Merge tag 'v5.15.34' into dev-5.15

This is the 5.15.34 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

178 files changed, 1545 insertions, 808 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index d1e69d6e8498..191589f26b1a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1141,6 +1141,7 @@ config HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 config RANDOMIZE_KSTACK_OFFSET_DEFAULT
 	bool "Randomize kernel stack offset on syscall entry"
 	depends on HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+	depends on INIT_STACK_NONE || !CC_IS_CLANG || CLANG_VERSION >= 140000
 	help
 	  The kernel stack offset can be randomized (after pt_regs) by
 	  roughly 5 bits of entropy, frustrating memory corruption
diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c
index ce3077946e1d..fb3025396ac9 100644
--- a/arch/alpha/kernel/rtc.c
+++ b/arch/alpha/kernel/rtc.c
@@ -80,7 +80,12 @@ init_rtc_epoch(void)
 static int
 alpha_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	mc146818_get_time(tm);
+	int ret = mc146818_get_time(tm);
+
+	if (ret < 0) {
+		dev_err_ratelimited(dev, "unable to read current time\n");
+		return ret;
+	}
 
 	/* Adjust for non-default epochs.  It's easier to depend on the
 	   generic __get_rtc_time and adjust the epoch here than create
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 8e90052f6f05..5f7f5aab361f 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -43,7 +43,7 @@ SYSCALL_DEFINE0(arc_gettls)
 	return task_thread_info(current)->thr_ptr;
 }
 
-SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
+SYSCALL_DEFINE3(arc_usr_cmpxchg, int __user *, uaddr, int, expected, int, new)
 {
 	struct pt_regs *regs = current_pt_regs();
 	u32 uval;
diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi
index 21294f775a20..89af57482bc8 100644
--- a/arch/arm/boot/dts/bcm2711.dtsi
+++ b/arch/arm/boot/dts/bcm2711.dtsi
@@ -459,12 +459,26 @@
 		#size-cells = <0>;
 		enable-method = "brcm,bcm2836-smp"; // for ARM 32-bit
 
+		/* Source for d/i-cache-line-size and d/i-cache-sets
+		 * https://developer.arm.com/documentation/100095/0003
+		 * /Level-1-Memory-System/About-the-L1-memory-system?lang=en
+		 * Source for d/i-cache-size
+		 * https://www.raspberrypi.com/documentation/computers
+		 * /processors.html#bcm2711
+		 */
 		cpu0: cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a72";
 			reg = <0>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x000000d8>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>; // 32KiB(size)/64(line-size)=512ways/2-way set
+			i-cache-size = <0xc000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>; // 48KiB(size)/64(line-size)=768ways/3-way set
+			next-level-cache = <&l2>;
 		};
 
 		cpu1: cpu@1 {
@@ -473,6 +487,13 @@
 			reg = <1>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x000000e0>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>; // 32KiB(size)/64(line-size)=512ways/2-way set
+			i-cache-size = <0xc000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>; // 48KiB(size)/64(line-size)=768ways/3-way set
+			next-level-cache = <&l2>;
 		};
 
 		cpu2: cpu@2 {
@@ -481,6 +502,13 @@
 			reg = <2>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x000000e8>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>; // 32KiB(size)/64(line-size)=512ways/2-way set
+			i-cache-size = <0xc000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>; // 48KiB(size)/64(line-size)=768ways/3-way set
+			next-level-cache = <&l2>;
 		};
 
 		cpu3: cpu@3 {
@@ -489,6 +517,28 @@
 			reg = <3>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x000000f0>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>; // 32KiB(size)/64(line-size)=512ways/2-way set
+			i-cache-size = <0xc000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>; // 48KiB(size)/64(line-size)=768ways/3-way set
+			next-level-cache = <&l2>;
+		};
+
+		/* Source for d/i-cache-line-size and d/i-cache-sets
+		 *  https://developer.arm.com/documentation/100095/0003
+		 *  /Level-2-Memory-System/About-the-L2-memory-system?lang=en
+		 *  Source for d/i-cache-size
+		 *  https://www.raspberrypi.com/documentation/computers
+		 *  /processors.html#bcm2711
+		 */
+		l2: l2-cache0 {
+			compatible = "cache";
+			cache-size = <0x100000>;
+			cache-line-size = <64>;
+			cache-sets = <1024>; // 1MiB(size)/64(line-size)=16384ways/16-way set
+			cache-level = <2>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/bcm2837.dtsi b/arch/arm/boot/dts/bcm2837.dtsi
index 0199ec98cd61..5dbdebc46259 100644
--- a/arch/arm/boot/dts/bcm2837.dtsi
+++ b/arch/arm/boot/dts/bcm2837.dtsi
@@ -40,12 +40,26 @@
 		#size-cells = <0>;
 		enable-method = "brcm,bcm2836-smp"; // for ARM 32-bit
 
+		/* Source for d/i-cache-line-size and d/i-cache-sets
+		 * https://developer.arm.com/documentation/ddi0500/e/level-1-memory-system
+		 * /about-the-l1-memory-system?lang=en
+		 *
+		 * Source for d/i-cache-size
+		 * https://magpi.raspberrypi.com/articles/raspberry-pi-3-specs-benchmarks
+		 */
 		cpu0: cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53";
 			reg = <0>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x000000d8>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>; // 32KiB(size)/64(line-size)=512ways/4-way set
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>; // 32KiB(size)/64(line-size)=512ways/2-way set
+			next-level-cache = <&l2>;
 		};
 
 		cpu1: cpu@1 {
@@ -54,6 +68,13 @@
 			reg = <1>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x000000e0>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>; // 32KiB(size)/64(line-size)=512ways/4-way set
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>; // 32KiB(size)/64(line-size)=512ways/2-way set
+			next-level-cache = <&l2>;
 		};
 
 		cpu2: cpu@2 {
@@ -62,6 +83,13 @@
 			reg = <2>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x000000e8>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>; // 32KiB(size)/64(line-size)=512ways/4-way set
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>; // 32KiB(size)/64(line-size)=512ways/2-way set
+			next-level-cache = <&l2>;
 		};
 
 		cpu3: cpu@3 {
@@ -70,6 +98,27 @@
 			reg = <3>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x000000f0>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>; // 32KiB(size)/64(line-size)=512ways/4-way set
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>; // 32KiB(size)/64(line-size)=512ways/2-way set
+			next-level-cache = <&l2>;
+		};
+
+		/* Source for cache-line-size + cache-sets
+		 * https://developer.arm.com/documentation/ddi0500
+		 * /e/level-2-memory-system/about-the-l2-memory-system?lang=en
+		 * Source for cache-size
+		 * https://datasheets.raspberrypi.com/cm/cm1-and-cm3-datasheet.pdf
+		 */
+		l2: l2-cache0 {
+			compatible = "cache";
+			cache-size = <0x80000>;
+			cache-line-size = <64>;
+			cache-sets = <512>; // 512KiB(size)/64(line-size)=8192ways/16-way set
+			cache-level = <2>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi
index 956a26d52a4c..0a11bacffc1f 100644
--- a/arch/arm/boot/dts/dra7-l4.dtsi
+++ b/arch/arm/boot/dts/dra7-l4.dtsi
@@ -3482,8 +3482,7 @@
 				ti,timer-pwm;
 			};
 		};
-
-		target-module@2c000 {			/* 0x4882c000, ap 17 02.0 */
+		timer15_target: target-module@2c000 {	/* 0x4882c000, ap 17 02.0 */
 			compatible = "ti,sysc-omap4-timer", "ti,sysc";
 			reg = <0x2c000 0x4>,
 			      <0x2c010 0x4>;
@@ -3511,7 +3510,7 @@
 			};
 		};
 
