Merge tag 'v4.3-rc6' into locking/core, to pick up fixes before applying new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

60 files changed, 346 insertions, 194 deletions

diff --git a/arch/alpha/include/asm/word-at-a-time.h b/arch/alpha/include/asm/word-at-a-time.h
index 6b340d0f1521..902e6ab00a06 100644
--- a/arch/alpha/include/asm/word-at-a-time.h
+++ b/arch/alpha/include/asm/word-at-a-time.h
@@ -52,4 +52,6 @@ static inline unsigned long find_zero(unsigned long bits)
 #endif
 }
 
+#define zero_bytemask(mask) ((2ul << (find_zero(mask) * 8)) - 1)
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 233159d2eaab..bb8fa023d574 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -578,7 +578,7 @@ dtb-$(CONFIG_MACH_SUN4I) += \
 	sun4i-a10-hackberry.dtb \
 	sun4i-a10-hyundai-a7hd.dtb \
 	sun4i-a10-inet97fv2.dtb \
-	sun4i-a10-itead-iteaduino-plus.dts \
+	sun4i-a10-itead-iteaduino-plus.dtb \
 	sun4i-a10-jesurun-q5.dtb \
 	sun4i-a10-marsboard.dtb \
 	sun4i-a10-mini-xplus.dtb \
diff --git a/arch/arm/boot/dts/exynos4412.dtsi b/arch/arm/boot/dts/exynos4412.dtsi
index ca0e3c15977f..294cfe40388d 100644
--- a/arch/arm/boot/dts/exynos4412.dtsi
+++ b/arch/arm/boot/dts/exynos4412.dtsi
@@ -98,6 +98,7 @@
 			opp-hz = /bits/ 64 <800000000>;
 			opp-microvolt = <1000000>;
 			clock-latency-ns = <200000>;
+			opp-suspend;
 		};
 		opp07 {
 			opp-hz = /bits/ 64 <900000000>;
diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts
index 15aea760c1da..c625e71217aa 100644
--- a/arch/arm/boot/dts/exynos5250-smdk5250.dts
+++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts
@@ -197,6 +197,7 @@
 				regulator-name = "P1.8V_LDO_OUT10";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
 			};
 
 			ldo11_reg: LDO11 {
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index df9aee92ecf4..1b3d6c769a3c 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -1117,7 +1117,7 @@
 		interrupt-parent = <&combiner>;
 		interrupts = <3 0>;
 		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_FIMD1M0>, <&clock CLK_FIMD1>;
+		clocks = <&clock CLK_SMMU_FIMD1M1>, <&clock CLK_FIMD1>;
 		power-domains = <&disp_pd>;
 		#iommu-cells = <0>;
 	};
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
index 79ffdfe712aa..3b43e57845ae 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
@@ -472,7 +472,6 @@
 	 */
 	pinctrl-0 = <&pwm0_out &pwm1_out &pwm2_out &pwm3_out>;
 	pinctrl-names = "default";
-	samsung,pwm-outputs = <0>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-qsrb.dts b/arch/arm/boot/dts/imx53-qsrb.dts
index 66e47de5e826..96d7eede412e 100644
--- a/arch/arm/boot/dts/imx53-qsrb.dts
+++ b/arch/arm/boot/dts/imx53-qsrb.dts
@@ -36,7 +36,7 @@
 		pinctrl-0 = <&pinctrl_pmic>;
 		reg = <0x08>;
 		interrupt-parent = <&gpio5>;
-		interrupts = <23 0x8>;
+		interrupts = <23 IRQ_TYPE_LEVEL_HIGH>;
 		regulators {
 			sw1_reg: sw1a {
 				regulator-name = "SW1";
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index c3e3ca9362fb..cd170376eaca 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -15,6 +15,7 @@
 #include <dt-bindings/clock/imx5-clock.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/irq.h>
 
 / {
 	aliases {
diff --git a/arch/arm/boot/dts/imx6qdl-rex.dtsi b/arch/arm/boot/dts/imx6qdl-rex.dtsi
index 3373fd958e95..a50356243888 100644
--- a/arch/arm/boot/dts/imx6qdl-rex.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-rex.dtsi
@@ -35,7 +35,6 @@
 			compatible = "regulator-fixed";
 			reg = <1>;
 			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usbh1>;
 			regulator-name = "usbh1_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
@@ -47,7 +46,6 @@
 			compatible = "regulator-fixed";
 			reg = <2>;
 			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usbotg>;
 			regulator-name = "usb_otg_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index a0b2a79cbfbd..4624d0f2a754 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -1627,6 +1627,7 @@
 				"mix.0", "mix.1",
 				"dvc.0", "dvc.1",
 				"clk_a", "clk_b", "clk_c", "clk_i";
+		power-domains = <&cpg_clocks>;
 
 		status = "disabled";
 
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 831525dd39a6..1666c8a6b143 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -1677,6 +1677,7 @@
 				"mix.0", "mix.1",
 				"dvc.0", "dvc.1",
 				"clk_a", "clk_b", "clk_c", "clk_i";
+		power-domains = <&cpg_clocks>;
 
 		status = "disabled";
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 2bebaa286f9a..391230c3dc93 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -107,7 +107,7 @@
 				720000	1200000
 				528000	1100000
 				312000	1000000
-				144000	900000
+				144000	1000000
 				>;
 			#cooling-cells = <2>;
 			cooling-min-level = <0>;
diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c
index 9bdf54795f05..56978199c479 100644
--- a/arch/arm/mach-exynos/mcpm-exynos.c
+++ b/arch/arm/mach-exynos/mcpm-exynos.c
@@ -20,6 +20,7 @@
 #include <asm/cputype.h>
 #include <asm/cp15.h>
 #include <asm/mcpm.h>
+#include <asm/smp_plat.h>
 
