135 files changed, 925 insertions, 945 deletions

diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 176062ac7f07..5df26a9976a2 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -65,6 +65,8 @@ $(obj)/%.dtb: $(src)/dts/%.dts
 
 $(obj)/dtbs: $(addprefix $(obj)/, $(dtb-y))
 
+clean-files := *.dtb
+
 quiet_cmd_uimage = UIMAGE  $@
       cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A arm -O linux -T kernel \
                    -C none -a $(LOADADDR) -e $(STARTADDR) \
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 1db1143a9483..7df239bcdf27 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -20,6 +20,8 @@
 #ifndef __ASM_ARM_HARDWARE_L2X0_H
 #define __ASM_ARM_HARDWARE_L2X0_H
 
+#include <linux/errno.h>
+
 #define L2X0_CACHE_ID                   0x000
 #define L2X0_CACHE_TYPE                 0x004
 #define L2X0_CTRL                       0x100
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 7d19425dd496..2b0efc3104ac 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -13,6 +13,7 @@
 struct tag;
 struct meminfo;
 struct sys_timer;
+struct pt_regs;
 
 struct machine_desc {
         unsigned int            nr;             /* architecture number  */
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index c60a2944f95b..4a1123783806 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -402,6 +402,8 @@
 #define __NR_syncfs                     (__NR_SYSCALL_BASE+373)
 #define __NR_sendmmsg                   (__NR_SYSCALL_BASE+374)
 #define __NR_setns                      (__NR_SYSCALL_BASE+375)
+#define __NR_process_vm_readv           (__NR_SYSCALL_BASE+376)
+#define __NR_process_vm_writev          (__NR_SYSCALL_BASE+377)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 9943e9e74a1b..463ff4a0ec8a 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -385,6 +385,8 @@
                 CALL(sys_syncfs)
                 CALL(sys_sendmmsg)
 /* 375 */       CALL(sys_setns)
+                CALL(sys_process_vm_readv)
+                CALL(sys_process_vm_writev)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 566c54c2a1fe..08c82fd844a8 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -360,7 +360,7 @@ __secondary_data:
  *  r13 = *virtual* address to jump to upon completion
  */
 __enable_mmu:
-#ifdef CONFIG_ALIGNMENT_TRAP
+#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
         orr     r0, r0, #CR_A
 #else
         bic     r0, r0, #CR_A
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index c1b4463dcc83..e59bbd496c39 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -32,24 +32,6 @@ static atomic_t waiting_for_crash_ipi;
 
 int machine_kexec_prepare(struct kimage *image)
 {
-        unsigned long page_list;
-        void *reboot_code_buffer;
-        page_list = image->head & PAGE_MASK;
-
-        reboot_code_buffer = page_address(image->control_code_page);
-
-        /* Prepare parameters for reboot_code_buffer*/
-        kexec_start_address = image->start;
-        kexec_indirection_page = page_list;
-        kexec_mach_type = machine_arch_type;
-        kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET;
-
-        /* copy our kernel relocation code to the control code page */
-        memcpy(reboot_code_buffer,
-               relocate_new_kernel, relocate_new_kernel_size);
-
-        flush_icache_range((unsigned long) reboot_code_buffer,
-                           (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
         return 0;
 }
 
@@ -100,14 +82,31 @@ void (*kexec_reinit)(void);
 
 void machine_kexec(struct kimage *image)
 {
+        unsigned long page_list;
         unsigned long reboot_code_buffer_phys;
         void *reboot_code_buffer;
 
+
+        page_list = image->head & PAGE_MASK;
+
         /* we need both effective and real address here */
         reboot_code_buffer_phys =
             page_to_pfn(image->control_code_page) << PAGE_SHIFT;
         reboot_code_buffer = page_address(image->control_code_page);
 
+        /* Prepare parameters for reboot_code_buffer*/
+        kexec_start_address = image->start;
+        kexec_indirection_page = page_list;
+        kexec_mach_type = machine_arch_type;
+        kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET;
+
+        /* copy our kernel relocation code to the control code page */
+        memcpy(reboot_code_buffer,
+               relocate_new_kernel, relocate_new_kernel_size);
+
+
+        flush_icache_range((unsigned long) reboot_code_buffer,
+                           (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
         printk(KERN_INFO "Bye!\n");
 
         if (kexec_reinit)
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 7e7977ab994f..3448a3f9cc8c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -461,8 +461,10 @@ static void __init setup_processor(void)
                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);
+        snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",
+                 list->arch_name, ENDIANNESS);
+        snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c",
+                 list->elf_name, ENDIANNESS);
         elf_hwcap = list->elf_hwcap;
 #ifndef CONFIG_ARM_THUMB
         elf_hwcap &= ~HWCAP_THUMB;
diff --git a/arch/arm/mach-bcmring/core.c b/arch/arm/mach-bcmring/core.c
index 43eadbcc29ed..430da120a297 100644
--- a/arch/arm/mach-bcmring/core.c
+++ b/arch/arm/mach-bcmring/core.c
@@ -235,7 +235,7 @@ void __init bcmring_init_timer(void)
          */
         bcmring_clocksource_init();
 
-        sp804_clockevents_register(TIMER0_VA_BASE, IRQ_TIMER0, "timer0");
+        sp804_clockevents_init(TIMER0_VA_BASE, IRQ_TIMER0, "timer0");
 }
 
 struct sys_timer bcmring_timer = {
diff --git a/arch/arm/mach-bcmring/dma.c b/arch/arm/mach-bcmring/dma.c
index b52b8de91bde..f4d4d6d174d0 100644
--- a/arch/arm/mach-bcmring/dma.c
+++ b/arch/arm/mach-bcmring/dma.c
@@ -36,6 +36,7 @@
 #include <linux/mm.h>
 #include <linux/pfn.h>
 #include <linux/atomic.h>
+#include <linux/sched.h>
 #include <mach/dma.h>
 
 /* I don't quite understand why dc4 fails when this is set to 1 and DMA is enabled */
diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c
index 0a5b22942fd3..34bbcbfb1706 100644
--- a/arch/arm/mach-shmobile/pm-sh7372.c
+++ b/arch/arm/mach-shmobile/pm-sh7372.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/bitrev.h>
+#include <linux/console.h>
 #include <asm/system.h>
 #include <asm/io.h>
 #include <asm/tlbflush.h>
@@ -106,9 +107,8 @@ static int pd_power_down(struct generic_pm_domain *genpd)
         return 0;
 }
 
-static int pd_power_up(struct generic_pm_domain *genpd)
+static int __pd_power_up(struct sh7372_pm_domain *sh7372_pd, bool do_resume)
 {
-        struct sh7372_pm_domain *sh7372_pd = to_sh7372_pd(genpd);
         unsigned int mask = 1 << sh7372_pd->bit_shift;
         unsigned int retry_count;
         int ret = 0;
@@ -123,13 +123,13 @@ static int pd_power_up(struct generic_pm_domain *genpd)
 
         for (retry_count = 2 * PSTR_RETRIES; retry_count; retry_count--) {
                 if (!(__raw_readl(SWUCR) & mask))
-                        goto out;
+                        break;
                 if (retry_count > PSTR_RETRIES)
                         udelay(PSTR_DELAY_US);
                 else
                         cpu_relax();
         }
-        if (__raw_readl(SWUCR) & mask)
+        if (!retry_count)
                 ret = -EIO;
 
         if (!sh7372_pd->no_debug)
@@ -137,12 +137,17 @@ static int pd_power_up(struct generic_pm_domain *genpd)
                          mask, __raw_readl(PSTR));
 
  out:
-        if (ret == 0 && sh7372_pd->resume)
+        if (ret == 0 && sh7372_pd->resume && do_resume)
                 sh7372_pd->resume();
 
         return ret;
 }
 
+static int pd_power_up(struct generic_pm_domain *genpd)
+{
+         return __pd_power_up(to_sh7372_pd(genpd), true);
+}
+
 static void sh7372_a4r_suspend(void)
 {
         sh7372_intcs_suspend();
@@ -174,7 +179,7 @@ void sh7372_init_pm_domain(struct sh7372_pm_domain *sh7372_pd)
         genpd->active_wakeup = pd_active_wakeup;
         genpd->power_off = pd_power_down;
         genpd->power_on = pd_power_up;
-        genpd->power_on(&sh7372_pd->genpd);
+        __pd_power_up(sh7372_pd, false);
 }
 
 void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd,
@@ -227,11 +232,23 @@ struct sh7372_pm_domain sh7372_a3sp = {
         .no_debug = true,
 };
 
+static void sh7372_a3sp_init(void)
+{
+        /* serial consoles make use of SCIF hardware located in A3SP,
+         * keep such power domain on if "no_console_suspend" is set.
+         */
+        sh7372_a3sp.stay_on = !console_suspend_enabled;
+}
+
 struct sh7372_pm_domain sh7372_a3sg = {
         .bit_shift = 13,
 };
 
-#endif /* CONFIG_PM */
+#else /* !CONFIG_PM */
+
+static inline void sh7372_a3sp_init(void) {}
+
+#endif /* !CONFIG_PM */
 
 #if defined(CONFIG_SUSPEND) || defined(CONFIG_CPU_IDLE)
 static int sh7372_do_idle_core_standby(unsigned long unused)
@@ -465,6 +482,8 @@ void __init sh7372_pm_init(void)
         /* do not convert A3SM, A3SP, A3SG, A4R power down into A4S */
         __raw_writel(0, PDNSEL);
 
+        sh7372_a3sp_init();
+
         sh7372_suspend_init();
         sh7372_cpuidle_init();
 }
diff --git a/arch/arm/mach-w90x900/dev.c b/arch/arm/mach-w90x900/dev.c
index 7a1fa6adb7c3..5b0c38abacc1 100644
--- a/arch/arm/mach-w90x900/dev.c
+++ b/arch/arm/mach-w90x900/dev.c
@@ -422,7 +422,7 @@ struct platform_device nuc900_device_kpi = {
 
 /* LCD controller*/
 
-static struct nuc900fb_display __initdata nuc900_lcd_info[] = {
+static struct nuc900fb_display nuc900_lcd_info[] = {
         /* Giantplus Technology GPM1040A0 320x240 Color TFT LCD */
         [0] = {
                 .type           = LCM_DCCS_VA_SRC_RGB565,
@@ -445,7 +445,7 @@ static struct nuc900fb_display __initdata nuc900_lcd_info[] = {
         },
 };
 
-static struct nuc900fb_mach_info nuc900_fb_info __initdata = {
+static struct nuc900fb_mach_info nuc900_fb_info = {
 #if defined(CONFIG_GPM1040A0_320X240)
         .displays               = &nuc900_lcd_info[0],
 #else
diff --git a/arch/arm/mach-w90x900/include/mach/mfp.h b/arch/arm/mach-w90x900/include/mach/mfp.h
index 94c0e71617c6..23ef1f573abd 100644
--- a/arch/arm/mach-w90x900/include/mach/mfp.h
+++ b/arch/arm/mach-w90x900/include/mach/mfp.h
@@ -19,6 +19,7 @@
 extern void mfp_set_groupf(struct device *dev);
 extern void mfp_set_groupc(struct device *dev);
 extern void mfp_set_groupi(struct device *dev);
-extern void mfp_set_groupg(struct device *dev);
+extern void mfp_set_groupg(struct device *dev, const char *subname);
+extern void mfp_set_groupd(struct device *dev, const char *subname);
 
 #endif /* __ASM_ARCH_MFP_H */
diff --git a/arch/arm/mach-w90x900/include/mach/nuc900_spi.h b/arch/arm/mach-w90x900/include/mach/nuc900_spi.h
index bd94819e314f..2c4e0c128501 100644
--- a/arch/arm/mach-w90x900/include/mach/nuc900_spi.h
+++ b/arch/arm/mach-w90x900/include/mach/nuc900_spi.h
@@ -14,7 +14,7 @@
 #ifndef __ASM_ARCH_SPI_H
 #define __ASM_ARCH_SPI_H
 
-extern void mfp_set_groupg(struct device *dev);
+extern void mfp_set_groupg(struct device *dev, const char *subname);
 
 struct nuc900_spi_info {
         unsigned int num_cs;
diff --git a/arch/arm/mach-w90x900/mfp.c b/arch/arm/mach-w90x900/mfp.c
index fb7fb627b1a5..9dd74612bb87 100644
--- a/arch/arm/mach-w90x900/mfp.c
+++ b/arch/arm/mach-w90x900/mfp.c
@@ -26,10 +26,8 @@
 #define REG_MFSEL       (W90X900_VA_GCR + 0xC)
 
 #define GPSELF          (0x01 << 1)
-
 #define GPSELC          (0x03 << 2)
-#define ENKPI           (0x02 << 2)
-#define ENNAND          (0x01 << 2)
+#define GPSELD          (0x0f << 4)
 
 #define GPSELEI0        (0x01 << 26)
 #define GPSELEI1        (0x01 << 27)
@@ -37,11 +35,16 @@
 #define GPIOG0TO1       (0x03 << 14)
 #define GPIOG2TO3       (0x03 << 16)
 #define GPIOG22TO23     (0x03 << 22)
+#define GPIOG18TO20     (0x07 << 18)
 
 #define ENSPI           (0x0a << 14)
 #define ENI2C0          (0x01 << 14)
 #define ENI2C1          (0x01 << 16)
 #define ENAC97          (0x02 << 22)
+#define ENSD1           (0x02 << 18)
+#define ENSD0           (0x0a << 4)
+#define ENKPI           (0x02 << 2)
+#define ENNAND          (0x01 << 2)
 
 static DEFINE_MUTEX(mfp_mutex);
 
@@ -127,16 +130,19 @@ void mfp_set_groupi(struct device *dev)
 }
 EXPORT_SYMBOL(mfp_set_groupi);
 
-void mfp_set_groupg(struct device *dev)
+void mfp_set_groupg(struct device *dev, const char *subname)
 {
         unsigned long mfpen;
         const char *dev_id;
 
-        BUG_ON(!dev);
+        BUG_ON((!dev) && (!subname));
 
         mutex_lock(&mfp_mutex);
 
-        dev_id = dev_name(dev);
+        if (subname != NULL)
+                dev_id = subname;
+        else
+                dev_id = dev_name(dev);
 
         mfpen = __raw_readl(REG_MFSEL);
 
@@ -152,6 +158,9 @@ void mfp_set_groupg(struct device *dev)
         } else if (strcmp(dev_id, "nuc900-audio") == 0) {
                 mfpen &= ~(GPIOG22TO23);
                 mfpen |= ENAC97;/*enable AC97*/
+        } else if (strcmp(dev_id, "nuc900-mmc-port1") == 0) {
+                mfpen &= ~(GPIOG18TO20);
+                mfpen |= (ENSD1 | 0x01);/*enable sd1*/
         } else {
                 mfpen &= ~(GPIOG0TO1 | GPIOG2TO3);/*GPIOG[3:0]*/
         }
@@ -162,3 +171,30 @@ void mfp_set_groupg(struct device *dev)
 }
 EXPORT_SYMBOL(mfp_set_groupg);
 
