Merge tag 'kvm-s390-master-4.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux

KVM: s390: Fixes for 4.19

- Fallout from the hugetlbfs support: pfmf interpretion and locking
- VSIE: fix keywrapping for nested guests

46 files changed, 464 insertions, 309 deletions

diff --git a/arch/arm/boot/dts/am335x-osd3358-sm-red.dts b/arch/arm/boot/dts/am335x-osd3358-sm-red.dts
index 4d969013f99a..4d969013f99a 100755..100644
--- a/arch/arm/boot/dts/am335x-osd3358-sm-red.dts
+++ b/arch/arm/boot/dts/am335x-osd3358-sm-red.dts
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index f0cbd86312dc..d4b7c59eec68 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -469,6 +469,7 @@
 			ti,hwmods = "rtc";
 			clocks = <&clk_32768_ck>;
 			clock-names = "int-clk";
+			system-power-controller;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/imx23-evk.dts b/arch/arm/boot/dts/imx23-evk.dts
index 9fb47724b9c1..ad2ae25b7b4d 100644
--- a/arch/arm/boot/dts/imx23-evk.dts
+++ b/arch/arm/boot/dts/imx23-evk.dts
@@ -13,6 +13,43 @@
 		reg = <0x40000000 0x08000000>;
 	};
 
+	reg_vddio_sd0: regulator-vddio-sd0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vddio-sd0";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio1 29 0>;
+	};
+
+	reg_lcd_3v3: regulator-lcd-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio1 18 0>;
+		enable-active-high;
+	};
+
+	reg_lcd_5v: regulator-lcd-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	panel {
+		compatible = "sii,43wvf1g";
+		backlight = <&backlight_display>;
+		dvdd-supply = <&reg_lcd_3v3>;
+		avdd-supply = <&reg_lcd_5v>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&display_out>;
+			};
+		};
+	};
+
 	apb@80000000 {
 		apbh@80000000 {
 			gpmi-nand@8000c000 {
@@ -52,31 +89,11 @@
 			lcdif@80030000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&lcdif_24bit_pins_a>;
-				lcd-supply = <&reg_lcd_3v3>;
-				display = <&display0>;
 				status = "okay";
 
-				display0: display0 {
-					bits-per-pixel = <32>;
-					bus-width = <24>;
-
-					display-timings {
-						native-mode = <&timing0>;
-						timing0: timing0 {
-							clock-frequency = <9200000>;
-							hactive = <480>;
-							vactive = <272>;
-							hback-porch = <15>;
-							hfront-porch = <8>;
-							vback-porch = <12>;
-							vfront-porch = <4>;
-							hsync-len = <1>;
-							vsync-len = <1>;
-							hsync-active = <0>;
-							vsync-active = <0>;
-							de-active = <1>;
-							pixelclk-active = <0>;
-						};
+				port {
+					display_out: endpoint {
+						remote-endpoint = <&panel_in>;
 					};
 				};
 			};
@@ -118,32 +135,7 @@
 		};
 	};
 
-	regulators {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		reg_vddio_sd0: regulator@0 {
-			compatible = "regulator-fixed";
-			reg = <0>;
-			regulator-name = "vddio-sd0";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpio = <&gpio1 29 0>;
-		};
-
-		reg_lcd_3v3: regulator@1 {
-			compatible = "regulator-fixed";
-			reg = <1>;
-			regulator-name = "lcd-3v3";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpio = <&gpio1 18 0>;
-			enable-active-high;
-		};
-	};
-
-	backlight {
+	backlight_display: backlight {
 		compatible = "pwm-backlight";
 		pwms = <&pwm 2 5000000>;
 		brightness-levels = <0 4 8 16 32 64 128 255>;
diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts
index 6b0ae667640f..93ab5bdfe068 100644
--- a/arch/arm/boot/dts/imx28-evk.dts
+++ b/arch/arm/boot/dts/imx28-evk.dts
@@ -13,6 +13,87 @@
 		reg = <0x40000000 0x08000000>;
 	};
 
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3P3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	reg_vddio_sd0: regulator-vddio-sd0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vddio-sd0";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio3 28 0>;
+	};
+
+	reg_fec_3v3: regulator-fec-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "fec-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio2 15 0>;
+	};
+
+	reg_usb0_vbus: regulator-usb0-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb0_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio3 9 0>;
+		enable-active-high;
+	};
+
+	reg_usb1_vbus: regulator-usb1-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb1_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio3 8 0>;
+		enable-active-high;
+	};
+
+	reg_lcd_3v3: regulator-lcd-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio3 30 0>;
+		enable-active-high;
+	};
+
+	reg_can_3v3: regulator-can-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "can-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio2 13 0>;
+		enable-active-high;
+	};
+
+	reg_lcd_5v: regulator-lcd-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	panel {
+		compatible = "sii,43wvf1g";
+		backlight = <&backlight_display>;
+		dvdd-supply = <&reg_lcd_3v3>;
+		avdd-supply = <&reg_lcd_5v>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&display_out>;
+			};
+		};
+	};
+
 	apb@80000000 {
 		apbh@80000000 {
 			gpmi-nand@8000c000 {
@@ -116,31 +197,11 @@
 				pinctrl-names = "default";
 				pinctrl-0 = <&lcdif_24bit_pins_a
 					     &lcdif_pins_evk>;
-				lcd-supply = <&reg_lcd_3v3>;
-				display = <&display0>;
 				status = "okay";
 
-				display0: display0 {
-					bits-per-pixel = <32>;
-					bus-width = <24>;
-
-					display-timings {
-						native-mode = <&timing0>;
-						timing0: timing0 {
-							clock-frequency = <33500000>;
-							hactive = <800>;
-							vactive = <480>;
-							hback-porch = <89>;
-							hfront-porch = <164>;
-							vback-porch = <23>;
-							vfront-porch = <10>;
-							hsync-len = <10>;
-							vsync-len = <10>;
-							hsync-active = <0>;
-							vsync-active = <0>;
-							de-active = <1>;
-							pixelclk-active = <0>;
-						};
+				port {
+					display_out: endpoint {
+						remote-endpoint = <&panel_in>;
 					};
 				};
 			};
@@ -269,80 +330,6 @@
 		};
 	};
 
