Merge 3.12-rc6 into staging-next.

We want these fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

60 files changed, 378 insertions, 179 deletions

diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index 333238564b67..5d76706139dd 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -102,7 +102,7 @@ static int genregs_set(struct task_struct *target,
 	REG_IGNORE_ONE(pad2);
 	REG_IN_CHUNK(callee, efa, cregs);	/* callee_regs[r25..r13] */
 	REG_IGNORE_ONE(efa);			/* efa update invalid */
-	REG_IN_ONE(stop_pc, &ptregs->ret);	/* stop_pc: PC update */
+	REG_IGNORE_ONE(stop_pc);			/* PC updated via @ret */
 
 	return ret;
 }
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index a37a50f575a2..db50b626be98 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -296,10 +296,15 @@ archprepare:
 # Convert bzImage to zImage
 bzImage: zImage
 
-zImage Image xipImage bootpImage uImage: vmlinux
+BOOT_TARGETS	= zImage Image xipImage bootpImage uImage
+INSTALL_TARGETS	= zinstall uinstall install
+
+PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
+
+$(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-zinstall uinstall install: vmlinux
+$(INSTALL_TARGETS):
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
 %.dtb: | scripts
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 84aa2caf07ed..ec2f8065f955 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -95,24 +95,24 @@ initrd:
 	@test "$(INITRD)" != "" || \
 	(echo You must specify INITRD; exit -1)
 
-install: $(obj)/Image
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+install:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
 
-zinstall: $(obj)/zImage
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+zinstall:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/zImage System.map "$(INSTALL_PATH)"
 
-uinstall: $(obj)/uImage
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+uinstall:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/uImage System.map "$(INSTALL_PATH)"
 
 zi:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/zImage System.map "$(INSTALL_PATH)"
 
 i:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
 
 subdir-	    := bootp compressed dts
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index 7d7cc777ff7b..bbac42a78ce5 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -96,6 +96,11 @@
 			     <1 14 0xf08>,
 			     <1 11 0xf08>,
 			     <1 10 0xf08>;
+		/* Unfortunately we need this since some versions of U-Boot
+		 * on Exynos don't set the CNTFRQ register, so we need the
+		 * value from DT.
+		 */
+		clock-frequency = <24000000>;
 	};
 
 	mct@101C0000 {
diff --git a/arch/arm/boot/dts/omap3-beagle-xm.dts b/arch/arm/boot/dts/omap3-beagle-xm.dts
index 0c514dc8460c..2816bf612672 100644
--- a/arch/arm/boot/dts/omap3-beagle-xm.dts
+++ b/arch/arm/boot/dts/omap3-beagle-xm.dts
@@ -11,7 +11,7 @@
 
 / {
 	model = "TI OMAP3 BeagleBoard xM";
-	compatible = "ti,omap3-beagle-xm", "ti,omap3-beagle", "ti,omap3";
+	compatible = "ti,omap3-beagle-xm", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 7d95cda1fae4..b41bd57f4328 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -108,7 +108,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			pinctrl-single,register-width = <16>;
-			pinctrl-single,function-mask = <0x7f1f>;
+			pinctrl-single,function-mask = <0xff1f>;
 		};
 
 		omap3_pmx_wkup: pinmux@0x48002a00 {
@@ -117,7 +117,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			pinctrl-single,register-width = <16>;
-			pinctrl-single,function-mask = <0x7f1f>;
+			pinctrl-single,function-mask = <0xff1f>;
 		};
 
 		gpio1: gpio@48310000 {
diff --git a/arch/arm/boot/install.sh b/arch/arm/boot/install.sh
index 06ea7d42ce8e..2a45092a40e3 100644
--- a/arch/arm/boot/install.sh
+++ b/arch/arm/boot/install.sh
@@ -20,6 +20,20 @@
 #   $4 - default install path (blank if root directory)
 #
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
 if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 370236dd1a03..990250965f2c 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -51,7 +51,8 @@ void mcpm_cpu_power_down(void)
 {
 	phys_reset_t phys_reset;
 
-	BUG_ON(!platform_ops);
+	if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down))
+		return;
 	BUG_ON(!irqs_disabled());
 
 	/*
@@ -93,7 +94,8 @@ void mcpm_cpu_suspend(u64 expected_residency)
 {
 	phys_reset_t phys_reset;
 
-	BUG_ON(!platform_ops);
+	if (WARN_ON_ONCE(!platform_ops || !platform_ops->suspend))
+		return;
 	BUG_ON(!irqs_disabled());
 
 	/* Very similar to mcpm_cpu_power_down() */
diff --git a/arch/arm/common/sharpsl_param.c b/arch/arm/common/sharpsl_param.c
index d56c932580eb..025f6ce38596 100644
--- a/arch/arm/common/sharpsl_param.c
+++ b/arch/arm/common/sharpsl_param.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <asm/mach/sharpsl_param.h>
+#include <asm/memory.h>
 
 /*
  * Certain hardware parameters determined at the time of device manufacture,
@@ -25,8 +26,10 @@
  */
 #ifdef CONFIG_ARCH_SA1100
 #define PARAM_BASE	0xe8ffc000
+#define param_start(x)	(void *)(x)
 #else
 #define PARAM_BASE	0xa0000a00
+#define param_start(x)	__va(x)
 #endif
 #define MAGIC_CHG(a,b,c,d) ( ( d << 24 ) | ( c << 16 )  | ( b << 8 ) | a )
 
