        unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
         u32 val, mask, bit;
 
-        if (cpu >= 8)
+        if (cpu >= 8 || cpu >= nr_cpu_ids)
                 return -EINVAL;
 
         mask = 0xff << shift;
         bit = 1 << (cpu + shift);
 
         spin_lock(&irq_controller_lock);
-        d->node = cpu;
         val = readl_relaxed(reg) & ~mask;
         writel_relaxed(val | bit, reg);
         spin_unlock(&irq_controller_lock);
 
-        return 0;
+        return IRQ_SET_MASK_OK;
 }
 #endif
 
diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c
index 7a21927c52e1..14ad62e16dd1 100644
--- a/arch/arm/common/it8152.c
+++ b/arch/arm/common/it8152.c
@@ -243,6 +243,12 @@ static struct resource it8152_mem = {
  * ITE8152 chip can address up to 64MByte, so all the devices
  * connected to ITE8152 (PCI and USB) should have limited DMA window
  */
+static int it8152_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
+{
+        dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
+                __func__, dma_addr, size);
+        return (dma_addr + size - PHYS_OFFSET) >= SZ_64M;
+}
 
 /*
  * Setup DMA mask to 64MB on devices connected to ITE8152. Ignore all
@@ -254,7 +260,7 @@ static int it8152_pci_platform_notify(struct device *dev)
                 if (dev->dma_mask)
                         *dev->dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
                 dev->coherent_dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
-                dmabounce_register_dev(dev, 2048, 4096);
+                dmabounce_register_dev(dev, 2048, 4096, it8152_needs_bounce);
         }
         return 0;
 }
@@ -267,14 +273,6 @@ static int it8152_pci_platform_notify_remove(struct device *dev)
         return 0;
 }
 
-int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-        dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
-                __func__, dma_addr, size);
-        return (dev->bus == &pci_bus_type) &&
-                ((dma_addr + size - PHYS_OFFSET) >= SZ_64M);
-}
-
 int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
         if (mask >= PHYS_OFFSET + SZ_64M - 1)
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 9c49a46a2b7a..0569de6acfba 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -579,7 +579,36 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac,
 
         sachip->dev->coherent_dma_mask &= sa1111_dma_mask[drac >> 2];
 }
+#endif
 
+#ifdef CONFIG_DMABOUNCE
+/*
+ * According to the "Intel StrongARM SA-1111 Microprocessor Companion
+ * Chip Specification Update" (June 2000), erratum #7, there is a
+ * significant bug in the SA1111 SDRAM shared memory controller.  If
+ * an access to a region of memory above 1MB relative to the bank base,
+ * it is important that address bit 10 _NOT_ be asserted. Depending
+ * on the configuration of the RAM, bit 10 may correspond to one
+ * of several different (processor-relative) address bits.
+ *
+ * This routine only identifies whether or not a given DMA address
+ * is susceptible to the bug.
+ *
+ * This should only get called for sa1111_device types due to the
+ * way we configure our device dma_masks.
+ */
+static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
+{
+        /*
+         * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
+         * User's Guide" mentions that jumpers R51 and R52 control the
+         * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
+         * SDRAM bank 1 on Neponset). The default configuration selects
+         * Assabet, so any address in bank 1 is necessarily invalid.
+         */
+        return (machine_is_assabet() || machine_is_pfs168()) &&
+                (addr >= 0xc8000000 || (addr + size) >= 0xc8000000);
+}
 #endif
 
 static void sa1111_dev_release(struct device *_dev)
@@ -644,7 +673,8 @@ sa1111_init_one_child(struct sa1111 *sachip, struct resource *parent,
                 dev->dev.dma_mask = &dev->dma_mask;
 
                 if (dev->dma_mask != 0xffffffffUL) {
-                        ret = dmabounce_register_dev(&dev->dev, 1024, 4096);
+                        ret = dmabounce_register_dev(&dev->dev, 1024, 4096,
+                                        sa1111_needs_bounce);
                         if (ret) {
                                 dev_err(&dev->dev, "SA1111: Failed to register"
                                         " with dmabounce\n");
@@ -818,34 +848,6 @@ static void __sa1111_remove(struct sa1111 *sachip)
         kfree(sachip);
 }
 
-/*
- * According to the "Intel StrongARM SA-1111 Microprocessor Companion
- * Chip Specification Update" (June 2000), erratum #7, there is a
- * significant bug in the SA1111 SDRAM shared memory controller.  If
- * an access to a region of memory above 1MB relative to the bank base,
- * it is important that address bit 10 _NOT_ be asserted. Depending
- * on the configuration of the RAM, bit 10 may correspond to one
- * of several different (processor-relative) address bits.
- *
- * This routine only identifies whether or not a given DMA address
- * is susceptible to the bug.
- *
- * This should only get called for sa1111_device types due to the
- * way we configure our device dma_masks.
- */
-int dma_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
-{
-        /*
-         * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
-         * User's Guide" mentions that jumpers R51 and R52 control the
-         * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
-         * SDRAM bank 1 on Neponset). The default configuration selects
-         * Assabet, so any address in bank 1 is necessarily invalid.
-         */
-        return ((machine_is_assabet() || machine_is_pfs168()) &&
-                (addr >= 0xc8000000 || (addr + size) >= 0xc8000000));
-}
-
 struct sa1111_save_data {
         unsigned int    skcr;
         unsigned int    skpcr;
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index bc2d2d75f706..65c3f2474f5e 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -13,6 +13,9 @@
  *  Do not include any C declarations in this file - it is included by
  *  assembler source.
  */
+#ifndef __ASM_ASSEMBLER_H__
+#define __ASM_ASSEMBLER_H__
+
 #ifndef __ASSEMBLY__
 #error "Only include this from assembly code"
 #endif
@@ -290,3 +293,4 @@
         .macro  ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f
         usracc  ldr, \reg, \ptr, \inc, \cond, \rept, \abort
         .endm
+#endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index b4892a06442c..f4280593dfa3 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -26,8 +26,8 @@
 #include <linux/compiler.h>
 #include <asm/system.h>
 
-#define smp_mb__before_clear_bit()      mb()
-#define smp_mb__after_clear_bit()       mb()
+#define smp_mb__before_clear_bit()      smp_mb()
+#define smp_mb__after_clear_bit()       smp_mb()
 
 /*
  * These functions are the basis of our bit ops.
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 4fff837363ed..7a21d0bf7134 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -115,39 +115,8 @@ static inline void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
                 ___dma_page_dev_to_cpu(page, off, size, dir);
 }
 
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- *
- * FIXME: This should really be a platform specific issue - we should
- * return false if GFP_DMA allocations may not satisfy the supplied 'mask'.
- */
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-        if (mask < ISA_DMA_THRESHOLD)
-                return 0;
-        return 1;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-#ifdef CONFIG_DMABOUNCE
-        if (dev->archdata.dmabounce) {
-                if (dma_mask >= ISA_DMA_THRESHOLD)
-                        return 0;
-                else
-                        return -EIO;
-        }
-#endif
-        if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-                return -EIO;
-
-        *dev->dma_mask = dma_mask;
-
-        return 0;
-}
+extern int dma_supported(struct device *, u64);
+extern int dma_set_mask(struct device *, u64);
 
 /*
  * DMA errors are defined by all-bits-set in the DMA address.
@@ -256,14 +225,14 @@ int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
  * @dev: valid struct device pointer
  * @small_buf_size: size of buffers to use with small buffer pool
  * @large_buf_size: size of buffers to use with large buffer pool (can be 0)
+ * @needs_bounce_fn: called to determine whether buffer needs bouncing
  *
  * This function should be called by low-level platform code to register
  * a device as requireing DMA buffer bouncing. The function will allocate
  * appropriate DMA pools for the device.
- *
  */
 extern int dmabounce_register_dev(struct device *, unsigned long,
-                unsigned long);
+                unsigned long, int (*)(struct device *, dma_addr_t, size_t));
 
 /**
  * dmabounce_unregister_dev
@@ -277,31 +246,9 @@ extern int dmabounce_register_dev(struct device *, unsigned long,
  */
 extern void dmabounce_unregister_dev(struct device *);
 
-/**
- * dma_needs_bounce
- *
- * @dev: valid struct device pointer
- * @dma_handle: dma_handle of unbounced buffer
- * @size: size of region being mapped
- *
- * Platforms that utilize the dmabounce mechanism must implement
- * this function.
- *
- * The dmabounce routines call this function whenever a dma-mapping
- * is requested to determine whether a given buffer needs to be bounced
- * or not. The function must return 0 if the buffer is OK for
- * DMA access and 1 if the buffer needs to be bounced.
- *
- */
-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,
-                enum dma_data_direction);
-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 *,
                 unsigned long, size_t, enum dma_data_direction);
 extern void __dma_unmap_page(struct device *, dma_addr_t, size_t,
@@ -328,13 +275,6 @@ 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)
 {
@@ -342,12 +282,6 @@ static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page,
         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)
 {
@@ -373,14 +307,18 @@ static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle,
 static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
                 size_t size, enum dma_data_direction dir)
 {
+        unsigned long offset;
+        struct page *page;
         dma_addr_t addr;
 
+        BUG_ON(!virt_addr_valid(cpu_addr));
+        BUG_ON(!virt_addr_valid(cpu_addr + size - 1));
         BUG_ON(!valid_dma_direction(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);
+        page = virt_to_page(cpu_addr);
+        offset = (unsigned long)cpu_addr & ~PAGE_MASK;
+        addr = __dma_map_page(dev, page, offset, size, dir);
+        debug_dma_map_page(dev, page, offset, size, dir, addr, true);
 
         return addr;
 }
@@ -430,7 +368,7 @@ static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
                 size_t size, enum dma_data_direction dir)
 {
         debug_dma_unmap_page(dev, handle, size, dir, true);
-        __dma_unmap_single(dev, handle, size, dir);
+        __dma_unmap_page(dev, handle, size, dir);
 }
 
 /**
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
index ec0bbf79c71f..2f1e2098dfe7 100644
--- a/arch/arm/include/asm/entry-macro-multi.S
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -1,9 +1,11 @@
+#include <asm/assembler.h>
+
 /*
  * 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
+        get_irqnr_preamble r6, lr
+1:      get_irqnr_and_base r0, r2, r6, lr
         movne   r1, sp
         @
         @ routine called with r0 = irq number, r1 = struct pt_regs *
@@ -15,17 +17,17 @@
         /*
          * XXX
          *
-         * this macro assumes that irqstat (r6) and base (r5) are
+         * this macro assumes that irqstat (r2) and base (r6) are
          * preserved from get_irqnr_and_base above
          */
-        ALT_SMP(test_for_ipi r0, r6, r5, lr)
+        ALT_SMP(test_for_ipi r0, r2, r6, 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
+        test_for_ltirq r0, r2, r6, lr
         movne   r0, sp
         adrne   lr, BSYM(1b)
         bne     do_local_timer
@@ -38,7 +40,7 @@
         .align  5
         .global \symbol_name
 \symbol_name:
-        mov     r4, lr
+        mov     r8, lr
         arch_irq_handler_default
-        mov     pc, r4
+        mov     pc, r8
         .endm
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index af44a8fb3480..b8de516e600e 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -204,18 +204,6 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 #endif
 
 /*
- * The DMA mask corresponding to the maximum bus address allocatable
- * using GFP_DMA.  The default here places no restriction on DMA
- * allocations.  This must be the smallest DMA mask in the system,
- * so a successful GFP_DMA allocation will always satisfy this.
- */
-#ifndef ARM_DMA_ZONE_SIZE
-#define ISA_DMA_THRESHOLD       (0xffffffffULL)
-#else
-#define ISA_DMA_THRESHOLD       (PHYS_OFFSET + ARM_DMA_ZONE_SIZE - 1)
-#endif
-
-/*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.
  *
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 7544ce6b481a..67c70a31a1be 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -52,7 +52,7 @@ reserve_pmu(enum arm_pmu_type device);
  * a cookie.
  */
 extern int
-release_pmu(struct platform_device *pdev);
+release_pmu(enum arm_pmu_type type);
 
 /**
  * init_pmu() - Initialise the PMU.
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 8ec535e11fd7..633d1cb84d87 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -82,13 +82,13 @@ extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 #else
-#define cpu_proc_init()                 processor._proc_init()
-#define cpu_proc_fin()                  processor._proc_fin()
-#define cpu_reset(addr)                 processor.reset(addr)
-#define cpu_do_idle()                   processor._do_idle()
-#define cpu_dcache_clean_area(addr,sz)  processor.dcache_clean_area(addr,sz)
-#define cpu_set_pte_ext(ptep,pte,ext)   processor.set_pte_ext(ptep,pte,ext)
-#define cpu_do_switch_mm(pgd,mm)        processor.switch_mm(pgd,mm)
+#define cpu_proc_init                   processor._proc_init
+#define cpu_proc_fin                    processor._proc_fin
+#define cpu_reset                       processor.reset
+#define cpu_do_idle                     processor._do_idle
+#define cpu_dcache_clean_area           processor.dcache_clean_area
+#define cpu_set_pte_ext                 processor.set_pte_ext
+#define cpu_do_switch_mm                processor.switch_mm
 #endif
 
 extern void cpu_resume(void);
diff --git a/arch/arm/include/asm/scatterlist.h b/arch/arm/include/asm/scatterlist.h
index 2f87870d9347..cefdb8f898a1 100644
--- a/arch/arm/include/asm/scatterlist.h
+++ b/arch/arm/include/asm/scatterlist.h
@@ -1,6 +1,10 @@
 #ifndef _ASMARM_SCATTERLIST_H
 #define _ASMARM_SCATTERLIST_H
 
+#ifdef CONFIG_ARM_HAS_SG_CHAIN
+#define ARCH_HAS_SG_CHAIN
+#endif
+
 #include <asm/memory.h>
 #include <asm/types.h>
 #include <asm-generic/scatterlist.h>
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index ee2ad8ae07af..915696dd9c7c 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -187,12 +187,16 @@ struct tagtable {
 
 #define __tag __used __attribute__((__section__(".taglist.init")))
 #define __tagtable(tag, fn) \
-static struct tagtable __tagtable_##fn __tag = { tag, fn }
+static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 
 /*
  * Memory map description
  */
-#define NR_BANKS 8
+#ifdef CONFIG_ARCH_EP93XX
+# define NR_BANKS 16
+#else
+# define NR_BANKS 8
+#endif
 
 struct membank {
         phys_addr_t start;
diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h
new file mode 100644
index 000000000000..b0e4e1a02318
--- /dev/null
+++ b/arch/arm/include/asm/suspend.h
@@ -0,0 +1,22 @@
+#ifndef __ASM_ARM_SUSPEND_H
+#define __ASM_ARM_SUSPEND_H
+
+#include <asm/memory.h>
+#include <asm/tlbflush.h>
+
+extern void cpu_resume(void);
+
+/*
+ * Hide the first two arguments to __cpu_suspend - these are an implementation
+ * detail which platform code shouldn't have to know about.
+ */
+static inline int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+        extern int __cpu_suspend(int, long, unsigned long,
+                                 int (*)(unsigned long));
+        int ret = __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn);
+        flush_tlb_all();
+        return ret;
+}
+
+#endif
diff --git a/arch/arm/include/asm/tcm.h b/arch/arm/include/asm/tcm.h
index 5929ef5d927a..8578d726ad78 100644
--- a/arch/arm/include/asm/tcm.h
+++ b/arch/arm/include/asm/tcm.h
@@ -27,5 +27,7 @@
 
 void *tcm_alloc(size_t len);
 void tcm_free(void *addr, size_t len);
+bool tcm_dtcm_present(void);
+bool tcm_itcm_present(void);
 
 #endif
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index f90756dc16dc..5b29a6673625 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -3,6 +3,9 @@
 
 #include <linux/list.h>
 
+struct pt_regs;
+struct task_struct;
+
 struct undef_hook {
         struct list_head node;
         u32 instr_mask;
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 927522cfc12e..16baba2e4369 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -59,6 +59,9 @@ int main(void)
   DEFINE(TI_TP_VALUE,           offsetof(struct thread_info, tp_value));
   DEFINE(TI_FPSTATE,            offsetof(struct thread_info, fpstate));
   DEFINE(TI_VFPSTATE,           offsetof(struct thread_info, vfpstate));
+#ifdef CONFIG_SMP
+  DEFINE(VFP_CPU,               offsetof(union vfp_state, hard.cpu));
+#endif
 #ifdef CONFIG_ARM_THUMBEE
   DEFINE(TI_THUMBEE_STATE,      offsetof(struct thread_info, thumbee_state));
 #endif
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 90c62cd51ca9..fa02a22a4c4b 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -29,21 +29,53 @@
 #include <asm/entry-macro-multi.S>
 
 /*
- * Interrupt handling.  Preserves r7, r8, r9
+ * Interrupt handling.
  */
         .macro  irq_handler
 #ifdef CONFIG_MULTI_IRQ_HANDLER
-        ldr     r5, =handle_arch_irq
+        ldr     r1, =handle_arch_irq
         mov     r0, sp
-        ldr     r5, [r5]
+        ldr     r1, [r1]
         adr     lr, BSYM(9997f)
-        teq     r5, #0
-        movne   pc, r5
+        teq     r1, #0
+        movne   pc, r1
 #endif
         arch_irq_handler_default
 9997:
         .endm
 
+        .macro  pabt_helper
+        @ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5
+#ifdef MULTI_PABORT
+        ldr     ip, .LCprocfns
+        mov     lr, pc
+        ldr     pc, [ip, #PROCESSOR_PABT_FUNC]
+#else
+        bl      CPU_PABORT_HANDLER
+#endif
+        .endm
+
+        .macro  dabt_helper
+
+        @
+        @ Call the processor-specific abort handler:
+        @
+        @  r2 - pt_regs
+        @  r4 - aborted context pc
+        @  r5 - aborted context psr
+        @
+        @ The abort handler must return the aborted address in r0, and
+        @ the fault status register in r1.  r9 must be preserved.
+        @
+#ifdef MULTI_DABORT
+        ldr     ip, .LCprocfns
+        mov     lr, pc
+        ldr     pc, [ip, #PROCESSOR_DABT_FUNC]
+#else
+        bl      CPU_DABORT_HANDLER
+#endif
+        .endm
+
 #ifdef CONFIG_KPROBES
         .section        .kprobes.text,"ax",%progbits
 #else
@@ -126,106 +158,74 @@ ENDPROC(__und_invalid)
  SPFIX( subeq   sp, sp, #4      )
         stmia   sp, {r1 - r12}
 
-        ldmia   r0, {r1 - r3}
-        add     r5, sp, #S_SP - 4       @ here for interlock avoidance
-        mov     r4, #-1                 @  ""  ""      ""       ""
-        add     r0, sp, #(S_FRAME_SIZE + \stack_hole - 4)
- SPFIX( addeq   r0, r0, #4      )
-        str     r1, [sp, #-4]!          @ save the "real" r0 copied
+        ldmia   r0, {r3 - r5}
+        add     r7, sp, #S_SP - 4       @ here for interlock avoidance
+        mov     r6, #-1                 @  ""  ""      ""       ""
+        add     r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+ SPFIX( addeq   r2, r2, #4      )
+        str     r3, [sp, #-4]!          @ save the "real" r0 copied
                                         @ from the exception stack
 
-        mov     r1, lr
+        mov     r3, lr
 
         @
         @ We are now ready to fill in the remaining blanks on the stack:
         @
-        @  r0 - sp_svc
-        @  r1 - lr_svc
-        @  r2 - lr_<exception>, already fixed up for correct return/restart
-        @  r3 - spsr_<exception>
-        @  r4 - orig_r0 (see pt_regs definition in ptrace.h)
+        @  r2 - sp_svc
+        @  r3 - lr_svc
+        @  r4 - lr_<exception>, already fixed up for correct return/restart
+        @  r5 - spsr_<exception>
+        @  r6 - orig_r0 (see pt_regs definition in ptrace.h)
         @
-        stmia   r5, {r0 - r4}
+        stmia   r7, {r2 - r6}
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+        bl      trace_hardirqs_off
+#endif
         .endm
 
         .align  5
 __dabt_svc:
         svc_entry
-
-        @
-        @ get ready to re-enable interrupts if appropriate
-        @
-        mrs     r9, cpsr
-        tst     r3, #PSR_I_BIT
-        biceq   r9, r9, #PSR_I_BIT
-
-        @
-        @ Call the processor-specific abort handler:
-        @
-        @  r2 - aborted context pc
-        @  r3 - aborted context cpsr
-        @
-        @ The abort handler must return the aborted address in r0, and
-        @ the fault status register in r1.  r9 must be preserved.
-        @
-#ifdef MULTI_DABORT
-        ldr     r4, .LCprocfns
-        mov     lr, pc
-        ldr     pc, [r4, #PROCESSOR_DABT_FUNC]
-#else
-        bl      CPU_DABORT_HANDLER
-#endif
-
-        @
-        @ set desired IRQ state, then call main handler
-        @
-        debug_entry r1
-        msr     cpsr_c, r9
         mov     r2, sp
-        bl      do_DataAbort
+        dabt_helper
 
         @
         @ IRQs off again before pulling preserved data off the stack
         @
         disable_irq_notrace
 
-        @
-        @ restore SPSR and restart the instruction
-        @
-        ldr     r2, [sp, #S_PSR]
-        svc_exit r2                             @ return from exception
+#ifdef CONFIG_TRACE_IRQFLAGS
+        tst     r5, #PSR_I_BIT
+        bleq    trace_hardirqs_on
+        tst     r5, #PSR_I_BIT
+        blne    trace_hardirqs_off
+#endif
+        svc_exit r5                             @ return from exception
  UNWIND(.fnend          )
 ENDPROC(__dabt_svc)
 
         .align  5
 __irq_svc:
         svc_entry
+        irq_handler
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-        bl      trace_hardirqs_off
-#endif
 #ifdef CONFIG_PREEMPT
         get_thread_info tsk
         ldr     r8, [tsk, #TI_PREEMPT]          @ get preempt count
-        add     r7, r8, #1                      @ increment it
-        str     r7, [tsk, #TI_PREEMPT]
-#endif
-
-        irq_handler
-#ifdef CONFIG_PREEMPT
-        str     r8, [tsk, #TI_PREEMPT]          @ restore preempt count
         ldr     r0, [tsk, #TI_FLAGS]            @ get flags
         teq     r8, #0                          @ if preempt count != 0
         movne   r0, #0                          @ force flags to 0
         tst     r0, #_TIF_NEED_RESCHED
         blne    svc_preempt
 #endif
-        ldr     r4, [sp, #S_PSR]                @ irqs are already disabled
+
 #ifdef CONFIG_TRACE_IRQFLAGS
-        tst     r4, #PSR_I_BIT
-        bleq    trace_hardirqs_on
+        @ The parent context IRQs must have been enabled to get here in
+        @ the first place, so there's no point checking the PSR I bit.
+        bl      trace_hardirqs_on
 #endif
-        svc_exit r4                             @ return from exception
+        svc_exit r5                             @ return from exception
  UNWIND(.fnend          )
 ENDPROC(__irq_svc)
 
@@ -251,7 +251,6 @@ __und_svc:
 #else
         svc_entry
 #endif
-
         @
         @ call emulation code, which returns using r9 if it has emulated
         @ the instruction, or the more conventional lr if we are to treat
@@ -260,15 +259,16 @@ __und_svc:
         @  r0 - instruction
         @
 #ifndef CONFIG_THUMB2_KERNEL
-        ldr     r0, [r2, #-4]
+        ldr     r0, [r4, #-4]
 #else
-        ldrh    r0, [r2, #-2]                   @ Thumb instruction at LR - 2
+        ldrh    r0, [r4, #-2]                   @ Thumb instruction at LR - 2
         and     r9, r0, #0xf800
         cmp     r9, #0xe800                     @ 32-bit instruction if xx >= 0
-        ldrhhs  r9, [r2]                        @ bottom 16 bits
+        ldrhhs  r9, [r4]                        @ bottom 16 bits
         orrhs   r0, r9, r0, lsl #16
 #endif
         adr     r9, BSYM(1f)
+        mov     r2, r4
         bl      call_fpe
 
         mov     r0, sp                          @ struct pt_regs *regs
@@ -282,45 +282,35 @@ __und_svc:
         @
         @ restore SPSR and restart the instruction
         @
-        ldr     r2, [sp, #S_PSR]                @ Get SVC cpsr
-        svc_exit r2                             @ return from exception
+        ldr     r5, [sp, #S_PSR]                @ Get SVC cpsr
+#ifdef CONFIG_TRACE_IRQFLAGS
+        tst     r5, #PSR_I_BIT
+        bleq    trace_hardirqs_on
+        tst     r5, #PSR_I_BIT
+        blne    trace_hardirqs_off
+#endif
+        svc_exit r5                             @ return from exception
  UNWIND(.fnend          )
 ENDPROC(__und_svc)
 
         .align  5
 __pabt_svc:
         svc_entry
-
-        @
-        @ re-enable interrupts if appropriate
-        @
-        mrs     r9, cpsr
-        tst     r3, #PSR_I_BIT
-        biceq   r9, r9, #PSR_I_BIT
-
-        mov     r0, r2                  @ pass address of aborted instruction.
-#ifdef MULTI_PABORT
-        ldr     r4, .LCprocfns
-        mov     lr, pc
-        ldr     pc, [r4, #PROCESSOR_PABT_FUNC]
-#else
-        bl      CPU_PABORT_HANDLER
-#endif
-        debug_entry r1
-        msr     cpsr_c, r9                      @ Maybe enable interrupts
         mov     r2, sp                          @ regs
-        bl      do_PrefetchAbort                @ call abort handler
+        pabt_helper
 
         @
         @ IRQs off again before pulling preserved data off the stack
         @
         disable_irq_notrace
 
-        @
-        @ restore SPSR and restart the instruction
-        @
-        ldr     r2, [sp, #S_PSR]
-        svc_exit r2                             @ return from exception
+#ifdef CONFIG_TRACE_IRQFLAGS
+        tst     r5, #PSR_I_BIT
+        bleq    trace_hardirqs_on
+        tst     r5, #PSR_I_BIT
+        blne    trace_hardirqs_off
+#endif
+        svc_exit r5                             @ return from exception
  UNWIND(.fnend          )
 ENDPROC(__pabt_svc)
 
@@ -351,23 +341,23 @@ ENDPROC(__pabt_svc)
  ARM(   stmib   sp, {r1 - r12}  )
  THUMB( stmia   sp, {r0 - r12}  )
 
-        ldmia   r0, {r1 - r3}
+        ldmia   r0, {r3 - r5}
         add     r0, sp, #S_PC           @ here for interlock avoidance
-        mov     r4, #-1                 @  ""  ""     ""        ""
+        mov     r6, #-1                 @  ""  ""     ""        ""
 
-        str     r1, [sp]                @ save the "real" r0 copied
+        str     r3, [sp]                @ save the "real" r0 copied
                                         @ from the exception stack
 
         @
         @ We are now ready to fill in the remaining blanks on the stack:
         @
-        @  r2 - lr_<exception>, already fixed up for correct return/restart
-        @  r3 - spsr_<exception>
-        @  r4 - orig_r0 (see pt_regs definition in ptrace.h)
+        @  r4 - lr_<exception>, already fixed up for correct return/restart
+        @  r5 - spsr_<exception>
+        @  r6 - orig_r0 (see pt_regs definition in ptrace.h)
         @
         @ Also, separately save sp_usr and lr_usr
         @
-        stmia   r0, {r2 - r4}
+        stmia   r0, {r4 - r6}
  ARM(   stmdb   r0, {sp, lr}^                   )
  THUMB( store_user_sp_lr r0, r1, S_SP - S_PC    )
 
@@ -380,6 +370,10 @@ ENDPROC(__pabt_svc)
         @ Clear FP to mark the first stack frame
         @
         zero_fp
+
+#ifdef CONFIG_IRQSOFF_TRACER
+        bl      trace_hardirqs_off
+#endif
         .endm
 
         .macro  kuser_cmpxchg_check
@@ -391,7 +385,7 @@ ENDPROC(__pabt_svc)
         @ if it was interrupted in a critical region.  Here we
         @ perform a quick test inline since it should be false
         @ 99.9999% of the time.  The rest is done out of line.
-        cmp     r2, #TASK_SIZE
+        cmp     r4, #TASK_SIZE
         blhs    kuser_cmpxchg_fixup
 #endif
 #endif
@@ -401,32 +395,9 @@ ENDPROC(__pabt_svc)
 __dabt_usr:
         usr_entry
         kuser_cmpxchg_check
-
-        @
-        @ Call the processor-specific abort handler:
-        @
-        @  r2 - aborted context pc
-        @  r3 - aborted context cpsr
-        @
-        @ The abort handler must return the aborted address in r0, and
-        @ the fault status register in r1.
-        @
-#ifdef MULTI_DABORT
-        ldr     r4, .LCprocfns
-        mov     lr, pc
-        ldr     pc, [r4, #PROCESSOR_DABT_FUNC]
-#else
-        bl      CPU_DABORT_HANDLER
-#endif
-
-        @
-        @ IRQs on, then call the main handler
-        @
-        debug_entry r1
-        enable_irq
         mov     r2, sp
-        adr     lr, BSYM(ret_from_exception)
-        b       do_DataAbort
+        dabt_helper
+        b       ret_from_exception
  UNWIND(.fnend          )
 ENDPROC(__dabt_usr)
 
@@ -434,28 +405,8 @@ ENDPROC(__dabt_usr)
 __irq_usr:
         usr_entry
         kuser_cmpxchg_check
-
-#ifdef CONFIG_IRQSOFF_TRACER
-        bl      trace_hardirqs_off
-#endif
-
-        get_thread_info tsk
-#ifdef CONFIG_PREEMPT
-        ldr     r8, [tsk, #TI_PREEMPT]          @ get preempt count
-        add     r7, r8, #1                      @ increment it
-        str     r7, [tsk, #TI_PREEMPT]
-#endif
-
         irq_handler
-#ifdef CONFIG_PREEMPT
-        ldr     r0, [tsk, #TI_PREEMPT]
-        str     r8, [tsk, #TI_PREEMPT]
-        teq     r0, r7
- ARM(   strne   r0, [r0, -r0]   )
- THUMB( movne   r0, #0          )
- THUMB( strne   r0, [r0]        )
-#endif
-
+        get_thread_info tsk
         mov     why, #0
         b       ret_to_user_from_irq
  UNWIND(.fnend          )
@@ -467,6 +418,9 @@ ENDPROC(__irq_usr)
 __und_usr:
         usr_entry
 
+        mov     r2, r4
+        mov     r3, r5
+
         @
         @ fall through to the emulation code, which returns using r9 if
         @ it has emulated the instruction, or the more conventional lr
@@ -682,19 +636,8 @@ ENDPROC(__und_usr_unknown)
         .align  5
 __pabt_usr:
         usr_entry
-
-        mov     r0, r2                  @ pass address of aborted instruction.
-#ifdef MULTI_PABORT
-        ldr     r4, .LCprocfns
-        mov     lr, pc
-        ldr     pc, [r4, #PROCESSOR_PABT_FUNC]
-#else
-        bl      CPU_PABORT_HANDLER
-#endif
-        debug_entry r1
-        enable_irq                              @ Enable interrupts
         mov     r2, sp                          @ regs
-        bl      do_PrefetchAbort                @ call abort handler
+        pabt_helper
  UNWIND(.fnend          )
         /* fall through */
 /*
@@ -927,13 +870,13 @@ __kuser_cmpxchg:				@ 0xffff0fc0
         .text
 kuser_cmpxchg_fixup:
         @ Called from kuser_cmpxchg_check macro.
-        @ r2 = address of interrupted insn (must be preserved).
+        @ r4 = address of interrupted insn (must be preserved).
         @ sp = saved regs. r7 and r8 are clobbered.
         @ 1b = first critical insn, 2b = last critical insn.
-        @ If r2 >= 1b and r2 <= 2b then saved pc_usr is set to 1b.
+        @ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b.
         mov     r7, #0xffff0fff
         sub     r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg)))
-        subs    r8, r2, r7
+        subs    r8, r4, r7
         rsbcss  r8, r8, #(2b - 1b)
         strcs   r7, [sp, #S_PC]
         mov     pc, lr
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 051166c2a932..4d6ad8348e89 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -165,25 +165,6 @@
         .endm
 #endif  /* !CONFIG_THUMB2_KERNEL */
 
-        @
-        @ Debug exceptions are taken as prefetch or data aborts.
-        @ We must disable preemption during the handler so that
-        @ we can access the debug registers safely.
-        @
-        .macro  debug_entry, fsr
-#if defined(CONFIG_HAVE_HW_BREAKPOINT) && defined(CONFIG_PREEMPT)
-        ldr     r4, =0x40f              @ mask out fsr.fs
-        and     r5, r4, \fsr
-        cmp     r5, #2                  @ debug exception
-        bne     1f
-        get_thread_info r10
-        ldr     r6, [r10, #TI_PREEMPT]  @ get preempt count
-        add     r11, r6, #1             @ increment it
-        str     r11, [r10, #TI_PREEMPT]
-1:
-#endif
-        .endm
-
 /*
  * These are the registers used in the syscall handler, and allow us to
  * have in theory up to 7 arguments to a function - r0 to r6.
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 6b1e0ad9ec3b..d46f25968bec 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -32,8 +32,16 @@
  * numbers for r1.
  *
  */
+        .arm
+
         __HEAD
 ENTRY(stext)
+
+ THUMB( adr     r9, BSYM(1f)    )       @ Kernel is always entered in ARM.
+ THUMB( bx      r9              )       @ If this is a Thumb-2 kernel,
+ THUMB( .thumb                  )       @ switch to Thumb now.
+ THUMB(1:                       )
+
         setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
                                                 @ and irqs disabled
 #ifndef CONFIG_CPU_CP15
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 278c1b0ebb2e..742b6108a001 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -71,8 +71,16 @@
  * crap here - that's what the boot loader (or in extreme, well justified
  * circumstances, zImage) is for.
  */
+        .arm
+
         __HEAD
 ENTRY(stext)
+
+ THUMB( adr     r9, BSYM(1f)    )       @ Kernel is always entered in ARM.
+ THUMB( bx      r9              )       @ If this is a Thumb-2 kernel,
+ THUMB( .thumb                  )       @ switch to Thumb now.
+ THUMB(1:                       )
+
         setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
                                                 @ and irqs disabled
         mrc     p15, 0, r9, c0, c0              @ get processor id
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 87acc25d7a3e..a927ca1f5566 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -796,7 +796,7 @@ unlock:
 