+void mfp_set_groupd(struct device *dev, const char *subname)
+{
+        unsigned long mfpen;
+        const char *dev_id;
+
+        BUG_ON((!dev) && (!subname));
+
+        mutex_lock(&mfp_mutex);
+
+        if (subname != NULL)
+                dev_id = subname;
+        else
+                dev_id = dev_name(dev);
+
+        mfpen = __raw_readl(REG_MFSEL);
+
+        if (strcmp(dev_id, "nuc900-mmc-port0") == 0) {
+                mfpen &= ~GPSELD;/*enable sd0*/
+                mfpen |= ENSD0;
+        } else
+                mfpen &= (~GPSELD);
+
+        __raw_writel(mfpen, REG_MFSEL);
+
+        mutex_unlock(&mfp_mutex);
+}
+EXPORT_SYMBOL(mfp_set_groupd);
diff --git a/arch/cris/arch-v10/drivers/Kconfig b/arch/cris/arch-v10/drivers/Kconfig
index 32d90867a984..5f2cdb3e428c 100644
--- a/arch/cris/arch-v10/drivers/Kconfig
+++ b/arch/cris/arch-v10/drivers/Kconfig
@@ -3,7 +3,7 @@ if ETRAX_ARCH_V10
 config ETRAX_ETHERNET
         bool "Ethernet support"
         depends on ETRAX_ARCH_V10
-        select NET_ETHERNET
+        select ETHERNET
         select NET_CORE
         select MII
         help
diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig
index e47e9c3401b0..de43aadcdbc4 100644
--- a/arch/cris/arch-v32/drivers/Kconfig
+++ b/arch/cris/arch-v32/drivers/Kconfig
@@ -3,7 +3,7 @@ if ETRAX_ARCH_V32
 config ETRAX_ETHERNET
         bool "Ethernet support"
         depends on ETRAX_ARCH_V32
-        select NET_ETHERNET
+        select ETHERNET
         select NET_CORE
         select MII
         help
diff --git a/arch/microblaze/include/asm/namei.h b/arch/microblaze/include/asm/namei.h
deleted file mode 100644
index 61d60b8a07d5..000000000000
--- a/arch/microblaze/include/asm/namei.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * 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.
- */
-
-#ifndef _ASM_MICROBLAZE_NAMEI_H
-#define _ASM_MICROBLAZE_NAMEI_H
-
-#ifdef __KERNEL__
-
-/* This dummy routine maybe changed to something useful
- * for /usr/gnemul/ emulation stuff.
- * Look at asm-sparc/namei.h for details.
- */
-#define __emul_prefix() NULL
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_MICROBLAZE_NAMEI_H */
diff --git a/arch/mips/cavium-octeon/flash_setup.c b/arch/mips/cavium-octeon/flash_setup.c
index 975c20327bb1..0a430e06f5e5 100644
--- a/arch/mips/cavium-octeon/flash_setup.c
+++ b/arch/mips/cavium-octeon/flash_setup.c
@@ -17,8 +17,6 @@
 
 static struct map_info flash_map;
 static struct mtd_info *mymtd;
-static int nr_parts;
-static struct mtd_partition *parts;
 static const char *part_probe_types[] = {
         "cmdlinepart",
 #ifdef CONFIG_MTD_REDBOOT_PARTS
@@ -61,11 +59,8 @@ static int __init flash_init(void)
                 mymtd = do_map_probe("cfi_probe", &flash_map);
                 if (mymtd) {
                         mymtd->owner = THIS_MODULE;
-
-                        nr_parts = parse_mtd_partitions(mymtd,
-                                                        part_probe_types,
-                                                        &parts, 0);
-                        mtd_device_register(mymtd, parts, nr_parts);
+                        mtd_device_parse_register(mymtd, part_probe_types,
+                                                  0, NULL, 0);
                 } else {
                         pr_err("Failed to register MTD device for flash\n");
                 }
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 8b606423bbd7..efcfff4d4627 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -207,8 +207,9 @@ void octeon_prepare_cpus(unsigned int max_cpus)
          * the other bits alone.
          */
         cvmx_write_csr(CVMX_CIU_MBOX_CLRX(cvmx_get_core_num()), 0xffff);
-        if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt, IRQF_DISABLED,
-                        "SMP-IPI", mailbox_interrupt)) {
+        if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt,
+                        IRQF_PERCPU | IRQF_NO_THREAD, "SMP-IPI",
+                        mailbox_interrupt)) {
                 panic("Cannot request_irq(OCTEON_IRQ_MBOX0)\n");
         }
 }
diff --git a/arch/mips/emma/common/prom.c b/arch/mips/emma/common/prom.c
index 708f08761406..cae42259d6da 100644
--- a/arch/mips/emma/common/prom.c
+++ b/arch/mips/emma/common/prom.c
@@ -50,7 +50,7 @@ void __init prom_init(void)
 
         /* arg[0] is "g", the rest is boot parameters */
         for (i = 1; i < argc; i++) {
-                if (strlen(arcs_cmdline) + strlen(arg[i] + 1)
+                if (strlen(arcs_cmdline) + strlen(arg[i]) + 1
                     >= sizeof(arcs_cmdline))
                         break;
                 strcat(arcs_cmdline, arg[i]);
diff --git a/arch/mips/include/asm/mach-bcm47xx/gpio.h b/arch/mips/include/asm/mach-bcm47xx/gpio.h
index 76961cabeedf..2ef17e8df403 100644
--- a/arch/mips/include/asm/mach-bcm47xx/gpio.h
+++ b/arch/mips/include/asm/mach-bcm47xx/gpio.h
@@ -36,6 +36,8 @@ static inline int gpio_get_value(unsigned gpio)
         return -EINVAL;
 }
 
+#define gpio_get_value_cansleep gpio_get_value
+
 static inline void gpio_set_value(unsigned gpio, int value)
 {
         switch (bcm47xx_bus_type) {
@@ -54,6 +56,19 @@ static inline void gpio_set_value(unsigned gpio, int value)
         }
 }
 
+#define gpio_set_value_cansleep gpio_set_value
+
+static inline int gpio_cansleep(unsigned gpio)
+{
+        return 0;
+}
+
+static inline int gpio_is_valid(unsigned gpio)
+{
+        return gpio < (BCM47XX_EXTIF_GPIO_LINES + BCM47XX_CHIPCO_GPIO_LINES);
+}
+
+
 static inline int gpio_direction_input(unsigned gpio)
 {
         switch (bcm47xx_bus_type) {
@@ -137,7 +152,4 @@ static inline int gpio_polarity(unsigned gpio, int value)
 }
 
 
-/* cansleep wrappers */
-#include <asm-generic/gpio.h>
-
 #endif /* __BCM47XX_GPIO_H */
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index ecea7871dec2..d8dad5340ea3 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -365,16 +365,18 @@
 #define __NR_syncfs                     (__NR_Linux + 342)
 #define __NR_sendmmsg                   (__NR_Linux + 343)
 #define __NR_setns                      (__NR_Linux + 344)
+#define __NR_process_vm_readv           (__NR_Linux + 345)
+#define __NR_process_vm_writev          (__NR_Linux + 346)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls             344
+#define __NR_Linux_syscalls             346
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux                  4000
-#define __NR_O32_Linux_syscalls         344
+#define __NR_O32_Linux_syscalls         346
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -686,16 +688,18 @@
 #define __NR_syncfs                     (__NR_Linux + 301)
 #define __NR_sendmmsg                   (__NR_Linux + 302)
 #define __NR_setns                      (__NR_Linux + 303)
+#define __NR_process_vm_readv           (__NR_Linux + 304)
+#define __NR_process_vm_writev          (__NR_Linux + 305)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls             303
+#define __NR_Linux_syscalls             305
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux                   5000
-#define __NR_64_Linux_syscalls          303
+#define __NR_64_Linux_syscalls          305
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1012,16 +1016,18 @@
 #define __NR_syncfs                     (__NR_Linux + 306)
 #define __NR_sendmmsg                   (__NR_Linux + 307)
 #define __NR_setns                      (__NR_Linux + 308)
+#define __NR_process_vm_readv           (__NR_Linux + 309)
+#define __NR_process_vm_writev          (__NR_Linux + 310)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls             308
+#define __NR_Linux_syscalls             310
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux                  6000
-#define __NR_N32_Linux_syscalls         308
+#define __NR_N32_Linux_syscalls         310
 
 #ifdef __KERNEL__
 
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 98c5a9737c14..e2d8e199be32 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -103,19 +103,10 @@ static int c0_compare_int_pending(void)
 
 /*
  * Compare interrupt can be routed and latched outside the core,
- * so a single execution hazard barrier may not be enough to give
- * it time to clear as seen in the Cause register.  4 time the
- * pipeline depth seems reasonably conservative, and empirically
- * works better in configurations with high CPU/bus clock ratios.
+ * so wait up to worst case number of cycle counter ticks for timer interrupt
+ * changes to propagate to the cause register.
  */
-
-#define compare_change_hazard() \
-        do { \
-                irq_disable_hazard(); \
-                irq_disable_hazard(); \
-                irq_disable_hazard(); \
-                irq_disable_hazard(); \
-        } while (0)
+#define COMPARE_INT_SEEN_TICKS 50
 
 int c0_compare_int_usable(void)
 {
@@ -126,8 +117,12 @@ int c0_compare_int_usable(void)
          * IP7 already pending?  Try to clear it by acking the timer.
          */
         if (c0_compare_int_pending()) {
-                write_c0_compare(read_c0_count());
-                compare_change_hazard();
+                cnt = read_c0_count();
+                write_c0_compare(cnt);
+                back_to_back_c0_hazard();
+                while (read_c0_count() < (cnt  + COMPARE_INT_SEEN_TICKS))
+                        if (!c0_compare_int_pending())
+                                break;
                 if (c0_compare_int_pending())
                         return 0;
         }
@@ -136,7 +131,7 @@ int c0_compare_int_usable(void)
                 cnt = read_c0_count();
                 cnt += delta;
                 write_c0_compare(cnt);
-                compare_change_hazard();
+                back_to_back_c0_hazard();
                 if ((int)(read_c0_count() - cnt) < 0)
                     break;
                 /* increase delta if the timer was already expired */
@@ -145,12 +140,17 @@ int c0_compare_int_usable(void)
         while ((int)(read_c0_count() - cnt) <= 0)
                 ;       /* Wait for expiry  */
 
-        compare_change_hazard();
+        while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS))
+                if (c0_compare_int_pending())
+                        break;
         if (!c0_compare_int_pending())
                 return 0;
-
-        write_c0_compare(read_c0_count());
-        compare_change_hazard();
+        cnt = read_c0_count();
+        write_c0_compare(cnt);
+        back_to_back_c0_hazard();
+        while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS))
+                if (!c0_compare_int_pending())
+                        break;
         if (c0_compare_int_pending())
                 return 0;
 
diff --git a/arch/mips/kernel/cpufreq/loongson2_clock.c b/arch/mips/kernel/cpufreq/loongson2_clock.c
index cefc6e259baf..5426779d9fdb 100644
--- a/arch/mips/kernel/cpufreq/loongson2_clock.c
+++ b/arch/mips/kernel/cpufreq/loongson2_clock.c
@@ -7,6 +7,7 @@
  * for more details.
  */
 
+#include <linux/module.h>
 #include <linux/cpufreq.h>
 #include <linux/platform_device.h>
 
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 47920657968d..a632bc144efa 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -591,6 +591,8 @@ einval:	li	v0, -ENOSYS
         sys     sys_syncfs              1
         sys     sys_sendmmsg            4
         sys     sys_setns               2
+        sys     sys_process_vm_readv    6       /* 4345 */
+        sys     sys_process_vm_writev   6
         .endm
 
         /* We pre-compute the number of _instruction_ bytes needed to
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index fb7334bea731..3b5a5e9ae49c 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -430,4 +430,6 @@ sys_call_table:
         PTR     sys_syncfs
         PTR     sys_sendmmsg
         PTR     sys_setns
+        PTR     sys_process_vm_readv
+        PTR     sys_process_vm_writev           /* 5305 */
         .size   sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 6de1f598346e..6be6f7020923 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -430,4 +430,6 @@ EXPORT(sysn32_call_table)
         PTR     sys_syncfs
         PTR     compat_sys_sendmmsg
         PTR     sys_setns
+        PTR     compat_sys_process_vm_readv
+        PTR     compat_sys_process_vm_writev    /* 6310 */
         .size   sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 1d813169e453..54228553691d 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -548,4 +548,6 @@ sys_call_table:
         PTR     sys_syncfs
         PTR     compat_sys_sendmmsg
         PTR     sys_setns
+        PTR     compat_sys_process_vm_readv     /* 4345 */
+        PTR     compat_sys_process_vm_writev
         .size   sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 261ccbc07740..5c8a49d55054 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1596,7 +1596,8 @@ void __cpuinit per_cpu_trap_init(void)
         }
 #endif /* CONFIG_MIPS_MT_SMTC */
 
-        cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
+        if (!cpu_data[cpu].asid_cache)
+                cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
 
         atomic_inc(&init_mm.mm_count);
         current->active_mm = &init_mm;
diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c
index 7e9c0ffc11a5..77ed70fc2fe5 100644
--- a/arch/mips/lantiq/clk.c
+++ b/arch/mips/lantiq/clk.c
@@ -7,7 +7,7 @@
  * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
  */
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/mips/lantiq/devices.c b/arch/mips/lantiq/devices.c
index 44a36771c819..de1cb2bcd79a 100644
--- a/arch/mips/lantiq/devices.c
+++ b/arch/mips/lantiq/devices.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
index 56ba007bf1e5..e34fcfd0d5ca 100644
--- a/arch/mips/lantiq/prom.c
+++ b/arch/mips/lantiq/prom.c
@@ -6,7 +6,7 @@
  * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/clk.h>
 #include <asm/bootinfo.h>
 #include <asm/time.h>
diff --git a/arch/mips/lantiq/setup.c b/arch/mips/lantiq/setup.c
index 9b8af77ed0f9..1ff6c9d6cb93 100644
--- a/arch/mips/lantiq/setup.c
+++ b/arch/mips/lantiq/setup.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <asm/bootinfo.h>
diff --git a/arch/mips/lantiq/xway/clk-ase.c b/arch/mips/lantiq/xway/clk-ase.c
index 22d823acd536..652258309c9c 100644
--- a/arch/mips/lantiq/xway/clk-ase.c
+++ b/arch/mips/lantiq/xway/clk-ase.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/clk.h>
 
diff --git a/arch/mips/lantiq/xway/clk-xway.c b/arch/mips/lantiq/xway/clk-xway.c
index ddd39593c581..696b1a3e0642 100644
--- a/arch/mips/lantiq/xway/clk-xway.c
+++ b/arch/mips/lantiq/xway/clk-xway.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/clk.h>
 
diff --git a/arch/mips/lantiq/xway/devices.c b/arch/mips/lantiq/xway/devices.c
index d0e32ab2ea07..d614aa7ff07f 100644
--- a/arch/mips/lantiq/xway/devices.c
+++ b/arch/mips/lantiq/xway/devices.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/mtd/physmap.h>
diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c
index 4278a459d6c4..cbb6ae5747b9 100644
--- a/arch/mips/lantiq/xway/dma.c
+++ b/arch/mips/lantiq/xway/dma.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
+#include <linux/export.h>
 
 #include <lantiq_soc.h>
 #include <xway_dma.h>
diff --git a/arch/mips/lantiq/xway/gpio.c b/arch/mips/lantiq/xway/gpio.c
index a321451a5455..d2fa98f3c78d 100644
--- a/arch/mips/lantiq/xway/gpio.c
+++ b/arch/mips/lantiq/xway/gpio.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/ioport.h>
diff --git a/arch/mips/lantiq/xway/gpio_ebu.c b/arch/mips/lantiq/xway/gpio_ebu.c
index a479355abdb9..b91c7f17f10f 100644
--- a/arch/mips/lantiq/xway/gpio_ebu.c
+++ b/arch/mips/lantiq/xway/gpio_ebu.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
diff --git a/arch/mips/lantiq/xway/gpio_stp.c b/arch/mips/lantiq/xway/gpio_stp.c
index 67d59d690340..ff9991cddeaa 100644
--- a/arch/mips/lantiq/xway/gpio_stp.c
+++ b/arch/mips/lantiq/xway/gpio_stp.c
@@ -9,7 +9,7 @@
 
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
diff --git a/arch/mips/lantiq/xway/prom-ase.c b/arch/mips/lantiq/xway/prom-ase.c
index abe49f4db57f..ae4959ae865c 100644
--- a/arch/mips/lantiq/xway/prom-ase.c
+++ b/arch/mips/lantiq/xway/prom-ase.c
@@ -6,7 +6,7 @@
  *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/clk.h>
 #include <asm/bootinfo.h>
 #include <asm/time.h>
diff --git a/arch/mips/lantiq/xway/prom-xway.c b/arch/mips/lantiq/xway/prom-xway.c
index 1686692ac24d..2228133ca356 100644
--- a/arch/mips/lantiq/xway/prom-xway.c
+++ b/arch/mips/lantiq/xway/prom-xway.c
@@ -6,7 +6,7 @@
  *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/clk.h>
 #include <asm/bootinfo.h>
 #include <asm/time.h>
diff --git a/arch/mips/lantiq/xway/reset.c b/arch/mips/lantiq/xway/reset.c
index a1be36d0e490..3d41f0bb5bf7 100644
--- a/arch/mips/lantiq/xway/reset.c
+++ b/arch/mips/lantiq/xway/reset.c
@@ -10,7 +10,7 @@
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/pm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/reboot.h>
 