@@ -41,7 +44,7 @@ EXPORT_SYMBOL(sharpsl_param);
 
 void sharpsl_save_param(void)
 {
-	memcpy(&sharpsl_param, (void *)PARAM_BASE, sizeof(struct sharpsl_param_info));
+	memcpy(&sharpsl_param, param_start(PARAM_BASE), sizeof(struct sharpsl_param_info));
 
 	if (sharpsl_param.comadj_keyword != COMADJ_MAGIC)
 		sharpsl_param.comadj=-1;
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index d3db39860b9c..59ceae8f3c95 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -31,5 +31,4 @@ generic-y += termbits.h
 generic-y += termios.h
 generic-y += timex.h
 generic-y += trace_clock.h
-generic-y += types.h
 generic-y += unaligned.h
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index bfc198c75913..863c892b4aaa 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -16,7 +16,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\n\t"
+	asm_volatile_goto("1:\n\t"
 		 JUMP_LABEL_NOP "\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 0f7b7620e9a5..fc82a88f5b69 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -76,8 +76,11 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
  *
  * This must be called with interrupts disabled.
  *
- * This does not return.  Re-entry in the kernel is expected via
- * mcpm_entry_point.
+ * On success this does not return.  Re-entry in the kernel is expected
+ * via mcpm_entry_point.
+ *
+ * This will return if mcpm_platform_register() has not been called
+ * previously in which case the caller should take appropriate action.
  */
 void mcpm_cpu_power_down(void);
 
@@ -98,8 +101,11 @@ void mcpm_cpu_power_down(void);
  *
  * This must be called with interrupts disabled.
  *
- * This does not return.  Re-entry in the kernel is expected via
- * mcpm_entry_point.
+ * On success this does not return.  Re-entry in the kernel is expected
+ * via mcpm_entry_point.
+ *
+ * This will return if mcpm_platform_register() has not been called
+ * previously in which case the caller should take appropriate action.
  */
 void mcpm_cpu_suspend(u64 expected_residency);
 
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index f1d96d4e8092..73ddd7239b33 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -57,6 +57,9 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
+	if (n == 0)
+		return;
+
 	if (i + n > SYSCALL_MAX_ARGS) {
 		unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
 		unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
@@ -81,6 +84,9 @@ static inline void syscall_set_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
+	if (n == 0)
+		return;
+
 	if (i + n > SYSCALL_MAX_ARGS) {
 		pr_warning("%s called with max args %d, handling only %d\n",
 			   __func__, i + n, SYSCALL_MAX_ARGS);
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 2c7cc1e03473..476de57dcef2 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -487,7 +487,26 @@ __fixup_smp:
 	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
 	and	r0, r0, #0xc0000000	@ multiprocessing extensions and
 	teq	r0, #0x80000000		@ not part of a uniprocessor system?
-	moveq	pc, lr			@ yes, assume SMP
+	bne    __fixup_smp_on_up	@ no, assume UP
+
+	@ Core indicates it is SMP. Check for Aegis SOC where a single
+	@ Cortex-A9 CPU is present but SMP operations fault.
+	mov	r4, #0x41000000
+	orr	r4, r4, #0x0000c000
+	orr	r4, r4, #0x00000090
+	teq	r3, r4			@ Check for ARM Cortex-A9
+	movne	pc, lr			@ Not ARM Cortex-A9,
+
+	@ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the
+	@ below address check will need to be #ifdef'd or equivalent
+	@ for the Aegis platform.
+	mrc	p15, 4, r0, c15, c0	@ get SCU base address
+	teq	r0, #0x0		@ '0' on actual UP A9 hardware
+	beq	__fixup_smp_on_up	@ So its an A9 UP
+	ldr	r0, [r0, #4]		@ read SCU Config
+	and	r0, r0, #0x3		@ number of CPUs
+	teq	r0, #0x0		@ is 1?
+	movne	pc, lr
 
 __fixup_smp_on_up:
 	adr	r0, 1f
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 39c78387ddec..87162e1b94a5 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -129,6 +129,24 @@ DT_MACHINE_START(OMAP3_DT, "Generic OMAP3 (Flattened Device Tree)")
 	.restart	= omap3xxx_restart,
 MACHINE_END
 
+static const char *omap36xx_boards_compat[] __initdata = {
+	"ti,omap36xx",
+	NULL,
+};
+
+DT_MACHINE_START(OMAP36XX_DT, "Generic OMAP36xx (Flattened Device Tree)")
+	.reserve	= omap_reserve,
+	.map_io		= omap3_map_io,
+	.init_early	= omap3630_init_early,
+	.init_irq	= omap_intc_of_init,
+	.handle_irq	= omap3_intc_handle_irq,
+	.init_machine	= omap_generic_init,
+	.init_late	= omap3_init_late,
+	.init_time	= omap3_sync32k_timer_init,
+	.dt_compat	= omap36xx_boards_compat,
+	.restart	= omap3xxx_restart,
+MACHINE_END
+
 static const char *omap3_gp_boards_compat[] __initdata = {
 	"ti,omap3-beagle",
 	"timll,omap3-devkit8000",
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index c3270c0f1fce..f6fe388af989 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -167,38 +167,47 @@ static struct lp55xx_led_config rx51_lp5523_led_config[] = {
 		.name		= "lp5523:kb1",
 		.chan_nr	= 0,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb2",
 		.chan_nr	= 1,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb3",
 		.chan_nr	= 2,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb4",
 		.chan_nr	= 3,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:b",
 		.chan_nr	= 4,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:g",
 		.chan_nr	= 5,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:r",
 		.chan_nr	= 6,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb5",
 		.chan_nr	= 7,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb6",
 		.chan_nr	= 8,
 		.led_current	= 50,
+		.max_current	= 100,
 	}
 };
 
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 64b5a8346982..8b6876c98ce1 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -272,9 +272,19 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base)
 	struct gpmc_timings t;
 	int ret;
 
-	if (gpmc_onenand_data->of_node)
+	if (gpmc_onenand_data->of_node) {
 		gpmc_read_settings_dt(gpmc_onenand_data->of_node,
 				      &onenand_async);
+		if (onenand_async.sync_read || onenand_async.sync_write) {
+			if (onenand_async.sync_write)
+				gpmc_onenand_data->flags |=
+					ONENAND_SYNC_READWRITE;
+			else
+				gpmc_onenand_data->flags |= ONENAND_SYNC_READ;
+			onenand_async.sync_read = false;
+			onenand_async.sync_write = false;
+		}
+	}
 
 	omap2_onenand_set_async_mode(onenand_base);
 
diff --git a/arch/arm/mach-omap2/mux.h b/arch/arm/mach-omap2/mux.h
index 5d2080ef7923..16f78a990d04 100644
--- a/arch/arm/mach-omap2/mux.h
+++ b/arch/arm/mach-omap2/mux.h
@@ -28,7 +28,7 @@
 #define OMAP_PULL_UP			(1 << 4)
 #define OMAP_ALTELECTRICALSEL		(1 << 5)
 