-		target-module@2e000 {			/* 0x4882e000, ap 19 14.0 */
+		timer16_target: target-module@2e000 {	/* 0x4882e000, ap 19 14.0 */
 			compatible = "ti,sysc-omap4-timer", "ti,sysc";
 			reg = <0x2e000 0x4>,
 			      <0x2e010 0x4>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index dfc1ef8ef6ae..61a3fb3e2a2f 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1320,20 +1320,20 @@
 };
 
 /* Local timers, see ARM architected timer wrap erratum i940 */
-&timer3_target {
+&timer15_target {
 	ti,no-reset-on-init;
 	ti,no-idle;
 	timer@0 {
-		assigned-clocks = <&l4per_clkctrl DRA7_L4PER_TIMER3_CLKCTRL 24>;
+		assigned-clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>;
 		assigned-clock-parents = <&timer_sys_clk_div>;
 	};
 };
 
-&timer4_target {
+&timer16_target {
 	ti,no-reset-on-init;
 	ti,no-idle;
 	timer@0 {
-		assigned-clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 24>;
+		assigned-clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>;
 		assigned-clock-parents = <&timer_sys_clk_div>;
 	};
 };
diff --git a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
index d31a68672bfa..d7d756614edd 100644
--- a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
@@ -260,7 +260,7 @@
 	};
 
 	uart3_data: uart3-data {
-		samsung,pins = "gpa1-4", "gpa1-4";
+		samsung,pins = "gpa1-4", "gpa1-5";
 		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
 		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
 		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts
index 39bbe18145cf..f042954bdfa5 100644
--- a/arch/arm/boot/dts/exynos5250-smdk5250.dts
+++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts
@@ -118,6 +118,9 @@
 	status = "okay";
 	ddc = <&i2c_2>;
 	hpd-gpios = <&gpx3 7 GPIO_ACTIVE_HIGH>;
+	vdd-supply = <&ldo8_reg>;
+	vdd_osc-supply = <&ldo10_reg>;
+	vdd_pll-supply = <&ldo8_reg>;
 };
 
 &i2c_0 {
diff --git a/arch/arm/boot/dts/exynos5420-smdk5420.dts b/arch/arm/boot/dts/exynos5420-smdk5420.dts
index a4f0e3ffedbd..07f65213aae6 100644
--- a/arch/arm/boot/dts/exynos5420-smdk5420.dts
+++ b/arch/arm/boot/dts/exynos5420-smdk5420.dts
@@ -124,6 +124,9 @@
 	hpd-gpios = <&gpx3 7 GPIO_ACTIVE_HIGH>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&hdmi_hpd_irq>;
+	vdd-supply = <&ldo6_reg>;
+	vdd_osc-supply = <&ldo7_reg>;
+	vdd_pll-supply = <&ldo6_reg>;
 };
 
 &hsi2c_4 {
diff --git a/arch/arm/boot/dts/imx53-m53menlo.dts b/arch/arm/boot/dts/imx53-m53menlo.dts
index 4f88e96d81dd..d5c68d1ea707 100644
--- a/arch/arm/boot/dts/imx53-m53menlo.dts
+++ b/arch/arm/boot/dts/imx53-m53menlo.dts
@@ -53,6 +53,31 @@
 		};
 	};
 
+	lvds-decoder {
+		compatible = "ti,ds90cf364a", "lvds-decoder";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lvds_decoder_in: endpoint {
+					remote-endpoint = <&lvds0_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				lvds_decoder_out: endpoint {
+					remote-endpoint = <&panel_in>;
+				};
+			};
+		};
+	};
+
 	panel {
 		compatible = "edt,etm0700g0dh6";
 		pinctrl-0 = <&pinctrl_display_gpio>;
@@ -61,7 +86,7 @@
 
 		port {
 			panel_in: endpoint {
-				remote-endpoint = <&lvds0_out>;
+				remote-endpoint = <&lvds_decoder_out>;
 			};
 		};
 	};
@@ -450,7 +475,7 @@
 			reg = <2>;
 
 			lvds0_out: endpoint {
-				remote-endpoint = <&panel_in>;
+				remote-endpoint = <&lvds_decoder_in>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/imx7-colibri.dtsi b/arch/arm/boot/dts/imx7-colibri.dtsi
index 62b771c1d5a9..f1c60b0cb143 100644
--- a/arch/arm/boot/dts/imx7-colibri.dtsi
+++ b/arch/arm/boot/dts/imx7-colibri.dtsi
@@ -40,7 +40,7 @@
 
 		dailink_master: simple-audio-card,codec {
 			sound-dai = <&codec>;
-			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		};
 	};
 };
@@ -293,7 +293,7 @@
 		compatible = "fsl,sgtl5000";
 		#sound-dai-cells = <0>;
 		reg = <0x0a>;
-		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_sai1_mclk>;
 		VDDA-supply = <&reg_module_3v3_avdd>;
diff --git a/arch/arm/boot/dts/imx7-mba7.dtsi b/arch/arm/boot/dts/imx7-mba7.dtsi
index 5e6bef230dc7..b55a7792a839 100644
--- a/arch/arm/boot/dts/imx7-mba7.dtsi
+++ b/arch/arm/boot/dts/imx7-mba7.dtsi
@@ -264,7 +264,7 @@
 	tlv320aic32x4: audio-codec@18 {
 		compatible = "ti,tlv320aic32x4";
 		reg = <0x18>;
-		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		clock-names = "mclk";
 		ldoin-supply = <&reg_audio_3v3>;
 		iov-supply = <&reg_audio_3v3>;
diff --git a/arch/arm/boot/dts/imx7d-nitrogen7.dts b/arch/arm/boot/dts/imx7d-nitrogen7.dts
index e0751e6ba3c0..a31de900139d 100644
--- a/arch/arm/boot/dts/imx7d-nitrogen7.dts
+++ b/arch/arm/boot/dts/imx7d-nitrogen7.dts
@@ -288,7 +288,7 @@
 	codec: wm8960@1a {
 		compatible = "wlf,wm8960";
 		reg = <0x1a>;
-		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		clock-names = "mclk";
 		wlf,shared-lrclk;
 	};
diff --git a/arch/arm/boot/dts/imx7d-pico-hobbit.dts b/arch/arm/boot/dts/imx7d-pico-hobbit.dts
index 7b2198a9372c..d917dc4f2f22 100644
--- a/arch/arm/boot/dts/imx7d-pico-hobbit.dts
+++ b/arch/arm/boot/dts/imx7d-pico-hobbit.dts
@@ -31,7 +31,7 @@
 
 		dailink_master: simple-audio-card,codec {
 			sound-dai = <&sgtl5000>;
-			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		};
 	};
 };
@@ -41,7 +41,7 @@
 		#sound-dai-cells = <0>;
 		reg = <0x0a>;
 		compatible = "fsl,sgtl5000";
-		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		VDDA-supply = <&reg_2p5v>;
 		VDDIO-supply = <&reg_vref_1v8>;
 	};
diff --git a/arch/arm/boot/dts/imx7d-pico-pi.dts b/arch/arm/boot/dts/imx7d-pico-pi.dts
index 70bea95c06d8..f263e391e24c 100644
--- a/arch/arm/boot/dts/imx7d-pico-pi.dts
+++ b/arch/arm/boot/dts/imx7d-pico-pi.dts
@@ -31,7 +31,7 @@
 