 #include "regs-pmu.h"
 #include "common.h"
@@ -70,7 +71,31 @@ static int exynos_cpu_powerup(unsigned int cpu, unsigned int cluster)
 		cluster >= EXYNOS5420_NR_CLUSTERS)
 		return -EINVAL;
 
-	exynos_cpu_power_up(cpunr);
+	if (!exynos_cpu_power_state(cpunr)) {
+		exynos_cpu_power_up(cpunr);
+
+		/*
+		 * This assumes the cluster number of the big cores(Cortex A15)
+		 * is 0 and the Little cores(Cortex A7) is 1.
+		 * When the system was booted from the Little core,
+		 * they should be reset during power up cpu.
+		 */
+		if (cluster &&
+		    cluster == MPIDR_AFFINITY_LEVEL(cpu_logical_map(0), 1)) {
+			/*
+			 * Before we reset the Little cores, we should wait
+			 * the SPARE2 register is set to 1 because the init
+			 * codes of the iROM will set the register after
+			 * initialization.
+			 */
+			while (!pmu_raw_readl(S5P_PMU_SPARE2))
+				udelay(10);
+
+			pmu_raw_writel(EXYNOS5420_KFC_CORE_RESET(cpu),
+					EXYNOS_SWRESET);
+		}
+	}
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-exynos/regs-pmu.h b/arch/arm/mach-exynos/regs-pmu.h
index b7614333d296..fba9068ed260 100644
--- a/arch/arm/mach-exynos/regs-pmu.h
+++ b/arch/arm/mach-exynos/regs-pmu.h
@@ -513,6 +513,12 @@ static inline unsigned int exynos_pmu_cpunr(unsigned int mpidr)
 #define SPREAD_ENABLE						0xF
 #define SPREAD_USE_STANDWFI					0xF
 
+#define EXYNOS5420_KFC_CORE_RESET0				BIT(8)
+#define EXYNOS5420_KFC_ETM_RESET0				BIT(20)
+
+#define EXYNOS5420_KFC_CORE_RESET(_nr)				\
+	((EXYNOS5420_KFC_CORE_RESET0 | EXYNOS5420_KFC_ETM_RESET0) << (_nr))
+
 #define EXYNOS5420_BB_CON1					0x0784
 #define EXYNOS5420_BB_SEL_EN					BIT(31)
 #define EXYNOS5420_BB_PMOS_EN					BIT(7)
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index f9914d7c1bb0..d10b5d483022 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -42,7 +42,7 @@ endif
 CHECKFLAGS	+= -D__aarch64__
 
 ifeq ($(CONFIG_ARM64_ERRATUM_843419), y)
-CFLAGS_MODULE	+= -mcmodel=large
+KBUILD_CFLAGS_MODULE	+= -mcmodel=large
 endif
 
 # Default value
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 3bc498c250dc..41e58fe3c041 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		388
+#define __NR_compat_syscalls		390
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index cef934a90f17..5b925b761a2a 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -797,3 +797,12 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create)
 __SYSCALL(__NR_bpf, sys_bpf)
 #define __NR_execveat 387
 __SYSCALL(__NR_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 388
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 389
+__SYSCALL(__NR_membarrier, sys_membarrier)
+
+/*
+ * Please add new compat syscalls above this comment and update
+ * __NR_compat_syscalls in asm/unistd.h.
+ */
diff --git a/arch/arm64/include/uapi/asm/signal.h b/arch/arm64/include/uapi/asm/signal.h
index 8d1e7236431b..991bf5db2ca1 100644
--- a/arch/arm64/include/uapi/asm/signal.h
+++ b/arch/arm64/include/uapi/asm/signal.h
@@ -19,6 +19,9 @@
 /* Required for AArch32 compatibility. */
 #define SA_RESTORER	0x04000000
 
+#define MINSIGSTKSZ 5120
+#define SIGSTKSZ    16384
+
 #include <asm-generic/signal.h>
 
 #endif
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index cebf78661a55..253021ef2769 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -201,7 +201,7 @@ void unregister_step_hook(struct step_hook *hook)
 }
 
 /*
- * Call registered single step handers
+ * Call registered single step handlers
  * There is no Syndrome info to check for determining the handler.
  * So we call all the registered handlers, until the right handler is
  * found which returns zero.
@@ -271,20 +271,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
  * Use reader/writer locks instead of plain spinlock.
  */
 static LIST_HEAD(break_hook);
-static DEFINE_RWLOCK(break_hook_lock);
+static DEFINE_SPINLOCK(break_hook_lock);
 
 void register_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_add(&hook->node, &break_hook);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_add_rcu(&hook->node, &break_hook);
+	spin_unlock(&break_hook_lock);
 }
 
 void unregister_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_del(&hook->node);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_del_rcu(&hook->node);
+	spin_unlock(&break_hook_lock);
+	synchronize_rcu();
 }
 
 static int call_break_hook(struct pt_regs *regs, unsigned int esr)
@@ -292,11 +293,11 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 	struct break_hook *hook;
 	int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
 
-	read_lock(&break_hook_lock);
-	list_for_each_entry(hook, &break_hook, node)
+	rcu_read_lock();
+	list_for_each_entry_rcu(hook, &break_hook, node)
 		if ((esr & hook->esr_mask) == hook->esr_val)
 			fn = hook->fn;
-	read_unlock(&break_hook_lock);
+	rcu_read_unlock();
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index f341866aa810..c08b9ad6f429 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -85,7 +85,7 @@ bool aarch64_insn_is_branch_imm(u32 insn)
 		aarch64_insn_is_bcond(insn));
 }
 
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap)
 {
@@ -131,13 +131,13 @@ static int __kprobes __aarch64_insn_write(void *addr, u32 insn)
 	unsigned long flags = 0;
 	int ret;
 