-/* 34xx specific mux bit defines */
+/* omap3/4/5 specific mux bit defines */
 #define OMAP_INPUT_EN			(1 << 8)
 #define OMAP_OFF_EN			(1 << 9)
 #define OMAP_OFFOUT_EN			(1 << 10)
@@ -36,8 +36,6 @@
 #define OMAP_OFF_PULL_EN		(1 << 12)
 #define OMAP_OFF_PULL_UP		(1 << 13)
 #define OMAP_WAKEUP_EN			(1 << 14)
-
-/* 44xx specific mux bit defines */
 #define OMAP_WAKEUP_EVENT		(1 << 15)
 
 /* Active pin states */
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index fa74a0625da1..ead48fa5715e 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -628,7 +628,7 @@ void __init omap4_local_timer_init(void)
 #endif /* CONFIG_HAVE_ARM_TWD */
 #endif /* CONFIG_ARCH_OMAP4 */
 
-#ifdef CONFIG_SOC_OMAP5
+#if defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX)
 void __init omap5_realtime_timer_init(void)
 {
 	omap4_sync32k_timer_init();
@@ -636,7 +636,7 @@ void __init omap5_realtime_timer_init(void)
 
 	clocksource_of_init();
 }
-#endif /* CONFIG_SOC_OMAP5 */
+#endif /* CONFIG_SOC_OMAP5 || CONFIG_SOC_DRA7XX */
 
 /**
  * omap_timer_init - build and register timer device with an
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f5e1a8471714..1272ed202dde 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1232,7 +1232,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
 				break;
 
 		len = (j - i) << PAGE_SHIFT;
-		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		ret = iommu_map(mapping->domain, iova, phys, len,
+				IOMMU_READ|IOMMU_WRITE);
 		if (ret < 0)
 			goto fail;
 		iova += len;
@@ -1431,6 +1432,27 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 					 GFP_KERNEL);
 }
 
+static int __dma_direction_to_prot(enum dma_data_direction dir)
+{
+	int prot;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		prot = IOMMU_READ | IOMMU_WRITE;
+		break;
+	case DMA_TO_DEVICE:
+		prot = IOMMU_READ;
+		break;
+	case DMA_FROM_DEVICE:
+		prot = IOMMU_WRITE;
+		break;
+	default:
+		prot = 0;
+	}
+
+	return prot;
+}
+
 /*
  * Map a part of the scatter-gather list into contiguous io address space
  */
@@ -1444,6 +1466,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 	int ret = 0;
 	unsigned int count;
 	struct scatterlist *s;
+	int prot;
 
 	size = PAGE_ALIGN(size);
 	*handle = DMA_ERROR_CODE;
@@ -1460,7 +1483,9 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 			!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
-		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		prot = __dma_direction_to_prot(dir);
+
+		ret = iommu_map(mapping->domain, iova, phys, len, prot);
 		if (ret < 0)
 			goto fail;
 		count += len >> PAGE_SHIFT;
@@ -1665,19 +1690,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	switch (dir) {
-	case DMA_BIDIRECTIONAL:
-		prot = IOMMU_READ | IOMMU_WRITE;
-		break;
-	case DMA_TO_DEVICE:
-		prot = IOMMU_READ;
-		break;
-	case DMA_FROM_DEVICE:
-		prot = IOMMU_WRITE;
-		break;
-	default:
-		prot = 0;
-	}
+	prot = __dma_direction_to_prot(dir);
 
 	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
 	if (ret < 0)
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index febaee7ca57b..18ec4c504abf 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -17,7 +17,6 @@
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
 #include <linux/of_fdt.h>
-#include <linux/of_reserved_mem.h>
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
@@ -379,8 +378,6 @@ void __init arm_memblock_init(struct meminfo *mi,
 	if (mdesc->reserve)
 		mdesc->reserve();
 
-	early_init_dt_scan_reserved_mem();
-
 	/*
 	 * reserve memory for DMA contigouos allocations,
 	 * must come from DMA area inside low memory
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 4d6d77ed9b9d..e194f957ca8c 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\tnop\n\t"
+	asm_volatile_goto("1:\tnop\n\t"
 		"nop\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S
index 4204d76af854..029e002a4ea0 100644
--- a/arch/mips/kernel/octeon_switch.S
+++ b/arch/mips/kernel/octeon_switch.S
@@ -73,7 +73,7 @@
 3:
 
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
-	PTR_L	t8, __stack_chk_guard
+	PTR_LA	t8, __stack_chk_guard
 	LONG_L	t9, TASK_STACK_CANARY(a1)
 	LONG_S	t9, 0(t8)
 #endif
diff --git a/arch/mips/kernel/r2300_switch.S b/arch/mips/kernel/r2300_switch.S
index 38af83f84c4a..20b7b040e76f 100644
--- a/arch/mips/kernel/r2300_switch.S
+++ b/arch/mips/kernel/r2300_switch.S
@@ -67,7 +67,7 @@ LEAF(resume)
 1:
 
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
-	PTR_L	t8, __stack_chk_guard
+	PTR_LA	t8, __stack_chk_guard
 	LONG_L	t9, TASK_STACK_CANARY(a1)
 	LONG_S	t9, 0(t8)
 #endif
diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S
index 921238a6bd26..078de5eaca8f 100644
--- a/arch/mips/kernel/r4k_switch.S
+++ b/arch/mips/kernel/r4k_switch.S
@@ -69,7 +69,7 @@
 1:
 
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
-	PTR_L	t8, __stack_chk_guard
+	PTR_LA	t8, __stack_chk_guard
 	LONG_L	t9, TASK_STACK_CANARY(a1)
 	LONG_S	t9, 0(t8)
 #endif
diff --git a/arch/parisc/include/asm/traps.h b/arch/parisc/include/asm/traps.h
index 1945f995f2df..4736020ba5ea 100644
--- a/arch/parisc/include/asm/traps.h
+++ b/arch/parisc/include/asm/traps.h
@@ -6,7 +6,7 @@ struct pt_regs;
 