 /*
  * Called from either the Data Abort Handler [watchpoint] or the
- * Prefetch Abort Handler [breakpoint] with preemption disabled.
+ * Prefetch Abort Handler [breakpoint] with interrupts disabled.
  */
 static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
                                  struct pt_regs *regs)
@@ -804,8 +804,10 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
         int ret = 0;
         u32 dscr;
 
-        /* We must be called with preemption disabled. */
-        WARN_ON(preemptible());
+        preempt_disable();
+
+        if (interrupts_enabled(regs))
+                local_irq_enable();
 
         /* We only handle watchpoints and hardware breakpoints. */
         ARM_DBG_READ(c1, 0, dscr);
@@ -824,10 +826,6 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
                 ret = 1; /* Unhandled fault. */
         }
 
-        /*
-         * Re-enable preemption after it was disabled in the
-         * low-level exception handling code.
-         */
         preempt_enable();
 
         return ret;
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 83bbad03fcc6..0f928a131af8 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -131,54 +131,63 @@ int __init arch_probe_nr_irqs(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static bool migrate_one_irq(struct irq_data *d)
+static bool migrate_one_irq(struct irq_desc *desc)
 {
-        unsigned int cpu = cpumask_any_and(d->affinity, cpu_online_mask);
+        struct irq_data *d = irq_desc_get_irq_data(desc);
+        const struct cpumask *affinity = d->affinity;
+        struct irq_chip *c;
         bool ret = false;
 
-        if (cpu >= nr_cpu_ids) {
-                cpu = cpumask_any(cpu_online_mask);
+        /*
+         * If this is a per-CPU interrupt, or the affinity does not
+         * include this CPU, then we have nothing to do.
+         */
+        if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
+                return false;
+
+        if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+                affinity = cpu_online_mask;
                 ret = true;
         }
 
-        pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", d->irq, d->node, cpu);
-
-        d->chip->irq_set_affinity(d, cpumask_of(cpu), true);
+        c = irq_data_get_irq_chip(d);
+        if (c->irq_set_affinity)
+                c->irq_set_affinity(d, affinity, true);
+        else
+                pr_debug("IRQ%u: unable to set affinity\n", d->irq);
 
         return ret;
 }
 
 /*
- * The CPU has been marked offline.  Migrate IRQs off this CPU.  If
- * the affinity settings do not allow other CPUs, force them onto any
+ * The current CPU has been marked offline.  Migrate IRQs off this CPU.
+ * If the affinity settings do not allow other CPUs, force them onto any
  * available CPU.
+ *
+ * Note: we must iterate over all IRQs, whether they have an attached
+ * action structure or not, as we need to get chained interrupts too.
  */
 void migrate_irqs(void)
 {
-        unsigned int i, cpu = smp_processor_id();
+        unsigned int i;
         struct irq_desc *desc;
         unsigned long flags;
 
         local_irq_save(flags);
 
         for_each_irq_desc(i, desc) {
-                struct irq_data *d = &desc->irq_data;
                 bool affinity_broken = false;
 
-                raw_spin_lock(&desc->lock);
-                do {
-                        if (desc->action == NULL)
-                                break;
-
-                        if (d->node != cpu)
-                                break;
+                if (!desc)
+                        continue;
 
-                        affinity_broken = migrate_one_irq(d);
-                } while (0);
+                raw_spin_lock(&desc->lock);
+                affinity_broken = migrate_one_irq(desc);
                 raw_spin_unlock(&desc->lock);
 
                 if (affinity_broken && printk_ratelimit())
-                        pr_warning("IRQ%u no longer affine to CPU%u\n", i, cpu);
+                        pr_warning("IRQ%u no longer affine to CPU%u\n", i,
+                                smp_processor_id());
         }
 
         local_irq_restore(flags);
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index fee7c36349eb..016d6a0830a3 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -193,8 +193,17 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                                 offset -= 0x02000000;
                         offset += sym->st_value - loc;
 
-                        /* only Thumb addresses allowed (no interworking) */
-                        if (!(offset & 1) ||
+                        /*
+                         * For function symbols, only Thumb addresses are
+                         * allowed (no interworking).
+                         *
+                         * For non-function symbols, the destination
+                         * has no specific ARM/Thumb disposition, so
+                         * the branch is resolved under the assumption
+                         * that interworking is not required.
+                         */
+                        if ((ELF32_ST_TYPE(sym->st_info) == STT_FUNC &&
+                                !(offset & 1)) ||
                             offset <= (s32)0xff000000 ||
                             offset >= (s32)0x01000000) {
                                 pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index d53c0abc4dd3..8d8507858e5c 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -435,7 +435,7 @@ armpmu_reserve_hardware(void)
                         if (irq >= 0)
                                 free_irq(irq, NULL);
                 }
-                release_pmu(pmu_device);
+                release_pmu(ARM_PMU_DEVICE_CPU);
                 pmu_device = NULL;
         }
 
@@ -454,7 +454,7 @@ armpmu_release_hardware(void)
         }
         armpmu->stop();
 
-        release_pmu(pmu_device);
+        release_pmu(ARM_PMU_DEVICE_CPU);
         pmu_device = NULL;
 }
 
@@ -583,7 +583,7 @@ static int armpmu_event_init(struct perf_event *event)
 static void armpmu_enable(struct pmu *pmu)
 {
         /* Enable all of the perf events on hardware. */
-        int idx;
+        int idx, enabled = 0;
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
         if (!armpmu)
@@ -596,9 +596,11 @@ static void armpmu_enable(struct pmu *pmu)
                         continue;
 
                 armpmu->enable(&event->hw, idx);
+                enabled = 1;
         }
 
-        armpmu->start();
+        if (enabled)
+                armpmu->start();
 }
 
 static void armpmu_disable(struct pmu *pmu)
diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c
index 2c79eec19262..2b70709376c3 100644
--- a/arch/arm/kernel/pmu.c
+++ b/arch/arm/kernel/pmu.c
@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 
 #include <asm/pmu.h>
@@ -25,36 +26,88 @@ static volatile long pmu_lock;
 
 static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES];
 
-static int __devinit pmu_device_probe(struct platform_device *pdev)
+static int __devinit pmu_register(struct platform_device *pdev,
+                                        enum arm_pmu_type type)
 {
-
-        if (pdev->id < 0 || pdev->id >= ARM_NUM_PMU_DEVICES) {
+        if (type < 0 || type >= ARM_NUM_PMU_DEVICES) {
                 pr_warning("received registration request for unknown "
-                                "device %d\n", pdev->id);
+                                "device %d\n", type);
                 return -EINVAL;
         }
 
-        if (pmu_devices[pdev->id])
-                pr_warning("registering new PMU device type %d overwrites "
-                                "previous registration!\n", pdev->id);
-        else
-                pr_info("registered new PMU device of type %d\n",
-                                pdev->id);
+        if (pmu_devices[type]) {
+                pr_warning("rejecting duplicate registration of PMU device "
+                        "type %d.", type);
+                return -ENOSPC;
+        }
 
-        pmu_devices[pdev->id] = pdev;
+        pr_info("registered new PMU device of type %d\n", type);
+        pmu_devices[type] = pdev;
         return 0;
 }
 
-static struct platform_driver pmu_driver = {
+#define OF_MATCH_PMU(_name, _type) {    \
+        .compatible = _name,            \
+        .data = (void *)_type,          \
+}
+
+#define OF_MATCH_CPU(name)      OF_MATCH_PMU(name, ARM_PMU_DEVICE_CPU)
+
+static struct of_device_id armpmu_of_device_ids[] = {
+        OF_MATCH_CPU("arm,cortex-a9-pmu"),
+        OF_MATCH_CPU("arm,cortex-a8-pmu"),
+        OF_MATCH_CPU("arm,arm1136-pmu"),
+        OF_MATCH_CPU("arm,arm1176-pmu"),
+        {},
+};
+
+#define PLAT_MATCH_PMU(_name, _type) {  \
+        .name           = _name,        \
+        .driver_data    = _type,        \
+}
+
+#define PLAT_MATCH_CPU(_name)   PLAT_MATCH_PMU(_name, ARM_PMU_DEVICE_CPU)
+
+static struct platform_device_id armpmu_plat_device_ids[] = {
+        PLAT_MATCH_CPU("arm-pmu"),
+        {},
+};
+
+enum arm_pmu_type armpmu_device_type(struct platform_device *pdev)
+{
+        const struct of_device_id       *of_id;
+        const struct platform_device_id *pdev_id;
+
+        /* provided by of_device_id table */
+        if (pdev->dev.of_node) {
+                of_id = of_match_device(armpmu_of_device_ids, &pdev->dev);
+                BUG_ON(!of_id);
+                return (enum arm_pmu_type)of_id->data;
+        }
+
+        /* Provided by platform_device_id table */
+        pdev_id = platform_get_device_id(pdev);
+        BUG_ON(!pdev_id);
+        return pdev_id->driver_data;
+}
+
+static int __devinit armpmu_device_probe(struct platform_device *pdev)
+{
+        return pmu_register(pdev, armpmu_device_type(pdev));
+}
+
+static struct platform_driver armpmu_driver = {
         .driver         = {
                 .name   = "arm-pmu",
+                .of_match_table = armpmu_of_device_ids,
         },
-        .probe          = pmu_device_probe,
+        .probe          = armpmu_device_probe,
+        .id_table       = armpmu_plat_device_ids,
 };
 
 static int __init register_pmu_driver(void)
 {
-        return platform_driver_register(&pmu_driver);
+        return platform_driver_register(&armpmu_driver);
 }
 device_initcall(register_pmu_driver);
 
@@ -77,11 +130,11 @@ reserve_pmu(enum arm_pmu_type device)
 EXPORT_SYMBOL_GPL(reserve_pmu);
 
 int
-release_pmu(struct platform_device *pdev)
+release_pmu(enum arm_pmu_type device)
 {
-        if (WARN_ON(pdev != pmu_devices[pdev->id]))
+        if (WARN_ON(!pmu_devices[device]))
                 return -EINVAL;
-        clear_bit_unlock(pdev->id, &pmu_lock);
+        clear_bit_unlock(device, &pmu_lock);
         return 0;
 }
 EXPORT_SYMBOL_GPL(release_pmu);
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index ed11fb08b05a..9c3278f37796 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -73,6 +73,7 @@ __setup("fpe=", fpe_setup);
 #endif
 
 extern void paging_init(struct machine_desc *desc);
+extern void sanity_check_meminfo(void);
 extern void reboot_setup(char *str);
 
 unsigned int processor_id;
@@ -342,54 +343,6 @@ static void __init feat_v6_fixup(void)
                 elf_hwcap &= ~HWCAP_TLS;
 }
 
-static void __init setup_processor(void)
-{
-        struct proc_info_list *list;
-
-        /*
-         * locate processor in the list of supported processor
-         * types.  The linker builds this table for us from the
-         * entries in arch/arm/mm/proc-*.S
-         */
-        list = lookup_processor_type(read_cpuid_id());
-        if (!list) {
-                printk("CPU configuration botched (ID %08x), unable "
-                       "to continue.\n", read_cpuid_id());
-                while (1);
-        }
-
-        cpu_name = list->cpu_name;
-
-#ifdef MULTI_CPU
-        processor = *list->proc;
-#endif
-#ifdef MULTI_TLB
-        cpu_tlb = *list->tlb;
-#endif
-#ifdef MULTI_USER
-        cpu_user = *list->user;
-#endif
-#ifdef MULTI_CACHE
-        cpu_cache = *list->cache;
-#endif
-
-        printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
-               cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
-               proc_arch[cpu_architecture()], cr_alignment);
-
-        sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS);
-        sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS);
-        elf_hwcap = list->elf_hwcap;
-#ifndef CONFIG_ARM_THUMB
-        elf_hwcap &= ~HWCAP_THUMB;
-#endif
-
-        feat_v6_fixup();
-
-        cacheid_init();
-        cpu_proc_init();
-}
-
 /*
  * cpu_init - initialise one CPU.
  *
@@ -405,6 +358,8 @@ void cpu_init(void)
                 BUG();
         }
 
+        cpu_proc_init();
+
         /*
          * Define the placement constraint for the inline asm directive below.
          * In Thumb-2, msr with an immediate value is not allowed.
@@ -441,6 +396,54 @@ void cpu_init(void)
             : "r14");
 }
 
+static void __init setup_processor(void)
+{
+        struct proc_info_list *list;
+
+        /*
+         * locate processor in the list of supported processor
+         * types.  The linker builds this table for us from the
+         * entries in arch/arm/mm/proc-*.S
+         */
+        list = lookup_processor_type(read_cpuid_id());
+        if (!list) {
+                printk("CPU configuration botched (ID %08x), unable "
+                       "to continue.\n", read_cpuid_id());
+                while (1);
+        }
+
+        cpu_name = list->cpu_name;
+
+#ifdef MULTI_CPU
+        processor = *list->proc;
+#endif
+#ifdef MULTI_TLB
+        cpu_tlb = *list->tlb;
+#endif
+#ifdef MULTI_USER
+        cpu_user = *list->user;
+#endif
+#ifdef MULTI_CACHE
+        cpu_cache = *list->cache;
+#endif
+
+        printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
+               cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
+               proc_arch[cpu_architecture()], cr_alignment);
+
+        sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS);
+        sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS);
+        elf_hwcap = list->elf_hwcap;
+#ifndef CONFIG_ARM_THUMB
+        elf_hwcap &= ~HWCAP_THUMB;
+#endif
+
+        feat_v6_fixup();
+
+        cacheid_init();
+        cpu_init();
+}
+
 void __init dump_machine_table(void)
 {
         struct machine_desc *p;
@@ -900,6 +903,7 @@ void __init setup_arch(char **cmdline_p)
 
         parse_early_param();
 
+        sanity_check_meminfo();
         arm_memblock_init(&meminfo, mdesc);
 
         paging_init(mdesc);
@@ -913,7 +917,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
         reserve_crashkernel();
 
-        cpu_init();
         tcm_init();
 
 #ifdef CONFIG_MULTI_IRQ_HANDLER
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 6398ead9d1c0..dc902f2c6845 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -10,64 +10,61 @@
 /*
  * Save CPU state for a suspend
  *  r1 = v:p offset
- *  r3 = virtual return function
- * Note: sp is decremented to allocate space for CPU state on stack
- * r0-r3,r9,r10,lr corrupted
+ *  r2 = suspend function arg0
+ *  r3 = suspend function
  */
-ENTRY(cpu_suspend)
-        mov     r9, lr
+ENTRY(__cpu_suspend)
+        stmfd   sp!, {r4 - r11, lr}
 #ifdef MULTI_CPU
         ldr     r10, =processor
-        mov     r2, sp                  @ current virtual SP
-        ldr     r0, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
+        ldr     r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
         ldr     ip, [r10, #CPU_DO_RESUME] @ virtual resume function
-        sub     sp, sp, r0              @ allocate CPU state on stack
-        mov     r0, sp                  @ save pointer
+#else
+        ldr     r5, =cpu_suspend_size
+        ldr     ip, =cpu_do_resume
+#endif
+        mov     r6, sp                  @ current virtual SP
+        sub     sp, sp, r5              @ allocate CPU state on stack
+        mov     r0, sp                  @ save pointer to CPU save block
         add     ip, ip, r1              @ convert resume fn to phys
-        stmfd   sp!, {r1, r2, r3, ip}   @ save v:p, virt SP, retfn, phys resume fn
-        ldr     r3, =sleep_save_sp
-        add     r2, sp, r1              @ convert SP to phys
+        stmfd   sp!, {r1, r6, ip}       @ save v:p, virt SP, phys resume fn
+        ldr     r5, =sleep_save_sp
+        add     r6, sp, r1              @ convert SP to phys
+        stmfd   sp!, {r2, r3}           @ save suspend func arg and pointer
 #ifdef CONFIG_SMP
         ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
         ALT_UP(mov lr, #0)
         and     lr, lr, #15
-        str     r2, [r3, lr, lsl #2]    @ save phys SP
+        str     r6, [r5, lr, lsl #2]    @ save phys SP
 #else
-        str     r2, [r3]                @ save phys SP
+        str     r6, [r5]                @ save phys SP
 #endif
+#ifdef MULTI_CPU
         mov     lr, pc
         ldr     pc, [r10, #CPU_DO_SUSPEND] @ save CPU state
 #else
-        mov     r2, sp                  @ current virtual SP
-        ldr     r0, =cpu_suspend_size
-        sub     sp, sp, r0              @ allocate CPU state on stack
-        mov     r0, sp                  @ save pointer
-        stmfd   sp!, {r1, r2, r3}       @ save v:p, virt SP, return fn
-        ldr     r3, =sleep_save_sp
-        add     r2, sp, r1              @ convert SP to phys
-#ifdef CONFIG_SMP
-        ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
-        ALT_UP(mov lr, #0)
-        and     lr, lr, #15
-        str     r2, [r3, lr, lsl #2]    @ save phys SP
-#else
-        str     r2, [r3]                @ save phys SP
-#endif
         bl      cpu_do_suspend
 #endif
 
         @ flush data cache
 #ifdef MULTI_CACHE
         ldr     r10, =cpu_cache
-        mov     lr, r9
+        mov     lr, pc
         ldr     pc, [r10, #CACHE_FLUSH_KERN_ALL]
 #else
-        mov     lr, r9
-        b       __cpuc_flush_kern_all
+        bl      __cpuc_flush_kern_all
 #endif
-ENDPROC(cpu_suspend)
+        adr     lr, BSYM(cpu_suspend_abort)
+        ldmfd   sp!, {r0, pc}           @ call suspend fn
+ENDPROC(__cpu_suspend)
         .ltorg
 
+cpu_suspend_abort:
+        ldmia   sp!, {r1 - r3}          @ pop v:p, virt SP, phys resume fn
+        mov     sp, r2
+        ldmfd   sp!, {r4 - r11, pc}
+ENDPROC(cpu_suspend_abort)
+
 /*
  * r0 = control register value
  * r1 = v:p offset (preserved by cpu_do_resume)
@@ -97,7 +94,9 @@ ENDPROC(cpu_resume_turn_mmu_on)
 cpu_resume_after_mmu:
         str     r5, [r2, r4, lsl #2]    @ restore old mapping
         mcr     p15, 0, r0, c1, c0, 0   @ turn on D-cache
-        mov     pc, lr
+        bl      cpu_init                @ restore the und/abt/irq banked regs
+        mov     r0, #0                  @ return zero on success
+        ldmfd   sp!, {r4 - r11, pc}
 ENDPROC(cpu_resume_after_mmu)
 
 /*
@@ -120,20 +119,11 @@ ENTRY(cpu_resume)
         ldr     r0, sleep_save_sp       @ stack phys addr
 #endif
         setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1  @ set SVC, irqs off
-#ifdef MULTI_CPU
-        @ load v:p, stack, return fn, resume fn
-  ARM(  ldmia   r0!, {r1, sp, lr, pc}   )
-THUMB(  ldmia   r0!, {r1, r2, r3, r4}   )
+        @ load v:p, stack, resume fn
+  ARM(  ldmia   r0!, {r1, sp, pc}       )
+THUMB(  ldmia   r0!, {r1, r2, r3}       )
 THUMB(  mov     sp, r2                  )
-THUMB(  mov     lr, r3                  )
-THUMB(  bx      r4                      )
-#else
-        @ load v:p, stack, return fn
-  ARM(  ldmia   r0!, {r1, sp, lr}       )
-THUMB(  ldmia   r0!, {r1, r2, lr}       )
-THUMB(  mov     sp, r2                  )
-        b       cpu_do_resume
-#endif
+THUMB(  bx      r3                      )
 ENDPROC(cpu_resume)
 
 sleep_save_sp:
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 344e52b16c8c..167e3cbe1f2f 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -318,9 +318,13 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
         smp_store_cpu_info(cpu);
 
         /*
-         * OK, now it's safe to let the boot CPU continue
+         * OK, now it's safe to let the boot CPU continue.  Wait for
+         * the CPU migration code to notice that the CPU is online
+         * before we continue.
          */
         set_cpu_online(cpu, true);
+        while (!cpu_active(cpu))
+                cpu_relax();
 
         /*
          * OK, it's off to the idle thread for us
@@ -361,8 +365,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
          */
         if (max_cpus > ncores)
                 max_cpus = ncores;
-
-        if (max_cpus > 1) {
+        if (ncores > 1 && max_cpus) {
                 /*
                  * Enable the local timer or broadcast device for the
                  * boot CPU, but only if we have more than one CPU.
@@ -370,6 +373,14 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
                 percpu_timer_setup();
 
                 /*
+                 * Initialise the present map, which describes the set of CPUs
+                 * actually populated at the present time. A platform should
+                 * re-initialize the map in platform_smp_prepare_cpus() if
+                 * present != possible (e.g. physical hotplug).
+                 */
+                init_cpu_present(&cpu_possible_map);
+
+                /*
                  * Initialise the SCU if there are more than one CPU
                  * and let them know where to start.
                  */
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index a1e757c3439b..79ed5e7f204a 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -20,6 +20,7 @@
 #define SCU_INVALIDATE          0x0c
 #define SCU_FPGA_REVISION       0x10
 
+#ifdef CONFIG_SMP
 /*
  * Get the number of CPU cores from the SCU configuration
  */
@@ -50,6 +51,7 @@ void __init scu_enable(void __iomem *scu_base)
          */
         flush_cache_all();
 }
+#endif
 
 /*
  * Set the executing CPUs power mode as defined.  This will be in
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 60636f499cb3..2c277d40cee6 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -115,7 +115,7 @@ static void __cpuinit twd_calibrate_rate(void)
                 twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
 
                 printk("%lu.%02luMHz.\n", twd_timer_rate / 1000000,
-                        (twd_timer_rate / 1000000) % 100);
+                        (twd_timer_rate / 10000) % 100);
         }
 }
 
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index f5cf660eefcc..30e302d33e0a 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -19,6 +19,8 @@
 #include "tcm.h"
 
 static struct gen_pool *tcm_pool;
+static bool dtcm_present;
+static bool itcm_present;
 
 /* TCM section definitions from the linker */
 extern char __itcm_start, __sitcm_text, __eitcm_text;
@@ -90,6 +92,18 @@ void tcm_free(void *addr, size_t len)
 }
 EXPORT_SYMBOL(tcm_free);
 
+bool tcm_dtcm_present(void)
+{
+        return dtcm_present;
+}
+EXPORT_SYMBOL(tcm_dtcm_present);
+
+bool tcm_itcm_present(void)
+{
+        return itcm_present;
+}
+EXPORT_SYMBOL(tcm_itcm_present);
+
 static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks,
                                   u32 *offset)
 {
@@ -134,6 +148,10 @@ static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks,
                         (tcm_region & 1) ? "" : "not ");
         }
 
+        /* Not much fun you can do with a size 0 bank */
+        if (tcm_size == 0)
+                return 0;
+
         /* Force move the TCM bank to where we want it, enable */
         tcm_region = *offset | (tcm_region & 0x00000ffeU) | 1;
 
@@ -165,12 +183,20 @@ void __init tcm_init(void)
         u32 tcm_status = read_cpuid_tcmstatus();
         u8 dtcm_banks = (tcm_status >> 16) & 0x03;
         u8 itcm_banks = (tcm_status & 0x03);
+        size_t dtcm_code_sz = &__edtcm_data - &__sdtcm_data;
+        size_t itcm_code_sz = &__eitcm_text - &__sitcm_text;
         char *start;
         char *end;
         char *ram;
         int ret;
         int i;
 
+        /* Values greater than 2 for D/ITCM banks are "reserved" */
+        if (dtcm_banks > 2)
+                dtcm_banks = 0;
+        if (itcm_banks > 2)
+                itcm_banks = 0;
+
         /* Setup DTCM if present */
         if (dtcm_banks > 0) {
                 for (i = 0; i < dtcm_banks; i++) {
@@ -178,6 +204,13 @@ void __init tcm_init(void)
                         if (ret)
                                 return;
                 }
+                /* This means you compiled more code than fits into DTCM */
+                if (dtcm_code_sz > (dtcm_end - DTCM_OFFSET)) {
+                        pr_info("CPU DTCM: %u bytes of code compiled to "
+                                "DTCM but only %lu bytes of DTCM present\n",
+                                dtcm_code_sz, (dtcm_end - DTCM_OFFSET));
+                        goto no_dtcm;
+                }
                 dtcm_res.end = dtcm_end - 1;
                 request_resource(&iomem_resource, &dtcm_res);
                 dtcm_iomap[0].length = dtcm_end - DTCM_OFFSET;
@@ -186,12 +219,16 @@ void __init tcm_init(void)
                 start = &__sdtcm_data;
                 end   = &__edtcm_data;
                 ram   = &__dtcm_start;
-                /* This means you compiled more code than fits into DTCM */
-                BUG_ON((end - start) > (dtcm_end - DTCM_OFFSET));
-                memcpy(start, ram, (end-start));
-                pr_debug("CPU DTCM: copied data from %p - %p\n", start, end);
+                memcpy(start, ram, dtcm_code_sz);
+                pr_debug("CPU DTCM: copied data from %p - %p\n",
+                         start, end);
+                dtcm_present = true;
+        } else if (dtcm_code_sz) {
+                pr_info("CPU DTCM: %u bytes of code compiled to DTCM but no "
+                        "DTCM banks present in CPU\n", dtcm_code_sz);
         }
 
+no_dtcm:
         /* Setup ITCM if present */
         if (itcm_banks > 0) {
                 for (i = 0; i < itcm_banks; i++) {
@@ -199,6 +236,13 @@ void __init tcm_init(void)
                         if (ret)
                                 return;
                 }
+                /* This means you compiled more code than fits into ITCM */
+                if (itcm_code_sz > (itcm_end - ITCM_OFFSET)) {
+                        pr_info("CPU ITCM: %u bytes of code compiled to "
+                                "ITCM but only %lu bytes of ITCM present\n",
+                                itcm_code_sz, (itcm_end - ITCM_OFFSET));
+                        return;
+                }
                 itcm_res.end = itcm_end - 1;
                 request_resource(&iomem_resource, &itcm_res);
                 itcm_iomap[0].length = itcm_end - ITCM_OFFSET;
@@ -207,10 +251,13 @@ void __init tcm_init(void)
                 start = &__sitcm_text;
                 end   = &__eitcm_text;
                 ram   = &__itcm_start;
-                /* This means you compiled more code than fits into ITCM */
-                BUG_ON((end - start) > (itcm_end - ITCM_OFFSET));
-                memcpy(start, ram, (end-start));
-                pr_debug("CPU ITCM: copied code from %p - %p\n", start, end);
+                memcpy(start, ram, itcm_code_sz);
+                pr_debug("CPU ITCM: copied code from %p - %p\n",
+                         start, end);
+                itcm_present = true;
+        } else if (itcm_code_sz) {
+                pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no "
+                        "ITCM banks present in CPU\n", itcm_code_sz);
         }
 }
 
@@ -221,7 +268,6 @@ void __init tcm_init(void)
  */
 static int __init setup_tcm_pool(void)
 {
-        u32 tcm_status = read_cpuid_tcmstatus();
         u32 dtcm_pool_start = (u32) &__edtcm_data;
         u32 itcm_pool_start = (u32) &__eitcm_text;
         int ret;
@@ -236,7 +282,7 @@ static int __init setup_tcm_pool(void)
         pr_debug("Setting up TCM memory pool\n");
 
         /* Add the rest of DTCM to the TCM pool */
-        if (tcm_status & (0x03 << 16)) {
+        if (dtcm_present) {
                 if (dtcm_pool_start < dtcm_end) {
                         ret = gen_pool_add(tcm_pool, dtcm_pool_start,
                                            dtcm_end - dtcm_pool_start, -1);
@@ -253,7 +299,7 @@ static int __init setup_tcm_pool(void)
         }
 
         /* Add the rest of ITCM to the TCM pool */
-        if (tcm_status & 0x03) {
+        if (itcm_present) {
                 if (itcm_pool_start < itcm_end) {
                         ret = gen_pool_add(tcm_pool, itcm_pool_start,
                                            itcm_end - itcm_pool_start, -1);
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index e5287f21badc..bf977f8514f6 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -38,57 +38,6 @@ jiffies = jiffies_64 + 4;
 
 SECTIONS
 {
-#ifdef CONFIG_XIP_KERNEL
-        . = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
-#else
-        . = PAGE_OFFSET + TEXT_OFFSET;
-#endif
-
-        .init : {                       /* Init code and data           */
-                _stext = .;
-                _sinittext = .;
-                        HEAD_TEXT
-                        INIT_TEXT
-                        ARM_EXIT_KEEP(EXIT_TEXT)
-                _einittext = .;
-                ARM_CPU_DISCARD(PROC_INFO)
-                __arch_info_begin = .;
-                        *(.arch.info.init)
-                __arch_info_end = .;
-                __tagtable_begin = .;
-                        *(.taglist.init)
-                __tagtable_end = .;
-#ifdef CONFIG_SMP_ON_UP
-                __smpalt_begin = .;
-                        *(.alt.smp.init)
-                __smpalt_end = .;
-#endif
-
-                __pv_table_begin = .;
-                        *(.pv_table)
-                __pv_table_end = .;
-
-                INIT_SETUP(16)
-
-                INIT_CALLS
-                CON_INITCALL
-                SECURITY_INITCALL
-                INIT_RAM_FS
-
-#ifndef CONFIG_XIP_KERNEL
-                __init_begin = _stext;
-                INIT_DATA
-                ARM_EXIT_KEEP(EXIT_DATA)
-#endif
-        }
-
-        PERCPU_SECTION(32)
-
-#ifndef CONFIG_XIP_KERNEL
-        . = ALIGN(PAGE_SIZE);
-        __init_end = .;
-#endif
-
         /*
          * unwind exit sections must be discarded before the rest of the
          * unwind sections get included.
@@ -106,10 +55,22 @@ SECTIONS
                 *(.fixup)
                 *(__ex_table)
 #endif
+#ifndef CONFIG_SMP_ON_UP
+                *(.alt.smp.init)
+#endif
         }
 
+#ifdef CONFIG_XIP_KERNEL
+        . = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
+#else
+        . = PAGE_OFFSET + TEXT_OFFSET;
+#endif
+        .head.text : {
+                _text = .;
+                HEAD_TEXT
+        }
         .text : {                       /* Real text segment            */
-                _text = .;              /* Text and read-only data      */
+                _stext = .;             /* Text and read-only data      */
                         __exception_text_start = .;
                         *(.exception.text)
                         __exception_text_end = .;
@@ -122,8 +83,6 @@ SECTIONS
                         *(.fixup)
 #endif
                         *(.gnu.warning)
-                        *(.rodata)
-                        *(.rodata.*)
                         *(.glue_7)
                         *(.glue_7t)
                 . = ALIGN(4);
@@ -152,10 +111,63 @@ SECTIONS
 
         _etext = .;                     /* End of text and rodata section */
 
+#ifndef CONFIG_XIP_KERNEL
+        . = ALIGN(PAGE_SIZE);
+        __init_begin = .;
+#endif
+
+        INIT_TEXT_SECTION(8)
+        .exit.text : {
+                ARM_EXIT_KEEP(EXIT_TEXT)
+        }
+        .init.proc.info : {
+                ARM_CPU_DISCARD(PROC_INFO)
+        }
+        .init.arch.info : {
+                __arch_info_begin = .;
+                *(.arch.info.init)
+                __arch_info_end = .;
+        }
+        .init.tagtable : {
+                __tagtable_begin = .;
+                *(.taglist.init)
+                __tagtable_end = .;
+        }
+#ifdef CONFIG_SMP_ON_UP
+        .init.smpalt : {
+                __smpalt_begin = .;
+                *(.alt.smp.init)
+                __smpalt_end = .;
+        }
+#endif
+        .init.pv_table : {
+                __pv_table_begin = .;
+                *(.pv_table)
+                __pv_table_end = .;
+        }
+        .init.data : {
+#ifndef CONFIG_XIP_KERNEL
+                INIT_DATA
+#endif
+                INIT_SETUP(16)
+                INIT_CALLS
+                CON_INITCALL
+                SECURITY_INITCALL
+                INIT_RAM_FS
+        }
+#ifndef CONFIG_XIP_KERNEL
+        .exit.data : {
+                ARM_EXIT_KEEP(EXIT_DATA)
+        }
+#endif
+
+        PERCPU_SECTION(32)
+
 #ifdef CONFIG_XIP_KERNEL
         __data_loc = ALIGN(4);          /* location in binary */
         . = PAGE_OFFSET + TEXT_OFFSET;
 #else
+        __init_end = .;
         . = ALIGN(THREAD_SIZE);
         __data_loc = .;
 #endif
@@ -270,12 +282,6 @@ SECTIONS
 
         /* Default discards */
         DISCARDS
-
-#ifndef CONFIG_SMP_ON_UP
-        /DISCARD/ : {
-                *(.alt.smp.init)
-        }
-#endif
 }
 
