Merge commit 'v3.16' into next

author: James Morris <james.l.morris@oracle.com> 2014-10-01 00:44:04 +1000
committer: James Morris <james.l.morris@oracle.com> 2014-10-01 00:44:04 +1000
commit: 6c8ff877cdf13cd5287ed9d700cfb6cb70e2bfa1 (patch)
tree: 2ab49b7d19fb69cdae5b6be9e7ba44f6cf3d45ef /arch
parent: 35e1efd25a9e7d5cf2884fa23441ab87353849bb (diff)
parent: 19583ca584d6f574384e17fe7613dfaeadcdc4a6 (diff)
106 files changed, 776 insertions, 398 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 245058b3b0ef..290f02ee0157 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -6,6 +6,7 @@ config ARM
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -312,7 +313,7 @@ config ARCH_MULTIPLATFORM
 config ARCH_INTEGRATOR
 	bool "ARM Ltd. Integrator family"
 	select ARM_AMBA
-	select ARM_PATCH_PHYS_VIRT
+	select ARM_PATCH_PHYS_VIRT if MMU
 	select AUTO_ZRELADDR
 	select COMMON_CLK
 	select COMMON_CLK_VERSATILE
@@ -658,7 +659,7 @@ config ARCH_MSM
 config ARCH_SHMOBILE_LEGACY
 	bool "Renesas ARM SoCs (non-multiplatform)"
 	select ARCH_SHMOBILE
-	select ARM_PATCH_PHYS_VIRT
+	select ARM_PATCH_PHYS_VIRT if MMU
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index 287795985e32..b84bac5bada4 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -925,7 +925,7 @@
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00500000 0x00100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>,
+			clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>,
 				 <&uhpck>;
 			clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck";
 			status = "disabled";
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 2ebc42140ea6..2c0d6ea3ab41 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -1124,6 +1124,7 @@
 				compatible = "atmel,at91sam9rl-pwm";
 				reg = <0xf8034000 0x300>;
 				interrupts = <18 IRQ_TYPE_LEVEL_HIGH 4>;
+				clocks = <&pwm_clk>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
@@ -1155,8 +1156,7 @@
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>,
-				 <&uhpck>;
+			clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>;
 			clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck";
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/hi3620.dtsi b/arch/arm/boot/dts/hi3620.dtsi
index ab1116d086be..83a5b8685bd9 100644
--- a/arch/arm/boot/dts/hi3620.dtsi
+++ b/arch/arm/boot/dts/hi3620.dtsi
@@ -73,7 +73,7 @@
 
 		L2: l2-cache {
 			compatible = "arm,pl310-cache";
-			reg = <0xfc10000 0x100000>;
+			reg = <0x100000 0x100000>;
 			interrupts = <0 15 4>;
 			cache-unified;
 			cache-level = <2>;
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 1fe45d1f75ec..b15f1a77d684 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -353,7 +353,7 @@
 	};
 
 	twl_power: power {
-		compatible = "ti,twl4030-power-n900", "ti,twl4030-power-idle-osc-off";
+		compatible = "ti,twl4030-power-n900";
 		ti,use_poweroff;
 	};
 };
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 8d7ffaeff6e0..79f68acfd5d4 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -540,9 +540,9 @@
 			#clock-cells = <0>;
 			clock-output-names = "sd1";
 		};
-		sd2_clk: sd3_clk@e615007c {
+		sd2_clk: sd3_clk@e615026c {
 			compatible = "renesas,r8a7791-div6-clock", "renesas,cpg-div6-clock";
-			reg = <0 0xe615007c 0 4>;
+			reg = <0 0xe615026c 0 4>;
 			clocks = <&pll1_div2_clk>;
 			#clock-cells = <0>;
 			clock-output-names = "sd2";
diff --git a/arch/arm/boot/dts/ste-nomadik-s8815.dts b/arch/arm/boot/dts/ste-nomadik-s8815.dts
index f557feb997f4..90d8b6c7a205 100644
--- a/arch/arm/boot/dts/ste-nomadik-s8815.dts
+++ b/arch/arm/boot/dts/ste-nomadik-s8815.dts
@@ -4,7 +4,7 @@
  */
 
 /dts-v1/;
-/include/ "ste-nomadik-stn8815.dtsi"
+#include "ste-nomadik-stn8815.dtsi"
 
 / {
 	model = "Calao Systems USB-S8815";
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index d316c955bd5f..dbcf521b017f 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -1,7 +1,9 @@
 /*
  * Device Tree for the ST-Ericsson Nomadik 8815 STn8815 SoC
  */
-/include/ "skeleton.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include "skeleton.dtsi"
 
 / {
 	#address-cells = <1>;
@@ -842,8 +844,7 @@
 			bus-width = <4>;
 			cap-mmc-highspeed;
 			cap-sd-highspeed;
-			cd-gpios = <&gpio3 15 0x1>;
-			cd-inverted;
+			cd-gpios = <&gpio3 15 GPIO_ACTIVE_LOW>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>;
 			vmmc-supply = <&vmmc_regulator>;
diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c
index 4522366da759..15468fbbdea3 100644
--- a/arch/arm/crypto/aesbs-glue.c
+++ b/arch/arm/crypto/aesbs-glue.c
@@ -137,7 +137,7 @@ static int aesbs_cbc_encrypt(struct blkcipher_desc *desc,
 				dst += AES_BLOCK_SIZE;
 			} while (--blocks);
 		}
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -158,7 +158,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
 		bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->dec, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	while (walk.nbytes) {
 		u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -182,7 +182,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
 			dst += AES_BLOCK_SIZE;
 			src += AES_BLOCK_SIZE;
 		} while (--blocks);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -268,7 +268,7 @@ static int aesbs_xts_encrypt(struct blkcipher_desc *desc,
 		bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->enc, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -292,7 +292,7 @@ static int aesbs_xts_decrypt(struct blkcipher_desc *desc,
 		bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->dec, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 060a75e99263..0406cb3f1af7 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -50,6 +50,7 @@ struct machine_desc {
 	struct smp_operations	*smp;		/* SMP operations	*/
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **);
+	void			(*dt_fixup)(void);
 	void			(*init_meminfo)(void);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index e94a157ddff1..11c54de9f8cf 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -212,7 +212,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 	mdesc_best = &__mach_desc_GENERIC_DT;
 #endif
 
-	if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys)))
+	if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys)))
 		return NULL;
 
 	mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach);
@@ -237,6 +237,12 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 		dump_machine_table(); /* does not return */
 	}
 
+	/* We really don't want to do this, but sometimes firmware provides buggy data */
+	if (mdesc->dt_fixup)
+		mdesc->dt_fixup();
+
+	early_init_dt_scan_nodes();
+
 	/* Change machine number to match the mdesc we're using */
 	__machine_arch_type = mdesc->nr;
 
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index a5599cfc43cb..2b32978ae905 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -94,13 +94,19 @@ ENTRY(iwmmxt_task_enable)
 
 	mrc	p15, 0, r2, c2, c0, 0
 	mov	r2, r2				@ cpwait
+	bl	concan_save
 
-	teq	r1, #0				@ test for last ownership
-	mov	lr, r9				@ normal exit from exception
-	beq	concan_load			@ no owner, skip save
+#ifdef CONFIG_PREEMPT_COUNT
+	get_thread_info r10
+#endif
+4:	dec_preempt_count r10, r3
+	mov	pc, r9				@ normal exit from exception
 
 concan_save:
 
+	teq	r1, #0				@ test for last ownership
+	beq	concan_load			@ no owner, skip save
+
 	tmrc	r2, wCon
 
 	@ CUP? wCx
@@ -138,7 +144,7 @@ concan_dump:
 	wstrd	wR15, [r1, #MMX_WR15]
 
 2:	teq	r0, #0				@ anything to load?
-	beq	3f
+	moveq	pc, lr				@ if not, return
 
 concan_load:
 
@@ -171,14 +177,9 @@ concan_load:
 	@ clear CUP/MUP (only if r1 != 0)
 	teq	r1, #0
 	mov 	r2, #0
-	beq	3f
-	tmcr	wCon, r2
+	moveq	pc, lr
 
-3:
-#ifdef CONFIG_PREEMPT_COUNT
-	get_thread_info r10
-#endif
-4:	dec_preempt_count r10, r3
+	tmcr	wCon, r2
 	mov	pc, lr
 
 /*
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index 778c2f7024ff..a74b53c1b7df 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -160,12 +160,16 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr)
 static struct undef_hook kgdb_brkpt_hook = {
 	.instr_mask		= 0xffffffff,
 	.instr_val		= KGDB_BREAKINST,
+	.cpsr_mask		= MODE_MASK,
+	.cpsr_val		= SVC_MODE,
 	.fn			= kgdb_brk_fn
 };
 
 static struct undef_hook kgdb_compiled_brkpt_hook = {
 	.instr_mask		= 0xffffffff,
 	.instr_val		= KGDB_COMPILED_BREAK,
+	.cpsr_mask		= MODE_MASK,
+	.cpsr_val		= SVC_MODE,
 	.fn			= kgdb_compiled_brk_fn
 };
 
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 9d853189028b..e35d880f9773 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -275,7 +275,7 @@ void store_cpu_topology(unsigned int cpuid)
 		cpu_topology[cpuid].socket_id, mpidr);
 }
 
-static inline const int cpu_corepower_flags(void)
+static inline int cpu_corepower_flags(void)
 {
 	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
 }
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index 46d893fcbe85..66c9b9614f3c 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -335,6 +335,15 @@ static void __init exynos_reserve(void)
 #endif
 }
 
+static void __init exynos_dt_fixup(void)
+{
+	/*
+	 * Some versions of uboot pass garbage entries in the memory node,
+	 * use the old CONFIG_ARM_NR_BANKS
+	 */
+	of_fdt_limit_memory(8);
+}
+
 DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)")
 	/* Maintainer: Thomas Abraham <thomas.abraham@linaro.org> */
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
@@ -348,4 +357,5 @@ DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)")
 	.dt_compat	= exynos_dt_compat,
 	.restart	= exynos_restart,
 	.reserve	= exynos_reserve,
+	.dt_fixup	= exynos_dt_fixup,
 MACHINE_END
diff --git a/arch/arm/mach-exynos/hotplug.c b/arch/arm/mach-exynos/hotplug.c
index 8a134d019cb3..920a4baa53cd 100644
--- a/arch/arm/mach-exynos/hotplug.c
+++ b/arch/arm/mach-exynos/hotplug.c
@@ -40,15 +40,17 @@ static inline void cpu_leave_lowpower(void)
 
 static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 {
+	u32 mpidr = cpu_logical_map(cpu);
+	u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+
 	for (;;) {
 
-		/* make cpu1 to be turned off at next WFI command */
-		if (cpu == 1)
-			exynos_cpu_power_down(cpu);
+		/* Turn the CPU off on next WFI instruction. */
+		exynos_cpu_power_down(core_id);
 
 		wfi();
 