-	regulators {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		reg_3p3v: regulator@0 {
-			compatible = "regulator-fixed";
-			reg = <0>;
-			regulator-name = "3P3V";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			regulator-always-on;
-		};
-
-		reg_vddio_sd0: regulator@1 {
-			compatible = "regulator-fixed";
-			reg = <1>;
-			regulator-name = "vddio-sd0";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpio = <&gpio3 28 0>;
-		};
-
-		reg_fec_3v3: regulator@2 {
-			compatible = "regulator-fixed";
-			reg = <2>;
-			regulator-name = "fec-3v3";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpio = <&gpio2 15 0>;
-		};
-
-		reg_usb0_vbus: regulator@3 {
-			compatible = "regulator-fixed";
-			reg = <3>;
-			regulator-name = "usb0_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			gpio = <&gpio3 9 0>;
-			enable-active-high;
-		};
-
-		reg_usb1_vbus: regulator@4 {
-			compatible = "regulator-fixed";
-			reg = <4>;
-			regulator-name = "usb1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			gpio = <&gpio3 8 0>;
-			enable-active-high;
-		};
-
-		reg_lcd_3v3: regulator@5 {
-			compatible = "regulator-fixed";
-			reg = <5>;
-			regulator-name = "lcd-3v3";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpio = <&gpio3 30 0>;
-			enable-active-high;
-		};
-
-		reg_can_3v3: regulator@6 {
-			compatible = "regulator-fixed";
-			reg = <6>;
-			regulator-name = "can-3v3";
-			regulator-min-microvolt = <3300000>;
-			regulator-max-microvolt = <3300000>;
-			gpio = <&gpio2 13 0>;
-			enable-active-high;
-		};
-
-	};
-
 	sound {
 		compatible = "fsl,imx28-evk-sgtl5000",
 			     "fsl,mxs-audio-sgtl5000";
@@ -363,7 +350,7 @@
 		};
 	};
 
-	backlight {
+	backlight_display: backlight {
 		compatible = "pwm-backlight";
 		pwms = <&pwm 2 5000000>;
 		brightness-levels = <0 4 8 16 32 64 128 255>;
diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi
index 7cbc2ffa4b3a..7234e8330a57 100644
--- a/arch/arm/boot/dts/imx7d.dtsi
+++ b/arch/arm/boot/dts/imx7d.dtsi
@@ -126,10 +126,14 @@
 		interrupt-names = "msi";
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0x7>;
-		interrupt-map = <0 0 0 1 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 2 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 3 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 4 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>;
+		/*
+		 * Reference manual lists pci irqs incorrectly
+		 * Real hardware ordering is same as imx6: D+MSI, C, B, A
+		 */
+		interrupt-map = <0 0 0 1 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 2 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 3 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 4 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&clks IMX7D_PCIE_CTRL_ROOT_CLK>,
 			 <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>,
 			 <&clks IMX7D_PCIE_PHY_ROOT_CLK>;
diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts
index 12d6822f0057..04758a2a87f0 100644
--- a/arch/arm/boot/dts/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts
@@ -354,7 +354,7 @@
 &mmc2 {
 	vmmc-supply = <&vsdio>;
 	bus-width = <8>;
-	non-removable;
+	ti,non-removable;
 };
 
 &mmc3 {
@@ -621,15 +621,6 @@
 		OMAP4_IOPAD(0x10c, PIN_INPUT | MUX_MODE1)	/* abe_mcbsp3_fsx */
 		>;
 	};
-};
-
-&omap4_pmx_wkup {
-	usb_gpio_mux_sel2: pinmux_usb_gpio_mux_sel2_pins {
-		/* gpio_wk0 */
-		pinctrl-single,pins = <
-		OMAP4_IOPAD(0x040, PIN_OUTPUT_PULLDOWN | MUX_MODE3)
-		>;
-	};
 
 	vibrator_direction_pin: pinmux_vibrator_direction_pin {
 		pinctrl-single,pins = <
@@ -644,6 +635,15 @@
 	};
 };
 
+&omap4_pmx_wkup {
+	usb_gpio_mux_sel2: pinmux_usb_gpio_mux_sel2_pins {
+		/* gpio_wk0 */
+		pinctrl-single,pins = <
+		OMAP4_IOPAD(0x040, PIN_OUTPUT_PULLDOWN | MUX_MODE3)
+		>;
+	};
+};
+
 /*
  * As uart1 is wired to mdm6600 with rts and cts, we can use the cts pin for
  * uart1 wakeirq.
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index e2c127608bcc..7eca43ff69bb 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -257,6 +257,7 @@ CONFIG_IMX_IPUV3_CORE=y
 CONFIG_DRM=y
 CONFIG_DRM_PANEL_LVDS=y
 CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_PANEL_SEIKO_43WVF1G=y
 CONFIG_DRM_DW_HDMI_AHB_AUDIO=m
 CONFIG_DRM_DW_HDMI_CEC=y
 CONFIG_DRM_IMX=y
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index 148226e36152..7b8212857535 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -95,6 +95,7 @@ CONFIG_MFD_MXS_LRADC=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_DRM=y
+CONFIG_DRM_PANEL_SEIKO_43WVF1G=y
 CONFIG_DRM_MXSFB=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
diff --git a/arch/arm/configs/versatile_defconfig b/arch/arm/configs/versatile_defconfig
index df68dc4056e5..5282324c7cef 100644
--- a/arch/arm/configs/versatile_defconfig
+++ b/arch/arm/configs/versatile_defconfig
@@ -5,19 +5,19 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_VERSATILE=y
 CONFIG_AEABI=y
 CONFIG_OABI_COMPAT=y
-CONFIG_CMA=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="root=1f03 mem=32M"
 CONFIG_FPE_NWFPE=y
 CONFIG_VFP=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_CMA=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -59,6 +59,7 @@ CONFIG_GPIO_PL061=y
 CONFIG_DRM=y
 CONFIG_DRM_PANEL_ARM_VERSATILE=y
 CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_DUMB_VGA_DAC=y
 CONFIG_DRM_PL111=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
@@ -89,9 +90,10 @@ CONFIG_NFSD=y
 CONFIG_NFSD_V3=y
 CONFIG_NLS_CODEPAGE_850=m
 CONFIG_NLS_ISO8859_1=m
+CONFIG_FONTS=y
+CONFIG_FONT_ACORN_8x8=y
+CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_USER=y
 CONFIG_DEBUG_LL=y
-CONFIG_FONTS=y
-CONFIG_FONT_ACORN_8x8=y
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 2ceffd85dd3d..cd65ea4e9c54 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2161,6 +2161,37 @@ static int of_dev_hwmod_lookup(struct device_node *np,
 }
 