 /* traps.c */
 void parisc_terminate(char *msg, struct pt_regs *regs,
-		int code, unsigned long offset);
+		int code, unsigned long offset) __noreturn __cold;
 
 /* mm/fault.c */
 void do_page_fault(struct pt_regs *regs, unsigned long code,
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index c035673209f7..b521c0adf4ec 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -602,6 +602,7 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
 }
+EXPORT_SYMBOL_GPL(flush_cache_page);
 
 #ifdef CONFIG_PARISC_TMPALIAS
 
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 8a252f2d6c08..2b96602e812f 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -72,7 +72,6 @@ enum ipi_message_type {
 	IPI_NOP=0,
 	IPI_RESCHEDULE=1,
 	IPI_CALL_FUNC,
-	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_START,
 	IPI_CPU_STOP,
 	IPI_CPU_TEST
@@ -164,11 +163,6 @@ ipi_interrupt(int irq, void *dev_id)
 				generic_smp_call_function_interrupt();
 				break;
 
-			case IPI_CALL_FUNC_SINGLE:
-				smp_debug(100, KERN_DEBUG "CPU%d IPI_CALL_FUNC_SINGLE\n", this_cpu);
-				generic_smp_call_function_single_interrupt();
-				break;
-
 			case IPI_CPU_START:
 				smp_debug(100, KERN_DEBUG "CPU%d IPI_CPU_START\n", this_cpu);
 				break;
@@ -260,7 +254,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_IPI_single(cpu, IPI_CALL_FUNC_SINGLE);
+	send_IPI_single(cpu, IPI_CALL_FUNC);
 }
 
 /*
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 04e47c6a4562..1cd1d0c83b6d 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -291,11 +291,6 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err)
 	do_exit(SIGSEGV);
 }
 
-int syscall_ipi(int (*syscall) (struct pt_regs *), struct pt_regs *regs)
-{
-	return syscall(regs);
-}
-
 /* gdb uses break 4,8 */
 #define GDB_BREAK_INSN 0x10004
 static void handle_gdb_break(struct pt_regs *regs, int wot)
@@ -805,14 +800,14 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	else {
 
 	    /*
-	     * The kernel should never fault on its own address space.
+	     * The kernel should never fault on its own address space,
+	     * unless pagefault_disable() was called before.
 	     */
 
-	    if (fault_space == 0) 
+	    if (fault_space == 0 && !in_atomic())
 	    {
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
 		parisc_terminate("Kernel Fault", regs, code, fault_address);
-	
 	    }
 	}
 
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index ac4370b1ca40..b5507ec06b84 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -56,7 +56,7 @@
 #ifdef __KERNEL__
 #include <linux/module.h>
 #include <linux/compiler.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #define s_space "%%sr1"
 #define d_space "%%sr2"
 #else
@@ -524,4 +524,17 @@ EXPORT_SYMBOL(copy_to_user);
 EXPORT_SYMBOL(copy_from_user);
 EXPORT_SYMBOL(copy_in_user);
 EXPORT_SYMBOL(memcpy);
+
+long probe_kernel_read(void *dst, const void *src, size_t size)
+{
+	unsigned long addr = (unsigned long)src;
+
+	if (size < 0 || addr < PAGE_SIZE)
+		return -EFAULT;
+
+	/* check for I/O space F_EXTEND(0xfff00000) access as well? */
+
+	return __probe_kernel_read(dst, src, size);
+}
+
 #endif
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 00c0ed333a3d..0293588d5b8c 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -171,20 +171,25 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 			      unsigned long address)
 {
 	struct vm_area_struct *vma, *prev_vma;
-	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
+	struct task_struct *tsk;
+	struct mm_struct *mm;
 	unsigned long acc_type;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	unsigned int flags;
 
-	if (in_atomic() || !mm)
+	if (in_atomic())
 		goto no_context;
 
+	tsk = current;
+	mm = tsk->mm;
+	if (!mm)
+		goto no_context;
+
+	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
 	acc_type = parisc_acctyp(code, regs->iir);
-
 	if (acc_type & VM_WRITE)
 		flags |= FAULT_FLAG_WRITE;
 retry:
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index ae098c438f00..f016bb699b5f 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -19,7 +19,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\n\t"
+	asm_volatile_goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 57d286a78f86..c7cb8c232d2f 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -495,14 +495,15 @@ void __do_irq(struct pt_regs *regs)
 void do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct thread_info *curtp, *irqtp;
+	struct thread_info *curtp, *irqtp, *sirqtp;
 
 	/* Switch to the irq stack to handle this */
 	curtp = current_thread_info();
 	irqtp = hardirq_ctx[raw_smp_processor_id()];
+	sirqtp = softirq_ctx[raw_smp_processor_id()];
 
 	/* Already there ? */
-	if (unlikely(curtp == irqtp)) {
+	if (unlikely(curtp == irqtp || curtp == sirqtp)) {
 		__do_irq(regs);
 		set_irq_regs(old_regs);
 		return;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 294b7af28cdd..c71103b8a748 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1066,7 +1066,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 BEGIN_FTR_SECTION
 	mfspr	r8, SPRN_DSCR
 	ld	r7, HSTATE_DSCR(r13)
-	std	r8, VCPU_DSCR(r7)
+	std	r8, VCPU_DSCR(r9)
 	mtspr	SPRN_DSCR, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 1c6a9d729df4..c65593abae8e 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -332,6 +332,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	unsigned long hva;
 	int pfnmap = 0;
 	int tsize = BOOK3E_PAGESZ_4K;
+	int ret = 0;
+	unsigned long mmu_seq;
+	struct kvm *kvm = vcpu_e500->vcpu.kvm;
+
+	/* used to check for invalidations in progress */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
 
 	/*
 	 * Translate guest physical to true physical, acquiring
@@ -449,6 +456,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
 	}
 