-		if (pen_release == cpu_logical_map(cpu)) {
+		if (pen_release == core_id) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 1c8d31e39520..50b9aad5e27b 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -90,7 +90,8 @@ static void exynos_secondary_init(unsigned int cpu)
 static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	unsigned long timeout;
-	unsigned long phys_cpu = cpu_logical_map(cpu);
+	u32 mpidr = cpu_logical_map(cpu);
+	u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 	int ret = -ENOSYS;
 
 	/*
@@ -104,17 +105,18 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * the holding pen - release it, then wait for it to flag
 	 * that it has been released by resetting pen_release.
 	 *
-	 * Note that "pen_release" is the hardware CPU ID, whereas
+	 * Note that "pen_release" is the hardware CPU core ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	write_pen_release(phys_cpu);
+	write_pen_release(core_id);
 
-	if (!exynos_cpu_power_state(cpu)) {
-		exynos_cpu_power_up(cpu);
+	if (!exynos_cpu_power_state(core_id)) {
+		exynos_cpu_power_up(core_id);
 		timeout = 10;
 
 		/* wait max 10 ms until cpu1 is on */
-		while (exynos_cpu_power_state(cpu) != S5P_CORE_LOCAL_PWR_EN) {
+		while (exynos_cpu_power_state(core_id)
+		       != S5P_CORE_LOCAL_PWR_EN) {
 			if (timeout-- == 0)
 				break;
 
@@ -145,20 +147,20 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 		 * Try to set boot address using firmware first
 		 * and fall back to boot register if it fails.
 		 */
-		ret = call_firmware_op(set_cpu_boot_addr, phys_cpu, boot_addr);
+		ret = call_firmware_op(set_cpu_boot_addr, core_id, boot_addr);
 		if (ret && ret != -ENOSYS)
 			goto fail;
 		if (ret == -ENOSYS) {
-			void __iomem *boot_reg = cpu_boot_reg(phys_cpu);
+			void __iomem *boot_reg = cpu_boot_reg(core_id);
 
 			if (IS_ERR(boot_reg)) {
 				ret = PTR_ERR(boot_reg);
 				goto fail;
 			}
-			__raw_writel(boot_addr, cpu_boot_reg(phys_cpu));
+			__raw_writel(boot_addr, cpu_boot_reg(core_id));
 		}
 
-		call_firmware_op(cpu_boot, phys_cpu);
+		call_firmware_op(cpu_boot, core_id);
 
 		arch_send_wakeup_ipi_mask(cpumask_of(cpu));
 
@@ -227,22 +229,24 @@ static void __init exynos_smp_prepare_cpus(unsigned int max_cpus)
 	 * boot register if it fails.
 	 */
 	for (i = 1; i < max_cpus; ++i) {
-		unsigned long phys_cpu;
 		unsigned long boot_addr;
+		u32 mpidr;
+		u32 core_id;
 		int ret;
 
-		phys_cpu = cpu_logical_map(i);
+		mpidr = cpu_logical_map(i);
+		core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 		boot_addr = virt_to_phys(exynos4_secondary_startup);
 
-		ret = call_firmware_op(set_cpu_boot_addr, phys_cpu, boot_addr);
+		ret = call_firmware_op(set_cpu_boot_addr, core_id, boot_addr);
 		if (ret && ret != -ENOSYS)
 			break;
 		if (ret == -ENOSYS) {
-			void __iomem *boot_reg = cpu_boot_reg(phys_cpu);
+			void __iomem *boot_reg = cpu_boot_reg(core_id);
 
 			if (IS_ERR(boot_reg))
 				break;
-			__raw_writel(boot_addr, cpu_boot_reg(phys_cpu));
+			__raw_writel(boot_addr, cpu_boot_reg(core_id));
 		}
 	}
 }
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 8e795dea02ec..8556c787e59c 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -70,7 +70,7 @@ static const char *cko_sels[] = { "cko1", "cko2", };
 static const char *lvds_sels[] = {
 	"dummy", "dummy", "dummy", "dummy", "dummy", "dummy",
 	"pll4_audio", "pll5_video", "pll8_mlb", "enet_ref",
-	"pcie_ref", "sata_ref",
+	"pcie_ref_125m", "sata_ref_100m",
 };
 
 enum mx6q_clks {
@@ -491,7 +491,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 
 	/* All existing boards with PCIe use LVDS1 */
 	if (IS_ENABLED(CONFIG_PCI_IMX6))
-		clk_set_parent(clk[lvds1_sel], clk[sata_ref]);
+		clk_set_parent(clk[lvds1_sel], clk[sata_ref_100m]);
 
 	/* Set initial power mode */
 	imx6q_set_lpm(WAIT_CLOCKED);
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 477202fd39cc..2bdc3233abe2 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -292,6 +292,10 @@ static struct notifier_block mvebu_hwcc_nb = {
 	.notifier_call = mvebu_hwcc_notifier,
 };
 
+static struct notifier_block mvebu_hwcc_pci_nb = {
+	.notifier_call = mvebu_hwcc_notifier,
+};
+
 static void __init armada_370_coherency_init(struct device_node *np)
 {
 	struct resource res;
@@ -427,7 +431,7 @@ static int __init coherency_pci_init(void)
 {
 	if (coherency_available())
 		bus_register_notifier(&pci_bus_type,
-				       &mvebu_hwcc_nb);
+				       &mvebu_hwcc_pci_nb);
 	return 0;
 }
 
diff --git a/arch/arm/mach-mvebu/headsmp-a9.S b/arch/arm/mach-mvebu/headsmp-a9.S
index 5925366bc03c..da5bb292b91c 100644
--- a/arch/arm/mach-mvebu/headsmp-a9.S
+++ b/arch/arm/mach-mvebu/headsmp-a9.S
@@ -15,6 +15,8 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
+#include <asm/assembler.h>
+
 	__CPUINIT
 #define CPU_RESUME_ADDR_REG 0xf10182d4
 
@@ -22,13 +24,18 @@
 .global armada_375_smp_cpu1_enable_code_end
 
 armada_375_smp_cpu1_enable_code_start:
-	ldr     r0, [pc, #4]
+ARM_BE8(setend	be)
+	adr     r0, 1f
+	ldr	r0, [r0]
 	ldr     r1, [r0]
+ARM_BE8(rev	r1, r1)
 	mov     pc, r1
+1:
 	.word   CPU_RESUME_ADDR_REG
 armada_375_smp_cpu1_enable_code_end:
 
 ENTRY(mvebu_cortex_a9_secondary_startup)
+ARM_BE8(setend	be)
 	bl      v7_invalidate_l1
 	b	secondary_startup
 ENDPROC(mvebu_cortex_a9_secondary_startup)
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
index a1d407c0febe..25aa8237d668 100644
--- a/arch/arm/mach-mvebu/pmsu.c
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -201,12 +201,12 @@ static noinline int do_armada_370_xp_cpu_suspend(unsigned long deepidle)
 
 	/* Test the CR_C bit and set it if it was cleared */
 	asm volatile(
-	"mrc	p15, 0, %0, c1, c0, 0 \n\t"
-	"tst	%0, #(1 << 2) \n\t"
-	"orreq	%0, %0, #(1 << 2) \n\t"
-	"mcreq	p15, 0, %0, c1, c0, 0 \n\t"
+	"mrc	p15, 0, r0, c1, c0, 0 \n\t"
+	"tst	r0, #(1 << 2) \n\t"
+	"orreq	r0, r0, #(1 << 2) \n\t"
+	"mcreq	p15, 0, r0, c1, c0, 0 \n\t"
 	"isb	"
-	: : "r" (0));
+	: : : "r0");
 
 	pr_warn("Failed to suspend the system\n");
 
diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c
index 17cd39360afe..93914d220069 100644
--- a/arch/arm/mach-omap2/gpmc-nand.c
+++ b/arch/arm/mach-omap2/gpmc-nand.c
@@ -50,6 +50,16 @@ static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
 		 soc_is_omap54xx() || soc_is_dra7xx())
 		return 1;
 
+	if (ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW ||
+		 ecc_opt == OMAP_ECC_BCH8_CODE_HW_DETECTION_SW) {
+		if (cpu_is_omap24xx())
+			return 0;
+		else if (cpu_is_omap3630() && (GET_OMAP_REVISION() == 0))
+			return 0;
+		else
+			return 1;
+	}
+
 	/* OMAP3xxx do not have ELM engine, so cannot support ECC schemes
 	 * which require H/W based ECC error detection */
 	if ((cpu_is_omap34xx() || cpu_is_omap3630()) &&
@@ -57,14 +67,6 @@ static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
 		 (ecc_opt == OMAP_ECC_BCH8_CODE_HW)))
 		return 0;
 
-	/*
-	 * For now, assume 4-bit mode is only supported on OMAP3630 ES1.x, x>=1
-	 * and AM33xx derivates. Other chips may be added if confirmed to work.
-	 */
-	if ((ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW) &&
-	    (!cpu_is_omap3630() || (GET_OMAP_REVISION() == 0)))
-		return 0;
-
 	/* legacy platforms support only HAM1 (1-bit Hamming) ECC scheme */
 	if (ecc_opt == OMAP_ECC_HAM1_CODE_HW)
 		return 1;
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 539e8106eb96..a0fe747634c1 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -168,6 +168,10 @@ static void omap4_l2c310_write_sec(unsigned long val, unsigned reg)
 		smc_op = OMAP4_MON_L2X0_PREFETCH_INDEX;
 		break;
 
+	case L310_POWER_CTRL:
+		pr_info_once("OMAP L2C310: ROM does not support power control setting\n");
+		return;
+
 	default:
 		WARN_ONCE(1, "OMAP L2C310: ignoring write to reg 0x%x\n", reg);
 		return;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4c88935654ca..1f88db06b133 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -461,12 +461,21 @@ void __init dma_contiguous_remap(void)
 		map.type = MT_MEMORY_DMA_READY;
 
 		/*
-		 * Clear previous low-memory mapping
+		 * Clear previous low-memory mapping to ensure that the
+		 * TLB does not see any conflicting entries, then flush
+		 * the TLB of the old entries before creating new mappings.
+		 *
+		 * This ensures that any speculatively loaded TLB entries
+		 * (even though they may be rare) can not cause any problems,
+		 * and ensures that this code is architecturally compliant.
 		 */
 		for (addr = __phys_to_virt(start); addr < __phys_to_virt(end);
 		     addr += PMD_SIZE)
 			pmd_clear(pmd_off_k(addr));
 
+		flush_tlb_kernel_range(__phys_to_virt(start),
+				       __phys_to_virt(end));
+
 		iotable_init(&map, 1);
 	}
 }
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 8e0e52eb76b5..c447ec70e868 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -9,6 +9,11 @@
 #include <asm/sections.h>
 #include <asm/system_info.h>
 
+/*
+ * Note: accesses outside of the kernel image and the identity map area
+ * are not supported on any CPU using the idmap tables as its current
+ * page tables.
+ */
 pgd_t *idmap_pgd;
 phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
 