 /**
+ * omap_hwmod_fix_mpu_rt_idx - fix up mpu_rt_idx register offsets
+ *
+ * @oh: struct omap_hwmod *
+ * @np: struct device_node *
+ *
+ * Fix up module register offsets for modules with mpu_rt_idx.
+ * Only needed for cpsw with interconnect target module defined
+ * in device tree while still using legacy hwmod platform data
+ * for rev, sysc and syss registers.
+ *
+ * Can be removed when all cpsw hwmod platform data has been
+ * dropped.
+ */
+static void omap_hwmod_fix_mpu_rt_idx(struct omap_hwmod *oh,
+				      struct device_node *np,
+				      struct resource *res)
+{
+	struct device_node *child = NULL;
+	int error;
+
+	child = of_get_next_child(np, child);
+	if (!child)
+		return;
+
+	error = of_address_to_resource(child, oh->mpu_rt_idx, res);
+	if (error)
+		pr_err("%s: error mapping mpu_rt_idx: %i\n",
+		       __func__, error);
+}
+
+/**
  * omap_hwmod_parse_module_range - map module IO range from device tree
  * @oh: struct omap_hwmod *
  * @np: struct device_node *
@@ -2220,7 +2251,13 @@ int omap_hwmod_parse_module_range(struct omap_hwmod *oh,
 	size = be32_to_cpup(ranges);
 
 	pr_debug("omap_hwmod: %s %s at 0x%llx size 0x%llx\n",
-		 oh->name, np->name, base, size);
+		 oh ? oh->name : "", np->name, base, size);
+
+	if (oh && oh->mpu_rt_idx) {
+		omap_hwmod_fix_mpu_rt_idx(oh, np, res);
+
+		return 0;
+	}
 
 	res->start = base;
 	res->end = base + size - 1;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 29e75b47becd..1b1a0e95c751 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -763,7 +763,6 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
 
 config HOLES_IN_ZONE
 	def_bool y
-	depends on NUMA
 
 source kernel/Kconfig.hz
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index f67e8d5e93ad..db8d364f8476 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -38,6 +38,7 @@ CONFIG_ARCH_BCM_IPROC=y
 CONFIG_ARCH_BERLIN=y
 CONFIG_ARCH_BRCMSTB=y
 CONFIG_ARCH_EXYNOS=y
+CONFIG_ARCH_K3=y
 CONFIG_ARCH_LAYERSCAPE=y
 CONFIG_ARCH_LG1K=y
 CONFIG_ARCH_HISI=y
@@ -605,6 +606,8 @@ CONFIG_ARCH_TEGRA_132_SOC=y
 CONFIG_ARCH_TEGRA_210_SOC=y
 CONFIG_ARCH_TEGRA_186_SOC=y
 CONFIG_ARCH_TEGRA_194_SOC=y
+CONFIG_ARCH_K3_AM6_SOC=y
+CONFIG_SOC_TI=y
 CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_EXTCON_USBC_CROS_EC=y
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 6e9f33d14930..067d8937d5af 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -417,7 +417,7 @@ static int gcm_encrypt(struct aead_request *req)
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
-		while (walk.nbytes >= AES_BLOCK_SIZE) {
+		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
@@ -437,11 +437,18 @@ static int gcm_encrypt(struct aead_request *req)
 					NULL);
 
 			err = skcipher_walk_done(&walk,
-						 walk.nbytes % AES_BLOCK_SIZE);
+						 walk.nbytes % (2 * AES_BLOCK_SIZE));
 		}
-		if (walk.nbytes)
+		if (walk.nbytes) {
 			__aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv,
 					    nrounds);
+			if (walk.nbytes > AES_BLOCK_SIZE) {
+				crypto_inc(iv, AES_BLOCK_SIZE);
+				__aes_arm64_encrypt(ctx->aes_key.key_enc,
+					            ks + AES_BLOCK_SIZE, iv,
+						    nrounds);
+			}
+		}
 	}
 
 	/* handle the tail */
@@ -545,7 +552,7 @@ static int gcm_decrypt(struct aead_request *req)
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
-		while (walk.nbytes >= AES_BLOCK_SIZE) {
+		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
@@ -564,11 +571,21 @@ static int gcm_decrypt(struct aead_request *req)
 			} while (--blocks > 0);
 
 			err = skcipher_walk_done(&walk,
-						 walk.nbytes % AES_BLOCK_SIZE);
+						 walk.nbytes % (2 * AES_BLOCK_SIZE));
 		}
-		if (walk.nbytes)
+		if (walk.nbytes) {
+			if (walk.nbytes > AES_BLOCK_SIZE) {
+				u8 *iv2 = iv + AES_BLOCK_SIZE;
+
+				memcpy(iv2, iv, AES_BLOCK_SIZE);
+				crypto_inc(iv2, AES_BLOCK_SIZE);
+
+				__aes_arm64_encrypt(ctx->aes_key.key_enc, iv2,
+						    iv2, nrounds);
+			}
 			__aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv,
 					    nrounds);
+		}
 	}
 
 	/* handle the tail */
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
index b7fb5274b250..0c4fc223f225 100644
--- a/arch/arm64/crypto/sm4-ce-glue.c
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -69,5 +69,5 @@ static void __exit sm4_ce_mod_fini(void)
 	crypto_unregister_alg(&sm4_ce_alg);
 }
 
-module_cpu_feature_match(SM3, sm4_ce_mod_init);
+module_cpu_feature_match(SM4, sm4_ce_mod_init);
 module_exit(sm4_ce_mod_fini);
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index 3534aa6a4dc2..1b083c500b9a 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -98,11 +98,10 @@ static time64_t pmu_read_time(void)
 
 	if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
 		return 0;
-	while (!req.complete)
-		pmu_poll();
+	pmu_wait_complete(&req);
 
-	time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) |
-		     (req.reply[3] << 8) | req.reply[4]);
+	time = (u32)((req.reply[0] << 24) | (req.reply[1] << 16) |
+		     (req.reply[2] << 8) | req.reply[3]);
 
 	return time - RTC_OFFSET;
 }
@@ -116,8 +115,7 @@ static void pmu_write_time(time64_t time)
 			(data >> 24) & 0xFF, (data >> 16) & 0xFF,
 			(data >> 8) & 0xFF, data & 0xFF) < 0)
 		return;
-	while (!req.complete)
-		pmu_poll();
+	pmu_wait_complete(&req);
 }
 
 static __u8 pmu_read_pram(int offset)
diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug
index 7a49f0d28d14..f1da8a7b17ff 100644
--- a/arch/nios2/Kconfig.debug
+++ b/arch/nios2/Kconfig.debug
@@ -3,15 +3,6 @@
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config DEBUG_STACK_USAGE
-	bool "Enable stack utilization instrumentation"
-	depends on DEBUG_KERNEL
-	help
-	  Enables the display of the minimum amount of free stack which each
-	  task has ever had available in the sysrq-T and sysrq-P debug output.
-
-	  This option will slow down process creation somewhat.
-
 config EARLY_PRINTK
 	bool "Activate early kernel debugging"
 	default y
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index db0b6eebbfa5..a80669209155 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -177,7 +177,6 @@ config PPC
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if COMPAT
-	select HAVE_ARCH_PREL32_RELOCATIONS
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_CBPF_JIT			if !PPC64
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index c229509288ea..439dc7072e05 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -14,6 +14,10 @@
 #ifndef _ASM_RISCV_TLB_H
 #define _ASM_RISCV_TLB_H
 