 		dailink_master: simple-audio-card,codec {
 			sound-dai = <&sgtl5000>;
-			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		};
 	};
 };
@@ -41,7 +41,7 @@
 		#sound-dai-cells = <0>;
 		reg = <0x0a>;
 		compatible = "fsl,sgtl5000";
-		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		VDDA-supply = <&reg_2p5v>;
 		VDDIO-supply = <&reg_vref_1v8>;
 	};
diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts
index 4a0d83784d7d..e5f1bdbe7992 100644
--- a/arch/arm/boot/dts/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/imx7d-sdb.dts
@@ -385,14 +385,14 @@
 	codec: wm8960@1a {
 		compatible = "wlf,wm8960";
 		reg = <0x1a>;
-		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		clock-names = "mclk";
 		wlf,shared-lrclk;
 		wlf,hp-cfg = <2 2 3>;
 		wlf,gpio-cfg = <1 3>;
 		assigned-clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_SRC>,
 				  <&clks IMX7D_PLL_AUDIO_POST_DIV>,
-				  <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+				  <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		assigned-clock-parents = <&clks IMX7D_PLL_AUDIO_POST_DIV>;
 		assigned-clock-rates = <0>, <884736000>, <12288000>;
 	};
diff --git a/arch/arm/boot/dts/imx7s-warp.dts b/arch/arm/boot/dts/imx7s-warp.dts
index 569bbd84e371..558b064da743 100644
--- a/arch/arm/boot/dts/imx7s-warp.dts
+++ b/arch/arm/boot/dts/imx7s-warp.dts
@@ -75,7 +75,7 @@
 
 		dailink_master: simple-audio-card,codec {
 			sound-dai = <&codec>;
-			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+			clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		};
 	};
 };
@@ -232,7 +232,7 @@
 		#sound-dai-cells = <0>;
 		reg = <0x0a>;
 		compatible = "fsl,sgtl5000";
-		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>;
+		clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_sai1_mclk>;
 		VDDA-supply = <&vgen4_reg>;
diff --git a/arch/arm/boot/dts/openbmc-flash-layout-64.dtsi b/arch/arm/boot/dts/openbmc-flash-layout-64.dtsi
index 31f59de5190b..7af41361c480 100644
--- a/arch/arm/boot/dts/openbmc-flash-layout-64.dtsi
+++ b/arch/arm/boot/dts/openbmc-flash-layout-64.dtsi
@@ -28,7 +28,7 @@ partitions {
 		label = "rofs";
 	};
 
-	rwfs@6000000 {
+	rwfs@2a00000 {
 		reg = <0x2a00000 0x1600000>; // 22MB
 		label = "rwfs";
 	};
diff --git a/arch/arm/boot/dts/openbmc-flash-layout.dtsi b/arch/arm/boot/dts/openbmc-flash-layout.dtsi
index 6c26524e93e1..b47e14063c38 100644
--- a/arch/arm/boot/dts/openbmc-flash-layout.dtsi
+++ b/arch/arm/boot/dts/openbmc-flash-layout.dtsi
@@ -20,7 +20,7 @@ partitions {
 		label = "kernel";
 	};
 
-	rofs@c0000 {
+	rofs@4c0000 {
 		reg = <0x4c0000 0x1740000>;
 		label = "rofs";
 	};
diff --git a/arch/arm/boot/dts/qcom-ipq4019.dtsi b/arch/arm/boot/dts/qcom-ipq4019.dtsi
index ff1bdb10ad19..08bc5f46649d 100644
--- a/arch/arm/boot/dts/qcom-ipq4019.dtsi
+++ b/arch/arm/boot/dts/qcom-ipq4019.dtsi
@@ -142,7 +142,8 @@
 	clocks {
 		sleep_clk: sleep_clk {
 			compatible = "fixed-clock";
-			clock-frequency = <32768>;
+			clock-frequency = <32000>;
+			clock-output-names = "gcc_sleep_clk_src";
 			#clock-cells = <0>;
 		};
 
diff --git a/arch/arm/boot/dts/qcom-msm8960.dtsi b/arch/arm/boot/dts/qcom-msm8960.dtsi
index 172ea3c70eac..c197927e7435 100644
--- a/arch/arm/boot/dts/qcom-msm8960.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8960.dtsi
@@ -146,7 +146,9 @@
 			reg		= <0x108000 0x1000>;
 			qcom,ipc	= <&l2cc 0x8 2>;
 
-			interrupts	= <0 19 0>, <0 21 0>, <0 22 0>;
+			interrupts	= <GIC_SPI 19 IRQ_TYPE_EDGE_RISING>,
+					  <GIC_SPI 21 IRQ_TYPE_EDGE_RISING>,
+					  <GIC_SPI 22 IRQ_TYPE_EDGE_RISING>;
 			interrupt-names	= "ack", "err", "wakeup";
 
 			regulators {
@@ -192,7 +194,7 @@
 				compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 				reg = <0x16440000 0x1000>,
 				      <0x16400000 0x1000>;
-				interrupts = <0 154 0x0>;
+				interrupts = <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI5_UART_CLK>, <&gcc GSBI5_H_CLK>;
 				clock-names = "core", "iface";
 				status = "disabled";
@@ -318,7 +320,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				reg = <0x16080000 0x1000>;
-				interrupts = <0 147 0>;
+				interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
 				spi-max-frequency = <24000000>;
 				cs-gpios = <&msmgpio 8 0>;
 
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index 801969c113d6..de88eb484718 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -413,7 +413,7 @@
 				pmecc: ecc-engine@f8014070 {
 					compatible = "atmel,sama5d2-pmecc";
 					reg = <0xf8014070 0x490>,
-					      <0xf8014500 0x100>;
+					      <0xf8014500 0x200>;
 				};
 			};
 
diff --git a/arch/arm/boot/dts/sama7g5.dtsi b/arch/arm/boot/dts/sama7g5.dtsi
index 6c58c151c6d9..ac84d2e37f9b 100644
--- a/arch/arm/boot/dts/sama7g5.dtsi
+++ b/arch/arm/boot/dts/sama7g5.dtsi
@@ -319,8 +319,6 @@
 				dmas = <&dma0 AT91_XDMAC_DT_PERID(7)>,
 					<&dma0 AT91_XDMAC_DT_PERID(8)>;
 				dma-names = "rx", "tx";
-				atmel,use-dma-rx;
-				atmel,use-dma-tx;
 				status = "disabled";
 			};
 		};
@@ -485,8 +483,6 @@
 				dmas = <&dma0 AT91_XDMAC_DT_PERID(21)>,
 					<&dma0 AT91_XDMAC_DT_PERID(22)>;
 				dma-names = "rx", "tx";
-				atmel,use-dma-rx;
-				atmel,use-dma-tx;
 				status = "disabled";
 			};
 		};
@@ -511,8 +507,6 @@
 				dmas = <&dma0 AT91_XDMAC_DT_PERID(23)>,
 					<&dma0 AT91_XDMAC_DT_PERID(24)>;
 				dma-names = "rx", "tx";
-				atmel,use-dma-rx;
-				atmel,use-dma-tx;
 				status = "disabled";
 			};
 		};
diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi
index 1a8f5e8b10e3..66cd473ecb61 100644
--- a/arch/arm/boot/dts/spear1340.dtsi
+++ b/arch/arm/boot/dts/spear1340.dtsi
@@ -136,9 +136,9 @@
 				reg = <0xb4100000 0x1000>;
 				interrupts = <0 105 0x4>;
 				status = "disabled";
-				dmas = <&dwdma0 12 0 1>,
-					<&dwdma0 13 1 0>;
-				dma-names = "tx", "rx";
+				dmas = <&dwdma0 13 0 1>,
+					<&dwdma0 12 1 0>;
+				dma-names = "rx", "tx";
 			};
 