+	spin_lock(&kvm->mmu_lock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
@@ -457,10 +470,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	/* Clear i-cache for new pages */
 	kvmppc_mmu_flush_icache(pfn);
 
+out:
+	spin_unlock(&kvm->mmu_lock);
+
 	/* Drop refcount on page, so that mmu notifiers can clear it */
 	kvm_release_pfn_clean(pfn);
 
-	return 0;
+	return ret;
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 6c32190dc73e..346b1c85ffb4 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -15,7 +15,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("0:	brcl 0,0\n"
+	asm_volatile_goto("0:	brcl 0,0\n"
 		".pushsection __jump_table, \"aw\"\n"
 		ASM_ALIGN "\n"
 		ASM_PTR " 0b, %l[label], %0\n"
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index c84f33d51f7b..7dd21720e5b0 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -40,28 +40,26 @@ static inline void *load_real_addr(void *addr)
 }
 
 /*
- * Copy up to one page to vmalloc or real memory
+ * Copy real to virtual or real memory
  */
-static ssize_t copy_page_real(void *buf, void *src, size_t csize)
+static int copy_from_realmem(void *dest, void *src, size_t count)
 {
-	size_t size;
+	unsigned long size;
+	int rc;
 
-	if (is_vmalloc_addr(buf)) {
-		BUG_ON(csize >= PAGE_SIZE);
-		/* If buf is not page aligned, copy first part */
-		size = min(roundup(__pa(buf), PAGE_SIZE) - __pa(buf), csize);
-		if (size) {
-			if (memcpy_real(load_real_addr(buf), src, size))
-				return -EFAULT;
-			buf += size;
-			src += size;
-		}
-		/* Copy second part */
-		size = csize - size;
-		return (size) ? memcpy_real(load_real_addr(buf), src, size) : 0;
-	} else {
-		return memcpy_real(buf, src, csize);
-	}
+	if (!count)
+		return 0;
+	if (!is_vmalloc_or_module_addr(dest))
+		return memcpy_real(dest, src, count);
+	do {
+		size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK));
+		if (memcpy_real(load_real_addr(dest), src, size))
+			return -EFAULT;
+		count -= size;
+		dest += size;
+		src += size;
+	} while (count);
+	return 0;
 }
 
 /*
@@ -114,7 +112,7 @@ static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize,
 		rc = copy_to_user_real((void __force __user *) buf,
 				       (void *) src, csize);
 	else
-		rc = copy_page_real(buf, (void *) src, csize);
+		rc = copy_from_realmem(buf, (void *) src, csize);
 	return (rc == 0) ? rc : csize;
 }
 
@@ -210,7 +208,7 @@ int copy_from_oldmem(void *dest, void *src, size_t count)
 	if (OLDMEM_BASE) {
 		if ((unsigned long) src < OLDMEM_SIZE) {
 			copied = min(count, OLDMEM_SIZE - (unsigned long) src);
-			rc = memcpy_real(dest, src + OLDMEM_BASE, copied);
+			rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied);
 			if (rc)
 				return rc;
 		}
@@ -223,7 +221,7 @@ int copy_from_oldmem(void *dest, void *src, size_t count)
 				return rc;
 		}
 	}
-	return memcpy_real(dest + copied, src + copied, count - copied);
+	return copy_from_realmem(dest + copied, src + copied, count - copied);
 }
 
 /*
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index cc30d1fb000c..0dc2b6d0a1ec 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -266,6 +266,7 @@ sysc_sigpending:
 	tm	__TI_flags+3(%r12),_TIF_SYSCALL
 	jno	sysc_return
 	lm	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	l	%r10,__TI_sysc_table(%r12)	# 31 bit system call table
 	xr	%r8,%r8			# svc 0 returns -ENOSYS
 	clc	__PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2)
 	jnl	sysc_nr_ok		# invalid svc number -> do svc 0
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 2b2188b97c6a..e5b43c97a834 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -297,6 +297,7 @@ sysc_sigpending:
 	tm	__TI_flags+7(%r12),_TIF_SYSCALL
 	jno	sysc_return
 	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
 	lghi	%r8,0			# svc 0 returns -ENOSYS
 	llgh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
 	cghi	%r1,NR_syscalls
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 0ce9fb245034..d86e64eddb42 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -67,6 +67,11 @@ static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn)
 	case 0xac:	/* stnsm */
 	case 0xad:	/* stosm */
 		return -EINVAL;
+	case 0xc6:
+		switch (insn[0] & 0x0f) {
+		case 0x00: /* exrl   */
+			return -EINVAL;
+		}
 	}
 	switch (insn[0]) {
 	case 0x0101:	/* pr	 */
@@ -180,7 +185,6 @@ static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn)
 		break;
 	case 0xc6:
 		switch (insn[0] & 0x0f) {
-		case 0x00: /* exrl   */
 		case 0x02: /* pfdrl  */
 		case 0x04: /* cghrl  */
 		case 0x05: /* chrl   */
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 5080d16a832f..ec2e2e2aba7d 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -9,7 +9,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-		asm goto("1:\n\t"
+		asm_volatile_goto("1:\n\t"
 			 "nop\n\t"
 			 "nop\n\t"
 			 ".pushsection __jump_table,  \"aw\"\n\t"
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index d385eaadece7..709798460763 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -166,7 +166,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int o, int n)
  *
  * Atomically sets @v to @i and returns old @v
  */
-static inline u64 atomic64_xchg(atomic64_t *v, u64 n)
+static inline long long atomic64_xchg(atomic64_t *v, long long n)
 {
 	return xchg64(&v->counter, n);
 }
@@ -180,7 +180,8 @@ static inline u64 atomic64_xchg(atomic64_t *v, u64 n)
  * Atomically checks if @v holds @o and replaces it with @n if so.
  * Returns the old value at @v.
  */
-static inline u64 atomic64_cmpxchg(atomic64_t *v, u64 o, u64 n)
+static inline long long atomic64_cmpxchg(atomic64_t *v, long long o,
+					long long n)
 {
 	return cmpxchg64(&v->counter, o, n);
 }
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index 0d0395b1b152..1ad4a1f7d42b 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -80,7 +80,7 @@ static inline void atomic_set(atomic_t *v, int n)
 /* A 64bit atomic type */
 
 typedef struct {
-	u64 __aligned(8) counter;
+	long long counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(val) { (val) }
@@ -91,14 +91,14 @@ typedef struct {
  *
  * Atomically reads the value of @v.
  */
-static inline u64 atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
 	/*
 	 * Requires an atomic op to read both 32-bit parts consistently.
 	 * Casting away const is safe since the atomic support routines
 	 * do not write to memory if the value has not been modified.
 	 */
-	return _atomic64_xchg_add((u64 *)&v->counter, 0);
+	return _atomic64_xchg_add((long long *)&v->counter, 0);
 }
 