+struct mmu_gather;
+
+static void tlb_flush(struct mmu_gather *tlb);
+
 #include <asm-generic/tlb.h>
 
 static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 568026ccf6e8..fb03a4482ad6 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -65,24 +65,11 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
 	uintptr_t, flags)
 {
-#ifdef CONFIG_SMP
-	struct mm_struct *mm = current->mm;
-	bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0;
-#endif
-
 	/* Check the reserved flags. */
 	if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL))
 		return -EINVAL;
 
-	/*
-	 * Without CONFIG_SMP flush_icache_mm is a just a flush_icache_all(),
-	 * which generates unused variable warnings all over this function.
-	 */
-#ifdef CONFIG_SMP
-	flush_icache_mm(mm, local);
-#else
-	flush_icache_all();
-#endif
+	flush_icache_mm(current->mm, flags & SYS_RISCV_FLUSH_ICACHE_LOCAL);
 
 	return 0;
 }
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index f31a15044c24..a8418e1379eb 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -16,7 +16,13 @@ typedef struct {
 	unsigned long asce;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
-	/* The mmu context allocates 4K page tables. */
+	/*
+	 * The following bitfields need a down_write on the mm
+	 * semaphore when they are written to. As they are only
+	 * written once, they can be read without a lock.
+	 *
+	 * The mmu context allocates 4K page tables.
+	 */
 	unsigned int alloc_pgste:1;
 	/* The mmu context uses extended page tables. */
 	unsigned int has_pgste:1;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 91ad4a9425c0..f69333fd2fa3 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -695,7 +695,9 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 			r = -EINVAL;
 		else {
 			r = 0;
+			down_write(&kvm->mm->mmap_sem);
 			kvm->mm->context.allow_gmap_hpage_1m = 1;
+			up_write(&kvm->mm->mmap_sem);
 			/*
 			 * We might have to create fake 4k page
 			 * tables. To avoid that the hardware works on
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d68f10441a16..8679bd74d337 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -280,9 +280,11 @@ retry:
 			goto retry;
 		}
 	}
-	if (rc)
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 	up_read(&current->mm->mmap_sem);
+	if (rc == -EFAULT)
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	if (rc < 0)
+		return rc;
 	vcpu->run->s.regs.gprs[reg1] &= ~0xff;
 	vcpu->run->s.regs.gprs[reg1] |= key;
 	return 0;
@@ -324,9 +326,11 @@ retry:
 			goto retry;
 		}
 	}
-	if (rc < 0)
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 	up_read(&current->mm->mmap_sem);
+	if (rc == -EFAULT)
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	if (rc < 0)
+		return rc;
 	kvm_s390_set_psw_cc(vcpu, rc);
 	return 0;
 }
@@ -390,12 +394,12 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 					      FAULT_FLAG_WRITE, &unlocked);
 			rc = !rc ? -EAGAIN : rc;
 		}
+		up_read(&current->mm->mmap_sem);
 		if (rc == -EFAULT)
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
-		up_read(&current->mm->mmap_sem);
-		if (rc >= 0)
-			start += PAGE_SIZE;
+		if (rc < 0)
+			return rc;
+		start += PAGE_SIZE;
 	}
 
 	if (m3 & (SSKE_MC | SSKE_MR)) {
@@ -1002,13 +1006,15 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 						      FAULT_FLAG_WRITE, &unlocked);
 				rc = !rc ? -EAGAIN : rc;
 			}
+			up_read(&current->mm->mmap_sem);
 			if (rc == -EFAULT)
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
-			up_read(&current->mm->mmap_sem);
-			if (rc >= 0)
-				start += PAGE_SIZE;
+			if (rc == -EAGAIN)
+				continue;
+			if (rc < 0)
+				return rc;
 		}
+		start += PAGE_SIZE;
 	}
 	if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
 		if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) {
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 63844b95c22c..a2b28cd1e3fe 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -173,7 +173,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		return set_validity_icpt(scb_s, 0x0039U);
 
 	/* copy only the wrapping keys */
-	if (read_guest_real(vcpu, crycb_addr + 72, &vsie_page->crycb, 56))
+	if (read_guest_real(vcpu, crycb_addr + 72,
+			    vsie_page->crycb.dea_wrapping_key_mask, 56))
 		return set_validity_icpt(scb_s, 0x0035U);
 
 	scb_s->ecb3 |= ecb3_flags;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c5ff296bc5d1..1a0be022f91d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2843,7 +2843,7 @@ config X86_SYSFB
 	  This option, if enabled, marks VGA/VBE/EFI framebuffers as generic
 	  framebuffers so the new generic system-framebuffer drivers can be
 	  used on x86. If the framebuffer is not compatible with the generic
-	  modes, it is adverticed as fallback platform framebuffer so legacy
+	  modes, it is advertised as fallback platform framebuffer so legacy
 	  drivers like efifb, vesafb and uvesafb can pick it up.
 	  If this option is not selected, all system framebuffers are always
 	  marked as fallback platform framebuffers as usual.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 94859241bc3e..8f6e7eb8ae9f 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -175,22 +175,6 @@ ifdef CONFIG_FUNCTION_GRAPH_TRACER
   endif
 endif
 
-ifndef CC_HAVE_ASM_GOTO
-  $(error Compiler lacks asm-goto support.)
-endif
-
-#
-# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a
-# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226).  There's no way
-# to test for this bug at compile-time because the test case needs to execute,
-# which is a no-go for cross compilers.  So check the GCC version instead.
-#
-ifdef CONFIG_JUMP_LABEL
-  ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1)
-	ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1)
-  endif
-endif
-
 ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
 	# This compiler flag is not supported by Clang:
 	KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,)
@@ -312,6 +296,13 @@ PHONY += vdso_install
 vdso_install:
 	$(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@
 