 #include <lantiq_soc.h>
diff --git a/arch/mips/nxp/pnx8550/common/pci.c b/arch/mips/nxp/pnx8550/common/pci.c
deleted file mode 100644
index 98e86ddb86cc..000000000000
--- a/arch/mips/nxp/pnx8550/common/pci.c
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- *
- * BRIEF MODULE DESCRIPTION
- *
- * Author: source@mvista.com
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- */
-#include <linux/types.h>
-#include <linux/pci.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-
-#include <pci.h>
-#include <glb.h>
-#include <nand.h>
-
-static struct resource pci_io_resource = {
-        .start  = PNX8550_PCIIO + 0x1000,       /* reserve regacy I/O space */
-        .end    = PNX8550_PCIIO + PNX8550_PCIIO_SIZE,
-        .name   = "pci IO space",
-        .flags  = IORESOURCE_IO
-};
-
-static struct resource pci_mem_resource = {
-        .start  = PNX8550_PCIMEM,
-        .end    = PNX8550_PCIMEM + PNX8550_PCIMEM_SIZE - 1,
-        .name   = "pci memory space",
-        .flags  = IORESOURCE_MEM
-};
-
-extern struct pci_ops pnx8550_pci_ops;
-
-static struct pci_controller pnx8550_controller = {
-        .pci_ops        = &pnx8550_pci_ops,
-        .io_map_base    = PNX8550_PORT_BASE,
-        .io_resource    = &pci_io_resource,
-        .mem_resource   = &pci_mem_resource,
-};
-
-/* Return the total size of DRAM-memory, (RANK0 + RANK1) */
-static inline unsigned long get_system_mem_size(void)
-{
-        /* Read IP2031_RANK0_ADDR_LO */
-        unsigned long dram_r0_lo = inl(PCI_BASE | 0x65010);
-        /* Read IP2031_RANK1_ADDR_HI */
-        unsigned long dram_r1_hi = inl(PCI_BASE | 0x65018);
-
-        return dram_r1_hi - dram_r0_lo + 1;
-}
-
-static int __init pnx8550_pci_setup(void)
-{
-        int pci_mem_code;
-        int mem_size = get_system_mem_size() >> 20;
-
-        /* Clear the Global 2 Register, PCI Inta Output Enable Registers
-           Bit 1:Enable DAC Powerdown
-          -> 0:DACs are enabled and are working normally
-             1:DACs are powerdown
-           Bit 0:Enable of PCI inta output
-          -> 0 = Disable PCI inta output
-             1 = Enable PCI inta output
-        */
-        PNX8550_GLB2_ENAB_INTA_O = 0;
-
-        /* Calc the PCI mem size code */
-        if (mem_size >= 128)
-                pci_mem_code = SIZE_128M;
-        else if (mem_size >= 64)
-                pci_mem_code = SIZE_64M;
-        else if (mem_size >= 32)
-                pci_mem_code = SIZE_32M;
-        else
-                pci_mem_code = SIZE_16M;
-
-        /* Set PCI_XIO registers */
-        outl(pci_mem_resource.start, PCI_BASE | PCI_BASE1_LO);
-        outl(pci_mem_resource.end + 1, PCI_BASE | PCI_BASE1_HI);
-        outl(pci_io_resource.start, PCI_BASE | PCI_BASE2_LO);
-        outl(pci_io_resource.end, PCI_BASE | PCI_BASE2_HI);
-
-        /* Send memory transaction via PCI_BASE2 */
-        outl(0x00000001, PCI_BASE | PCI_IO);
-
-        /* Unlock the setup register */
-        outl(0xca, PCI_BASE | PCI_UNLOCKREG);
-
-        /*
-         * BAR0 of PNX8550 (pci base 10) must be zero in order for ide
-         * to work, and in order for bus_to_baddr to work without any
-         * hacks.
-         */
-        outl(0x00000000, PCI_BASE | PCI_BASE10);
-
-        /*
-         *These two bars are set by default or the boot code.
-         * However, it's safer to set them here so we're not boot
-         * code dependent.
-         */
-        outl(0x1be00000, PCI_BASE | PCI_BASE14);  /* PNX MMIO */
-        outl(PNX8550_NAND_BASE_ADDR, PCI_BASE | PCI_BASE18);  /* XIO      */
-
-        outl(PCI_EN_TA |
-             PCI_EN_PCI2MMI |
-             PCI_EN_XIO |
-             PCI_SETUP_BASE18_SIZE(SIZE_32M) |
-             PCI_SETUP_BASE18_EN |
-             PCI_SETUP_BASE14_EN |
-             PCI_SETUP_BASE10_PREF |
-             PCI_SETUP_BASE10_SIZE(pci_mem_code) |
-             PCI_SETUP_CFGMANAGE_EN |
-             PCI_SETUP_PCIARB_EN,
-             PCI_BASE |
-             PCI_SETUP);        /* PCI_SETUP */
-        outl(0x00000000, PCI_BASE | PCI_CTRL);  /* PCI_CONTROL */
-
-        register_pci_controller(&pnx8550_controller);
-
-        return 0;
-}
-
-arch_initcall(pnx8550_pci_setup);
diff --git a/arch/mips/nxp/pnx8550/common/setup.c b/arch/mips/nxp/pnx8550/common/setup.c
deleted file mode 100644
index 71adac323323..000000000000
--- a/arch/mips/nxp/pnx8550/common/setup.c
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- *
- * 2.6 port, Embedded Alley Solutions, Inc
- *
- *  Based on Per Hallsmark, per.hallsmark@mvista.com
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- */
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/irq.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/serial_pnx8xxx.h>
-#include <linux/pm.h>
-
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
-#include <asm/time.h>
-
-#include <glb.h>
-#include <int.h>
-#include <pci.h>
-#include <uart.h>
-#include <nand.h>
-
-extern void __init board_setup(void);
-extern void pnx8550_machine_restart(char *);
-extern void pnx8550_machine_halt(void);
-extern void pnx8550_machine_power_off(void);
-extern struct resource ioport_resource;
-extern struct resource iomem_resource;
-extern char *prom_getcmdline(void);
-
-struct resource standard_io_resources[] = {
-        {
-                .start  = 0x00,
-                .end    = 0x1f,
-                .name   = "dma1",
-                .flags  = IORESOURCE_BUSY
-        }, {
-                .start  = 0x40,
-                .end    = 0x5f,
-                .name   = "timer",
-                .flags  = IORESOURCE_BUSY
-        }, {
-                .start  = 0x80,
-                .end    = 0x8f,
-                .name   = "dma page reg",
-                .flags  = IORESOURCE_BUSY
-        }, {
-                .start  = 0xc0,
-                .end    = 0xdf,
-                .name   = "dma2",
-                .flags  = IORESOURCE_BUSY
-        },
-};
-
-#define STANDARD_IO_RESOURCES ARRAY_SIZE(standard_io_resources)
-
-extern struct resource pci_io_resource;
-extern struct resource pci_mem_resource;
-
-/* Return the total size of DRAM-memory, (RANK0 + RANK1) */
-unsigned long get_system_mem_size(void)
-{
-        /* Read IP2031_RANK0_ADDR_LO */
-        unsigned long dram_r0_lo = inl(PCI_BASE | 0x65010);
-        /* Read IP2031_RANK1_ADDR_HI */
-        unsigned long dram_r1_hi = inl(PCI_BASE | 0x65018);
-
-        return dram_r1_hi - dram_r0_lo + 1;
-}
-
-int pnx8550_console_port = -1;
-
-void __init plat_mem_setup(void)
-{
-        int i;
-        char* argptr;
-
-        board_setup();  /* board specific setup */
-
-        _machine_restart = pnx8550_machine_restart;
-        _machine_halt = pnx8550_machine_halt;
-        pm_power_off = pnx8550_machine_power_off;
-
-        /* Clear the Global 2 Register, PCI Inta Output Enable Registers
-           Bit 1:Enable DAC Powerdown
-          -> 0:DACs are enabled and are working normally
-             1:DACs are powerdown
-           Bit 0:Enable of PCI inta output
-          -> 0 = Disable PCI inta output
-             1 = Enable PCI inta output
-        */
-        PNX8550_GLB2_ENAB_INTA_O = 0;
-
-        /* IO/MEM resources. */
-        set_io_port_base(PNX8550_PORT_BASE);
-        ioport_resource.start = 0;
-        ioport_resource.end = ~0;
-        iomem_resource.start = 0;
-        iomem_resource.end = ~0;
-
-        /* Request I/O space for devices on this board */
-        for (i = 0; i < STANDARD_IO_RESOURCES; i++)
-                request_resource(&ioport_resource, standard_io_resources + i);
-
-        /* Place the Mode Control bit for GPIO pin 16 in primary function */
-        /* Pin 16 is used by UART1, UA1_TX                                */
-        outl((PNX8550_GPIO_MODE_PRIMOP << PNX8550_GPIO_MC_16_BIT) |
-                        (PNX8550_GPIO_MODE_PRIMOP << PNX8550_GPIO_MC_17_BIT),
-                        PNX8550_GPIO_MC1);
-
-        argptr = prom_getcmdline();
-        if ((argptr = strstr(argptr, "console=ttyS")) != NULL) {
-                argptr += strlen("console=ttyS");
-                pnx8550_console_port = *argptr == '0' ? 0 : 1;
-
-                /* We must initialize the UART (console) before early printk */
-                /* Set LCR to 8-bit and BAUD to 38400 (no 5)                */
-                ip3106_lcr(UART_BASE, pnx8550_console_port) =
-                        PNX8XXX_UART_LCR_8BIT;
-                ip3106_baud(UART_BASE, pnx8550_console_port) = 5;
-        }
-}
diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c
index 4ee57104e47b..b5ce041cdafb 100644
--- a/arch/mips/pci/pci-alchemy.c
+++ b/arch/mips/pci/pci-alchemy.c
@@ -7,6 +7,7 @@
  * Support for all devices (greater than 16) added by David Gathright.
  */
 
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 8656388b34bd..be1e1afe12c3 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <linux/export.h>
 #include <linux/platform_device.h>
 
 #include <asm/pci.h>
diff --git a/arch/mips/pmc-sierra/yosemite/prom.c b/arch/mips/pmc-sierra/yosemite/prom.c
index cf4c868715ac..dcc926e06fce 100644
--- a/arch/mips/pmc-sierra/yosemite/prom.c
+++ b/arch/mips/pmc-sierra/yosemite/prom.c
@@ -102,7 +102,7 @@ void __init prom_init(void)
 
         /* Get the boot parameters */
         for (i = 1; i < argc; i++) {
-                if (strlen(arcs_cmdline) + strlen(arg[i] + 1) >=
+                if (strlen(arcs_cmdline) + strlen(arg[i]) + 1 >=
                     sizeof(arcs_cmdline))
                         break;
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b177caa56d95..951e18f5335b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -345,7 +345,7 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
 
 config KEXEC
         bool "kexec system call (EXPERIMENTAL)"
-        depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP && !47x)) && EXPERIMENTAL
+        depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP && !PPC_47x)) && EXPERIMENTAL
         help
           kexec is a system call that implements the ability to shutdown your
           current kernel, and to start another kernel.  It is like a reboot
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 57af16edc192..70ba0c0a1223 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -255,12 +255,6 @@ checkbin:
                 echo 'disable kernel modules' ; \
                 false ; \
         fi
-        @if ! /bin/echo dssall | $(AS) -many -o $(TOUT) >/dev/null 2>&1 ; then \
-                echo -n '*** ${VERSION}.${PATCHLEVEL} kernels no longer build ' ; \
-                echo 'correctly with old versions of binutils.' ; \
-                echo '*** Please upgrade your binutils to 2.12.1 or newer' ; \
-                false ; \
-        fi
 
 CLEAN_FILES += $(TOUT)
 
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index e2a4c26ad377..02e41b53488d 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -49,13 +49,13 @@ static __inline__ int atomic_add_return(int a, atomic_t *v)
         int t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %0,0,%2         # atomic_add_return\n\
         add     %0,%1,%0\n"
         PPC405_ERR77(0,%2)
 "       stwcx.  %0,0,%2 \n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         : "=&r" (t)
         : "r" (a), "r" (&v->counter)
         : "cc", "memory");
@@ -85,13 +85,13 @@ static __inline__ int atomic_sub_return(int a, atomic_t *v)
         int t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %0,0,%2         # atomic_sub_return\n\
         subf    %0,%1,%0\n"
         PPC405_ERR77(0,%2)
 "       stwcx.  %0,0,%2 \n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         : "=&r" (t)
         : "r" (a), "r" (&v->counter)
         : "cc", "memory");
@@ -119,13 +119,13 @@ static __inline__ int atomic_inc_return(atomic_t *v)
         int t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %0,0,%1         # atomic_inc_return\n\
         addic   %0,%0,1\n"
         PPC405_ERR77(0,%1)
 "       stwcx.  %0,0,%1 \n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         : "=&r" (t)
         : "r" (&v->counter)
         : "cc", "xer", "memory");
@@ -163,13 +163,13 @@ static __inline__ int atomic_dec_return(atomic_t *v)
         int t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %0,0,%1         # atomic_dec_return\n\
         addic   %0,%0,-1\n"
         PPC405_ERR77(0,%1)
 "       stwcx.  %0,0,%1\n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         : "=&r" (t)
         : "r" (&v->counter)
         : "cc", "xer", "memory");
@@ -194,7 +194,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
         int t;
 
         __asm__ __volatile__ (
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %0,0,%1         # __atomic_add_unless\n\
         cmpw    0,%0,%3 \n\
         beq-    2f \n\
@@ -202,7 +202,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
         PPC405_ERR77(0,%2)
 "       stwcx.  %0,0,%1 \n\
         bne-    1b \n"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
 "       subf    %0,%2,%0 \n\
 2:"
         : "=&r" (t)
@@ -226,7 +226,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
         int t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %0,0,%1         # atomic_dec_if_positive\n\
         cmpwi   %0,1\n\
         addi    %0,%0,-1\n\
@@ -234,7 +234,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
         PPC405_ERR77(0,%1)
 "       stwcx.  %0,0,%1\n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         "\n\
 2:"     : "=&b" (t)
         : "r" (&v->counter)
@@ -285,12 +285,12 @@ static __inline__ long atomic64_add_return(long a, atomic64_t *v)
         long t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     ldarx   %0,0,%2         # atomic64_add_return\n\
         add     %0,%1,%0\n\
         stdcx.  %0,0,%2 \n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         : "=&r" (t)
         : "r" (a), "r" (&v->counter)
         : "cc", "memory");
@@ -319,12 +319,12 @@ static __inline__ long atomic64_sub_return(long a, atomic64_t *v)
         long t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     ldarx   %0,0,%2         # atomic64_sub_return\n\
         subf    %0,%1,%0\n\
         stdcx.  %0,0,%2 \n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         : "=&r" (t)
         : "r" (a), "r" (&v->counter)
         : "cc", "memory");
@@ -351,12 +351,12 @@ static __inline__ long atomic64_inc_return(atomic64_t *v)
         long t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     ldarx   %0,0,%1         # atomic64_inc_return\n\
         addic   %0,%0,1\n\
         stdcx.  %0,0,%1 \n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         : "=&r" (t)
         : "r" (&v->counter)
         : "cc", "xer", "memory");
@@ -393,12 +393,12 @@ static __inline__ long atomic64_dec_return(atomic64_t *v)
         long t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     ldarx   %0,0,%1         # atomic64_dec_return\n\
         addic   %0,%0,-1\n\
         stdcx.  %0,0,%1\n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         : "=&r" (t)
         : "r" (&v->counter)
         : "cc", "xer", "memory");
@@ -418,13 +418,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
         long t;
 
         __asm__ __volatile__(
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     ldarx   %0,0,%1         # atomic64_dec_if_positive\n\
         addic.  %0,%0,-1\n\
         blt-    2f\n\
         stdcx.  %0,0,%1\n\
         bne-    1b"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
         "\n\
 2:"     : "=&r" (t)
         : "r" (&v->counter)
@@ -450,14 +450,14 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
         long t;
 
         __asm__ __volatile__ (
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     ldarx   %0,0,%1         # __atomic_add_unless\n\
         cmpd    0,%0,%3 \n\
         beq-    2f \n\
         add     %0,%2,%0 \n"
 "       stdcx.  %0,0,%1 \n\
         bne-    1b \n"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
 "       subf    %0,%2,%0 \n\
 2:"
         : "=&r" (t)
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index e137afcc10fa..efdc92618b38 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -124,14 +124,14 @@ static __inline__ unsigned long fn(			\
         return (old & mask);                            \
 }
 
-DEFINE_TESTOP(test_and_set_bits, or, PPC_RELEASE_BARRIER,
-              PPC_ACQUIRE_BARRIER, 0)
+DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER,
+              PPC_ATOMIC_EXIT_BARRIER, 0)
 DEFINE_TESTOP(test_and_set_bits_lock, or, "",
               PPC_ACQUIRE_BARRIER, 1)
-DEFINE_TESTOP(test_and_clear_bits, andc, PPC_RELEASE_BARRIER,
-              PPC_ACQUIRE_BARRIER, 0)
-DEFINE_TESTOP(test_and_change_bits, xor, PPC_RELEASE_BARRIER,
-              PPC_ACQUIRE_BARRIER, 0)
+DEFINE_TESTOP(test_and_clear_bits, andc, PPC_ATOMIC_ENTRY_BARRIER,
+              PPC_ATOMIC_EXIT_BARRIER, 0)
+DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER,
+              PPC_ATOMIC_EXIT_BARRIER, 0)
 
 static __inline__ int test_and_set_bit(unsigned long nr,
                                        volatile unsigned long *addr)
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index c94e4a3fe2ef..2a9cf845473b 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -11,12 +11,13 @@
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \
   __asm__ __volatile ( \
-        PPC_RELEASE_BARRIER \
+        PPC_ATOMIC_ENTRY_BARRIER \
 "1:     lwarx   %0,0,%2\n" \
         insn \
         PPC405_ERR77(0, %2) \
 "2:     stwcx.  %1,0,%2\n" \
         "bne-   1b\n" \
+        PPC_ATOMIC_EXIT_BARRIER \
         "li     %1,0\n" \
 "3:     .section .fixup,\"ax\"\n" \
 "4:     li      %1,%3\n" \
@@ -92,14 +93,14 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
                 return -EFAULT;
 