 /*
diff --git a/arch/arm/mach-at91/at91cap9.c b/arch/arm/mach-at91/at91cap9.c
index 17fae4a42ab5..f1013d08bb57 100644
--- a/arch/arm/mach-at91/at91cap9.c
+++ b/arch/arm/mach-at91/at91cap9.c
@@ -223,15 +223,15 @@ static struct clk *periph_clocks[] __initdata = {
 };
 
 static struct clk_lookup periph_clocks_lookups[] = {
-        CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
-        CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
+        CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk),
+        CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk),
         CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk),
         CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk),
         CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
         CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
         CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb_clk),
-        CLKDEV_CON_DEV_ID("ssc", "ssc.0", &ssc0_clk),
-        CLKDEV_CON_DEV_ID("ssc", "ssc.1", &ssc1_clk),
+        CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
+        CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
 };
 
 static struct clk_lookup usart_clocks_lookups[] = {
diff --git a/arch/arm/mach-at91/at91cap9_devices.c b/arch/arm/mach-at91/at91cap9_devices.c
index cd850ed6f335..dba0d8d8a4bd 100644
--- a/arch/arm/mach-at91/at91cap9_devices.c
+++ b/arch/arm/mach-at91/at91cap9_devices.c
@@ -1220,7 +1220,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
         if (portnr < ATMEL_MAX_UART) {
                 atmel_default_console_device = at91_uarts[portnr];
-                at91cap9_set_console_clock(portnr);
+                at91cap9_set_console_clock(at91_uarts[portnr]->id);
         }
 }
 
diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
index b228ce9e21a1..83a1a3fee554 100644
--- a/arch/arm/mach-at91/at91rm9200.c
+++ b/arch/arm/mach-at91/at91rm9200.c
@@ -199,9 +199,9 @@ static struct clk_lookup periph_clocks_lookups[] = {
         CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tc3_clk),
         CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.1", &tc4_clk),
         CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.1", &tc5_clk),
-        CLKDEV_CON_DEV_ID("ssc", "ssc.0", &ssc0_clk),
-        CLKDEV_CON_DEV_ID("ssc", "ssc.1", &ssc1_clk),
-        CLKDEV_CON_DEV_ID("ssc", "ssc.2", &ssc2_clk),
+        CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
+        CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+        CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk),
 };
 
 static struct clk_lookup usart_clocks_lookups[] = {
diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c
index a0ba475be04c..7227755ffec6 100644
--- a/arch/arm/mach-at91/at91rm9200_devices.c
+++ b/arch/arm/mach-at91/at91rm9200_devices.c
@@ -1135,7 +1135,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
         if (portnr < ATMEL_MAX_UART) {
                 atmel_default_console_device = at91_uarts[portnr];
-                at91rm9200_set_console_clock(portnr);
+                at91rm9200_set_console_clock(at91_uarts[portnr]->id);
         }
 }
 
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 1fdeb9058a76..39f81f47b4ba 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -1173,7 +1173,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
         if (portnr < ATMEL_MAX_UART) {
                 atmel_default_console_device = at91_uarts[portnr];
-                at91sam9260_set_console_clock(portnr);
+                at91sam9260_set_console_clock(at91_uarts[portnr]->id);
         }
 }
 
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 3eb4538fceeb..5004bf0a05f2 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -1013,7 +1013,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
         if (portnr < ATMEL_MAX_UART) {
                 atmel_default_console_device = at91_uarts[portnr];
-                at91sam9261_set_console_clock(portnr);
+                at91sam9261_set_console_clock(at91_uarts[portnr]->id);
         }
 }
 
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index ffe081b77ed0..a050f41fc860 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -1395,7 +1395,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
         if (portnr < ATMEL_MAX_UART) {
                 atmel_default_console_device = at91_uarts[portnr];
-                at91sam9263_set_console_clock(portnr);
+                at91sam9263_set_console_clock(at91_uarts[portnr]->id);
         }
 }
 
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index 2bb6ff9af1c7..11e214121b23 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -217,11 +217,11 @@ static struct clk *periph_clocks[] __initdata = {
 static struct clk_lookup periph_clocks_lookups[] = {
         /* One additional fake clock for ohci */
         CLKDEV_CON_ID("ohci_clk", &uhphs_clk),
-        CLKDEV_CON_DEV_ID("ehci_clk", "atmel-ehci.0", &uhphs_clk),
-        CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
-        CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
-        CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk),
-        CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk),
+        CLKDEV_CON_DEV_ID("ehci_clk", "atmel-ehci", &uhphs_clk),
+        CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk),
+        CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk),
+        CLKDEV_CON_DEV_ID("mci_clk", "atmel_mci.0", &mmc0_clk),
+        CLKDEV_CON_DEV_ID("mci_clk", "atmel_mci.1", &mmc1_clk),
         CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
         CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk),
         CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb0_clk),
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 05674865bc21..600bffb01edb 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -1550,7 +1550,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
         if (portnr < ATMEL_MAX_UART) {
                 atmel_default_console_device = at91_uarts[portnr];
-                at91sam9g45_set_console_clock(portnr);
+                at91sam9g45_set_console_clock(at91_uarts[portnr]->id);
         }
 }
 
diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c
index 1a40f16b66c8..29dff18ed130 100644
--- a/arch/arm/mach-at91/at91sam9rl.c
+++ b/arch/arm/mach-at91/at91sam9rl.c
@@ -191,8 +191,8 @@ static struct clk *periph_clocks[] __initdata = {
 };
 
 static struct clk_lookup periph_clocks_lookups[] = {
-        CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk),
-        CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk),
+        CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk),
+        CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk),
         CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
         CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
         CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index c296045f2b6a..aacb19dc9225 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -1168,7 +1168,7 @@ void __init at91_set_serial_console(unsigned portnr)
 {
         if (portnr < ATMEL_MAX_UART) {
                 atmel_default_console_device = at91_uarts[portnr];
-                at91sam9rl_set_console_clock(portnr);
+                at91sam9rl_set_console_clock(at91_uarts[portnr]->id);
         }
 }
 
diff --git a/arch/arm/mach-at91/board-cap9adk.c b/arch/arm/mach-at91/board-cap9adk.c
index 1904fdf87613..cdb65d483250 100644
--- a/arch/arm/mach-at91/board-cap9adk.c
+++ b/arch/arm/mach-at91/board-cap9adk.c
@@ -215,7 +215,7 @@ static void __init cap9adk_add_device_nand(void)
         csa = at91_sys_read(AT91_MATRIX_EBICSA);
         at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_VDDIOMSEL_3_3V);
 
-        cap9adk_nand_data.bus_width_16 = !board_have_nand_8bit();
+        cap9adk_nand_data.bus_width_16 = board_have_nand_16bit();
         /* setup bus-width (8 or 16) */
         if (cap9adk_nand_data.bus_width_16)
                 cap9adk_nand_smc_config.mode |= AT91_SMC_DBW_16;
diff --git a/arch/arm/mach-at91/board-sam9260ek.c b/arch/arm/mach-at91/board-sam9260ek.c
index d600dc123227..5c240743c5b7 100644
--- a/arch/arm/mach-at91/board-sam9260ek.c
+++ b/arch/arm/mach-at91/board-sam9260ek.c
@@ -214,7 +214,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-        ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+        ek_nand_data.bus_width_16 = board_have_nand_16bit();
         /* setup bus-width (8 or 16) */
         if (ek_nand_data.bus_width_16)
                 ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c
index f897f84d43dc..b60c22b6e241 100644
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@@ -220,7 +220,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-        ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+        ek_nand_data.bus_width_16 = board_have_nand_16bit();
         /* setup bus-width (8 or 16) */
         if (ek_nand_data.bus_width_16)
                 ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index 605b26f40a4c..9bbdc92ea194 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -221,7 +221,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-        ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+        ek_nand_data.bus_width_16 = board_have_nand_16bit();
         /* setup bus-width (8 or 16) */
         if (ek_nand_data.bus_width_16)
                 ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
diff --git a/arch/arm/mach-at91/board-sam9g20ek.c b/arch/arm/mach-at91/board-sam9g20ek.c
index 7624cf0d006b..1325a50101a8 100644
--- a/arch/arm/mach-at91/board-sam9g20ek.c
+++ b/arch/arm/mach-at91/board-sam9g20ek.c
@@ -198,7 +198,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-        ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+        ek_nand_data.bus_width_16 = board_have_nand_16bit();
         /* setup bus-width (8 or 16) */
         if (ek_nand_data.bus_width_16)
                 ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
diff --git a/arch/arm/mach-at91/board-sam9m10g45ek.c b/arch/arm/mach-at91/board-sam9m10g45ek.c
index 063c95d0e8f0..33eaa135f248 100644
--- a/arch/arm/mach-at91/board-sam9m10g45ek.c
+++ b/arch/arm/mach-at91/board-sam9m10g45ek.c
@@ -178,7 +178,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = {
 
 static void __init ek_add_device_nand(void)
 {
-        ek_nand_data.bus_width_16 = !board_have_nand_8bit();
+        ek_nand_data.bus_width_16 = board_have_nand_16bit();
         /* setup bus-width (8 or 16) */
         if (ek_nand_data.bus_width_16)
                 ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
diff --git a/arch/arm/mach-at91/include/mach/system_rev.h b/arch/arm/mach-at91/include/mach/system_rev.h
index b855ee75f72c..8f4866045b41 100644
--- a/arch/arm/mach-at91/include/mach/system_rev.h
+++ b/arch/arm/mach-at91/include/mach/system_rev.h
@@ -13,13 +13,13 @@
  * the 16-31 bit are reserved for at91 generic information
  *
  * bit 31:
- *      0 => nand 16 bit
- *      1 => nand 8 bit
+ *      0 => nand 8 bit
+ *      1 => nand 16 bit
  */
-#define BOARD_HAVE_NAND_8BIT    (1 << 31)
-static int inline board_have_nand_8bit(void)
+#define BOARD_HAVE_NAND_16BIT   (1 << 31)
+static inline int board_have_nand_16bit(void)
 {
-        return system_rev & BOARD_HAVE_NAND_8BIT;
+        return system_rev & BOARD_HAVE_NAND_16BIT;
 }
 
 #endif /* __ARCH_SYSTEM_REV_H__ */
diff --git a/arch/arm/mach-bcmring/include/mach/entry-macro.S b/arch/arm/mach-bcmring/include/mach/entry-macro.S
index 7d393ca010ac..94c950d783ba 100644
--- a/arch/arm/mach-bcmring/include/mach/entry-macro.S
+++ b/arch/arm/mach-bcmring/include/mach/entry-macro.S
@@ -80,7 +80,3 @@
 
                 .macro  arch_ret_to_user, tmp1, tmp2
                 .endm
-
-                .macro  irq_prio_table
-                .endm
-
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index c67f684ee3e5..09a87e61ffcf 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -520,7 +520,7 @@ fail:
          */
         if (have_imager()) {
                 label = "HD imager";
-                mux |= 1;
+                mux |= 2;
 
                 /* externally mux MMC1/ENET/AIC33 to imager */
                 mux |= BIT(6) | BIT(5) | BIT(3);
@@ -540,7 +540,7 @@ fail:
                 resets &= ~BIT(1);
 
                 if (have_tvp7002()) {
-                        mux |= 2;
+                        mux |= 1;
                         resets &= ~BIT(2);
                         label = "tvp7002 HD";
                 } else {
diff --git a/arch/arm/mach-davinci/gpio.c b/arch/arm/mach-davinci/gpio.c
index e7221398e5af..cafbe13a82a5 100644
--- a/arch/arm/mach-davinci/gpio.c
+++ b/arch/arm/mach-davinci/gpio.c
@@ -254,8 +254,10 @@ gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 {
         struct davinci_gpio_regs __iomem *g;
         u32 mask = 0xffff;
+        struct davinci_gpio_controller *d;
 
-        g = (__force struct davinci_gpio_regs __iomem *) irq_desc_get_handler_data(desc);
+        d = (struct davinci_gpio_controller *)irq_desc_get_handler_data(desc);
+        g = (struct davinci_gpio_regs __iomem *)d->regs;
 
         /* we only care about one bank */
         if (irq & 1)
@@ -274,11 +276,14 @@ gpio_irq_handler(unsigned irq, struct irq_desc *desc)
                 if (!status)
                         break;
                 __raw_writel(status, &g->intstat);
-                if (irq & 1)
-                        status >>= 16;
 
                 /* now demux them to the right lowlevel handler */
-                n = (int)irq_get_handler_data(irq);
+                n = d->irq_base;
+                if (irq & 1) {
+                        n += 16;
+                        status >>= 16;
+                }
+
                 while (status) {
                         res = ffs(status);
                         n += res;
@@ -424,7 +429,13 @@ static int __init davinci_gpio_irq_setup(void)
 
                 /* set up all irqs in this bank */
                 irq_set_chained_handler(bank_irq, gpio_irq_handler);
-                irq_set_handler_data(bank_irq, (__force void *)g);
+
+                /*
+                 * Each chip handles 32 gpios, and each irq bank consists of 16
+                 * gpio irqs. Pass the irq bank's corresponding controller to
+                 * the chained irq handler.
+                 */
+                irq_set_handler_data(bank_irq, &chips[gpio / 32]);
 
                 for (i = 0; i < 16 && gpio < ngpio; i++, irq++, gpio++) {
                         irq_set_chip(irq, &gpio_irqchip);
diff --git a/arch/arm/mach-davinci/include/mach/entry-macro.S b/arch/arm/mach-davinci/include/mach/entry-macro.S
index fbdebc7cb409..e14c0dc0e12c 100644
--- a/arch/arm/mach-davinci/include/mach/entry-macro.S
+++ b/arch/arm/mach-davinci/include/mach/entry-macro.S
@@ -46,6 +46,3 @@
 #endif
 1002:
                 .endm
-
-                .macro  irq_prio_table
-                .endm
diff --git a/arch/arm/mach-davinci/irq.c b/arch/arm/mach-davinci/irq.c
index bfe68ec4e1a6..952dc126c390 100644
--- a/arch/arm/mach-davinci/irq.c
+++ b/arch/arm/mach-davinci/irq.c
@@ -52,8 +52,14 @@ davinci_alloc_gc(void __iomem *base, unsigned int irq_start, unsigned int num)
         struct irq_chip_type *ct;
 
         gc = irq_alloc_generic_chip("AINTC", 1, irq_start, base, handle_edge_irq);
+        if (!gc) {
+                pr_err("%s: irq_alloc_generic_chip for IRQ %u failed\n",
+                       __func__, irq_start);
+                return;
+        }
+
         ct = gc->chip_types;
-        ct->chip.irq_ack = irq_gc_ack;
+        ct->chip.irq_ack = irq_gc_ack_set_bit;
         ct->chip.irq_mask = irq_gc_mask_clr_bit;
         ct->chip.irq_unmask = irq_gc_mask_set_bit;
 
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index 1d4b65fd673e..6659a0d137a3 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -251,9 +251,9 @@ static void ep93xx_uart_set_mctrl(struct amba_device *dev,
         unsigned int mcr;
 
         mcr = 0;
-        if (!(mctrl & TIOCM_RTS))
+        if (mctrl & TIOCM_RTS)
                 mcr |= 2;
-        if (!(mctrl & TIOCM_DTR))
+        if (mctrl & TIOCM_DTR)
                 mcr |= 1;
 
         __raw_writel(mcr, base + EP93XX_UART_MCR_OFFSET);
diff --git a/arch/arm/mach-exynos4/cpu.c b/arch/arm/mach-exynos4/cpu.c
index 9babe4473e88..bfd621460abf 100644
--- a/arch/arm/mach-exynos4/cpu.c
+++ b/arch/arm/mach-exynos4/cpu.c
@@ -23,6 +23,7 @@
 #include <plat/sdhci.h>
 #include <plat/devs.h>
 #include <plat/fimc-core.h>
+#include <plat/iic-core.h>
 
 #include <mach/regs-irq.h>
 
@@ -132,6 +133,11 @@ void __init exynos4_map_io(void)
         s3c_fimc_setname(1, "exynos4-fimc");
         s3c_fimc_setname(2, "exynos4-fimc");
         s3c_fimc_setname(3, "exynos4-fimc");
+
+        /* The I2C bus controllers are directly compatible with s3c2440 */
+        s3c_i2c0_setname("s3c2440-i2c");
+        s3c_i2c1_setname("s3c2440-i2c");
+        s3c_i2c2_setname("s3c2440-i2c");
 }
 
 void __init exynos4_init_clocks(int xtal)
diff --git a/arch/arm/mach-exynos4/dev-audio.c b/arch/arm/mach-exynos4/dev-audio.c
index 1eed5f9f7bd3..983069a53239 100644
--- a/arch/arm/mach-exynos4/dev-audio.c
+++ b/arch/arm/mach-exynos4/dev-audio.c
@@ -330,7 +330,7 @@ struct platform_device exynos4_device_ac97 = {
 
 static int exynos4_spdif_cfg_gpio(struct platform_device *pdev)
 {
-        s3c_gpio_cfgpin_range(EXYNOS4_GPC1(0), 2, S3C_GPIO_SFN(3));
+        s3c_gpio_cfgpin_range(EXYNOS4_GPC1(0), 2, S3C_GPIO_SFN(4));
 
         return 0;
 }
diff --git a/arch/arm/mach-exynos4/headsmp.S b/arch/arm/mach-exynos4/headsmp.S
index 6c6cfc50c46b..3cdeb3647542 100644
--- a/arch/arm/mach-exynos4/headsmp.S
+++ b/arch/arm/mach-exynos4/headsmp.S
@@ -13,7 +13,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
-        __INIT
+        __CPUINIT
 
 /*
  * exynos4 specific entry point for secondary CPUs.  This provides
diff --git a/arch/arm/mach-exynos4/init.c b/arch/arm/mach-exynos4/init.c
index cf91f50e43ab..a8a83e3881a4 100644
--- a/arch/arm/mach-exynos4/init.c
+++ b/arch/arm/mach-exynos4/init.c
@@ -35,6 +35,7 @@ void __init exynos4_common_init_uarts(struct s3c2410_uartcfg *cfg, int no)
                         tcfg->clocks = exynos4_serial_clocks;
                         tcfg->clocks_size = ARRAY_SIZE(exynos4_serial_clocks);
                 }
+                tcfg->flags |= NO_NEED_CHECK_CLKSRC;
         }
 
         s3c24xx_init_uartdevs("s5pv210-uart", s5p_uart_resources, cfg, no);
diff --git a/arch/arm/mach-exynos4/mach-smdkv310.c b/arch/arm/mach-exynos4/mach-smdkv310.c
index 152676471b67..edd814110da8 100644
--- a/arch/arm/mach-exynos4/mach-smdkv310.c
+++ b/arch/arm/mach-exynos4/mach-smdkv310.c
@@ -78,9 +78,7 @@ static struct s3c2410_uartcfg smdkv310_uartcfgs[] __initdata = {
 };
 
 static struct s3c_sdhci_platdata smdkv310_hsmmc0_pdata __initdata = {
-        .cd_type                = S3C_SDHCI_CD_GPIO,
-        .ext_cd_gpio            = EXYNOS4_GPK0(2),
-        .ext_cd_gpio_invert     = 1,
+        .cd_type                = S3C_SDHCI_CD_INTERNAL,
         .clk_type               = S3C_SDHCI_CLK_DIV_EXTERNAL,
 #ifdef CONFIG_EXYNOS4_SDHCI_CH0_8BIT
         .max_width              = 8,
@@ -96,9 +94,7 @@ static struct s3c_sdhci_platdata smdkv310_hsmmc1_pdata __initdata = {
 };
 
 static struct s3c_sdhci_platdata smdkv310_hsmmc2_pdata __initdata = {
-        .cd_type                = S3C_SDHCI_CD_GPIO,
-        .ext_cd_gpio            = EXYNOS4_GPK2(2),
-        .ext_cd_gpio_invert     = 1,
+        .cd_type                = S3C_SDHCI_CD_INTERNAL,
         .clk_type               = S3C_SDHCI_CLK_DIV_EXTERNAL,
 #ifdef CONFIG_EXYNOS4_SDHCI_CH2_8BIT
         .max_width              = 8,
diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c
index c5e65a02be8d..b68d5bdf04cf 100644
--- a/arch/arm/mach-exynos4/platsmp.c
+++ b/arch/arm/mach-exynos4/platsmp.c
@@ -154,14 +154,6 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-        int i;
-
-        /*
-         * Initialise the present map, which describes the set of CPUs
-         * actually populated at the present time.
-         */
-        for (i = 0; i < max_cpus; i++)
-                set_cpu_present(i, true);
 
         scu_enable(scu_base_addr());
 
diff --git a/arch/arm/mach-exynos4/pm.c b/arch/arm/mach-exynos4/pm.c
index 8755ca8dd48d..533c28f758ca 100644
--- a/arch/arm/mach-exynos4/pm.c
+++ b/arch/arm/mach-exynos4/pm.c
@@ -280,7 +280,7 @@ static struct sleep_save exynos4_l2cc_save[] = {
         SAVE_ITEM(S5P_VA_L2CC + L2X0_AUX_CTRL),
 };
 
-void exynos4_cpu_suspend(void)
+static int exynos4_cpu_suspend(unsigned long arg)
 {
         unsigned long tmp;
         unsigned long mask = 0xFFFFFFFF;
diff --git a/arch/arm/mach-exynos4/sleep.S b/arch/arm/mach-exynos4/sleep.S
index 6b62425417a6..0984078f1eba 100644
--- a/arch/arm/mach-exynos4/sleep.S
+++ b/arch/arm/mach-exynos4/sleep.S
@@ -33,28 +33,6 @@
         .text
 
         /*
-         * s3c_cpu_save
-         *
-         * entry:
-         *      r1 = v:p offset
-         */
-
-ENTRY(s3c_cpu_save)
-
-        stmfd   sp!, { r3 - r12, lr }
-        ldr     r3, =resume_with_mmu
-        bl      cpu_suspend
-
-        ldr     r0, =pm_cpu_sleep
-        ldr     r0, [ r0 ]
-        mov     pc, r0
-
-resume_with_mmu:
-        ldmfd   sp!, { r3 - r12, pc }
-
-        .ltorg
-
-        /*
          * sleep magic, to allow the bootloader to check for an valid
          * image to resume to. Must be the first word before the
          * s3c_cpu_resume entry.
diff --git a/arch/arm/mach-h720x/Kconfig b/arch/arm/mach-h720x/Kconfig
index 9b6982efbd22..abf356c02343 100644
--- a/arch/arm/mach-h720x/Kconfig
+++ b/arch/arm/mach-h720x/Kconfig
@@ -6,12 +6,14 @@ config ARCH_H7201
         bool "gms30c7201"
         depends on ARCH_H720X
         select CPU_H7201
+        select ZONE_DMA
         help
           Say Y here if you are using the Hynix GMS30C7201 Reference Board
 
 config ARCH_H7202
         bool "hms30c7202"
         select CPU_H7202
+        select ZONE_DMA
         depends on ARCH_H720X
         help
           Say Y here if you are using the Hynix HMS30C7202 Reference Board
diff --git a/arch/arm/mach-h720x/include/mach/entry-macro.S b/arch/arm/mach-h720x/include/mach/entry-macro.S
index 6d3b917c4a18..c3948e5ba4a0 100644
--- a/arch/arm/mach-h720x/include/mach/entry-macro.S
+++ b/arch/arm/mach-h720x/include/mach/entry-macro.S
@@ -57,9 +57,6 @@
                 tst     \irqstat, #1                   @ bit 0 should be set
                 .endm
 
-                .macro  irq_prio_table
-                .endm
-
 #else
 #error hynix processor selection missmatch
 #endif
diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c
index e9a589395723..e2e98bbb6413 100644
--- a/arch/arm/mach-ixp4xx/common-pci.c
+++ b/arch/arm/mach-ixp4xx/common-pci.c
@@ -316,6 +316,11 @@ static int abort_handler(unsigned long addr, unsigned int fsr, struct pt_regs *r
 }
 
 
+static int ixp4xx_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
+{
+        return (dma_addr + size) >= SZ_64M;
+}
+
 /*
  * Setup DMA mask to 64MB on PCI devices. Ignore all other devices.
  */
@@ -324,7 +329,7 @@ static int ixp4xx_pci_platform_notify(struct device *dev)
         if(dev->bus == &pci_bus_type) {
                 *dev->dma_mask =  SZ_64M - 1;
                 dev->coherent_dma_mask = SZ_64M - 1;
-                dmabounce_register_dev(dev, 2048, 4096);
+                dmabounce_register_dev(dev, 2048, 4096, ixp4xx_needs_bounce);
         }
         return 0;
 }
@@ -337,11 +342,6 @@ static int ixp4xx_pci_platform_notify_remove(struct device *dev)
         return 0;
 }
 
-int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-        return (dev->bus == &pci_bus_type ) && ((dma_addr + size) >= SZ_64M);
-}
-
 void __init ixp4xx_pci_preinit(void)
 {
         unsigned long cpuid = read_cpuid_id();
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 74ed81a3cb1a..07772575d7ab 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -419,14 +419,20 @@ static void notrace ixp4xx_update_sched_clock(void)
 /*
  * clocksource
  */
+
+static cycle_t ixp4xx_clocksource_read(struct clocksource *c)
+{
+        return *IXP4XX_OSTS;
+}
+
 unsigned long ixp4xx_timer_freq = IXP4XX_TIMER_FREQ;
 EXPORT_SYMBOL(ixp4xx_timer_freq);
 static void __init ixp4xx_clocksource_init(void)
 {
         init_sched_clock(&cd, ixp4xx_update_sched_clock, 32, ixp4xx_timer_freq);
 
-        clocksource_mmio_init(&IXP4XX_OSTS, "OSTS", ixp4xx_timer_freq, 200, 32,
-                        clocksource_mmio_readl_up);
+        clocksource_mmio_init(NULL, "OSTS", ixp4xx_timer_freq, 200, 32,
+                        ixp4xx_clocksource_read);
 }
 
 /*
diff --git a/arch/arm/mach-lpc32xx/include/mach/entry-macro.S b/arch/arm/mach-lpc32xx/include/mach/entry-macro.S
index 870227c96602..b725f6c93975 100644
--- a/arch/arm/mach-lpc32xx/include/mach/entry-macro.S
+++ b/arch/arm/mach-lpc32xx/include/mach/entry-macro.S
@@ -41,7 +41,3 @@
         rsb     \irqnr, \irqnr, #31
         teq     \irqstat, #0
         .endm
-
-        .macro  irq_prio_table
-        .endm
-
diff --git a/arch/arm/mach-mmp/pxa168.c b/arch/arm/mach-mmp/pxa168.c
index 72b4e7631583..ab9f999106c7 100644
--- a/arch/arm/mach-mmp/pxa168.c
+++ b/arch/arm/mach-mmp/pxa168.c
@@ -79,7 +79,7 @@ static APBC_CLK(ssp4, PXA168_SSP4, 4, 0);
 static APBC_CLK(ssp5, PXA168_SSP5, 4, 0);
 static APBC_CLK(keypad, PXA168_KPC, 0, 32000);
 
-static APMU_CLK(nand, NAND, 0x01db, 208000000);
+static APMU_CLK(nand, NAND, 0x19b, 156000000);
 static APMU_CLK(lcd, LCD, 0x7f, 312000000);
 
 /* device and clock bindings */
diff --git a/arch/arm/mach-mmp/pxa910.c b/arch/arm/mach-mmp/pxa910.c
index 8f92ccd26edf..1464607aa60d 100644
--- a/arch/arm/mach-mmp/pxa910.c
+++ b/arch/arm/mach-mmp/pxa910.c
@@ -110,7 +110,7 @@ static APBC_CLK(pwm2, PXA910_PWM2, 1, 13000000);
 static APBC_CLK(pwm3, PXA910_PWM3, 1, 13000000);
 static APBC_CLK(pwm4, PXA910_PWM4, 1, 13000000);
 
-static APMU_CLK(nand, NAND, 0x01db, 208000000);
+static APMU_CLK(nand, NAND, 0x19b, 156000000);
 static APMU_CLK(u2o, USB, 0x1b, 480000000);
 
 /* device and clock bindings */
diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c
index 2034098cf015..315b9f365329 100644
--- a/arch/arm/mach-msm/platsmp.c
+++ b/arch/arm/mach-msm/platsmp.c
@@ -157,12 +157,4 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-        int i;
-
-        /*
-         * Initialise the present map, which describes the set of CPUs
-         * actually populated at the present time.
-         */
-        for (i = 0; i < max_cpus; i++)
-                set_cpu_present(i, true);
 }
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 38b95e949d13..63621f152c98 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -23,6 +23,8 @@
 #include <linux/io.h>
 
 #include <asm/mach/time.h>
+#include <asm/hardware/gic.h>
+
 #include <mach/msm_iomap.h>
 #include <mach/cpu.h>
 
@@ -55,10 +57,12 @@ enum timer_location {
 #if defined(CONFIG_ARCH_QSD8X50)
 #define DGT_HZ (19200000 / 4) /* 19.2 MHz / 4 by default */
 #define MSM_DGT_SHIFT (0)
-#elif defined(CONFIG_ARCH_MSM7X30) || defined(CONFIG_ARCH_MSM8X60) || \
-                                      defined(CONFIG_ARCH_MSM8960)
+#elif defined(CONFIG_ARCH_MSM7X30)
 #define DGT_HZ (24576000 / 4) /* 24.576 MHz (LPXO) / 4 by default */
 #define MSM_DGT_SHIFT (0)
+#elif defined(CONFIG_ARCH_MSM8X60) || defined(CONFIG_ARCH_MSM8960)
+#define DGT_HZ (27000000 / 4) /* 27 MHz (PXO) / 4 by default */
+#define MSM_DGT_SHIFT (0)
 #else
 #define DGT_HZ 19200000 /* 19.2 MHz or 600 KHz after shift */
 #define MSM_DGT_SHIFT (5)
@@ -100,7 +104,11 @@ static cycle_t msm_read_timer_count(struct clocksource *cs)
 {
         struct msm_clock *clk = container_of(cs, struct msm_clock, clocksource);
 
-        return readl(clk->global_counter);
+        /*
+         * Shift timer count down by a constant due to unreliable lower bits
+         * on some targets.
+         */
+        return readl(clk->global_counter) >> clk->shift;
 }
 
 static struct msm_clock *clockevent_to_clock(struct clock_event_device *evt)
diff --git a/arch/arm/mach-omap1/Makefile b/arch/arm/mach-omap1/Makefile
index af98117043d2..5b114d1558c8 100644
--- a/arch/arm/mach-omap1/Makefile
+++ b/arch/arm/mach-omap1/Makefile
@@ -4,14 +4,14 @@
 
 # Common support
 obj-y := io.o id.o sram.o time.o irq.o mux.o flash.o serial.o devices.o dma.o
-obj-y += clock.o clock_data.o opp_data.o reset.o
+obj-y += clock.o clock_data.o opp_data.o reset.o pm_bus.o
 
 obj-$(CONFIG_OMAP_MCBSP) += mcbsp.o
 
 obj-$(CONFIG_OMAP_32K_TIMER)    += timer32k.o
 
 # Power Management
-obj-$(CONFIG_PM) += pm.o sleep.o pm_bus.o
+obj-$(CONFIG_PM) += pm.o sleep.o
 
 # DSP
 obj-$(CONFIG_OMAP_MBOX_FWK)     += mailbox_mach.o
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index de88c9297b68..f49ce85d2448 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -215,7 +215,7 @@ static struct omap_kp_platform_data ams_delta_kp_data __initdata = {
         .delay          = 9,
 };
 
-static struct platform_device ams_delta_kp_device __initdata = {
+static struct platform_device ams_delta_kp_device = {
         .name           = "omap-keypad",
         .id             = -1,
         .dev            = {
@@ -225,12 +225,12 @@ static struct platform_device ams_delta_kp_device __initdata = {
         .resource       = ams_delta_kp_resources,
 };
 
-static struct platform_device ams_delta_lcd_device __initdata = {
+static struct platform_device ams_delta_lcd_device = {
         .name   = "lcd_ams_delta",
         .id     = -1,
 };
 
-static struct platform_device ams_delta_led_device __initdata = {
+static struct platform_device ams_delta_led_device = {
         .name   = "ams-delta-led",
         .id     = -1
 };
@@ -267,7 +267,7 @@ static struct soc_camera_link ams_delta_iclink = {
         .power          = ams_delta_camera_power,
 };
 
-static struct platform_device ams_delta_camera_device __initdata = {
+static struct platform_device ams_delta_camera_device = {
         .name   = "soc-camera-pdrv",
         .id     = 0,
         .dev    = {
diff --git a/arch/arm/mach-omap1/gpio15xx.c b/arch/arm/mach-omap1/gpio15xx.c
index 04c4b04cf54e..364137c2042c 100644
--- a/arch/arm/mach-omap1/gpio15xx.c
+++ b/arch/arm/mach-omap1/gpio15xx.c
@@ -41,7 +41,7 @@ static struct __initdata omap_gpio_platform_data omap15xx_mpu_gpio_config = {
         .bank_stride            = 1,
 };
 
-static struct __initdata platform_device omap15xx_mpu_gpio = {
+static struct platform_device omap15xx_mpu_gpio = {
         .name           = "omap_gpio",
         .id             = 0,
         .dev            = {
@@ -70,7 +70,7 @@ static struct __initdata omap_gpio_platform_data omap15xx_gpio_config = {
         .bank_width             = 16,
 };
 
-static struct __initdata platform_device omap15xx_gpio = {
+static struct platform_device omap15xx_gpio = {
         .name           = "omap_gpio",
         .id             = 1,
         .dev            = {
diff --git a/arch/arm/mach-omap1/gpio16xx.c b/arch/arm/mach-omap1/gpio16xx.c
index 5dd0d4c82b24..293a246e2824 100644
--- a/arch/arm/mach-omap1/gpio16xx.c
+++ b/arch/arm/mach-omap1/gpio16xx.c
@@ -44,7 +44,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_mpu_gpio_config = {
         .bank_stride            = 1,
 };
 
-static struct __initdata platform_device omap16xx_mpu_gpio = {
+static struct platform_device omap16xx_mpu_gpio = {
         .name           = "omap_gpio",
         .id             = 0,
         .dev            = {
@@ -73,7 +73,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_gpio1_config = {
         .bank_width             = 16,
 };
 
-static struct __initdata platform_device omap16xx_gpio1 = {
+static struct platform_device omap16xx_gpio1 = {
         .name           = "omap_gpio",
         .id             = 1,
         .dev            = {
@@ -102,7 +102,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_gpio2_config = {
         .bank_width             = 16,
 };
 
-static struct __initdata platform_device omap16xx_gpio2 = {
+static struct platform_device omap16xx_gpio2 = {
         .name           = "omap_gpio",
         .id             = 2,
         .dev            = {
@@ -131,7 +131,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_gpio3_config = {
         .bank_width             = 16,
 };
 
-static struct __initdata platform_device omap16xx_gpio3 = {
+static struct platform_device omap16xx_gpio3 = {
         .name           = "omap_gpio",
         .id             = 3,
         .dev            = {
@@ -160,7 +160,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_gpio4_config = {
         .bank_width             = 16,
 };
 