 /**
@@ -108,7 +108,7 @@ static inline u64 atomic64_read(const atomic64_t *v)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic64_add(u64 i, atomic64_t *v)
+static inline void atomic64_add(long long i, atomic64_t *v)
 {
 	_atomic64_xchg_add(&v->counter, i);
 }
@@ -120,7 +120,7 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
 	smp_mb();  /* barrier for proper semantics */
 	return _atomic64_xchg_add(&v->counter, i) + i;
@@ -135,7 +135,8 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns non-zero if @v was not @u, and zero otherwise.
  */
-static inline u64 atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+static inline long long atomic64_add_unless(atomic64_t *v, long long a,
+					long long u)
 {
 	smp_mb();  /* barrier for proper semantics */
 	return _atomic64_xchg_add_unless(&v->counter, a, u) != u;
@@ -151,7 +152,7 @@ static inline u64 atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
  * atomic64_set() can't be just a raw store, since it would be lost if it
  * fell between the load and store of one of the other atomic ops.
  */
-static inline void atomic64_set(atomic64_t *v, u64 n)
+static inline void atomic64_set(atomic64_t *v, long long n)
 {
 	_atomic64_xchg(&v->counter, n);
 }
@@ -236,11 +237,13 @@ extern struct __get_user __atomic_xchg_add_unless(volatile int *p,
 extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
-extern u64 __atomic64_cmpxchg(volatile u64 *p, int *lock, u64 o, u64 n);
-extern u64 __atomic64_xchg(volatile u64 *p, int *lock, u64 n);
-extern u64 __atomic64_xchg_add(volatile u64 *p, int *lock, u64 n);
-extern u64 __atomic64_xchg_add_unless(volatile u64 *p,
-				      int *lock, u64 o, u64 n);
+extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
+					long long o, long long n);
+extern long long __atomic64_xchg(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_xchg_add(volatile long long *p, int *lock,
+					long long n);
+extern long long __atomic64_xchg_add_unless(volatile long long *p,
+					int *lock, long long o, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);
diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h
index 4001d5eab4bb..0ccda3c425be 100644
--- a/arch/tile/include/asm/cmpxchg.h
+++ b/arch/tile/include/asm/cmpxchg.h
@@ -35,10 +35,10 @@ int _atomic_xchg(int *ptr, int n);
 int _atomic_xchg_add(int *v, int i);
 int _atomic_xchg_add_unless(int *v, int a, int u);
 int _atomic_cmpxchg(int *ptr, int o, int n);
-u64 _atomic64_xchg(u64 *v, u64 n);
-u64 _atomic64_xchg_add(u64 *v, u64 i);
-u64 _atomic64_xchg_add_unless(u64 *v, u64 a, u64 u);
-u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
+long long _atomic64_xchg(long long *v, long long n);
+long long _atomic64_xchg_add(long long *v, long long i);
+long long _atomic64_xchg_add_unless(long long *v, long long a, long long u);
+long long _atomic64_cmpxchg(long long *v, long long o, long long n);
 
 #define xchg(ptr, n)							\
 	({								\
@@ -53,7 +53,8 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
 		if (sizeof(*(ptr)) != 4)				\
 			__cmpxchg_called_with_bad_pointer();		\
 		smp_mb();						\
-		(typeof(*(ptr)))_atomic_cmpxchg((int *)ptr, (int)o, (int)n); \
+		(typeof(*(ptr)))_atomic_cmpxchg((int *)ptr, (int)o,	\
+						(int)n);		\
 	})
 
 #define xchg64(ptr, n)							\
@@ -61,7 +62,8 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
 		if (sizeof(*(ptr)) != 8)				\
 			__xchg_called_with_bad_pointer();		\
 		smp_mb();						\
-		(typeof(*(ptr)))_atomic64_xchg((u64 *)(ptr), (u64)(n));	\
+		(typeof(*(ptr)))_atomic64_xchg((long long *)(ptr),	\
+						(long long)(n));	\
 	})
 
 #define cmpxchg64(ptr, o, n)						\
@@ -69,7 +71,8 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
 		if (sizeof(*(ptr)) != 8)				\
 			__cmpxchg_called_with_bad_pointer();		\
 		smp_mb();						\
-		(typeof(*(ptr)))_atomic64_cmpxchg((u64 *)ptr, (u64)o, (u64)n); \
+		(typeof(*(ptr)))_atomic64_cmpxchg((long long *)ptr,	\
+					(long long)o, (long long)n);	\
 	})
 
 #else
@@ -81,10 +84,11 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
 		switch (sizeof(*(ptr))) {				\
 		case 4:							\
 			__x = (typeof(__x))(unsigned long)		\
-				__insn_exch4((ptr), (u32)(unsigned long)(n)); \
+				__insn_exch4((ptr),			\
+					(u32)(unsigned long)(n));	\
 			break;						\
 		case 8:							\
-			__x = (typeof(__x))			\
+			__x = (typeof(__x))				\
 				__insn_exch((ptr), (unsigned long)(n));	\
 			break;						\
 		default:						\
@@ -103,10 +107,12 @@ u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n);
 		switch (sizeof(*(ptr))) {				\
 		case 4:							\
 			__x = (typeof(__x))(unsigned long)		\
-				__insn_cmpexch4((ptr), (u32)(unsigned long)(n)); \
+				__insn_cmpexch4((ptr),			\
+					(u32)(unsigned long)(n));	\
 			break;						\
 		case 8:							\
-			__x = (typeof(__x))__insn_cmpexch((ptr), (u64)(n)); \
+			__x = (typeof(__x))__insn_cmpexch((ptr),	\
+						(long long)(n));	\
 			break;						\
 		default:						\
 			__cmpxchg_called_with_bad_pointer();		\
diff --git a/arch/tile/include/asm/percpu.h b/arch/tile/include/asm/percpu.h
index 63294f5a8efb..4f7ae39fa202 100644
--- a/arch/tile/include/asm/percpu.h
+++ b/arch/tile/include/asm/percpu.h
@@ -15,9 +15,37 @@
 #ifndef _ASM_TILE_PERCPU_H
 #define _ASM_TILE_PERCPU_H
 
