Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
	net/ipv6/ip6_tunnel.c
	net/ipv6/ip6_vti.c

ipv6 tunnel statistic bug fixes conflicting with consolidation into
generic sw per-cpu net stats.

qlogic conflict between queue counting bug fix and the addition
of multiple MAC address support.

Signed-off-by: David S. Miller <davem@davemloft.net>

40 files changed, 305 insertions, 163 deletions

diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 68125dd766c6..39e58d1cdf90 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -8,7 +8,11 @@
 
 /******** no-legacy-syscalls-ABI *******/
 
-#ifndef _UAPI_ASM_ARC_UNISTD_H
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
 #define _UAPI_ASM_ARC_UNISTD_H
 
 #define __ARCH_WANT_SYS_EXECVE
@@ -36,4 +40,6 @@ __SYSCALL(__NR_arc_gettls, sys_arc_gettls)
 #define __NR_sysfs		(__NR_arch_specific_syscall + 3)
 __SYSCALL(__NR_sysfs, sys_sysfs)
 
+#undef __SYSCALL
+
 #endif
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index ee845fad939b..9987dd0e9c59 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -87,9 +87,9 @@
 		interrupts = <1 9 0xf04>;
 	};
 
-	gpio0: gpio@ffc40000 {
+	gpio0: gpio@e6050000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc40000 0 0x2c>;
+		reg = <0 0xe6050000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 4 0x4>;
 		#gpio-cells = <2>;
@@ -99,9 +99,9 @@
 		interrupt-controller;
 	};
 
-	gpio1: gpio@ffc41000 {
+	gpio1: gpio@e6051000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc41000 0 0x2c>;
+		reg = <0 0xe6051000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 5 0x4>;
 		#gpio-cells = <2>;
@@ -111,9 +111,9 @@
 		interrupt-controller;
 	};
 
-	gpio2: gpio@ffc42000 {
+	gpio2: gpio@e6052000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc42000 0 0x2c>;
+		reg = <0 0xe6052000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 6 0x4>;
 		#gpio-cells = <2>;
@@ -123,9 +123,9 @@
 		interrupt-controller;
 	};
 
-	gpio3: gpio@ffc43000 {
+	gpio3: gpio@e6053000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc43000 0 0x2c>;
+		reg = <0 0xe6053000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 7 0x4>;
 		#gpio-cells = <2>;
@@ -135,9 +135,9 @@
 		interrupt-controller;
 	};
 
-	gpio4: gpio@ffc44000 {
+	gpio4: gpio@e6054000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc44000 0 0x2c>;
+		reg = <0 0xe6054000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 8 0x4>;
 		#gpio-cells = <2>;
@@ -147,9 +147,9 @@
 		interrupt-controller;
 	};
 
-	gpio5: gpio@ffc45000 {
+	gpio5: gpio@e6055000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc45000 0 0x2c>;
+		reg = <0 0xe6055000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 9 0x4>;
 		#gpio-cells = <2>;
@@ -241,7 +241,7 @@
 
 	sdhi0: sdhi@ee100000 {
 		compatible = "renesas,sdhi-r8a7790";
-		reg = <0 0xee100000 0 0x100>;
+		reg = <0 0xee100000 0 0x200>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 165 4>;
 		cap-sd-highspeed;
@@ -250,7 +250,7 @@
 
 	sdhi1: sdhi@ee120000 {
 		compatible = "renesas,sdhi-r8a7790";
-		reg = <0 0xee120000 0 0x100>;
+		reg = <0 0xee120000 0 0x200>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 166 4>;
 		cap-sd-highspeed;
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index 4ec8d82b0492..44a59c3abfb0 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -242,12 +242,18 @@ static void __init ldp_display_init(void)
 
 static int ldp_twl_gpio_setup(struct device *dev, unsigned gpio, unsigned ngpio)
 {
+	int res;
+
 	/* LCD enable GPIO */
 	ldp_lcd_pdata.enable_gpio = gpio + 7;
 
 	/* Backlight enable GPIO */
 	ldp_lcd_pdata.backlight_gpio = gpio + 15;
 
+	res = platform_device_register(&ldp_lcd_device);
+	if (res)
+		pr_err("Unable to register LCD: %d\n", res);
+
 	return 0;
 }
 
@@ -346,7 +352,6 @@ static struct omap2_hsmmc_info mmc[] __initdata = {
 
 static struct platform_device *ldp_devices[] __initdata = {
 	&ldp_gpio_keys_device,
-	&ldp_lcd_device,
 };
 
 #ifdef CONFIG_OMAP_MUX
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 58347bb874a0..4cf165502b35 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -101,13 +101,51 @@ static const struct omap_dss_hwmod_data omap4_dss_hwmod_data[] __initconst = {
 	{ "dss_hdmi", "omapdss_hdmi", -1 },
 };
 
+static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
+{
+	u32 enable_mask, enable_shift;
+	u32 pipd_mask, pipd_shift;
+	u32 reg;
+
+	if (dsi_id == 0) {
+		enable_mask = OMAP4_DSI1_LANEENABLE_MASK;
+		enable_shift = OMAP4_DSI1_LANEENABLE_SHIFT;
+		pipd_mask = OMAP4_DSI1_PIPD_MASK;
+		pipd_shift = OMAP4_DSI1_PIPD_SHIFT;
+	} else if (dsi_id == 1) {
+		enable_mask = OMAP4_DSI2_LANEENABLE_MASK;
+		enable_shift = OMAP4_DSI2_LANEENABLE_SHIFT;
+		pipd_mask = OMAP4_DSI2_PIPD_MASK;
+		pipd_shift = OMAP4_DSI2_PIPD_SHIFT;
+	} else {
+		return -ENODEV;
+	}
+
+	reg = omap4_ctrl_pad_readl(OMAP4_CTRL_MODULE_PAD_CORE_CONTROL_DSIPHY);
+
+	reg &= ~enable_mask;
+	reg &= ~pipd_mask;
+
+	reg |= (lanes << enable_shift) & enable_mask;
+	reg |= (lanes << pipd_shift) & pipd_mask;
+
+	omap4_ctrl_pad_writel(reg, OMAP4_CTRL_MODULE_PAD_CORE_CONTROL_DSIPHY);
+
+	return 0;
+}
+
 static int omap_dsi_enable_pads(int dsi_id, unsigned lane_mask)
 {
+	if (cpu_is_omap44xx())
+		return omap4_dsi_mux_pads(dsi_id, lane_mask);
+
 	return 0;
 }
 