+archprepare: checkbin
+checkbin:
+ifndef CC_HAVE_ASM_GOTO
+	@echo Compiler lacks asm-goto support.
+	@exit 1
+endif
+
 archclean:
 	$(Q)rm -rf $(objtree)/arch/i386
 	$(Q)rm -rf $(objtree)/arch/x86_64
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 9bd139569b41..cb2deb61c5d9 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -223,34 +223,34 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	pcmpeqd TWOONE(%rip), \TMP2
 	pand	POLY(%rip), \TMP2
 	pxor	\TMP2, \TMP3
-	movdqa	\TMP3, HashKey(%arg2)
+	movdqu	\TMP3, HashKey(%arg2)
 
 	movdqa	   \TMP3, \TMP5
 	pshufd	   $78, \TMP3, \TMP1
 	pxor	   \TMP3, \TMP1
-	movdqa	   \TMP1, HashKey_k(%arg2)
+	movdqu	   \TMP1, HashKey_k(%arg2)
 
 	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
 # TMP5 = HashKey^2<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_2(%arg2)
+	movdqu	   \TMP5, HashKey_2(%arg2)
 # HashKey_2 = HashKey^2<<1 (mod poly)
 	pshufd	   $78, \TMP5, \TMP1
 	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_2_k(%arg2)
+	movdqu	   \TMP1, HashKey_2_k(%arg2)
 
 	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
 # TMP5 = HashKey^3<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_3(%arg2)
+	movdqu	   \TMP5, HashKey_3(%arg2)
 	pshufd	   $78, \TMP5, \TMP1
 	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_3_k(%arg2)
+	movdqu	   \TMP1, HashKey_3_k(%arg2)
 
 	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
 # TMP5 = HashKey^3<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_4(%arg2)
+	movdqu	   \TMP5, HashKey_4(%arg2)
 	pshufd	   $78, \TMP5, \TMP1
 	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_4_k(%arg2)
+	movdqu	   \TMP1, HashKey_4_k(%arg2)
 .endm
 
 # GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding.
@@ -271,7 +271,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
 
 	PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
-	movdqa HashKey(%arg2), %xmm13
+	movdqu HashKey(%arg2), %xmm13
 
 	CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \
 	%xmm4, %xmm5, %xmm6
@@ -997,7 +997,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pshufd	  $78, \XMM5, \TMP6
 	pxor	  \XMM5, \TMP6
 	paddd     ONE(%rip), \XMM0		# INCR CNT
-	movdqa	  HashKey_4(%arg2), \TMP5
+	movdqu	  HashKey_4(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
 	movdqa    \XMM0, \XMM1
 	paddd     ONE(%rip), \XMM0		# INCR CNT
@@ -1016,7 +1016,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pxor	  (%arg1), \XMM2
 	pxor	  (%arg1), \XMM3
 	pxor	  (%arg1), \XMM4
-	movdqa	  HashKey_4_k(%arg2), \TMP5
+	movdqu	  HashKey_4_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
 	movaps 0x10(%arg1), \TMP1
 	AESENC	  \TMP1, \XMM1              # Round 1
@@ -1031,7 +1031,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM6, \TMP1
 	pshufd	  $78, \XMM6, \TMP2
 	pxor	  \XMM6, \TMP2
-	movdqa	  HashKey_3(%arg2), \TMP5
+	movdqu	  HashKey_3(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
 	movaps 0x30(%arg1), \TMP3
 	AESENC    \TMP3, \XMM1              # Round 3
@@ -1044,7 +1044,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM2
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
-	movdqa	  HashKey_3_k(%arg2), \TMP5
+	movdqu	  HashKey_3_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x50(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1              # Round 5
@@ -1058,7 +1058,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM7, \TMP1
 	pshufd	  $78, \XMM7, \TMP2
 	pxor	  \XMM7, \TMP2
-	movdqa	  HashKey_2(%arg2), \TMP5
+	movdqu	  HashKey_2(%arg2), \TMP5
 
         # Multiply TMP5 * HashKey using karatsuba
 
@@ -1074,7 +1074,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM2
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
-	movdqa	  HashKey_2_k(%arg2), \TMP5
+	movdqu	  HashKey_2_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x80(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1             # Round 8
@@ -1092,7 +1092,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM8, \TMP1
 	pshufd	  $78, \XMM8, \TMP2
 	pxor	  \XMM8, \TMP2
-	movdqa	  HashKey(%arg2), \TMP5
+	movdqu	  HashKey(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
 	movaps 0x90(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1            # Round 9
@@ -1121,7 +1121,7 @@ aes_loop_par_enc_done\@:
 	AESENCLAST \TMP3, \XMM2
 	AESENCLAST \TMP3, \XMM3
 	AESENCLAST \TMP3, \XMM4
-	movdqa    HashKey_k(%arg2), \TMP5
+	movdqu    HashKey_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
 	movdqu	  (%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
@@ -1205,7 +1205,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pshufd	  $78, \XMM5, \TMP6
 	pxor	  \XMM5, \TMP6
 	paddd     ONE(%rip), \XMM0		# INCR CNT
-	movdqa	  HashKey_4(%arg2), \TMP5
+	movdqu	  HashKey_4(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
 	movdqa    \XMM0, \XMM1
 	paddd     ONE(%rip), \XMM0		# INCR CNT
@@ -1224,7 +1224,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pxor	  (%arg1), \XMM2
 	pxor	  (%arg1), \XMM3
 	pxor	  (%arg1), \XMM4
-	movdqa	  HashKey_4_k(%arg2), \TMP5
+	movdqu	  HashKey_4_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
 	movaps 0x10(%arg1), \TMP1
 	AESENC	  \TMP1, \XMM1              # Round 1
@@ -1239,7 +1239,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM6, \TMP1
 	pshufd	  $78, \XMM6, \TMP2
 	pxor	  \XMM6, \TMP2
-	movdqa	  HashKey_3(%arg2), \TMP5
+	movdqu	  HashKey_3(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
 	movaps 0x30(%arg1), \TMP3
 	AESENC    \TMP3, \XMM1              # Round 3
@@ -1252,7 +1252,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM2
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
-	movdqa	  HashKey_3_k(%arg2), \TMP5
+	movdqu	  HashKey_3_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x50(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1              # Round 5
@@ -1266,7 +1266,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM7, \TMP1
 	pshufd	  $78, \XMM7, \TMP2
 	pxor	  \XMM7, \TMP2
-	movdqa	  HashKey_2(%arg2), \TMP5
+	movdqu	  HashKey_2(%arg2), \TMP5
 