         __asm__ __volatile__ (
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
         cmpw    0,%1,%4\n\
         bne-    3f\n"
         PPC405_ERR77(0,%3)
 "2:     stwcx.  %5,0,%3\n\
         bne-    1b\n"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
 "3:     .section .fixup,\"ax\"\n\
 4:      li      %0,%6\n\
         b       3b\n\
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index 08fe69edcd10..0ad432bc81d6 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -149,12 +149,6 @@ struct kvm_regs {
 #define KVM_SREGS_E_UPDATE_DBSR         (1 << 3)
 
 /*
- * Book3S special bits to indicate contents in the struct by maintaining
- * backwards compatibility with older structs. If adding a new field,
- * please make sure to add a flag for that new field */
-#define KVM_SREGS_S_HIOR                (1 << 0)
-
-/*
  * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a
  * previous KVM_GET_REGS.
  *
@@ -179,8 +173,6 @@ struct kvm_sregs {
                                 __u64 ibat[8]; 
                                 __u64 dbat[8]; 
                         } ppc32;
-                        __u64 flags; /* KVM_SREGS_S_ */
-                        __u64 hior;
                 } s;
                 struct {
                         union {
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index a384ffdf33de..d4df013ad779 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -90,8 +90,6 @@ struct kvmppc_vcpu_book3s {
 #endif
         int context_id[SID_CONTEXTS];
 
-        bool hior_sregs;                /* HIOR is set by SREGS, not PVR */
-
         struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
         struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
         struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 28cdbd9f399c..03c48e819c8e 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -31,7 +31,7 @@
 
 #define MSR_            MSR_ME | MSR_CE
 #define MSR_KERNEL      MSR_ | MSR_64BIT
-#define MSR_USER32      MSR_ | MSR_PR | MSR_EE | MSR_DE
+#define MSR_USER32      MSR_ | MSR_PR | MSR_EE
 #define MSR_USER64      MSR_USER32 | MSR_64BIT
 #elif defined (CONFIG_40x)
 #define MSR_KERNEL      (MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 6fbce725c710..a0f358d4a00c 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -8,7 +8,7 @@
 
 #ifdef __powerpc64__
 
-extern char _end[];
+extern char __end_interrupts[];
 
 static inline int in_kernel_text(unsigned long addr)
 {
diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h
index d7cab44643c5..e682a7143edb 100644
--- a/arch/powerpc/include/asm/synch.h
+++ b/arch/powerpc/include/asm/synch.h
@@ -13,6 +13,7 @@
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
                              void *fixup_end);
+extern void do_final_fixups(void);
 
 static inline void eieio(void)
 {
@@ -41,11 +42,15 @@ static inline void isync(void)
         START_LWSYNC_SECTION(97);                       \
         isync;                                          \
         MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup);
-#define PPC_ACQUIRE_BARRIER     "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
-#define PPC_RELEASE_BARRIER     stringify_in_c(LWSYNC) "\n"
+#define PPC_ACQUIRE_BARRIER      "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
+#define PPC_RELEASE_BARRIER      stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_EXIT_BARRIER  "\n" stringify_in_c(sync) "\n"
 #else
 #define PPC_ACQUIRE_BARRIER
 #define PPC_RELEASE_BARRIER
+#define PPC_ATOMIC_ENTRY_BARRIER
+#define PPC_ATOMIC_EXIT_BARRIER
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 56212bc0ab08..4f80cf1ce77b 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -215,7 +215,22 @@ reenable_mmu:				/* re-enable mmu so we can */
         stw     r9,8(r1)
         stw     r11,12(r1)
         stw     r3,ORIG_GPR3(r1)
+        /*
+         * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
+         * If from user mode there is only one stack frame on the stack, and
+         * accessing CALLER_ADDR1 will cause oops. So we need create a dummy
+         * stack frame to make trace_hardirqs_off happy.
+         */
+        andi.   r12,r12,MSR_PR
+        beq     11f
+        stwu    r1,-16(r1)
+        bl      trace_hardirqs_off
+        addi    r1,r1,16
+        b       12f
+
+11:
         bl      trace_hardirqs_off
+12:
         lwz     r0,GPR0(r1)
         lwz     r3,ORIG_GPR3(r1)
         lwz     r4,GPR4(r1)
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index 368d158d665d..a1ed8a8c7cb4 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <asm/code-patching.h>
 
+#ifdef HAVE_JUMP_LABEL
 void arch_jump_label_transform(struct jump_entry *entry,
                                enum jump_label_type type)
 {
@@ -21,3 +22,4 @@ void arch_jump_label_transform(struct jump_entry *entry,
         else
                 patch_instruction(addr, PPC_INST_NOP);
 }
+#endif
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 35f27646c4ff..2985338d0e10 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -132,7 +132,6 @@ static void kvm_patch_ins_b(u32 *inst, int addr)
         /* On relocatable kernels interrupts handlers and our code
            can be in different regions, so we don't patch them */
 
-        extern u32 __end_interrupts;
         if ((ulong)inst < (ulong)&__end_interrupts)
                 return;
 #endif
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index f7d760ab5ca1..7cd07b42ca1a 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -738,7 +738,7 @@ relocate_new_kernel:
         mr      r5, r31
 
         li      r0, 0
-#elif defined(CONFIG_44x)  && !defined(CONFIG_47x)
+#elif defined(CONFIG_44x)  && !defined(CONFIG_PPC_47x)
 
 /*
  * Code for setting up 1:1 mapping for PPC440x for KEXEC
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9054ca9ab4f9..6457574c0b2f 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -486,28 +486,6 @@ struct task_struct *__switch_to(struct task_struct *prev,
         new_thread = &new->thread;
         old_thread = &current->thread;
 
-#if defined(CONFIG_PPC_BOOK3E_64)
-        /* XXX Current Book3E code doesn't deal with kernel side DBCR0,
-         * we always hold the user values, so we set it now.
-         *
-         * However, we ensure the kernel MSR:DE is appropriately cleared too
-         * to avoid spurrious single step exceptions in the kernel.
-         *
-         * This will have to change to merge with the ppc32 code at some point,
-         * but I don't like much what ppc32 is doing today so there's some
-         * thinking needed there
-         */
-        if ((new_thread->dbcr0 | old_thread->dbcr0) & DBCR0_IDM) {
-                u32 dbcr0;
-
-                mtmsr(mfmsr() & ~MSR_DE);
-                isync();
-                dbcr0 = mfspr(SPRN_DBCR0);
-                dbcr0 = (dbcr0 & DBCR0_EDM) | new_thread->dbcr0;
-                mtspr(SPRN_DBCR0, dbcr0);
-        }
-#endif /* CONFIG_PPC64_BOOK3E */
-
 #ifdef CONFIG_PPC64
         /*
          * Collect processor utilization data per process
@@ -657,7 +635,7 @@ void show_regs(struct pt_regs * regs)
         if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
                 printk("CFAR: "REG"\n", regs->orig_gpr3);
         if (trap == 0x300 || trap == 0x600)
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
                 printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr);
 #else
                 printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr);
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index b4fa66127495..cc584865b3df 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1579,10 +1579,8 @@ static void __init prom_instantiate_rtas(void)
                 return;
 
         base = alloc_down(size, PAGE_SIZE, 0);
-        if (base == 0) {
-                prom_printf("RTAS allocation failed !\n");
-                return;
-        }
+        if (base == 0)
+                prom_panic("Could not allocate memory for RTAS\n");
 
         rtas_inst = call_prom("open", 1, 1, ADDR("/rtas"));
         if (!IHANDLE_VALID(rtas_inst)) {
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index c1ce86357ecb..ac7610815113 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -107,6 +107,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
                          PTRRELOC(&__start___lwsync_fixup),
                          PTRRELOC(&__stop___lwsync_fixup));
 
+        do_final_fixups();
+
         return KERNELBASE + offset;
 }
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 1a9dea80a69b..fb9bb46e7e88 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -359,6 +359,7 @@ void __init setup_system(void)
                           &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
         do_lwsync_fixups(cur_cpu_spec->cpu_features,
                          &__start___lwsync_fixup, &__stop___lwsync_fixup);
+        do_final_fixups();
 
         /*
          * Unflatten the device-tree passed by prom_init or kexec
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 78b76dc54dfb..836a5a19eb2c 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -97,7 +97,7 @@ static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set)
         compat_sigset_t cset;
 
         switch (_NSIG_WORDS) {
-        case 4: cset.sig[5] = set->sig[3] & 0xffffffffull;
+        case 4: cset.sig[6] = set->sig[3] & 0xffffffffull;
                 cset.sig[7] = set->sig[3] >> 32;
         case 3: cset.sig[4] = set->sig[2] & 0xffffffffull;
                 cset.sig[5] = set->sig[2] >> 32;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4e5908264d1a..5459d148a0f6 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1298,14 +1298,12 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 
                 if (user_mode(regs)) {
                         current->thread.dbcr0 &= ~DBCR0_IC;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
                         if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0,
                                                current->thread.dbcr1))
                                 regs->msr |= MSR_DE;
                         else
                                 /* Make sure the IDM bit is off */
                                 current->thread.dbcr0 &= ~DBCR0_IDM;
-#endif
                 }
 
                 _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0cdbc07cec14..0cb137a9b038 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -44,6 +44,7 @@
 #include <asm/processor.h>
 #include <asm/cputhreads.h>
 #include <asm/page.h>
+#include <asm/hvcall.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index bc4d50dec78b..3c791e1eb675 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -151,16 +151,14 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 #ifdef CONFIG_PPC_BOOK3S_64
         if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
                 kvmppc_mmu_book3s_64_init(vcpu);
-                if (!to_book3s(vcpu)->hior_sregs)
-                        to_book3s(vcpu)->hior = 0xfff00000;
+                to_book3s(vcpu)->hior = 0xfff00000;
                 to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
                 vcpu->arch.cpu_type = KVM_CPU_3S_64;
         } else
 #endif
         {
                 kvmppc_mmu_book3s_32_init(vcpu);
-                if (!to_book3s(vcpu)->hior_sregs)
-                        to_book3s(vcpu)->hior = 0;
+                to_book3s(vcpu)->hior = 0;
                 to_book3s(vcpu)->msr_mask = 0xffffffffULL;
                 vcpu->arch.cpu_type = KVM_CPU_3S_32;
         }
@@ -797,9 +795,6 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
                 }
         }
 
-        if (sregs->u.s.flags & KVM_SREGS_S_HIOR)
-                sregs->u.s.hior = to_book3s(vcpu)->hior;
-
         return 0;
 }
 
@@ -836,11 +831,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
         /* Flush the MMU after messing with the segments */
         kvmppc_mmu_pte_flush(vcpu, 0, 0);
 
-        if (sregs->u.s.flags & KVM_SREGS_S_HIOR) {
-                to_book3s(vcpu)->hior_sregs = true;
-                to_book3s(vcpu)->hior = sregs->u.s.hior;
-        }
-
         return 0;
 }
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index efbf9ad87203..607fbdf24b84 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -208,7 +208,6 @@ int kvm_dev_ioctl_check_extension(long ext)
         case KVM_CAP_PPC_BOOKE_SREGS:
 #else
         case KVM_CAP_PPC_SEGSTATE:
-        case KVM_CAP_PPC_HIOR:
         case KVM_CAP_PPC_PAPR:
 #endif
         case KVM_CAP_PPC_UNSET_IRQ:
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 0d08d0171392..7a8a7487cee8 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -18,6 +18,8 @@
 #include <linux/init.h>
 #include <asm/cputable.h>
 #include <asm/code-patching.h>
+#include <asm/page.h>
+#include <asm/sections.h>
 
 
 struct fixup_entry {
@@ -128,6 +130,27 @@ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
         }
 }
 
+void do_final_fixups(void)
+{
+#if defined(CONFIG_PPC64) && defined(CONFIG_RELOCATABLE)
+        int *src, *dest;
+        unsigned long length;
+
+        if (PHYSICAL_START == 0)
+                return;
+
+        src = (int *)(KERNELBASE + PHYSICAL_START);
+        dest = (int *)KERNELBASE;
+        length = (__end_interrupts - _stext) / sizeof(int);
+
+        while (length--) {
+                patch_instruction(dest, *src);
+                src++;
+                dest++;
+        }
+#endif
+}
+
 #ifdef CONFIG_FTR_FIXUP_SELFTEST
 
 #define check(x)        \
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index e4588721ef34..3fe6d927ad70 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -347,7 +347,7 @@ config SIMPLE_GPIO
 
 config MCU_MPC8349EMITX
         bool "MPC8349E-mITX MCU driver"
-        depends on I2C && PPC_83xx
+        depends on I2C=y && PPC_83xx
         select GENERIC_GPIO
         select ARCH_REQUIRE_GPIOLIB
         help
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 404bc52b7806..1d6f4f478fe2 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -88,6 +88,7 @@ struct ps3_private {
         struct ps3_bmp bmp __attribute__ ((aligned (PS3_BMP_MINALIGN)));
         u64 ppe_id;
         u64 thread_id;
+        unsigned long ipi_mask;
 };
 
 static DEFINE_PER_CPU(struct ps3_private, ps3_private);
@@ -144,7 +145,11 @@ static void ps3_chip_unmask(struct irq_data *d)
 static void ps3_chip_eoi(struct irq_data *d)
 {
         const struct ps3_private *pd = irq_data_get_irq_chip_data(d);
-        lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq);
+
+        /* non-IPIs are EOIed here. */
+
+        if (!test_bit(63 - d->irq, &pd->ipi_mask))
+                lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq);
 }
 
 /**
@@ -691,6 +696,16 @@ void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq)
                 cpu, virq, pd->bmp.ipi_debug_brk_mask);
 }
 
+void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq)
+{
+        struct ps3_private *pd = &per_cpu(ps3_private, cpu);
+
+        set_bit(63 - virq, &pd->ipi_mask);
+
+        DBG("%s:%d: cpu %u, virq %u, ipi_mask %lxh\n", __func__, __LINE__,
+                cpu, virq, pd->ipi_mask);
+}
+
 static unsigned int ps3_get_irq(void)
 {
         struct ps3_private *pd = &__get_cpu_var(ps3_private);
@@ -720,6 +735,12 @@ static unsigned int ps3_get_irq(void)
                 BUG();
         }
 #endif
+
+        /* IPIs are EOIed here. */
+
+        if (test_bit(63 - plug, &pd->ipi_mask))
+                lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, plug);
+
         return plug;
 }
 
diff --git a/arch/powerpc/platforms/ps3/platform.h b/arch/powerpc/platforms/ps3/platform.h
index 9a196a88eda7..1a633ed0fe98 100644
--- a/arch/powerpc/platforms/ps3/platform.h
+++ b/arch/powerpc/platforms/ps3/platform.h
@@ -43,6 +43,7 @@ void ps3_mm_shutdown(void);
 void ps3_init_IRQ(void);
 void ps3_shutdown_IRQ(int cpu);
 void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq);
+void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq);
 
 /* smp */
 
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index 4c44794faac0..efc1cd8c034a 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -59,46 +59,49 @@ static void ps3_smp_message_pass(int cpu, int msg)
 
 static int ps3_smp_probe(void)
 {
-        return 2;
-}
+        int cpu;
 
-static void __init ps3_smp_setup_cpu(int cpu)
-{
-        int result;
-        unsigned int *virqs = per_cpu(ps3_ipi_virqs, cpu);
-        int i;
+        for (cpu = 0; cpu < 2; cpu++) {
+                int result;
+                unsigned int *virqs = per_cpu(ps3_ipi_virqs, cpu);
+                int i;
 
-        DBG(" -> %s:%d: (%d)\n", __func__, __LINE__, cpu);
+                DBG(" -> %s:%d: (%d)\n", __func__, __LINE__, cpu);
 
-        /*
-         * Check assumptions on ps3_ipi_virqs[] indexing. If this
-         * check fails, then a different mapping of PPC_MSG_
-         * to index needs to be setup.
-         */
+                /*
+                * Check assumptions on ps3_ipi_virqs[] indexing. If this
+                * check fails, then a different mapping of PPC_MSG_
+                * to index needs to be setup.
+                */
 
-        BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION    != 0);
-        BUILD_BUG_ON(PPC_MSG_RESCHEDULE       != 1);
-        BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2);
-        BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK   != 3);
+                BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION    != 0);
+                BUILD_BUG_ON(PPC_MSG_RESCHEDULE       != 1);
+                BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2);
+                BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK   != 3);
 
-        for (i = 0; i < MSG_COUNT; i++) {
-                result = ps3_event_receive_port_setup(cpu, &virqs[i]);
+                for (i = 0; i < MSG_COUNT; i++) {
+                        result = ps3_event_receive_port_setup(cpu, &virqs[i]);
 
-                if (result)
-                        continue;
+                        if (result)
+                                continue;
 
-                DBG("%s:%d: (%d, %d) => virq %u\n",
-                        __func__, __LINE__, cpu, i, virqs[i]);
+                        DBG("%s:%d: (%d, %d) => virq %u\n",
+                                __func__, __LINE__, cpu, i, virqs[i]);
 