 static void omap_dsi_disable_pads(int dsi_id, unsigned lane_mask)
 {
+	if (cpu_is_omap44xx())
+		omap4_dsi_mux_pads(dsi_id, 0);
 }
 
 static int omap_dss_set_min_bus_tput(struct device *dev, unsigned long tput)
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index 56cebb05509e..d23c77fadb31 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -796,7 +796,7 @@ struct omap_hwmod omap2xxx_counter_32k_hwmod = {
 
 /* gpmc */
 static struct omap_hwmod_irq_info omap2xxx_gpmc_irqs[] = {
-	{ .irq = 20 },
+	{ .irq = 20 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -841,7 +841,7 @@ static struct omap_hwmod_class omap2_rng_hwmod_class = {
 };
 
 static struct omap_hwmod_irq_info omap2_rng_mpu_irqs[] = {
-	{ .irq = 52 },
+	{ .irq = 52 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index d33742908f97..4c3b1e6df508 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -2165,7 +2165,7 @@ static struct omap_hwmod_class omap3xxx_gpmc_hwmod_class = {
 };
 
 static struct omap_hwmod_irq_info omap3xxx_gpmc_irqs[] = {
-	{ .irq = 20 },
+	{ .irq = 20 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -2999,7 +2999,7 @@ static struct omap_mmu_dev_attr mmu_isp_dev_attr = {
 
 static struct omap_hwmod omap3xxx_mmu_isp_hwmod;
 static struct omap_hwmod_irq_info omap3xxx_mmu_isp_irqs[] = {
-	{ .irq = 24 },
+	{ .irq = 24 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -3041,7 +3041,7 @@ static struct omap_mmu_dev_attr mmu_iva_dev_attr = {
 
 static struct omap_hwmod omap3xxx_mmu_iva_hwmod;
 static struct omap_hwmod_irq_info omap3xxx_mmu_iva_irqs[] = {
-	{ .irq = 28 },
+	{ .irq = 28 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index db32d5380b11..18f333c440db 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1637,7 +1637,7 @@ static struct omap_hwmod dra7xx_uart1_hwmod = {
 	.class		= &dra7xx_uart_hwmod_class,
 	.clkdm_name	= "l4per_clkdm",
 	.main_clk	= "uart1_gfclk_mux",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= HWMOD_SWSUP_SIDLE_ACT | DEBUG_OMAP2UART1_FLAGS,
 	.prcm = {
 		.omap4 = {
 			.clkctrl_offs = DRA7XX_CM_L4PER_UART1_CLKCTRL_OFFSET,
diff --git a/arch/arm/mach-pxa/include/mach/lubbock.h b/arch/arm/mach-pxa/include/mach/lubbock.h
index 2a086e8373eb..958cd6af9384 100644
--- a/arch/arm/mach-pxa/include/mach/lubbock.h
+++ b/arch/arm/mach-pxa/include/mach/lubbock.h
@@ -10,6 +10,8 @@
  * published by the Free Software Foundation.
  */
 
+#include <mach/irqs.h>
+
 #define LUBBOCK_ETH_PHYS	PXA_CS3_PHYS
 
 #define LUBBOCK_FPGA_PHYS	PXA_CS2_PHYS
diff --git a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
index 7eb9a10fc1af..2fddf38192df 100644
--- a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
+++ b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
@@ -8,8 +8,6 @@
  * published by the Free Software Foundation.
 */
 
-#include <linux/clk-provider.h>
-#include <linux/irqchip.h>
 #include <linux/of_platform.h>
 
 #include <asm/mach/arch.h>
@@ -48,15 +46,9 @@ static void __init s3c64xx_dt_map_io(void)
 		panic("SoC is not S3C64xx!");
 }
 
-static void __init s3c64xx_dt_init_irq(void)
-{
-	of_clk_init(NULL);
-	samsung_wdt_reset_of_init();
-	irqchip_init();
-};
-
 static void __init s3c64xx_dt_init_machine(void)
 {
+	samsung_wdt_reset_of_init();
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
@@ -79,7 +71,6 @@ DT_MACHINE_START(S3C6400_DT, "Samsung S3C64xx (Flattened Device Tree)")
 	/* Maintainer: Tomasz Figa <tomasz.figa@gmail.com> */
 	.dt_compat	= s3c64xx_dt_compat,
 	.map_io		= s3c64xx_dt_map_io,
-	.init_irq	= s3c64xx_dt_init_irq,
 	.init_machine	= s3c64xx_dt_init_machine,
 	.restart        = s3c64xx_dt_restart,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index 958e3cbf0ac2..c18689123023 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -614,6 +614,11 @@ static struct regulator_consumer_supply fixed3v3_power_consumers[] = {
 	REGULATOR_SUPPLY("vqmmc", "sh_mmcif"),
 };
 