-register unsigned long __my_cpu_offset __asm__("tp");
-#define __my_cpu_offset __my_cpu_offset
-#define set_my_cpu_offset(tp) (__my_cpu_offset = (tp))
+register unsigned long my_cpu_offset_reg asm("tp");
+
+#ifdef CONFIG_PREEMPT
+/*
+ * For full preemption, we can't just use the register variable
+ * directly, since we need barrier() to hazard against it, causing the
+ * compiler to reload anything computed from a previous "tp" value.
+ * But we also don't want to use volatile asm, since we'd like the
+ * compiler to be able to cache the value across multiple percpu reads.
+ * So we use a fake stack read as a hazard against barrier().
+ * The 'U' constraint is like 'm' but disallows postincrement.
+ */
+static inline unsigned long __my_cpu_offset(void)
+{
+	unsigned long tp;
+	register unsigned long *sp asm("sp");
+	asm("move %0, tp" : "=r" (tp) : "U" (*sp));
+	return tp;
+}
+#define __my_cpu_offset __my_cpu_offset()
+#else
+/*
+ * We don't need to hazard against barrier() since "tp" doesn't ever
+ * change with PREEMPT_NONE, and with PREEMPT_VOLUNTARY it only
+ * changes at function call points, at which we are already re-reading
+ * the value of "tp" due to "my_cpu_offset_reg" being a global variable.
+ */
+#define __my_cpu_offset my_cpu_offset_reg
+#endif
+
+#define set_my_cpu_offset(tp) (my_cpu_offset_reg = (tp))
 
 #include <asm-generic/percpu.h>
 
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index df27a1fd94a3..531f4c365351 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -66,7 +66,7 @@ static struct hardwall_type hardwall_types[] = {
 		0,
 		"udn",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_UDN].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_UDN].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_UDN].lock),
 		NULL
 	},
 #ifndef __tilepro__
@@ -77,7 +77,7 @@ static struct hardwall_type hardwall_types[] = {
 		1,  /* disabled pending hypervisor support */
 		"idn",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_IDN].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_IDN].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_IDN].lock),
 		NULL
 	},
 	{  /* access to user-space IPI */
@@ -87,7 +87,7 @@ static struct hardwall_type hardwall_types[] = {
 		0,
 		"ipi",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_IPI].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_IPI].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_IPI].lock),
 		NULL
 	},
 #endif
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index 088d5c141e68..2cbe6d5dd6b0 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -815,6 +815,9 @@ STD_ENTRY(interrupt_return)
 	}
 	bzt     r28, 1f
 	bnz     r29, 1f
+	/* Disable interrupts explicitly for preemption. */
+	IRQ_DISABLE(r20,r21)
+	TRACE_IRQS_OFF
 	jal     preempt_schedule_irq
 	FEEDBACK_REENTER(interrupt_return)
 1:
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index ec755d3f3734..b8fc497f2437 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -841,6 +841,9 @@ STD_ENTRY(interrupt_return)
 	}
 	beqzt   r28, 1f
 	bnez    r29, 1f
+	/* Disable interrupts explicitly for preemption. */
+	IRQ_DISABLE(r20,r21)
+	TRACE_IRQS_OFF
 	jal     preempt_schedule_irq
 	FEEDBACK_REENTER(interrupt_return)
 1:
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index 362284af3afd..c93977a62116 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -23,6 +23,7 @@
 #include <linux/mmzone.h>
 #include <linux/dcache.h>
 #include <linux/fs.h>
+#include <linux/string.h>
 #include <asm/backtrace.h>
 #include <asm/page.h>
 #include <asm/ucontext.h>
@@ -332,21 +333,18 @@ static void describe_addr(struct KBacktraceIterator *kbt,
 	}
 
 	if (vma->vm_file) {
-		char *s;
 		p = d_path(&vma->vm_file->f_path, buf, bufsize);
 		if (IS_ERR(p))
 			p = "?";
-		s = strrchr(p, '/');
-		if (s)
-			p = s+1;
+		name = kbasename(p);
 	} else {
-		p = "anon";
+		name = "anon";
 	}
 
 	/* Generate a string description of the vma info. */
-	namelen = strlen(p);
+	namelen = strlen(name);
 	remaining = (bufsize - 1) - namelen;
-	memmove(buf, p, namelen);
+	memmove(buf, name, namelen);
 	snprintf(buf + namelen, remaining, "[%lx+%lx] ",
 		 vma->vm_start, vma->vm_end - vma->vm_start);
 }
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index 759efa337be8..c89b211fd9e7 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -107,19 +107,19 @@ unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask)
 EXPORT_SYMBOL(_atomic_xor);
 
 
-u64 _atomic64_xchg(u64 *v, u64 n)
+long long _atomic64_xchg(long long *v, long long n)
 {
 	return __atomic64_xchg(v, __atomic_setup(v), n);
 }
 EXPORT_SYMBOL(_atomic64_xchg);
 
-u64 _atomic64_xchg_add(u64 *v, u64 i)
+long long _atomic64_xchg_add(long long *v, long long i)
 {
 	return __atomic64_xchg_add(v, __atomic_setup(v), i);
 }
 EXPORT_SYMBOL(_atomic64_xchg_add);
 