@@ -25,6 +30,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 			pr_warning("Failed to allocate identity pmd.\n");
 			return;
 		}
+		/*
+		 * Copy the original PMD to ensure that the PMD entries for
+		 * the kernel image are preserved.
+		 */
+		if (!pud_none(*pud))
+			memcpy(pmd, pmd_offset(pud, 0),
+			       PTRS_PER_PMD * sizeof(pmd_t));
 		pud_populate(&init_mm, pud, pmd);
 		pmd += pmd_index(addr);
 	} else
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index ab14b79b03f0..6e3ba8d112a2 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1406,8 +1406,8 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 		return;
 
 	/* remap kernel code and data */
-	map_start = init_mm.start_code;
-	map_end   = init_mm.brk;
+	map_start = init_mm.start_code & PMD_MASK;
+	map_end   = ALIGN(init_mm.brk, PMD_SIZE);
 
 	/* get a handle on things... */
 	pgd0 = pgd_offset_k(0);
@@ -1442,7 +1442,7 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 	}
 
 	/* remap pmds for kernel mapping */
-	phys = __pa(map_start) & PMD_MASK;
+	phys = __pa(map_start);
 	do {
 		*pmdk++ = __pmd(phys | pmdprot);
 		phys += PMD_SIZE;
diff --git a/arch/arm/xen/grant-table.c b/arch/arm/xen/grant-table.c
index 859a9bb002d5..91cf08ba1e95 100644
--- a/arch/arm/xen/grant-table.c
+++ b/arch/arm/xen/grant-table.c
@@ -51,3 +51,8 @@ int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
 {
 	return -ENOSYS;
 }
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
+{
+	return 0;
+}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a474de346be6..839f48c26ef0 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -4,6 +4,7 @@ config ARM64
 	select ARCH_HAS_OPP
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 60f2f4c12256..79cd911ef88c 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -106,7 +106,7 @@ static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
 		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_enc, rounds, blocks, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -128,7 +128,7 @@ static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
 		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_dec, rounds, blocks, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -151,7 +151,7 @@ static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
 				first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -174,7 +174,7 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_dec, rounds, blocks, walk.iv,
 				first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -243,7 +243,7 @@ static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_enc, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 
@@ -267,7 +267,7 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_dec, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 
diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c
index 60e98a639ac5..e786e6cdc400 100644
--- a/arch/arm64/kernel/efi-stub.c
+++ b/arch/arm64/kernel/efi-stub.c
@@ -12,8 +12,6 @@
 #include <linux/efi.h>
 #include <linux/libfdt.h>
 #include <asm/sections.h>
-#include <generated/compile.h>
-#include <generated/utsrelease.h>
 
 /*
  * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f43db8a69262..e90c5426fe14 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -60,6 +60,17 @@ static int __init early_initrd(char *p)
 early_param("initrd", early_initrd);
 #endif
 
+/*
+ * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
+ * currently assumes that for memory starting above 4G, 32-bit devices will
+ * use a DMA offset.
+ */
+static phys_addr_t max_zone_dma_phys(void)
+{
+	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
+	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+}
+
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
@@ -70,9 +81,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
-		unsigned long max_dma_phys =
-			(unsigned long)(dma_to_phys(NULL, DMA_BIT_MASK(32)) + 1);
-		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+		max_dma = PFN_DOWN(max_zone_dma_phys());
 		zone_size[ZONE_DMA] = max_dma - min;
 	}
 	zone_size[ZONE_NORMAL] = max - max_dma;
@@ -146,7 +155,7 @@ void __init arm64_memblock_init(void)
 
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		dma_phys_limit = dma_to_phys(NULL, DMA_BIT_MASK(32)) + 1;
+		dma_phys_limit = max_zone_dma_phys();
 	dma_contiguous_reserve(dma_phys_limit);
 
 	memblock_allow_resize();
diff --git a/arch/blackfin/configs/BF609-EZKIT_defconfig b/arch/blackfin/configs/BF609-EZKIT_defconfig
index a7e9bfd84183..fcec5ce71392 100644
--- a/arch/blackfin/configs/BF609-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF609-EZKIT_defconfig
@@ -102,7 +102,7 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_BLACKFIN_TWI=y
 CONFIG_I2C_BLACKFIN_TWI_CLK_KHZ=100
 CONFIG_SPI=y
-CONFIG_SPI_BFIN_V3=y
+CONFIG_SPI_ADI_V3=y
 CONFIG_GPIOLIB=y
 CONFIG_GPIO_SYSFS=y
 # CONFIG_HWMON is not set
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index ba35864b2b74..c9eec84aa258 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -145,7 +145,7 @@ SECTIONS
 
 	.text_l1 L1_CODE_START : AT(LOADADDR(.exit.data) + SIZEOF(.exit.data))
 #else
-	.init.data : AT(__data_lma + __data_len)
+	.init.data : AT(__data_lma + __data_len + 32)
 	{
 		__sinitdata = .;
 		INIT_DATA
diff --git a/arch/blackfin/mach-bf533/boards/blackstamp.c b/arch/blackfin/mach-bf533/boards/blackstamp.c
index 63b0e4fe760c..0ccf0cf4daaf 100644
--- a/arch/blackfin/mach-bf533/boards/blackstamp.c
+++ b/arch/blackfin/mach-bf533/boards/blackstamp.c
@@ -20,6 +20,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/flash.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537e.c b/arch/blackfin/mach-bf537/boards/cm_bf537e.c
index c65c6dbda3da..1e7290ef3525 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537e.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537e.c
@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537u.c b/arch/blackfin/mach-bf537/boards/cm_bf537u.c
index af58454b4bff..c7495dc74690 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537u.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537u.c
@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
index a0211225748d..6b988ad653d8 100644
--- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c
+++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c
index 90138e6112c1..1fe7ff286619 100644
--- a/arch/blackfin/mach-bf548/boards/ezkit.c
+++ b/arch/blackfin/mach-bf548/boards/ezkit.c
@@ -2118,7 +2118,7 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-rotary",  "pinctrl-adi2.0", NULL, "rotary"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.0",  "pinctrl-adi2.0", NULL, "can0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.1",  "pinctrl-adi2.0", NULL, "can1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-lq043",  "pinctrl-adi2.0", NULL, "ppi0_24b"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-lq043",  "pinctrl-adi2.0", "ppi0_24bgrp", "ppi0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-ac97.0",  "pinctrl-adi2.0", NULL, "sport0"),
@@ -2140,7 +2140,9 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("pata-bf54x",  "pinctrl-adi2.0", NULL, "atapi_alter"),
 #endif
 	PIN_MAP_MUX_GROUP_DEFAULT("bf5xx-nand.0",  "pinctrl-adi2.0", NULL, "nfc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-keys",  "pinctrl-adi2.0", NULL, "keys_4x4"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-keys",  "pinctrl-adi2.0", "keys_4x4grp", "keys"),
+	PIN_MAP_MUX_GROUP("bf54x-keys", "4bit",  "pinctrl-adi2.0", "keys_4x4grp", "keys"),
+	PIN_MAP_MUX_GROUP("bf54x-keys", "8bit",  "pinctrl-adi2.0", "keys_8x8grp", "keys"),
 };
 
 static int __init ezkit_init(void)
diff --git a/arch/blackfin/mach-bf561/boards/acvilon.c b/arch/blackfin/mach-bf561/boards/acvilon.c
index 430b16d5ccb1..6ab951534d79 100644
--- a/arch/blackfin/mach-bf561/boards/acvilon.c
+++ b/arch/blackfin/mach-bf561/boards/acvilon.c
@@ -44,6 +44,7 @@
 #include <linux/spi/flash.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/gpio.h>
 #include <linux/jiffies.h>
 #include <linux/i2c-pca-platform.h>
 #include <linux/delay.h>
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index 9f777df4cacc..e862f7823e68 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -18,6 +18,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index 88dee43e7abe..2de71e8c104b 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -14,6 +14,7 @@
 #include <linux/spi/spi.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/gpio.h>
 #include <linux/delay.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c
index 1ba4600de69f..e2c0b024ce88 100644
--- a/arch/blackfin/mach-bf609/boards/ezkit.c
+++ b/arch/blackfin/mach-bf609/boards/ezkit.c
@@ -698,8 +698,6 @@ int bf609_nor_flash_init(struct platform_device *pdev)
 {
 #define CONFIG_SMC_GCTL_VAL     0x00000010
 
-	if (!devm_pinctrl_get_select_default(&pdev->dev))
-		return -EBUSY;
 	bfin_write32(SMC_GCTL, CONFIG_SMC_GCTL_VAL);
 	bfin_write32(SMC_B0CTL, 0x01002011);
 	bfin_write32(SMC_B0TIM, 0x08170977);
@@ -709,7 +707,6 @@ int bf609_nor_flash_init(struct platform_device *pdev)
 
 void bf609_nor_flash_exit(struct platform_device *pdev)
 {
-	devm_pinctrl_put(pdev->dev.pins->p);
 	bfin_write32(SMC_GCTL, 0);
 }
 
@@ -2058,15 +2055,14 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-rotary",  "pinctrl-adi2.0", NULL, "rotary"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.0",  "pinctrl-adi2.0", NULL, "can0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("physmap-flash.0",  "pinctrl-adi2.0", NULL, "smc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf609_nl8048.2",  "pinctrl-adi2.0", NULL, "ppi2_16b"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_display.0",  "pinctrl-adi2.0", NULL, "ppi0_16b"),
-#if IS_ENABLED(CONFIG_VIDEO_MT9M114)
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_8b"),
-#elif IS_ENABLED(CONFIG_VIDEO_VS6624)
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_16b"),
-#else
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_24b"),
-#endif
+	PIN_MAP_MUX_GROUP_DEFAULT("bf609_nl8048.2",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_display.0", "8bit",  "pinctrl-adi2.0", "ppi2_8bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bfin_display.0",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_display.0", "16bit",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "8bit",  "pinctrl-adi2.0", "ppi0_8bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", "ppi0_16bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "16bit",  "pinctrl-adi2.0", "ppi0_16bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "24bit",  "pinctrl-adi2.0", "ppi0_24bgrp", "ppi0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.1",  "pinctrl-adi2.0", NULL, "sport1"),
diff --git a/arch/blackfin/mach-bf609/include/mach/pm.h b/arch/blackfin/mach-bf609/include/mach/pm.h
index 3ca0fb965636..a1efd936dd30 100644
--- a/arch/blackfin/mach-bf609/include/mach/pm.h
+++ b/arch/blackfin/mach-bf609/include/mach/pm.h
@@ -10,6 +10,7 @@
 #define __MACH_BF609_PM_H__
 
 #include <linux/suspend.h>
+#include <linux/platform_device.h>
 
 extern int bfin609_pm_enter(suspend_state_t state);
 extern int bf609_pm_prepare(void);
@@ -19,6 +20,6 @@ void bf609_hibernate(void);
 void bfin_sec_raise_irq(unsigned int sid);
 void coreb_enable(void);
 