+/* Fixed 3.3V regulator used by LCD backlight */
+static struct regulator_consumer_supply fixed5v0_power_consumers[] = {
+	REGULATOR_SUPPLY("power", "pwm-backlight.0"),
+};
+
 /* Fixed 3.3V regulator to be used by SDHI0 */
 static struct regulator_consumer_supply vcc_sdhi0_consumers[] = {
 	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
@@ -1196,6 +1201,8 @@ static void __init eva_init(void)
 
 	regulator_register_always_on(0, "fixed-3.3V", fixed3v3_power_consumers,
 				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
+	regulator_register_always_on(3, "fixed-5.0V", fixed5v0_power_consumers,
+				     ARRAY_SIZE(fixed5v0_power_consumers), 5000000);
 
 	pinctrl_register_mappings(eva_pinctrl_map, ARRAY_SIZE(eva_pinctrl_map));
 	pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
diff --git a/arch/arm/mach-shmobile/board-bockw.c b/arch/arm/mach-shmobile/board-bockw.c
index 38611526fe9a..3c4995aebd22 100644
--- a/arch/arm/mach-shmobile/board-bockw.c
+++ b/arch/arm/mach-shmobile/board-bockw.c
@@ -679,7 +679,7 @@ static void __init bockw_init(void)
 			.id             = i,
 			.data           = &rsnd_card_info[i],
 			.size_data      = sizeof(struct asoc_simple_card_info),
-			.dma_mask       = ~0,
+			.dma_mask	= DMA_BIT_MASK(32),
 		};
 
 		platform_device_register_full(&cardinfo);
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index a8d3ce646fb9..e0406fd37390 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -245,7 +245,9 @@ static void __init lager_init(void)
 {
 	lager_add_standard_devices();
 
-	phy_register_fixup_for_id("r8a7790-ether-ff:01", lager_ksz8041_fixup);
+	if (IS_ENABLED(CONFIG_PHYLIB))
+		phy_register_fixup_for_id("r8a7790-ether-ff:01",
+					  lager_ksz8041_fixup);
 }
 
 static const char * const lager_boards_compat_dt[] __initconst = {
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 83e4f959ee47..85501238b425 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -96,7 +96,7 @@ static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
 	struct remap_data *info = data;
 	struct page *page = info->pages[info->index++];
 	unsigned long pfn = page_to_pfn(page);
-	pte_t pte = pfn_pte(pfn, info->prot);
+	pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot));
 
 	if (map_foreign_page(pfn, info->fgmfn, info->domid))
 		return -EFAULT;
@@ -224,10 +224,10 @@ static int __init xen_guest_init(void)
 	}
 	if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res))
 		return 0;
-	xen_hvm_resume_frames = res.start >> PAGE_SHIFT;
+	xen_hvm_resume_frames = res.start;
 	xen_events_irq = irq_of_parse_and_map(node, 0);
 	pr_info("Xen %s support found, events_irq=%d gnttab_frame_pfn=%lx\n",
-			version, xen_events_irq, xen_hvm_resume_frames);
+			version, xen_events_irq, (xen_hvm_resume_frames >> PAGE_SHIFT));
 	xen_domain_type = XEN_HVM_DOMAIN;
 
 	xen_setup_features();
diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
index 2820f1a6eebe..dde3fc9c49f0 100644
--- a/arch/arm64/include/asm/xen/page-coherent.h
+++ b/arch/arm64/include/asm/xen/page-coherent.h
@@ -23,25 +23,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir,
 	     struct dma_attrs *attrs)
 {
-	__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
 }
 
 static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir,
 		struct dma_attrs *attrs)
 {
-	__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
 }
 
 static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
 }
 
 static inline void xen_dma_sync_single_for_device(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
 }
 #endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6777a2192b83..6a8928bba03c 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -214,31 +214,29 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 {
 	int err, len, type, disabled = !ctrl.enabled;
 
-	if (disabled) {
-		len = 0;
-		type = HW_BREAKPOINT_EMPTY;
-	} else {
-		err = arch_bp_generic_fields(ctrl, &len, &type);
-		if (err)
-			return err;
-
-		switch (note_type) {
-		case NT_ARM_HW_BREAK:
-			if ((type & HW_BREAKPOINT_X) != type)
-				return -EINVAL;
-			break;
-		case NT_ARM_HW_WATCH:
-			if ((type & HW_BREAKPOINT_RW) != type)
-				return -EINVAL;
-			break;
-		default:
+	attr->disabled = disabled;
+	if (disabled)
+		return 0;
+
+	err = arch_bp_generic_fields(ctrl, &len, &type);
+	if (err)
+		return err;
+
+	switch (note_type) {
+	case NT_ARM_HW_BREAK:
+		if ((type & HW_BREAKPOINT_X) != type)
 			return -EINVAL;
-		}
+		break;
+	case NT_ARM_HW_WATCH:
+		if ((type & HW_BREAKPOINT_RW) != type)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	attr->bp_len	= len;
 	attr->bp_type	= type;
-	attr->disabled	= disabled;
 
 	return 0;
 }
diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts
index 4177b62240c2..a618dfc13e4c 100644
--- a/arch/powerpc/boot/dts/mpc5125twr.dts
+++ b/arch/powerpc/boot/dts/mpc5125twr.dts
@@ -58,7 +58,6 @@
 		compatible = "fsl,mpc5121-immr";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		#interrupt-cells = <2>;
 		ranges = <0x0 0x80000000 0x400000>;
 		reg = <0x80000000 0x400000>;
 		bus-frequency = <66000000>;	// 66 MHz ips bus
@@ -189,6 +188,10 @@
 			reg = <0xA000 0x1000>;
 		};
 
+		// disable USB1 port
+		// TODO:
+		// correct pinmux config and fix USB3320 ulpi dependency
+		// before re-enabling it
 		usb@3000 {
 			compatible = "fsl,mpc5121-usb2-dr";
 			reg = <0x3000 0x400>;
@@ -197,6 +200,7 @@
 			interrupts = <43 0x8>;
 			dr_mode = "host";
 			phy_type = "ulpi";
+			status = "disabled";
 		};
 