-static struct __initdata platform_device omap16xx_gpio4 = {
+static struct platform_device omap16xx_gpio4 = {
         .name           = "omap_gpio",
         .id             = 4,
         .dev            = {
diff --git a/arch/arm/mach-omap1/gpio7xx.c b/arch/arm/mach-omap1/gpio7xx.c
index 1204c8b871af..c6ad248d63a6 100644
--- a/arch/arm/mach-omap1/gpio7xx.c
+++ b/arch/arm/mach-omap1/gpio7xx.c
@@ -46,7 +46,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_mpu_gpio_config = {
         .bank_stride            = 2,
 };
 
-static struct __initdata platform_device omap7xx_mpu_gpio = {
+static struct platform_device omap7xx_mpu_gpio = {
         .name           = "omap_gpio",
         .id             = 0,
         .dev            = {
@@ -75,7 +75,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio1_config = {
         .bank_width             = 32,
 };
 
-static struct __initdata platform_device omap7xx_gpio1 = {
+static struct platform_device omap7xx_gpio1 = {
         .name           = "omap_gpio",
         .id             = 1,
         .dev            = {
@@ -104,7 +104,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio2_config = {
         .bank_width             = 32,
 };
 
-static struct __initdata platform_device omap7xx_gpio2 = {
+static struct platform_device omap7xx_gpio2 = {
         .name           = "omap_gpio",
         .id             = 2,
         .dev            = {
@@ -133,7 +133,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio3_config = {
         .bank_width             = 32,
 };
 
-static struct __initdata platform_device omap7xx_gpio3 = {
+static struct platform_device omap7xx_gpio3 = {
         .name           = "omap_gpio",
         .id             = 3,
         .dev            = {
@@ -162,7 +162,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio4_config = {
         .bank_width             = 32,
 };
 
-static struct __initdata platform_device omap7xx_gpio4 = {
+static struct platform_device omap7xx_gpio4 = {
         .name           = "omap_gpio",
         .id             = 4,
         .dev            = {
@@ -191,7 +191,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio5_config = {
         .bank_width             = 32,
 };
 
-static struct __initdata platform_device omap7xx_gpio5 = {
+static struct platform_device omap7xx_gpio5 = {
         .name           = "omap_gpio",
         .id             = 5,
         .dev            = {
@@ -220,7 +220,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio6_config = {
         .bank_width             = 32,
 };
 
-static struct __initdata platform_device omap7xx_gpio6 = {
+static struct platform_device omap7xx_gpio6 = {
         .name           = "omap_gpio",
         .id             = 6,
         .dev            = {
diff --git a/arch/arm/mach-omap1/pm_bus.c b/arch/arm/mach-omap1/pm_bus.c
index fe31d933f0ed..334fb8871bc3 100644
--- a/arch/arm/mach-omap1/pm_bus.c
+++ b/arch/arm/mach-omap1/pm_bus.c
@@ -56,9 +56,13 @@ static struct dev_power_domain default_power_domain = {
                 USE_PLATFORM_PM_SLEEP_OPS
         },
 };
+#define OMAP1_PWR_DOMAIN (&default_power_domain)
+#else
+#define OMAP1_PWR_DOMAIN NULL
+#endif /* CONFIG_PM_RUNTIME */
 
 static struct pm_clk_notifier_block platform_bus_notifier = {
-        .pwr_domain = &default_power_domain,
+        .pwr_domain = OMAP1_PWR_DOMAIN,
         .con_ids = { "ick", "fck", NULL, },
 };
 
@@ -72,4 +76,4 @@ static int __init omap1_pm_runtime_init(void)
         return 0;
 }
 core_initcall(omap1_pm_runtime_init);
-#endif /* CONFIG_PM_RUNTIME */
+
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index 2a0bb4818cae..23f71d40883e 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -84,7 +84,8 @@ static struct mtd_partition omap3pandora_nand_partitions[] = {
 
 static struct omap_nand_platform_data pandora_nand_data = {
         .cs             = 0,
-        .devsize        = 1,    /* '0' for 8-bit, '1' for 16-bit device */
+        .devsize        = NAND_BUSWIDTH_16,
+        .xfer_type      = NAND_OMAP_PREFETCH_DMA,
         .parts          = omap3pandora_nand_partitions,
         .nr_parts       = ARRAY_SIZE(omap3pandora_nand_partitions),
 };
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 990366726c58..88bd6f7705f0 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -558,7 +558,7 @@ static struct radio_si4713_platform_data rx51_si4713_data __initdata_or_module =
         .subdev_board_info = &rx51_si4713_board_info,
 };
 
-static struct platform_device rx51_si4713_dev __initdata_or_module = {
+static struct platform_device rx51_si4713_dev = {
         .name   = "radio-si4713",
         .id     = -1,
         .dev    = {
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index da53ba3917ca..aab884fecc55 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -286,14 +286,15 @@ void omap3_save_scratchpad_contents(void)
         scratchpad_contents.boot_config_ptr = 0x0;
         if (cpu_is_omap3630())
                 scratchpad_contents.public_restore_ptr =
-                        virt_to_phys(get_omap3630_restore_pointer());
+                        virt_to_phys(omap3_restore_3630);
         else if (omap_rev() != OMAP3430_REV_ES3_0 &&
                                         omap_rev() != OMAP3430_REV_ES3_1)
                 scratchpad_contents.public_restore_ptr =
-                        virt_to_phys(get_restore_pointer());
+                        virt_to_phys(omap3_restore);
         else
                 scratchpad_contents.public_restore_ptr =
-                        virt_to_phys(get_es3_restore_pointer());
+                        virt_to_phys(omap3_restore_es3);
+
         if (omap_type() == OMAP2_DEVICE_TYPE_GP)
                 scratchpad_contents.secure_ram_restore_ptr = 0x0;
         else
diff --git a/arch/arm/mach-omap2/control.h b/arch/arm/mach-omap2/control.h
index a016c8b59e00..d4ef75d5a382 100644
--- a/arch/arm/mach-omap2/control.h
+++ b/arch/arm/mach-omap2/control.h
@@ -386,9 +386,9 @@ extern void omap4_ctrl_pad_writel(u32 val, u16 offset);
 
 extern void omap3_save_scratchpad_contents(void);
 extern void omap3_clear_scratchpad_contents(void);
-extern u32 *get_restore_pointer(void);
-extern u32 *get_es3_restore_pointer(void);
-extern u32 *get_omap3630_restore_pointer(void);
+extern void omap3_restore(void);
+extern void omap3_restore_es3(void);
+extern void omap3_restore_3630(void);
 extern u32 omap3_arm_context[128];
 extern void omap3_control_save_context(void);
 extern void omap3_control_restore_context(void);
diff --git a/arch/arm/mach-omap2/include/mach/entry-macro.S b/arch/arm/mach-omap2/include/mach/entry-macro.S
index a48690b90990..ceb8b7e593d7 100644
--- a/arch/arm/mach-omap2/include/mach/entry-macro.S
+++ b/arch/arm/mach-omap2/include/mach/entry-macro.S
@@ -165,6 +165,3 @@
 #endif
 
 #endif  /* MULTI_OMAP2 */
-
-                .macro  irq_prio_table
-                .endm
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index ecfe93c4b585..ce65e9329c7b 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -125,14 +125,6 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-        int i;
-
-        /*
-         * Initialise the present map, which describes the set of CPUs
-         * actually populated at the present time.
-         */
-        for (i = 0; i < max_cpus; i++)
-                set_cpu_present(i, true);
 
         /*
          * Initialise the SCU and wake up the secondary core using
diff --git a/arch/arm/mach-omap2/pm-debug.c b/arch/arm/mach-omap2/pm-debug.c
index a5a83b358ddd..e01da45c0537 100644
--- a/arch/arm/mach-omap2/pm-debug.c
+++ b/arch/arm/mach-omap2/pm-debug.c
@@ -189,7 +189,7 @@ static struct dentry *pm_dbg_dir;
 
 static int pm_dbg_init_done;
 
-static int __init pm_dbg_init(void);
+static int pm_dbg_init(void);
 
 enum {
         DEBUG_FILE_COUNTERS = 0,
@@ -595,7 +595,7 @@ static int option_set(void *data, u64 val)
 
 DEFINE_SIMPLE_ATTRIBUTE(pm_dbg_option_fops, option_get, option_set, "%llu\n");
 
-static int __init pm_dbg_init(void)
+static int pm_dbg_init(void)
 {
         int i;
         struct dentry *d;
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index 45bcfce77352..04ee56646126 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -88,18 +88,28 @@ extern int pm_dbg_regset_init(int reg_set);
 #define pm_dbg_regset_init(reg_set) do {} while (0);
 #endif /* CONFIG_PM_DEBUG */
 
+/* 24xx */
 extern void omap24xx_idle_loop_suspend(void);
+extern unsigned int omap24xx_idle_loop_suspend_sz;
 
 extern void omap24xx_cpu_suspend(u32 dll_ctrl, void __iomem *sdrc_dlla_ctrl,
                                         void __iomem *sdrc_power);
-extern void omap34xx_cpu_suspend(u32 *addr, int save_state);
-extern int save_secure_ram_context(u32 *addr);
-extern void omap3_save_scratchpad_contents(void);
+extern unsigned int omap24xx_cpu_suspend_sz;
 
-extern unsigned int omap24xx_idle_loop_suspend_sz;
+/* 3xxx */
+extern void omap34xx_cpu_suspend(int save_state);
+
+/* omap3_do_wfi function pointer and size, for copy to SRAM */
+extern void omap3_do_wfi(void);
+extern unsigned int omap3_do_wfi_sz;
+/* ... and its pointer from SRAM after copy */
+extern void (*omap3_do_wfi_sram)(void);
+
+/* save_secure_ram_context function pointer and size, for copy to SRAM */
+extern int save_secure_ram_context(u32 *addr);
 extern unsigned int save_secure_ram_context_sz;
-extern unsigned int omap24xx_cpu_suspend_sz;
-extern unsigned int omap34xx_cpu_suspend_sz;
+
+extern void omap3_save_scratchpad_contents(void);
 
 #define PM_RTA_ERRATUM_i608             (1 << 0)
 #define PM_SDRC_WAKEUP_ERRATUM_i583     (1 << 1)
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index c155c9d1c82c..b77d82665abb 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -31,6 +31,8 @@
 #include <linux/console.h>
 #include <trace/events/power.h>
 
+#include <asm/suspend.h>
+
 #include <plat/sram.h>
 #include "clockdomain.h"
 #include "powerdomain.h"
@@ -40,8 +42,6 @@
 #include <plat/gpmc.h>
 #include <plat/dma.h>
 
-#include <asm/tlbflush.h>
-
 #include "cm2xxx_3xxx.h"
 #include "cm-regbits-34xx.h"
 #include "prm-regbits-34xx.h"
@@ -64,11 +64,6 @@ static inline bool is_suspending(void)
 }
 #endif
 
-/* Scratchpad offsets */
-#define OMAP343X_TABLE_ADDRESS_OFFSET      0xc4
-#define OMAP343X_TABLE_VALUE_OFFSET        0xc0
-#define OMAP343X_CONTROL_REG_VALUE_OFFSET  0xc8
-
 /* pm34xx errata defined in pm.h */
 u16 pm34xx_errata;
 
@@ -83,9 +78,8 @@ struct power_state {
 
 static LIST_HEAD(pwrst_list);
 
-static void (*_omap_sram_idle)(u32 *addr, int save_state);
-
 static int (*_omap_save_secure_sram)(u32 *addr);
+void (*omap3_do_wfi_sram)(void);
 
 static struct powerdomain *mpu_pwrdm, *neon_pwrdm;
 static struct powerdomain *core_pwrdm, *per_pwrdm;
@@ -312,28 +306,25 @@ static irqreturn_t prcm_interrupt_handler (int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
-/* Function to restore the table entry that was modified for enabling MMU */
-static void restore_table_entry(void)
+static void omap34xx_save_context(u32 *save)
 {
-        void __iomem *scratchpad_address;
-        u32 previous_value, control_reg_value;
-        u32 *address;
+        u32 val;
 
-        scratchpad_address = OMAP2_L4_IO_ADDRESS(OMAP343X_SCRATCHPAD);
+        /* Read Auxiliary Control Register */
+        asm("mrc p15, 0, %0, c1, c0, 1" : "=r" (val));
+        *save++ = 1;
+        *save++ = val;
 
-        /* Get address of entry that was modified */
-        address = (u32 *)__raw_readl(scratchpad_address +
-                                     OMAP343X_TABLE_ADDRESS_OFFSET);
-        /* Get the previous value which needs to be restored */
-        previous_value = __raw_readl(scratchpad_address +
-                                     OMAP343X_TABLE_VALUE_OFFSET);
-        address = __va(address);
-        *address = previous_value;
-        flush_tlb_all();
-        control_reg_value = __raw_readl(scratchpad_address
-                                        + OMAP343X_CONTROL_REG_VALUE_OFFSET);
-        /* This will enable caches and prediction */
-        set_cr(control_reg_value);
+        /* Read L2 AUX ctrl register */
+        asm("mrc p15, 1, %0, c9, c0, 2" : "=r" (val));
+        *save++ = 1;
+        *save++ = val;
+}
+
+static int omap34xx_do_sram_idle(unsigned long save_state)
+{
+        omap34xx_cpu_suspend(save_state);
+        return 0;
 }
 
 void omap_sram_idle(void)
@@ -352,9 +343,6 @@ void omap_sram_idle(void)
         int core_prev_state, per_prev_state;
         u32 sdrc_pwr = 0;
 
-        if (!_omap_sram_idle)
-                return;
-
         pwrdm_clear_all_prev_pwrst(mpu_pwrdm);
         pwrdm_clear_all_prev_pwrst(neon_pwrdm);
         pwrdm_clear_all_prev_pwrst(core_pwrdm);
@@ -432,12 +420,16 @@ void omap_sram_idle(void)
                 sdrc_pwr = sdrc_read_reg(SDRC_POWER);
 
         /*
-         * omap3_arm_context is the location where ARM registers
-         * get saved. The restore path then reads from this
-         * location and restores them back.
+         * omap3_arm_context is the location where some ARM context
+         * get saved. The rest is placed on the stack, and restored
+         * from there before resuming.
          */
-        _omap_sram_idle(omap3_arm_context, save_state);
-        cpu_init();
+        if (save_state)
+                omap34xx_save_context(omap3_arm_context);
+        if (save_state == 1 || save_state == 3)
+                cpu_suspend(save_state, omap34xx_do_sram_idle);
+        else
+                omap34xx_do_sram_idle(save_state);
 
         /* Restore normal SDRC POWER settings */
         if (omap_rev() >= OMAP3430_REV_ES3_0 &&
@@ -445,10 +437,6 @@ void omap_sram_idle(void)
             core_next_state == PWRDM_POWER_OFF)
                 sdrc_write_reg(sdrc_pwr, SDRC_POWER);
 
-        /* Restore table entry modified during MMU restoration */
-        if (pwrdm_read_prev_pwrst(mpu_pwrdm) == PWRDM_POWER_OFF)
-                restore_table_entry();
-
         /* CORE */
         if (core_next_state < PWRDM_POWER_ON) {
                 core_prev_state = pwrdm_read_prev_pwrst(core_pwrdm);
@@ -852,10 +840,17 @@ static int __init clkdms_setup(struct clockdomain *clkdm, void *unused)
         return 0;
 }
 
+/*
+ * Push functions to SRAM
+ *
+ * The minimum set of functions is pushed to SRAM for execution:
+ * - omap3_do_wfi for erratum i581 WA,
+ * - save_secure_ram_context for security extensions.
+ */
 void omap_push_sram_idle(void)
 {
-        _omap_sram_idle = omap_sram_push(omap34xx_cpu_suspend,
-                                        omap34xx_cpu_suspend_sz);
+        omap3_do_wfi_sram = omap_sram_push(omap3_do_wfi, omap3_do_wfi_sz);
+
         if (omap_type() != OMAP2_DEVICE_TYPE_GP)
                 _omap_save_secure_sram = omap_sram_push(save_secure_ram_context,
                                 save_secure_ram_context_sz);
@@ -920,7 +915,6 @@ static int __init omap3_pm_init(void)
         per_clkdm = clkdm_lookup("per_clkdm");
         core_clkdm = clkdm_lookup("core_clkdm");
 
-        omap_push_sram_idle();
 #ifdef CONFIG_SUSPEND
         suspend_set_ops(&omap_pm_ops);
 #endif /* CONFIG_SUSPEND */
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index 63f10669571a..f2ea1bd1c691 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -74,46 +74,6 @@
  * API functions
  */
 
-/*
- * The "get_*restore_pointer" functions are used to provide a
- * physical restore address where the ROM code jumps while waking
- * up from MPU OFF/OSWR state.
- * The restore pointer is stored into the scratchpad.
- */
-
-        .text
-/* Function call to get the restore pointer for resume from OFF */
-ENTRY(get_restore_pointer)
-        stmfd   sp!, {lr}       @ save registers on stack
-        adr     r0, restore
-        ldmfd   sp!, {pc}       @ restore regs and return
-ENDPROC(get_restore_pointer)
-        .align
-ENTRY(get_restore_pointer_sz)
-        .word   . - get_restore_pointer
-
-        .text
-/* Function call to get the restore pointer for 3630 resume from OFF */
-ENTRY(get_omap3630_restore_pointer)
-        stmfd   sp!, {lr}       @ save registers on stack
-        adr     r0, restore_3630
-        ldmfd   sp!, {pc}       @ restore regs and return
-ENDPROC(get_omap3630_restore_pointer)
-        .align
-ENTRY(get_omap3630_restore_pointer_sz)
-        .word   . - get_omap3630_restore_pointer
-
-        .text
-/* Function call to get the restore pointer for ES3 to resume from OFF */
-ENTRY(get_es3_restore_pointer)
-        stmfd   sp!, {lr}       @ save registers on stack
-        adr     r0, restore_es3
-        ldmfd   sp!, {pc}       @ restore regs and return
-ENDPROC(get_es3_restore_pointer)
-        .align
-ENTRY(get_es3_restore_pointer_sz)
-        .word   . - get_es3_restore_pointer
-
         .text
 /*
  * L2 cache needs to be toggled for stable OFF mode functionality on 3630.
@@ -133,7 +93,7 @@ ENDPROC(enable_omap3630_toggle_l2_on_restore)
 /* Function to call rom code to save secure ram context */
         .align  3
 ENTRY(save_secure_ram_context)
-        stmfd   sp!, {r1-r12, lr}       @ save registers on stack
+        stmfd   sp!, {r4 - r11, lr}     @ save registers on stack
         adr     r3, api_params          @ r3 points to parameters
         str     r0, [r3,#0x4]           @ r0 has sdram address
         ldr     r12, high_mask
@@ -152,7 +112,7 @@ ENTRY(save_secure_ram_context)
         nop
         nop
         nop
-        ldmfd   sp!, {r1-r12, pc}
+        ldmfd   sp!, {r4 - r11, pc}
         .align
 sram_phy_addr_mask:
         .word   SRAM_BASE_P
@@ -179,69 +139,38 @@ ENTRY(save_secure_ram_context_sz)
  *
  *
  * Notes:
- * - this code gets copied to internal SRAM at boot and after wake-up
- *   from OFF mode. The execution pointer in SRAM is _omap_sram_idle.
+ * - only the minimum set of functions gets copied to internal SRAM at boot
+ *   and after wake-up from OFF mode, cf. omap_push_sram_idle. The function
+ *   pointers in SDRAM or SRAM are called depending on the desired low power
+ *   target state.
  * - when the OMAP wakes up it continues at different execution points
  *   depending on the low power mode (non-OFF vs OFF modes),
  *   cf. 'Resume path for xxx mode' comments.
  */
         .align  3
 ENTRY(omap34xx_cpu_suspend)
-        stmfd   sp!, {r0-r12, lr}       @ save registers on stack
+        stmfd   sp!, {r4 - r11, lr}     @ save registers on stack
 
         /*
-         * r0 contains CPU context save/restore pointer in sdram
-         * r1 contains information about saving context:
+         * r0 contains information about saving context:
          *   0 - No context lost
          *   1 - Only L1 and logic lost
          *   2 - Only L2 lost (Even L1 is retained we clean it along with L2)
          *   3 - Both L1 and L2 lost and logic lost
          */
 
-        /* Directly jump to WFI is the context save is not required */
-        cmp     r1, #0x0
-        beq     omap3_do_wfi
+        /*
+         * For OFF mode: save context and jump to WFI in SDRAM (omap3_do_wfi)
+         * For non-OFF modes: jump to the WFI code in SRAM (omap3_do_wfi_sram)
+         */
+        ldr     r4, omap3_do_wfi_sram_addr
+        ldr     r5, [r4]
+        cmp     r0, #0x0                @ If no context save required,
+        bxeq    r5                      @  jump to the WFI code in SRAM
+
 
         /* Otherwise fall through to the save context code */
 save_context_wfi:
-        mov     r8, r0                  @ Store SDRAM address in r8
-        mrc     p15, 0, r5, c1, c0, 1   @ Read Auxiliary Control Register
-        mov     r4, #0x1                @ Number of parameters for restore call
-        stmia   r8!, {r4-r5}            @ Push parameters for restore call
-        mrc     p15, 1, r5, c9, c0, 2   @ Read L2 AUX ctrl register
-        stmia   r8!, {r4-r5}            @ Push parameters for restore call
-
-        /* Check what that target sleep state is from r1 */
-        cmp     r1, #0x2                @ Only L2 lost, no need to save context
-        beq     clean_caches
-
-l1_logic_lost:
-        mov     r4, sp                  @ Store sp
-        mrs     r5, spsr                @ Store spsr
-        mov     r6, lr                  @ Store lr
-        stmia   r8!, {r4-r6}
-
-        mrc     p15, 0, r4, c1, c0, 2   @ Coprocessor access control register
-        mrc     p15, 0, r5, c2, c0, 0   @ TTBR0
-        mrc     p15, 0, r6, c2, c0, 1   @ TTBR1
-        mrc     p15, 0, r7, c2, c0, 2   @ TTBCR
-        stmia   r8!, {r4-r7}
-
-        mrc     p15, 0, r4, c3, c0, 0   @ Domain access Control Register
-        mrc     p15, 0, r5, c10, c2, 0  @ PRRR
-        mrc     p15, 0, r6, c10, c2, 1  @ NMRR
-        stmia   r8!,{r4-r6}
-
-        mrc     p15, 0, r4, c13, c0, 1  @ Context ID
-        mrc     p15, 0, r5, c13, c0, 2  @ User r/w thread and process ID
-        mrc     p15, 0, r6, c12, c0, 0  @ Secure or NS vector base address
-        mrs     r7, cpsr                @ Store current cpsr
-        stmia   r8!, {r4-r7}
-
-        mrc     p15, 0, r4, c1, c0, 0   @ save control register
-        stmia   r8!, {r4}
-
-clean_caches:
         /*
          * jump out to kernel flush routine
          *  - reuse that code is better
@@ -284,7 +213,32 @@ clean_caches:
  THUMB( nop             )
         .arm
 
-omap3_do_wfi:
+        b       omap3_do_wfi
+
+/*
+ * Local variables
+ */
+omap3_do_wfi_sram_addr:
+        .word omap3_do_wfi_sram
+kernel_flush:
+        .word v7_flush_dcache_all
+
+/* ===================================
+ * == WFI instruction => Enter idle ==
+ * ===================================
+ */
+
+/*
+ * Do WFI instruction
+ * Includes the resume path for non-OFF modes
+ *
+ * This code gets copied to internal SRAM and is accessible
+ * from both SDRAM and SRAM:
+ * - executed from SRAM for non-off modes (omap3_do_wfi_sram),
+ * - executed from SDRAM for OFF mode (omap3_do_wfi).
+ */
+        .align  3
+ENTRY(omap3_do_wfi)
         ldr     r4, sdrc_power          @ read the SDRC_POWER register
         ldr     r5, [r4]                @ read the contents of SDRC_POWER
         orr     r5, r5, #0x40           @ enable self refresh on idle req
@@ -316,8 +270,86 @@ omap3_do_wfi:
         nop
         nop
         nop
-        bl wait_sdrc_ok
 
+/*
+ * This function implements the erratum ID i581 WA:
+ *  SDRC state restore before accessing the SDRAM
+ *
+ * Only used at return from non-OFF mode. For OFF
+ * mode the ROM code configures the SDRC and
+ * the DPLL before calling the restore code directly
+ * from DDR.
+ */
+
+/* Make sure SDRC accesses are ok */
+wait_sdrc_ok:
+
+/* DPLL3 must be locked before accessing the SDRC. Maybe the HW ensures this */
+        ldr     r4, cm_idlest_ckgen
+wait_dpll3_lock:
+        ldr     r5, [r4]
+        tst     r5, #1
+        beq     wait_dpll3_lock
+
+        ldr     r4, cm_idlest1_core
+wait_sdrc_ready:
+        ldr     r5, [r4]
+        tst     r5, #0x2
+        bne     wait_sdrc_ready
+        /* allow DLL powerdown upon hw idle req */
+        ldr     r4, sdrc_power
+        ldr     r5, [r4]
+        bic     r5, r5, #0x40
+        str     r5, [r4]
+
+/*
+ * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a
+ * base instead.
+ * Be careful not to clobber r7 when maintaing this code.
+ */
+
+is_dll_in_lock_mode:
+        /* Is dll in lock mode? */
+        ldr     r4, sdrc_dlla_ctrl
+        ldr     r5, [r4]
+        tst     r5, #0x4
+        bne     exit_nonoff_modes       @ Return if locked
+        /* wait till dll locks */
+        adr     r7, kick_counter
+wait_dll_lock_timed:
+        ldr     r4, wait_dll_lock_counter
+        add     r4, r4, #1
+        str     r4, [r7, #wait_dll_lock_counter - kick_counter]
+        ldr     r4, sdrc_dlla_status
+        /* Wait 20uS for lock */
+        mov     r6, #8
+wait_dll_lock:
+        subs    r6, r6, #0x1
+        beq     kick_dll
+        ldr     r5, [r4]
+        and     r5, r5, #0x4
+        cmp     r5, #0x4
+        bne     wait_dll_lock
+        b       exit_nonoff_modes       @ Return when locked
+
+        /* disable/reenable DLL if not locked */
+kick_dll:
+        ldr     r4, sdrc_dlla_ctrl
+        ldr     r5, [r4]
+        mov     r6, r5
+        bic     r6, #(1<<3)             @ disable dll
+        str     r6, [r4]
+        dsb
+        orr     r6, r6, #(1<<3)         @ enable dll
+        str     r6, [r4]
+        dsb
+        ldr     r4, kick_counter
+        add     r4, r4, #1
+        str     r4, [r7]                @ kick_counter
+        b       wait_dll_lock_timed
+
+exit_nonoff_modes:
+        /* Re-enable C-bit if needed */
         mrc     p15, 0, r0, c1, c0, 0
         tst     r0, #(1 << 2)           @ Check C bit enabled?
         orreq   r0, r0, #(1 << 2)       @ Enable the C bit if cleared
@@ -329,7 +361,32 @@ omap3_do_wfi:
  * == Exit point from non-OFF modes ==
  * ===================================
  */
-        ldmfd   sp!, {r0-r12, pc}       @ restore regs and return
+        ldmfd   sp!, {r4 - r11, pc}     @ restore regs and return
+
+/*
+ * Local variables
+ */
+sdrc_power:
+        .word   SDRC_POWER_V
+cm_idlest1_core:
+        .word   CM_IDLEST1_CORE_V
+cm_idlest_ckgen:
+        .word   CM_IDLEST_CKGEN_V
+sdrc_dlla_status:
+        .word   SDRC_DLLA_STATUS_V
+sdrc_dlla_ctrl:
+        .word   SDRC_DLLA_CTRL_V
+        /*
+         * When exporting to userspace while the counters are in SRAM,
+         * these 2 words need to be at the end to facilitate retrival!
+         */
+kick_counter:
+        .word   0
+wait_dll_lock_counter:
+        .word   0
+
+ENTRY(omap3_do_wfi_sz)
+        .word   . - omap3_do_wfi
 
 
 /*
@@ -346,13 +403,17 @@ omap3_do_wfi:
  *  restore_es3: applies to 34xx >= ES3.0
  *  restore_3630: applies to 36xx
  *  restore: common code for 3xxx
+ *
+ * Note: when back from CORE and MPU OFF mode we are running
+ *  from SDRAM, without MMU, without the caches and prediction.
+ *  Also the SRAM content has been cleared.
  */
-restore_es3:
+ENTRY(omap3_restore_es3)
         ldr     r5, pm_prepwstst_core_p
         ldr     r4, [r5]
         and     r4, r4, #0x3
         cmp     r4, #0x0        @ Check if previous power state of CORE is OFF
-        bne     restore
+        bne     omap3_restore   @ Fall through to OMAP3 common code
         adr     r0, es3_sdrc_fix
         ldr     r1, sram_base
         ldr     r2, es3_sdrc_fix_sz
@@ -364,35 +425,32 @@ copy_to_sram:
         bne     copy_to_sram
         ldr     r1, sram_base
         blx     r1
-        b       restore
+        b       omap3_restore   @ Fall through to OMAP3 common code
+ENDPROC(omap3_restore_es3)
 
-restore_3630:
+ENTRY(omap3_restore_3630)
         ldr     r1, pm_prepwstst_core_p
         ldr     r2, [r1]
         and     r2, r2, #0x3
         cmp     r2, #0x0        @ Check if previous power state of CORE is OFF
-        bne     restore
+        bne     omap3_restore   @ Fall through to OMAP3 common code
         /* Disable RTA before giving control */
         ldr     r1, control_mem_rta
         mov     r2, #OMAP36XX_RTA_DISABLE
         str     r2, [r1]
+ENDPROC(omap3_restore_3630)
 
         /* Fall through to common code for the remaining logic */
 
-restore:
+ENTRY(omap3_restore)
         /*
-         * Check what was the reason for mpu reset and store the reason in r9:
-         *  0 - No context lost
-         *  1 - Only L1 and logic lost
-         *  2 - Only L2 lost - In this case, we wont be here
-         *  3 - Both L1 and L2 lost
+         * Read the pwstctrl register to check the reason for mpu reset.
+         * This tells us what was lost.
          */
         ldr     r1, pm_pwstctrl_mpu
         ldr     r2, [r1]
         and     r2, r2, #0x3
         cmp     r2, #0x0        @ Check if target power state was OFF or RET
-        moveq   r9, #0x3        @ MPU OFF => L1 and L2 lost
-        movne   r9, #0x1        @ Only L1 and L2 lost => avoid L2 invalidation
         bne     logic_l1_restore
 
         ldr     r0, l2dis_3630
@@ -471,115 +529,39 @@ logic_l1_restore:
         orr     r1, r1, #2              @ re-enable L2 cache
         mcr     p15, 0, r1, c1, c0, 1
 skipl2reen:
-        mov     r1, #0
-        /*
-         * Invalidate all instruction caches to PoU
-         * and flush branch target cache
-         */
-        mcr     p15, 0, r1, c7, c5, 0
 
-        ldr     r4, scratchpad_base
-        ldr     r3, [r4,#0xBC]
-        adds    r3, r3, #16
-
-        ldmia   r3!, {r4-r6}
-        mov     sp, r4                  @ Restore sp
-        msr     spsr_cxsf, r5           @ Restore spsr
-        mov     lr, r6                  @ Restore lr
-
-        ldmia   r3!, {r4-r7}
-        mcr     p15, 0, r4, c1, c0, 2   @ Coprocessor access Control Register
-        mcr     p15, 0, r5, c2, c0, 0   @ TTBR0
-        mcr     p15, 0, r6, c2, c0, 1   @ TTBR1
-        mcr     p15, 0, r7, c2, c0, 2   @ TTBCR
-
-        ldmia   r3!,{r4-r6}
-        mcr     p15, 0, r4, c3, c0, 0   @ Domain access Control Register
-        mcr     p15, 0, r5, c10, c2, 0  @ PRRR
-        mcr     p15, 0, r6, c10, c2, 1  @ NMRR
-
-
-        ldmia   r3!,{r4-r7}
-        mcr     p15, 0, r4, c13, c0, 1  @ Context ID
-        mcr     p15, 0, r5, c13, c0, 2  @ User r/w thread and process ID
-        mrc     p15, 0, r6, c12, c0, 0  @ Secure or NS vector base address
-        msr     cpsr, r7                @ store cpsr
-
-        /* Enabling MMU here */
-        mrc     p15, 0, r7, c2, c0, 2   @ Read TTBRControl
-        /* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1 */
-        and     r7, #0x7
-        cmp     r7, #0x0
-        beq     usettbr0
-ttbr_error:
-        /*
-         * More work needs to be done to support N[0:2] value other than 0
-         * So looping here so that the error can be detected
-         */
-        b       ttbr_error
-usettbr0:
-        mrc     p15, 0, r2, c2, c0, 0
-        ldr     r5, ttbrbit_mask
-        and     r2, r5
-        mov     r4, pc
-        ldr     r5, table_index_mask
-        and     r4, r5                  @ r4 = 31 to 20 bits of pc
-        /* Extract the value to be written to table entry */
-        ldr     r1, table_entry
-        /* r1 has the value to be written to table entry*/
-        add     r1, r1, r4
-        /* Getting the address of table entry to modify */
-        lsr     r4, #18
-        /* r2 has the location which needs to be modified */
-        add     r2, r4
-        /* Storing previous entry of location being modified */
-        ldr     r5, scratchpad_base
-        ldr     r4, [r2]
-        str     r4, [r5, #0xC0]
-        /* Modify the table entry */
-        str     r1, [r2]
-        /*
-         * Storing address of entry being modified
-         * - will be restored after enabling MMU
-         */
-        ldr     r5, scratchpad_base
-        str     r2, [r5, #0xC4]
-
-        mov     r0, #0
-        mcr     p15, 0, r0, c7, c5, 4   @ Flush prefetch buffer
-        mcr     p15, 0, r0, c7, c5, 6   @ Invalidate branch predictor array
-        mcr     p15, 0, r0, c8, c5, 0   @ Invalidate instruction TLB
-        mcr     p15, 0, r0, c8, c6, 0   @ Invalidate data TLB
-        /*
-         * Restore control register. This enables the MMU.
-         * The caches and prediction are not enabled here, they
-         * will be enabled after restoring the MMU table entry.
-         */
-        ldmia   r3!, {r4}
-        /* Store previous value of control register in scratchpad */
-        str     r4, [r5, #0xC8]
-        ldr     r2, cache_pred_disable_mask
-        and     r4, r2
-        mcr     p15, 0, r4, c1, c0, 0
-        dsb
-        isb
-        ldr     r0, =restoremmu_on
-        bx      r0
+        /* Now branch to the common CPU resume function */
+        b       cpu_resume
+ENDPROC(omap3_restore)
+
+        .ltorg
 