-int bf609_nor_flash_init(void);
-void bf609_nor_flash_exit(void);
+int bf609_nor_flash_init(struct platform_device *pdev);
+void bf609_nor_flash_exit(struct platform_device *pdev);
 #endif
diff --git a/arch/blackfin/mach-bf609/pm.c b/arch/blackfin/mach-bf609/pm.c
index 0cdd6955c7be..b1bfcf434d16 100644
--- a/arch/blackfin/mach-bf609/pm.c
+++ b/arch/blackfin/mach-bf609/pm.c
@@ -291,13 +291,13 @@ static struct bfin_cpu_pm_fns bf609_cpu_pm = {
 #if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE)
 static int smc_pm_syscore_suspend(void)
 {
-	bf609_nor_flash_exit();
+	bf609_nor_flash_exit(NULL);
 	return 0;
 }
 
 static void smc_pm_syscore_resume(void)
 {
-	bf609_nor_flash_init();
+	bf609_nor_flash_init(NULL);
 }
 
 static struct syscore_ops smc_pm_syscore_ops = {
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 867b7cef204c..1f94784eab6d 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -1208,8 +1208,6 @@ int __init init_arch_irq(void)
 
 	bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority);
 
-	bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority);
-
 	/* Enable interrupts IVG7-15 */
 	bfin_irq_flags |= IMASK_IVG15 |
 	    IMASK_IVG14 | IMASK_IVG13 | IMASK_IVG12 | IMASK_IVG11 |
diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h
index a2fa297196bc..f5645d6a89f2 100644
--- a/arch/parisc/include/uapi/asm/signal.h
+++ b/arch/parisc/include/uapi/asm/signal.h
@@ -69,8 +69,6 @@
 #define SA_NOMASK	SA_NODEFER
 #define SA_ONESHOT	SA_RESETHAND
 
-#define SA_RESTORER	0x04000000 /* obsolete -- ignored */
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index ae085ad0fba0..0bef864264c0 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -728,7 +728,6 @@ static void __init pagetable_init(void)
 #endif
 
 	empty_zero_page = alloc_bootmem_pages(PAGE_SIZE);
-	memset(empty_zero_page, 0, PAGE_SIZE);
 }
 
 static void __init gateway_init(void)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fefe7c8bf05f..80b94b0add1f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -145,6 +145,7 @@ config PPC
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK
 	select ARCH_USE_CMPXCHG_LOCKREF if PPC64
 	select HAVE_ARCH_AUDITSYSCALL
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index bc2347774f0a..0fdd7eece6d9 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -447,6 +447,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
 	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
+#define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index fddb72b48ce9..d645428a65a4 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -198,8 +198,10 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	return rb;
 }
 
-static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l,
+					     bool is_base_size)
 {
+
 	int size, a_psize;
 	/* Look at the 8 bit LP value */
 	unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
@@ -214,14 +216,27 @@ static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
 				continue;
 
 			a_psize = __hpte_actual_psize(lp, size);
-			if (a_psize != -1)
+			if (a_psize != -1) {
+				if (is_base_size)
+					return 1ul << mmu_psize_defs[size].shift;
 				return 1ul << mmu_psize_defs[a_psize].shift;
+			}
 		}
 
 	}
 	return 0;
 }
 
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 0);
+}
+
+static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 1);
+}
+
 static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)
 {
 	return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 807014dde821..c2b4dcf23d03 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -22,6 +22,7 @@
  */
 #include <asm/pgtable-ppc64.h>
 #include <asm/bug.h>
+#include <asm/processor.h>
 
 /*
  * Segment table
@@ -496,7 +497,7 @@ extern void slb_set_size(u16 size);
  */
 struct subpage_prot_table {
 	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[2];
+	unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)];
 	unsigned int *low_prot[4];
 };
 
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 9ea266eae33e..7e4612528546 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -277,6 +277,8 @@ n:
 	.globl n;	\
 n:
 
+#define _GLOBAL_TOC(name) _GLOBAL(name)
+
 #define _KPROBE(n)	\
 	.section ".kprobes.text","a";	\
 	.globl	n;	\
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 965291b4c2fa..0c157642c2a1 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -527,6 +527,26 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
+	{	/* Power8 DD1: Does not support doorbell IPIs */
+		.pvr_mask		= 0xffffff00,
+		.pvr_value		= 0x004d0100,
+		.cpu_name		= "POWER8 (raw)",
+		.cpu_features		= CPU_FTRS_POWER8_DD1,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.flush_tlb		= __flush_tlb_power8,
+		.machine_check_early	= __machine_check_early_realmode_p8,
+		.platform		= "power8",
+	},
 	{	/* Power8 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x004d0000,
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 658e89d2025b..db2b482af658 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -611,17 +611,19 @@ static void rtas_flash_firmware(int reboot_type)
 	for (f = flist; f; f = next) {
 		/* Translate data addrs to absolute */
 		for (i = 0; i < f->num_blocks; i++) {
-			f->blocks[i].data = (char *)__pa(f->blocks[i].data);
+			f->blocks[i].data = (char *)cpu_to_be64(__pa(f->blocks[i].data));
 			image_size += f->blocks[i].length;
+			f->blocks[i].length = cpu_to_be64(f->blocks[i].length);
 		}
 		next = f->next;
 		/* Don't translate NULL pointer for last entry */
 		if (f->next)
-			f->next = (struct flash_block_list *)__pa(f->next);
+			f->next = (struct flash_block_list *)cpu_to_be64(__pa(f->next));
 		else
 			f->next = NULL;
 		/* make num_blocks into the version/length field */
 		f->num_blocks = (FLASH_BLOCK_LIST_VERSION << 56) | ((f->num_blocks+1)*16);
+		f->num_blocks = cpu_to_be64(f->num_blocks);
 	}
 
 	printk(KERN_ALERT "FLASH: flash image is %ld bytes\n", image_size);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 51a3ff78838a..1007fb802e6b 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -747,7 +747,7 @@ int setup_profiling_timer(unsigned int multiplier)
 
 #ifdef CONFIG_SCHED_SMT
 /* cpumask of CPUs with asymetric SMT dependancy */
-static const int powerpc_smt_flags(void)
+static int powerpc_smt_flags(void)
 {
 	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 80561074078d..68468d695f12 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1562,7 +1562,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 				goto out;
 			}
 			if (!rma_setup && is_vrma_hpte(v)) {
-				unsigned long psize = hpte_page_size(v, r);
+				unsigned long psize = hpte_base_page_size(v, r);
 				unsigned long senc = slb_pgsize_encoding(psize);
 				unsigned long lpcr;
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6e6224318c36..5a24d3c2b6b8 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -814,13 +814,10 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			r = hpte[i+1];
 
 			/*
-			 * Check the HPTE again, including large page size
-			 * Since we don't currently allow any MPSS (mixed
-			 * page-size segment) page sizes, it is sufficient
-			 * to check against the actual page size.
+			 * Check the HPTE again, including base page size
 			 */
 			if ((v & valid) && (v & mask) == val &&
-			    hpte_page_size(v, r) == (1ul << pshift))
+			    hpte_base_page_size(v, r) == (1ul << pshift))
 				/* Return with the HPTE still locked */
 				return (hash << 3) + (i >> 1);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 868347ef09fd..558a67df8126 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -48,7 +48,7 @@
  *
  * LR = return address to continue at after eventually re-enabling MMU
  */
-_GLOBAL(kvmppc_hv_entry_trampoline)
+_GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
 	stdu	r1, -112(r1)
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index e2c29e381dc7..d044b8b7c69d 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -25,7 +25,11 @@
 #include <asm/exception-64s.h>
 
 #if defined(CONFIG_PPC_BOOK3S_64)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define FUNC(name) 		name
+#else
 #define FUNC(name) 		GLUE(.,name)
+#endif
 #define GET_SHADOW_VCPU(reg)    addi	reg, r13, PACA_SVCPU
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 9eec675220e6..16c4d88ba27d 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -36,7 +36,11 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define FUNC(name) 		name
+#else
 #define FUNC(name) 		GLUE(.,name)
+#endif
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
@@ -146,7 +150,7 @@ kvmppc_handler_skip_ins:
  * On entry, r4 contains the guest shadow MSR
  * MSR.EE has to be 0 when calling this function
  */
-_GLOBAL(kvmppc_entry_trampoline)
+_GLOBAL_TOC(kvmppc_entry_trampoline)
 	mfmsr	r5
 	LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter)
 	toreal(r7)
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index edb14ba992b3..ef27fbd5d9c5 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -23,20 +23,20 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq, server, priority;
 	int rc;
 
-	if (args->nargs != 3 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 3 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
-	server = args->args[1];
-	priority = args->args[2];
+	irq = be32_to_cpu(args->args[0]);
+	server = be32_to_cpu(args->args[1]);
+	priority = be32_to_cpu(args->args[2]);
 
 	rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -44,12 +44,12 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq, server, priority;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 3) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 3) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	server = priority = 0;
 	rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
@@ -58,10 +58,10 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 		goto out;
 	}
 
-	args->rets[1] = server;
-	args->rets[2] = priority;
+	args->rets[1] = cpu_to_be32(server);
+	args->rets[2] = cpu_to_be32(priority);
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -69,18 +69,18 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	rc = kvmppc_xics_int_off(vcpu->kvm, irq);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -88,18 +88,18 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	rc = kvmppc_xics_int_on(vcpu->kvm, irq);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 #endif /* CONFIG_KVM_XICS */
 
@@ -205,32 +205,6 @@ int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp)
 	return rc;
 }
 
-static void kvmppc_rtas_swap_endian_in(struct rtas_args *args)
-{
-#ifdef __LITTLE_ENDIAN__
-	int i;
-
-	args->token = be32_to_cpu(args->token);
-	args->nargs = be32_to_cpu(args->nargs);
-	args->nret = be32_to_cpu(args->nret);
-	for (i = 0; i < args->nargs; i++)
-		args->args[i] = be32_to_cpu(args->args[i]);
-#endif
-}
-
-static void kvmppc_rtas_swap_endian_out(struct rtas_args *args)
-{
-#ifdef __LITTLE_ENDIAN__
-	int i;
-
-	for (i = 0; i < args->nret; i++)
-		args->args[i] = cpu_to_be32(args->args[i]);
-	args->token = cpu_to_be32(args->token);
-	args->nargs = cpu_to_be32(args->nargs);
-	args->nret = cpu_to_be32(args->nret);
-#endif
-}
-
 int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 {
 	struct rtas_token_definition *d;
@@ -249,8 +223,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	if (rc)
 		goto fail;
 