 		// 5125 PSCs are not 52xx or 5121 PSC compatible
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 894662a5d4d5..243ce69ad685 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -284,7 +284,7 @@ do_kvm_##n:								\
 	subi	r1,r1,INT_FRAME_SIZE;	/* alloc frame on kernel stack	*/ \
 	beq-	1f;							   \
 	ld	r1,PACAKSAVE(r13);	/* kernel stack to use		*/ \
-1:	cmpdi	cr1,r1,0;		/* check if r1 is in userspace	*/ \
+1:	cmpdi	cr1,r1,-INT_FRAME_SIZE;	/* check if r1 is in userspace	*/ \
 	blt+	cr1,3f;			/* abort if it is		*/ \
 	li	r1,(n);			/* will be reloaded later	*/ \
 	sth	r1,PACA_TRAP_SAVE(r13);					   \
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4a594b76674d..bc23b1ba7980 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -192,6 +192,10 @@ extern void kvmppc_load_up_vsx(void);
 extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
 extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
 extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
+extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
+				 struct kvm_vcpu *vcpu);
+extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
+				   struct kvmppc_book3s_shadow_vcpu *svcpu);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 0bd9348a4db9..192917d2239c 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -79,6 +79,7 @@ struct kvmppc_host_state {
 	ulong vmhandler;
 	ulong scratch0;
 	ulong scratch1;
+	ulong scratch2;
 	u8 in_guest;
 	u8 restore_hid5;
 	u8 napping;
@@ -106,6 +107,7 @@ struct kvmppc_host_state {
 };
 
 struct kvmppc_book3s_shadow_vcpu {
+	bool in_use;
 	ulong gpr[14];
 	u32 cr;
 	u32 xer;
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 9ee12610af02..aace90547614 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -35,7 +35,7 @@ extern void giveup_vsx(struct task_struct *);
 extern void enable_kernel_spe(void);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
-extern void switch_booke_debug_regs(struct thread_struct *new_thread);
+extern void switch_booke_debug_regs(struct debug_reg *new_debug);
 
 #ifndef CONFIG_SMP
 extern void discard_lazy_cpu_state(void);
diff --git a/arch/powerpc/include/asm/unaligned.h b/arch/powerpc/include/asm/unaligned.h
index 5f1b1e3c2137..8296381ae432 100644
--- a/arch/powerpc/include/asm/unaligned.h
+++ b/arch/powerpc/include/asm/unaligned.h
@@ -4,13 +4,18 @@
 #ifdef __KERNEL__
 
 /*
- * The PowerPC can do unaligned accesses itself in big endian mode.
+ * The PowerPC can do unaligned accesses itself based on its endian mode.
  */
 #include <linux/unaligned/access_ok.h>
 #include <linux/unaligned/generic.h>
 
+#ifdef __LITTLE_ENDIAN__
+#define get_unaligned	__get_unaligned_le
+#define put_unaligned	__put_unaligned_le
+#else
 #define get_unaligned	__get_unaligned_be
 #define put_unaligned	__put_unaligned_be
+#endif
 
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_UNALIGNED_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 2ea5cc033ec8..d3de01066f7d 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -576,6 +576,7 @@ int main(void)
 	HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
 	HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
 	HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+	HSTATE_FIELD(HSTATE_SCRATCH2, scratch2);
 	HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
 	HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
 	HSTATE_FIELD(HSTATE_NAPPING, napping);
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 2ae41aba4053..4f0946de2d5c 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -80,6 +80,7 @@ END_FTR_SECTION(0, 1)
 	 * of the function that the cpu should jump to to continue
 	 * initialization.
 	 */
+	.balign 8
 	.globl  __secondary_hold_spinloop
 __secondary_hold_spinloop:
 	.llong	0x0
@@ -470,6 +471,7 @@ _STATIC(__after_prom_start)
 	mtctr	r8
 	bctr
 
+.balign 8
 p_end:	.llong	_end - _stext
 
 4:	/* Now copy the rest of the kernel up to _end */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3386d8ab7eb0..4a96556fd2d4 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -339,7 +339,7 @@ static void set_debug_reg_defaults(struct thread_struct *thread)
 #endif
 }
 
-static void prime_debug_regs(struct thread_struct *thread)
+static void prime_debug_regs(struct debug_reg *debug)
 {
 	/*
 	 * We could have inherited MSR_DE from userspace, since
@@ -348,22 +348,22 @@ static void prime_debug_regs(struct thread_struct *thread)
 	 */
 	mtmsr(mfmsr() & ~MSR_DE);
 