 /*
- * ==============================
- * == Exit point from OFF mode ==
- * ==============================
+ * Local variables
  */
-restoremmu_on:
-        ldmfd   sp!, {r0-r12, pc}       @ restore regs and return
-
+pm_prepwstst_core_p:
+        .word   PM_PREPWSTST_CORE_P
+pm_pwstctrl_mpu:
+        .word   PM_PWSTCTRL_MPU_P
+scratchpad_base:
+        .word   SCRATCHPAD_BASE_P
+sram_base:
+        .word   SRAM_BASE_P + 0x8000
+control_stat:
+        .word   CONTROL_STAT
+control_mem_rta:
+        .word   CONTROL_MEM_RTA_CTRL
+l2dis_3630:
+        .word   0
 
 /*
  * Internal functions
  */
 
-/* This function implements the erratum ID i443 WA, applies to 34xx >= ES3.0 */
+/*
+ * This function implements the erratum ID i443 WA, applies to 34xx >= ES3.0
+ * Copied to and run from SRAM in order to reconfigure the SDRC parameters.
+ */
         .text
         .align  3
 ENTRY(es3_sdrc_fix)
@@ -609,6 +591,9 @@ ENTRY(es3_sdrc_fix)
         str     r5, [r4]                @ kick off refreshes
         bx      lr
 
+/*
+ * Local variables
+ */
         .align
 sdrc_syscfg:
         .word   SDRC_SYSCONFIG_P
@@ -627,128 +612,3 @@ sdrc_manual_1:
 ENDPROC(es3_sdrc_fix)
 ENTRY(es3_sdrc_fix_sz)
         .word   . - es3_sdrc_fix
-
-/*
- * This function implements the erratum ID i581 WA:
- *  SDRC state restore before accessing the SDRAM
- *
- * Only used at return from non-OFF mode. For OFF
- * mode the ROM code configures the SDRC and
- * the DPLL before calling the restore code directly
- * from DDR.
- */
-
-/* Make sure SDRC accesses are ok */
-wait_sdrc_ok:
-
-/* DPLL3 must be locked before accessing the SDRC. Maybe the HW ensures this */
-        ldr     r4, cm_idlest_ckgen
-wait_dpll3_lock:
-        ldr     r5, [r4]
-        tst     r5, #1
-        beq     wait_dpll3_lock
-
-        ldr     r4, cm_idlest1_core
-wait_sdrc_ready:
-        ldr     r5, [r4]
-        tst     r5, #0x2
-        bne     wait_sdrc_ready
-        /* allow DLL powerdown upon hw idle req */
-        ldr     r4, sdrc_power
-        ldr     r5, [r4]
-        bic     r5, r5, #0x40
-        str     r5, [r4]
-
-/*
- * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a
- * base instead.
- * Be careful not to clobber r7 when maintaing this code.
- */
-
-is_dll_in_lock_mode:
-        /* Is dll in lock mode? */
-        ldr     r4, sdrc_dlla_ctrl
-        ldr     r5, [r4]
-        tst     r5, #0x4
-        bxne    lr                      @ Return if locked
-        /* wait till dll locks */
-        adr     r7, kick_counter
-wait_dll_lock_timed:
-        ldr     r4, wait_dll_lock_counter
-        add     r4, r4, #1
-        str     r4, [r7, #wait_dll_lock_counter - kick_counter]
-        ldr     r4, sdrc_dlla_status
-        /* Wait 20uS for lock */
-        mov     r6, #8
-wait_dll_lock:
-        subs    r6, r6, #0x1
-        beq     kick_dll
-        ldr     r5, [r4]
-        and     r5, r5, #0x4
-        cmp     r5, #0x4
-        bne     wait_dll_lock
-        bx      lr                      @ Return when locked
-
-        /* disable/reenable DLL if not locked */
-kick_dll:
-        ldr     r4, sdrc_dlla_ctrl
-        ldr     r5, [r4]
-        mov     r6, r5
-        bic     r6, #(1<<3)             @ disable dll
-        str     r6, [r4]
-        dsb
-        orr     r6, r6, #(1<<3)         @ enable dll
-        str     r6, [r4]
-        dsb
-        ldr     r4, kick_counter
-        add     r4, r4, #1
-        str     r4, [r7]                @ kick_counter
-        b       wait_dll_lock_timed
-
-        .align
-cm_idlest1_core:
-        .word   CM_IDLEST1_CORE_V
-cm_idlest_ckgen:
-        .word   CM_IDLEST_CKGEN_V
-sdrc_dlla_status:
-        .word   SDRC_DLLA_STATUS_V
-sdrc_dlla_ctrl:
-        .word   SDRC_DLLA_CTRL_V
-pm_prepwstst_core_p:
-        .word   PM_PREPWSTST_CORE_P
-pm_pwstctrl_mpu:
-        .word   PM_PWSTCTRL_MPU_P
-scratchpad_base:
-        .word   SCRATCHPAD_BASE_P
-sram_base:
-        .word   SRAM_BASE_P + 0x8000
-sdrc_power:
-        .word   SDRC_POWER_V
-ttbrbit_mask:
-        .word   0xFFFFC000
-table_index_mask:
-        .word   0xFFF00000
-table_entry:
-        .word   0x00000C02
-cache_pred_disable_mask:
-        .word   0xFFFFE7FB
-control_stat:
-        .word   CONTROL_STAT
-control_mem_rta:
-        .word   CONTROL_MEM_RTA_CTRL
-kernel_flush:
-        .word   v7_flush_dcache_all
-l2dis_3630:
-        .word   0
-        /*
-         * When exporting to userspace while the counters are in SRAM,
-         * these 2 words need to be at the end to facilitate retrival!
-         */
-kick_counter:
-        .word   0
-wait_dll_lock_counter:
-        .word   0
-ENDPROC(omap34xx_cpu_suspend)
-
-ENTRY(omap34xx_cpu_suspend_sz)
-        .word   . - omap34xx_cpu_suspend
diff --git a/arch/arm/mach-pnx4008/include/mach/entry-macro.S b/arch/arm/mach-pnx4008/include/mach/entry-macro.S
index 8003037578ed..db7eeebf30d7 100644
--- a/arch/arm/mach-pnx4008/include/mach/entry-macro.S
+++ b/arch/arm/mach-pnx4008/include/mach/entry-macro.S
@@ -120,8 +120,3 @@
 1003:
                 .endm
 
-
-                .macro  irq_prio_table
-                .endm
-
-
diff --git a/arch/arm/mach-pxa/include/mach/pm.h b/arch/arm/mach-pxa/include/mach/pm.h
index f15afe012995..51558bcee999 100644
--- a/arch/arm/mach-pxa/include/mach/pm.h
+++ b/arch/arm/mach-pxa/include/mach/pm.h
@@ -22,8 +22,8 @@ struct pxa_cpu_pm_fns {
 extern struct pxa_cpu_pm_fns *pxa_cpu_pm_fns;
 
 /* sleep.S */
-extern void pxa25x_cpu_suspend(unsigned int, long);
-extern void pxa27x_cpu_suspend(unsigned int, long);
+extern int pxa25x_finish_suspend(unsigned long);
+extern int pxa27x_finish_suspend(unsigned long);
 
 extern int pxa_pm_enter(suspend_state_t state);
 extern int pxa_pm_prepare(void);
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c
index 87ae3129f4f7..b27544bcafcb 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.c
@@ -347,9 +347,9 @@ static int pxa2xx_mfp_suspend(void)
                 if ((gpio_desc[i].config & MFP_LPM_KEEP_OUTPUT) &&
                     (GPDR(i) & GPIO_bit(i))) {
                         if (GPLR(i) & GPIO_bit(i))
-                                PGSR(i) |= GPIO_bit(i);
+                                PGSR(gpio_to_bank(i)) |= GPIO_bit(i);
                         else
-                                PGSR(i) &= ~GPIO_bit(i);
+                                PGSR(gpio_to_bank(i)) &= ~GPIO_bit(i);
                 }
         }
 
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index 65f24f0b77e8..5a5329bc33f1 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -33,6 +33,7 @@
 #include <linux/i2c-gpio.h>
 
 #include <asm/mach-types.h>
+#include <asm/suspend.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
diff --git a/arch/arm/mach-pxa/pm.c b/arch/arm/mach-pxa/pm.c
index 51e1583265b2..37178a8559b1 100644
--- a/arch/arm/mach-pxa/pm.c
+++ b/arch/arm/mach-pxa/pm.c
@@ -42,7 +42,6 @@ int pxa_pm_enter(suspend_state_t state)
 
         /* *** go zzz *** */
         pxa_cpu_pm_fns->enter(state);
-        cpu_init();
 
         if (state != PM_SUSPEND_STANDBY && pxa_cpu_pm_fns->restore) {
                 /* after sleeping, validate the checksum */
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index fed363cec9c6..9c434d21a271 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -25,6 +25,7 @@
 #include <linux/irq.h>
 
 #include <asm/mach/map.h>
+#include <asm/suspend.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/gpio.h>
@@ -244,7 +245,7 @@ static void pxa25x_cpu_pm_enter(suspend_state_t state)
 
         switch (state) {
         case PM_SUSPEND_MEM:
-                pxa25x_cpu_suspend(PWRMODE_SLEEP, PLAT_PHYS_OFFSET - PAGE_OFFSET);
+                cpu_suspend(PWRMODE_SLEEP, pxa25x_finish_suspend);
                 break;
         }
 }
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 2fecbec58d88..9d2400b5f503 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -24,6 +24,7 @@
 #include <asm/mach/map.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
+#include <asm/suspend.h>
 #include <mach/irqs.h>
 #include <mach/gpio.h>
 #include <mach/pxa27x.h>
@@ -284,6 +285,11 @@ void pxa27x_cpu_pm_restore(unsigned long *sleep_save)
 void pxa27x_cpu_pm_enter(suspend_state_t state)
 {
         extern void pxa_cpu_standby(void);
+#ifndef CONFIG_IWMMXT
+        u64 acc0;
+
+        asm volatile("mra %Q0, %R0, acc0" : "=r" (acc0));
+#endif
 
         /* ensure voltage-change sequencer not initiated, which hangs */
         PCFR &= ~PCFR_FVC;
@@ -299,7 +305,10 @@ void pxa27x_cpu_pm_enter(suspend_state_t state)
                 pxa_cpu_standby();
                 break;
         case PM_SUSPEND_MEM:
-                pxa27x_cpu_suspend(pwrmode, PLAT_PHYS_OFFSET - PAGE_OFFSET);
+                cpu_suspend(pwrmode, pxa27x_finish_suspend);
+#ifndef CONFIG_IWMMXT
+                asm volatile("mar acc0, %Q0, %R0" : "=r" (acc0));
+#endif
                 break;
         }
 }
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 8521d7d6f1da..ef1c56a67afc 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -24,6 +24,7 @@
 #include <linux/i2c/pxa-i2c.h>
 
 #include <asm/mach/map.h>
+#include <asm/suspend.h>
 #include <mach/hardware.h>
 #include <mach/gpio.h>
 #include <mach/pxa3xx-regs.h>
@@ -141,8 +142,13 @@ static void pxa3xx_cpu_pm_suspend(void)
 {
         volatile unsigned long *p = (volatile void *)0xc0000000;
         unsigned long saved_data = *p;
+#ifndef CONFIG_IWMMXT
+        u64 acc0;
 
-        extern void pxa3xx_cpu_suspend(long);
+        asm volatile("mra %Q0, %R0, acc0" : "=r" (acc0));
+#endif
+
+        extern int pxa3xx_finish_suspend(unsigned long);
 
         /* resuming from D2 requires the HSIO2/BOOT/TPM clocks enabled */
         CKENA |= (1 << CKEN_BOOT) | (1 << CKEN_TPM);
@@ -162,11 +168,15 @@ static void pxa3xx_cpu_pm_suspend(void)
         /* overwrite with the resume address */
         *p = virt_to_phys(cpu_resume);
 
-        pxa3xx_cpu_suspend(PLAT_PHYS_OFFSET - PAGE_OFFSET);
+        cpu_suspend(0, pxa3xx_finish_suspend);
 
         *p = saved_data;
 
         AD3ER = 0;
+
+#ifndef CONFIG_IWMMXT
+        asm volatile("mar acc0, %Q0, %R0" : "=r" (acc0));
+#endif
 }
 
 static void pxa3xx_cpu_pm_enter(suspend_state_t state)
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index d130f77b6d11..2f37d43f51b6 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -573,10 +573,10 @@ static struct pxafb_mode_info sharp_lq043t3dx02_mode = {
         .xres           = 480,
         .yres           = 272,
         .bpp            = 16,
-        .hsync_len      = 4,
+        .hsync_len      = 41,
         .left_margin    = 2,
         .right_margin   = 1,
-        .vsync_len      = 1,
+        .vsync_len      = 10,
         .upper_margin   = 3,
         .lower_margin   = 1,
         .sync           = 0,
@@ -596,29 +596,31 @@ static void __init raumfeld_lcd_init(void)
 {
         int ret;
 
-        pxa_set_fb_info(NULL, &raumfeld_sharp_lcd_info);
-
-        /* Earlier devices had the backlight regulator controlled
-         * via PWM, later versions use another controller for that */
-        if ((system_rev & 0xff) < 2) {
-                mfp_cfg_t raumfeld_pwm_pin_config = GPIO17_PWM0_OUT;
-                pxa3xx_mfp_config(&raumfeld_pwm_pin_config, 1);
-                platform_device_register(&raumfeld_pwm_backlight_device);
-        } else
-                platform_device_register(&raumfeld_lt3593_device);
-
         ret = gpio_request(GPIO_TFT_VA_EN, "display VA enable");
         if (ret < 0)
                 pr_warning("Unable to request GPIO_TFT_VA_EN\n");
         else
                 gpio_direction_output(GPIO_TFT_VA_EN, 1);
 
+        msleep(100);
+
         ret = gpio_request(GPIO_DISPLAY_ENABLE, "display enable");
         if (ret < 0)
                 pr_warning("Unable to request GPIO_DISPLAY_ENABLE\n");
         else
                 gpio_direction_output(GPIO_DISPLAY_ENABLE, 1);
 
+        /* Hardware revision 2 has the backlight regulator controlled
+         * by an LT3593, earlier and later devices use PWM for that. */
+        if ((system_rev & 0xff) == 2) {
+                platform_device_register(&raumfeld_lt3593_device);
+        } else {
+                mfp_cfg_t raumfeld_pwm_pin_config = GPIO17_PWM0_OUT;
+                pxa3xx_mfp_config(&raumfeld_pwm_pin_config, 1);
+                platform_device_register(&raumfeld_pwm_backlight_device);
+        }
+
+        pxa_set_fb_info(NULL, &raumfeld_sharp_lcd_info);
         platform_device_register(&pxa3xx_device_gcu);
 }
 
@@ -657,10 +659,10 @@ static struct lis3lv02d_platform_data lis3_pdata = {
 
 #define SPI_AK4104      \
 {                       \
-        .modalias       = "ak4104",     \
-        .max_speed_hz   = 10000,        \
-        .bus_num        = 0,            \
-        .chip_select    = 0,            \
+        .modalias       = "ak4104-codec",       \
+        .max_speed_hz   = 10000,                \
+        .bus_num        = 0,                    \
+        .chip_select    = 0,                    \
         .controller_data = (void *) GPIO_SPDIF_CS,      \
 }
 
diff --git a/arch/arm/mach-pxa/sleep.S b/arch/arm/mach-pxa/sleep.S
index 6f5368899d84..1e544be9905d 100644
--- a/arch/arm/mach-pxa/sleep.S
+++ b/arch/arm/mach-pxa/sleep.S
@@ -24,20 +24,9 @@
 
 #ifdef CONFIG_PXA3xx
 /*
- * pxa3xx_cpu_suspend() - forces CPU into sleep state (S2D3C4)
- *
- * r0 = v:p offset
+ * pxa3xx_finish_suspend() - forces CPU into sleep state (S2D3C4)
  */
-ENTRY(pxa3xx_cpu_suspend)
-
-#ifndef CONFIG_IWMMXT
-        mra     r2, r3, acc0
-#endif
-        stmfd   sp!, {r2 - r12, lr}     @ save registers on stack
-        mov     r1, r0
-        ldr     r3, =pxa_cpu_resume     @ resume function
-        bl      cpu_suspend
-
+ENTRY(pxa3xx_finish_suspend)
         mov     r0, #0x06               @ S2D3C4 mode
         mcr     p14, 0, r0, c7, c0, 0   @ enter sleep
 
@@ -46,28 +35,18 @@ ENTRY(pxa3xx_cpu_suspend)
 
 #ifdef CONFIG_PXA27x
 /*
- * pxa27x_cpu_suspend()
+ * pxa27x_finish_suspend()
  *
  * Forces CPU into sleep state.
  *
  * r0 = value for PWRMODE M field for desired sleep state
- * r1 = v:p offset
  */
-ENTRY(pxa27x_cpu_suspend)
-
-#ifndef CONFIG_IWMMXT
-        mra     r2, r3, acc0
-#endif
-        stmfd   sp!, {r2 - r12, lr}             @ save registers on stack
-        mov     r4, r0                          @ save sleep mode
-        ldr     r3, =pxa_cpu_resume             @ resume function
-        bl      cpu_suspend
-
+ENTRY(pxa27x_finish_suspend)
         @ Put the processor to sleep
         @ (also workaround for sighting 28071)
 
         @ prepare value for sleep mode
-        mov     r1, r4                          @ sleep mode
+        mov     r1, r0                          @ sleep mode
 
         @ prepare pointer to physical address 0 (virtual mapping in generic.c)
         mov     r2, #UNCACHED_PHYS_0
@@ -99,21 +78,16 @@ ENTRY(pxa27x_cpu_suspend)
 
 #ifdef CONFIG_PXA25x
 /*
- * pxa25x_cpu_suspend()
+ * pxa25x_finish_suspend()
  *
  * Forces CPU into sleep state.
  *
  * r0 = value for PWRMODE M field for desired sleep state
- * r1 = v:p offset
  */
 
-ENTRY(pxa25x_cpu_suspend)
-        stmfd   sp!, {r2 - r12, lr}             @ save registers on stack
-        mov     r4, r0                          @ save sleep mode
-        ldr     r3, =pxa_cpu_resume             @ resume function
-        bl      cpu_suspend
+ENTRY(pxa25x_finish_suspend)
         @ prepare value for sleep mode
-        mov     r1, r4                          @ sleep mode
+        mov     r1, r0                          @ sleep mode
 
         @ prepare pointer to physical address 0 (virtual mapping in generic.c)
         mov     r2, #UNCACHED_PHYS_0
@@ -195,16 +169,3 @@ pxa_cpu_do_suspend:
         mcr     p14, 0, r1, c7, c0, 0           @ PWRMODE
 
 20:     b       20b                             @ loop waiting for sleep
-
-/*
- * pxa_cpu_resume()
- *
- * entry point from bootloader into kernel during resume
- */
-        .align 5
-pxa_cpu_resume:
-        ldmfd   sp!, {r2, r3}
-#ifndef CONFIG_IWMMXT
-        mar     acc0, r2, r3
-#endif
-        ldmfd   sp!, {r4 - r12, pc}             @ return to caller
diff --git a/arch/arm/mach-pxa/spitz_pm.c b/arch/arm/mach-pxa/spitz_pm.c
index 7fe74067d85f..094279aefe9c 100644
--- a/arch/arm/mach-pxa/spitz_pm.c
+++ b/arch/arm/mach-pxa/spitz_pm.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/apm-emulation.h>
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 00363c7ac182..9b99cc164de5 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -31,6 +31,7 @@
 #include <linux/can/platform/mcp251x.h>
 
 #include <asm/mach-types.h>
+#include <asm/suspend.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
@@ -676,7 +677,7 @@ static struct pxa2xx_udc_mach_info zeus_udc_info = {
 static void zeus_power_off(void)
 {
         local_irq_disable();
-        pxa27x_cpu_suspend(PWRMODE_DEEPSLEEP, PLAT_PHYS_OFFSET - PAGE_OFFSET);
+        cpu_suspend(PWRMODE_DEEPSLEEP, pxa27x_finish_suspend);
 }
 #else
 #define zeus_power_off   NULL
diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig
index b9a9805e4828..dba6d0c1fc17 100644
--- a/arch/arm/mach-realview/Kconfig
+++ b/arch/arm/mach-realview/Kconfig
@@ -50,6 +50,7 @@ config MACH_REALVIEW_PB1176
         bool "Support RealView(R) Platform Baseboard for ARM1176JZF-S"
         select CPU_V6
         select ARM_GIC
+        select HAVE_TCM
         help
           Include support for the ARM(R) RealView(R) Platform Baseboard for
           ARM1176JZF-S.
diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c
index 963bf0d8119a..4ae943bafa92 100644
--- a/arch/arm/mach-realview/platsmp.c
+++ b/arch/arm/mach-realview/platsmp.c
@@ -68,14 +68,6 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-        int i;
-
-        /*
-         * Initialise the present map, which describes the set of CPUs
-         * actually populated at the present time.
-         */
-        for (i = 0; i < max_cpus; i++)
-                set_cpu_present(i, true);
 
         scu_enable(scu_base_addr());
 
diff --git a/arch/arm/mach-s3c2412/pm.c b/arch/arm/mach-s3c2412/pm.c
index 752b13a7b3db..f4077efa51fa 100644
--- a/arch/arm/mach-s3c2412/pm.c
+++ b/arch/arm/mach-s3c2412/pm.c
@@ -37,12 +37,10 @@
 
 extern void s3c2412_sleep_enter(void);
 
-static void s3c2412_cpu_suspend(void)
+static int s3c2412_cpu_suspend(unsigned long arg)
 {
         unsigned long tmp;
 
-        flush_cache_all();
-
         /* set our standby method to sleep */
 
         tmp = __raw_readl(S3C2412_PWRCFG);
@@ -50,6 +48,8 @@ static void s3c2412_cpu_suspend(void)
         __raw_writel(tmp, S3C2412_PWRCFG);
 
         s3c2412_sleep_enter();
+
+        panic("sleep resumed to originator?");
 }
 
 static void s3c2412_pm_prepare(void)
diff --git a/arch/arm/mach-s3c2416/pm.c b/arch/arm/mach-s3c2416/pm.c
index 41db2b21e213..9ec54f1d8e75 100644
--- a/arch/arm/mach-s3c2416/pm.c
+++ b/arch/arm/mach-s3c2416/pm.c
@@ -24,10 +24,8 @@
 
 extern void s3c2412_sleep_enter(void);
 
-static void s3c2416_cpu_suspend(void)
+static int s3c2416_cpu_suspend(unsigned long arg)
 {
-        flush_cache_all();
-
         /* enable wakeup sources regardless of battery state */
         __raw_writel(S3C2443_PWRCFG_SLEEP, S3C2443_PWRCFG);
 
@@ -35,6 +33,8 @@ static void s3c2416_cpu_suspend(void)
         __raw_writel(0x2BED, S3C2443_PWRMODE);
 
         s3c2412_sleep_enter();
+
+        panic("sleep resumed to originator?");
 }
 
 static void s3c2416_pm_prepare(void)
diff --git a/arch/arm/mach-s3c2440/mach-mini2440.c b/arch/arm/mach-s3c2440/mach-mini2440.c
index dd3120df09fe..fc2dc0b3d4fe 100644
--- a/arch/arm/mach-s3c2440/mach-mini2440.c
+++ b/arch/arm/mach-s3c2440/mach-mini2440.c
@@ -552,7 +552,7 @@ struct mini2440_features_t {
         struct platform_device *optional[8];
 };
 
-static void mini2440_parse_features(
+static void __init mini2440_parse_features(
                 struct mini2440_features_t * features,
                 const char * features_str )
 {
diff --git a/arch/arm/mach-s3c64xx/dev-spi.c b/arch/arm/mach-s3c64xx/dev-spi.c
index 82db072cb836..5e6b42089eb4 100644
--- a/arch/arm/mach-s3c64xx/dev-spi.c
+++ b/arch/arm/mach-s3c64xx/dev-spi.c
@@ -88,6 +88,7 @@ static struct s3c64xx_spi_info s3c64xx_spi0_pdata = {
         .cfg_gpio = s3c64xx_spi_cfg_gpio,
         .fifo_lvl_mask = 0x7f,
         .rx_lvl_offset = 13,
+        .tx_st_done = 21,
 };
 
 static u64 spi_dmamask = DMA_BIT_MASK(32);
@@ -132,6 +133,7 @@ static struct s3c64xx_spi_info s3c64xx_spi1_pdata = {
         .cfg_gpio = s3c64xx_spi_cfg_gpio,
         .fifo_lvl_mask = 0x7f,
         .rx_lvl_offset = 13,
+        .tx_st_done = 21,
 };
 
 struct platform_device s3c64xx_device_spi1 = {
diff --git a/arch/arm/mach-s3c64xx/dma.c b/arch/arm/mach-s3c64xx/dma.c
index b197171e7d03..204bfafe4bfc 100644
--- a/arch/arm/mach-s3c64xx/dma.c
+++ b/arch/arm/mach-s3c64xx/dma.c
@@ -113,7 +113,7 @@ found:
         return chan;
 }
 
-int s3c2410_dma_config(unsigned int channel, int xferunit)
+int s3c2410_dma_config(enum dma_ch channel, int xferunit)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
 
@@ -297,7 +297,7 @@ static int s3c64xx_dma_flush(struct s3c2410_dma_chan *chan)
         return 0;
 }
 
-int s3c2410_dma_ctrl(unsigned int channel, enum s3c2410_chan_op op)
+int s3c2410_dma_ctrl(enum dma_ch channel, enum s3c2410_chan_op op)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
 
@@ -331,7 +331,7 @@ EXPORT_SYMBOL(s3c2410_dma_ctrl);
  *
  */
 
-int s3c2410_dma_enqueue(unsigned int channel, void *id,
+int s3c2410_dma_enqueue(enum dma_ch channel, void *id,
                         dma_addr_t data, int size)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
@@ -415,7 +415,7 @@ err_buff:
 EXPORT_SYMBOL(s3c2410_dma_enqueue);
 
 
-int s3c2410_dma_devconfig(unsigned int channel,
+int s3c2410_dma_devconfig(enum dma_ch channel,
                           enum s3c2410_dmasrc source,
                           unsigned long devaddr)
 {
@@ -463,7 +463,7 @@ int s3c2410_dma_devconfig(unsigned int channel,
 EXPORT_SYMBOL(s3c2410_dma_devconfig);
 
 
-int s3c2410_dma_getposition(unsigned int channel,
+int s3c2410_dma_getposition(enum dma_ch channel,
                             dma_addr_t *src, dma_addr_t *dst)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
@@ -487,7 +487,7 @@ EXPORT_SYMBOL(s3c2410_dma_getposition);
  * get control of an dma channel
 */
 
-int s3c2410_dma_request(unsigned int channel,
+int s3c2410_dma_request(enum dma_ch channel,
                         struct s3c2410_dma_client *client,
                         void *dev)
 {
@@ -533,7 +533,7 @@ EXPORT_SYMBOL(s3c2410_dma_request);
  * allowed to go through.
 */
 
-int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *client)
+int s3c2410_dma_free(enum dma_ch channel, struct s3c2410_dma_client *client)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
         unsigned long flags;
diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c
index bc1c470b7de6..8bad64370689 100644
--- a/arch/arm/mach-s3c64xx/pm.c
+++ b/arch/arm/mach-s3c64xx/pm.c
@@ -112,7 +112,7 @@ void s3c_pm_save_core(void)
  * this.
  */
 
-static void s3c64xx_cpu_suspend(void)
+static int s3c64xx_cpu_suspend(unsigned long arg)
 {
         unsigned long tmp;
 
diff --git a/arch/arm/mach-s3c64xx/sleep.S b/arch/arm/mach-s3c64xx/sleep.S
index 1f87732b2320..34313f9c8792 100644
--- a/arch/arm/mach-s3c64xx/sleep.S
+++ b/arch/arm/mach-s3c64xx/sleep.S
@@ -25,29 +25,6 @@
 
         .text
 
-        /* s3c_cpu_save
-         *
-         * Save enough processor state to allow the restart of the pm.c
-         * code after resume.
-         *
-         * entry:
-         *      r1 = v:p offset
-        */
-
-ENTRY(s3c_cpu_save)
-        stmfd   sp!, { r4 - r12, lr }
-        ldr     r3, =resume_with_mmu
-        bl      cpu_suspend
-
-        @@ call final suspend code
-        ldr     r0, =pm_cpu_sleep
-        ldr     pc, [r0]
-        
-        @@ return to the caller, after the MMU is turned on.
-        @@ restore the last bits of the stack and return.
-resume_with_mmu:
-        ldmfd   sp!, { r4 - r12, pc }   @ return, from sp from s3c_cpu_save
-
         /* Sleep magic, the word before the resume entry point so that the
          * bootloader can check for a resumeable image. */
 
diff --git a/arch/arm/mach-s5p64x0/dev-spi.c b/arch/arm/mach-s5p64x0/dev-spi.c
index e78ee18c76e3..ac825e826326 100644
--- a/arch/arm/mach-s5p64x0/dev-spi.c
+++ b/arch/arm/mach-s5p64x0/dev-spi.c
@@ -112,12 +112,14 @@ static struct s3c64xx_spi_info s5p6440_spi0_pdata = {
         .cfg_gpio       = s5p6440_spi_cfg_gpio,
         .fifo_lvl_mask  = 0x1ff,
         .rx_lvl_offset  = 15,
+        .tx_st_done     = 25,
 };
 
 static struct s3c64xx_spi_info s5p6450_spi0_pdata = {
         .cfg_gpio       = s5p6450_spi_cfg_gpio,
         .fifo_lvl_mask  = 0x1ff,
         .rx_lvl_offset  = 15,
+        .tx_st_done     = 25,
 };
 
 static u64 spi_dmamask = DMA_BIT_MASK(32);
@@ -160,12 +162,14 @@ static struct s3c64xx_spi_info s5p6440_spi1_pdata = {
         .cfg_gpio       = s5p6440_spi_cfg_gpio,
         .fifo_lvl_mask  = 0x7f,
         .rx_lvl_offset  = 15,
+        .tx_st_done     = 25,
 };
 
 static struct s3c64xx_spi_info s5p6450_spi1_pdata = {
         .cfg_gpio       = s5p6450_spi_cfg_gpio,
         .fifo_lvl_mask  = 0x7f,
         .rx_lvl_offset  = 15,
+        .tx_st_done     = 25,
 };
 
 struct platform_device s5p64x0_device_spi1 = {
diff --git a/arch/arm/mach-s5pc100/dev-spi.c b/arch/arm/mach-s5pc100/dev-spi.c
index 57b19794d9bb..e5d6c4dceb56 100644
--- a/arch/arm/mach-s5pc100/dev-spi.c
+++ b/arch/arm/mach-s5pc100/dev-spi.c
@@ -15,6 +15,7 @@
 #include <mach/dma.h>
 #include <mach/map.h>
 #include <mach/spi-clocks.h>
+#include <mach/irqs.h>
 
 #include <plat/s3c64xx-spi.h>
 #include <plat/gpio-cfg.h>
@@ -90,6 +91,7 @@ static struct s3c64xx_spi_info s5pc100_spi0_pdata = {
         .fifo_lvl_mask = 0x7f,
         .rx_lvl_offset = 13,
         .high_speed = 1,
+        .tx_st_done = 21,
 };
 
 static u64 spi_dmamask = DMA_BIT_MASK(32);
@@ -134,6 +136,7 @@ static struct s3c64xx_spi_info s5pc100_spi1_pdata = {
         .fifo_lvl_mask = 0x7f,
         .rx_lvl_offset = 13,
         .high_speed = 1,
+        .tx_st_done = 21,
 };
 
 struct platform_device s5pc100_device_spi1 = {
@@ -176,6 +179,7 @@ static struct s3c64xx_spi_info s5pc100_spi2_pdata = {
         .fifo_lvl_mask = 0x7f,
         .rx_lvl_offset = 13,
         .high_speed = 1,
+        .tx_st_done = 21,
 };
 
 struct platform_device s5pc100_device_spi2 = {
diff --git a/arch/arm/mach-s5pv210/dev-spi.c b/arch/arm/mach-s5pv210/dev-spi.c
index e3249a47e3b1..eaf9a7bff7a0 100644
--- a/arch/arm/mach-s5pv210/dev-spi.c
+++ b/arch/arm/mach-s5pv210/dev-spi.c
@@ -85,6 +85,7 @@ static struct s3c64xx_spi_info s5pv210_spi0_pdata = {
         .fifo_lvl_mask = 0x1ff,
         .rx_lvl_offset = 15,
         .high_speed = 1,
+        .tx_st_done = 25,
 };
 
 static u64 spi_dmamask = DMA_BIT_MASK(32);
@@ -129,6 +130,7 @@ static struct s3c64xx_spi_info s5pv210_spi1_pdata = {
         .fifo_lvl_mask = 0x7f,
         .rx_lvl_offset = 15,
         .high_speed = 1,
+        .tx_st_done = 25,
 };
 
 struct platform_device s5pv210_device_spi1 = {
diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c
index 24febae3d4c0..309e388a8a83 100644
--- a/arch/arm/mach-s5pv210/pm.c
+++ b/arch/arm/mach-s5pv210/pm.c
@@ -88,7 +88,7 @@ static struct sleep_save s5pv210_core_save[] = {
         SAVE_ITEM(S3C2410_TCNTO(0)),
 };
 
-void s5pv210_cpu_suspend(void)
+void s5pv210_cpu_suspend(unsigned long arg)
 {
         unsigned long tmp;
 
diff --git a/arch/arm/mach-s5pv210/sleep.S b/arch/arm/mach-s5pv210/sleep.S
index a3d649466fb1..e3452ccd4b08 100644
--- a/arch/arm/mach-s5pv210/sleep.S
+++ b/arch/arm/mach-s5pv210/sleep.S
@@ -32,27 +32,6 @@
 