-	kvmppc_rtas_swap_endian_in(&args);
-
 	/*
 	 * args->rets is a pointer into args->args. Now that we've
 	 * copied args we need to fix it up to point into our copy,
@@ -258,13 +230,13 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	 * value so we can restore it on the way out.
 	 */
 	orig_rets = args.rets;
-	args.rets = &args.args[args.nargs];
+	args.rets = &args.args[be32_to_cpu(args.nargs)];
 
 	mutex_lock(&vcpu->kvm->lock);
 
 	rc = -ENOENT;
 	list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) {
-		if (d->token == args.token) {
+		if (d->token == be32_to_cpu(args.token)) {
 			d->handler->handler(vcpu, &args);
 			rc = 0;
 			break;
@@ -275,7 +247,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 
 	if (rc == 0) {
 		args.rets = orig_rets;
-		kvmppc_rtas_swap_endian_out(&args);
 		rc = kvm_write_guest(vcpu->kvm, args_phys, &args, sizeof(args));
 		if (rc)
 			goto fail;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index dd2cc03f406f..86903d3f5a03 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -473,7 +473,8 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		if (printk_ratelimit())
 			pr_err("%s: pte not present: gfn %lx, pfn %lx\n",
 				__func__, (long)gfn, pfn);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);
 
diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S
index 0738f96befbf..43435c6892fb 100644
--- a/arch/powerpc/lib/mem_64.S
+++ b/arch/powerpc/lib/mem_64.S
@@ -77,7 +77,7 @@ _GLOBAL(memset)
 	stb	r4,0(r6)
 	blr
 
-_GLOBAL(memmove)
+_GLOBAL_TOC(memmove)
 	cmplw	0,r3,r4
 	bgt	backwards_memcpy
 	b	memcpy
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 412dd46dd0b7..5c09f365c842 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1198,7 +1198,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = regs->gpr[rb] & 0x3f;
 			ival = (signed int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> (sh < 32 ? sh : 31);
-			if (ival < 0 && (sh >= 32 || (ival & ((1 << sh) - 1)) != 0))
+			if (ival < 0 && (sh >= 32 || (ival & ((1ul << sh) - 1)) != 0))
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1208,7 +1208,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = rb;
 			ival = (signed int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> sh;
-			if (ival < 0 && (ival & ((1 << sh) - 1)) != 0)
+			if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0)
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1216,7 +1216,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef __powerpc64__
 		case 27:	/* sld */
-			sh = regs->gpr[rd] & 0x7f;
+			sh = regs->gpr[rb] & 0x7f;
 			if (sh < 64)
 				regs->gpr[ra] = regs->gpr[rd] << sh;
 			else
@@ -1235,7 +1235,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = regs->gpr[rb] & 0x7f;
 			ival = (signed long int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> (sh < 64 ? sh : 63);
-			if (ival < 0 && (sh >= 64 || (ival & ((1 << sh) - 1)) != 0))
+			if (ival < 0 && (sh >= 64 || (ival & ((1ul << sh) - 1)) != 0))
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1246,7 +1246,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = rb | ((instr & 2) << 4);
 			ival = (signed long int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> sh;
-			if (ival < 0 && (ival & ((1 << sh) - 1)) != 0)
+			if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0)
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 6dcdadefd8d0..82e82cadcde5 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -390,12 +390,16 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 		case BPF_ANC | SKF_AD_VLAN_TAG:
 		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+			BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+
 			PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  vlan_tci));
-			if (code == (BPF_ANC | SKF_AD_VLAN_TAG))
-				PPC_ANDI(r_A, r_A, VLAN_VID_MASK);
-			else
+			if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
+				PPC_ANDI(r_A, r_A, ~VLAN_TAG_PRESENT);
+			} else {
 				PPC_ANDI(r_A, r_A, VLAN_TAG_PRESENT);
+				PPC_SRWI(r_A, r_A, 12);
+			}
 			break;
 		case BPF_ANC | SKF_AD_QUEUE:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 6b0641c3f03f..fe52db2eea6a 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1307,6 +1307,9 @@ static void power_pmu_enable(struct pmu *pmu)
  out_enable:
 	pmao_restore_workaround(ebb);
 
+	if (ppmu->flags & PPMU_ARCH_207S)
+		mtspr(SPRN_MMCR2, 0);
+
 	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
 
 	mb();
@@ -1315,9 +1318,6 @@ static void power_pmu_enable(struct pmu *pmu)
 
 	write_mmcr0(cpuhw, mmcr0);
 
-	if (ppmu->flags & PPMU_ARCH_207S)
-		mtspr(SPRN_MMCR2, 0);
-
 	/*
 	 * Enable instruction sampling if necessary
 	 */
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 10268c41d830..0ad533b617f7 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -249,7 +249,7 @@ static void elog_work_fn(struct work_struct *work)
 
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
-		pr_err("ELOG: Opal log read failed\n");
+		pr_err("ELOG: OPAL log info read failed\n");
 		return;
 	}
 
@@ -257,7 +257,7 @@ static void elog_work_fn(struct work_struct *work)
 	log_id = be64_to_cpu(id);
 	elog_type = be64_to_cpu(type);
 
-	BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
+	WARN_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
 
 	if (elog_size >= OPAL_MAX_ERRLOG_SIZE)
 		elog_size  =  OPAL_MAX_ERRLOG_SIZE;
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 022b38e6a80b..2d0b4d68a40a 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -86,6 +86,7 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa,
 	}
 
 	of_node_set_flag(dn, OF_DYNAMIC);
+	of_node_init(dn);
 
 	return dn;
 }
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 0435bb65d0aa..1c0a60d98867 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -69,6 +69,7 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist
 
 	np->properties = proplist;
 	of_node_set_flag(np, OF_DYNAMIC);
+	of_node_init(np);
 
 	np->parent = derive_parent(path);
 	if (IS_ERR(np->parent)) {
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index df38c70cd59e..18ea9e3f8142 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -51,8 +51,8 @@ static inline int restore_fp_ctl(u32 *fpc)
 		return 0;
 
 	asm volatile(
-		"0:	lfpc    %1\n"
-		"	la	%0,0\n"
+		"	lfpc    %1\n"
+		"0:	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
 		: "=d" (rc) : "Q" (*fpc), "0" (-EINVAL));
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 7ba7d6784510..e88d35d74950 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -437,11 +437,11 @@ ENTRY(startup_kdump)
 
 #if defined(CONFIG_64BIT)
 #if defined(CONFIG_MARCH_ZEC12)
-	.long 3, 0xc100efea, 0xf46ce800, 0x00400000
+	.long 3, 0xc100eff2, 0xf46ce800, 0x00400000
 #elif defined(CONFIG_MARCH_Z196)
-	.long 2, 0xc100efea, 0xf46c0000
+	.long 2, 0xc100eff2, 0xf46c0000
 #elif defined(CONFIG_MARCH_Z10)
-	.long 2, 0xc100efea, 0xf0680000
+	.long 2, 0xc100eff2, 0xf0680000
 #elif defined(CONFIG_MARCH_Z9_109)
 	.long 1, 0xc100efc2
 #elif defined(CONFIG_MARCH_Z990)
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 2d716734b5b1..5dc7ad9e2fbf 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -334,9 +334,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 			unsigned long mask = PSW_MASK_USER;
 
 			mask |= is_ri_task(child) ? PSW_MASK_RI : 0;
-			if ((data & ~mask) != PSW_USER_BITS)
+			if ((data ^ PSW_USER_BITS) & ~mask)
+				/* Invalid psw mask. */
+				return -EINVAL;
+			if ((data & PSW_MASK_ASC) == PSW_ASC_HOME)
+				/* Invalid address-space-control bits */
 				return -EINVAL;
 			if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))
+				/* Invalid addressing mode bits */
 				return -EINVAL;
 		}
 		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
@@ -672,9 +677,12 @@ static int __poke_user_compat(struct task_struct *child,
 
 			mask |= is_ri_task(child) ? PSW32_MASK_RI : 0;
 			/* Build a 64 bit psw mask from 31 bit mask. */
-			if ((tmp & ~mask) != PSW32_USER_BITS)
+			if ((tmp ^ PSW32_USER_BITS) & ~mask)
 				/* Invalid psw mask. */
 				return -EINVAL;
+			if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME)
+				/* Invalid address-space-control bits */
+				return -EINVAL;
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
 				(regs->psw.mask & PSW_MASK_BA) |
 				(__u64)(tmp & mask) << 32;
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 9ddc51eeb8d6..30de42730b2f 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -48,13 +48,10 @@
 static LIST_HEAD(zpci_list);
 static DEFINE_SPINLOCK(zpci_list_lock);
 
-static void zpci_enable_irq(struct irq_data *data);
-static void zpci_disable_irq(struct irq_data *data);
-
 static struct irq_chip zpci_irq_chip = {
 	.name = "zPCI",
-	.irq_unmask = zpci_enable_irq,
-	.irq_mask = zpci_disable_irq,
+	.irq_unmask = unmask_msi_irq,
+	.irq_mask = mask_msi_irq,
 };
 
 static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
@@ -244,43 +241,6 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 	return rc;
 }
 
-static int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
-{
-	int offset, pos;
-	u32 mask_bits;
-
-	if (msi->msi_attrib.is_msix) {
-		offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_VECTOR_CTRL;
-		msi->masked = readl(msi->mask_base + offset);
-		writel(flag, msi->mask_base + offset);
-	} else if (msi->msi_attrib.maskbit) {
-		pos = (long) msi->mask_base;
-		pci_read_config_dword(msi->dev, pos, &mask_bits);
-		mask_bits &= ~(mask);
-		mask_bits |= flag & mask;
-		pci_write_config_dword(msi->dev, pos, mask_bits);
-	} else
-		return 0;
-
-	msi->msi_attrib.maskbit = !!flag;
-	return 1;
-}
-
-static void zpci_enable_irq(struct irq_data *data)
-{
-	struct msi_desc *msi = irq_get_msi_desc(data->irq);
-
-	zpci_msi_set_mask_bits(msi, 1, 0);
-}
-
-static void zpci_disable_irq(struct irq_data *data)
-{
-	struct msi_desc *msi = irq_get_msi_desc(data->irq);
-
-	zpci_msi_set_mask_bits(msi, 1, 1);
-}
-
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
 }
@@ -487,7 +447,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 
 	/* Release MSI interrupts */
 	list_for_each_entry(msi, &pdev->msi_list, list) {
-		zpci_msi_set_mask_bits(msi, 1, 1);
+		if (msi->msi_attrib.is_msix)
+			default_msix_mask_irq(msi, 1);
+		else
+			default_msi_mask_irq(msi, 1, 1);
 		irq_set_msi_desc(msi->irq, NULL);
 		irq_free_desc(msi->irq);
 		msi->msg.address_lo = 0;
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index d4d16e4be07c..bf5b3f5f4962 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -32,7 +32,8 @@ endif
 
 cflags-$(CONFIG_CPU_SH2)		:= $(call cc-option,-m2,)
 cflags-$(CONFIG_CPU_SH2A)		+= $(call cc-option,-m2a,) \
-					   $(call cc-option,-m2a-nofpu,)
+					   $(call cc-option,-m2a-nofpu,) \
+					   $(call cc-option,-m4-nofpu,)
 cflags-$(CONFIG_CPU_SH3)		:= $(call cc-option,-m3,)
 cflags-$(CONFIG_CPU_SH4)		:= $(call cc-option,-m4,) \
 	$(call cc-option,-mno-implicit-fp,-m4-nofpu)
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 29f2e988c56a..407c87d9879a 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -78,6 +78,7 @@ config SPARC64
 	select HAVE_C_RECORDMCOUNT
 	select NO_BOOTMEM
 	select HAVE_ARCH_AUDITSYSCALL
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index b73274fb961a..42f2bca1d338 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -410,8 +410,9 @@
 #define __NR_finit_module	342
 #define __NR_sched_setattr	343
 #define __NR_sched_getattr	344
+#define __NR_renameat2		345
 