-	mtspr(SPRN_IAC1, thread->debug.iac1);
-	mtspr(SPRN_IAC2, thread->debug.iac2);
+	mtspr(SPRN_IAC1, debug->iac1);
+	mtspr(SPRN_IAC2, debug->iac2);
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2
-	mtspr(SPRN_IAC3, thread->debug.iac3);
-	mtspr(SPRN_IAC4, thread->debug.iac4);
+	mtspr(SPRN_IAC3, debug->iac3);
+	mtspr(SPRN_IAC4, debug->iac4);
 #endif
-	mtspr(SPRN_DAC1, thread->debug.dac1);
-	mtspr(SPRN_DAC2, thread->debug.dac2);
+	mtspr(SPRN_DAC1, debug->dac1);
+	mtspr(SPRN_DAC2, debug->dac2);
 #if CONFIG_PPC_ADV_DEBUG_DVCS > 0
-	mtspr(SPRN_DVC1, thread->debug.dvc1);
-	mtspr(SPRN_DVC2, thread->debug.dvc2);
+	mtspr(SPRN_DVC1, debug->dvc1);
+	mtspr(SPRN_DVC2, debug->dvc2);
 #endif
-	mtspr(SPRN_DBCR0, thread->debug.dbcr0);
-	mtspr(SPRN_DBCR1, thread->debug.dbcr1);
+	mtspr(SPRN_DBCR0, debug->dbcr0);
+	mtspr(SPRN_DBCR1, debug->dbcr1);
 #ifdef CONFIG_BOOKE
-	mtspr(SPRN_DBCR2, thread->debug.dbcr2);
+	mtspr(SPRN_DBCR2, debug->dbcr2);
 #endif
 }
 /*
@@ -371,11 +371,11 @@ static void prime_debug_regs(struct thread_struct *thread)
  * debug registers, set the debug registers from the values
  * stored in the new thread.
  */
-void switch_booke_debug_regs(struct thread_struct *new_thread)
+void switch_booke_debug_regs(struct debug_reg *new_debug)
 {
 	if ((current->thread.debug.dbcr0 & DBCR0_IDM)
-		|| (new_thread->debug.dbcr0 & DBCR0_IDM))
-			prime_debug_regs(new_thread);
+		|| (new_debug->dbcr0 & DBCR0_IDM))
+			prime_debug_regs(new_debug);
 }
 EXPORT_SYMBOL_GPL(switch_booke_debug_regs);
 #else	/* !CONFIG_PPC_ADV_DEBUG_REGS */
@@ -683,7 +683,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	switch_booke_debug_regs(&new->thread);
+	switch_booke_debug_regs(&new->thread.debug);
 #else
 /*
  * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index f3ff587a8b7d..c5d148434c08 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -469,11 +469,14 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		slb_v = vcpu->kvm->arch.vrma_slb_v;
 	}
 
+	preempt_disable();
 	/* Find the HPTE in the hash table */
 	index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
 					 HPTE_V_VALID | HPTE_V_ABSENT);
-	if (index < 0)
+	if (index < 0) {
+		preempt_enable();
 		return -ENOENT;
+	}
 	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
 	v = hptep[0] & ~HPTE_V_HVLOCK;
 	gr = kvm->arch.revmap[index].guest_rpte;
@@ -481,6 +484,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Unlock the HPTE */
 	asm volatile("lwsync" : : : "memory");
 	hptep[0] = v;
+	preempt_enable();
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
@@ -665,6 +669,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			return -EFAULT;
 	} else {
 		page = pages[0];
+		pfn = page_to_pfn(page);
 		if (PageHuge(page)) {
 			page = compound_head(page);
 			pte_size <<= compound_order(page);
@@ -689,7 +694,6 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			}
 			rcu_read_unlock_sched();
 		}
-		pfn = page_to_pfn(page);
 	}
 
 	ret = -EFAULT;
@@ -707,8 +711,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
 	}
 
-	/* Set the HPTE to point to pfn */
-	r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
+	/*
+	 * Set the HPTE to point to pfn.
+	 * Since the pfn is at PAGE_SIZE granularity, make sure we
+	 * don't mask out lower-order bits if psize < PAGE_SIZE.
+	 */
+	if (psize < PAGE_SIZE)
+		psize = PAGE_SIZE;
+	r = (r & ~(HPTE_R_PP0 - psize)) | ((pfn << PAGE_SHIFT) & ~(psize - 1));
 	if (hpte_is_writable(r) && !write_ok)
 		r = hpte_make_readonly(r);
 	ret = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 072287f1c3bc..b51d5db78068 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -131,8 +131,9 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
 
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE &&
 	    vc->preempt_tb != TB_NIL) {
 		vc->stolen_tb += mftb() - vc->preempt_tb;
@@ -143,19 +144,20 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 		vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
 		vcpu->arch.busy_preempt = TB_NIL;
 	}
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
 static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
 
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
 		vc->preempt_tb = mftb();
 	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
 		vcpu->arch.busy_preempt = mftb();
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
 static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
@@ -486,11 +488,11 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
 	 */
 	if (vc->vcore_state != VCORE_INACTIVE &&
 	    vc->runner->arch.run_task != current) {
-		spin_lock(&vc->runner->arch.tbacct_lock);
+		spin_lock_irq(&vc->runner->arch.tbacct_lock);
 		p = vc->stolen_tb;
 		if (vc->preempt_tb != TB_NIL)
 			p += now - vc->preempt_tb;
-		spin_unlock(&vc->runner->arch.tbacct_lock);
+		spin_unlock_irq(&vc->runner->arch.tbacct_lock);
 	} else {
 		p = vc->stolen_tb;
 	}
@@ -512,10 +514,10 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	core_stolen = vcore_stolen_time(vc, now);
 	stolen = core_stolen - vcpu->arch.stolen_logged;
 	vcpu->arch.stolen_logged = core_stolen;
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
 	stolen += vcpu->arch.busy_stolen;
 	vcpu->arch.busy_stolen = 0;
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	if (!dt || !vpa)
 		return;
 	memset(dt, 0, sizeof(struct dtl_entry));
@@ -589,7 +591,9 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
 			return RESUME_HOST;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		rc = kvmppc_rtas_hcall(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 		if (rc == -ENOENT)
 			return RESUME_HOST;
@@ -1115,13 +1119,13 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
 	now = mftb();
 	vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
 		vcpu->arch.stolen_logged;
 	vcpu->arch.busy_preempt = now;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	--vc->n_runnable;
 	list_del(&vcpu->arch.run_list);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 9c515440ad1a..8689e2e30857 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -225,6 +225,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		is_io = pa & (HPTE_R_I | HPTE_R_W);
 		pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
 		pa &= PAGE_MASK;
+		pa |= gpa & ~PAGE_MASK;
 	} else {
 		/* Translate to host virtual address */
 		hva = __gfn_to_hva_memslot(memslot, gfn);
@@ -238,13 +239,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 				ptel = hpte_make_readonly(ptel);
 			is_io = hpte_cache_bits(pte_val(pte));
 			pa = pte_pfn(pte) << PAGE_SHIFT;
+			pa |= hva & (pte_size - 1);
+			pa |= gpa & ~PAGE_MASK;
 		}
 	}
 
 	if (pte_size < psize)
 		return H_PARAMETER;
-	if (pa && pte_size > psize)
-		pa |= gpa & (pte_size - 1);
 
 	ptel &= ~(HPTE_R_PP0 - psize);
 	ptel |= pa;
@@ -749,6 +750,10 @@ static int slb_base_page_shift[4] = {
 	20,	/* 1M, unsupported */
 };
 