-	spin_lock_irqsave(&patch_lock, flags);
+	raw_spin_lock_irqsave(&patch_lock, flags);
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
 	ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE);
 
 	patch_unmap(FIX_TEXT_POKE0);
-	spin_unlock_irqrestore(&patch_lock, flags);
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 6bab21f84a9f..232247945b1c 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -364,6 +364,8 @@ static void __init relocate_initrd(void)
 		to_free = ram_end - orig_start;
 
 	size = orig_end - orig_start;
+	if (!size)
+		return;
 
 	/* initrd needs to be relocated completely inside linear mapping */
 	new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn),
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index aba9ead1384c..9fadf6d7039b 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -287,6 +287,7 @@ retry:
 			 * starvation.
 			 */
 			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			mm_flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 70e6ae1e7006..373cb23301e3 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -73,4 +73,5 @@ generic-y += uaccess.h
 generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 9e777cd42b67..d10fd80dbb7e 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -256,6 +256,7 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si
  */
 #define ioremap_nocache(offset, size)					\
 	__ioremap_mode((offset), (size), _CACHE_UNCACHED)
+#define ioremap_uc ioremap_nocache
 
 /*
  * ioremap_cachable -	map bus memory into CPU space
diff --git a/arch/mips/include/uapi/asm/swab.h b/arch/mips/include/uapi/asm/swab.h
index c4ddc4f0d2dc..23cd9b118c9e 100644
--- a/arch/mips/include/uapi/asm/swab.h
+++ b/arch/mips/include/uapi/asm/swab.h
@@ -13,16 +13,15 @@
 
 #define __SWAB_64_THRU_32__
 
-#if (defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) ||		\
-    defined(_MIPS_ARCH_LOONGSON3A)
+#if !defined(__mips16) &&					\
+	((defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) ||	\
+	 defined(_MIPS_ARCH_LOONGSON3A))
 
-static inline __attribute__((nomips16)) __attribute_const__
-		__u16 __arch_swab16(__u16 x)
+static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips32r2		\n"
-	"	.set	nomips16		\n"
 	"	wsbh	%0, %1			\n"
 	"	.set	pop			\n"
 	: "=r" (x)
@@ -32,13 +31,11 @@ static inline __attribute__((nomips16)) __attribute_const__
 }
 #define __arch_swab16 __arch_swab16
 
-static inline __attribute__((nomips16)) __attribute_const__
-		__u32 __arch_swab32(__u32 x)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips32r2		\n"
-	"	.set	nomips16		\n"
 	"	wsbh	%0, %1			\n"
 	"	rotr	%0, %0, 16		\n"
 	"	.set	pop			\n"
@@ -54,13 +51,11 @@ static inline __attribute__((nomips16)) __attribute_const__
  * 64-bit kernel on r2 CPUs.
  */
 #ifdef __mips64
-static inline __attribute__((nomips16)) __attribute_const__
-		__u64 __arch_swab64(__u64 x)
+static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 {
 	__asm__(
 	"	.set	push			\n"
 	"	.set	arch=mips64r2		\n"
-	"	.set	nomips16		\n"
 	"	dsbh	%0, %1			\n"
 	"	dshd	%0, %0			\n"
 	"	.set	pop			\n"
@@ -71,5 +66,5 @@ static inline __attribute__((nomips16)) __attribute_const__
 }
 #define __arch_swab64 __arch_swab64
 #endif /* __mips64 */
-#endif /* MIPS R2 or newer or Loongson 3A */
+#endif /* (not __mips16) and (MIPS R2 or newer or Loongson 3A) */
 #endif /* _ASM_SWAB_H */
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 6bc0ee4b1070..2c041b535a64 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -111,7 +111,7 @@ CONFIG_SCSI_QLA_FC=m
 CONFIG_SCSI_QLA_ISCSI=m
 CONFIG_SCSI_LPFC=m
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_ALUA=m
 CONFIG_ATA=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 7991f37e5fe2..36871a4bfa54 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -114,7 +114,7 @@ CONFIG_SCSI_QLA_FC=m
 CONFIG_SCSI_QLA_ISCSI=m
 CONFIG_SCSI_LPFC=m
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_ALUA=m
 CONFIG_ATA=y
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index ac1662956e0c..ab9f4e0ed4cf 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -7,4 +7,3 @@ generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += rwsem.h
 generic-y += vtime.h
-generic-y += word-at-a-time.h
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index cab6753f1be5..3f191f573d4f 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -61,8 +61,13 @@ struct machdep_calls {
 					       unsigned long addr,
 					       unsigned char *hpte_slot_array,
 					       int psize, int ssize, int local);
-	/* special for kexec, to be called in real mode, linear mapping is
-	 * destroyed as well */
+	/*
+	 * Special for kexec.
+	 * To be called in real mode with interrupts disabled. No locks are
+	 * taken as such, concurrent access on pre POWER5 hardware could result
+	 * in a deadlock.
+	 * The linear mapping is destroyed as well.
+	 */
 	void		(*hpte_clear_all)(void);
 
 	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,
diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h
index 5b3a903adae6..e4396a7d0f7c 100644
--- a/arch/powerpc/include/asm/word-at-a-time.h
+++ b/arch/powerpc/include/asm/word-at-a-time.h
@@ -40,6 +40,11 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
 	return (val + c->high_bits) & ~rhs;
 }
 
+static inline unsigned long zero_bytemask(unsigned long mask)
+{
+	return ~1ul << __fls(mask);
+}
+
 #else
 
 #ifdef CONFIG_64BIT
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 13befa35d8a8..c8822af10a58 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -582,13 +582,21 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
  * be when they isi), and we are the only one left.  We rely on our kernel
  * mapping being 0xC0's and the hardware ignoring those two real bits.
  *
+ * This must be called with interrupts disabled.
+ *
+ * Taking the native_tlbie_lock is unsafe here due to the possibility of
+ * lockdep being on. On pre POWER5 hardware, not taking the lock could
+ * cause deadlock. POWER5 and newer not taking the lock is fine. This only
+ * gets called during boot before secondary CPUs have come up and during
+ * crashdump and all bets are off anyway.
+ *
  * TODO: add batching support when enabled.  remember, no dynamic memory here,
  * athough there is the control page available...
  */
 static void native_hpte_clear(void)
 {
 	unsigned long vpn = 0;
-	unsigned long slot, slots, flags;
+	unsigned long slot, slots;
 	struct hash_pte *hptep = htab_address;
 	unsigned long hpte_v;
 	unsigned long pteg_count;
@@ -596,13 +604,6 @@ static void native_hpte_clear(void)
 
 	pteg_count = htab_hash_mask + 1;
 