-#define NR_syscalls		345
+#define NR_syscalls		346
 
 /* Bitmask values returned from kern_features system call.  */
 #define KERN_FEATURE_MIXED_MODE_STACK	0x00000001
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index d066eb18650c..f834224208ed 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -48,6 +48,7 @@ SIGN1(sys32_futex, compat_sys_futex, %o1)
 SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
 SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0)
 SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0)
+SIGN2(sys32_renameat2, sys_renameat2, %o0, %o2)
 
 	.globl		sys32_mmap2
 sys32_mmap2:
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index 151ace8766cc..85fe9b1087cd 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -86,3 +86,4 @@ sys_call_table:
 /*330*/	.long sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
 /*335*/	.long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+/*345*/	.long sys_renameat2
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 4bd4e2bb26cf..33ecba2826ea 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -87,6 +87,7 @@ sys_call_table32:
 /*330*/	.word compat_sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, compat_sys_open_by_handle_at, compat_sys_clock_adjtime
 	.word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+	.word sys32_renameat2
 
 #endif /* CONFIG_COMPAT */
 
@@ -165,3 +166,4 @@ sys_call_table:
 /*330*/	.word sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
 	.word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+	.word sys_renameat2
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index 9472079471bb..f1b3eb14b855 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -12,6 +12,7 @@
 #include <mem_user.h>
 #include <os.h>
 #include <skas.h>
+#include <kern_util.h>
 
 struct host_vm_change {
 	struct host_vm_op {
@@ -124,6 +125,9 @@ static int add_munmap(unsigned long addr, unsigned long len,
 	struct host_vm_op *last;
 	int ret = 0;
 
+	if ((addr >= STUB_START) && (addr < STUB_END))
+		return -EINVAL;
+
 	if (hvc->index != 0) {
 		last = &hvc->ops[hvc->index - 1];
 		if ((last->type == MUNMAP) &&
@@ -283,8 +287,11 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 	/* This is not an else because ret is modified above */
 	if (ret) {
 		printk(KERN_ERR "fix_range_common: failed, killing current "
-		       "process\n");
+		       "process: %d\n", task_tgid_vnr(current));
+		/* We are under mmap_sem, release it such that current can terminate */
+		up_write(&current->mm->mmap_sem);
 		force_sig(SIGKILL, current);
+		do_signal();
 	}
 }
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 974b87474a99..5678c3571e7c 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -206,7 +206,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 	int is_write = FAULT_WRITE(fi);
 	unsigned long address = FAULT_ADDRESS(fi);
 
-	if (regs)
+	if (!is_user && regs)
 		current->thread.segv_regs = container_of(regs, struct pt_regs, regs);
 
 	if (!is_user && (address >= start_vm) && (address < end_vm)) {
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index d531879a4617..908579f2b0ab 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -54,7 +54,7 @@ static int ptrace_dump_regs(int pid)
 
 void wait_stub_done(int pid)
 {
-	int n, status, err, bad_stop = 0;
+	int n, status, err;
 
 	while (1) {
 		CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL));
@@ -74,8 +74,6 @@ void wait_stub_done(int pid)
 
 	if (((1 << WSTOPSIG(status)) & STUB_DONE_MASK) != 0)
 		return;
-	else
-		bad_stop = 1;
 
 bad_wait:
 	err = ptrace_dump_regs(pid);
@@ -85,10 +83,7 @@ bad_wait:
 	printk(UM_KERN_ERR "wait_stub_done : failed to wait for SIGTRAP, "
 	       "pid = %d, n = %d, errno = %d, status = 0x%x\n", pid, n, errno,
 	       status);
-	if (bad_stop)
-		kill(pid, SIGKILL);
-	else
-		fatal_sigsegv();
+	fatal_sigsegv();
 }
 
 extern unsigned long current_stub_stack(void);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a8f749ef0fdc..d24887b645dc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -131,6 +131,7 @@ config X86
 	select HAVE_CC_STACKPROTECTOR
 	select GENERIC_CPU_AUTOPROBE
 	select HAVE_ARCH_AUDITSYSCALL
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 84c223479e3c..7a6d43a554d7 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -91,10 +91,9 @@ bs_die:
 
 	.section ".bsdata", "a"
 bugger_off_msg:
-	.ascii	"Direct floppy boot is not supported. "
-	.ascii	"Use a boot loader program instead.\r\n"
+	.ascii	"Use a boot loader.\r\n"
 	.ascii	"\n"
-	.ascii	"Remove disk and press any key to reboot ...\r\n"
+	.ascii	"Remove disk and press any key to reboot...\r\n"
 	.byte	0
 
 #ifdef CONFIG_EFI_STUB
@@ -108,7 +107,7 @@ coff_header:
 #else
 	.word	0x8664				# x86-64
 #endif
-	.word	3				# nr_sections
+	.word	4				# nr_sections
 	.long	0 				# TimeDateStamp
 	.long	0				# PointerToSymbolTable
 	.long	1				# NumberOfSymbols
@@ -250,6 +249,25 @@ section_table:
 	.word	0				# NumberOfLineNumbers
 	.long	0x60500020			# Characteristics (section flags)
 
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".bss"
+	.byte	0
+	.byte	0
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0xc8000080			# Characteristics (section flags)
+
 #endif /* CONFIG_EFI_STUB */
 
 	# Kernel attributes; used by setup.  This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 1a2f2121cada..a7661c430cd9 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -143,7 +143,7 @@ static void usage(void)
 
 #ifdef CONFIG_EFI_STUB
 
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
 {
 	unsigned int pe_header;
 	unsigned short num_sections;
@@ -164,10 +164,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
 			put_unaligned_le32(size, section + 0x8);
 
 			/* section header vma field */
-			put_unaligned_le32(offset, section + 0xc);
+			put_unaligned_le32(vma, section + 0xc);
 
 			/* section header 'size of initialised data' field */
-			put_unaligned_le32(size, section + 0x10);
+			put_unaligned_le32(datasz, section + 0x10);
 
 			/* section header 'file offset' field */
 			put_unaligned_le32(offset, section + 0x14);
@@ -179,6 +179,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
 	}
 }
 
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+	update_pecoff_section_header_fields(section_name, offset, size, size, offset);
+}
+
 static void update_pecoff_setup_and_reloc(unsigned int size)
 {
 	u32 setup_offset = 0x200;
@@ -203,9 +208,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
 
 	pe_header = get_unaligned_le32(&buf[0x3c]);
 
-	/* Size of image */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
 	/*
 	 * Size of code: Subtract the size of the first sector (512 bytes)
 	 * which includes the header.
@@ -220,6 +222,22 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
 	update_pecoff_section_header(".text", text_start, text_sz);
 }
 
+static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz)
+{
+	unsigned int pe_header;
+	unsigned int bss_sz = init_sz - file_sz;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+
+	/* Size of uninitialized data */
+	put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]);
+
+	/* Size of image */
+	put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
+
+	update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0);
+}
+
 static int reserve_pecoff_reloc_section(int c)
 {
 	/* Reserve 0x20 bytes for .reloc section */
@@ -259,6 +277,8 @@ static void efi_stub_entry_update(void)
 static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
 static inline void update_pecoff_text(unsigned int text_start,
 				      unsigned int file_sz) {}
+static inline void update_pecoff_bss(unsigned int file_sz,
+				     unsigned int init_sz) {}
 static inline void efi_stub_defaults(void) {}
 static inline void efi_stub_entry_update(void) {}
 
@@ -310,7 +330,7 @@ static void parse_zoffset(char *fname)
 
 int main(int argc, char ** argv)
 {
-	unsigned int i, sz, setup_sectors;
+	unsigned int i, sz, setup_sectors, init_sz;
 	int c;
 	u32 sys_size;
 	struct stat sb;
@@ -376,7 +396,9 @@ int main(int argc, char ** argv)
 	buf[0x1f1] = setup_sectors-1;
 	put_unaligned_le32(sys_size, &buf[0x1f4]);
 
-	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+	update_pecoff_text(setup_sectors * 512, i + (sys_size * 16));
+	init_sz = get_unaligned_le32(&buf[0x260]);
+	update_pecoff_bss(i + (sys_size * 16), init_sz);
 
 	efi_stub_entry_update();
 
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf88e624..0a8b519226b8 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
 
 #define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
 
-#define INTERRUPT_RETURN	iretq
+#define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
 	sysretq;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index f3a1f04ed4cb..584874451414 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -841,7 +841,6 @@ static int apm_do_idle(void)
 	u32 eax;
 	u8 ret = 0;
 	int idled = 0;
-	int polling;
 	int err = 0;
 
 	if (!need_resched()) {
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a80029035bf2..f9e4fdd3b877 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -370,6 +370,17 @@ static void init_intel(struct cpuinfo_x86 *c)
 	 */
 	detect_extended_topology(c);
 
+	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+		/*
+		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+		 * detection.
+		 */
+		c->x86_max_cores = intel_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+		detect_ht(c);
+#endif
+	}
+
 	l2 = init_intel_cacheinfo(c);
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
@@ -438,17 +449,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_P3);
 #endif
 
-	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
-		/*
-		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
-		 * detection.
-		 */
-		c->x86_max_cores = intel_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
-		detect_ht(c);
-#endif
-	}
-
 	/* Work around errata */
 	srat_detect_node(c);
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index a952e9c85b6f..9c8f7394c612 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -730,6 +730,18 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 #endif
 	}
 
+#ifdef CONFIG_X86_HT
+	/*
+	 * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
+	 * turns means that the only possibility is SMT (as indicated in
+	 * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
+	 * that SMT shares all caches, we can unconditionally set cpu_llc_id to
+	 * c->phys_proc_id.
+	 */
+	if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
+		per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+#endif
+
 	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
 
 	return l2;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index bb92f38153b2..9a79c8dbd8e8 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2451,6 +2451,12 @@ static __init int mcheck_init_device(void)
 	for_each_online_cpu(i) {
 		err = mce_device_create(i);
 		if (err) {
+			/*
+			 * Register notifier anyway (and do not unreg it) so
+			 * that we don't leave undeleted timers, see notifier
+			 * callback above.
+			 */
+			__register_hotcpu_notifier(&mce_cpu_notifier);
 			cpu_notifier_register_done();
 			goto err_device_create;
 		}
@@ -2471,10 +2477,6 @@ static __init int mcheck_init_device(void)
 err_register:
 	unregister_syscore_ops(&mce_syscore_ops);
 