+/* When called from virtmode, this func should be protected by
+ * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
+ * can trigger deadlock issue.
+ */
 long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			      unsigned long valid)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bc8de75b1925..be4fa04a37c9 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -153,7 +153,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 13:	b	machine_check_fwnmi
 
-
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
  * Relocation is off and most register values are lost.
@@ -224,6 +223,11 @@ kvm_start_guest:
 	/* Clear our vcpu pointer so we don't come back in early */
 	li	r0, 0
 	std	r0, HSTATE_KVM_VCPU(r13)
+	/*
+	 * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
+	 * the nap_count, because once the increment to nap_count is
+	 * visible we could be given another vcpu.
+	 */
 	lwsync
 	/* Clear any pending IPI - we're an offline thread */
 	ld	r5, HSTATE_XICS_PHYS(r13)
@@ -241,7 +245,6 @@ kvm_start_guest:
 	/* increment the nap count and then go to nap mode */
 	ld	r4, HSTATE_KVM_VCORE(r13)
 	addi	r4, r4, VCORE_NAP_COUNT
-	lwsync				/* make previous updates visible */
 51:	lwarx	r3, 0, r4
 	addi	r3, r3, 1
 	stwcx.	r3, 0, r4
@@ -751,15 +754,14 @@ kvmppc_interrupt_hv:
 	 * guest CR, R12 saved in shadow VCPU SCRATCH1/0
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
-	/* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
-	std	r9, HSTATE_HOST_R2(r13)
+	std	r9, HSTATE_SCRATCH2(r13)
 
 	lbz	r9, HSTATE_IN_GUEST(r13)
 	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
 	beq	kvmppc_bad_host_intr
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	cmpwi	r9, KVM_GUEST_MODE_GUEST
-	ld	r9, HSTATE_HOST_R2(r13)
+	ld	r9, HSTATE_SCRATCH2(r13)
 	beq	kvmppc_interrupt_pr
 #endif
 	/* We're now back in the host but in guest MMU context */
@@ -779,7 +781,7 @@ kvmppc_interrupt_hv:
 	std	r6, VCPU_GPR(R6)(r9)
 	std	r7, VCPU_GPR(R7)(r9)
 	std	r8, VCPU_GPR(R8)(r9)
-	ld	r0, HSTATE_HOST_R2(r13)
+	ld	r0, HSTATE_SCRATCH2(r13)
 	std	r0, VCPU_GPR(R9)(r9)
 	std	r10, VCPU_GPR(R10)(r9)
 	std	r11, VCPU_GPR(R11)(r9)
@@ -990,14 +992,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 */
 	/* Increment the threads-exiting-guest count in the 0xff00
 	   bits of vcore->entry_exit_count */
-	lwsync
 	ld	r5,HSTATE_KVM_VCORE(r13)
 	addi	r6,r5,VCORE_ENTRY_EXIT
 41:	lwarx	r3,0,r6
 	addi	r0,r3,0x100
 	stwcx.	r0,0,r6
 	bne	41b
-	lwsync
+	isync		/* order stwcx. vs. reading napping_threads */
 
 	/*
 	 * At this point we have an interrupt that we have to pass
@@ -1030,6 +1031,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	sld	r0,r0,r4
 	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
 	beq	43f
+	/* Order entry/exit update vs. IPIs */
+	sync
 	mulli	r4,r4,PACA_SIZE		/* get paca for thread 0 */
 	subf	r6,r4,r13
 42:	andi.	r0,r3,1
@@ -1638,10 +1641,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	bge	kvm_cede_exit
 	stwcx.	r4,0,r6
 	bne	31b
+	/* order napping_threads update vs testing entry_exit_count */
+	isync
 	li	r0,1
 	stb	r0,HSTATE_NAPPING(r13)
-	/* order napping_threads update vs testing entry_exit_count */
-	lwsync
 	mr	r4,r3
 	lwz	r7,VCORE_ENTRY_EXIT(r5)
 	cmpwi	r7,0x100
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index f4dd041c14ea..f779450cb07c 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -129,29 +129,32 @@ kvm_start_lightweight:
 	 * R12      = exit handler id
 	 * R13      = PACA
 	 * SVCPU.*  = guest *
+	 * MSR.EE   = 1
 	 *
 	 */
 
+	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+
+	/*
+	 * kvmppc_copy_from_svcpu can clobber volatile registers, save
+	 * the exit handler id to the vcpu and restore it from there later.
+	 */
+	stw	r12, VCPU_TRAP(r3)
+
 	/* Transfer reg values from shadow vcpu back to vcpu struct */
 	/* On 64-bit, interrupts are still off at this point */
-	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+
 	GET_SHADOW_VCPU(r4)
 	bl	FUNC(kvmppc_copy_from_svcpu)
 	nop
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	/* Re-enable interrupts */
-	ld	r3, HSTATE_HOST_MSR(r13)
-	ori	r3, r3, MSR_EE
-	MTMSR_EERI(r3)
-
 	/*
 	 * Reload kernel SPRG3 value.
 	 * No need to save guest value as usermode can't modify SPRG3.
 	 */
 	ld	r3, PACA_SPRG3(r13)
 	mtspr	SPRN_SPRG3, r3
-
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	/* R7 = vcpu */
@@ -177,7 +180,7 @@ kvm_start_lightweight:
 	PPC_STL	r31, VCPU_GPR(R31)(r7)
 