-	local_irq_save(flags);
-
-	/* we take the tlbie lock and hold it.  Some hardware will
-	 * deadlock if we try to tlbie from two processors at once.
-	 */
-	raw_spin_lock(&native_tlbie_lock);
-
 	slots = pteg_count * HPTES_PER_GROUP;
 
 	for (slot = 0; slot < slots; slot++, hptep++) {
@@ -614,8 +615,8 @@ static void native_hpte_clear(void)
 		hpte_v = be64_to_cpu(hptep->v);
 
 		/*
-		 * Call __tlbie() here rather than tlbie() since we
-		 * already hold the native_tlbie_lock.
+		 * Call __tlbie() here rather than tlbie() since we can't take the
+		 * native_tlbie_lock.
 		 */
 		if (hpte_v & HPTE_V_VALID) {
 			hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
@@ -625,8 +626,6 @@ static void native_hpte_clear(void)
 	}
 
 	asm volatile("eieio; tlbsync; ptesync":::"memory");
-	raw_spin_unlock(&native_tlbie_lock);
-	local_irq_restore(flags);
 }
 
 /*
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 230f3a7cdea4..4296d55e88f3 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -487,9 +487,12 @@ int opal_machine_check(struct pt_regs *regs)
 	 *    PRD component would have already got notified about this
 	 *    error through other channels.
 	 *
-	 * In any case, let us just fall through. We anyway heading
-	 * down to panic path.
+	 * If hardware marked this as an unrecoverable MCE, we are
+	 * going to panic anyway. Even if it didn't, it's not safe to
+	 * continue at this point, so we should explicitly panic.
 	 */
+
+	panic("PowerNV Unrecovered Machine Check");
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
index 09787139834d..3db53e8aff92 100644
--- a/arch/powerpc/platforms/ps3/os-area.c
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -194,11 +194,6 @@ static const struct os_area_db_id os_area_db_id_rtc_diff = {
 	.key = OS_AREA_DB_KEY_RTC_DIFF
 };
 
-static const struct os_area_db_id os_area_db_id_video_mode = {
-	.owner = OS_AREA_DB_OWNER_LINUX,
-	.key = OS_AREA_DB_KEY_VIDEO_MODE
-};
-
 #define SECONDS_FROM_1970_TO_2000 946684800LL
 
 /**
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index d4788111c161..fac6ac9790fa 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -10,7 +10,7 @@ targets += misc.o piggy.o sizes.h head.o
 
 KBUILD_CFLAGS := -m64 -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks
+KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
 KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 0c98f1508542..ed7da281df66 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -381,7 +381,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_DEBUG=m
 CONFIG_ZFCP=y
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_HP_SW=m
 CONFIG_SCSI_DH_EMC=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index 82083e1fbdc4..9858b14cde1e 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -377,7 +377,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_DEBUG=m
 CONFIG_ZFCP=y
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_HP_SW=m
 CONFIG_SCSI_DH_EMC=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index c05c9e0821e3..7f14f80717d4 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -377,7 +377,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_DEBUG=m
 CONFIG_ZFCP=y
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_HP_SW=m
 CONFIG_SCSI_DH_EMC=m
diff --git a/arch/s390/include/asm/numa.h b/arch/s390/include/asm/numa.h
index 2a0efc63b9e5..dc19ee0c92aa 100644
--- a/arch/s390/include/asm/numa.h
+++ b/arch/s390/include/asm/numa.h
@@ -19,7 +19,7 @@ int numa_pfn_to_nid(unsigned long pfn);
 int __node_distance(int a, int b);
 void numa_update_cpu_topology(void);
 
-extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+extern cpumask_t node_to_cpumask_map[MAX_NUMNODES];
 extern int numa_debug_enabled;
 
 #else
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 27ebde643933..94fc55fc72ce 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -68,7 +68,7 @@ static inline int cpu_to_node(int cpu)
 #define cpumask_of_node cpumask_of_node
 static inline const struct cpumask *cpumask_of_node(int node)
 {
-	return node_to_cpumask_map[node];
+	return &node_to_cpumask_map[node];
 }
 