-                result = smp_request_message_ipi(virqs[i], i);
+                        result = smp_request_message_ipi(virqs[i], i);
 
-                if (result)
-                        virqs[i] = NO_IRQ;
-        }
+                        if (result)
+                                virqs[i] = NO_IRQ;
+                        else
+                                ps3_register_ipi_irq(cpu, virqs[i]);
+                }
 
-        ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
+                ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
 
-        DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
+                DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
+        }
+
+        return 2;
 }
 
 void ps3_smp_cleanup_cpu(int cpu)
@@ -121,7 +124,6 @@ static struct smp_ops_t ps3_smp_ops = {
         .probe          = ps3_smp_probe,
         .message_pass   = ps3_smp_message_pass,
         .kick_cpu       = smp_generic_kick_cpu,
-        .setup_cpu      = ps3_smp_setup_cpu,
 };
 
 void smp_init_ps3(void)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a9fbd43395f7..373679b3744a 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -572,6 +572,7 @@ config KEXEC
 config CRASH_DUMP
         bool "kernel crash dumps"
         depends on 64BIT
+        select KEXEC
         help
           Generate crash dump after being started by kexec.
           Crash dump kernels are loaded in the main kernel with kexec-tools
diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h
index 49676771bd66..ffd1ac255f19 100644
--- a/arch/s390/crypto/crypt_s390.h
+++ b/arch/s390/crypto/crypt_s390.h
@@ -368,9 +368,12 @@ static inline int crypt_s390_func_available(int func,
 
         if (facility_mask & CRYPT_S390_MSA && !test_facility(17))
                 return 0;
-        if (facility_mask & CRYPT_S390_MSA3 && !test_facility(76))
+
+        if (facility_mask & CRYPT_S390_MSA3 &&
+            (!test_facility(2) || !test_facility(76)))
                 return 0;
-        if (facility_mask & CRYPT_S390_MSA4 && !test_facility(77))
+        if (facility_mask & CRYPT_S390_MSA4 &&
+            (!test_facility(2) || !test_facility(77)))
                 return 0;
 
         switch (func & CRYPT_S390_OP_MASK) {
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 24e18473d926..b0c235cb6ad5 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -47,7 +47,7 @@ struct sca_block {
 #define KVM_HPAGE_MASK(x)       (~(KVM_HPAGE_SIZE(x) - 1))
 #define KVM_PAGES_PER_HPAGE(x)  (KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
-#define CPUSTAT_HOST       0x80000000
+#define CPUSTAT_STOPPED    0x80000000
 #define CPUSTAT_WAIT       0x10000000
 #define CPUSTAT_ECALL_PEND 0x08000000
 #define CPUSTAT_STOP_INT   0x04000000
@@ -139,6 +139,7 @@ struct kvm_vcpu_stat {
         u32 instruction_stfl;
         u32 instruction_tprot;
         u32 instruction_sigp_sense;
+        u32 instruction_sigp_sense_running;
         u32 instruction_sigp_external_call;
         u32 instruction_sigp_emergency;
         u32 instruction_sigp_stop;
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 34ede0ea85a9..524d23b8610c 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -593,6 +593,8 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
         unsigned long address, bits;
         unsigned char skey;
 
+        if (!pte_present(*ptep))
+                return pgste;
         address = pte_val(*ptep) & PAGE_MASK;
         skey = page_get_storage_key(address);
         bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
@@ -625,6 +627,8 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 #ifdef CONFIG_PGSTE
         int young;
 
+        if (!pte_present(*ptep))
+                return pgste;
         young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
         /* Transfer page referenced bit to pte software bit (host view) */
         if (young || (pgste_val(pgste) & RCP_HR_BIT))
@@ -638,13 +642,15 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 
 }
 
-static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
+static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 {
 #ifdef CONFIG_PGSTE
         unsigned long address;
         unsigned long okey, nkey;
 
-        address = pte_val(*ptep) & PAGE_MASK;
+        if (!pte_present(entry))
+                return;
+        address = pte_val(entry) & PAGE_MASK;
         okey = nkey = page_get_storage_key(address);
         nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT);
         /* Set page access key and fetch protection bit from pgste */
@@ -712,7 +718,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
         if (mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
-                pgste_set_pte(ptep, pgste);
+                pgste_set_pte(ptep, pgste, entry);
                 *ptep = entry;
                 pgste_set_unlock(ptep, pgste);
         } else
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 5a099714df04..097183c70407 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -82,6 +82,7 @@ extern unsigned int user_mode;
 #define MACHINE_FLAG_LPAR       (1UL << 12)
 #define MACHINE_FLAG_SPP        (1UL << 13)
 #define MACHINE_FLAG_TOPOLOGY   (1UL << 14)
+#define MACHINE_FLAG_STCKF      (1UL << 15)
 
 #define MACHINE_IS_VM           (S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM          (S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -100,6 +101,7 @@ extern unsigned int user_mode;
 #define MACHINE_HAS_PFMF        (0)
 #define MACHINE_HAS_SPP         (0)
 #define MACHINE_HAS_TOPOLOGY    (0)
+#define MACHINE_HAS_STCKF       (0)
 #else /* __s390x__ */
 #define MACHINE_HAS_IEEE        (1)
 #define MACHINE_HAS_CSP         (1)
@@ -111,6 +113,7 @@ extern unsigned int user_mode;
 #define MACHINE_HAS_PFMF        (S390_lowcore.machine_flags & MACHINE_FLAG_PFMF)
 #define MACHINE_HAS_SPP         (S390_lowcore.machine_flags & MACHINE_FLAG_SPP)
 #define MACHINE_HAS_TOPOLOGY    (S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
+#define MACHINE_HAS_STCKF       (S390_lowcore.machine_flags & MACHINE_FLAG_STCKF)
 #endif /* __s390x__ */
 
 #define ZFCPDUMP_HSA_SIZE       (32UL<<20)
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index d610bef9c5e9..c447a27a7fdb 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -90,7 +90,7 @@ static inline unsigned long long get_clock_fast(void)
 {
         unsigned long long clk;
 
-        if (test_facility(25))
+        if (MACHINE_HAS_STCKF)
                 asm volatile(".insn     s,0xb27c0000,%0" : "=Q" (clk) : : "cc");
         else
                 clk = get_clock();
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 404bdb9671b4..58de4c91c333 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -277,7 +277,9 @@
 #define __NR_clock_adjtime      337
 #define __NR_syncfs             338
 #define __NR_setns              339
-#define NR_syscalls 340
+#define __NR_process_vm_readv   340
+#define __NR_process_vm_writev  341
+#define NR_syscalls 342
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 5006a1d9f5d0..18c51df9fe06 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1627,3 +1627,23 @@ ENTRY(sys_setns_wrapper)
         lgfr    %r2,%r2                 # int
         lgfr    %r3,%r3                 # int
         jg      sys_setns
+
+ENTRY(compat_sys_process_vm_readv_wrapper)
+        lgfr    %r2,%r2                 # compat_pid_t
+        llgtr   %r3,%r3                 # struct compat_iovec __user *
+        llgfr   %r4,%r4                 # unsigned long
+        llgtr   %r5,%r5                 # struct compat_iovec __user *
+        llgfr   %r6,%r6                 # unsigned long
+        llgf    %r0,164(%r15)           # unsigned long
+        stg     %r0,160(%r15)
+        jg      sys_process_vm_readv
+
+ENTRY(compat_sys_process_vm_writev_wrapper)
+        lgfr    %r2,%r2                 # compat_pid_t
+        llgtr   %r3,%r3                 # struct compat_iovec __user *
+        llgfr   %r4,%r4                 # unsigned long
+        llgtr   %r5,%r5                 # struct compat_iovec __user *
+        llgfr   %r6,%r6                 # unsigned long
+        llgf    %r0,164(%r15)           # unsigned long
+        stg     %r0,160(%r15)
+        jg      sys_process_vm_writev
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 37394b3413e2..c9ffe0025197 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -390,6 +390,8 @@ static __init void detect_machine_facilities(void)
                 S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS;
         if (test_facility(40))
                 S390_lowcore.machine_flags |= MACHINE_FLAG_SPP;
+        if (test_facility(25))
+                S390_lowcore.machine_flags |= MACHINE_FLAG_STCKF;
 #endif
 }
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 8ac6bfa2786c..e58a462949b1 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -211,6 +211,8 @@ static void __init setup_zfcpdump(unsigned int console_devno)
 
         if (ipl_info.type != IPL_TYPE_FCP_DUMP)
                 return;
+        if (OLDMEM_BASE)
+                return;
         if (console_devno != -1)
                 sprintf(str, " cio_ignore=all,!0.0.%04x,!0.0.%04x",
                         ipl_info.data.fcp.dev_id.devno, console_devno);
@@ -482,7 +484,7 @@ static void __init setup_memory_end(void)
 
 
 #ifdef CONFIG_ZFCPDUMP
-        if (ipl_info.type == IPL_TYPE_FCP_DUMP) {
+        if (ipl_info.type == IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) {
                 memory_end = ZFCPDUMP_HSA_SIZE;
                 memory_end_set = 1;
         }
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 73eb08c874fb..bcab2f04ba58 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -348,3 +348,5 @@ SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at
 SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper)
 SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper)
 SYSCALL(sys_setns,sys_setns,sys_setns_wrapper)
+SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */
+SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper)
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 77b8942b9a15..fdb5b8cb260f 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -68,8 +68,10 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
         return mask;
 }
 
-static void add_cpus_to_mask(struct topology_cpu *tl_cpu,
-                             struct mask_info *book, struct mask_info *core)
+static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
+                                          struct mask_info *book,
+                                          struct mask_info *core,
+                                          int z10)
 {
         unsigned int cpu;
 
@@ -88,10 +90,16 @@ static void add_cpus_to_mask(struct topology_cpu *tl_cpu,
                         cpu_book_id[lcpu] = book->id;
 #endif
                         cpumask_set_cpu(lcpu, &core->mask);
-                        cpu_core_id[lcpu] = core->id;
+                        if (z10) {
+                                cpu_core_id[lcpu] = rcpu;
+                                core = core->next;
+                        } else {
+                                cpu_core_id[lcpu] = core->id;
+                        }
                         smp_cpu_polarization[lcpu] = tl_cpu->pp;
                 }
         }
+        return core;
 }
 
 static void clear_masks(void)
@@ -123,18 +131,41 @@ static void tl_to_cores(struct sysinfo_15_1_x *info)
 {
 #ifdef CONFIG_SCHED_BOOK
         struct mask_info *book = &book_info;
+        struct cpuid cpu_id;
 #else
         struct mask_info *book = NULL;
 #endif
         struct mask_info *core = &core_info;
         union topology_entry *tle, *end;
+        int z10 = 0;
 
-
+#ifdef CONFIG_SCHED_BOOK
+        get_cpu_id(&cpu_id);
+        z10 = cpu_id.machine == 0x2097 || cpu_id.machine == 0x2098;
+#endif
         spin_lock_irq(&topology_lock);
         clear_masks();
         tle = info->tle;
         end = (union topology_entry *)((unsigned long)info + info->length);
         while (tle < end) {
+#ifdef CONFIG_SCHED_BOOK
+                if (z10) {
+                        switch (tle->nl) {
+                        case 1:
+                                book = book->next;
+                                book->id = tle->container.id;
+                                break;
+                        case 0:
+                                core = add_cpus_to_mask(&tle->cpu, book, core, z10);
+                                break;
+                        default:
+                                clear_masks();
+                                goto out;
+                        }
+                        tle = next_tle(tle);
+                        continue;
+                }
+#endif
                 switch (tle->nl) {
 #ifdef CONFIG_SCHED_BOOK
                 case 2:
@@ -147,7 +178,7 @@ static void tl_to_cores(struct sysinfo_15_1_x *info)
                         core->id = tle->container.id;
                         break;
                 case 0:
-                        add_cpus_to_mask(&tle->cpu, book, core);
+                        add_cpus_to_mask(&tle->cpu, book, core, z10);
                         break;
                 default:
                         clear_masks();
@@ -328,8 +359,8 @@ void __init s390_init_cpu_topology(void)
         for (i = 0; i < TOPOLOGY_NR_MAG; i++)
                 printk(" %d", info->mag[i]);
         printk(" / %d\n", info->mnest);
-        alloc_masks(info, &core_info, 2);
+        alloc_masks(info, &core_info, 1);
 #ifdef CONFIG_SCHED_BOOK
-        alloc_masks(info, &book_info, 3);
+        alloc_masks(info, &book_info, 2);
 #endif
 }
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 56fe6bc81fee..e4c79ebb40e6 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -43,6 +43,8 @@ SECTIONS
 
         NOTES :text :note
 
+        .dummy : { *(.dummy) } :data
+
         RODATA
 
 #ifdef CONFIG_SHARED_KERNEL
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 87cedd61be04..8943e82cd4d9 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -70,7 +70,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
                 return -EOPNOTSUPP;
         }
 
-        atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+        atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
         vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
         vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
         vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index c7c51898984e..02434543eabb 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -132,7 +132,6 @@ static int handle_stop(struct kvm_vcpu *vcpu)
         int rc = 0;
 
         vcpu->stat.exit_stop_request++;
-        atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
         spin_lock_bh(&vcpu->arch.local_int.lock);
         if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
                 vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
@@ -149,6 +148,8 @@ static int handle_stop(struct kvm_vcpu *vcpu)
         }
 
         if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
+                atomic_set_mask(CPUSTAT_STOPPED,
+                                &vcpu->arch.sie_block->cpuflags);
                 vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
                 VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
                 rc = -EOPNOTSUPP;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 87c16705b381..278ee009ce65 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -252,6 +252,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
                         offsetof(struct _lowcore, restart_psw), sizeof(psw_t));
                 if (rc == -EFAULT)
                         exception = 1;
+                atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
                 break;
 
         case KVM_S390_PROGRAM_INT:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0bd3bea1e4cd..d1c445732451 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -65,6 +65,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
         { "instruction_stfl", VCPU_STAT(instruction_stfl) },
         { "instruction_tprot", VCPU_STAT(instruction_tprot) },
         { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
+        { "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
         { "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
         { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
         { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
@@ -127,6 +128,7 @@ int kvm_dev_ioctl_check_extension(long ext)
         switch (ext) {
         case KVM_CAP_S390_PSW:
         case KVM_CAP_S390_GMAP:
+        case KVM_CAP_SYNC_MMU:
                 r = 1;
                 break;
         default:
@@ -270,10 +272,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
         restore_fp_regs(&vcpu->arch.guest_fpregs);
         restore_access_regs(vcpu->arch.guest_acrs);
         gmap_enable(vcpu->arch.gmap);
+        atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+        atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
         gmap_disable(vcpu->arch.gmap);
         save_fp_regs(&vcpu->arch.guest_fpregs);
         save_access_regs(vcpu->arch.guest_acrs);
@@ -301,7 +305,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-        atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM);
+        atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
+                                                    CPUSTAT_SM |
+                                                    CPUSTAT_STOPPED);
         vcpu->arch.sie_block->ecb   = 6;
         vcpu->arch.sie_block->eca   = 0xC1002001U;
         vcpu->arch.sie_block->fac   = (int) (long) facilities;
@@ -428,7 +434,7 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
 {
         int rc = 0;
 
-        if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
+        if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
                 rc = -EBUSY;
         else {
                 vcpu->run->psw_mask = psw.mask;
@@ -501,7 +507,7 @@ rerun_vcpu:
         if (vcpu->sigset_active)
                 sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
-        atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+        atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 
         BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
 
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 391626361084..d02638959922 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -336,6 +336,7 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
         u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
         u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
         struct vm_area_struct *vma;
+        unsigned long user_address;
 
         vcpu->stat.instruction_tprot++;
 
@@ -349,9 +350,14 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
                 return -EOPNOTSUPP;
 
 
+        /* we must resolve the address without holding the mmap semaphore.
+         * This is ok since the userspace hypervisor is not supposed to change
+         * the mapping while the guest queries the memory. Otherwise the guest
+         * might crash or get wrong info anyway. */
+        user_address = (unsigned long) __guestaddr_to_user(vcpu, address1);
+
         down_read(&current->mm->mmap_sem);
-        vma = find_vma(current->mm,
-                        (unsigned long) __guestaddr_to_user(vcpu, address1));
+        vma = find_vma(current->mm, user_address);
         if (!vma) {
                 up_read(&current->mm->mmap_sem);
                 return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index f815118835f3..0a7941d74bc6 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -31,9 +31,11 @@
 #define SIGP_SET_PREFIX        0x0d
 #define SIGP_STORE_STATUS_ADDR 0x0e
 #define SIGP_SET_ARCH          0x12
+#define SIGP_SENSE_RUNNING     0x15
 