 	/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
-	mr	r5, r12
+	lwz	r5, VCPU_TRAP(r7)
 
 	/* Restore r3 (kvm_run) and r4 (vcpu) */
 	REST_2GPRS(3, r1)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index fe14ca3dd171..5b9e9063cfaf 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -66,6 +66,7 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 	memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
 	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+	svcpu->in_use = 0;
 	svcpu_put(svcpu);
 #endif
 	vcpu->cpu = smp_processor_id();
@@ -78,6 +79,9 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	if (svcpu->in_use) {
+		kvmppc_copy_from_svcpu(vcpu, svcpu);
+	}
 	memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
 	to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
 	svcpu_put(svcpu);
@@ -110,12 +114,26 @@ void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
 	svcpu->ctr = vcpu->arch.ctr;
 	svcpu->lr  = vcpu->arch.lr;
 	svcpu->pc  = vcpu->arch.pc;
+	svcpu->in_use = true;
 }
 
 /* Copy data touched by real-mode code from shadow vcpu back to vcpu */
 void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 			    struct kvmppc_book3s_shadow_vcpu *svcpu)
 {
+	/*
+	 * vcpu_put would just call us again because in_use hasn't
+	 * been updated yet.
+	 */
+	preempt_disable();
+
+	/*
+	 * Maybe we were already preempted and synced the svcpu from
+	 * our preempt notifiers. Don't bother touching this svcpu then.
+	 */
+	if (!svcpu->in_use)
+		goto out;
+
 	vcpu->arch.gpr[0] = svcpu->gpr[0];
 	vcpu->arch.gpr[1] = svcpu->gpr[1];
 	vcpu->arch.gpr[2] = svcpu->gpr[2];
@@ -139,6 +157,10 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 	vcpu->arch.fault_dar   = svcpu->fault_dar;
 	vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
 	vcpu->arch.last_inst   = svcpu->last_inst;
+	svcpu->in_use = false;
+
+out:
+	preempt_enable();
 }
 
 static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index a38c4c9edab8..c3c5231adade 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -153,15 +153,11 @@ _GLOBAL(kvmppc_entry_trampoline)
 
 	li	r6, MSR_IR | MSR_DR
 	andc	r6, r5, r6	/* Clear DR and IR in MSR value */
-#ifdef CONFIG_PPC_BOOK3S_32
 	/*
 	 * Set EE in HOST_MSR so that it's enabled when we get into our
-	 * C exit handler function.  On 64-bit we delay enabling
-	 * interrupts until we have finished transferring stuff
-	 * to or from the PACA.
+	 * C exit handler function.
 	 */
 	ori	r5, r5, MSR_EE
-#endif
 	mtsrr0	r7
 	mtsrr1	r6
 	RFI
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 53e65a210b9a..0591e05db74b 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -681,7 +681,7 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret, s;
-	struct thread_struct thread;
+	struct debug_reg debug;
 #ifdef CONFIG_PPC_FPU
 	struct thread_fp_state fp;
 	int fpexc_mode;
@@ -723,9 +723,9 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
 
 	/* Switch to guest debug context */
-	thread.debug = vcpu->arch.shadow_dbg_reg;
-	switch_booke_debug_regs(&thread);
-	thread.debug = current->thread.debug;
+	debug = vcpu->arch.shadow_dbg_reg;
+	switch_booke_debug_regs(&debug);
+	debug = current->thread.debug;
 	current->thread.debug = vcpu->arch.shadow_dbg_reg;
 
 	kvmppc_fix_ee_before_entry();
@@ -736,8 +736,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	   We also get here with interrupts enabled. */
 
 	/* Switch back to user space debug context */
-	switch_booke_debug_regs(&thread);
-	current->thread.debug = thread.debug;
+	switch_booke_debug_regs(&debug);
+	current->thread.debug = debug;
 
 #ifdef CONFIG_PPC_FPU
 	kvmppc_save_guest_fp(vcpu);
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index d73a59014900..596a285c0755 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -9,6 +9,14 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 
+#ifdef __BIG_ENDIAN__
+#define sLd sld		/* Shift towards low-numbered address. */
+#define sHd srd		/* Shift towards high-numbered address. */
+#else
+#define sLd srd		/* Shift towards low-numbered address. */
+#define sHd sld		/* Shift towards high-numbered address. */
+#endif
+
 	.align	7
 _GLOBAL(__copy_tofrom_user)
 BEGIN_FTR_SECTION
@@ -118,10 +126,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 
 24:	ld	r9,0(r4)	/* 3+2n loads, 2+2n stores */
 25:	ld	r0,8(r4)
-	sld	r6,r9,r10
+	sLd	r6,r9,r10
 26:	ldu	r9,16(r4)
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	or	r7,r7,r6
 	blt	cr6,79f
 27:	ld	r0,8(r4)
@@ -129,35 +137,35 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 
 28:	ld	r0,0(r4)	/* 4+2n loads, 3+2n stores */
 29:	ldu	r9,8(r4)
-	sld	r8,r0,r10
+	sLd	r8,r0,r10
 	addi	r3,r3,-8
 	blt	cr6,5f
 30:	ld	r0,8(r4)
-	srd	r12,r9,r11
-	sld	r6,r9,r10
+	sHd	r12,r9,r11
+	sLd	r6,r9,r10
 31:	ldu	r9,16(r4)
 	or	r12,r8,r12
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	addi	r3,r3,16
 	beq	cr6,78f
 