         .text
 
-        /* s3c_cpu_save
-         *
-         * entry:
-         *      r1 = v:p offset
-        */
-
-ENTRY(s3c_cpu_save)
-
-        stmfd   sp!, { r3 - r12, lr }
-        ldr     r3, =resume_with_mmu
-        bl      cpu_suspend
-
-        ldr     r0, =pm_cpu_sleep
-        ldr     r0, [ r0 ]
-        mov     pc, r0
-
-resume_with_mmu:
-        ldmfd   sp!, { r3 - r12, pc }
-
-        .ltorg
-
         /* sleep magic, to allow the bootloader to check for an valid
          * image to resume to. Must be the first word before the
          * s3c_cpu_resume entry.
diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c
index c4661aab22fb..bf85b8b259d5 100644
--- a/arch/arm/mach-sa1100/pm.c
+++ b/arch/arm/mach-sa1100/pm.c
@@ -29,10 +29,11 @@
 
 #include <mach/hardware.h>
 #include <asm/memory.h>
+#include <asm/suspend.h>
 #include <asm/system.h>
 #include <asm/mach/time.h>
 
-extern void sa1100_cpu_suspend(long);
+extern int sa1100_finish_suspend(unsigned long);
 
 #define SAVE(x)         sleep_save[SLEEP_SAVE_##x] = x
 #define RESTORE(x)      x = sleep_save[SLEEP_SAVE_##x]
@@ -75,9 +76,7 @@ static int sa11x0_pm_enter(suspend_state_t state)
         PSPR = virt_to_phys(cpu_resume);
 
         /* go zzz */
-        sa1100_cpu_suspend(PLAT_PHYS_OFFSET - PAGE_OFFSET);
-
-        cpu_init();
+        cpu_suspend(0, sa1100_finish_suspend);
 
         /*
          * Ensure not to come back here if it wasn't intended
diff --git a/arch/arm/mach-sa1100/sleep.S b/arch/arm/mach-sa1100/sleep.S
index 04f2a618d4ef..e8223315b442 100644
--- a/arch/arm/mach-sa1100/sleep.S
+++ b/arch/arm/mach-sa1100/sleep.S
@@ -22,18 +22,13 @@
 
                 .text
 /*
- * sa1100_cpu_suspend()
+ * sa1100_finish_suspend()
  *
  * Causes sa11x0 to enter sleep state
  *
  */
 
-ENTRY(sa1100_cpu_suspend)
-        stmfd   sp!, {r4 - r12, lr}             @ save registers on stack
-        mov     r1, r0
-        ldr     r3, =sa1100_cpu_resume          @ return function
-        bl      cpu_suspend
-
+ENTRY(sa1100_finish_suspend)
         @ disable clock switching
         mcr     p15, 0, r1, c15, c2, 2
 
@@ -139,13 +134,3 @@ sa1110_sdram_controller_fix:
         str     r13, [r12]
 
 20:     b       20b                     @ loop waiting for sleep
-
-/*
- * cpu_sa1100_resume()
- *
- * entry point from bootloader into kernel during resume
- */
-        .align 5
-sa1100_cpu_resume:
-        mcr     p15, 0, r1, c15, c1, 2          @ enable clock switching
-        ldmfd   sp!, {r4 - r12, pc}             @ return to caller
diff --git a/arch/arm/mach-shark/include/mach/entry-macro.S b/arch/arm/mach-shark/include/mach/entry-macro.S
index e2853c0a3333..0bb6cc626eb7 100644
--- a/arch/arm/mach-shark/include/mach/entry-macro.S
+++ b/arch/arm/mach-shark/include/mach/entry-macro.S
@@ -11,17 +11,17 @@
                 .endm
 
                 .macro  get_irqnr_preamble, base, tmp
+                mov     \base, #0xe0000000
                 .endm
 
                 .macro  arch_ret_to_user, tmp1, tmp2
                 .endm
 
                 .macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-                mov     r4, #0xe0000000
 
                 mov     \irqstat, #0x0C
-                strb    \irqstat, [r4, #0x20]           @outb(0x0C, 0x20) /* Poll command */
-                ldrb    \irqnr, [r4, #0x20]             @irq = inb(0x20) & 7
+                strb    \irqstat, [\base, #0x20]        @outb(0x0C, 0x20) /* Poll command */
+                ldrb    \irqnr, [\base, #0x20]          @irq = inb(0x20) & 7
                 and     \irqstat, \irqnr, #0x80
                 teq     \irqstat, #0
                 beq     43f
@@ -29,8 +29,8 @@
                 teq     \irqnr, #2
                 bne     44f
 43:             mov     \irqstat, #0x0C
-                strb    \irqstat, [r4, #0xa0]           @outb(0x0C, 0xA0) /* Poll command */
-                ldrb    \irqnr, [r4, #0xa0]             @irq = (inb(0xA0) & 7) + 8
+                strb    \irqstat, [\base, #0xa0]        @outb(0x0C, 0xA0) /* Poll command */
+                ldrb    \irqnr, [\base, #0xa0]          @irq = (inb(0xA0) & 7) + 8
                 and     \irqstat, \irqnr, #0x80
                 teq     \irqstat, #0
                 beq     44f
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index 1e2aba23e0d6..ce5c2513c6ce 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -381,7 +381,7 @@ void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state)
         gpio_set_value(GPIO_PORT114, state);
 }
 
-static struct sh_mobile_sdhi_info sh_sdhi1_platdata = {
+static struct sh_mobile_sdhi_info sh_sdhi1_info = {
         .tmio_flags     = TMIO_MMC_WRPROTECT_DISABLE,
         .tmio_caps      = MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ,
         .tmio_ocr_mask  = MMC_VDD_32_33 | MMC_VDD_33_34,
@@ -413,7 +413,7 @@ static struct platform_device sdhi1_device = {
         .name           = "sh_mobile_sdhi",
         .id             = 1,
         .dev            = {
-                .platform_data  = &sh_sdhi1_platdata,
+                .platform_data  = &sh_sdhi1_info,
         },
         .num_resources  = ARRAY_SIZE(sdhi1_resources),
         .resource       = sdhi1_resources,
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index f6b687f61c28..803bc6edfca4 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -913,7 +913,7 @@ static struct i2c_board_info imx074_info = {
         I2C_BOARD_INFO("imx074", 0x1a),
 };
 
-struct soc_camera_link imx074_link = {
+static struct soc_camera_link imx074_link = {
         .bus_id         = 0,
         .board_info     = &imx074_info,
         .i2c_adapter_id = 0,
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 7e1d37584321..3802f2afabef 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -1287,9 +1287,9 @@ static struct platform_device *mackerel_devices[] __initdata = {
         &nor_flash_device,
         &smc911x_device,
         &lcdc_device,
-        &usbhs0_device,
         &usb1_host_device,
         &usbhs1_device,
+        &usbhs0_device,
         &leds_device,
         &fsi_device,
         &fsi_ak4643_device,
diff --git a/arch/arm/mach-shmobile/include/mach/sdhi-sh7372.h b/arch/arm/mach-shmobile/include/mach/sdhi-sh7372.h
new file mode 100644
index 000000000000..4a81b01f1e8f
--- /dev/null
+++ b/arch/arm/mach-shmobile/include/mach/sdhi-sh7372.h
@@ -0,0 +1,21 @@
+#ifndef SDHI_SH7372_H
+#define SDHI_SH7372_H
+
+#define SDGENCNTA       0xfe40009c
+
+/* The countdown of SDGENCNTA is controlled by
+ * ZB3D2CLK which runs at 149.5MHz.
+ * That is 149.5ticks/us. Approximate this as 150ticks/us.
+ */
+static void udelay(int us)
+{
+        __raw_writel(us * 150, SDGENCNTA);
+        while(__raw_readl(SDGENCNTA)) ;
+}
+
+static void msleep(int ms)
+{
+        udelay(ms * 1000);
+}
+
+#endif
diff --git a/arch/arm/mach-shmobile/include/mach/sdhi.h b/arch/arm/mach-shmobile/include/mach/sdhi.h
new file mode 100644
index 000000000000..0ec9e69f2c3b
--- /dev/null
+++ b/arch/arm/mach-shmobile/include/mach/sdhi.h
@@ -0,0 +1,16 @@
+#ifndef SDHI_H
+#define SDHI_H
+
+/**************************************************
+ *
+ *              CPU specific settings
+ *
+ **************************************************/
+
+#ifdef CONFIG_ARCH_SH7372
+#include "mach/sdhi-sh7372.h"
+#else
+#error "unsupported CPU."
+#endif
+
+#endif /* SDHI_H */
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index f3888feb1c68..66f980625a33 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -64,10 +64,5 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-        int i;
-
-        for (i = 0; i < max_cpus; i++)
-                set_cpu_present(i, true);
-
         shmobile_smp_prepare_cpus();
 }
diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c
index b8ae3c978dee..1a594dce8fbc 100644
--- a/arch/arm/mach-tegra/platsmp.c
+++ b/arch/arm/mach-tegra/platsmp.c
@@ -129,14 +129,6 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-        int i;
-
-        /*
-         * Initialise the present map, which describes the set of CPUs
-         * actually populated at the present time.
-         */
-        for (i = 0; i < max_cpus; i++)
-                set_cpu_present(i, true);
 
         scu_enable(scu_base);
 }
diff --git a/arch/arm/mach-ux500/board-mop500-pins.c b/arch/arm/mach-ux500/board-mop500-pins.c
index fd4cf1ca5efd..70cdbd60596a 100644
--- a/arch/arm/mach-ux500/board-mop500-pins.c
+++ b/arch/arm/mach-ux500/board-mop500-pins.c
@@ -110,10 +110,18 @@ static pin_cfg_t mop500_pins_common[] = {
         GPIO168_KP_O0,
 
         /* UART */
-        GPIO0_U0_CTSn   | PIN_INPUT_PULLUP,
-        GPIO1_U0_RTSn   | PIN_OUTPUT_HIGH,
-        GPIO2_U0_RXD    | PIN_INPUT_PULLUP,
-        GPIO3_U0_TXD    | PIN_OUTPUT_HIGH,
+        /* uart-0 pins gpio configuration should be
+         * kept intact to prevent glitch in tx line
+         * when tty dev is opened. Later these pins
+         * are configured to uart mop500_pins_uart0
+         *
+         * It will be replaced with uart configuration
+         * once the issue is solved.
+         */
+        GPIO0_GPIO      | PIN_INPUT_PULLUP,
+        GPIO1_GPIO      | PIN_OUTPUT_HIGH,
+        GPIO2_GPIO      | PIN_INPUT_PULLUP,
+        GPIO3_GPIO      | PIN_OUTPUT_HIGH,
 
         GPIO29_U2_RXD   | PIN_INPUT_PULLUP,
         GPIO30_U2_TXD   | PIN_OUTPUT_HIGH,
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index bb26f40493e6..2a08c07dec6d 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -27,18 +27,21 @@
 #include <linux/leds-lp5521.h>
 #include <linux/input.h>
 #include <linux/gpio_keys.h>
+#include <linux/delay.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
 #include <plat/i2c.h>
 #include <plat/ste_dma40.h>
+#include <plat/pincfg.h>
 
 #include <mach/hardware.h>
 #include <mach/setup.h>
 #include <mach/devices.h>
 #include <mach/irqs.h>
 
+#include "pins-db8500.h"
 #include "ste-dma40-db8500.h"
 #include "devices-db8500.h"
 #include "board-mop500.h"
@@ -393,12 +396,63 @@ static struct stedma40_chan_cfg uart2_dma_cfg_tx = {
 };
 #endif
 
+
+static pin_cfg_t mop500_pins_uart0[] = {
+        GPIO0_U0_CTSn   | PIN_INPUT_PULLUP,
+        GPIO1_U0_RTSn   | PIN_OUTPUT_HIGH,
+        GPIO2_U0_RXD    | PIN_INPUT_PULLUP,
+        GPIO3_U0_TXD    | PIN_OUTPUT_HIGH,
+};
+
+#define PRCC_K_SOFTRST_SET      0x18
+#define PRCC_K_SOFTRST_CLEAR    0x1C
+static void ux500_uart0_reset(void)
+{
+        void __iomem *prcc_rst_set, *prcc_rst_clr;
+
+        prcc_rst_set = (void __iomem *)IO_ADDRESS(U8500_CLKRST1_BASE +
+                        PRCC_K_SOFTRST_SET);
+        prcc_rst_clr = (void __iomem *)IO_ADDRESS(U8500_CLKRST1_BASE +
+                        PRCC_K_SOFTRST_CLEAR);
+
+        /* Activate soft reset PRCC_K_SOFTRST_CLEAR */
+        writel((readl(prcc_rst_clr) | 0x1), prcc_rst_clr);
+        udelay(1);
+
+        /* Release soft reset PRCC_K_SOFTRST_SET */
+        writel((readl(prcc_rst_set) | 0x1), prcc_rst_set);
+        udelay(1);
+}
+
+static void ux500_uart0_init(void)
+{
+        int ret;
+
+        ret = nmk_config_pins(mop500_pins_uart0,
+                        ARRAY_SIZE(mop500_pins_uart0));
+        if (ret < 0)
+                pr_err("pl011: uart pins_enable failed\n");
+}
+
+static void ux500_uart0_exit(void)
+{
+        int ret;
+
+        ret = nmk_config_pins_sleep(mop500_pins_uart0,
+                        ARRAY_SIZE(mop500_pins_uart0));
+        if (ret < 0)
+                pr_err("pl011: uart pins_disable failed\n");
+}
+
 static struct amba_pl011_data uart0_plat = {
 #ifdef CONFIG_STE_DMA40
         .dma_filter = stedma40_filter,
         .dma_rx_param = &uart0_dma_cfg_rx,
         .dma_tx_param = &uart0_dma_cfg_tx,
 #endif
+        .init = ux500_uart0_init,
+        .exit = ux500_uart0_exit,
+        .reset = ux500_uart0_reset,
 };
 
 static struct amba_pl011_data uart1_plat = {
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index 0c527fe2cebb..a33df5f4c27a 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -172,14 +172,6 @@ void __init smp_init_cpus(void)
 
 void __init platform_smp_prepare_cpus(unsigned int max_cpus)
 {
-        int i;
-
-        /*
-         * Initialise the present map, which describes the set of CPUs
-         * actually populated at the present time.
-         */
-        for (i = 0; i < max_cpus; i++)
-                set_cpu_present(i, true);
 
         scu_enable(scu_base_addr());
         wakeup_secondary();
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 765a71ff7f3b..bfd32f52c2db 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -229,10 +229,6 @@ static void ct_ca9x4_init_cpu_map(void)
 
 static void ct_ca9x4_smp_enable(unsigned int max_cpus)
 {
-        int i;
-        for (i = 0; i < max_cpus; i++)
-                set_cpu_present(i, true);
-
         scu_enable(MMIO_P2V(A9_MPCORE_SCU));
 }
 #endif
diff --git a/arch/arm/mach-vt8500/irq.c b/arch/arm/mach-vt8500/irq.c
index 245140c0df10..642de0408f25 100644
--- a/arch/arm/mach-vt8500/irq.c
+++ b/arch/arm/mach-vt8500/irq.c
@@ -39,9 +39,10 @@
 static void __iomem *ic_regbase;
 static void __iomem *sic_regbase;
 
-static void vt8500_irq_mask(unsigned int irq)
+static void vt8500_irq_mask(struct irq_data *d)
 {
         void __iomem *base = ic_regbase;
+        unsigned irq = d->irq;
         u8 edge;
 
         if (irq >= 64) {
@@ -64,9 +65,10 @@ static void vt8500_irq_mask(unsigned int irq)
         }
 }
 
-static void vt8500_irq_unmask(unsigned int irq)
+static void vt8500_irq_unmask(struct irq_data *d)
 {
         void __iomem *base = ic_regbase;
+        unsigned irq = d->irq;
         u8 dctr;
 
         if (irq >= 64) {
@@ -78,10 +80,11 @@ static void vt8500_irq_unmask(unsigned int irq)
         writeb(dctr, base + VT8500_IC_DCTR + irq);
 }
 
-static int vt8500_irq_set_type(unsigned int irq, unsigned int flow_type)
+static int vt8500_irq_set_type(struct irq_data *d, unsigned int flow_type)
 {
         void __iomem *base = ic_regbase;
-        unsigned int orig_irq = irq;
+        unsigned irq = d->irq;
+        unsigned orig_irq = irq;
         u8 dctr;
 
         if (irq >= 64) {
@@ -114,11 +117,11 @@ static int vt8500_irq_set_type(unsigned int irq, unsigned int flow_type)
 }
 
 static struct irq_chip vt8500_irq_chip = {
-        .name      = "vt8500",
-        .ack       = vt8500_irq_mask,
-        .mask      = vt8500_irq_mask,
-        .unmask    = vt8500_irq_unmask,
-        .set_type  = vt8500_irq_set_type,
+        .name = "vt8500",
+        .irq_ack = vt8500_irq_mask,
+        .irq_mask = vt8500_irq_mask,
+        .irq_unmask = vt8500_irq_unmask,
+        .irq_set_type = vt8500_irq_set_type,
 };
 
 void __init vt8500_init_irq(void)
diff --git a/arch/arm/mm/abort-ev4.S b/arch/arm/mm/abort-ev4.S
index 4f18f9e87bae..54473cd4aba9 100644
--- a/arch/arm/mm/abort-ev4.S
+++ b/arch/arm/mm/abort-ev4.S
@@ -3,14 +3,11 @@
 /*
  * Function: v4_early_abort
  *
- * Params  : r2 = address of aborted instruction
- *         : r3 = saved SPSR
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
- * Returns : r0 = address of abort
- *         : r1 = FSR, bit 11 = write
- *         : r2-r8 = corrupted
- *         : r9 = preserved
- *         : sp = pointer to registers
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  * Note: we read user space.  This means we might cause a data
@@ -21,10 +18,8 @@
 ENTRY(v4_early_abort)
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
-        ldr     r3, [r2]                        @ read aborted ARM instruction
+        ldr     r3, [r4]                        @ read aborted ARM instruction
         bic     r1, r1, #1 << 11 | 1 << 10      @ clear bits 11 and 10 of FSR
         tst     r3, #1 << 20                    @ L = 1 -> write?
         orreq   r1, r1, #1 << 11                @ yes.
-        mov     pc, lr
-
-
+        b       do_DataAbort
diff --git a/arch/arm/mm/abort-ev4t.S b/arch/arm/mm/abort-ev4t.S
index b6282548f922..9da704e7b86e 100644
--- a/arch/arm/mm/abort-ev4t.S
+++ b/arch/arm/mm/abort-ev4t.S
@@ -4,14 +4,11 @@
 /*
  * Function: v4t_early_abort
  *
- * Params  : r2 = address of aborted instruction
- *         : r3 = saved SPSR
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
- * Returns : r0 = address of abort
- *         : r1 = FSR, bit 11 = write
- *         : r2-r8 = corrupted
- *         : r9 = preserved
- *         : sp = pointer to registers
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  * Note: we read user space.  This means we might cause a data
@@ -22,9 +19,9 @@
 ENTRY(v4t_early_abort)
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
-        do_thumb_abort
-        ldreq   r3, [r2]                        @ read aborted ARM instruction
+        do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
+        ldreq   r3, [r4]                        @ read aborted ARM instruction
         bic     r1, r1, #1 << 11 | 1 << 10      @ clear bits 11 and 10 of FSR
         tst     r3, #1 << 20                    @ check write
         orreq   r1, r1, #1 << 11
-        mov     pc, lr
+        b       do_DataAbort
diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S
index 02251b526c0d..a0908d4653a3 100644
--- a/arch/arm/mm/abort-ev5t.S
+++ b/arch/arm/mm/abort-ev5t.S
@@ -4,14 +4,11 @@
 /*
  * Function: v5t_early_abort
  *
- * Params  : r2 = address of aborted instruction
- *         : r3 = saved SPSR
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
- * Returns : r0 = address of abort
- *         : r1 = FSR, bit 11 = write
- *         : r2-r8 = corrupted
- *         : r9 = preserved
- *         : sp = pointer to registers
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  * Note: we read user space.  This means we might cause a data
@@ -22,10 +19,10 @@
 ENTRY(v5t_early_abort)
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
-        do_thumb_abort
-        ldreq   r3, [r2]                        @ read aborted ARM instruction
+        do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
+        ldreq   r3, [r4]                        @ read aborted ARM instruction
         bic     r1, r1, #1 << 11                @ clear bits 11 of FSR
-        do_ldrd_abort
+        do_ldrd_abort tmp=ip, insn=r3
         tst     r3, #1 << 20                    @ check write
         orreq   r1, r1, #1 << 11
-        mov     pc, lr
+        b       do_DataAbort
diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S
index bce68d601c8b..4006b7a61264 100644
--- a/arch/arm/mm/abort-ev5tj.S
+++ b/arch/arm/mm/abort-ev5tj.S
@@ -4,14 +4,11 @@
 /*
  * Function: v5tj_early_abort
  *
- * Params  : r2 = address of aborted instruction
- *         : r3 = saved SPSR
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
- * Returns : r0 = address of abort
- *         : r1 = FSR, bit 11 = write
- *         : r2-r8 = corrupted
- *         : r9 = preserved
- *         : sp = pointer to registers
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  * Note: we read user space.  This means we might cause a data
@@ -23,13 +20,11 @@ ENTRY(v5tj_early_abort)
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
         bic     r1, r1, #1 << 11 | 1 << 10      @ clear bits 11 and 10 of FSR
-        tst     r3, #PSR_J_BIT                  @ Java?
-        movne   pc, lr
-        do_thumb_abort
-        ldreq   r3, [r2]                        @ read aborted ARM instruction
-        do_ldrd_abort
+        tst     r5, #PSR_J_BIT                  @ Java?
+        bne     do_DataAbort
+        do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
+        ldreq   r3, [r4]                        @ read aborted ARM instruction
+        do_ldrd_abort tmp=ip, insn=r3
         tst     r3, #1 << 20                    @ L = 0 -> write
         orreq   r1, r1, #1 << 11                @ yes.
-        mov     pc, lr
-
-
+        b       do_DataAbort
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 1478aa522144..ff1f7cc11f87 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -4,14 +4,11 @@
 /*
  * Function: v6_early_abort
  *
- * Params  : r2 = address of aborted instruction
- *         : r3 = saved SPSR
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
- * Returns : r0 = address of abort
- *         : r1 = FSR, bit 11 = write
- *         : r2-r8 = corrupted
- *         : r9 = preserved
- *         : sp = pointer to registers
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  * Note: we read user space.  This means we might cause a data
@@ -33,16 +30,14 @@ ENTRY(v6_early_abort)
  * The test below covers all the write situations, including Java bytecodes
  */
         bic     r1, r1, #1 << 11                @ clear bit 11 of FSR
-        tst     r3, #PSR_J_BIT                  @ Java?
-        movne   pc, lr
-        do_thumb_abort
-        ldreq   r3, [r2]                        @ read aborted ARM instruction
+        tst     r5, #PSR_J_BIT                  @ Java?
+        bne     do_DataAbort
+        do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
+        ldreq   r3, [r4]                        @ read aborted ARM instruction
 #ifdef CONFIG_CPU_ENDIAN_BE8
         reveq   r3, r3
 #endif
-        do_ldrd_abort
+        do_ldrd_abort tmp=ip, insn=r3
         tst     r3, #1 << 20                    @ L = 0 -> write
         orreq   r1, r1, #1 << 11                @ yes.
-        mov     pc, lr
-
-
+        b       do_DataAbort
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index ec88b157d3bb..703375277ba6 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -3,14 +3,11 @@
 /*
  * Function: v7_early_abort
  *
- * Params  : r2 = address of aborted instruction
- *         : r3 = saved SPSR
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
- * Returns : r0 = address of abort
- *         : r1 = FSR, bit 11 = write
- *         : r2-r8 = corrupted
- *         : r9 = preserved
- *         : sp = pointer to registers
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  */
@@ -37,18 +34,18 @@ ENTRY(v7_early_abort)
         ldr     r3, =0x40d                      @ On permission fault
         and     r3, r1, r3
         cmp     r3, #0x0d
-        movne   pc, lr
+        bne     do_DataAbort
 
         mcr     p15, 0, r0, c7, c8, 0           @ Retranslate FAR
         isb
-        mrc     p15, 0, r2, c7, c4, 0           @ Read the PAR
-        and     r3, r2, #0x7b                   @ On translation fault
+        mrc     p15, 0, ip, c7, c4, 0           @ Read the PAR
+        and     r3, ip, #0x7b                   @ On translation fault
         cmp     r3, #0x0b
-        movne   pc, lr
+        bne     do_DataAbort
         bic     r1, r1, #0xf                    @ Fix up FSR FS[5:0]
-        and     r2, r2, #0x7e
-        orr     r1, r1, r2, LSR #1
+        and     ip, ip, #0x7e
+        orr     r1, r1, ip, LSR #1
 #endif
 
-        mov     pc, lr
+        b       do_DataAbort
 ENDPROC(v7_early_abort)
diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S
index 9fb7b0e25ea1..f3982580c273 100644
--- a/arch/arm/mm/abort-lv4t.S
+++ b/arch/arm/mm/abort-lv4t.S
@@ -3,14 +3,11 @@
 /*
  * Function: v4t_late_abort
  *
- * Params  : r2 = address of aborted instruction
- *         : r3 = saved SPSR
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
- * Returns : r0 = address of abort
- *         : r1 = FSR, bit 11 = write
- *         : r2-r8 = corrupted
- *         : r9 = preserved
- *         : sp = pointer to registers
+ * Returns : r4-r5, r10-r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  * Note: we read user space.  This means we might cause a data
@@ -18,7 +15,7 @@
  * picture.  Unfortunately, this does happen.  We live with it.
  */
 ENTRY(v4t_late_abort)
-        tst     r3, #PSR_T_BIT                  @ check for thumb mode
+        tst     r5, #PSR_T_BIT                  @ check for thumb mode
 #ifdef CONFIG_CPU_CP15_MMU
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
@@ -28,7 +25,7 @@ ENTRY(v4t_late_abort)
         mov     r1, #0
 #endif
         bne     .data_thumb_abort
-        ldr     r8, [r2]                        @ read arm instruction
+        ldr     r8, [r4]                        @ read arm instruction
         tst     r8, #1 << 20                    @ L = 1 -> write?
         orreq   r1, r1, #1 << 11                @ yes.
         and     r7, r8, #15 << 24
@@ -47,86 +44,84 @@ ENTRY(v4t_late_abort)
 /* 9 */ b       .data_arm_ldmstm                @ ldm*b rn, <rlist>
 /* a */ b       .data_unknown
 /* b */ b       .data_unknown
-/* c */ mov     pc, lr                          @ ldc   rd, [rn], #m    @ Same as ldr   rd, [rn], #m
-/* d */ mov     pc, lr                          @ ldc   rd, [rn, #m]
+/* c */ b       do_DataAbort                    @ ldc   rd, [rn], #m    @ Same as ldr   rd, [rn], #m
+/* d */ b       do_DataAbort                    @ ldc   rd, [rn, #m]
 /* e */ b       .data_unknown
 /* f */
 .data_unknown:  @ Part of jumptable
-        mov     r0, r2
+        mov     r0, r4
         mov     r1, r8
-        mov     r2, sp
-        bl      baddataabort
-        b       ret_from_exception
+        b       baddataabort
 
 .data_arm_ldmstm:
         tst     r8, #1 << 21                    @ check writeback bit
-        moveq   pc, lr                          @ no writeback -> no fixup
+        beq     do_DataAbort                    @ no writeback -> no fixup
         mov     r7, #0x11
         orr     r7, r7, #0x1100
         and     r6, r8, r7
-        and     r2, r8, r7, lsl #1
-        add     r6, r6, r2, lsr #1
-        and     r2, r8, r7, lsl #2
-        add     r6, r6, r2, lsr #2
-        and     r2, r8, r7, lsl #3
-        add     r6, r6, r2, lsr #3
+        and     r9, r8, r7, lsl #1
+        add     r6, r6, r9, lsr #1
+        and     r9, r8, r7, lsl #2
+        add     r6, r6, r9, lsr #2
+        and     r9, r8, r7, lsl #3
+        add     r6, r6, r9, lsr #3
         add     r6, r6, r6, lsr #8
         add     r6, r6, r6, lsr #4
         and     r6, r6, #15                     @ r6 = no. of registers to transfer.
-        and     r5, r8, #15 << 16               @ Extract 'n' from instruction
-        ldr     r7, [sp, r5, lsr #14]           @ Get register 'Rn'
+        and     r9, r8, #15 << 16               @ Extract 'n' from instruction
+        ldr     r7, [r2, r9, lsr #14]           @ Get register 'Rn'
         tst     r8, #1 << 23                    @ Check U bit
         subne   r7, r7, r6, lsl #2              @ Undo increment
         addeq   r7, r7, r6, lsl #2              @ Undo decrement
-        str     r7, [sp, r5, lsr #14]           @ Put register 'Rn'
-        mov     pc, lr
+        str     r7, [r2, r9, lsr #14]           @ Put register 'Rn'
+        b       do_DataAbort
 
 .data_arm_lateldrhpre:
         tst     r8, #1 << 21                    @ Check writeback bit
-        moveq   pc, lr                          @ No writeback -> no fixup
+        beq     do_DataAbort                    @ No writeback -> no fixup
 .data_arm_lateldrhpost:
-        and     r5, r8, #0x00f                  @ get Rm / low nibble of immediate value
+        and     r9, r8, #0x00f                  @ get Rm / low nibble of immediate value
         tst     r8, #1 << 22                    @ if (immediate offset)
         andne   r6, r8, #0xf00                  @ { immediate high nibble
-        orrne   r6, r5, r6, lsr #4              @   combine nibbles } else
-        ldreq   r6, [sp, r5, lsl #2]            @ { load Rm value }
+        orrne   r6, r9, r6, lsr #4              @   combine nibbles } else
+        ldreq   r6, [r2, r9, lsl #2]            @ { load Rm value }
 .data_arm_apply_r6_and_rn:
-        and     r5, r8, #15 << 16               @ Extract 'n' from instruction
-        ldr     r7, [sp, r5, lsr #14]           @ Get register 'Rn'
+        and     r9, r8, #15 << 16               @ Extract 'n' from instruction
+        ldr     r7, [r2, r9, lsr #14]           @ Get register 'Rn'
         tst     r8, #1 << 23                    @ Check U bit
         subne   r7, r7, r6                      @ Undo incrmenet
         addeq   r7, r7, r6                      @ Undo decrement
-        str     r7, [sp, r5, lsr #14]           @ Put register 'Rn'
-        mov     pc, lr
+        str     r7, [r2, r9, lsr #14]           @ Put register 'Rn'
+        b       do_DataAbort
 
 .data_arm_lateldrpreconst:
         tst     r8, #1 << 21                    @ check writeback bit
-        moveq   pc, lr                          @ no writeback -> no fixup
+        beq     do_DataAbort                    @ no writeback -> no fixup
 .data_arm_lateldrpostconst:
-        movs    r2, r8, lsl #20                 @ Get offset
-        moveq   pc, lr                          @ zero -> no fixup
-        and     r5, r8, #15 << 16               @ Extract 'n' from instruction
-        ldr     r7, [sp, r5, lsr #14]           @ Get register 'Rn'
+        movs    r6, r8, lsl #20                 @ Get offset
+        beq     do_DataAbort                    @ zero -> no fixup
+        and     r9, r8, #15 << 16               @ Extract 'n' from instruction
+        ldr     r7, [r2, r9, lsr #14]           @ Get register 'Rn'
         tst     r8, #1 << 23                    @ Check U bit
-        subne   r7, r7, r2, lsr #20             @ Undo increment
-        addeq   r7, r7, r2, lsr #20             @ Undo decrement
-        str     r7, [sp, r5, lsr #14]           @ Put register 'Rn'
-        mov     pc, lr
+        subne   r7, r7, r6, lsr #20             @ Undo increment
+        addeq   r7, r7, r6, lsr #20             @ Undo decrement
+        str     r7, [r2, r9, lsr #14]           @ Put register 'Rn'
+        b       do_DataAbort
 
 .data_arm_lateldrprereg:
         tst     r8, #1 << 21                    @ check writeback bit
-        moveq   pc, lr                          @ no writeback -> no fixup
+        beq     do_DataAbort                    @ no writeback -> no fixup
 .data_arm_lateldrpostreg:
         and     r7, r8, #15                     @ Extract 'm' from instruction
-        ldr     r6, [sp, r7, lsl #2]            @ Get register 'Rm'
-        mov     r5, r8, lsr #7                  @ get shift count
-        ands    r5, r5, #31
+        ldr     r6, [r2, r7, lsl #2]            @ Get register 'Rm'
+        mov     r9, r8, lsr #7                  @ get shift count
+        ands    r9, r9, #31
         and     r7, r8, #0x70                   @ get shift type
         orreq   r7, r7, #8                      @ shift count = 0
         add     pc, pc, r7
         nop
 
-        mov     r6, r6, lsl r5                  @ 0: LSL #!0
+        mov     r6, r6, lsl r9                  @ 0: LSL #!0
         b       .data_arm_apply_r6_and_rn
         b       .data_arm_apply_r6_and_rn       @ 1: LSL #0
         nop
@@ -134,7 +129,7 @@ ENTRY(v4t_late_abort)
         nop
         b       .data_unknown                   @ 3: MUL?
         nop
-        mov     r6, r6, lsr r5                  @ 4: LSR #!0
+        mov     r6, r6, lsr r9                  @ 4: LSR #!0
         b       .data_arm_apply_r6_and_rn
         mov     r6, r6, lsr #32                 @ 5: LSR #32
         b       .data_arm_apply_r6_and_rn
@@ -142,7 +137,7 @@ ENTRY(v4t_late_abort)
         nop
         b       .data_unknown                   @ 7: MUL?
         nop
-        mov     r6, r6, asr r5                  @ 8: ASR #!0
+        mov     r6, r6, asr r9                  @ 8: ASR #!0
         b       .data_arm_apply_r6_and_rn
         mov     r6, r6, asr #32                 @ 9: ASR #32
         b       .data_arm_apply_r6_and_rn
@@ -150,7 +145,7 @@ ENTRY(v4t_late_abort)
         nop
         b       .data_unknown                   @ B: MUL?
         nop
-        mov     r6, r6, ror r5                  @ C: ROR #!0
+        mov     r6, r6, ror r9                  @ C: ROR #!0
         b       .data_arm_apply_r6_and_rn
         mov     r6, r6, rrx                     @ D: RRX
         b       .data_arm_apply_r6_and_rn
@@ -159,7 +154,7 @@ ENTRY(v4t_late_abort)
         b       .data_unknown                   @ F: MUL?
 