         # Multiply TMP5 * HashKey using karatsuba
 
@@ -1282,7 +1282,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM2
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
-	movdqa	  HashKey_2_k(%arg2), \TMP5
+	movdqu	  HashKey_2_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x80(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1             # Round 8
@@ -1300,7 +1300,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM8, \TMP1
 	pshufd	  $78, \XMM8, \TMP2
 	pxor	  \XMM8, \TMP2
-	movdqa	  HashKey(%arg2), \TMP5
+	movdqu	  HashKey(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
 	movaps 0x90(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1            # Round 9
@@ -1329,7 +1329,7 @@ aes_loop_par_dec_done\@:
 	AESENCLAST \TMP3, \XMM2
 	AESENCLAST \TMP3, \XMM3
 	AESENCLAST \TMP3, \XMM4
-	movdqa    HashKey_k(%arg2), \TMP5
+	movdqu    HashKey_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
 	movdqu	  (%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
@@ -1405,10 +1405,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	movdqa	  \XMM1, \TMP6
 	pshufd	  $78, \XMM1, \TMP2
 	pxor	  \XMM1, \TMP2
-	movdqa	  HashKey_4(%arg2), \TMP5
+	movdqu	  HashKey_4(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP6       # TMP6 = a1*b1
 	PCLMULQDQ 0x00, \TMP5, \XMM1       # XMM1 = a0*b0
-	movdqa	  HashKey_4_k(%arg2), \TMP4
+	movdqu	  HashKey_4_k(%arg2), \TMP4
 	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	movdqa	  \XMM1, \XMMDst
 	movdqa	  \TMP2, \XMM1              # result in TMP6, XMMDst, XMM1
@@ -1418,10 +1418,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	movdqa	  \XMM2, \TMP1
 	pshufd	  $78, \XMM2, \TMP2
 	pxor	  \XMM2, \TMP2
-	movdqa	  HashKey_3(%arg2), \TMP5
+	movdqu	  HashKey_3(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
 	PCLMULQDQ 0x00, \TMP5, \XMM2       # XMM2 = a0*b0
-	movdqa	  HashKey_3_k(%arg2), \TMP4
+	movdqu	  HashKey_3_k(%arg2), \TMP4
 	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM2, \XMMDst
@@ -1433,10 +1433,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	movdqa	  \XMM3, \TMP1
 	pshufd	  $78, \XMM3, \TMP2
 	pxor	  \XMM3, \TMP2
-	movdqa	  HashKey_2(%arg2), \TMP5
+	movdqu	  HashKey_2(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
 	PCLMULQDQ 0x00, \TMP5, \XMM3       # XMM3 = a0*b0
-	movdqa	  HashKey_2_k(%arg2), \TMP4
+	movdqu	  HashKey_2_k(%arg2), \TMP4
 	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM3, \XMMDst
@@ -1446,10 +1446,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	movdqa	  \XMM4, \TMP1
 	pshufd	  $78, \XMM4, \TMP2
 	pxor	  \XMM4, \TMP2
-	movdqa	  HashKey(%arg2), \TMP5
+	movdqu	  HashKey(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1	    # TMP1 = a1*b1
 	PCLMULQDQ 0x00, \TMP5, \XMM4       # XMM4 = a0*b0
-	movdqa	  HashKey_k(%arg2), \TMP4
+	movdqu	  HashKey_k(%arg2), \TMP4
 	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM4, \XMMDst
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 5f4829f10129..dfb2f7c0d019 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2465,7 +2465,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 
 	perf_callchain_store(entry, regs->ip);
 
-	if (!current->mm)
+	if (!nmi_uaccess_okay())
 		return;
 
 	if (perf_callchain_user32(regs, entry))
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c14f2a74b2be..15450a675031 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -33,7 +33,8 @@ extern inline unsigned long native_save_fl(void)
 	return flags;
 }
 
-static inline void native_restore_fl(unsigned long flags)
+extern inline void native_restore_fl(unsigned long flags);
+extern inline void native_restore_fl(unsigned long flags)
 {
 	asm volatile("push %0 ; popf"
 		     : /* no output */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index a564084c6141..f8b1ad2c3828 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_PGTABLE_3LEVEL_H
 #define _ASM_X86_PGTABLE_3LEVEL_H
 
+#include <asm/atomic64_32.h>
+
 /*
  * Intel Physical Address Extension (PAE) Mode - three-level page
  * tables on PPro+ CPUs.
@@ -150,10 +152,7 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 {
 	pte_t res;
 
-	/* xchg acts as a barrier before the setting of the high bits */
-	res.pte_low = xchg(&ptep->pte_low, 0);
-	res.pte_high = ptep->pte_high;
-	ptep->pte_high = 0;
+	res.pte = (pteval_t)arch_atomic64_xchg((atomic64_t *)ptep, 0);
 
 	return res;
 }
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c24297268ebc..d53c54b842da 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -132,6 +132,8 @@ struct cpuinfo_x86 {
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
+	/* Address space bits used by the cache internally */
+	u8			x86_cache_bits;
 	unsigned		initialized : 1;
 } __randomize_layout;
 
@@ -183,7 +185,7 @@ extern void cpu_detect(struct cpuinfo_x86 *c);
 
 static inline unsigned long long l1tf_pfn_limit(void)
 {
-	return BIT_ULL(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT);
+	return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT);
 }
 
 extern void early_cpu_init(void);
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 5f9012ff52ed..33d3c88a7225 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -39,6 +39,7 @@ extern void do_signal(struct pt_regs *regs);
 
 #define __ARCH_HAS_SA_RESTORER
 
+#include <asm/asm.h>
 #include <uapi/asm/sigcontext.h>
 
 #ifdef __i386__
@@ -86,9 +87,9 @@ static inline int __const_sigismember(sigset_t *set, int _sig)
 
 static inline int __gen_sigismember(sigset_t *set, int _sig)
 {
-	unsigned char ret;
-	asm("btl %2,%1\n\tsetc %0"
-	    : "=qm"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+	bool ret;
+	asm("btl %2,%1" CC_SET(c)
+	    : CC_OUT(c) (ret) : "m"(*set), "Ir"(_sig-1));
 	return ret;
 }
 
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index b6dc698f992a..f335aad404a4 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -111,6 +111,6 @@ static inline unsigned long caller_frame_pointer(void)
 	return (unsigned long)frame;
 }
 