 1:	or	r7,r7,r6
 32:	ld	r0,8(r4)
 76:	std	r12,8(r3)
-2:	srd	r12,r9,r11
-	sld	r6,r9,r10
+2:	sHd	r12,r9,r11
+	sLd	r6,r9,r10
 33:	ldu	r9,16(r4)
 	or	r12,r8,r12
 77:	stdu	r7,16(r3)
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	bdnz	1b
 
 78:	std	r12,8(r3)
 	or	r7,r7,r6
 79:	std	r7,16(r3)
-5:	srd	r12,r9,r11
+5:	sHd	r12,r9,r11
 	or	r12,r8,r12
 80:	std	r12,24(r3)
 	bne	6f
@@ -165,23 +173,38 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	blr
 6:	cmpwi	cr1,r5,8
 	addi	r3,r3,32
-	sld	r9,r9,r10
+	sLd	r9,r9,r10
 	ble	cr1,7f
 34:	ld	r0,8(r4)
-	srd	r7,r0,r11
+	sHd	r7,r0,r11
 	or	r9,r7,r9
 7:
 	bf	cr7*4+1,1f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,32
+#endif
 94:	stw	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,32
+#endif
 	addi	r3,r3,4
 1:	bf	cr7*4+2,2f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,16
+#endif
 95:	sth	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,16
+#endif
 	addi	r3,r3,2
 2:	bf	cr7*4+3,3f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,8
+#endif
 96:	stb	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,8
+#endif
 3:	li	r3,0
 	blr
 
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 02245cee7818..d7ddcee7feb8 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -36,7 +36,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static char *hub_diag = NULL;
 static int ioda_eeh_nb_init = 0;
 
 static int ioda_eeh_event(struct notifier_block *nb,
@@ -140,15 +139,6 @@ static int ioda_eeh_post_init(struct pci_controller *hose)
 		ioda_eeh_nb_init = 1;
 	}
 
-	/* We needn't HUB diag-data on PHB3 */
-	if (phb->type == PNV_PHB_IODA1 && !hub_diag) {
-		hub_diag = (char *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-		if (!hub_diag) {
-			pr_err("%s: Out of memory !\n", __func__);
-			return -ENOMEM;
-		}
-	}
-
 #ifdef CONFIG_DEBUG_FS
 	if (phb->dbgfs) {
 		debugfs_create_file("err_injct_outbound", 0600,
@@ -633,11 +623,10 @@ static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
 static void ioda_eeh_hub_diag(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
-	struct OpalIoP7IOCErrorData *data;
+	struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag;
 	long rc;
 
-	data = (struct OpalIoP7IOCErrorData *)ioda_eeh_hub_diag;
-	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, PAGE_SIZE);
+	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data));
 	if (rc != OPAL_SUCCESS) {
 		pr_warning("%s: Failed to get HUB#%llx diag-data (%ld)\n",
 			   __func__, phb->hub_id, rc);
@@ -820,14 +809,15 @@ static void ioda_eeh_phb_diag(struct pci_controller *hose)
 	struct OpalIoPhbErrorCommon *common;
 	long rc;
 
-	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, common, PAGE_SIZE);
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
 	if (rc != OPAL_SUCCESS) {
 		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
 			    __func__, hose->global_number, rc);
 		return;
 	}
 
+	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
 	switch (common->ioType) {
 	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
 		ioda_eeh_p7ioc_phb_diag(hose, common);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 911c24ef033e..1ed8d5f40f5a 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -172,11 +172,13 @@ struct pnv_phb {
 		} ioda;
 	};
 
-	/* PHB status structure */
+	/* PHB and hub status structure */
 	union {
 		unsigned char			blob[PNV_PCI_DIAG_BUF_SIZE];
 		struct OpalIoP7IOCPhbErrorData	p7ioc;
+		struct OpalIoP7IOCErrorData 	hub_diag;
 	} diag;
+
 };
 
 extern struct pci_ops pnv_pci_ops;
diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile
index 7b95f29e3174..3baff31e58cf 100644
--- a/arch/sh/lib/Makefile
+++ b/arch/sh/lib/Makefile
@@ -6,7 +6,7 @@ lib-y  = delay.o memmove.o memchr.o \
 	 checksum.o strlen.o div64.o div64-generic.o
 
 # Extracted from libgcc
-lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
 	 ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
 	 udiv_qrnnd.o
 
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 8358dc144959..0f9e94537eee 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -619,7 +619,7 @@ static inline unsigned long pte_present(pte_t pte)
 }
 
 #define pte_accessible pte_accessible
-static inline unsigned long pte_accessible(pte_t a)
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
 {
 	return pte_val(a) & _PAGE_VALID;
 }
@@ -847,7 +847,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
 	 *             and SUN4V pte layout, so this inline test is fine.
 	 */
-	if (likely(mm != &init_mm) && pte_accessible(orig))
+	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
 		tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3d1999458709..bbc8b12fa443 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -452,9 +452,16 @@ static inline int pte_present(pte_t a)
 }
 
 #define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
-	return pte_flags(a) & _PAGE_PRESENT;
+	if (pte_flags(a) & _PAGE_PRESENT)
+		return true;
+
+	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+			mm_tlb_flush_pending(mm))
+		return true;
+
+	return false;
 }
 
 static inline int pte_hidden(pte_t pte)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index dc1ec0dff939..ea04b342c026 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -387,7 +387,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_PEBS);
 	}
 
-	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
+	if (c->x86 == 6 && cpu_has_clflush &&
+	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
 		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dd74e46828c0..0596e8e0cc19 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -83,6 +83,12 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
+		/* Similar to the PMD case, NUMA hinting must take slow path */
+		if (pte_numa(pte)) {
+			pte_unmap(ptep);
+			return 0;
+		}
+
 		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
@@ -167,6 +173,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_numa(pmd))
+				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;
 		} else {