 			thermal@e07008c4 {
diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi
index c87b881b2c8b..913553367687 100644
--- a/arch/arm/boot/dts/spear13xx.dtsi
+++ b/arch/arm/boot/dts/spear13xx.dtsi
@@ -284,9 +284,9 @@
 				#size-cells = <0>;
 				interrupts = <0 31 0x4>;
 				status = "disabled";
-				dmas = <&dwdma0 4 0 0>,
-					<&dwdma0 5 0 0>;
-				dma-names = "tx", "rx";
+				dmas = <&dwdma0 5 0 0>,
+					<&dwdma0 4 0 0>;
+				dma-names = "rx", "tx";
 			};
 
 			rtc@e0580000 {
diff --git a/arch/arm/boot/dts/sun8i-v3s.dtsi b/arch/arm/boot/dts/sun8i-v3s.dtsi
index b30bc1a25ebb..084323d5c61c 100644
--- a/arch/arm/boot/dts/sun8i-v3s.dtsi
+++ b/arch/arm/boot/dts/sun8i-v3s.dtsi
@@ -593,6 +593,17 @@
 			#size-cells = <0>;
 		};
 
+		gic: interrupt-controller@1c81000 {
+			compatible = "arm,gic-400";
+			reg = <0x01c81000 0x1000>,
+			      <0x01c82000 0x2000>,
+			      <0x01c84000 0x2000>,
+			      <0x01c86000 0x2000>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
+		};
+
 		csi1: camera@1cb4000 {
 			compatible = "allwinner,sun8i-v3s-csi";
 			reg = <0x01cb4000 0x3000>;
@@ -604,16 +615,5 @@
 			resets = <&ccu RST_BUS_CSI>;
 			status = "disabled";
 		};
-
-		gic: interrupt-controller@1c81000 {
-			compatible = "arm,gic-400";
-			reg = <0x01c81000 0x1000>,
-			      <0x01c82000 0x2000>,
-			      <0x01c84000 0x2000>,
-			      <0x01c86000 0x2000>;
-			interrupt-controller;
-			#interrupt-cells = <3>;
-			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
-		};
 	};
 };
diff --git a/arch/arm/boot/dts/tegra20-tamonten.dtsi b/arch/arm/boot/dts/tegra20-tamonten.dtsi
index dd4d506683de..7f14f0d005c3 100644
--- a/arch/arm/boot/dts/tegra20-tamonten.dtsi
+++ b/arch/arm/boot/dts/tegra20-tamonten.dtsi
@@ -183,8 +183,8 @@
 			};
 			conf_ata {
 				nvidia,pins = "ata", "atb", "atc", "atd", "ate",
-					"cdev1", "cdev2", "dap1", "dtb", "gma",
-					"gmb", "gmc", "gmd", "gme", "gpu7",
+					"cdev1", "cdev2", "dap1", "dtb", "dtf",
+					"gma", "gmb", "gmc", "gmd", "gme", "gpu7",
 					"gpv", "i2cp", "irrx", "irtx", "pta",
 					"rm", "slxa", "slxk", "spia", "spib",
 					"uac";
@@ -203,7 +203,7 @@
 			};
 			conf_crtp {
 				nvidia,pins = "crtp", "dap2", "dap3", "dap4",
-					"dtc", "dte", "dtf", "gpu", "sdio1",
+					"dtc", "dte", "gpu", "sdio1",
 					"slxc", "slxd", "spdi", "spdo", "spig",
 					"uda";
 				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig
index 80a3ae02d759..e883cb6dc645 100644
--- a/arch/arm/configs/multi_v5_defconfig
+++ b/arch/arm/configs/multi_v5_defconfig
@@ -188,6 +188,7 @@ CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_MEDIA_SUPPORT=y
 CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_MEDIA_PLATFORM_SUPPORT=y
 CONFIG_V4L_PLATFORM_DRIVERS=y
 CONFIG_VIDEO_ASPEED=m
 CONFIG_VIDEO_ATMEL_ISI=m
@@ -195,6 +196,7 @@ CONFIG_DRM=y
 CONFIG_DRM_ATMEL_HLCDC=m
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_ASPEED_GFX=m
+CONFIG_FB=y
 CONFIG_FB_IMX=y
 CONFIG_FB_ATMEL=y
 CONFIG_BACKLIGHT_ATMEL_LCDC=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 2b575792363e..e4dba5461cb3 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -102,6 +102,8 @@ config CRYPTO_AES_ARM_BS
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
+	select CRYPTO_AES
+	select CRYPTO_CBC
 	select CRYPTO_SIMD
 	help
 	  Use a faster and more secure NEON based implementation of AES in CBC,
diff --git a/arch/arm/kernel/entry-ftrace.S b/arch/arm/kernel/entry-ftrace.S
index a74289ebc803..5f1b1ce10473 100644
--- a/arch/arm/kernel/entry-ftrace.S
+++ b/arch/arm/kernel/entry-ftrace.S
@@ -22,10 +22,7 @@
  * mcount can be thought of as a function called in the middle of a subroutine
  * call.  As such, it needs to be transparent for both the caller and the
  * callee: the original lr needs to be restored when leaving mcount, and no
- * registers should be clobbered.  (In the __gnu_mcount_nc implementation, we
- * clobber the ip register.  This is OK because the ARM calling convention
- * allows it to be clobbered in subroutines and doesn't use it to hold
- * parameters.)
+ * registers should be clobbered.
  *
  * When using dynamic ftrace, we patch out the mcount call by a "pop {lr}"
  * instead of the __gnu_mcount_nc call (see arch/arm/kernel/ftrace.c).
@@ -70,26 +67,25 @@
 
 .macro __ftrace_regs_caller
 
-	sub	sp, sp, #8	@ space for PC and CPSR OLD_R0,
+	str	lr, [sp, #-8]!	@ store LR as PC and make space for CPSR/OLD_R0,
 				@ OLD_R0 will overwrite previous LR
 
-	add 	ip, sp, #12	@ move in IP the value of SP as it was
-				@ before the push {lr} of the mcount mechanism
+	ldr	lr, [sp, #8]    @ get previous LR
 
-	str     lr, [sp, #0]    @ store LR instead of PC
+	str	r0, [sp, #8]	@ write r0 as OLD_R0 over previous LR
 
-	ldr     lr, [sp, #8]    @ get previous LR
+	str	lr, [sp, #-4]!	@ store previous LR as LR
 
-	str	r0, [sp, #8]	@ write r0 as OLD_R0 over previous LR
+	add 	lr, sp, #16	@ move in LR the value of SP as it was
+				@ before the push {lr} of the mcount mechanism
 
-	stmdb   sp!, {ip, lr}
-	stmdb   sp!, {r0-r11, lr}
+	push	{r0-r11, ip, lr}
 
 	@ stack content at this point:
 	@ 0  4          48   52       56            60   64    68       72
-	@ R0 | R1 | ... | LR | SP + 4 | previous LR | LR | PSR | OLD_R0 |
+	@ R0 | R1 | ... | IP | SP + 4 | previous LR | LR | PSR | OLD_R0 |
 