-void show_opcodes(u8 *rip, const char *loglvl);
+void show_opcodes(struct pt_regs *regs, const char *loglvl);
 void show_ip(struct pt_regs *regs, const char *loglvl);
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 29c9da6c62fc..58ce5288878e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -175,8 +175,16 @@ struct tlb_state {
 	 * are on.  This means that it may not match current->active_mm,
 	 * which will contain the previous user mm when we're in lazy TLB
 	 * mode even if we've already switched back to swapper_pg_dir.
+	 *
+	 * During switch_mm_irqs_off(), loaded_mm will be set to
+	 * LOADED_MM_SWITCHING during the brief interrupts-off window
+	 * when CR3 and loaded_mm would otherwise be inconsistent.  This
+	 * is for nmi_uaccess_okay()'s benefit.
 	 */
 	struct mm_struct *loaded_mm;
+
+#define LOADED_MM_SWITCHING ((struct mm_struct *)1)
+
 	u16 loaded_mm_asid;
 	u16 next_asid;
 	/* last user mm's ctx id */
@@ -246,6 +254,38 @@ struct tlb_state {
 };
 DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 
+/*
+ * Blindly accessing user memory from NMI context can be dangerous
+ * if we're in the middle of switching the current user task or
+ * switching the loaded mm.  It can also be dangerous if we
+ * interrupted some kernel code that was temporarily using a
+ * different mm.
+ */
+static inline bool nmi_uaccess_okay(void)
+{
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	struct mm_struct *current_mm = current->mm;
+
+	VM_WARN_ON_ONCE(!loaded_mm);
+
+	/*
+	 * The condition we want to check is
+	 * current_mm->pgd == __va(read_cr3_pa()).  This may be slow, though,
+	 * if we're running in a VM with shadow paging, and nmi_uaccess_okay()
+	 * is supposed to be reasonably fast.
+	 *
+	 * Instead, we check the almost equivalent but somewhat conservative
+	 * condition below, and we rely on the fact that switch_mm_irqs_off()
+	 * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3.
+	 */
+	if (loaded_mm != current_mm)
+		return false;
+
+	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+
+	return true;
+}
+
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index fb856c9f0449..53748541c487 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -93,7 +93,7 @@ static inline unsigned int __getcpu(void)
 	 *
 	 * If RDPID is available, use it.
 	 */
-	alternative_io ("lsl %[p],%[seg]",
+	alternative_io ("lsl %[seg],%[p]",
 			".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
 			X86_FEATURE_RDPID,
 			[p] "=a" (p), [seg] "r" (__PER_CPU_SEG));
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 014f214da581..b9d5e7c9ef43 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -684,8 +684,6 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
  * It means the size must be writable atomically and the address must be aligned
  * in a way that permits an atomic write. It also makes sure we fit on a single
  * page.
- *
- * Note: Must be called under text_mutex.
  */
 void *text_poke(void *addr, const void *opcode, size_t len)
 {
@@ -700,6 +698,8 @@ void *text_poke(void *addr, const void *opcode, size_t len)
 	 */
 	BUG_ON(!after_bootmem);
 
+	lockdep_assert_held(&text_mutex);
+
 	if (!core_kernel_text((unsigned long)addr)) {
 		pages[0] = vmalloc_to_page(addr);
 		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
@@ -782,8 +782,6 @@ int poke_int3_handler(struct pt_regs *regs)
  *	- replace the first byte (int3) by the first byte of
  *	  replacing opcode
  *	- sync cores
- *
- * Note: must be called under text_mutex.
  */
 void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 {
@@ -792,6 +790,9 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 	bp_int3_handler = handler;
 	bp_int3_addr = (u8 *)addr + sizeof(int3);
 	bp_patching_in_progress = true;
+
+	lockdep_assert_held(&text_mutex);
+
 	/*
 	 * Corresponding read barrier in int3 notifier for making sure the
 	 * in_progress and handler are correctly ordered wrt. patching.
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4c2313d0b9ca..40bdaea97fe7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -668,6 +668,45 @@ EXPORT_SYMBOL_GPL(l1tf_mitigation);
 enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
 
+/*
+ * These CPUs all support 44bits physical address space internally in the
+ * cache but CPUID can report a smaller number of physical address bits.
+ *
+ * The L1TF mitigation uses the top most address bit for the inversion of
+ * non present PTEs. When the installed memory reaches into the top most
+ * address bit due to memory holes, which has been observed on machines
+ * which report 36bits physical address bits and have 32G RAM installed,
+ * then the mitigation range check in l1tf_select_mitigation() triggers.
+ * This is a false positive because the mitigation is still possible due to
+ * the fact that the cache uses 44bit internally. Use the cache bits
+ * instead of the reported physical bits and adjust them on the affected
+ * machines to 44bit if the reported bits are less than 44.
+ */
+static void override_cache_bits(struct cpuinfo_x86 *c)
+{
+	if (c->x86 != 6)
+		return;
+
+	switch (c->x86_model) {
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_HASWELL_CORE:
+	case INTEL_FAM6_HASWELL_ULT:
+	case INTEL_FAM6_HASWELL_GT3E:
+	case INTEL_FAM6_BROADWELL_CORE:
+	case INTEL_FAM6_BROADWELL_GT3E:
+	case INTEL_FAM6_SKYLAKE_MOBILE:
+	case INTEL_FAM6_SKYLAKE_DESKTOP:
+	case INTEL_FAM6_KABYLAKE_MOBILE:
+	case INTEL_FAM6_KABYLAKE_DESKTOP:
+		if (c->x86_cache_bits < 44)
+			c->x86_cache_bits = 44;
+		break;
+	}
+}
+
 static void __init l1tf_select_mitigation(void)
 {
 	u64 half_pa;
@@ -675,6 +714,8 @@ static void __init l1tf_select_mitigation(void)
 	if (!boot_cpu_has_bug(X86_BUG_L1TF))
 		return;
 
+	override_cache_bits(&boot_cpu_data);
+
 	switch (l1tf_mitigation) {
 	case L1TF_MITIGATION_OFF:
 	case L1TF_MITIGATION_FLUSH_NOWARN:
@@ -694,11 +735,6 @@ static void __init l1tf_select_mitigation(void)
 	return;
 #endif
 
-	/*
-	 * This is extremely unlikely to happen because almost all
-	 * systems have far more MAX_PA/2 than RAM can be fit into
-	 * DIMM slots.
-	 */
 	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
 	if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
 		pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 84dee5ab745a..44c4ef3d989b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -919,6 +919,7 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
 		c->x86_phys_bits = 36;
 #endif
+	c->x86_cache_bits = c->x86_phys_bits;
 }
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 401e8c133108..fc3c07fe7df5 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -150,6 +150,9 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
 		return false;
 
+	if (c->x86 != 6)
+		return false;
+
 	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
 		if (c->x86_model == spectre_bad_microcodes[i].model &&
 		    c->x86_stepping == spectre_bad_microcodes[i].stepping)
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 9c8652974f8e..f56895106ccf 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -17,6 +17,7 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
+#include <linux/kasan.h>
 
 #include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
@@ -89,14 +90,24 @@ static void printk_stack_address(unsigned long address, int reliable,
  * Thus, the 2/3rds prologue and 64 byte OPCODE_BUFSIZE is just a random
  * guesstimate in attempt to achieve all of the above.
  */
-void show_opcodes(u8 *rip, const char *loglvl)
+void show_opcodes(struct pt_regs *regs, const char *loglvl)
 {
 #define PROLOGUE_SIZE 42
 #define EPILOGUE_SIZE 21
 #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
+	unsigned long prologue = regs->ip - PROLOGUE_SIZE;
+	bool bad_ip;
 