 /* cpu status bits */
 #define SIGP_STAT_EQUIPMENT_CHECK   0x80000000UL
+#define SIGP_STAT_NOT_RUNNING       0x00000400UL
 #define SIGP_STAT_INCORRECT_STATE   0x00000200UL
 #define SIGP_STAT_INVALID_PARAMETER 0x00000100UL
 #define SIGP_STAT_EXT_CALL_PENDING  0x00000080UL
@@ -57,8 +59,8 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
         spin_lock(&fi->lock);
         if (fi->local_int[cpu_addr] == NULL)
                 rc = 3; /* not operational */
-        else if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
-                 & CPUSTAT_RUNNING) {
+        else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags)
+                  & CPUSTAT_STOPPED)) {
                 *reg &= 0xffffffff00000000UL;
                 rc = 1; /* status stored */
         } else {
@@ -251,7 +253,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 
         spin_lock_bh(&li->lock);
         /* cpu must be in stopped state */
-        if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+        if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
                 rc = 1; /* incorrect state */
                 *reg &= SIGP_STAT_INCORRECT_STATE;
                 kfree(inti);
@@ -275,6 +277,38 @@ out_fi:
         return rc;
 }
 
+static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
+                                unsigned long *reg)
+{
+        int rc;
+        struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+
+        if (cpu_addr >= KVM_MAX_VCPUS)
+                return 3; /* not operational */
+
+        spin_lock(&fi->lock);
+        if (fi->local_int[cpu_addr] == NULL)
+                rc = 3; /* not operational */
+        else {
+                if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+                    & CPUSTAT_RUNNING) {
+                        /* running */
+                        rc = 1;
+                } else {
+                        /* not running */
+                        *reg &= 0xffffffff00000000UL;
+                        *reg |= SIGP_STAT_NOT_RUNNING;
+                        rc = 0;
+                }
+        }
+        spin_unlock(&fi->lock);
+
+        VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr,
+                   rc);
+
+        return rc;
+}
+
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
         int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
@@ -331,6 +365,11 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
                 rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
                                        &vcpu->arch.guest_gprs[r1]);
                 break;
+        case SIGP_SENSE_RUNNING:
+                vcpu->stat.instruction_sigp_sense_running++;
+                rc = __sigp_sense_running(vcpu, cpu_addr,
+                                          &vcpu->arch.guest_gprs[r1]);
+                break;
         case SIGP_RESTART:
                 vcpu->stat.instruction_sigp_restart++;
                 /* user space must know about restart */
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 1766def5bc3f..a9a301866b3c 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -587,8 +587,13 @@ static void pfault_interrupt(unsigned int ext_int_code,
                 } else {
                         /* Completion interrupt was faster than initial
                          * interrupt. Set pfault_wait to -1 so the initial
-                         * interrupt doesn't put the task to sleep. */
-                        tsk->thread.pfault_wait = -1;
+                         * interrupt doesn't put the task to sleep.
+                         * If the task is not running, ignore the completion
+                         * interrupt since it must be a leftover of a PFAULT
+                         * CANCEL operation which didn't remove all pending
+                         * completion interrupts. */
+                        if (tsk->state == TASK_RUNNING)
+                                tsk->thread.pfault_wait = -1;
                 }
                 put_task_struct(tsk);
         } else {
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 5b31a8e89823..a790cc657476 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -431,10 +431,6 @@ extern unsigned long *sparc_valid_addr_bitmap;
 #define kern_addr_valid(addr) \
         (test_bit(__pa((unsigned long)(addr))>>20, sparc_valid_addr_bitmap))
 
-extern int io_remap_pfn_range(struct vm_area_struct *vma,
-                              unsigned long from, unsigned long pfn,
-                              unsigned long size, pgprot_t prot);
-
 /*
  * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
  * its high 4 bits.  These macros/functions put it there or get it from there.
@@ -443,6 +439,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma,
 #define GET_IOSPACE(pfn)                (pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)                    (pfn & 0x0fffffffUL)
 
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+                           unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+                                     unsigned long from, unsigned long pfn,
+                                     unsigned long size, pgprot_t prot)
+{
+        unsigned long long offset, space, phys_base;
+
+        offset = ((unsigned long long) GET_PFN(pfn)) << PAGE_SHIFT;
+        space = GET_IOSPACE(pfn);
+        phys_base = offset | (space << 32ULL);
+
+        return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
 ({                                                                        \
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index adf89329af59..38ebb2c60137 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -757,10 +757,6 @@ static inline bool kern_addr_valid(unsigned long addr)
 
 extern int page_in_phys_avail(unsigned long paddr);
 
-extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-                               unsigned long pfn,
-                               unsigned long size, pgprot_t prot);
-
 /*
  * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
  * its high 4 bits.  These macros/functions put it there or get it from there.
@@ -769,6 +765,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 #define GET_IOSPACE(pfn)                (pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)                    (pfn & 0x0fffffffffffffffUL)
 
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+                           unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+                                     unsigned long from, unsigned long pfn,
+                                     unsigned long size, pgprot_t prot)
+{
+        unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
+        int space = GET_IOSPACE(pfn);
+        unsigned long phys_base;
+
+        phys_base = offset | (((unsigned long) space) << 32UL);
+
+        return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
 #include <asm-generic/pgtable.h>
 
 /* We provide our own get_unmapped_area to cope with VA holes and
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index e27f8ea8656e..0c218e4c0881 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -42,6 +42,9 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 extern void fpload(unsigned long *fpregs, unsigned long *fsr);
 
 #else /* CONFIG_SPARC32 */
+
+#include <asm/trap_block.h>
+
 struct popc_3insn_patch_entry {
         unsigned int    addr;
         unsigned int    insns[3];
@@ -57,6 +60,10 @@ extern struct popc_6insn_patch_entry __popc_6insn_patch,
         __popc_6insn_patch_end;
 
 extern void __init per_cpu_patch(void);
+extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
+                                    struct sun4v_1insn_patch_entry *);
+extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+                                    struct sun4v_2insn_patch_entry *);
 extern void __init sun4v_patch(void);
 extern void __init boot_cpu_id_too_large(int cpu);
 extern unsigned int dcache_parity_tl1_occurred;
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index da0c6c70ccb2..e5519870c3d9 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -17,6 +17,8 @@
 #include <asm/processor.h>
 #include <asm/spitfire.h>
 
+#include "entry.h"
+
 #ifdef CONFIG_SPARC64
 
 #include <linux/jump_label.h>
@@ -203,6 +205,29 @@ int apply_relocate_add(Elf_Shdr *sechdrs,
 }
 
 #ifdef CONFIG_SPARC64
+static void do_patch_sections(const Elf_Ehdr *hdr,
+                              const Elf_Shdr *sechdrs)
+{
+        const Elf_Shdr *s, *sun4v_1insn = NULL, *sun4v_2insn = NULL;
+        char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+        for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+                if (!strcmp(".sun4v_1insn_patch", secstrings + s->sh_name))
+                        sun4v_1insn = s;
+                if (!strcmp(".sun4v_2insn_patch", secstrings + s->sh_name))
+                        sun4v_2insn = s;
+        }
+
+        if (sun4v_1insn && tlb_type == hypervisor) {
+                void *p = (void *) sun4v_1insn->sh_addr;
+                sun4v_patch_1insn_range(p, p + sun4v_1insn->sh_size);
+        }
+        if (sun4v_2insn && tlb_type == hypervisor) {
+                void *p = (void *) sun4v_2insn->sh_addr;
+                sun4v_patch_2insn_range(p, p + sun4v_2insn->sh_size);
+        }
+}
+
 int module_finalize(const Elf_Ehdr *hdr,
                     const Elf_Shdr *sechdrs,
                     struct module *me)
@@ -210,6 +235,8 @@ int module_finalize(const Elf_Ehdr *hdr,
         /* make jump label nops */
         jump_label_apply_nops(me);
 
+        do_patch_sections(hdr, sechdrs);
+
         /* Cheetah's I-cache is fully coherent.  */
         if (tlb_type == spitfire) {
                 unsigned long va;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c965595aa7e9..a854a1c240ff 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -234,40 +234,50 @@ void __init per_cpu_patch(void)
         }
 }
 
-void __init sun4v_patch(void)
+void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *start,
+                             struct sun4v_1insn_patch_entry *end)
 {
-        extern void sun4v_hvapi_init(void);
-        struct sun4v_1insn_patch_entry *p1;
-        struct sun4v_2insn_patch_entry *p2;
-
-        if (tlb_type != hypervisor)
-                return;
+        while (start < end) {
+                unsigned long addr = start->addr;
 
-        p1 = &__sun4v_1insn_patch;
-        while (p1 < &__sun4v_1insn_patch_end) {
-                unsigned long addr = p1->addr;
-
-                *(unsigned int *) (addr +  0) = p1->insn;
+                *(unsigned int *) (addr +  0) = start->insn;
                 wmb();
                 __asm__ __volatile__("flush     %0" : : "r" (addr +  0));
 
-                p1++;
+                start++;
         }
+}
 
-        p2 = &__sun4v_2insn_patch;
-        while (p2 < &__sun4v_2insn_patch_end) {
-                unsigned long addr = p2->addr;
+void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+                             struct sun4v_2insn_patch_entry *end)
+{
+        while (start < end) {
+                unsigned long addr = start->addr;
 
-                *(unsigned int *) (addr +  0) = p2->insns[0];
+                *(unsigned int *) (addr +  0) = start->insns[0];
                 wmb();
                 __asm__ __volatile__("flush     %0" : : "r" (addr +  0));
 
-                *(unsigned int *) (addr +  4) = p2->insns[1];
+                *(unsigned int *) (addr +  4) = start->insns[1];
                 wmb();
                 __asm__ __volatile__("flush     %0" : : "r" (addr +  4));
 
-                p2++;
+                start++;
         }
+}
+
+void __init sun4v_patch(void)
+{
+        extern void sun4v_hvapi_init(void);
+
+        if (tlb_type != hypervisor)
+                return;
+
+        sun4v_patch_1insn_range(&__sun4v_1insn_patch,
+                                &__sun4v_1insn_patch_end);
+
+        sun4v_patch_2insn_range(&__sun4v_2insn_patch,
+                                &__sun4v_2insn_patch_end);
 
         sun4v_hvapi_init();
 }
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 2caa556db86d..023b8860dc97 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -822,21 +822,23 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-void do_signal32(sigset_t *oldset, struct pt_regs * regs,
-                 int restart_syscall, unsigned long orig_i0)
+void do_signal32(sigset_t *oldset, struct pt_regs * regs)
 {
         struct k_sigaction ka;
+        unsigned long orig_i0;
+        int restart_syscall;
         siginfo_t info;
         int signr;
         
         signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 
-        /* If the debugger messes with the program counter, it clears
-         * the "in syscall" bit, directing us to not perform a syscall
-         * restart.
-         */
-        if (restart_syscall && !pt_regs_is_syscall(regs))
-                restart_syscall = 0;
+        restart_syscall = 0;
+        orig_i0 = 0;
+        if (pt_regs_is_syscall(regs) &&
+            (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+                restart_syscall = 1;
+                orig_i0 = regs->u_regs[UREG_G6];
+        }
 
         if (signr > 0) {
                 if (restart_syscall)
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 8ce247ac04cc..d54c6e53aba0 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -519,10 +519,26 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
         siginfo_t info;
         int signr;
 
+        /* It's a lot of work and synchronization to add a new ptrace
+         * register for GDB to save and restore in order to get
+         * orig_i0 correct for syscall restarts when debugging.
+         *
+         * Although it should be the case that most of the global
+         * registers are volatile across a system call, glibc already
+         * depends upon that fact that we preserve them.  So we can't
+         * just use any global register to save away the orig_i0 value.
+         *
+         * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+         * preserved across a system call trap by various pieces of
+         * code in glibc.
+         *
+         * %g7 is used as the "thread register".   %g6 is not used in
+         * any fixed manner.  %g6 is used as a scratch register and
+         * a compiler temporary, but it's value is never used across
+         * a system call.  Therefore %g6 is usable for orig_i0 storage.
+         */
         if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C))
-                restart_syscall = 1;
-        else
-                restart_syscall = 0;
+                regs->u_regs[UREG_G6] = orig_i0;
 
         if (test_thread_flag(TIF_RESTORE_SIGMASK))
                 oldset = &current->saved_sigmask;
@@ -535,8 +551,12 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
          * the software "in syscall" bit, directing us to not perform
          * a syscall restart.
          */
-        if (restart_syscall && !pt_regs_is_syscall(regs))
-                restart_syscall = 0;
+        restart_syscall = 0;
+        if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) {
+                restart_syscall = 1;
+                orig_i0 = regs->u_regs[UREG_G6];
+        }
+
 
         if (signr > 0) {
                 if (restart_syscall)
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index a2b81598d905..f0836cd0e2f2 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -529,11 +529,27 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
         siginfo_t info;
         int signr;
         
+        /* It's a lot of work and synchronization to add a new ptrace
+         * register for GDB to save and restore in order to get
+         * orig_i0 correct for syscall restarts when debugging.
+         *
+         * Although it should be the case that most of the global
+         * registers are volatile across a system call, glibc already
+         * depends upon that fact that we preserve them.  So we can't
+         * just use any global register to save away the orig_i0 value.
+         *
+         * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+         * preserved across a system call trap by various pieces of
+         * code in glibc.
+         *
+         * %g7 is used as the "thread register".   %g6 is not used in
+         * any fixed manner.  %g6 is used as a scratch register and
+         * a compiler temporary, but it's value is never used across
+         * a system call.  Therefore %g6 is usable for orig_i0 storage.
+         */
         if (pt_regs_is_syscall(regs) &&
-            (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
-                restart_syscall = 1;
-        } else
-                restart_syscall = 0;
+            (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY)))
+                regs->u_regs[UREG_G6] = orig_i0;
 
         if (current_thread_info()->status & TS_RESTORE_SIGMASK)
                 oldset = &current->saved_sigmask;
@@ -542,22 +558,20 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 
 #ifdef CONFIG_COMPAT
         if (test_thread_flag(TIF_32BIT)) {
-                extern void do_signal32(sigset_t *, struct pt_regs *,
-                                        int restart_syscall,
-                                        unsigned long orig_i0);
-                do_signal32(oldset, regs, restart_syscall, orig_i0);
+                extern void do_signal32(sigset_t *, struct pt_regs *);
+                do_signal32(oldset, regs);
                 return;
         }
 #endif  
 
         signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 
-        /* If the debugger messes with the program counter, it clears
-         * the software "in syscall" bit, directing us to not perform
-         * a syscall restart.
-         */
-        if (restart_syscall && !pt_regs_is_syscall(regs))
-                restart_syscall = 0;
+        restart_syscall = 0;
+        if (pt_regs_is_syscall(regs) &&
+            (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+                restart_syscall = 1;
+                orig_i0 = regs->u_regs[UREG_G6];
+        }
 
         if (signr > 0) {
                 if (restart_syscall)
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
index e7dc508c38eb..b19570d41a39 100644
--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -2,6 +2,7 @@
 #include <linux/types.h>
 #include <linux/thread_info.h>
 #include <linux/uaccess.h>
+#include <linux/errno.h>
 