 /*
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 48c9af7a7683..3aeeb1b562c0 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -176,6 +176,7 @@ int main(void)
 	DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste));
 	DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area));
 	DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr));
+	DEFINE(__LC_PERCPU_OFFSET, offsetof(struct _lowcore, percpu_offset));
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb));
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 09b039d7983d..582fe44ab07c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -733,6 +733,14 @@ ENTRY(psw_idle)
 	stg	%r3,__SF_EMPTY(%r15)
 	larl	%r1,.Lpsw_idle_lpsw+4
 	stg	%r1,__SF_EMPTY+8(%r15)
+#ifdef CONFIG_SMP
+	larl	%r1,smp_cpu_mtid
+	llgf	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	.Lpsw_idle_stcctm
+	.insn	rsy,0xeb0000000017,%r1,5,__SF_EMPTY+16(%r15)
+.Lpsw_idle_stcctm:
+#endif
 	STCK	__CLOCK_IDLE_ENTER(%r2)
 	stpt	__TIMER_IDLE_ENTER(%r2)
 .Lpsw_idle_lpsw:
@@ -1159,7 +1167,27 @@ cleanup_critical:
 	jhe	1f
 	mvc	__CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2)
 	mvc	__TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2)
-1:	# account system time going idle
+1:	# calculate idle cycles
+#ifdef CONFIG_SMP
+	clg	%r9,BASED(.Lcleanup_idle_insn)
+	jl	3f
+	larl	%r1,smp_cpu_mtid
+	llgf	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	3f
+	.insn	rsy,0xeb0000000017,%r1,5,__SF_EMPTY+80(%r15)
+	larl	%r3,mt_cycles
+	ag	%r3,__LC_PERCPU_OFFSET
+	la	%r4,__SF_EMPTY+16(%r15)
+2:	lg	%r0,0(%r3)
+	slg	%r0,0(%r4)
+	alg	%r0,64(%r4)
+	stg	%r0,0(%r3)
+	la	%r3,8(%r3)
+	la	%r4,8(%r4)
+	brct	%r1,2b
+#endif
+3:	# account system time going idle
 	lg	%r9,__LC_STEAL_TIMER
 	alg	%r9,__CLOCK_IDLE_ENTER(%r2)
 	slg	%r9,__LC_LAST_UPDATE_CLOCK
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index c8653435c70d..dafc44f519c3 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -25,7 +25,7 @@ static DEFINE_SPINLOCK(virt_timer_lock);
 static atomic64_t virt_timer_current;
 static atomic64_t virt_timer_elapsed;
 
-static DEFINE_PER_CPU(u64, mt_cycles[32]);
+DEFINE_PER_CPU(u64, mt_cycles[8]);
 static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 };
 static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 };
 static DEFINE_PER_CPU(u64, mt_scaling_jiffies);
@@ -60,6 +60,34 @@ static inline int virt_timer_forward(u64 elapsed)
 	return elapsed >= atomic64_read(&virt_timer_current);
 }
 
+static void update_mt_scaling(void)
+{
+	u64 cycles_new[8], *cycles_old;
+	u64 delta, fac, mult, div;
+	int i;
+
+	stcctm5(smp_cpu_mtid + 1, cycles_new);
+	cycles_old = this_cpu_ptr(mt_cycles);
+	fac = 1;
+	mult = div = 0;
+	for (i = 0; i <= smp_cpu_mtid; i++) {
+		delta = cycles_new[i] - cycles_old[i];
+		div += delta;
+		mult *= i + 1;
+		mult += delta * fac;
+		fac *= i + 1;
+	}
+	div *= fac;
+	if (div > 0) {
+		/* Update scaling factor */
+		__this_cpu_write(mt_scaling_mult, mult);
+		__this_cpu_write(mt_scaling_div, div);
+		memcpy(cycles_old, cycles_new,
+		       sizeof(u64) * (smp_cpu_mtid + 1));
+	}
+	__this_cpu_write(mt_scaling_jiffies, jiffies_64);
+}
+
 /*
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
@@ -69,7 +97,6 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 	struct thread_info *ti = task_thread_info(tsk);
 	u64 timer, clock, user, system, steal;
 	u64 user_scaled, system_scaled;
-	int i;
 
 	timer = S390_lowcore.last_update_timer;
 	clock = S390_lowcore.last_update_clock;
@@ -85,34 +112,10 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
 	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
 	S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
 
-	/* Do MT utilization calculation */
+	/* Update MT utilization calculation */
 	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) {
-		u64 cycles_new[32], *cycles_old;
-		u64 delta, fac, mult, div;
-
-		cycles_old = this_cpu_ptr(mt_cycles);
-		if (stcctm5(smp_cpu_mtid + 1, cycles_new) < 2) {
-			fac = 1;
-			mult = div = 0;
-			for (i = 0; i <= smp_cpu_mtid; i++) {
-				delta = cycles_new[i] - cycles_old[i];
-				div += delta;
-				mult *= i + 1;
-				mult += delta * fac;
-				fac *= i + 1;
-			}
-			div *= fac;
-			if (div > 0) {
-				/* Update scaling factor */
-				__this_cpu_write(mt_scaling_mult, mult);
-				__this_cpu_write(mt_scaling_div, div);
-				memcpy(cycles_old, cycles_new,
-				       sizeof(u64) * (smp_cpu_mtid + 1));
-			}
-		}
-		__this_cpu_write(mt_scaling_jiffies, jiffies_64);
-	}
+	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
+		update_mt_scaling();
 
 	user = S390_lowcore.user_timer - ti->user_timer;
 	S390_lowcore.steal_timer -= user;
@@ -181,6 +184,11 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 	S390_lowcore.last_update_timer = get_vtimer();
 	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
 
+	/* Update MT utilization calculation */
+	if (smp_cpu_mtid &&
+	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
+		update_mt_scaling();
+
 	system = S390_lowcore.system_timer - ti->system_timer;
 	S390_lowcore.steal_timer -= system;
 	ti->system_timer = S390_lowcore.system_timer;
diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c
index 7de4e2f780d7..30b2698a28e2 100644
--- a/arch/s390/numa/mode_emu.c
+++ b/arch/s390/numa/mode_emu.c
@@ -368,7 +368,7 @@ static void topology_add_core(struct toptree *core)
 		cpumask_copy(&top->thread_mask, &core->mask);
 		cpumask_copy(&top->core_mask, &core_mc(core)->mask);
 		cpumask_copy(&top->book_mask, &core_book(core)->mask);
-		cpumask_set_cpu(cpu, node_to_cpumask_map[core_node(core)->id]);
+		cpumask_set_cpu(cpu, &node_to_cpumask_map[core_node(core)->id]);
 		top->node_id = core_node(core)->id;
 	}
 }
@@ -383,7 +383,7 @@ static void toptree_to_topology(struct toptree *numa)
 
 	/* Clear all node masks */
 	for (i = 0; i < MAX_NUMNODES; i++)
-		cpumask_clear(node_to_cpumask_map[i]);
+		cpumask_clear(&node_to_cpumask_map[i]);
 