-	if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) {
+	/*
+	 * Make sure userspace isn't trying to trick us into dumping kernel
+	 * memory by pointing the userspace instruction pointer at it.
+	 */
+	bad_ip = user_mode(regs) &&
+		__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
+
+	if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue,
+					OPCODE_BUFSIZE)) {
 		printk("%sCode: Bad RIP value.\n", loglvl);
 	} else {
 		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
@@ -112,7 +123,7 @@ void show_ip(struct pt_regs *regs, const char *loglvl)
 #else
 	printk("%sRIP: %04x:%pS\n", loglvl, (int)regs->cs, (void *)regs->ip);
 #endif
-	show_opcodes((u8 *)regs->ip, loglvl);
+	show_opcodes(regs, loglvl);
 }
 
 void show_iret_regs(struct pt_regs *regs)
@@ -346,7 +357,10 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 	 * We're not going to return, but we might be on an IST stack or
 	 * have very little stack space left.  Rewind the stack and kill
 	 * the task.
+	 * Before we rewind the stack, we have to tell KASAN that we're going to
+	 * reuse the task stack and that existing poisons are invalid.
 	 */
+	kasan_unpoison_task_stack(current);
 	rewind_stack_do_exit(signr);
 }
 NOKPROBE_SYMBOL(oops_end);
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index c8c6ad0d58b8..3f435d7fca5e 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -7,6 +7,8 @@
 #include <linux/uaccess.h>
 #include <linux/export.h>
 
+#include <asm/tlbflush.h>
+
 /*
  * We rely on the nested NMI work to allow atomic faults from the NMI path; the
  * nested NMI paths are careful to preserve CR2.
@@ -19,6 +21,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	if (__range_not_ok(from, n, TASK_SIZE))
 		return n;
 
+	if (!nmi_uaccess_okay())
+		return n;
+
 	/*
 	 * Even though this function is typically called from NMI/IRQ context
 	 * disable pagefaults so that its behaviour is consistent even when
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b9123c497e0a..47bebfe6efa7 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -837,7 +837,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 
 	printk(KERN_CONT "\n");
 
-	show_opcodes((u8 *)regs->ip, loglvl);
+	show_opcodes(regs, loglvl);
 }
 
 static void
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 8d6c34fe49be..51a5a69ecac9 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1420,6 +1420,29 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 	return 0;
 }
 
+/*
+ * Machine check recovery code needs to change cache mode of poisoned
+ * pages to UC to avoid speculative access logging another error. But
+ * passing the address of the 1:1 mapping to set_memory_uc() is a fine
+ * way to encourage a speculative access. So we cheat and flip the top
+ * bit of the address. This works fine for the code that updates the
+ * page tables. But at the end of the process we need to flush the cache
+ * and the non-canonical address causes a #GP fault when used by the
+ * CLFLUSH instruction.
+ *
+ * But in the common case we already have a canonical address. This code
+ * will fix the top bit if needed and is a no-op otherwise.
+ */
+static inline unsigned long make_addr_canonical_again(unsigned long addr)
+{
+#ifdef CONFIG_X86_64
+	return (long)(addr << 1) >> 1;
+#else
+	return addr;
+#endif
+}
+
+
 static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 				    pgprot_t mask_set, pgprot_t mask_clr,
 				    int force_split, int in_flag,
@@ -1465,7 +1488,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 		 * Save address for cache flush. *addr is modified in the call
 		 * to __change_page_attr_set_clr() below.
 		 */
-		baddr = *addr;
+		baddr = make_addr_canonical_again(*addr);
 	}
 
 	/* Must avoid aliasing mappings in the highmem code */
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 31341ae7309f..c1fc1ae6b429 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -248,7 +248,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
  *
  * Returns a pointer to a PTE on success, or NULL on failure.
  */
-static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+static pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	pmd_t *pmd;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 9517d1b2a281..e96b99eb800c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -305,6 +305,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
 
+		/* Let nmi_uaccess_okay() know that we're changing CR3. */
+		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
+		barrier();
+
 		if (need_flush) {
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
@@ -335,6 +339,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		if (next != &init_mm)
 			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
 
+		/* Make sure we write CR3 before loaded_mm. */
+		barrier();
+
 		this_cpu_write(cpu_tlbstate.loaded_mm, next);
 		this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
 	}
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 324b93328b37..05ca14222463 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -85,14 +85,10 @@ pgd_t * __init efi_call_phys_prolog(void)
 
 void __init efi_call_phys_epilog(pgd_t *save_pgd)
 {
-	struct desc_ptr gdt_descr;
-
-	gdt_descr.address = (unsigned long)get_cpu_gdt_rw(0);
-	gdt_descr.size = GDT_SIZE - 1;
-	load_gdt(&gdt_descr);
-
 	load_cr3(save_pgd);
 	__flush_tlb_all();
+
+	load_fixmap_gdt(0);
 }
 
 void __init efi_runtime_update_mappings(void)
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 45b700ac5fe7..2fe5c9b1816b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -435,14 +435,13 @@ static void xen_set_pud(pud_t *ptr, pud_t val)
 static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
 	trace_xen_mmu_set_pte_atomic(ptep, pte);
-	set_64bit((u64 *)ptep, native_pte_val(pte));
+	__xen_set_pte(ptep, pte);
 }
 
 static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	trace_xen_mmu_pte_clear(mm, addr, ptep);
-	if (!xen_batched_set_pte(ptep, native_make_pte(0)))
-		native_pte_clear(mm, addr, ptep);
+	__xen_set_pte(ptep, native_make_pte(0));
 }
 
 static void xen_pmd_clear(pmd_t *pmdp)
@@ -1570,7 +1569,7 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
 			       pte_val_ma(pte));
 #endif
-	native_set_pte(ptep, pte);
+	__xen_set_pte(ptep, pte);
 }
 
 /* Early in boot, while setting up the initial pagetable, assume
@@ -2061,7 +2060,6 @@ void __init xen_relocate_p2m(void)
 	pud_t *pud;
 	pgd_t *pgd;
 	unsigned long *new_p2m;
-	int save_pud;
 
 	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
 	n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
@@ -2091,7 +2089,6 @@ void __init xen_relocate_p2m(void)
 
 	pgd = __va(read_cr3_pa());
 	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
-	save_pud = n_pud;
 	for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
 		pud = early_memremap(pud_phys, PAGE_SIZE);
 		clear_page(pud);