 #include <asm/sigcontext.h>
 #include <asm/fpumacro.h>
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index e3cda21b5ee9..301421c11291 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o gup.o
 obj-y                   += fault_$(BITS).o
 obj-y                   += init_$(BITS).o
 obj-$(CONFIG_SPARC32)   += loadmmu.o
-obj-y                   += generic_$(BITS).o
 obj-$(CONFIG_SPARC32)   += extable.o btfixup.o srmmu.o iommu.o io-unit.o
 obj-$(CONFIG_SPARC32)   += hypersparc.o viking.o tsunami.o swift.o
 obj-$(CONFIG_SPARC_LEON)+= leon_mm.o
diff --git a/arch/sparc/mm/generic_32.c b/arch/sparc/mm/generic_32.c
deleted file mode 100644
index 6ca39a60a196..000000000000
--- a/arch/sparc/mm/generic_32.c
+++ /dev/null
@@ -1,99 +0,0 @@
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- *            MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/pagemap.h>
-#include <linux/export.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, unsigned long address, unsigned long size,
-        unsigned long offset, pgprot_t prot, int space)
-{
-        unsigned long end;
-
-        address &= ~PMD_MASK;
-        end = address + size;
-        if (end > PMD_SIZE)
-                end = PMD_SIZE;
-        do {
-                set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space));
-                address += PAGE_SIZE;
-                offset += PAGE_SIZE;
-                pte++;
-        } while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
-        unsigned long offset, pgprot_t prot, int space)
-{
-        unsigned long end;
-
-        address &= ~PGDIR_MASK;
-        end = address + size;
-        if (end > PGDIR_SIZE)
-                end = PGDIR_SIZE;
-        offset -= address;
-        do {
-                pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
-                if (!pte)
-                        return -ENOMEM;
-                io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
-                address = (address + PMD_SIZE) & PMD_MASK;
-                pmd++;
-        } while (address < end);
-        return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-                       unsigned long pfn, unsigned long size, pgprot_t prot)
-{
-        int error = 0;
-        pgd_t * dir;
-        unsigned long beg = from;
-        unsigned long end = from + size;
-        struct mm_struct *mm = vma->vm_mm;
-        int space = GET_IOSPACE(pfn);
-        unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
-
-        /* See comment in mm/memory.c remap_pfn_range */
-        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
-        vma->vm_pgoff = (offset >> PAGE_SHIFT) |
-                ((unsigned long)space << 28UL);
-
-        offset -= from;
-        dir = pgd_offset(mm, from);
-        flush_cache_range(vma, beg, end);
-
-        while (from < end) {
-                pmd_t *pmd = pmd_alloc(mm, dir, from);
-                error = -ENOMEM;
-                if (!pmd)
-                        break;
-                error = io_remap_pmd_range(mm, pmd, from, end - from, offset + from, prot, space);
-                if (error)
-                        break;
-                from = (from + PGDIR_SIZE) & PGDIR_MASK;
-                dir++;
-        }
-
-        flush_tlb_range(vma, beg, end);
-        return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
diff --git a/arch/sparc/mm/generic_64.c b/arch/sparc/mm/generic_64.c
deleted file mode 100644
index 9b357ddae39d..000000000000
--- a/arch/sparc/mm/generic_64.c
+++ /dev/null
@@ -1,165 +0,0 @@
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- *            MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/export.h>
-#include <linux/pagemap.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte,
-                                      unsigned long address,
-                                      unsigned long size,
-                                      unsigned long offset, pgprot_t prot,
-                                      int space)
-{
-        unsigned long end;
-
-        /* clear hack bit that was used as a write_combine side-effect flag */
-        offset &= ~0x1UL;
-        address &= ~PMD_MASK;
-        end = address + size;
-        if (end > PMD_SIZE)
-                end = PMD_SIZE;
-        do {
-                pte_t entry;
-                unsigned long curend = address + PAGE_SIZE;
-                
-                entry = mk_pte_io(offset, prot, space, PAGE_SIZE);
-                if (!(address & 0xffff)) {
-                        if (PAGE_SIZE < (4 * 1024 * 1024) &&
-                            !(address & 0x3fffff) &&
-                            !(offset & 0x3ffffe) &&
-                            end >= address + 0x400000) {
-                                entry = mk_pte_io(offset, prot, space,
-                                                  4 * 1024 * 1024);
-                                curend = address + 0x400000;
-                                offset += 0x400000;
-                        } else if (PAGE_SIZE < (512 * 1024) &&
-                                   !(address & 0x7ffff) &&
-                                   !(offset & 0x7fffe) &&
-                                   end >= address + 0x80000) {
-                                entry = mk_pte_io(offset, prot, space,
-                                                  512 * 1024 * 1024);
-                                curend = address + 0x80000;
-                                offset += 0x80000;
-                        } else if (PAGE_SIZE < (64 * 1024) &&
-                                   !(offset & 0xfffe) &&
-                                   end >= address + 0x10000) {
-                                entry = mk_pte_io(offset, prot, space,
-                                                  64 * 1024);
-                                curend = address + 0x10000;
-                                offset += 0x10000;
-                        } else
-                                offset += PAGE_SIZE;
-                } else
-                        offset += PAGE_SIZE;
-
-                if (pte_write(entry))
-                        entry = pte_mkdirty(entry);
-                do {
-                        BUG_ON(!pte_none(*pte));
-                        set_pte_at(mm, address, pte, entry);
-                        address += PAGE_SIZE;
-                        pte_val(entry) += PAGE_SIZE;
-                        pte++;
-                } while (address < curend);
-        } while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
-        unsigned long offset, pgprot_t prot, int space)
-{
-        unsigned long end;
-
-        address &= ~PGDIR_MASK;
-        end = address + size;
-        if (end > PGDIR_SIZE)
-                end = PGDIR_SIZE;
-        offset -= address;
-        do {
-                pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
-                if (!pte)
-                        return -ENOMEM;
-                io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
-                pte_unmap(pte);
-                address = (address + PMD_SIZE) & PMD_MASK;
-                pmd++;
-        } while (address < end);
-        return 0;
-}
-
-static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, unsigned long address, unsigned long size,
-        unsigned long offset, pgprot_t prot, int space)
-{
-        unsigned long end;
-
-        address &= ~PUD_MASK;
-        end = address + size;
-        if (end > PUD_SIZE)
-                end = PUD_SIZE;
-        offset -= address;
-        do {
-                pmd_t *pmd = pmd_alloc(mm, pud, address);
-                if (!pud)
-                        return -ENOMEM;
-                io_remap_pmd_range(mm, pmd, address, end - address, address + offset, prot, space);
-                address = (address + PUD_SIZE) & PUD_MASK;
-                pud++;
-        } while (address < end);
-        return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-                unsigned long pfn, unsigned long size, pgprot_t prot)
-{
-        int error = 0;
-        pgd_t * dir;
-        unsigned long beg = from;
-        unsigned long end = from + size;
-        struct mm_struct *mm = vma->vm_mm;
-        int space = GET_IOSPACE(pfn);
-        unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
-        unsigned long phys_base;
-
-        phys_base = offset | (((unsigned long) space) << 32UL);
-
-        /* See comment in mm/memory.c remap_pfn_range */
-        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
-        vma->vm_pgoff = phys_base >> PAGE_SHIFT;
-
-        offset -= from;
-        dir = pgd_offset(mm, from);
-        flush_cache_range(vma, beg, end);
-
-        while (from < end) {
-                pud_t *pud = pud_alloc(mm, dir, from);
-                error = -ENOMEM;
-                if (!pud)
-                        break;
-                error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space);
-                if (error)
-                        break;
-                from = (from + PGDIR_SIZE) & PGDIR_MASK;
-                dir++;
-        }
-
-        flush_tlb_range(vma, beg, end);
-        return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index e57dcce9bfda..942ed6174f1d 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -237,13 +237,13 @@ menu "PKUnity NetBook-0916 Features"
 
 config I2C_BATTERY_BQ27200
         tristate "I2C Battery BQ27200 Support"
-        select PUV3_I2C
+        select I2C_PUV3
         select POWER_SUPPLY
         select BATTERY_BQ27x00
 
 config I2C_EEPROM_AT24
         tristate "I2C EEPROMs AT24 support"
-        select PUV3_I2C
+        select I2C_PUV3
         select MISC_DEVICES
         select EEPROM_AT24
 
diff --git a/arch/unicore32/Kconfig.debug b/arch/unicore32/Kconfig.debug
index ae2ec334c3c6..1a3626239843 100644
--- a/arch/unicore32/Kconfig.debug
+++ b/arch/unicore32/Kconfig.debug
@@ -44,18 +44,4 @@ config DEBUG_OCD
           Say Y here if you want the debug print routines to direct their
           output to the UniCore On-Chip-Debugger channel using CP #1.
 
-config DEBUG_OCD_BREAKPOINT
-        bool "Breakpoint support via On-Chip-Debugger"
-        depends on DEBUG_OCD
-
-config DEBUG_UART
-        int "Kernel low-level debugging messages via serial port"
-        depends on DEBUG_LL
-        range 0 1
-        default "0"
-        help
-          Choice for UART for kernel low-level using PKUnity UARTS,
-          should be between zero and one. The port must have been
-          initialised by the boot-loader before use.
-
 endmenu
diff --git a/arch/unicore32/boot/compressed/Makefile b/arch/unicore32/boot/compressed/Makefile
index b0954a2d23cf..950a9afa38f8 100644
--- a/arch/unicore32/boot/compressed/Makefile
+++ b/arch/unicore32/boot/compressed/Makefile
@@ -10,8 +10,8 @@
 # Copyright (C) 2001~2010 GUAN Xue-tao
 #
 
-EXTRA_CFLAGS    := -fpic -fno-builtin
-EXTRA_AFLAGS    := -Wa,-march=all
+ccflags-y       := -fpic -fno-builtin
+asflags-y       := -Wa,-march=all
 
 OBJS            := misc.o
 
diff --git a/arch/unicore32/include/asm/bitops.h b/arch/unicore32/include/asm/bitops.h
index 1628a6328994..401f597bc38c 100644
--- a/arch/unicore32/include/asm/bitops.h
+++ b/arch/unicore32/include/asm/bitops.h
@@ -13,12 +13,6 @@
 #ifndef __UNICORE_BITOPS_H__
 #define __UNICORE_BITOPS_H__
 
-#define find_next_bit           __uc32_find_next_bit
-#define find_next_zero_bit      __uc32_find_next_zero_bit
-
-#define find_first_bit          __uc32_find_first_bit
-#define find_first_zero_bit     __uc32_find_first_zero_bit
-
 #define _ASM_GENERIC_BITOPS_FLS_H_
 #define _ASM_GENERIC_BITOPS___FLS_H_
 #define _ASM_GENERIC_BITOPS_FFS_H_
@@ -44,4 +38,10 @@ static inline int fls(int x)
 
 #include <asm-generic/bitops.h>
 
+/* following definitions: to avoid using codes in lib/find_*.c */
+#define find_next_bit           find_next_bit
+#define find_next_zero_bit      find_next_zero_bit
+#define find_first_bit          find_first_bit
+#define find_first_zero_bit     find_first_zero_bit
+
 #endif /* __UNICORE_BITOPS_H__ */
diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h
index e11cb0786578..f0d780a51f9b 100644
--- a/arch/unicore32/include/asm/processor.h
+++ b/arch/unicore32/include/asm/processor.h
@@ -53,7 +53,6 @@ struct thread_struct {
 #define start_thread(regs, pc, sp)                                      \
 ({                                                                      \
         unsigned long *stack = (unsigned long *)sp;                     \
-        set_fs(USER_DS);                                                \
         memset(regs->uregs, 0, sizeof(regs->uregs));                    \
         regs->UCreg_asr = USER_MODE;                                    \
         regs->UCreg_pc = pc & ~1;       /* pc */                        \
diff --git a/arch/unicore32/kernel/ksyms.c b/arch/unicore32/kernel/ksyms.c
index a8970809428a..d98bd812cae1 100644
--- a/arch/unicore32/kernel/ksyms.c
+++ b/arch/unicore32/kernel/ksyms.c
@@ -24,8 +24,8 @@
 
 #include "ksyms.h"
 
-EXPORT_SYMBOL(__uc32_find_next_zero_bit);
-EXPORT_SYMBOL(__uc32_find_next_bit);
+EXPORT_SYMBOL(find_next_zero_bit);
+EXPORT_SYMBOL(find_next_bit);
 
 EXPORT_SYMBOL(__backtrace);
 
diff --git a/arch/unicore32/lib/findbit.S b/arch/unicore32/lib/findbit.S
index c360ce905d8b..c77746247d36 100644
--- a/arch/unicore32/lib/findbit.S
+++ b/arch/unicore32/lib/findbit.S
@@ -17,7 +17,7 @@
  * Purpose  : Find a 'zero' bit
  * Prototype: int find_first_zero_bit(void *addr, unsigned int maxbit);
  */
-__uc32_find_first_zero_bit:
+ENTRY(find_first_zero_bit)
                 cxor.a  r1, #0
                 beq     3f
                 mov     r2, #0
@@ -29,13 +29,14 @@ __uc32_find_first_zero_bit:
                 bub     1b
 3:              mov     r0, r1                  @ no free bits
                 mov     pc, lr
+ENDPROC(find_first_zero_bit)
 
 /*
  * Purpose  : Find next 'zero' bit
  * Prototype: int find_next_zero_bit
  *              (void *addr, unsigned int maxbit, int offset)
  */
-ENTRY(__uc32_find_next_zero_bit)
+ENTRY(find_next_zero_bit)
                 cxor.a  r1, #0
                 beq     3b
                 and.a   ip, r2, #7
@@ -47,14 +48,14 @@ ENTRY(__uc32_find_next_zero_bit)
                 or      r2, r2, #7              @ if zero, then no bits here
                 add     r2, r2, #1              @ align bit pointer
                 b       2b                      @ loop for next bit
-ENDPROC(__uc32_find_next_zero_bit)
+ENDPROC(find_next_zero_bit)
 
 /*
  * Purpose  : Find a 'one' bit
  * Prototype: int find_first_bit
  *              (const unsigned long *addr, unsigned int maxbit);
  */
-__uc32_find_first_bit:
+ENTRY(find_first_bit)
                 cxor.a  r1, #0
                 beq     3f
                 mov     r2, #0
@@ -66,13 +67,14 @@ __uc32_find_first_bit:
                 bub     1b
 3:              mov     r0, r1                  @ no free bits
                 mov     pc, lr
+ENDPROC(find_first_bit)
 
 /*
  * Purpose  : Find next 'one' bit
  * Prototype: int find_next_zero_bit
  *              (void *addr, unsigned int maxbit, int offset)
  */
-ENTRY(__uc32_find_next_bit)
+ENTRY(find_next_bit)
                 cxor.a  r1, #0
                 beq     3b
                 and.a   ip, r2, #7
@@ -83,7 +85,7 @@ ENTRY(__uc32_find_next_bit)
                 or      r2, r2, #7              @ if zero, then no bits here
                 add     r2, r2, #1              @ align bit pointer
                 b       2b                      @ loop for next bit
-ENDPROC(__uc32_find_next_bit)
+ENDPROC(find_next_bit)
 
 /*
  * One or more bits in the LSB of r3 are assumed to be set.
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 9b7273cb2193..1a6c09af048f 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -49,6 +49,7 @@ extern unsigned int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
+extern unsigned int lapic_timer_frequency;
 
 #ifdef CONFIG_SMP
 extern void __inquire_remote_apic(int apicid);
diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index 72a8b52e7dfd..a01e7ec7d237 100644
--- a/arch/x86/include/asm/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
@@ -17,7 +17,7 @@
 #define NMI_REASON_CLEAR_IOCHK  0x08
 #define NMI_REASON_CLEAR_MASK   0x0f
 
-static inline unsigned char get_nmi_reason(void)
+static inline unsigned char default_get_nmi_reason(void)
 {
         return inb(NMI_REASON_PORT);
 }
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c9321f34e55b..0e8ae57d3656 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -201,7 +201,10 @@ int mce_notify_irq(void);
 void mce_notify_process(void);
 
 DECLARE_PER_CPU(struct mce, injectm);
-extern struct file_operations mce_chrdev_ops;
+
+extern void register_mce_write_callback(ssize_t (*)(struct file *filp,
+                                    const char __user *ubuf,
+                                    size_t usize, loff_t *off));
 
 /*
  * Exception handler
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 719f00b28ff5..e6283129c821 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -44,6 +44,13 @@ enum mrst_timer_options {
 
 extern enum mrst_timer_options mrst_timer_options;
 
+/*
+ * Penwell uses spread spectrum clock, so the freq number is not exactly
+ * the same as reported by MSR based on SDM.
+ */
+#define PENWELL_FSB_FREQ_83SKU         83200
+#define PENWELL_FSB_FREQ_100SKU        99840
+
 #define SFI_MTMR_MAX_NUM 8
 #define SFI_MRTC_MAX    8
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index d3d859035af9..1971e652d24b 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -152,6 +152,7 @@ struct x86_cpuinit_ops {
 /**
  * struct x86_platform_ops - platform specific runtime functions
  * @calibrate_tsc:              calibrate TSC
+ * @wallclock_init:             init the wallclock device
  * @get_wallclock:              get time from HW clock like RTC etc.
  * @set_wallclock:              set time back to HW clock
  * @is_untracked_pat_range      exclude from PAT logic
@@ -160,11 +161,13 @@ struct x86_cpuinit_ops {
  */
 struct x86_platform_ops {
         unsigned long (*calibrate_tsc)(void);
+        void (*wallclock_init)(void);
         unsigned long (*get_wallclock)(void);
         int (*set_wallclock)(unsigned long nowtime);
         void (*iommu_shutdown)(void);
         bool (*is_untracked_pat_range)(u64 start, u64 end);
         void (*nmi_init)(void);
+        unsigned char (*get_nmi_reason)(void);
         int (*i8042_detect)(void);
 };
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c63822816249..1f84794f0759 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -738,5 +738,5 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
 
         atomic_set(&stop_machine_first, 1);
         wrote_text = 0;
-        __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+        __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
 }
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index a2fd72e0ab35..f98d84caf94c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -186,7 +186,7 @@ static struct resource lapic_resource = {
         .flags = IORESOURCE_MEM | IORESOURCE_BUSY,
 };
 
-static unsigned int calibration_result;
+unsigned int lapic_timer_frequency = 0;
 
 static void apic_pm_activate(void);
 
@@ -454,7 +454,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
         switch (mode) {
         case CLOCK_EVT_MODE_PERIODIC:
         case CLOCK_EVT_MODE_ONESHOT:
-                __setup_APIC_LVTT(calibration_result,
+                __setup_APIC_LVTT(lapic_timer_frequency,
                                   mode != CLOCK_EVT_MODE_PERIODIC, 1);
                 break;
         case CLOCK_EVT_MODE_UNUSED:
@@ -638,6 +638,25 @@ static int __init calibrate_APIC_clock(void)
         long delta, deltatsc;
         int pm_referenced = 0;
 