 	/* Rebuild all masks */
 	toptree_for_each(core, numa, CORE)
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index 09b1d2355bd9..43f32ce60aa3 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -23,7 +23,7 @@
 pg_data_t *node_data[MAX_NUMNODES];
 EXPORT_SYMBOL(node_data);
 
-cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+cpumask_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
 const struct numa_mode numa_mode_plain = {
@@ -144,7 +144,7 @@ void __init numa_setup(void)
 static int __init numa_init_early(void)
 {
 	/* Attach all possible CPUs to node 0 for now. */
-	cpumask_copy(node_to_cpumask_map[0], cpu_possible_mask);
+	cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
 	return 0;
 }
 early_initcall(numa_init_early);
diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h
index fe20d14ae051..ceb5201a30ed 100644
--- a/arch/sh/include/asm/page.h
+++ b/arch/sh/include/asm/page.h
@@ -59,6 +59,7 @@ pages_do_alias(unsigned long addr1, unsigned long addr2)
 
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, void *from);
+#define copy_user_page(to, from, vaddr, pg)  __copy_user(to, from, PAGE_SIZE)
 
 struct page;
 struct vm_area_struct;
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index 2e48eb8813ff..c90930de76ba 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -433,6 +433,7 @@ static struct crypto_alg algs[] = { {
 		.blkcipher = {
 			.min_keysize	= AES_MIN_KEY_SIZE,
 			.max_keysize	= AES_MAX_KEY_SIZE,
+			.ivsize		= AES_BLOCK_SIZE,
 			.setkey		= aes_set_key,
 			.encrypt	= cbc_encrypt,
 			.decrypt	= cbc_decrypt,
@@ -452,6 +453,7 @@ static struct crypto_alg algs[] = { {
 		.blkcipher = {
 			.min_keysize	= AES_MIN_KEY_SIZE,
 			.max_keysize	= AES_MAX_KEY_SIZE,
+			.ivsize		= AES_BLOCK_SIZE,
 			.setkey		= aes_set_key,
 			.encrypt	= ctr_crypt,
 			.decrypt	= ctr_crypt,
diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c
index 6bf2479a12fb..561a84d93cf6 100644
--- a/arch/sparc/crypto/camellia_glue.c
+++ b/arch/sparc/crypto/camellia_glue.c
@@ -274,6 +274,7 @@ static struct crypto_alg algs[] = { {
 		.blkcipher = {
 			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
 			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
 			.setkey		= camellia_set_key,
 			.encrypt	= cbc_encrypt,
 			.decrypt	= cbc_decrypt,
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index dd6a34fa6e19..61af794aa2d3 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -429,6 +429,7 @@ static struct crypto_alg algs[] = { {
 		.blkcipher = {
 			.min_keysize	= DES_KEY_SIZE,
 			.max_keysize	= DES_KEY_SIZE,
+			.ivsize		= DES_BLOCK_SIZE,
 			.setkey		= des_set_key,
 			.encrypt	= cbc_encrypt,
 			.decrypt	= cbc_decrypt,
@@ -485,6 +486,7 @@ static struct crypto_alg algs[] = { {
 		.blkcipher = {
 			.min_keysize	= DES3_EDE_KEY_SIZE,
 			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.ivsize		= DES3_EDE_BLOCK_SIZE,
 			.setkey		= des3_ede_set_key,
 			.encrypt	= cbc3_encrypt,
 			.decrypt	= cbc3_decrypt,
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 0b6cacaad933..ba35c41c71ff 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -40,5 +40,4 @@ generic-y += termbits.h
 generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += types.h
-generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/tile/include/asm/word-at-a-time.h b/arch/tile/include/asm/word-at-a-time.h
index 9e5ce0d7b292..b66a693c2c34 100644
--- a/arch/tile/include/asm/word-at-a-time.h
+++ b/arch/tile/include/asm/word-at-a-time.h
@@ -6,7 +6,7 @@
 struct word_at_a_time { /* unused */ };
 #define WORD_AT_A_TIME_CONSTANTS {}
 
-/* Generate 0x01 byte values for non-zero bytes using a SIMD instruction. */
+/* Generate 0x01 byte values for zero bytes using a SIMD instruction. */
 static inline unsigned long has_zero(unsigned long val, unsigned long *data,
 				     const struct word_at_a_time *c)
 {
@@ -33,4 +33,10 @@ static inline long find_zero(unsigned long mask)
 #endif
 }
 
+#ifdef __BIG_ENDIAN
+#define zero_bytemask(mask) (~1ul << (63 - __builtin_clzl(mask)))
+#else
+#define zero_bytemask(mask) ((2ul << __builtin_ctzl(mask)) - 1)
+#endif
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 328c8352480c..96d058a87100 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1308,6 +1308,7 @@ config HIGHMEM
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
 	depends on X86_32 && !HIGHMEM4G
+	select SWIOTLB
 	---help---
 	  PAE is required for NX support, and furthermore enables
 	  larger swapspace support for non-overcommit purposes. It
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 80a0e4389c9a..bacaa13acac5 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -554,6 +554,11 @@ static int __init camellia_aesni_init(void)
 {
 	const char *feature_name;
 
+	if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
+		pr_info("AVX or AES-NI instructions are not detected.\n");
+		return -ENODEV;
+	}
+
 	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
 		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2beee0382088..3a36ee704c30 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1226,10 +1226,8 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 
 int kvm_is_in_guest(void);
 
-int __x86_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
-int x86_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
+int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 83aea8055119..4c20dd333412 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -336,10 +336,10 @@ HYPERVISOR_update_descriptor(u64 ma, u64 desc)
 	return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
 }
 