-	cpu_notifier_register_begin();
-	__unregister_hotcpu_notifier(&mce_cpu_notifier);
-	cpu_notifier_register_done();
-
 err_device_create:
 	/*
 	 * We didn't keep track of which devices were created above, but
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bdfbff8a4f6..2879ecdaac43 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
 			return -EINVAL;
+		/* Check if the extra msrs can be safely accessed*/
+		if (!er->extra_msr_access)
+			return -ENXIO;
 
 		reg->idx = er->idx;
 		reg->config = event->attr.config1;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 3b2f9bdd974b..8ade93111e03 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -295,14 +295,16 @@ struct extra_reg {
 	u64			config_mask;
 	u64			valid_mask;
 	int			idx;  /* per_xxx->regs[] reg index */
+	bool			extra_msr_access;
 };
 
 #define EVENT_EXTRA_REG(e, ms, m, vm, i) {	\
-	.event = (e),		\
-	.msr = (ms),		\
-	.config_mask = (m),	\
-	.valid_mask = (vm),	\
-	.idx = EXTRA_REG_##i,	\
+	.event = (e),			\
+	.msr = (ms),			\
+	.config_mask = (m),		\
+	.valid_mask = (vm),		\
+	.idx = EXTRA_REG_##i,		\
+	.extra_msr_access = true,	\
 	}
 
 #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)	\
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index adb02aa62af5..2502d0d9d246 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1382,6 +1382,15 @@ again:
 	intel_pmu_lbr_read();
 
 	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
+	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
@@ -2173,6 +2182,41 @@ static void intel_snb_check_microcode(void)
 	}
 }
 
+/*
+ * Under certain circumstances, access certain MSR may cause #GP.
+ * The function tests if the input MSR can be safely accessed.
+ */
+static bool check_msr(unsigned long msr, u64 mask)
+{
+	u64 val_old, val_new, val_tmp;
+
+	/*
+	 * Read the current value, change it and read it back to see if it
+	 * matches, this is needed to detect certain hardware emulators
+	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
+	 */
+	if (rdmsrl_safe(msr, &val_old))
+		return false;
+
+	/*
+	 * Only change the bits which can be updated by wrmsrl.
+	 */
+	val_tmp = val_old ^ mask;
+	if (wrmsrl_safe(msr, val_tmp) ||
+	    rdmsrl_safe(msr, &val_new))
+		return false;
+
+	if (val_new != val_tmp)
+		return false;
+
+	/* Here it's sure that the MSR can be safely accessed.
+	 * Restore the old value and return.
+	 */
+	wrmsrl(msr, val_old);
+
+	return true;
+}
+
 static __init void intel_sandybridge_quirk(void)
 {
 	x86_pmu.check_microcode = intel_snb_check_microcode;
@@ -2262,7 +2306,8 @@ __init int intel_pmu_init(void)
 	union cpuid10_ebx ebx;
 	struct event_constraint *c;
 	unsigned int unused;
-	int version;
+	struct extra_reg *er;
+	int version, i;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
 		switch (boot_cpu_data.x86) {
@@ -2465,6 +2510,9 @@ __init int intel_pmu_init(void)
 	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		/* dTLB-load-misses on IVB is different than SNB */
+		hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
 		       sizeof(hw_cache_extra_regs));
 
@@ -2565,6 +2613,34 @@ __init int intel_pmu_init(void)
 		}
 	}
 
+	/*
+	 * Access LBR MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support LBR MSR
+	 * Check all LBT MSR here.
+	 * Disable LBR access if any LBR MSRs can not be accessed.
+	 */
+	if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL))
+		x86_pmu.lbr_nr = 0;
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) &&
+		      check_msr(x86_pmu.lbr_to + i, 0xffffUL)))
+			x86_pmu.lbr_nr = 0;
+	}
+
+	/*
+	 * Access extra MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support offcore event
+	 * Check all extra_regs here.
+	 */
+	if (x86_pmu.extra_regs) {
+		for (er = x86_pmu.extra_regs; er->msr; er++) {
+			er->extra_msr_access = check_msr(er->msr, 0x1ffUL);
+			/* Disable LBR select mapping */
+			if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access)
+				x86_pmu.lbr_sel_map = NULL;
+		}
+	}
+
 	/* Support full width counters using alternative MSR range */
 	if (x86_pmu.intel_cap.full_width_write) {
 		x86_pmu.max_period = x86_pmu.cntval_mask;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 980970cb744d..696ade311ded 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -311,9 +311,11 @@ static int alloc_bts_buffer(int cpu)
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node);
-	if (unlikely(!buffer))
+	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	if (unlikely(!buffer)) {
+		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
+	}
 
 	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
 	thresh = max / 16;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 65bbbea38b9c..ae6552a0701f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -550,16 +550,16 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
@@ -1222,6 +1222,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
 				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
@@ -1245,7 +1246,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index dbaa23e78b36..0d0c9d4ab6d5 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -425,8 +425,8 @@ sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
 	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
-	movl %eax,PT_EAX(%esp)
 sysenter_after_call:
+	movl %eax,PT_EAX(%esp)
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
@@ -502,6 +502,7 @@ ENTRY(system_call)
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
+syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
@@ -675,12 +676,12 @@ syscall_fault:
 END(syscall_fault)
 
 syscall_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
-	jmp syscall_exit
+	movl $-ENOSYS,%eax
+	jmp syscall_after_call
 END(syscall_badsys)
 
 sysenter_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
+	movl $-ENOSYS,%eax
 	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b25ca969edd2..c844f0816ab8 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -830,27 +830,24 @@ restore_args:
 	RESTORE_ARGS 1,8,1
 
 irq_return:
+	INTERRUPT_RETURN
+
+ENTRY(native_iret)
 	/*
 	 * Are we returning to a stack segment from the LDT?  Note: in
 	 * 64-bit mode SS:RSP on the exception stack is always valid.
 	 */
 #ifdef CONFIG_X86_ESPFIX64
 	testb $4,(SS-RIP)(%rsp)
-	jnz irq_return_ldt
+	jnz native_irq_return_ldt
 #endif
 
-irq_return_iret:
-	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return_iret, bad_iret)
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
+native_irq_return_iret:
 	iretq
-	_ASM_EXTABLE(native_iret, bad_iret)
-#endif
+	_ASM_EXTABLE(native_irq_return_iret, bad_iret)
 
 #ifdef CONFIG_X86_ESPFIX64
-irq_return_ldt:
+native_irq_return_ldt:
 	pushq_cfi %rax
 	pushq_cfi %rdi
 	SWAPGS
@@ -872,7 +869,7 @@ irq_return_ldt:
 	SWAPGS
 	movq %rax,%rsp
 	popq_cfi %rax
-	jmp irq_return_iret
+	jmp native_irq_return_iret
 #endif
 
 	.section .fixup,"ax"
@@ -956,13 +953,8 @@ __do_double_fault:
 	cmpl $__KERNEL_CS,CS(%rdi)
 	jne do_double_fault
 	movq RIP(%rdi),%rax
-	cmpq $irq_return_iret,%rax
-#ifdef CONFIG_PARAVIRT
-	je 1f
-	cmpq $native_iret,%rax
-#endif
+	cmpq $native_irq_return_iret,%rax
 	jne do_double_fault		/* This shouldn't happen... */
-1:
 	movq PER_CPU_VAR(kernel_stack),%rax
 	subq $(6*8-KERNEL_STACK_OFFSET),%rax	/* Reset to original stack */
 	movq %rax,RSP(%rdi)
@@ -1428,7 +1420,7 @@ error_sti:
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return_iret(%rip),%rcx
+	leaq native_irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
 	je error_swapgs
 	movl %ecx,%eax	/* zero extend */
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 6afbb16e9b79..94d857fb1033 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -175,7 +175,7 @@ void init_espfix_ap(void)
 	if (!pud_present(pud)) {
 		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
 			set_pud(&pud_p[n], pud);
 	}
@@ -185,7 +185,7 @@ void init_espfix_ap(void)
 	if (!pmd_present(pmd)) {
 		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
 			set_pmd(&pmd_p[n], pmd);
 	}
@@ -193,7 +193,6 @@ void init_espfix_ap(void)
 	pte_p = pte_offset_kernel(&pmd, addr);
 	stack_page = (void *)__get_free_page(GFP_KERNEL);
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
-	paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 7596df664901..67e6d19ef1be 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -574,6 +574,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
+	if (user_mode_vm(regs))
+		return 0;
+
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
 	/*
 	 * We don't want to be preempted for the entire
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34f93eb..a1da6737ba5b 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
 DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
 DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, iret);
 		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 57e5ce126d5a..ea030319b321 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -920,9 +920,9 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 			mark_tsc_unstable("cpufreq changes");
-	}
 
-	set_cyc2ns_scale(tsc_khz, freq->cpu);
+		set_cyc2ns_scale(tsc_khz, freq->cpu);
+	}
 
 	return 0;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f6449334ec45..ef432f891d30 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5887,6 +5887,18 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 			kvm_x86_ops->set_nmi(vcpu);
 		}
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
+		/*
+		 * Because interrupts can be injected asynchronously, we are
+		 * calling check_nested_events again here to avoid a race condition.
+		 * See https://lkml.org/lkml/2014/7/2/60 for discussion about this
+		 * proposal and current concerns.  Perhaps we should be setting
+		 * KVM_REQ_EVENT only on certain events and not unconditionally?
+		 */
+		if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+			r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+			if (r != 0)
+				return r;
+		}
 		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
 			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
 					    false);
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index c98583588580..ebfa9b2c871d 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -36,99 +36,133 @@
 
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 
 #include <xen/interface/xen.h>
 #include <xen/page.h>
 #include <xen/grant_table.h>
+#include <xen/xen.h>
 
 #include <asm/pgtable.h>
 
-static int map_pte_fn(pte_t *pte, struct page *pmd_page,
-		      unsigned long addr, void *data)
+static struct gnttab_vm_area {
+	struct vm_struct *area;
+	pte_t **ptes;
+} gnttab_shared_vm_area, gnttab_status_vm_area;
+
+int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   void **__shared)
 {
-	unsigned long **frames = (unsigned long **)data;
+	void *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
 
-	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
-	(*frames)++;
-	return 0;
-}
+	if (shared == NULL)
+		*__shared = shared = gnttab_shared_vm_area.area->addr;
 
-/*
- * This function is used to map shared frames to store grant status. It is
- * different from map_pte_fn above, the frames type here is uint64_t.
- */
-static int map_pte_fn_status(pte_t *pte, struct page *pmd_page,
-			     unsigned long addr, void *data)
-{
-	uint64_t **frames = (uint64_t **)data;
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
+	}
 
-	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
-	(*frames)++;
 	return 0;
 }
 
-static int unmap_pte_fn(pte_t *pte, struct page *pmd_page,
-			unsigned long addr, void *data)
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   grant_status_t **__shared)
 {
+	grant_status_t *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
+
+	if (shared == NULL)
+		*__shared = shared = gnttab_status_vm_area.area->addr;
+
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
+	}
 