-	mov r3, sp				@ struct pt_regs*
+	mov	r3, sp				@ struct pt_regs*
 
 	ldr r2, =function_trace_op
 	ldr r2, [r2]				@ pointer to the current
@@ -112,11 +108,9 @@ ftrace_graph_regs_call:
 #endif
 
 	@ pop saved regs
-	ldmia   sp!, {r0-r12}			@ restore r0 through r12
-	ldr	ip, [sp, #8]			@ restore PC
-	ldr	lr, [sp, #4]			@ restore LR
-	ldr	sp, [sp, #0]			@ restore SP
-	mov	pc, ip				@ return
+	pop	{r0-r11, ip, lr}		@ restore r0 through r12
+	ldr	lr, [sp], #4			@ restore LR
+	ldr	pc, [sp], #12
 .endm
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -132,11 +126,9 @@ ftrace_graph_regs_call:
 	bl	prepare_ftrace_return
 
 	@ pop registers saved in ftrace_regs_caller
-	ldmia   sp!, {r0-r12}			@ restore r0 through r12
-	ldr	ip, [sp, #8]			@ restore PC
-	ldr	lr, [sp, #4]			@ restore LR
-	ldr	sp, [sp, #0]			@ restore SP
-	mov	pc, ip				@ return
+	pop	{r0-r11, ip, lr}		@ restore r0 through r12
+	ldr	lr, [sp], #4			@ restore LR
+	ldr	pc, [sp], #12
 
 .endm
 #endif
@@ -202,16 +194,17 @@ ftrace_graph_call\suffix:
 .endm
 
 .macro mcount_exit
-	ldmia	sp!, {r0-r3, ip, lr}
-	ret	ip
+	ldmia	sp!, {r0-r3}
+	ldr	lr, [sp, #4]
+	ldr	pc, [sp], #8
 .endm
 
 ENTRY(__gnu_mcount_nc)
 UNWIND(.fnstart)
 #ifdef CONFIG_DYNAMIC_FTRACE
-	mov	ip, lr
-	ldmia	sp!, {lr}
-	ret	ip
+	push	{lr}
+	ldr	lr, [sp, #4]
+	ldr	pc, [sp], #8
 #else
 	__mcount
 #endif
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 6166ba38bf99..b74bfcf94fb1 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -195,7 +195,7 @@ static int swp_handler(struct pt_regs *regs, unsigned int instr)
 		 destreg, EXTRACT_REG_NUM(instr, RT2_OFFSET), data);
 
 	/* Check access in reasonable access range for both SWP and SWPB */
-	if (!access_ok((address & ~3), 4)) {
+	if (!access_ok((void __user *)(address & ~3), 4)) {
 		pr_debug("SWP{B} emulation: access to %p not allowed!\n",
 			 (void *)address);
 		res = -EFAULT;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 655c4fe0b4d0..54abd8720dde 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -575,7 +575,7 @@ do_cache_op(unsigned long start, unsigned long end, int flags)
 	if (end < start || flags)
 		return -EINVAL;
 
-	if (!access_ok(start, end - start))
+	if (!access_ok((void __user *)start, end - start))
 		return -EFAULT;
 
 	return __do_cache_op(start, end);
diff --git a/arch/arm/mach-iop32x/include/mach/entry-macro.S b/arch/arm/mach-iop32x/include/mach/entry-macro.S
index 8e6766d4621e..341e5d9a6616 100644
--- a/arch/arm/mach-iop32x/include/mach/entry-macro.S
+++ b/arch/arm/mach-iop32x/include/mach/entry-macro.S
@@ -20,7 +20,7 @@
 	mrc     p6, 0, \irqstat, c8, c0, 0	@ Read IINTSRC
 	cmp     \irqstat, #0
 	clzne   \irqnr, \irqstat
-	rsbne   \irqnr, \irqnr, #31
+	rsbne   \irqnr, \irqnr, #32
 	.endm
 
 	.macro arch_ret_to_user, tmp1, tmp2
diff --git a/arch/arm/mach-iop32x/include/mach/irqs.h b/arch/arm/mach-iop32x/include/mach/irqs.h
index c4e78df428e8..e09ae5f48aec 100644
--- a/arch/arm/mach-iop32x/include/mach/irqs.h
+++ b/arch/arm/mach-iop32x/include/mach/irqs.h
@@ -9,6 +9,6 @@
 #ifndef __IRQS_H
 #define __IRQS_H
 
-#define NR_IRQS			32
+#define NR_IRQS			33
 
 #endif
diff --git a/arch/arm/mach-iop32x/irq.c b/arch/arm/mach-iop32x/irq.c
index 2d48bf1398c1..d1e8824cbd82 100644
--- a/arch/arm/mach-iop32x/irq.c
+++ b/arch/arm/mach-iop32x/irq.c
@@ -32,14 +32,14 @@ static void intstr_write(u32 val)
 static void
 iop32x_irq_mask(struct irq_data *d)
 {
-	iop32x_mask &= ~(1 << d->irq);
+	iop32x_mask &= ~(1 << (d->irq - 1));
 	intctl_write(iop32x_mask);
 }
 
 static void
 iop32x_irq_unmask(struct irq_data *d)
 {
-	iop32x_mask |= 1 << d->irq;
+	iop32x_mask |= 1 << (d->irq - 1);
 	intctl_write(iop32x_mask);
 }
 
@@ -65,7 +65,7 @@ void __init iop32x_init_irq(void)
 	    machine_is_em7210())
 		*IOP3XX_PCIIRSR = 0x0f;
 
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 1; i < NR_IRQS; i++) {
 		irq_set_chip_and_handler(i, &ext_chip, handle_level_irq);
 		irq_clear_status_flags(i, IRQ_NOREQUEST | IRQ_NOPROBE);
 	}
diff --git a/arch/arm/mach-iop32x/irqs.h b/arch/arm/mach-iop32x/irqs.h
index 69858e4e905d..e1dfc8b4e7d7 100644
--- a/arch/arm/mach-iop32x/irqs.h
+++ b/arch/arm/mach-iop32x/irqs.h
@@ -7,36 +7,40 @@
 #ifndef __IOP32X_IRQS_H
 #define __IOP32X_IRQS_H
 