-static inline int
+static inline long
 HYPERVISOR_memory_op(unsigned int cmd, void *arg)
 {
-	return _hypercall2(int, memory_op, cmd, arg);
+	return _hypercall2(long, memory_op, cmd, arg);
 }
 
 static inline int
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b372a7557c16..9da95b9daf8d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2418,7 +2418,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	u64 val, cr0, cr4;
 	u32 base3;
 	u16 selector;
-	int i;
+	int i, r;
 
 	for (i = 0; i < 16; i++)
 		*reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
@@ -2460,13 +2460,17 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
+	r = rsm_enter_protected_mode(ctxt, cr0, cr4);
+	if (r != X86EMUL_CONTINUE)
+		return r;
+
 	for (i = 0; i < 6; i++) {
-		int r = rsm_load_seg_64(ctxt, smbase, i);
+		r = rsm_load_seg_64(ctxt, smbase, i);
 		if (r != X86EMUL_CONTINUE)
 			return r;
 	}
 
-	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+	return X86EMUL_CONTINUE;
 }
 
 static int em_rsm(struct x86_emulate_ctxt *ctxt)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 06ef4908ba61..6a8bc64566ab 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4105,17 +4105,13 @@ static void seg_setup(int seg)
 static int alloc_apic_access_page(struct kvm *kvm)
 {
 	struct page *page;
-	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
 	mutex_lock(&kvm->slots_lock);
 	if (kvm->arch.apic_access_page_done)
 		goto out;
-	kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
-	kvm_userspace_mem.flags = 0;
-	kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE;
-	kvm_userspace_mem.memory_size = PAGE_SIZE;
-	r = __x86_set_memory_region(kvm, &kvm_userspace_mem);
+	r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+				    APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
 	if (r)
 		goto out;
 
@@ -4140,17 +4136,12 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 {
 	/* Called with kvm->slots_lock held. */
 
-	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
 	BUG_ON(kvm->arch.ept_identity_pagetable_done);
 
-	kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
-	kvm_userspace_mem.flags = 0;
-	kvm_userspace_mem.guest_phys_addr =
-		kvm->arch.ept_identity_map_addr;
-	kvm_userspace_mem.memory_size = PAGE_SIZE;
-	r = __x86_set_memory_region(kvm, &kvm_userspace_mem);
+	r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
+				    kvm->arch.ept_identity_map_addr, PAGE_SIZE);
 
 	return r;
 }
@@ -4949,14 +4940,9 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 {
 	int ret;
-	struct kvm_userspace_memory_region tss_mem = {
-		.slot = TSS_PRIVATE_MEMSLOT,
-		.guest_phys_addr = addr,
-		.memory_size = PAGE_SIZE * 3,
-		.flags = 0,
-	};
 
-	ret = x86_set_memory_region(kvm, &tss_mem);
+	ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr,
+				    PAGE_SIZE * 3);
 	if (ret)
 		return ret;
 	kvm->arch.tss_addr = addr;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 92511d4b7236..9a9a19830321 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6453,6 +6453,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
+		!vcpu->arch.apf.halted);
+}
+
 static int vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -6461,8 +6467,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 
 	for (;;) {
-		if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
-		    !vcpu->arch.apf.halted)
+		if (kvm_vcpu_running(vcpu))
 			r = vcpu_enter_guest(vcpu);
 		else
 			r = vcpu_block(kvm, vcpu);
@@ -7474,34 +7479,66 @@ void kvm_arch_sync_events(struct kvm *kvm)
 	kvm_free_pit(kvm);
 }
 
-int __x86_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem)
+int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 {
 	int i, r;
+	unsigned long hva;
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *slot, old;
 
 	/* Called with kvm->slots_lock held.  */
-	BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM);
+	if (WARN_ON(id >= KVM_MEM_SLOTS_NUM))
+		return -EINVAL;
+
+	slot = id_to_memslot(slots, id);
+	if (size) {
+		if (WARN_ON(slot->npages))
+			return -EEXIST;
+
+		/*
+		 * MAP_SHARED to prevent internal slot pages from being moved
+		 * by fork()/COW.
+		 */
+		hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE,
+			      MAP_SHARED | MAP_ANONYMOUS, 0);
+		if (IS_ERR((void *)hva))
+			return PTR_ERR((void *)hva);
+	} else {
+		if (!slot->npages)
+			return 0;
 
+		hva = 0;
+	}
+
+	old = *slot;
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		struct kvm_userspace_memory_region m = *mem;
+		struct kvm_userspace_memory_region m;
 
-		m.slot |= i << 16;
+		m.slot = id | (i << 16);
+		m.flags = 0;
+		m.guest_phys_addr = gpa;
+		m.userspace_addr = hva;
+		m.memory_size = size;
 		r = __kvm_set_memory_region(kvm, &m);
 		if (r < 0)
 			return r;
 	}
 
+	if (!size) {
+		r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
+		WARN_ON(r < 0);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__x86_set_memory_region);
 
-int x86_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem)
+int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 {
 	int r;
 
 	mutex_lock(&kvm->slots_lock);
-	r = __x86_set_memory_region(kvm, mem);
+	r = __x86_set_memory_region(kvm, id, gpa, size);
 	mutex_unlock(&kvm->slots_lock);
 
 	return r;
@@ -7516,16 +7553,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		 * unless the the memory map has changed due to process exit
 		 * or fd copying.
 		 */
-		struct kvm_userspace_memory_region mem;
-		memset(&mem, 0, sizeof(mem));
-		mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
-		x86_set_memory_region(kvm, &mem);
-
-		mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
-		x86_set_memory_region(kvm, &mem);
-
-		mem.slot = TSS_PRIVATE_MEMSLOT;
-		x86_set_memory_region(kvm, &mem);
+		x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0);
+		x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0);
+		x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
 	}
 	kvm_iommu_unmap_guest(kvm);
 	kfree(kvm->arch.vpic);
@@ -7628,27 +7658,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				enum kvm_mr_change change)
 {
-	/*
-	 * Only private memory slots need to be mapped here since
-	 * KVM_SET_MEMORY_REGION ioctl is no longer supported.
-	 */
-	if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) {
-		unsigned long userspace_addr;
-
-		/*
-		 * MAP_SHARED to prevent internal slot pages from being moved
-		 * by fork()/COW.
-		 */
-		userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE,
-					 PROT_READ | PROT_WRITE,
-					 MAP_SHARED | MAP_ANONYMOUS, 0);
-
-		if (IS_ERR((void *)userspace_addr))
-			return PTR_ERR((void *)userspace_addr);
-
-		memslot->userspace_addr = userspace_addr;
-	}
-
 	return 0;
 }
 