-	set_pte_at(&init_mm, addr, pte, __pte(0));
 	return 0;
 }
 
-int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
-			   unsigned long max_nr_gframes,
-			   void **__shared)
+void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
 {
-	int rc;
-	void *shared = *__shared;
+	pte_t **ptes;
+	unsigned long addr;
+	unsigned long i;
 
-	if (shared == NULL) {
-		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
-		BUG_ON(area == NULL);
-		shared = area->addr;
-		*__shared = shared;
-	}
+	if (shared == gnttab_status_vm_area.area->addr)
+		ptes = gnttab_status_vm_area.ptes;
+	else
+		ptes = gnttab_shared_vm_area.ptes;
 
-	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
-				 PAGE_SIZE * nr_gframes,
-				 map_pte_fn, &frames);
-	return rc;
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, ptes[i], __pte(0));
+		addr += PAGE_SIZE;
+	}
 }
 
-int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
-			   unsigned long max_nr_gframes,
-			   grant_status_t **__shared)
+static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
 {
-	int rc;
-	grant_status_t *shared = *__shared;
+	area->ptes = kmalloc(sizeof(pte_t *) * nr_frames, GFP_KERNEL);
+	if (area->ptes == NULL)
+		return -ENOMEM;
 
-	if (shared == NULL) {
-		/* No need to pass in PTE as we are going to do it
-		 * in apply_to_page_range anyhow. */
-		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
-		BUG_ON(area == NULL);
-		shared = area->addr;
-		*__shared = shared;
+	area->area = alloc_vm_area(PAGE_SIZE * nr_frames, area->ptes);
+	if (area->area == NULL) {
+		kfree(area->ptes);
+		return -ENOMEM;
 	}
 
-	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
-				 PAGE_SIZE * nr_gframes,
-				 map_pte_fn_status, &frames);
-	return rc;
+	return 0;
 }
 
-void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
+static void arch_gnttab_vfree(struct gnttab_vm_area *area)
+{
+	free_vm_area(area->area);
+	kfree(area->ptes);
+}
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
 {
-	apply_to_page_range(&init_mm, (unsigned long)shared,
-			    PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL);
+	int ret;
+
+	if (!xen_pv_domain())
+		return 0;
+
+	ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Always allocate the space for the status frames in case
+	 * we're migrated to a host with V2 support.
+	 */
+	ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+  err:
+	arch_gnttab_vfree(&gnttab_shared_vm_area);
+	return -ENOMEM;
 }
+
 #ifdef CONFIG_XEN_PVH
 #include <xen/balloon.h>
 #include <xen/events.h>
-#include <xen/xen.h>
 #include <linux/slab.h>
 static int __init xlated_setup_gnttab_pages(void)
 {
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index f9e1ec346e35..8453e6e39895 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -376,38 +376,42 @@ _DoubleExceptionVector_WindowOverflow:
 	beqz	a2, 1f		# if at start of vector, don't restore
 
 	addi	a0, a0, -128
-	bbsi	a0, 8, 1f	# don't restore except for overflow 8 and 12
-	bbsi	a0, 7, 2f
+	bbsi.l	a0, 8, 1f	# don't restore except for overflow 8 and 12
+
+	/*
+	 * This fixup handler is for the extremely unlikely case where the
+	 * overflow handler's reference thru a0 gets a hardware TLB refill
+	 * that bumps out the (distinct, aliasing) TLB entry that mapped its
+	 * prior references thru a9/a13, and where our reference now thru
+	 * a9/a13 gets a 2nd-level miss exception (not hardware TLB refill).
+	 */
+	movi	a2, window_overflow_restore_a0_fixup
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+
+	bbsi.l	a0, 7, 2f
 
 	/*
 	 * Restore a0 as saved by _WindowOverflow8().
-	 *
-	 * FIXME:  we really need a fixup handler for this L32E,
-	 * for the extremely unlikely case where the overflow handler's
-	 * reference thru a0 gets a hardware TLB refill that bumps out
-	 * the (distinct, aliasing) TLB entry that mapped its prior
-	 * references thru a9, and where our reference now thru a9
-	 * gets a 2nd-level miss exception (not hardware TLB refill).
 	 */
 
-	l32e	a2, a9, -16
-	wsr	a2, depc	# replace the saved a0
-	j	1f
+	l32e	a0, a9, -16
+	wsr	a0, depc	# replace the saved a0
+	j	3f
 
 2:
 	/*
 	 * Restore a0 as saved by _WindowOverflow12().
-	 *
-	 * FIXME:  we really need a fixup handler for this L32E,
-	 * for the extremely unlikely case where the overflow handler's
-	 * reference thru a0 gets a hardware TLB refill that bumps out
-	 * the (distinct, aliasing) TLB entry that mapped its prior
-	 * references thru a13, and where our reference now thru a13
-	 * gets a 2nd-level miss exception (not hardware TLB refill).
 	 */
 
-	l32e	a2, a13, -16
-	wsr	a2, depc	# replace the saved a0
+	l32e	a0, a13, -16
+	wsr	a0, depc	# replace the saved a0
+3:
+	xsr	a3, excsave1
+	movi	a0, 0
+	s32i	a0, a3, EXC_TABLE_FIXUP
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
 1:
 	/*
 	 * Restore WindowBase while leaving all address registers restored.
@@ -449,6 +453,7 @@ _DoubleExceptionVector_WindowOverflow:
 
 	s32i	a0, a2, PT_DEPC
 
+_DoubleExceptionVector_handle_exception:
 	addx4	a0, a0, a3
 	l32i	a0, a0, EXC_TABLE_FAST_USER
 	xsr	a3, excsave1
@@ -464,11 +469,120 @@ _DoubleExceptionVector_WindowOverflow:
 	rotw	-3
 	j	1b
 
-	.end literal_prefix
 
 ENDPROC(_DoubleExceptionVector)
 
 /*
+ * Fixup handler for TLB miss in double exception handler for window owerflow.
+ * We get here with windowbase set to the window that was being spilled and
+ * a0 trashed. a0 bit 7 determines if this is a call8 (bit clear) or call12
+ * (bit set) window.
+ *
+ * We do the following here:
+ * - go to the original window retaining a0 value;
+ * - set up exception stack to return back to appropriate a0 restore code
+ *   (we'll need to rotate window back and there's no place to save this
+ *    information, use different return address for that);
+ * - handle the exception;
+ * - go to the window that was being spilled;
+ * - set up window_overflow_restore_a0_fixup as a fixup routine;
+ * - reload a0;
+ * - restore the original window;
+ * - reset the default fixup routine;
+ * - return to user. By the time we get to this fixup handler all information
+ *   about the conditions of the original double exception that happened in
+ *   the window overflow handler is lost, so we just return to userspace to
+ *   retry overflow from start.
+ *
+ * a0: value of depc, original value in depc
+ * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
+ * a3: exctable, original value in excsave1
+ */
+
+ENTRY(window_overflow_restore_a0_fixup)
+
+	rsr	a0, ps
+	extui	a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH
+	rsr	a2, windowbase
+	sub	a0, a2, a0
+	extui	a0, a0, 0, 3
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+
+	_beqi	a0, 1, .Lhandle_1
+	_beqi	a0, 3, .Lhandle_3
+
+	.macro	overflow_fixup_handle_exception_pane n
+
+	rsr	a0, depc
+	rotw	-\n
+
+	xsr	a3, excsave1
+	wsr	a2, depc
+	l32i	a2, a3, EXC_TABLE_KSTK
+	s32i	a0, a2, PT_AREG0
+
+	movi	a0, .Lrestore_\n
+	s32i	a0, a2, PT_DEPC
+	rsr	a0, exccause
+	j	_DoubleExceptionVector_handle_exception
+
+	.endm
+
+	overflow_fixup_handle_exception_pane 2
+.Lhandle_1:
+	overflow_fixup_handle_exception_pane 1
+.Lhandle_3:
+	overflow_fixup_handle_exception_pane 3
+
+	.macro	overflow_fixup_restore_a0_pane n
+
+	rotw	\n
+	/* Need to preserve a0 value here to be able to handle exception
+	 * that may occur on a0 reload from stack. It may occur because
+	 * TLB miss handler may not be atomic and pointer to page table
+	 * may be lost before we get here. There are no free registers,
+	 * so we need to use EXC_TABLE_DOUBLE_SAVE area.
+	 */
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	movi	a2, window_overflow_restore_a0_fixup
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+	bbsi.l	a0, 7, 1f
+	l32e	a0, a9, -16
+	j	2f
+1:
+	l32e	a0, a13, -16
+2:
+	rotw	-\n
+
+	.endm
+
+.Lrestore_2:
+	overflow_fixup_restore_a0_pane 2
+
+.Lset_default_fixup:
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	movi	a2, 0
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+	rfe
+
+.Lrestore_1:
+	overflow_fixup_restore_a0_pane 1
+	j	.Lset_default_fixup
+.Lrestore_3:
+	overflow_fixup_restore_a0_pane 3
+	j	.Lset_default_fixup
+
+ENDPROC(window_overflow_restore_a0_fixup)
+
+	.end literal_prefix
+/*
  * Debug interrupt vector
  *
  * There is not much space here, so simply jump to another handler.
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index ee32c0085dff..d16db6df86f8 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -269,13 +269,13 @@ SECTIONS
 		  .UserExceptionVector.literal)
   SECTION_VECTOR (_DoubleExceptionVector_literal,
 		  .DoubleExceptionVector.literal,
-		  DOUBLEEXC_VECTOR_VADDR - 16,
+		  DOUBLEEXC_VECTOR_VADDR - 40,
 		  SIZEOF(.UserExceptionVector.text),
 		  .UserExceptionVector.text)
   SECTION_VECTOR (_DoubleExceptionVector_text,
 		  .DoubleExceptionVector.text,
 		  DOUBLEEXC_VECTOR_VADDR,
-		  32,
+		  40,
 		  .DoubleExceptionVector.literal)
 
   . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3;
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 4224256bb215..77ed20209ca5 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -191,7 +191,7 @@ int __init mem_reserve(unsigned long start, unsigned long end, int must_exist)
 		return -EINVAL;
 	}
 
-	if (it && start - it->start < bank_sz) {
+	if (it && start - it->start <= bank_sz) {
 		if (start == it->start) {
 			if (end - it->start < bank_sz) {
 				it->start = end;
author	James Morris <james.l.morris@oracle.com>	2014-10-01 00:44:04 +1000
committer	James Morris <james.l.morris@oracle.com>	2014-10-01 00:44:04 +1000
commit	6c8ff877cdf13cd5287ed9d700cfb6cb70e2bfa1 (patch)
tree	2ab49b7d19fb69cdae5b6be9e7ba44f6cf3d45ef /arch
parent	35e1efd25a9e7d5cf2884fa23441ab87353849bb (diff)
parent	19583ca584d6f574384e17fe7613dfaeadcdc4a6 (diff)