+/* Interrupts in Linux start at 1, hardware starts at 0 */
+
+#define IOP_IRQ(x) ((x) + 1)
+
 /*
  * IOP80321 chipset interrupts
  */
-#define IRQ_IOP32X_DMA0_EOT	0
-#define IRQ_IOP32X_DMA0_EOC	1
-#define IRQ_IOP32X_DMA1_EOT	2
-#define IRQ_IOP32X_DMA1_EOC	3
-#define IRQ_IOP32X_AA_EOT	6
-#define IRQ_IOP32X_AA_EOC	7
-#define IRQ_IOP32X_CORE_PMON	8
-#define IRQ_IOP32X_TIMER0	9
-#define IRQ_IOP32X_TIMER1	10
-#define IRQ_IOP32X_I2C_0	11
-#define IRQ_IOP32X_I2C_1	12
-#define IRQ_IOP32X_MESSAGING	13
-#define IRQ_IOP32X_ATU_BIST	14
-#define IRQ_IOP32X_PERFMON	15
-#define IRQ_IOP32X_CORE_PMU	16
-#define IRQ_IOP32X_BIU_ERR	17
-#define IRQ_IOP32X_ATU_ERR	18
-#define IRQ_IOP32X_MCU_ERR	19
-#define IRQ_IOP32X_DMA0_ERR	20
-#define IRQ_IOP32X_DMA1_ERR	21
-#define IRQ_IOP32X_AA_ERR	23
-#define IRQ_IOP32X_MSG_ERR	24
-#define IRQ_IOP32X_SSP		25
-#define IRQ_IOP32X_XINT0	27
-#define IRQ_IOP32X_XINT1	28
-#define IRQ_IOP32X_XINT2	29
-#define IRQ_IOP32X_XINT3	30
-#define IRQ_IOP32X_HPI		31
+#define IRQ_IOP32X_DMA0_EOT	IOP_IRQ(0)
+#define IRQ_IOP32X_DMA0_EOC	IOP_IRQ(1)
+#define IRQ_IOP32X_DMA1_EOT	IOP_IRQ(2)
+#define IRQ_IOP32X_DMA1_EOC	IOP_IRQ(3)
+#define IRQ_IOP32X_AA_EOT	IOP_IRQ(6)
+#define IRQ_IOP32X_AA_EOC	IOP_IRQ(7)
+#define IRQ_IOP32X_CORE_PMON	IOP_IRQ(8)
+#define IRQ_IOP32X_TIMER0	IOP_IRQ(9)
+#define IRQ_IOP32X_TIMER1	IOP_IRQ(10)
+#define IRQ_IOP32X_I2C_0	IOP_IRQ(11)
+#define IRQ_IOP32X_I2C_1	IOP_IRQ(12)
+#define IRQ_IOP32X_MESSAGING	IOP_IRQ(13)
+#define IRQ_IOP32X_ATU_BIST	IOP_IRQ(14)
+#define IRQ_IOP32X_PERFMON	IOP_IRQ(15)
+#define IRQ_IOP32X_CORE_PMU	IOP_IRQ(16)
+#define IRQ_IOP32X_BIU_ERR	IOP_IRQ(17)
+#define IRQ_IOP32X_ATU_ERR	IOP_IRQ(18)
+#define IRQ_IOP32X_MCU_ERR	IOP_IRQ(19)
+#define IRQ_IOP32X_DMA0_ERR	IOP_IRQ(20)
+#define IRQ_IOP32X_DMA1_ERR	IOP_IRQ(21)
+#define IRQ_IOP32X_AA_ERR	IOP_IRQ(23)
+#define IRQ_IOP32X_MSG_ERR	IOP_IRQ(24)
+#define IRQ_IOP32X_SSP		IOP_IRQ(25)
+#define IRQ_IOP32X_XINT0	IOP_IRQ(27)
+#define IRQ_IOP32X_XINT1	IOP_IRQ(28)
+#define IRQ_IOP32X_XINT2	IOP_IRQ(29)
+#define IRQ_IOP32X_XINT3	IOP_IRQ(30)
+#define IRQ_IOP32X_HPI		IOP_IRQ(31)
 
 #endif
diff --git a/arch/arm/mach-mmp/sram.c b/arch/arm/mach-mmp/sram.c
index 6794e2db1ad5..ecc46c31004f 100644
--- a/arch/arm/mach-mmp/sram.c
+++ b/arch/arm/mach-mmp/sram.c
@@ -72,6 +72,8 @@ static int sram_probe(struct platform_device *pdev)
 	if (!info)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, info);
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
 		dev_err(&pdev->dev, "no memory resource defined\n");
@@ -107,8 +109,6 @@ static int sram_probe(struct platform_device *pdev)
 	list_add(&info->node, &sram_bank_list);
 	mutex_unlock(&sram_lock);
 
-	platform_set_drvdata(pdev, info);
-
 	dev_info(&pdev->dev, "initialized\n");
 	return 0;
 
@@ -127,17 +127,19 @@ static int sram_remove(struct platform_device *pdev)
 	struct sram_bank_info *info;
 
 	info = platform_get_drvdata(pdev);
-	if (info == NULL)
-		return -ENODEV;
 
-	mutex_lock(&sram_lock);
-	list_del(&info->node);
-	mutex_unlock(&sram_lock);
+	if (info->sram_size) {
+		mutex_lock(&sram_lock);
+		list_del(&info->node);
+		mutex_unlock(&sram_lock);
+
+		gen_pool_destroy(info->gpool);
+		iounmap(info->sram_virt);
+		kfree(info->pool_name);
+	}
 
-	gen_pool_destroy(info->gpool);
-	iounmap(info->sram_virt);
-	kfree(info->pool_name);
 	kfree(info);
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-mstar/Kconfig b/arch/arm/mach-mstar/Kconfig
index cd300eeedc20..0bf4d312bcfd 100644
--- a/arch/arm/mach-mstar/Kconfig
+++ b/arch/arm/mach-mstar/Kconfig
@@ -3,6 +3,7 @@ menuconfig ARCH_MSTARV7
 	depends on ARCH_MULTI_V7
 	select ARM_GIC
 	select ARM_HEAVY_MB
+	select HAVE_ARM_ARCH_TIMER
 	select MST_IRQ
 	select MSTAR_MSC313_MPLL
 	help
diff --git a/arch/arm/mach-s3c/mach-jive.c b/arch/arm/mach-s3c/mach-jive.c
index 0785638a9069..7d15b84ae217 100644
--- a/arch/arm/mach-s3c/mach-jive.c
+++ b/arch/arm/mach-s3c/mach-jive.c
@@ -236,11 +236,11 @@ static int __init jive_mtdset(char *options)
 	unsigned long set;
 
 	if (options == NULL || options[0] == '\0')
-		return 0;
+		return 1;
 
 	if (kstrtoul(options, 10, &set)) {
 		printk(KERN_ERR "failed to parse mtdset=%s\n", options);
-		return 0;
+		return 1;
 	}
 
 	switch (set) {
@@ -255,7 +255,7 @@ static int __init jive_mtdset(char *options)
 		       "using default.", set);
 	}
 
-	return 0;
+	return 1;
 }
 
 /* parse the mtdset= option given to the kernel command line */
diff --git a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi
index 5118816b1ed7..e8907d3fe2d1 100644
--- a/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm4908/bcm4908.dtsi
@@ -273,9 +273,9 @@
 		#size-cells = <1>;
 		ranges = <0x00 0x00 0xff800000 0x3000>;
 
-		timer: timer@400 {
-			compatible = "brcm,bcm6328-timer", "syscon";
-			reg = <0x400 0x3c>;
+		twd: timer-mfd@400 {
+			compatible = "brcm,bcm4908-twd", "simple-mfd", "syscon";
+			reg = <0x400 0x4c>;
 		};
 
 		gpio0: gpio-controller@500 {
@@ -330,7 +330,7 @@
 
 	reboot {
 		compatible = "syscon-reboot";
-		regmap = <&timer>;
+		regmap = <&twd>;
 		offset = <0x34>;
 		mask = <1>;
 	};
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/northstar2/ns2-svk.dts
index ec19fbf928a1..12a4b1c03390 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2-svk.dts
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2-svk.dts
@@ -111,8 +111,8 @@
 		compatible = "silabs,si3226x";
 		reg = <0>;
 		spi-max-frequency = <5000000>;
-		spi-cpha = <1>;
-		spi-cpol = <1>;
+		spi-cpha;
+		spi-cpol;
 		pl022,hierarchy = <0>;
 		pl022,interface = <0>;
 		pl022,slave-tx-disable = <0>;
@@ -135,8 +135,8 @@
 		at25,byte-len = <0x8000>;
 		at25,addr-mode = <2>;
 		at25,page-size = <64>;
-		spi-cpha = <1>;
-		spi-cpol = <1>;
+		spi-cpha;
+		spi-cpol;
 		pl022,hierarchy = <0>;
 		pl022,interface = <0>;
 		pl022,slave-tx-disable = <0>;
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 2cfeaf3b0a87..8c218689fef7 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -687,7 +687,7 @@
 			};
 		};
 