 .data_thumb_abort:
-        ldrh    r8, [r2]                        @ read instruction
+        ldrh    r8, [r4]                        @ read instruction
         tst     r8, #1 << 11                    @ L = 1 -> write?
         orreq   r1, r1, #1 << 8                 @ yes
         and     r7, r8, #15 << 12
@@ -172,10 +167,10 @@ ENTRY(v4t_late_abort)
 /* 3 */ b       .data_unknown
 /* 4 */ b       .data_unknown
 /* 5 */ b       .data_thumb_reg
-/* 6 */ mov     pc, lr
-/* 7 */ mov     pc, lr
-/* 8 */ mov     pc, lr
-/* 9 */ mov     pc, lr
+/* 6 */ b       do_DataAbort
+/* 7 */ b       do_DataAbort
+/* 8 */ b       do_DataAbort
+/* 9 */ b       do_DataAbort
 /* A */ b       .data_unknown
 /* B */ b       .data_thumb_pushpop
 /* C */ b       .data_thumb_ldmstm
@@ -185,41 +180,41 @@ ENTRY(v4t_late_abort)
 
 .data_thumb_reg:
         tst     r8, #1 << 9
-        moveq   pc, lr
+        beq     do_DataAbort
         tst     r8, #1 << 10                    @ If 'S' (signed) bit is set
         movne   r1, #0                          @ it must be a load instr
-        mov     pc, lr
+        b       do_DataAbort
 
 .data_thumb_pushpop:
         tst     r8, #1 << 10
         beq     .data_unknown
         and     r6, r8, #0x55                   @ hweight8(r8) + R bit
-        and     r2, r8, #0xaa
-        add     r6, r6, r2, lsr #1
-        and     r2, r6, #0xcc
+        and     r9, r8, #0xaa
+        add     r6, r6, r9, lsr #1
+        and     r9, r6, #0xcc
         and     r6, r6, #0x33
-        add     r6, r6, r2, lsr #2
+        add     r6, r6, r9, lsr #2
         movs    r7, r8, lsr #9                  @ C = r8 bit 8 (R bit)
         adc     r6, r6, r6, lsr #4              @ high + low nibble + R bit
         and     r6, r6, #15                     @ number of regs to transfer
-        ldr     r7, [sp, #13 << 2]
+        ldr     r7, [r2, #13 << 2]
         tst     r8, #1 << 11
         addeq   r7, r7, r6, lsl #2              @ increment SP if PUSH
         subne   r7, r7, r6, lsl #2              @ decrement SP if POP
-        str     r7, [sp, #13 << 2]
-        mov     pc, lr
+        str     r7, [r2, #13 << 2]
+        b       do_DataAbort
 
 .data_thumb_ldmstm:
         and     r6, r8, #0x55                   @ hweight8(r8)
-        and     r2, r8, #0xaa
-        add     r6, r6, r2, lsr #1
-        and     r2, r6, #0xcc
+        and     r9, r8, #0xaa
+        add     r6, r6, r9, lsr #1
+        and     r9, r6, #0xcc
         and     r6, r6, #0x33
-        add     r6, r6, r2, lsr #2
+        add     r6, r6, r9, lsr #2
         add     r6, r6, r6, lsr #4
-        and     r5, r8, #7 << 8
-        ldr     r7, [sp, r5, lsr #6]
+        and     r9, r8, #7 << 8
+        ldr     r7, [r2, r9, lsr #6]
         and     r6, r6, #15                     @ number of regs to transfer
         sub     r7, r7, r6, lsl #2              @ always decrement
-        str     r7, [sp, r5, lsr #6]
-        mov     pc, lr
+        str     r7, [r2, r9, lsr #6]
+        b       do_DataAbort
diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S
index d7cb1bfa51a4..52162d59407a 100644
--- a/arch/arm/mm/abort-macro.S
+++ b/arch/arm/mm/abort-macro.S
@@ -9,34 +9,32 @@
  *
  */
 
-        .macro  do_thumb_abort
-        tst     r3, #PSR_T_BIT
+        .macro  do_thumb_abort, fsr, pc, psr, tmp
+        tst     \psr, #PSR_T_BIT
         beq     not_thumb
-        ldrh    r3, [r2]                        @ Read aborted Thumb instruction
-        and     r3, r3, # 0xfe00                @ Mask opcode field
-        cmp     r3, # 0x5600                    @ Is it ldrsb?
-        orreq   r3, r3, #1 << 11                @ Set L-bit if yes
-        tst     r3, #1 << 11                    @ L = 0 -> write
-        orreq   r1, r1, #1 << 11                @ yes.
-        mov     pc, lr
+        ldrh    \tmp, [\pc]                     @ Read aborted Thumb instruction
+        and     \tmp, \tmp, # 0xfe00            @ Mask opcode field
+        cmp     \tmp, # 0x5600                  @ Is it ldrsb?
+        orreq   \tmp, \tmp, #1 << 11            @ Set L-bit if yes
+        tst     \tmp, #1 << 11                  @ L = 0 -> write
+        orreq   \psr, \psr, #1 << 11            @ yes.
+        b       do_DataAbort
 not_thumb:
         .endm
 
 /*
- * We check for the following insturction encoding for LDRD.
+ * We check for the following instruction encoding for LDRD.
  *
- * [27:25] == 0
+ * [27:25] == 000
  *   [7:4] == 1101
  *    [20] == 0
  */
-        .macro  do_ldrd_abort
-        tst     r3, #0x0e000000                 @ [27:25] == 0
+        .macro  do_ldrd_abort, tmp, insn
+        tst     \insn, #0x0e100000              @ [27:25,20] == 0
         bne     not_ldrd
-        and     r2, r3, #0x000000f0             @ [7:4] == 1101
-        cmp     r2, #0x000000d0
-        bne     not_ldrd
-        tst     r3, #1 << 20                    @ [20] == 0
-        moveq   pc, lr
+        and     \tmp, \insn, #0x000000f0        @ [7:4] == 1101
+        cmp     \tmp, #0x000000d0
+        beq     do_DataAbort
 not_ldrd:
         .endm
 
diff --git a/arch/arm/mm/abort-nommu.S b/arch/arm/mm/abort-nommu.S
index 625e580945b5..119cb479c2ab 100644
--- a/arch/arm/mm/abort-nommu.S
+++ b/arch/arm/mm/abort-nommu.S
@@ -3,11 +3,11 @@
 /*
  * Function: nommu_early_abort
  *
- * Params  : r2 = address of aborted instruction
- *         : r3 = saved SPSR
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
- * Returns : r0 = 0 (abort address)
- *         : r1 = 0 (FSR)
+ * Returns : r4 - r11, r13 preserved
  *
  * Note: There is no FSR/FAR on !CPU_CP15_MMU cores.
  *       Just fill zero into the registers.
@@ -16,5 +16,5 @@
 ENTRY(nommu_early_abort)
         mov     r0, #0                          @ clear r0, r1 (no FSR/FAR)
         mov     r1, #0
-        mov     pc, lr
+        b       do_DataAbort
 ENDPROC(nommu_early_abort)
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 724ba3bce72c..be7c638b648b 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -727,6 +727,9 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
         int isize = 4;
         int thumb2_32b = 0;
 
+        if (interrupts_enabled(regs))
+                local_irq_enable();
+
         instrptr = instruction_pointer(regs);
 
         fs = get_fs();
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index ef59099a5463..44c086710d2b 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -120,17 +120,22 @@ static void l2x0_cache_sync(void)
         spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_flush_all(void)
+static void __l2x0_flush_all(void)
 {
-        unsigned long flags;
-
-        /* clean all ways */
-        spin_lock_irqsave(&l2x0_lock, flags);
         debug_writel(0x03);
         writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY);
         cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask);
         cache_sync();
         debug_writel(0x00);
+}
+
+static void l2x0_flush_all(void)
+{
+        unsigned long flags;
+
+        /* clean all ways */
+        spin_lock_irqsave(&l2x0_lock, flags);
+        __l2x0_flush_all();
         spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
@@ -266,7 +271,9 @@ static void l2x0_disable(void)
         unsigned long flags;
 
         spin_lock_irqsave(&l2x0_lock, flags);
-        writel(0, l2x0_base + L2X0_CTRL);
+        __l2x0_flush_all();
+        writel_relaxed(0, l2x0_base + L2X0_CTRL);
+        dsb();
         spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index bdba6c65c901..63cca0097130 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -41,7 +41,6 @@ static void v6_copy_user_highpage_nonaliasing(struct page *to,
         kfrom = kmap_atomic(from, KM_USER0);
         kto = kmap_atomic(to, KM_USER1);
         copy_page(kto, kfrom);
-        __cpuc_flush_dcache_area(kto, PAGE_SIZE);
         kunmap_atomic(kto, KM_USER1);
         kunmap_atomic(kfrom, KM_USER0);
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 82a093cee09a..0a0a1e7c20d2 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -25,9 +25,11 @@
 #include <asm/tlbflush.h>
 #include <asm/sizes.h>
 
+#include "mm.h"
+
 static u64 get_coherent_dma_mask(struct device *dev)
 {
-        u64 mask = ISA_DMA_THRESHOLD;
+        u64 mask = (u64)arm_dma_limit;
 
         if (dev) {
                 mask = dev->coherent_dma_mask;
@@ -41,10 +43,10 @@ static u64 get_coherent_dma_mask(struct device *dev)
                         return 0;
                 }
 
-                if ((~mask) & ISA_DMA_THRESHOLD) {
+                if ((~mask) & (u64)arm_dma_limit) {
                         dev_warn(dev, "coherent DMA mask %#llx is smaller "
                                  "than system GFP_DMA mask %#llx\n",
-                                 mask, (unsigned long long)ISA_DMA_THRESHOLD);
+                                 mask, (u64)arm_dma_limit);
                         return 0;
                 }
         }
@@ -657,6 +659,33 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 }
 EXPORT_SYMBOL(dma_sync_sg_for_device);
 
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly.  For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask
+ * to this function.
+ */
+int dma_supported(struct device *dev, u64 mask)
+{
+        if (mask < (u64)arm_dma_limit)
+                return 0;
+        return 1;
+}
+EXPORT_SYMBOL(dma_supported);
+
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+        if (!dev->dma_mask || !dma_supported(dev, dma_mask))
+                return -EIO;
+
+#ifndef CONFIG_DMABOUNCE
+        *dev->dma_mask = dma_mask;
+#endif
+
+        return 0;
+}
+EXPORT_SYMBOL(dma_set_mask);
+
 #define PREALLOC_DMA_DEBUG_ENTRIES      4096
 
 static int __init dma_debug_do_init(void)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index bc0e1d88fd3b..55657c222d7c 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -94,7 +94,7 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 
                 pud = pud_offset(pgd, addr);
                 if (PTRS_PER_PUD != 1)
-                        printk(", *pud=%08lx", pud_val(*pud));
+                        printk(", *pud=%08llx", (long long)pud_val(*pud));
 
                 if (pud_none(*pud))
                         break;
@@ -285,6 +285,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
         tsk = current;
         mm  = tsk->mm;
 
+        /* Enable interrupts if they were enabled in the parent context. */
+        if (interrupts_enabled(regs))
+                local_irq_enable();
+
         /*
          * If we're in an interrupt or have no user
          * context, we must not take the fault..
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index c19571c40a21..e5ab4362322f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -212,6 +212,14 @@ static void __init arm_bootmem_init(unsigned long start_pfn,
 }
 
 #ifdef CONFIG_ZONE_DMA
+/*
+ * The DMA mask corresponding to the maximum bus address allocatable
+ * using GFP_DMA.  The default here places no restriction on DMA
+ * allocations.  This must be the smallest DMA mask in the system,
+ * so a successful GFP_DMA allocation will always satisfy this.
+ */
+u32 arm_dma_limit;
+
 static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
         unsigned long dma_size)
 {
@@ -278,6 +286,8 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
          */
         arm_adjust_dma_zone(zone_size, zhole_size,
                 ARM_DMA_ZONE_SIZE >> PAGE_SHIFT);
+
+        arm_dma_limit = PHYS_OFFSET + ARM_DMA_ZONE_SIZE - 1;
 #endif
 
         free_area_init_node(0, zone_size, min, zhole_size);
@@ -422,6 +432,17 @@ static inline int free_area(unsigned long pfn, unsigned long end, char *s)
         return pages;
 }
 
+/*
+ * Poison init memory with an undefined instruction (ARM) or a branch to an
+ * undefined instruction (Thumb).
+ */
+static inline void poison_init_mem(void *s, size_t count)
+{
+        u32 *p = (u32 *)s;
+        while ((count = count - 4))
+                *p++ = 0xe7fddef0;
+}
+
 static inline void
 free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -639,8 +660,8 @@ void __init mem_init(void)
                         "    pkmap   : 0x%08lx - 0x%08lx   (%4ld MB)\n"
 #endif
                         "    modules : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-                        "      .init : 0x%p" " - 0x%p" "   (%4d kB)\n"
                         "      .text : 0x%p" " - 0x%p" "   (%4d kB)\n"
+                        "      .init : 0x%p" " - 0x%p" "   (%4d kB)\n"
                         "      .data : 0x%p" " - 0x%p" "   (%4d kB)\n"
                         "       .bss : 0x%p" " - 0x%p" "   (%4d kB)\n",
 
@@ -662,8 +683,8 @@ void __init mem_init(void)
 #endif
                         MLM(MODULES_VADDR, MODULES_END),
 
-                        MLK_ROUNDUP(__init_begin, __init_end),
                         MLK_ROUNDUP(_text, _etext),
+                        MLK_ROUNDUP(__init_begin, __init_end),
                         MLK_ROUNDUP(_sdata, _edata),
                         MLK_ROUNDUP(__bss_start, __bss_stop));
 
@@ -704,11 +725,13 @@ void free_initmem(void)
 #ifdef CONFIG_HAVE_TCM
         extern char __tcm_start, __tcm_end;
 
+        poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start);
         totalram_pages += free_area(__phys_to_pfn(__pa(&__tcm_start)),
                                     __phys_to_pfn(__pa(&__tcm_end)),
                                     "TCM link");
 #endif
 
+        poison_init_mem(__init_begin, __init_end - __init_begin);
         if (!machine_is_integrator() && !machine_is_cintegrator())
                 totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),
                                             __phys_to_pfn(__pa(__init_end)),
@@ -721,10 +744,12 @@ static int keep_initrd;
 
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        if (!keep_initrd)
+        if (!keep_initrd) {
+                poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
                 totalram_pages += free_area(__phys_to_pfn(__pa(start)),
                                             __phys_to_pfn(__pa(end)),
                                             "initrd");
+        }
 }
 
 static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 5b3d7d543659..010566799c80 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -23,5 +23,11 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 
 #endif
 
+#ifdef CONFIG_ZONE_DMA
+extern u32 arm_dma_limit;
+#else
+#define arm_dma_limit ((u32)~0)
+#endif
+
 void __init bootmem_init(void);
 void arm_mm_memblock_reserve(void);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 9d9e736c2b4f..594d677b92c8 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -759,7 +759,7 @@ early_param("vmalloc", early_vmalloc);
 
 static phys_addr_t lowmem_limit __initdata = 0;
 
-static void __init sanity_check_meminfo(void)
+void __init sanity_check_meminfo(void)
 {
         int i, j, highmem = 0;
 
@@ -1032,8 +1032,9 @@ void __init paging_init(struct machine_desc *mdesc)
 {
         void *zero_page;
 
+        memblock_set_current_limit(lowmem_limit);
+
         build_mem_type_table();
-        sanity_check_meminfo();
         prepare_page_table();
         map_lowmem();
         devicemaps_init(mdesc);
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 687d02319a41..941a98c9e8aa 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -27,6 +27,10 @@ void __init arm_mm_memblock_reserve(void)
         memblock_reserve(CONFIG_VECTORS_BASE, PAGE_SIZE);
 }
 
+void __init sanity_check_meminfo(void)
+{
+}
+
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
diff --git a/arch/arm/mm/pabort-legacy.S b/arch/arm/mm/pabort-legacy.S
index 87970eba88ea..8bbff025269a 100644
--- a/arch/arm/mm/pabort-legacy.S
+++ b/arch/arm/mm/pabort-legacy.S
@@ -4,16 +4,18 @@
 /*
  * Function: legacy_pabort
  *
- * Params  : r0 = address of aborted instruction
+ * Params  : r2 = pt_regs
+ *         : r4 = address of aborted instruction
+ *         : r5 = psr for parent context
  *
- * Returns : r0 = address of abort
- *         : r1 = Simulated IFSR with section translation fault status
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current prefetch abort.
  */
 
         .align  5
 ENTRY(legacy_pabort)
+        mov     r0, r4
         mov     r1, #5
-        mov     pc, lr
+        b       do_PrefetchAbort
 ENDPROC(legacy_pabort)
diff --git a/arch/arm/mm/pabort-v6.S b/arch/arm/mm/pabort-v6.S
index 06e3d1ef2115..9627646ce783 100644
--- a/arch/arm/mm/pabort-v6.S
+++ b/arch/arm/mm/pabort-v6.S
@@ -4,16 +4,18 @@
 /*
  * Function: v6_pabort
  *
- * Params  : r0 = address of aborted instruction
+ * Params  : r2 = pt_regs
+ *         : r4 = address of aborted instruction
+ *         : r5 = psr for parent context
  *
- * Returns : r0 = address of abort
- *         : r1 = IFSR
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current prefetch abort.
  */
 
         .align  5
 ENTRY(v6_pabort)
+        mov     r0, r4
         mrc     p15, 0, r1, c5, c0, 1           @ get IFSR
-        mov     pc, lr
+        b       do_PrefetchAbort
 ENDPROC(v6_pabort)
diff --git a/arch/arm/mm/pabort-v7.S b/arch/arm/mm/pabort-v7.S
index a8b3b300a18d..875761f44f3b 100644
--- a/arch/arm/mm/pabort-v7.S
+++ b/arch/arm/mm/pabort-v7.S
@@ -2,12 +2,13 @@
 #include <asm/assembler.h>
 
 /*
- * Function: v6_pabort
+ * Function: v7_pabort
  *
- * Params  : r0 = address of aborted instruction
+ * Params  : r2 = pt_regs
+ *         : r4 = address of aborted instruction
+ *         : r5 = psr for parent context
  *
- * Returns : r0 = address of abort
- *         : r1 = IFSR
+ * Returns : r4 - r11, r13 preserved
  *
  * Purpose : obtain information about current prefetch abort.
  */
@@ -16,5 +17,5 @@
 ENTRY(v7_pabort)
         mrc     p15, 0, r0, c6, c0, 2           @ get IFAR
         mrc     p15, 0, r1, c5, c0, 1           @ get IFSR
-        mov     pc, lr
+        b       do_PrefetchAbort
 ENDPROC(v7_pabort)
diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S
index 5f79dc4ce3fb..50e3543d03bf 100644
--- a/arch/arm/mm/proc-arm6_7.S
+++ b/arch/arm/mm/proc-arm6_7.S
@@ -29,19 +29,19 @@ ENTRY(cpu_arm7_dcache_clean_area)
 /*
  * Function: arm6_7_data_abort ()
  *
- * Params  : r2 = address of aborted instruction
- *         : sp = pointer to registers
+ * Params  : r2 = pt_regs
+ *         : r4 = aborted context pc
+ *         : r5 = aborted context psr
  *
  * Purpose : obtain information about current aborted instruction
  *
- * Returns : r0 = address of abort
- *         : r1 = FSR
+ * Returns : r4-r5, r10-r11, r13 preserved
  */
 
 ENTRY(cpu_arm7_data_abort)
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
-        ldr     r8, [r2]                        @ read arm instruction
+        ldr     r8, [r4]                        @ read arm instruction
         tst     r8, #1 << 20                    @ L = 0 -> write?
         orreq   r1, r1, #1 << 11                @ yes.
         and     r7, r8, #15 << 24
@@ -49,7 +49,7 @@ ENTRY(cpu_arm7_data_abort)
         nop
 
 /* 0 */ b       .data_unknown
-/* 1 */ mov     pc, lr                          @ swp
+/* 1 */ b       do_DataAbort                    @ swp
 /* 2 */ b       .data_unknown
 /* 3 */ b       .data_unknown
 /* 4 */ b       .data_arm_lateldrpostconst      @ ldr   rd, [rn], #m
@@ -60,87 +60,85 @@ ENTRY(cpu_arm7_data_abort)
 /* 9 */ b       .data_arm_ldmstm                @ ldm*b rn, <rlist>
 /* a */ b       .data_unknown
 /* b */ b       .data_unknown
-/* c */ mov     pc, lr                          @ ldc   rd, [rn], #m    @ Same as ldr   rd, [rn], #m
-/* d */ mov     pc, lr                          @ ldc   rd, [rn, #m]
+/* c */ b       do_DataAbort                    @ ldc   rd, [rn], #m    @ Same as ldr   rd, [rn], #m
+/* d */ b       do_DataAbort                    @ ldc   rd, [rn, #m]
 /* e */ b       .data_unknown
 /* f */
 .data_unknown:  @ Part of jumptable
-        mov     r0, r2
+        mov     r0, r4
         mov     r1, r8
-        mov     r2, sp
-        bl      baddataabort
-        b       ret_from_exception
+        b       baddataabort
 
 ENTRY(cpu_arm6_data_abort)
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
-        ldr     r8, [r2]                        @ read arm instruction
+        ldr     r8, [r4]                        @ read arm instruction
         tst     r8, #1 << 20                    @ L = 0 -> write?
         orreq   r1, r1, #1 << 11                @ yes.
         and     r7, r8, #14 << 24
         teq     r7, #8 << 24                    @ was it ldm/stm
-        movne   pc, lr
+        bne     do_DataAbort
 
 .data_arm_ldmstm:
         tst     r8, #1 << 21                    @ check writeback bit
-        moveq   pc, lr                          @ no writeback -> no fixup
+        beq     do_DataAbort                    @ no writeback -> no fixup
         mov     r7, #0x11
         orr     r7, r7, #0x1100
         and     r6, r8, r7
-        and     r2, r8, r7, lsl #1
-        add     r6, r6, r2, lsr #1
-        and     r2, r8, r7, lsl #2
-        add     r6, r6, r2, lsr #2
-        and     r2, r8, r7, lsl #3
-        add     r6, r6, r2, lsr #3
+        and     r9, r8, r7, lsl #1
+        add     r6, r6, r9, lsr #1
+        and     r9, r8, r7, lsl #2
+        add     r6, r6, r9, lsr #2
+        and     r9, r8, r7, lsl #3
+        add     r6, r6, r9, lsr #3
         add     r6, r6, r6, lsr #8
         add     r6, r6, r6, lsr #4
         and     r6, r6, #15                     @ r6 = no. of registers to transfer.
-        and     r5, r8, #15 << 16               @ Extract 'n' from instruction
-        ldr     r7, [sp, r5, lsr #14]           @ Get register 'Rn'
+        and     r9, r8, #15 << 16               @ Extract 'n' from instruction
+        ldr     r7, [r2, r9, lsr #14]           @ Get register 'Rn'
         tst     r8, #1 << 23                    @ Check U bit
         subne   r7, r7, r6, lsl #2              @ Undo increment
         addeq   r7, r7, r6, lsl #2              @ Undo decrement
-        str     r7, [sp, r5, lsr #14]           @ Put register 'Rn'
-        mov     pc, lr
+        str     r7, [r2, r9, lsr #14]           @ Put register 'Rn'
+        b       do_DataAbort
 
 .data_arm_apply_r6_and_rn:
-        and     r5, r8, #15 << 16               @ Extract 'n' from instruction
-        ldr     r7, [sp, r5, lsr #14]           @ Get register 'Rn'
+        and     r9, r8, #15 << 16               @ Extract 'n' from instruction
+        ldr     r7, [r2, r9, lsr #14]           @ Get register 'Rn'
         tst     r8, #1 << 23                    @ Check U bit
         subne   r7, r7, r6                      @ Undo incrmenet
         addeq   r7, r7, r6                      @ Undo decrement
-        str     r7, [sp, r5, lsr #14]           @ Put register 'Rn'
-        mov     pc, lr
+        str     r7, [r2, r9, lsr #14]           @ Put register 'Rn'
+        b       do_DataAbort
 
 .data_arm_lateldrpreconst:
         tst     r8, #1 << 21                    @ check writeback bit
-        moveq   pc, lr                          @ no writeback -> no fixup
+        beq     do_DataAbort                    @ no writeback -> no fixup
 .data_arm_lateldrpostconst:
-        movs    r2, r8, lsl #20                 @ Get offset
-        moveq   pc, lr                          @ zero -> no fixup
-        and     r5, r8, #15 << 16               @ Extract 'n' from instruction
-        ldr     r7, [sp, r5, lsr #14]           @ Get register 'Rn'
+        movs    r6, r8, lsl #20                 @ Get offset
+        beq     do_DataAbort                    @ zero -> no fixup
+        and     r9, r8, #15 << 16               @ Extract 'n' from instruction
+        ldr     r7, [r2, r9, lsr #14]           @ Get register 'Rn'
         tst     r8, #1 << 23                    @ Check U bit
-        subne   r7, r7, r2, lsr #20             @ Undo increment
-        addeq   r7, r7, r2, lsr #20             @ Undo decrement
-        str     r7, [sp, r5, lsr #14]           @ Put register 'Rn'
-        mov     pc, lr
+        subne   r7, r7, r6, lsr #20             @ Undo increment
+        addeq   r7, r7, r6, lsr #20             @ Undo decrement
+        str     r7, [r2, r9, lsr #14]           @ Put register 'Rn'
+        b       do_DataAbort
 
 .data_arm_lateldrprereg:
         tst     r8, #1 << 21                    @ check writeback bit
-        moveq   pc, lr                          @ no writeback -> no fixup
+        beq     do_DataAbort                    @ no writeback -> no fixup
 .data_arm_lateldrpostreg:
         and     r7, r8, #15                     @ Extract 'm' from instruction
-        ldr     r6, [sp, r7, lsl #2]            @ Get register 'Rm'
-        mov     r5, r8, lsr #7                  @ get shift count
-        ands    r5, r5, #31
+        ldr     r6, [r2, r7, lsl #2]            @ Get register 'Rm'
+        mov     r9, r8, lsr #7                  @ get shift count
+        ands    r9, r9, #31
         and     r7, r8, #0x70                   @ get shift type
         orreq   r7, r7, #8                      @ shift count = 0
         add     pc, pc, r7
         nop
 
-        mov     r6, r6, lsl r5                  @ 0: LSL #!0
+        mov     r6, r6, lsl r9                  @ 0: LSL #!0
         b       .data_arm_apply_r6_and_rn
         b       .data_arm_apply_r6_and_rn       @ 1: LSL #0
         nop
@@ -148,7 +146,7 @@ ENTRY(cpu_arm6_data_abort)
         nop
         b       .data_unknown                   @ 3: MUL?
         nop
-        mov     r6, r6, lsr r5                  @ 4: LSR #!0
+        mov     r6, r6, lsr r9                  @ 4: LSR #!0
         b       .data_arm_apply_r6_and_rn
         mov     r6, r6, lsr #32                 @ 5: LSR #32
         b       .data_arm_apply_r6_and_rn
@@ -156,7 +154,7 @@ ENTRY(cpu_arm6_data_abort)
         nop
         b       .data_unknown                   @ 7: MUL?
         nop
-        mov     r6, r6, asr r5                  @ 8: ASR #!0
+        mov     r6, r6, asr r9                  @ 8: ASR #!0
         b       .data_arm_apply_r6_and_rn
         mov     r6, r6, asr #32                 @ 9: ASR #32
         b       .data_arm_apply_r6_and_rn
@@ -164,7 +162,7 @@ ENTRY(cpu_arm6_data_abort)
         nop
         b       .data_unknown                   @ B: MUL?
         nop
-        mov     r6, r6, ror r5                  @ C: ROR #!0
+        mov     r6, r6, ror r9                  @ C: ROR #!0
         b       .data_arm_apply_r6_and_rn
         mov     r6, r6, rrx                     @ D: RRX
         b       .data_arm_apply_r6_and_rn
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 184a9c997e36..e9c47271732d 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -34,7 +34,7 @@
  */
 #define DCACHELINESIZE  32
 
-        __INIT
+        .section .text
 
 /*
  * cpu_sa1100_proc_init()
@@ -45,8 +45,6 @@ ENTRY(cpu_sa1100_proc_init)
         mcr     p15, 0, r0, c9, c0, 5           @ Allow read-buffer operations from userland
         mov     pc, lr
 
-        .section .text
-
 /*
  * cpu_sa1100_proc_fin()
  *
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3c3867850a30..089c0b5e454f 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -210,19 +210,21 @@ cpu_v7_name:
 
 /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
 .globl  cpu_v7_suspend_size
-.equ    cpu_v7_suspend_size, 4 * 8
+.equ    cpu_v7_suspend_size, 4 * 9
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_v7_do_suspend)
         stmfd   sp!, {r4 - r11, lr}
         mrc     p15, 0, r4, c13, c0, 0  @ FCSE/PID
         mrc     p15, 0, r5, c13, c0, 1  @ Context ID
+        mrc     p15, 0, r6, c13, c0, 3  @ User r/o thread ID
+        stmia   r0!, {r4 - r6}
         mrc     p15, 0, r6, c3, c0, 0   @ Domain ID
         mrc     p15, 0, r7, c2, c0, 0   @ TTB 0
         mrc     p15, 0, r8, c2, c0, 1   @ TTB 1
         mrc     p15, 0, r9, c1, c0, 0   @ Control register
         mrc     p15, 0, r10, c1, c0, 1  @ Auxiliary control register
         mrc     p15, 0, r11, c1, c0, 2  @ Co-processor access control
-        stmia   r0, {r4 - r11}
+        stmia   r0, {r6 - r11}
         ldmfd   sp!, {r4 - r11, pc}
 ENDPROC(cpu_v7_do_suspend)
 
@@ -230,9 +232,11 @@ ENTRY(cpu_v7_do_resume)
         mov     ip, #0
         mcr     p15, 0, ip, c8, c7, 0   @ invalidate TLBs
         mcr     p15, 0, ip, c7, c5, 0   @ invalidate I cache
-        ldmia   r0, {r4 - r11}
+        ldmia   r0!, {r4 - r6}
         mcr     p15, 0, r4, c13, c0, 0  @ FCSE/PID
         mcr     p15, 0, r5, c13, c0, 1  @ Context ID
+        mcr     p15, 0, r6, c13, c0, 3  @ User r/o thread ID
+        ldmia   r0, {r6 - r11}
         mcr     p15, 0, r6, c3, c0, 0   @ Domain ID
         mcr     p15, 0, r7, c2, c0, 0   @ TTB 0
         mcr     p15, 0, r8, c2, c0, 1   @ TTB 1
@@ -418,9 +422,9 @@ ENTRY(v7_processor_functions)
         .word   cpu_v7_dcache_clean_area
         .word   cpu_v7_switch_mm
         .word   cpu_v7_set_pte_ext
-        .word   0
-        .word   0
-        .word   0
+        .word   cpu_v7_suspend_size
+        .word   cpu_v7_do_suspend
+        .word   cpu_v7_do_resume
         .size   v7_processor_functions, . - v7_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/plat-iop/cp6.c b/arch/arm/plat-iop/cp6.c
index 9612a87e2a88..bab73e2c79db 100644
--- a/arch/arm/plat-iop/cp6.c
+++ b/arch/arm/plat-iop/cp6.c
@@ -18,6 +18,7 @@
  */
 #include <linux/init.h>
 #include <asm/traps.h>
+#include <asm/ptrace.h>
 
 static int cp6_trap(struct pt_regs *regs, unsigned int instr)
 {
diff --git a/arch/arm/plat-mxc/include/mach/entry-macro.S b/arch/arm/plat-mxc/include/mach/entry-macro.S
index 2e49e71b1b98..066d464d322d 100644
--- a/arch/arm/plat-mxc/include/mach/entry-macro.S
+++ b/arch/arm/plat-mxc/include/mach/entry-macro.S
@@ -78,7 +78,3 @@
         movs \irqnr, \irqnr
 #endif
         .endm
-
-        @ irq priority table (not used)
-        .macro  irq_prio_table
-        .endm
diff --git a/arch/arm/plat-omap/omap_device.c b/arch/arm/plat-omap/omap_device.c
index a37b8eb65b76..49fc0df0c21f 100644
--- a/arch/arm/plat-omap/omap_device.c
+++ b/arch/arm/plat-omap/omap_device.c
@@ -84,6 +84,7 @@
 #include <linux/io.h>
 #include <linux/clk.h>
 #include <linux/clkdev.h>
+#include <linux/pm_runtime.h>
 
 #include <plat/omap_device.h>
 #include <plat/omap_hwmod.h>
@@ -539,20 +540,34 @@ int omap_early_device_register(struct omap_device *od)
 static int _od_runtime_suspend(struct device *dev)
 {
         struct platform_device *pdev = to_platform_device(dev);
+        int ret;
+
+        ret = pm_generic_runtime_suspend(dev);
+
+        if (!ret)
+                omap_device_idle(pdev);
+
+        return ret;
+}
 
-        return omap_device_idle(pdev);
+static int _od_runtime_idle(struct device *dev)
+{
+        return pm_generic_runtime_idle(dev);
 }
 
 static int _od_runtime_resume(struct device *dev)
 {
         struct platform_device *pdev = to_platform_device(dev);
 
-        return omap_device_enable(pdev);
+        omap_device_enable(pdev);
+
+        return pm_generic_runtime_resume(dev);
 }
 
 static struct dev_power_domain omap_device_power_domain = {
         .ops = {
                 .runtime_suspend = _od_runtime_suspend,
+                .runtime_idle = _od_runtime_idle,
                 .runtime_resume = _od_runtime_resume,
                 USE_PLATFORM_PM_SLEEP_OPS
         }
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index 6af3d0b1f8d0..363c91e44efb 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -394,20 +394,15 @@ void omap3_sram_restore_context(void)
 }
 #endif /* CONFIG_PM */
 