-u64 _atomic64_xchg_add_unless(u64 *v, u64 a, u64 u)
+long long _atomic64_xchg_add_unless(long long *v, long long a, long long u)
 {
 	/*
 	 * Note: argument order is switched here since it is easier
@@ -130,7 +130,7 @@ u64 _atomic64_xchg_add_unless(u64 *v, u64 a, u64 u)
 }
 EXPORT_SYMBOL(_atomic64_xchg_add_unless);
 
-u64 _atomic64_cmpxchg(u64 *v, u64 o, u64 n)
+long long _atomic64_cmpxchg(long long *v, long long o, long long n)
 {
 	return __atomic64_cmpxchg(v, __atomic_setup(v), o, n);
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ee2fb9d37745..f67e839f06c8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -860,7 +860,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+	depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
 	---help---
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -885,11 +885,11 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
+	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
 
 config X86_IO_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
+	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI
 
 config X86_VISWS_APIC
 	def_bool y
@@ -1033,6 +1033,7 @@ config X86_REBOOTFIXUPS
 
 config MICROCODE
 	tristate "CPU microcode loading support"
+	depends on CPU_SUP_AMD || CPU_SUP_INTEL
 	select FW_LOADER
 	---help---
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index d3f5c63078d8..89270b4318db 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -374,7 +374,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 		 * Catch too early usage of this before alternatives
 		 * have run.
 		 */
-		asm goto("1: jmp %l[t_warn]\n"
+		asm_volatile_goto("1: jmp %l[t_warn]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -388,7 +388,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 
 #endif
 
-		asm goto("1: jmp %l[t_no]\n"
+		asm_volatile_goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -453,7 +453,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
  * have. Thus, we force the jump to the widest, 4-byte, signed relative
  * offset even though the last would often fit in less bytes.
  */
-		asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+		asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"		/* src offset */
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 64507f35800c..6a2cefb4395a 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:"
+	asm_volatile_goto("1:"
 		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index e7e6751648ed..07537a44216e 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -20,7 +20,7 @@
 static inline void __mutex_fastpath_lock(atomic_t *v,
 					 void (*fail_fn)(atomic_t *))
 {
-	asm volatile goto(LOCK_PREFIX "   decl %0\n"
+	asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
 			  "   jns %l[exit]\n"
 			  : : "m" (v->counter)
 			  : "memory", "cc"
@@ -75,7 +75,7 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count)
 static inline void __mutex_fastpath_unlock(atomic_t *v,
 					   void (*fail_fn)(atomic_t *))
 {
-	asm volatile goto(LOCK_PREFIX "   incl %0\n"
+	asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
 			  "   jg %l[exit]\n"
 			  : : "m" (v->counter)
 			  : "memory", "cc"
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1191ac1c9d25..a419814cea57 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -113,7 +113,7 @@ static int __init early_get_pnodeid(void)
 		break;
 	case UV3_HUB_PART_NUMBER:
 	case UV3_HUB_PART_NUMBER_X:
-		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1;
+		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
 		break;
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 897783b3302a..9d8449158cf9 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1888,10 +1888,7 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
-		return;
-
-	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+	if (!sched_clock_stable)
 		return;
 
 	userpg->cap_user_time = 1;
@@ -1899,10 +1896,8 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
-	if (sched_clock_stable && !check_tsc_disabled()) {
-		userpg->cap_user_time_zero = 1;
-		userpg->time_zero = this_cpu_read(cyc2ns_offset);
-	}
+	userpg->cap_user_time_zero = 1;
+	userpg->time_zero = this_cpu_read(cyc2ns_offset);
 }
 
 /*
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 697b93af02dd..a0e2a8a80c94 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -775,11 +775,22 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
-	printk(KERN_INFO "KVM setup paravirtual spinlock\n");
+	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
+	pv_lock_ops.unlock_kick = kvm_unlock_kick;
+}
+
+static __init int kvm_spinlock_init_jump(void)
+{
+	if (!kvm_para_available())
+		return 0;
+	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+		return 0;
 
 	static_key_slow_inc(&paravirt_ticketlocks_enabled);
+	printk(KERN_INFO "KVM setup paravirtual spinlock\n");
 
-	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
-	pv_lock_ops.unlock_kick = kvm_unlock_kick;
+	return 0;
 }
+early_initcall(kvm_spinlock_init_jump);
+
 #endif	/* CONFIG_PARAVIRT_SPINLOCKS */
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e643e744e4d8..7e920bff99a3 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -326,6 +326,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Latitude E5410. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E5410",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5410"),
+		},
+	},
 	{	/* Handle problems with rebooting on the Latitude E5420. */
 		.callback = set_pci_reboot,
 		.ident = "Dell Latitude E5420",
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3b8e7459dd4d..2b2fce1b2009 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3255,25 +3255,29 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 
 static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (!test_bit(VCPU_EXREG_PDPTR,
 		      (unsigned long *)&vcpu->arch.regs_dirty))
 		return;
 
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]);
-		vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]);
-		vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]);
-		vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]);
+		vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
+		vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
+		vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
+		vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
 	}
 }
 
 static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
-		vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
-		vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
-		vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+		mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+		mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+		mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
 
 	__set_bit(VCPU_EXREG_PDPTR,
@@ -7777,10 +7781,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
 		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
 		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
-		__clear_bit(VCPU_EXREG_PDPTR,
-				(unsigned long *)&vcpu->arch.regs_avail);
-		__clear_bit(VCPU_EXREG_PDPTR,
-				(unsigned long *)&vcpu->arch.regs_dirty);
 	}
 
 	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index d1e4777b4e75..31d04758b76f 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -278,6 +278,15 @@ static void __init xen_smp_prepare_boot_cpu(void)
 		   old memory can be recycled */
 		make_lowmem_page_readwrite(xen_initial_gdt);
 
+#ifdef CONFIG_X86_32
+		/*
+		 * Xen starts us with XEN_FLAT_RING1_DS, but linux code
+		 * expects __USER_DS
+		 */
+		loadsegment(ds, __USER_DS);
+		loadsegment(es, __USER_DS);
+#endif
+
 		xen_filter_cpu_maps();
 		xen_setup_vcpu_info_placement();
 	}