-		sata: ahci@663f2000 {
+		sata: sata@663f2000 {
 			compatible = "brcm,iproc-ahci", "generic-ahci";
 			reg = <0x663f2000 0x1000>;
 			dma-coherent;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 01b01e320411..35d1939e690b 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -536,9 +536,9 @@
 			clock-names = "i2c";
 			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
 					    QORIQ_CLK_PLL_DIV(1)>;
-			dmas = <&edma0 1 39>,
-			       <&edma0 1 38>;
-			dma-names = "tx", "rx";
+			dmas = <&edma0 1 38>,
+			       <&edma0 1 39>;
+			dma-names = "rx", "tx";
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index 687fea6d8afa..4e7bd04d9798 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -499,9 +499,9 @@
 			interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
 					    QORIQ_CLK_PLL_DIV(2)>;
-			dmas = <&edma0 1 39>,
-			       <&edma0 1 38>;
-			dma-names = "tx", "rx";
+			dmas = <&edma0 1 38>,
+			       <&edma0 1 39>;
+			dma-names = "rx", "tx";
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index 519ca9a705b4..d20eacfc1017 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -3608,10 +3608,10 @@
 					#clock-cells = <0>;
 					clock-frequency = <9600000>;
 					clock-output-names = "mclk";
-					qcom,micbias1-millivolt = <1800>;
-					qcom,micbias2-millivolt = <1800>;
-					qcom,micbias3-millivolt = <1800>;
-					qcom,micbias4-millivolt = <1800>;
+					qcom,micbias1-microvolt = <1800000>;
+					qcom,micbias2-microvolt = <1800000>;
+					qcom,micbias3-microvolt = <1800000>;
+					qcom,micbias4-microvolt = <1800000>;
 
 					#address-cells = <1>;
 					#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi
index ef0232c2cf45..f347f752d536 100644
--- a/arch/arm64/boot/dts/qcom/sm8150.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi
@@ -3434,9 +3434,9 @@
 			qcom,tcs-offset = <0xd00>;
 			qcom,drv-id = <2>;
 			qcom,tcs-config = <ACTIVE_TCS  2>,
-					  <SLEEP_TCS   1>,
-					  <WAKE_TCS    1>,
-					  <CONTROL_TCS 0>;
+					  <SLEEP_TCS   3>,
+					  <WAKE_TCS    3>,
+					  <CONTROL_TCS 1>;
 
 			rpmhcc: clock-controller {
 				compatible = "qcom,sm8150-rpmh-clk";
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index d12e4cbfc852..2786e2c8e565 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -1434,8 +1434,8 @@
 			phys = <&pcie0_lane>;
 			phy-names = "pciephy";
 
-			perst-gpio = <&tlmm 79 GPIO_ACTIVE_LOW>;
-			enable-gpio = <&tlmm 81 GPIO_ACTIVE_HIGH>;
+			perst-gpios = <&tlmm 79 GPIO_ACTIVE_LOW>;
+			wake-gpios = <&tlmm 81 GPIO_ACTIVE_HIGH>;
 
 			pinctrl-names = "default";
 			pinctrl-0 = <&pcie0_default_state>;
@@ -1495,7 +1495,7 @@
 			ranges = <0x01000000 0x0 0x40200000 0x0 0x40200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>;
 
-			interrupts = <GIC_SPI 306 IRQ_TYPE_EDGE_RISING>;
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
@@ -1538,8 +1538,8 @@
 			phys = <&pcie1_lane>;
 			phy-names = "pciephy";
 
-			perst-gpio = <&tlmm 82 GPIO_ACTIVE_LOW>;
-			enable-gpio = <&tlmm 84 GPIO_ACTIVE_HIGH>;
+			perst-gpios = <&tlmm 82 GPIO_ACTIVE_LOW>;
+			wake-gpios = <&tlmm 84 GPIO_ACTIVE_HIGH>;
 
 			pinctrl-names = "default";
 			pinctrl-0 = <&pcie1_default_state>;
@@ -1601,7 +1601,7 @@
 			ranges = <0x01000000 0x0 0x64200000 0x0 0x64200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x64300000 0x0 0x64300000 0x0 0x3d00000>;
 
-			interrupts = <GIC_SPI 236 IRQ_TYPE_EDGE_RISING>;
+			interrupts = <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
@@ -1644,8 +1644,8 @@
 			phys = <&pcie2_lane>;
 			phy-names = "pciephy";
 
-			perst-gpio = <&tlmm 85 GPIO_ACTIVE_LOW>;
-			enable-gpio = <&tlmm 87 GPIO_ACTIVE_HIGH>;
+			perst-gpios = <&tlmm 85 GPIO_ACTIVE_LOW>;
+			wake-gpios = <&tlmm 87 GPIO_ACTIVE_HIGH>;
 
 			pinctrl-names = "default";
 			pinctrl-0 = <&pcie2_default_state>;
diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi
index a8886adaaf37..3d32d5581816 100644
--- a/arch/arm64/boot/dts/qcom/sm8350.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi
@@ -979,7 +979,7 @@
 			qcom,tcs-offset = <0xd00>;
 			qcom,drv-id = <2>;
 			qcom,tcs-config = <ACTIVE_TCS  2>, <SLEEP_TCS   3>,
-					  <WAKE_TCS    3>, <CONTROL_TCS 1>;
+					  <WAKE_TCS    3>, <CONTROL_TCS 0>;
 
 			rpmhcc: clock-controller {
 				compatible = "qcom,sm8350-rpmh-clk";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
index c4dd2a6b4836..f81ce3240342 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
@@ -770,8 +770,8 @@
 	sd-uhs-sdr104;
 
 	/* Power supply */
-	vqmmc-supply = &vcc1v8_s3;	/* IO line */
-	vmmc-supply = &vcc_sdio;	/* card's power */
+	vqmmc-supply = <&vcc1v8_s3>;	/* IO line */
+	vmmc-supply = <&vcc_sdio>;	/* card's power */
 