@@ -7710,17 +7719,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 {
 	int nr_mmu_pages = 0;
 
-	if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) {
-		int ret;
-
-		ret = vm_munmap(old->userspace_addr,
-				old->npages * PAGE_SIZE);
-		if (ret < 0)
-			printk(KERN_WARNING
-			       "kvm_vm_ioctl_set_memory_region: "
-			       "failed to munmap memory\n");
-	}
-
 	if (!kvm->arch.n_requested_mmu_pages)
 		nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
 
@@ -7769,19 +7767,36 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	kvm_mmu_invalidate_zap_all_pages(kvm);
 }
 
+static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
+{
+	if (!list_empty_careful(&vcpu->async_pf.done))
+		return true;
+
+	if (kvm_apic_has_events(vcpu))
+		return true;
+
+	if (vcpu->arch.pv.pv_unhalted)
+		return true;
+
+	if (atomic_read(&vcpu->arch.nmi_queued))
+		return true;
+
+	if (test_bit(KVM_REQ_SMI, &vcpu->requests))
+		return true;
+
+	if (kvm_arch_interrupt_allowed(vcpu) &&
+	    kvm_cpu_has_interrupt(vcpu))
+		return true;
+
+	return false;
+}
+
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
 		kvm_x86_ops->check_nested_events(vcpu, false);
 
-	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
-		!vcpu->arch.apf.halted)
-		|| !list_empty_careful(&vcpu->async_pf.done)
-		|| kvm_apic_has_events(vcpu)
-		|| vcpu->arch.pv.pv_unhalted
-		|| atomic_read(&vcpu->arch.nmi_queued) ||
-		(kvm_arch_interrupt_allowed(vcpu) &&
-		 kvm_cpu_has_interrupt(vcpu));
+	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 30d12afe52ed..993b7a71386d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,6 +33,10 @@
 #include <linux/memblock.h>
 #include <linux/edd.h>
 
+#ifdef CONFIG_KEXEC_CORE
+#include <linux/kexec.h>
+#endif
+
 #include <xen/xen.h>
 #include <xen/events.h>
 #include <xen/interface/xen.h>
@@ -1077,6 +1081,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		/* Fast syscall setup is all done in hypercalls, so
 		   these are all ignored.  Stub them out here to stop
 		   Xen console noise. */
+		break;
 
 	default:
 		if (!pmu_msr_write(msr, low, high, &ret))
@@ -1807,6 +1812,21 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 	.notifier_call	= xen_hvm_cpu_notify,
 };
 
+#ifdef CONFIG_KEXEC_CORE
+static void xen_hvm_shutdown(void)
+{
+	native_machine_shutdown();
+	if (kexec_in_progress)
+		xen_reboot(SHUTDOWN_soft_reset);
+}
+
+static void xen_hvm_crash_shutdown(struct pt_regs *regs)
+{
+	native_machine_crash_shutdown(regs);
+	xen_reboot(SHUTDOWN_soft_reset);
+}
+#endif
+
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -1826,6 +1846,10 @@ static void __init xen_hvm_guest_init(void)
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.shutdown = xen_hvm_shutdown;
+	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
+#endif
 }
 #endif
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index bfc08b13044b..660b3cfef234 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -112,6 +112,15 @@ static unsigned long *p2m_identity;
 static pte_t *p2m_missing_pte;
 static pte_t *p2m_identity_pte;
 
+/*
+ * Hint at last populated PFN.
+ *
+ * Used to set HYPERVISOR_shared_info->arch.max_pfn so the toolstack
+ * can avoid scanning the whole P2M (which may be sized to account for
+ * hotplugged memory).
+ */
+static unsigned long xen_p2m_last_pfn;
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -270,7 +279,7 @@ void xen_setup_mfn_list_list(void)
 	else
 		HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
 			virt_to_mfn(p2m_top_mfn);
-	HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
+	HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
 	HYPERVISOR_shared_info->arch.p2m_generation = 0;
 	HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr;
 	HYPERVISOR_shared_info->arch.p2m_cr3 =
@@ -406,6 +415,8 @@ void __init xen_vmalloc_p2m_tree(void)
 	static struct vm_struct vm;
 	unsigned long p2m_limit;
 
+	xen_p2m_last_pfn = xen_max_p2m_pfn;
+
 	p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
 	vm.flags = VM_ALLOC;
 	vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
@@ -608,6 +619,12 @@ static bool alloc_p2m(unsigned long pfn)
 			free_p2m_page(p2m);
 	}
 
+	/* Expanded the p2m? */
+	if (pfn > xen_p2m_last_pfn) {
+		xen_p2m_last_pfn = pfn;
+		HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
+	}
+
 	return true;
 }
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f5ef6746d47a..1c30e4ab1022 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -548,7 +548,7 @@ static unsigned long __init xen_get_max_pages(void)
 {
 	unsigned long max_pages, limit;
 	domid_t domid = DOMID_SELF;
-	int ret;
+	long ret;
 
 	limit = xen_get_pages_limit();
 	max_pages = limit;
@@ -798,7 +798,7 @@ char * __init xen_memory_setup(void)
 		xen_ignore_unusable();
 
 	/* Make sure the Xen-supplied memory map is well-ordered. */
-	sanitize_e820_map(xen_e820_map, xen_e820_map_entries,
+	sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
 			  &xen_e820_map_entries);
 
 	max_pages = xen_get_max_pages();