-static int __init omap34xx_sram_init(void)
-{
-        _omap3_sram_configure_core_dpll =
-                omap_sram_push(omap3_sram_configure_core_dpll,
-                               omap3_sram_configure_core_dpll_sz);
-        omap_push_sram_idle();
-        return 0;
-}
-#else
+#endif /* CONFIG_ARCH_OMAP3 */
+
 static inline int omap34xx_sram_init(void)
 {
+#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM)
+        omap3_sram_restore_context();
+#endif
         return 0;
 }
-#endif
 
 int __init omap_sram_init(void)
 {
diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c
index 5b4fffab1eb4..41ab97ebe4cf 100644
--- a/arch/arm/plat-orion/gpio.c
+++ b/arch/arm/plat-orion/gpio.c
@@ -432,7 +432,7 @@ void __init orion_gpio_init(int gpio_base, int ngpio,
         ct->regs.mask = ochip->mask_offset + GPIO_EDGE_MASK_OFF;
         ct->regs.ack = GPIO_EDGE_CAUSE_OFF;
         ct->type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING;
-        ct->chip.irq_ack = irq_gc_ack;
+        ct->chip.irq_ack = irq_gc_ack_clr_bit;
         ct->chip.irq_mask = irq_gc_mask_clr_bit;
         ct->chip.irq_unmask = irq_gc_mask_set_bit;
         ct->chip.irq_set_type = gpio_irq_set_type;
diff --git a/arch/arm/plat-pxa/gpio.c b/arch/arm/plat-pxa/gpio.c
index 48ebb9479b61..a11dc3670505 100644
--- a/arch/arm/plat-pxa/gpio.c
+++ b/arch/arm/plat-pxa/gpio.c
@@ -50,7 +50,7 @@ static inline void __iomem *gpio_chip_base(struct gpio_chip *c)
         return container_of(c, struct pxa_gpio_chip, chip)->regbase;
 }
 
-static inline struct pxa_gpio_chip *gpio_to_chip(unsigned gpio)
+static inline struct pxa_gpio_chip *gpio_to_pxachip(unsigned gpio)
 {
         return &pxa_gpio_chips[gpio_to_bank(gpio)];
 }
@@ -161,7 +161,7 @@ static int pxa_gpio_irq_type(struct irq_data *d, unsigned int type)
         int gpio = irq_to_gpio(d->irq);
         unsigned long gpdr, mask = GPIO_bit(gpio);
 
-        c = gpio_to_chip(gpio);
+        c = gpio_to_pxachip(gpio);
 
         if (type == IRQ_TYPE_PROBE) {
                 /* Don't mess with enabled GPIOs using preconfigured edges or
@@ -230,7 +230,7 @@ static void pxa_gpio_demux_handler(unsigned int irq, struct irq_desc *desc)
 static void pxa_ack_muxed_gpio(struct irq_data *d)
 {
         int gpio = irq_to_gpio(d->irq);
-        struct pxa_gpio_chip *c = gpio_to_chip(gpio);
+        struct pxa_gpio_chip *c = gpio_to_pxachip(gpio);
 
         __raw_writel(GPIO_bit(gpio), c->regbase + GEDR_OFFSET);
 }
@@ -238,7 +238,7 @@ static void pxa_ack_muxed_gpio(struct irq_data *d)
 static void pxa_mask_muxed_gpio(struct irq_data *d)
 {
         int gpio = irq_to_gpio(d->irq);
-        struct pxa_gpio_chip *c = gpio_to_chip(gpio);
+        struct pxa_gpio_chip *c = gpio_to_pxachip(gpio);
         uint32_t grer, gfer;
 
         c->irq_mask &= ~GPIO_bit(gpio);
@@ -252,7 +252,7 @@ static void pxa_mask_muxed_gpio(struct irq_data *d)
 static void pxa_unmask_muxed_gpio(struct irq_data *d)
 {
         int gpio = irq_to_gpio(d->irq);
-        struct pxa_gpio_chip *c = gpio_to_chip(gpio);
+        struct pxa_gpio_chip *c = gpio_to_pxachip(gpio);
 
         c->irq_mask |= GPIO_bit(gpio);
         update_edge_detect(c);
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index 2abf9660bc6c..539bd0e3defd 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -712,7 +712,7 @@ static struct s3c2410_dma_chan *s3c2410_dma_map_channel(int channel);
  * get control of an dma channel
 */
 
-int s3c2410_dma_request(unsigned int channel,
+int s3c2410_dma_request(enum dma_ch channel,
                         struct s3c2410_dma_client *client,
                         void *dev)
 {
@@ -783,7 +783,7 @@ EXPORT_SYMBOL(s3c2410_dma_request);
  * allowed to go through.
 */
 
-int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *client)
+int s3c2410_dma_free(enum dma_ch channel, struct s3c2410_dma_client *client)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
         unsigned long flags;
@@ -974,7 +974,7 @@ static int s3c2410_dma_started(struct s3c2410_dma_chan *chan)
 }
 
 int
-s3c2410_dma_ctrl(unsigned int channel, enum s3c2410_chan_op op)
+s3c2410_dma_ctrl(enum dma_ch channel, enum s3c2410_chan_op op)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
 
@@ -1021,23 +1021,19 @@ EXPORT_SYMBOL(s3c2410_dma_ctrl);
  * xfersize:     size of unit in bytes (1,2,4)
 */
 
-int s3c2410_dma_config(unsigned int channel,
+int s3c2410_dma_config(enum dma_ch channel,
                        int xferunit)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
         unsigned int dcon;
 
-        pr_debug("%s: chan=%d, xfer_unit=%d, dcon=%08x\n",
-                 __func__, channel, xferunit, dcon);
+        pr_debug("%s: chan=%d, xfer_unit=%d\n", __func__, channel, xferunit);
 
         if (chan == NULL)
                 return -EINVAL;
 
-        pr_debug("%s: Initial dcon is %08x\n", __func__, dcon);
-
         dcon = chan->dcon & dma_sel.dcon_mask;
-
-        pr_debug("%s: New dcon is %08x\n", __func__, dcon);
+        pr_debug("%s: dcon is %08x\n", __func__, dcon);
 
         switch (chan->req_ch) {
         case DMACH_I2S_IN:
@@ -1104,7 +1100,7 @@ EXPORT_SYMBOL(s3c2410_dma_config);
  * devaddr:   physical address of the source
 */
 
-int s3c2410_dma_devconfig(unsigned int channel,
+int s3c2410_dma_devconfig(enum dma_ch channel,
                           enum s3c2410_dmasrc source,
                           unsigned long devaddr)
 {
@@ -1177,7 +1173,7 @@ EXPORT_SYMBOL(s3c2410_dma_devconfig);
  * returns the current transfer points for the dma source and destination
 */
 
-int s3c2410_dma_getposition(unsigned int channel, dma_addr_t *src, dma_addr_t *dst)
+int s3c2410_dma_getposition(enum dma_ch channel, dma_addr_t *src, dma_addr_t *dst)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
 
@@ -1235,7 +1231,7 @@ static void s3c2410_dma_resume_chan(struct s3c2410_dma_chan *cp)
         /* restore channel's hardware configuration */
 
         if (!cp->in_use)
-                return 0;
+                return;
 
         printk(KERN_INFO "dma%d: restoring configuration\n", cp->number);
 
@@ -1246,8 +1242,6 @@ static void s3c2410_dma_resume_chan(struct s3c2410_dma_chan *cp)
 
         if (cp->map != NULL)
                 dma_sel.select(cp, cp->map);
-
-        return 0;
 }
 
 static void s3c2410_dma_resume(void)
diff --git a/arch/arm/plat-s3c24xx/sleep.S b/arch/arm/plat-s3c24xx/sleep.S
index fd7032f84ae7..c56612569b40 100644
--- a/arch/arm/plat-s3c24xx/sleep.S
+++ b/arch/arm/plat-s3c24xx/sleep.S
@@ -41,31 +41,6 @@
 
         .text
 
-        /* s3c_cpu_save
-         *
-         * entry:
-         *      r1 = v:p offset
-        */
-
-ENTRY(s3c_cpu_save)
-        stmfd   sp!, { r4 - r12, lr }
-        ldr     r3, =resume_with_mmu
-        bl      cpu_suspend
-
-        @@ jump to final code to send system to sleep
-        ldr     r0, =pm_cpu_sleep
-        @@ldr   pc, [ r0 ]
-        ldr     r0, [ r0 ]
-        mov     pc, r0
-        
-        @@ return to the caller, after having the MMU
-        @@ turned on, this restores the last bits from the
-        @@ stack
-resume_with_mmu:
-        ldmfd   sp!, { r4 - r12, pc }
-
-        .ltorg
-
         /* sleep magic, to allow the bootloader to check for an valid
          * image to resume to. Must be the first word before the
          * s3c_cpu_resume entry.
diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c
index 135abda31c9a..327ab9f662e8 100644
--- a/arch/arm/plat-s5p/irq-gpioint.c
+++ b/arch/arm/plat-s5p/irq-gpioint.c
@@ -152,7 +152,7 @@ static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip)
         if (!gc)
                 return -ENOMEM;
         ct = gc->chip_types;
-        ct->chip.irq_ack = irq_gc_ack;
+        ct->chip.irq_ack = irq_gc_ack_set_bit;
         ct->chip.irq_mask = irq_gc_mask_set_bit;
         ct->chip.irq_unmask = irq_gc_mask_clr_bit;
         ct->chip.irq_set_type = s5p_gpioint_set_type,
diff --git a/arch/arm/plat-s5p/s5p-time.c b/arch/arm/plat-s5p/s5p-time.c
index 899a8cc011ff..612934c48b0d 100644
--- a/arch/arm/plat-s5p/s5p-time.c
+++ b/arch/arm/plat-s5p/s5p-time.c
@@ -370,11 +370,11 @@ static void __init s5p_clocksource_init(void)
 
         clock_rate = clk_get_rate(tin_source);
 
-        init_sched_clock(&cd, s5p_update_sched_clock, 32, clock_rate);
-
         s5p_time_setup(timer_source.source_id, TCNT_MAX);
         s5p_time_start(timer_source.source_id, PERIODIC);
 
+        init_sched_clock(&cd, s5p_update_sched_clock, 32, clock_rate);
+
         if (clocksource_register_hz(&time_clocksource, clock_rate))
                 panic("%s: can't register clocksource\n", time_clocksource.name);
 }
diff --git a/arch/arm/plat-samsung/dma.c b/arch/arm/plat-samsung/dma.c
index cb459dd95459..6143aa147688 100644
--- a/arch/arm/plat-samsung/dma.c
+++ b/arch/arm/plat-samsung/dma.c
@@ -41,7 +41,7 @@ struct s3c2410_dma_chan *s3c_dma_lookup_channel(unsigned int channel)
  * irq?
 */
 
-int s3c2410_dma_set_opfn(unsigned int channel, s3c2410_dma_opfn_t rtn)
+int s3c2410_dma_set_opfn(enum dma_ch channel, s3c2410_dma_opfn_t rtn)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
 
@@ -56,7 +56,7 @@ int s3c2410_dma_set_opfn(unsigned int channel, s3c2410_dma_opfn_t rtn)
 }
 EXPORT_SYMBOL(s3c2410_dma_set_opfn);
 
-int s3c2410_dma_set_buffdone_fn(unsigned int channel, s3c2410_dma_cbfn_t rtn)
+int s3c2410_dma_set_buffdone_fn(enum dma_ch channel, s3c2410_dma_cbfn_t rtn)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
 
@@ -71,7 +71,7 @@ int s3c2410_dma_set_buffdone_fn(unsigned int channel, s3c2410_dma_cbfn_t rtn)
 }
 EXPORT_SYMBOL(s3c2410_dma_set_buffdone_fn);
 
-int s3c2410_dma_setflags(unsigned int channel, unsigned int flags)
+int s3c2410_dma_setflags(enum dma_ch channel, unsigned int flags)
 {
         struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
 
diff --git a/arch/arm/plat-samsung/include/plat/devs.h b/arch/arm/plat-samsung/include/plat/devs.h
index 4af108ff4112..e3b31c26ac3e 100644
--- a/arch/arm/plat-samsung/include/plat/devs.h
+++ b/arch/arm/plat-samsung/include/plat/devs.h
@@ -12,6 +12,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
 */
+
+#ifndef __PLAT_DEVS_H
+#define __PLAT_DEVS_H __FILE__
+
 #include <linux/platform_device.h>
 
 struct s3c24xx_uart_resources {
@@ -159,3 +163,5 @@ extern struct platform_device s3c_device_ac97;
  */
 extern void *s3c_set_platdata(void *pd, size_t pdsize,
                               struct platform_device *pdev);
+
+#endif /* __PLAT_DEVS_H */
diff --git a/arch/arm/plat-samsung/include/plat/dma.h b/arch/arm/plat-samsung/include/plat/dma.h
index 2e8f8c6560d7..8c273b7a6f56 100644
--- a/arch/arm/plat-samsung/include/plat/dma.h
+++ b/arch/arm/plat-samsung/include/plat/dma.h
@@ -42,6 +42,7 @@ struct s3c2410_dma_client {
 };
 
 struct s3c2410_dma_chan;
+enum dma_ch;
 
 /* s3c2410_dma_cbfn_t
  *
@@ -62,7 +63,7 @@ typedef int  (*s3c2410_dma_opfn_t)(struct s3c2410_dma_chan *,
  * request a dma channel exclusivley
 */
 
-extern int s3c2410_dma_request(unsigned int channel,
+extern int s3c2410_dma_request(enum dma_ch channel,
                                struct s3c2410_dma_client *, void *dev);
 
 
@@ -71,14 +72,14 @@ extern int s3c2410_dma_request(unsigned int channel,
  * change the state of the dma channel
 */
 
-extern int s3c2410_dma_ctrl(unsigned int channel, enum s3c2410_chan_op op);
+extern int s3c2410_dma_ctrl(enum dma_ch channel, enum s3c2410_chan_op op);
 
 /* s3c2410_dma_setflags
  *
  * set the channel's flags to a given state
 */
 
-extern int s3c2410_dma_setflags(unsigned int channel,
+extern int s3c2410_dma_setflags(enum dma_ch channel,
                                 unsigned int flags);
 
 /* s3c2410_dma_free
@@ -86,7 +87,7 @@ extern int s3c2410_dma_setflags(unsigned int channel,
  * free the dma channel (will also abort any outstanding operations)
 */
 
-extern int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *);
+extern int s3c2410_dma_free(enum dma_ch channel, struct s3c2410_dma_client *);
 
 /* s3c2410_dma_enqueue
  *
@@ -95,7 +96,7 @@ extern int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *);
  * drained before the buffer is given to the DMA system.
 */
 
-extern int s3c2410_dma_enqueue(unsigned int channel, void *id,
+extern int s3c2410_dma_enqueue(enum dma_ch channel, void *id,
                                dma_addr_t data, int size);
 
 /* s3c2410_dma_config
@@ -103,14 +104,14 @@ extern int s3c2410_dma_enqueue(unsigned int channel, void *id,
  * configure the dma channel
 */
 
-extern int s3c2410_dma_config(unsigned int channel, int xferunit);
+extern int s3c2410_dma_config(enum dma_ch channel, int xferunit);
 
 /* s3c2410_dma_devconfig
  *
  * configure the device we're talking to
 */
 
-extern int s3c2410_dma_devconfig(unsigned int channel,
+extern int s3c2410_dma_devconfig(enum dma_ch channel,
                 enum s3c2410_dmasrc source, unsigned long devaddr);
 
 /* s3c2410_dma_getposition
@@ -118,10 +119,10 @@ extern int s3c2410_dma_devconfig(unsigned int channel,
  * get the position that the dma transfer is currently at
 */
 
-extern int s3c2410_dma_getposition(unsigned int channel,
+extern int s3c2410_dma_getposition(enum dma_ch channel,
                                    dma_addr_t *src, dma_addr_t *dest);
 
-extern int s3c2410_dma_set_opfn(unsigned int, s3c2410_dma_opfn_t rtn);
-extern int s3c2410_dma_set_buffdone_fn(unsigned int, s3c2410_dma_cbfn_t rtn);
+extern int s3c2410_dma_set_opfn(enum dma_ch, s3c2410_dma_opfn_t rtn);
+extern int s3c2410_dma_set_buffdone_fn(enum dma_ch, s3c2410_dma_cbfn_t rtn);
 
 
diff --git a/arch/arm/plat-samsung/include/plat/pm.h b/arch/arm/plat-samsung/include/plat/pm.h
index 7fb6f6be8c81..f6749916d194 100644
--- a/arch/arm/plat-samsung/include/plat/pm.h
+++ b/arch/arm/plat-samsung/include/plat/pm.h
@@ -42,7 +42,7 @@ extern unsigned long s3c_irqwake_eintallow;
 /* per-cpu sleep functions */
 
 extern void (*pm_cpu_prep)(void);
-extern void (*pm_cpu_sleep)(void);
+extern int (*pm_cpu_sleep)(unsigned long);
 
 /* Flags for PM Control */
 
@@ -52,10 +52,9 @@ extern unsigned char pm_uart_udivslot;  /* true to save UART UDIVSLOT */
 
 /* from sleep.S */
 
-extern int  s3c_cpu_save(unsigned long *saveblk, long);
 extern void s3c_cpu_resume(void);
 
-extern void s3c2410_cpu_suspend(void);
+extern int s3c2410_cpu_suspend(unsigned long);
 
 /* sleep save info */
 
diff --git a/arch/arm/plat-samsung/include/plat/regs-serial.h b/arch/arm/plat-samsung/include/plat/regs-serial.h
index c151c5f94a87..116edfe120b9 100644
--- a/arch/arm/plat-samsung/include/plat/regs-serial.h
+++ b/arch/arm/plat-samsung/include/plat/regs-serial.h
@@ -224,6 +224,8 @@
 #define S5PV210_UFSTAT_RXMASK   (255<<0)
 #define S5PV210_UFSTAT_RXSHIFT  (0)
 
+#define NO_NEED_CHECK_CLKSRC    1
+
 #ifndef __ASSEMBLY__
 
 /* struct s3c24xx_uart_clksrc
diff --git a/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h b/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
index 0ffe34a21554..4c16fa3621bb 100644
--- a/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
+++ b/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
@@ -39,6 +39,7 @@ struct s3c64xx_spi_csinfo {
  * @fifo_lvl_mask: All tx fifo_lvl fields start at offset-6
  * @rx_lvl_offset: Depends on tx fifo_lvl field and bus number
  * @high_speed: If the controller supports HIGH_SPEED_EN bit
+ * @tx_st_done: Depends on tx fifo_lvl field
  */
 struct s3c64xx_spi_info {
         int src_clk_nr;
@@ -53,6 +54,7 @@ struct s3c64xx_spi_info {
         int fifo_lvl_mask;
         int rx_lvl_offset;
         int high_speed;
+        int tx_st_done;
 };
 
 /**
diff --git a/arch/arm/plat-samsung/irq-uart.c b/arch/arm/plat-samsung/irq-uart.c
index 32582c0958e3..657405c481d0 100644
--- a/arch/arm/plat-samsung/irq-uart.c
+++ b/arch/arm/plat-samsung/irq-uart.c
@@ -54,8 +54,15 @@ static void __init s3c_init_uart_irq(struct s3c_uart_irq *uirq)
 
         gc = irq_alloc_generic_chip("s3c-uart", 1, uirq->base_irq, reg_base,
                                     handle_level_irq);
+
+        if (!gc) {
+                pr_err("%s: irq_alloc_generic_chip for IRQ %u failed\n",
+                       __func__, uirq->base_irq);
+                return;
+        }
+
         ct = gc->chip_types;
-        ct->chip.irq_ack = irq_gc_ack;
+        ct->chip.irq_ack = irq_gc_ack_set_bit;
         ct->chip.irq_mask = irq_gc_mask_set_bit;
         ct->chip.irq_unmask = irq_gc_mask_clr_bit;
         ct->regs.ack = S3C64XX_UINTP;
diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c
index a607546ddbd0..f714d060370d 100644
--- a/arch/arm/plat-samsung/irq-vic-timer.c
+++ b/arch/arm/plat-samsung/irq-vic-timer.c
@@ -54,6 +54,13 @@ void __init s3c_init_vic_timer_irq(unsigned int num, unsigned int timer_irq)
 
         s3c_tgc = irq_alloc_generic_chip("s3c-timer", 1, timer_irq,
                                          S3C64XX_TINT_CSTAT, handle_level_irq);
+
+        if (!s3c_tgc) {
+                pr_err("%s: irq_alloc_generic_chip for IRQ %d failed\n",
+                       __func__, timer_irq);
+                return;
+        }
+
         ct = s3c_tgc->chip_types;
         ct->chip.irq_mask = irq_gc_mask_clr_bit;
         ct->chip.irq_unmask = irq_gc_mask_set_bit;
diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c
index 5c0a440d6e16..5fa1742d019b 100644
--- a/arch/arm/plat-samsung/pm.c
+++ b/arch/arm/plat-samsung/pm.c
@@ -20,6 +20,7 @@
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
+#include <asm/suspend.h>
 #include <mach/hardware.h>
 #include <mach/map.h>
 
@@ -231,7 +232,7 @@ static void __maybe_unused s3c_pm_show_resume_irqs(int start,
 
 
 void (*pm_cpu_prep)(void);
-void (*pm_cpu_sleep)(void);
+int (*pm_cpu_sleep)(unsigned long);
 
 #define any_allowed(mask, allow) (((mask) & (allow)) != (allow))
 
@@ -294,15 +295,11 @@ static int s3c_pm_enter(suspend_state_t state)
 
         s3c_pm_arch_stop_clocks();
 
-        /* s3c_cpu_save will also act as our return point from when
+        /* this will also act as our return point from when
          * we resume as it saves its own register state and restores it
          * during the resume.  */
 
-        s3c_cpu_save(0, PLAT_PHYS_OFFSET - PAGE_OFFSET);
-
-        /* restore the cpu state using the kernel's cpu init code. */
-
-        cpu_init();
+        cpu_suspend(0, pm_cpu_sleep);
 
         /* restore the system state */
 
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index 9897dcfc16d6..2d30c7f6edd3 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -77,27 +77,27 @@ ENTRY(vfp_support_entry)
         bne     look_for_VFP_exceptions @ VFP is already enabled
 
         DBGSTR1 "enable %x", r10
-        ldr     r3, last_VFP_context_address
+        ldr     r3, vfp_current_hw_state_address
         orr     r1, r1, #FPEXC_EN       @ user FPEXC has the enable bit set
-        ldr     r4, [r3, r11, lsl #2]   @ last_VFP_context pointer
+        ldr     r4, [r3, r11, lsl #2]   @ vfp_current_hw_state pointer
         bic     r5, r1, #FPEXC_EX       @ make sure exceptions are disabled
-        cmp     r4, r10
-        beq     check_for_exception     @ we are returning to the same
-                                        @ process, so the registers are
-                                        @ still there.  In this case, we do
-                                        @ not want to drop a pending exception.
+        cmp     r4, r10                 @ this thread owns the hw context?
+#ifndef CONFIG_SMP
+        @ For UP, checking that this thread owns the hw context is
+        @ sufficient to determine that the hardware state is valid.
+        beq     vfp_hw_state_valid
+
+        @ On UP, we lazily save the VFP context.  As a different
+        @ thread wants ownership of the VFP hardware, save the old
+        @ state if there was a previous (valid) owner.
 
         VFPFMXR FPEXC, r5               @ enable VFP, disable any pending
                                         @ exceptions, so we can get at the
                                         @ rest of it
 
-#ifndef CONFIG_SMP
-        @ Save out the current registers to the old thread state
-        @ No need for SMP since this is not done lazily
-
         DBGSTR1 "save old state %p", r4
-        cmp     r4, #0
-        beq     no_old_VFP_process
+        cmp     r4, #0                  @ if the vfp_current_hw_state is NULL
+        beq     vfp_reload_hw           @ then the hw state needs reloading
         VFPFSTMIA r4, r5                @ save the working registers
         VFPFMRX r5, FPSCR               @ current status
 #ifndef CONFIG_CPU_FEROCEON
@@ -110,13 +110,35 @@ ENTRY(vfp_support_entry)
 1:
 #endif
         stmia   r4, {r1, r5, r6, r8}    @ save FPEXC, FPSCR, FPINST, FPINST2
-                                        @ and point r4 at the word at the
-                                        @ start of the register dump
+vfp_reload_hw:
+
+#else
+        @ For SMP, if this thread does not own the hw context, then we
+        @ need to reload it.  No need to save the old state as on SMP,
+        @ we always save the state when we switch away from a thread.
+        bne     vfp_reload_hw
+
+        @ This thread has ownership of the current hardware context.
+        @ However, it may have been migrated to another CPU, in which
+        @ case the saved state is newer than the hardware context.
+        @ Check this by looking at the CPU number which the state was
+        @ last loaded onto.
+        ldr     ip, [r10, #VFP_CPU]
+        teq     ip, r11
+        beq     vfp_hw_state_valid
+
+vfp_reload_hw:
+        @ We're loading this threads state into the VFP hardware. Update
+        @ the CPU number which contains the most up to date VFP context.
+        str     r11, [r10, #VFP_CPU]
+
+        VFPFMXR FPEXC, r5               @ enable VFP, disable any pending
+                                        @ exceptions, so we can get at the
+                                        @ rest of it
 #endif
 
-no_old_VFP_process:
         DBGSTR1 "load state %p", r10
-        str     r10, [r3, r11, lsl #2]  @ update the last_VFP_context pointer
+        str     r10, [r3, r11, lsl #2]  @ update the vfp_current_hw_state pointer
                                         @ Load the saved state back into the VFP
         VFPFLDMIA r10, r5               @ reload the working registers while
                                         @ FPEXC is in a safe state
@@ -132,7 +154,8 @@ no_old_VFP_process:
 #endif
         VFPFMXR FPSCR, r5               @ restore status
 
-check_for_exception:
+@ The context stored in the VFP hardware is up to date with this thread
+vfp_hw_state_valid:
         tst     r1, #FPEXC_EX
         bne     process_exception       @ might as well handle the pending
                                         @ exception before retrying branch
@@ -207,8 +230,8 @@ ENTRY(vfp_save_state)
 ENDPROC(vfp_save_state)
 
         .align
-last_VFP_context_address:
-        .word   last_VFP_context
+vfp_current_hw_state_address:
+        .word   vfp_current_hw_state
 
         .macro  tbl_branch, base, tmp, shift
 #ifdef CONFIG_THUMB2_KERNEL
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index f25e7ec89416..0a96f71f0abd 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -33,7 +33,6 @@ void vfp_support_entry(void);
 void vfp_null_entry(void);
 
 void (*vfp_vector)(void) = vfp_null_entry;
-union vfp_state *last_VFP_context[NR_CPUS];
 
 /*
  * Dual-use variable.
@@ -43,6 +42,46 @@ union vfp_state *last_VFP_context[NR_CPUS];
 unsigned int VFP_arch;
 
 /*
+ * The pointer to the vfpstate structure of the thread which currently
+ * owns the context held in the VFP hardware, or NULL if the hardware
+ * context is invalid.
+ *
+ * For UP, this is sufficient to tell which thread owns the VFP context.
+ * However, for SMP, we also need to check the CPU number stored in the
+ * saved state too to catch migrations.
+ */
+union vfp_state *vfp_current_hw_state[NR_CPUS];
+
+/*
+ * Is 'thread's most up to date state stored in this CPUs hardware?
+ * Must be called from non-preemptible context.
+ */
+static bool vfp_state_in_hw(unsigned int cpu, struct thread_info *thread)
+{
+#ifdef CONFIG_SMP
+        if (thread->vfpstate.hard.cpu != cpu)
+                return false;
+#endif
+        return vfp_current_hw_state[cpu] == &thread->vfpstate;
+}
+
+/*
+ * Force a reload of the VFP context from the thread structure.  We do
+ * this by ensuring that access to the VFP hardware is disabled, and
+ * clear last_VFP_context.  Must be called from non-preemptible context.
+ */
+static void vfp_force_reload(unsigned int cpu, struct thread_info *thread)
+{
+        if (vfp_state_in_hw(cpu, thread)) {
+                fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
+                vfp_current_hw_state[cpu] = NULL;
+        }
+#ifdef CONFIG_SMP
+        thread->vfpstate.hard.cpu = NR_CPUS;
+#endif
+}
+
+/*
  * Per-thread VFP initialization.
  */
 static void vfp_thread_flush(struct thread_info *thread)
@@ -50,21 +89,27 @@ static void vfp_thread_flush(struct thread_info *thread)
         union vfp_state *vfp = &thread->vfpstate;
         unsigned int cpu;
 
-        memset(vfp, 0, sizeof(union vfp_state));
-
-        vfp->hard.fpexc = FPEXC_EN;
-        vfp->hard.fpscr = FPSCR_ROUND_NEAREST;
-
         /*
          * Disable VFP to ensure we initialize it first.  We must ensure
-         * that the modification of last_VFP_context[] and hardware disable
-         * are done for the same CPU and without preemption.
+         * that the modification of vfp_current_hw_state[] and hardware
+         * disable are done for the same CPU and without preemption.
+         *
+         * Do this first to ensure that preemption won't overwrite our
+         * state saving should access to the VFP be enabled at this point.
          */
         cpu = get_cpu();
-        if (last_VFP_context[cpu] == vfp)
-                last_VFP_context[cpu] = NULL;
+        if (vfp_current_hw_state[cpu] == vfp)
+                vfp_current_hw_state[cpu] = NULL;
         fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
         put_cpu();
+
+        memset(vfp, 0, sizeof(union vfp_state));
+
+        vfp->hard.fpexc = FPEXC_EN;
+        vfp->hard.fpscr = FPSCR_ROUND_NEAREST;
+#ifdef CONFIG_SMP
+        vfp->hard.cpu = NR_CPUS;
+#endif
 }
 
 static void vfp_thread_exit(struct thread_info *thread)
@@ -73,8 +118,8 @@ static void vfp_thread_exit(struct thread_info *thread)
         union vfp_state *vfp = &thread->vfpstate;
         unsigned int cpu = get_cpu();
 
-        if (last_VFP_context[cpu] == vfp)
-                last_VFP_context[cpu] = NULL;
+        if (vfp_current_hw_state[cpu] == vfp)
+                vfp_current_hw_state[cpu] = NULL;
         put_cpu();
 }
 
@@ -84,6 +129,9 @@ static void vfp_thread_copy(struct thread_info *thread)
 
         vfp_sync_hwstate(parent);
         thread->vfpstate = parent->vfpstate;
+#ifdef CONFIG_SMP
+        thread->vfpstate.hard.cpu = NR_CPUS;
+#endif
 }
 
 /*
@@ -129,17 +177,8 @@ static int vfp_notifier(struct notifier_block *self, unsigned long cmd, void *v)
                  * case the thread migrates to a different CPU. The
                  * restoring is done lazily.
                  */
-                if ((fpexc & FPEXC_EN) && last_VFP_context[cpu]) {
-                        vfp_save_state(last_VFP_context[cpu], fpexc);
-                        last_VFP_context[cpu]->hard.cpu = cpu;
-                }
-                /*
-                 * Thread migration, just force the reloading of the
-                 * state on the new CPU in case the VFP registers
-                 * contain stale data.
-                 */
-                if (thread->vfpstate.hard.cpu != cpu)
-                        last_VFP_context[cpu] = NULL;
+                if ((fpexc & FPEXC_EN) && vfp_current_hw_state[cpu])
+                        vfp_save_state(vfp_current_hw_state[cpu], fpexc);
 #endif
 
                 /*
@@ -415,7 +454,7 @@ static int vfp_pm_suspend(void)
         }
 
         /* clear any information we had about last context state */
-        memset(last_VFP_context, 0, sizeof(last_VFP_context));
+        memset(vfp_current_hw_state, 0, sizeof(vfp_current_hw_state));
 
         return 0;
 }
@@ -443,15 +482,15 @@ static void vfp_pm_init(void)
 static inline void vfp_pm_init(void) { }
 #endif /* CONFIG_PM */
 
+/*
+ * Ensure that the VFP state stored in 'thread->vfpstate' is up to date
+ * with the hardware state.
+ */
 void vfp_sync_hwstate(struct thread_info *thread)
 {
         unsigned int cpu = get_cpu();
 
-        /*
-         * If the thread we're interested in is the current owner of the
-         * hardware VFP state, then we need to save its state.
-         */
-        if (last_VFP_context[cpu] == &thread->vfpstate) {
+        if (vfp_state_in_hw(cpu, thread)) {
                 u32 fpexc = fmrx(FPEXC);
 
                 /*
@@ -465,36 +504,13 @@ void vfp_sync_hwstate(struct thread_info *thread)
         put_cpu();
 }
 
+/* Ensure that the thread reloads the hardware VFP state on the next use. */
 void vfp_flush_hwstate(struct thread_info *thread)
 {
         unsigned int cpu = get_cpu();
 
-        /*
-         * If the thread we're interested in is the current owner of the
-         * hardware VFP state, then we need to save its state.
-         */
-        if (last_VFP_context[cpu] == &thread->vfpstate) {
-                u32 fpexc = fmrx(FPEXC);
-
-                fmxr(FPEXC, fpexc & ~FPEXC_EN);
-
-                /*
-                 * Set the context to NULL to force a reload the next time
-                 * the thread uses the VFP.
-                 */
-                last_VFP_context[cpu] = NULL;
-        }
+        vfp_force_reload(cpu, thread);
 
-#ifdef CONFIG_SMP
-        /*
-         * For SMP we still have to take care of the case where the thread
-         * migrates to another CPU and then back to the original CPU on which
-         * the last VFP user is still the same thread. Mark the thread VFP
-         * state as belonging to a non-existent CPU so that the saved one will
-         * be reloaded in the above case.
-         */
-        thread->vfpstate.hard.cpu = NR_CPUS;
-#endif
         put_cpu();
 }
 
@@ -513,8 +529,7 @@ 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;
+                vfp_force_reload((long)hcpu, current_thread_info());
         } else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
                 vfp_enable(NULL);
         return NOTIFY_OK;