+        /**
+         * check if lapic timer has already been calibrated by platform
+         * specific routine, such as tsc calibration code. if so, we just fill
+         * in the clockevent structure and return.
+         */
+
+        if (lapic_timer_frequency) {
+                apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
+                                lapic_timer_frequency);
+                lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+                                        TICK_NSEC, lapic_clockevent.shift);
+                lapic_clockevent.max_delta_ns =
+                        clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+                lapic_clockevent.min_delta_ns =
+                        clockevent_delta2ns(0xF, &lapic_clockevent);
+                lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+                return 0;
+        }
+
         local_irq_disable();
 
         /* Replace the global interrupt handler */
@@ -679,12 +698,12 @@ static int __init calibrate_APIC_clock(void)
         lapic_clockevent.min_delta_ns =
                 clockevent_delta2ns(0xF, &lapic_clockevent);
 
-        calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+        lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
 
         apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
         apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
         apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
-                    calibration_result);
+                    lapic_timer_frequency);
 
         if (cpu_has_tsc) {
                 apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
@@ -695,13 +714,13 @@ static int __init calibrate_APIC_clock(void)
 
         apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
                     "%u.%04u MHz.\n",
-                    calibration_result / (1000000 / HZ),
-                    calibration_result % (1000000 / HZ));
+                    lapic_timer_frequency / (1000000 / HZ),
+                    lapic_timer_frequency % (1000000 / HZ));
 
         /*
          * Do a sanity check on the APIC calibration result
          */
-        if (calibration_result < (1000000 / HZ)) {
+        if (lapic_timer_frequency < (1000000 / HZ)) {
                 local_irq_enable();
                 pr_warning("APIC frequency too slow, disabling apic timer\n");
                 return -1;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 3c31fa98af6d..6d939d7847e2 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -193,10 +193,8 @@ int __init arch_early_irq_init(void)
         struct irq_cfg *cfg;
         int count, node, i;
 
-        if (!legacy_pic->nr_legacy_irqs) {
-                nr_irqs_gsi = 0;
+        if (!legacy_pic->nr_legacy_irqs)
                 io_apic_irqs = ~0UL;
-        }
 
         for (i = 0; i < nr_ioapics; i++) {
                 ioapics[i].saved_registers =
@@ -1696,6 +1694,7 @@ __apicdebuginit(void) print_IO_APICs(void)
         int ioapic_idx;
         struct irq_cfg *cfg;
         unsigned int irq;
+        struct irq_chip *chip;
 
         printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
         for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
@@ -1716,6 +1715,10 @@ __apicdebuginit(void) print_IO_APICs(void)
         for_each_active_irq(irq) {
                 struct irq_pin_list *entry;
 
+                chip = irq_get_chip(irq);
+                if (chip != &ioapic_chip)
+                        continue;
+
                 cfg = irq_get_chip_data(irq);
                 if (!cfg)
                         continue;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 6199232161cf..319882ef848d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -208,7 +208,7 @@ static int inject_init(void)
         if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
                 return -ENOMEM;
         printk(KERN_INFO "Machine check injector initialized\n");
-        mce_chrdev_ops.write = mce_write;
+        register_mce_write_callback(mce_write);
         register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
                                 "mce_notify");
         return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 362056aefeb4..2af127d4c3d1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1634,16 +1634,35 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
         }
 }
 
-/* Modified in mce-inject.c, so not static or const */
-struct file_operations mce_chrdev_ops = {
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+                            size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+                             const char __user *ubuf,
+                             size_t usize, loff_t *off))
+{
+        mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+                         size_t usize, loff_t *off)
+{
+        if (mce_write)
+                return mce_write(filp, ubuf, usize, off);
+        else
+                return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
         .open                   = mce_chrdev_open,
         .release                = mce_chrdev_release,
         .read                   = mce_chrdev_read,
+        .write                  = mce_chrdev_write,
         .poll                   = mce_chrdev_poll,
         .unlocked_ioctl         = mce_chrdev_ioctl,
         .llseek                 = no_llseek,
 };
-EXPORT_SYMBOL_GPL(mce_chrdev_ops);
 
 static struct miscdevice mce_chrdev_device = {
         MISC_MCELOG_MINOR,
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index c1a0188e29ae..44842d756b29 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -74,9 +74,10 @@ static cycle_t kvm_clock_read(void)
         struct pvclock_vcpu_time_info *src;
         cycle_t ret;
 
-        src = &get_cpu_var(hv_clock);
+        preempt_disable_notrace();
+        src = &__get_cpu_var(hv_clock);
         ret = pvclock_clocksource_read(src);
-        put_cpu_var(hv_clock);
+        preempt_enable_notrace();
         return ret;
 }
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index b9c8628974af..e88f37b58ddd 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -29,6 +29,7 @@
 #include <asm/traps.h>
 #include <asm/mach_traps.h>
 #include <asm/nmi.h>
+#include <asm/x86_init.h>
 
 #define NMI_MAX_NAMELEN 16
 struct nmiaction {
@@ -348,7 +349,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 
         /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
         raw_spin_lock(&nmi_reason_lock);
-        reason = get_nmi_reason();
+        reason = x86_platform.get_nmi_reason();
 
         if (reason & NMI_REASON_MASK) {
                 if (reason & NMI_REASON_SERR)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index afaf38447ef5..cf0ef986cb6d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1045,6 +1045,8 @@ void __init setup_arch(char **cmdline_p)
 
         x86_init.timers.wallclock_init();
 
+        x86_platform.wallclock_init();
+
         mcheck_init();
 
         arch_init_ideal_nops();
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 6f164bd5e14d..c1d6cd549397 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -21,12 +21,14 @@
 #include <asm/pat.h>
 #include <asm/tsc.h>
 #include <asm/iommu.h>
+#include <asm/mach_traps.h>
 
 void __cpuinit x86_init_noop(void) { }
 void __init x86_init_uint_noop(unsigned int unused) { }
 void __init x86_init_pgd_noop(pgd_t *unused) { }
 int __init iommu_init_noop(void) { return 0; }
 void iommu_shutdown_noop(void) { }
+void wallclock_init_noop(void) { }
 
 /*
  * The platform setup functions are preset with the default functions
@@ -97,11 +99,13 @@ static int default_i8042_detect(void) { return 1; };
 
 struct x86_platform_ops x86_platform = {
         .calibrate_tsc                  = native_calibrate_tsc,
+        .wallclock_init                 = wallclock_init_noop,
         .get_wallclock                  = mach_get_cmos_time,
         .set_wallclock                  = mach_set_rtc_mmss,
         .iommu_shutdown                 = iommu_shutdown_noop,
         .is_untracked_pat_range         = is_ISA_range,
         .nmi_init                       = default_nmi_init,
+        .get_nmi_reason                 = default_get_nmi_reason,
         .i8042_detect                   = default_i8042_detect
 };
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a0d6bd9ad442..579a0b51696a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -39,6 +39,7 @@
 #include <asm/mce.h>
 #include <asm/i387.h>
 #include <asm/xcr.h>
+#include <asm/perf_event.h>
 
 #include "trace.h"
 
@@ -118,7 +119,7 @@ module_param(ple_gap, int, S_IRUGO);
 static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
 module_param(ple_window, int, S_IRUGO);
 
-#define NR_AUTOLOAD_MSRS 1
+#define NR_AUTOLOAD_MSRS 8
 #define VMCS02_POOL_SIZE 1
 
 struct vmcs {
@@ -622,6 +623,7 @@ static unsigned long *vmx_msr_bitmap_legacy;
 static unsigned long *vmx_msr_bitmap_longmode;
 
 static bool cpu_has_load_ia32_efer;
+static bool cpu_has_load_perf_global_ctrl;
 
 static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
 static DEFINE_SPINLOCK(vmx_vpid_lock);
@@ -1191,15 +1193,34 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
         vmcs_write32(EXCEPTION_BITMAP, eb);
 }
 
+static void clear_atomic_switch_msr_special(unsigned long entry,
+                unsigned long exit)
+{
+        vmcs_clear_bits(VM_ENTRY_CONTROLS, entry);
+        vmcs_clear_bits(VM_EXIT_CONTROLS, exit);
+}
+
 static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 {
         unsigned i;
         struct msr_autoload *m = &vmx->msr_autoload;
 
-        if (msr == MSR_EFER && cpu_has_load_ia32_efer) {
-                vmcs_clear_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER);
-                vmcs_clear_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER);
-                return;
+        switch (msr) {
+        case MSR_EFER:
+                if (cpu_has_load_ia32_efer) {
+                        clear_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER,
+                                        VM_EXIT_LOAD_IA32_EFER);
+                        return;
+                }
+                break;
+        case MSR_CORE_PERF_GLOBAL_CTRL:
+                if (cpu_has_load_perf_global_ctrl) {
+                        clear_atomic_switch_msr_special(
+                                        VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+                                        VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
+                        return;
+                }
+                break;
         }
 
         for (i = 0; i < m->nr; ++i)
@@ -1215,25 +1236,55 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
         vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
 }
 
+static void add_atomic_switch_msr_special(unsigned long entry,
+                unsigned long exit, unsigned long guest_val_vmcs,
+                unsigned long host_val_vmcs, u64 guest_val, u64 host_val)
+{
+        vmcs_write64(guest_val_vmcs, guest_val);
+        vmcs_write64(host_val_vmcs, host_val);
+        vmcs_set_bits(VM_ENTRY_CONTROLS, entry);
+        vmcs_set_bits(VM_EXIT_CONTROLS, exit);
+}
+
 static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
                                   u64 guest_val, u64 host_val)
 {
         unsigned i;
         struct msr_autoload *m = &vmx->msr_autoload;
 
-        if (msr == MSR_EFER && cpu_has_load_ia32_efer) {
-                vmcs_write64(GUEST_IA32_EFER, guest_val);
-                vmcs_write64(HOST_IA32_EFER, host_val);
-                vmcs_set_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER);
-                vmcs_set_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER);
-                return;
+        switch (msr) {
+        case MSR_EFER:
+                if (cpu_has_load_ia32_efer) {
+                        add_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER,
+                                        VM_EXIT_LOAD_IA32_EFER,
+                                        GUEST_IA32_EFER,
+                                        HOST_IA32_EFER,
+                                        guest_val, host_val);
+                        return;
+                }
+                break;
+        case MSR_CORE_PERF_GLOBAL_CTRL:
+                if (cpu_has_load_perf_global_ctrl) {
+                        add_atomic_switch_msr_special(
+                                        VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+                                        VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL,
+                                        GUEST_IA32_PERF_GLOBAL_CTRL,
+                                        HOST_IA32_PERF_GLOBAL_CTRL,
+                                        guest_val, host_val);
+                        return;
+                }
+                break;
         }
 
         for (i = 0; i < m->nr; ++i)
                 if (m->guest[i].index == msr)
                         break;
 
-        if (i == m->nr) {
+        if (i == NR_AUTOLOAD_MSRS) {
+                printk_once(KERN_WARNING"Not enough mst switch entries. "
+                                "Can't add msr %x\n", msr);
+                return;
+        } else if (i == m->nr) {
                 ++m->nr;
                 vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
                 vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
@@ -2455,6 +2506,42 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
                 && allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
                                    VM_EXIT_LOAD_IA32_EFER);
 
+        cpu_has_load_perf_global_ctrl =
+                allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS,
+                                VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+                && allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
+                                   VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
+
+        /*
+         * Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL
+         * but due to arrata below it can't be used. Workaround is to use
+         * msr load mechanism to switch IA32_PERF_GLOBAL_CTRL.
+         *
+         * VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32]
+         *
+         * AAK155             (model 26)
+         * AAP115             (model 30)
+         * AAT100             (model 37)
+         * BC86,AAY89,BD102   (model 44)
+         * BA97               (model 46)
+         *
+         */
+        if (cpu_has_load_perf_global_ctrl && boot_cpu_data.x86 == 0x6) {
+                switch (boot_cpu_data.x86_model) {
+                case 26:
+                case 30:
+                case 37:
+                case 44:
+                case 46:
+                        cpu_has_load_perf_global_ctrl = false;
+                        printk_once(KERN_WARNING"kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
+                                        "does not work properly. Using workaround\n");
+                        break;
+                default:
+                        break;
+                }
+        }
+
         return 0;
 }
 
@@ -5968,6 +6055,24 @@ static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
         vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
 }
 
+static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
+{
+        int i, nr_msrs;
+        struct perf_guest_switch_msr *msrs;
+
+        msrs = perf_guest_get_msrs(&nr_msrs);
+
+        if (!msrs)
+                return;
+
+        for (i = 0; i < nr_msrs; i++)
+                if (msrs[i].host == msrs[i].guest)
+                        clear_atomic_switch_msr(vmx, msrs[i].msr);
+                else
+                        add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
+                                        msrs[i].host);
+}
+
 #ifdef CONFIG_X86_64
 #define R "r"
 #define Q "q"
@@ -6017,6 +6122,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
         if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
                 vmx_set_interrupt_shadow(vcpu, 0);
 
+        atomic_switch_perf_msrs(vmx);
+
         vmx->__launched = vmx->loaded_vmcs->launched;
         asm(
                 /* Store host registers */
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 541020df0da6..b1489a06a49d 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -187,11 +187,34 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 static unsigned long __init mrst_calibrate_tsc(void)
 {
         unsigned long flags, fast_calibrate;
-
-        local_irq_save(flags);
-        fast_calibrate = apbt_quick_calibrate();
-        local_irq_restore(flags);
-
+        if (__mrst_cpu_chip == MRST_CPU_CHIP_PENWELL) {
+                u32 lo, hi, ratio, fsb;
+
+                rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+                pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
+                ratio = (hi >> 8) & 0x1f;
+                pr_debug("ratio is %d\n", ratio);
+                if (!ratio) {
+                        pr_err("read a zero ratio, should be incorrect!\n");
+                        pr_err("force tsc ratio to 16 ...\n");
+                        ratio = 16;
+                }
+                rdmsr(MSR_FSB_FREQ, lo, hi);
+                if ((lo & 0x7) == 0x7)
+                        fsb = PENWELL_FSB_FREQ_83SKU;
+                else
+                        fsb = PENWELL_FSB_FREQ_100SKU;
+                fast_calibrate = ratio * fsb;
+                pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
+                lapic_timer_frequency = fsb * 1000 / HZ;
+                /* mark tsc clocksource as reliable */
+                set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
+        } else {
+                local_irq_save(flags);
+                fast_calibrate = apbt_quick_calibrate();
+                local_irq_restore(flags);
+        }
+        
         if (fast_calibrate)
                 return fast_calibrate;
 
@@ -254,6 +277,17 @@ static void mrst_reboot(void)
 }
 
 /*
+ * Moorestown does not have external NMI source nor port 0x61 to report
+ * NMI status. The possible NMI sources are from pmu as a result of NMI
+ * watchdog or lock debug. Reading io port 0x61 results in 0xff which
+ * misled NMI handler.
+ */
+static unsigned char mrst_get_nmi_reason(void)
+{
+        return 0;
+}
+
+/*
  * Moorestown specific x86_init function overrides and early setup
  * calls.
  */
@@ -274,6 +308,8 @@ void __init x86_mrst_early_setup(void)
         x86_platform.calibrate_tsc = mrst_calibrate_tsc;
         x86_platform.i8042_detect = mrst_i8042_detect;
         x86_init.timers.wallclock_init = mrst_rtc_init;
+        x86_platform.get_nmi_reason = mrst_get_nmi_reason;
+
         x86_init.pci.init = pci_mrst_init;
         x86_init.pci.fixup_irqs = x86_init_noop;
 
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 118c143a9cb4..2c32df6fe231 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -11,7 +11,7 @@
 #endif
 
 #define KSTK_EIP(tsk) KSTK_REG(tsk, HOST_IP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_IP)
+#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_SP)
 #define KSTK_EBP(tsk) KSTK_REG(tsk, HOST_BP)
 
 #define ARCH_IS_STACKGROW(address) \
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index da8afd576a6b..1f928659c338 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1356,7 +1356,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
         int cpu = (long)hcpu;
         switch (action) {
         case CPU_UP_PREPARE:
-                per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+                xen_vcpu_setup(cpu);
                 if (xen_have_vector_callback)
                         xen_init_lock_cpu(cpu);
                 break;
@@ -1386,7 +1386,6 @@ static void __init xen_hvm_guest_init(void)
         xen_hvm_smp_init();
         register_cpu_notifier(&xen_hvm_cpu_notifier);
         xen_unplug_emulated_devices();
-        have_vcpu_info_placement = 0;
         x86_init.irqs.intr_init = xen_init_IRQ;
         xen_hvm_init_time_ops();
         xen_hvm_init_mmu_ops();
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 65160a8a0ba3..3a5f55d51907 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -85,7 +85,7 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 
         if (shared == NULL) {
                 struct vm_struct *area =
-                        alloc_vm_area(PAGE_SIZE * max_nr_gframes);
+                        alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
                 BUG_ON(area == NULL);
                 shared = area->addr;
                 *__shared = shared;