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
index 42d1d219a3fd..86291f3469f1 100644
--- a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
@@ -59,7 +59,10 @@
 		#interrupt-cells = <3>;
 		interrupt-controller;
 		reg = <0x00 0x01800000 0x00 0x10000>,	/* GICD */
-		      <0x00 0x01840000 0x00 0xC0000>;	/* GICR */
+		      <0x00 0x01840000 0x00 0xC0000>,	/* GICR */
+		      <0x01 0x00000000 0x00 0x2000>,	/* GICC */
+		      <0x01 0x00010000 0x00 0x1000>,	/* GICH */
+		      <0x01 0x00020000 0x00 0x2000>;	/* GICV */
 		/*
 		 * vcpumntirq:
 		 * virtual CPU interface maintenance interrupt
diff --git a/arch/arm64/boot/dts/ti/k3-am64.dtsi b/arch/arm64/boot/dts/ti/k3-am64.dtsi
index de6805b0c72c..e589c58f6088 100644
--- a/arch/arm64/boot/dts/ti/k3-am64.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64.dtsi
@@ -85,6 +85,7 @@
 			 <0x00 0x68000000 0x00 0x68000000 0x00 0x08000000>, /* PCIe DAT0 */
 			 <0x00 0x70000000 0x00 0x70000000 0x00 0x00200000>, /* OC SRAM */
 			 <0x00 0x78000000 0x00 0x78000000 0x00 0x00800000>, /* Main R5FSS */
+			 <0x01 0x00000000 0x01 0x00000000 0x00 0x00310000>, /* A53 PERIPHBASE */
 			 <0x06 0x00000000 0x06 0x00000000 0x01 0x00000000>, /* PCIe DAT1 */
 			 <0x05 0x00000000 0x05 0x00000000 0x01 0x00000000>, /* FSS0 DAT3 */
 
diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
index ba4e5d3e1ed7..82be00069bcd 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
@@ -35,7 +35,10 @@
 		#interrupt-cells = <3>;
 		interrupt-controller;
 		reg = <0x00 0x01800000 0x00 0x10000>,	/* GICD */
-		      <0x00 0x01880000 0x00 0x90000>;	/* GICR */
+		      <0x00 0x01880000 0x00 0x90000>,	/* GICR */
+		      <0x00 0x6f000000 0x00 0x2000>,	/* GICC */
+		      <0x00 0x6f010000 0x00 0x1000>,	/* GICH */
+		      <0x00 0x6f020000 0x00 0x2000>;	/* GICV */
 		/*
 		 * vcpumntirq:
 		 * virtual CPU interface maintenance interrupt
diff --git a/arch/arm64/boot/dts/ti/k3-am65.dtsi b/arch/arm64/boot/dts/ti/k3-am65.dtsi
index a9fc1af03f27..1607db9b32dd 100644
--- a/arch/arm64/boot/dts/ti/k3-am65.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65.dtsi
@@ -84,6 +84,7 @@
 			 <0x00 0x46000000 0x00 0x46000000 0x00 0x00200000>,
 			 <0x00 0x47000000 0x00 0x47000000 0x00 0x00068400>,
 			 <0x00 0x50000000 0x00 0x50000000 0x00 0x8000000>,
+			 <0x00 0x6f000000 0x00 0x6f000000 0x00 0x00310000>, /* A53 PERIPHBASE */
 			 <0x00 0x70000000 0x00 0x70000000 0x00 0x200000>,
 			 <0x05 0x00000000 0x05 0x00000000 0x01 0x0000000>,
 			 <0x07 0x00000000 0x07 0x00000000 0x01 0x0000000>;
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
index 7daa28022044..000b5732ea0c 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
@@ -54,7 +54,10 @@
 		#interrupt-cells = <3>;
 		interrupt-controller;
 		reg = <0x00 0x01800000 0x00 0x10000>,	/* GICD */
-		      <0x00 0x01900000 0x00 0x100000>;	/* GICR */
+		      <0x00 0x01900000 0x00 0x100000>,	/* GICR */
+		      <0x00 0x6f000000 0x00 0x2000>,	/* GICC */
+		      <0x00 0x6f010000 0x00 0x1000>,	/* GICH */
+		      <0x00 0x6f020000 0x00 0x2000>;	/* GICV */
 
 		/* vcpumntirq: virtual CPU interface maintenance interrupt */
 		interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/ti/k3-j7200.dtsi b/arch/arm64/boot/dts/ti/k3-j7200.dtsi
index 7586b5aea446..afe99f3920cc 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200.dtsi
@@ -127,6 +127,7 @@
 			 <0x00 0x00a40000 0x00 0x00a40000 0x00 0x00000800>, /* timesync router */
 			 <0x00 0x01000000 0x00 0x01000000 0x00 0x0d000000>, /* Most peripherals */
 			 <0x00 0x30000000 0x00 0x30000000 0x00 0x0c400000>, /* MAIN NAVSS */
+			 <0x00 0x6f000000 0x00 0x6f000000 0x00 0x00310000>, /* A72 PERIPHBASE */
 			 <0x00 0x70000000 0x00 0x70000000 0x00 0x00800000>, /* MSMC RAM */
 			 <0x00 0x18000000 0x00 0x18000000 0x00 0x08000000>, /* PCIe1 DAT0 */
 			 <0x41 0x00000000 0x41 0x00000000 0x01 0x00000000>, /* PCIe1 DAT1 */
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
index e85c89eebfa3..6c81997ee28a 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
@@ -76,7 +76,10 @@
 		#interrupt-cells = <3>;
 		interrupt-controller;
 		reg = <0x00 0x01800000 0x00 0x10000>,	/* GICD */
-		      <0x00 0x01900000 0x00 0x100000>;	/* GICR */
+		      <0x00 0x01900000 0x00 0x100000>,	/* GICR */
+		      <0x00 0x6f000000 0x00 0x2000>,	/* GICC */
+		      <0x00 0x6f010000 0x00 0x1000>,	/* GICH */
+		      <0x00 0x6f020000 0x00 0x2000>;	/* GICV */
 
 		/* vcpumntirq: virtual CPU interface maintenance interrupt */
 		interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e.dtsi b/arch/arm64/boot/dts/ti/k3-j721e.dtsi
index 69ce048a2136..2cd8883de5b5 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e.dtsi
@@ -136,6 +136,7 @@
 			 <0x00 0x0e000000 0x00 0x0e000000 0x00 0x01800000>, /* PCIe Core*/
 			 <0x00 0x10000000 0x00 0x10000000 0x00 0x10000000>, /* PCIe DAT */
 			 <0x00 0x64800000 0x00 0x64800000 0x00 0x00800000>, /* C71 */
+			 <0x00 0x6f000000 0x00 0x6f000000 0x00 0x00310000>, /* A72 PERIPHBASE */
 			 <0x44 0x00000000 0x44 0x00000000 0x00 0x08000000>, /* PCIe2 DAT */
 			 <0x44 0x10000000 0x44 0x10000000 0x00 0x08000000>, /* PCIe3 DAT */
 			 <0x4d 0x80800000 0x4d 0x80800000 0x00 0x00800000>, /* C66_0 */
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 545197bc0501..4972a81d40d6 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -921,7 +921,7 @@ CONFIG_DMADEVICES=y
 CONFIG_DMA_BCM2835=y
 CONFIG_DMA_SUN6I=m
 CONFIG_FSL_EDMA=y
-CONFIG_IMX_SDMA=y
+CONFIG_IMX_SDMA=m
 CONFIG_K3_DMA=y
 CONFIG_MV_XOR=y
 CONFIG_MV_XOR_V2=y
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index bfbf0c4c7c5e..39f5c1672f48 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
 #define ARM_CPU_PART_NEOVERSE_V1	0xD40
 #define ARM_CPU_PART_CORTEX_A78		0xD41
+#define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
 #define ARM_CPU_PART_CORTEX_A710	0xD47
@@ -123,6 +124,7 @@
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
 #define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
 #define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
index a11ccadd47d2..094701ec5500 100644
--- a/arch/arm64/include/asm/module.lds.h
+++ b/arch/arm64/include/asm/module.lds.h
@@ -1,8 +1,8 @@
 SECTIONS {
 #ifdef CONFIG_ARM64_MODULE_PLTS
-	.plt 0 (NOLOAD) : { BYTE(0) }
-	.init.plt 0 (NOLOAD) : { BYTE(0) }
-	.text.ftrace_trampoline 0 (NOLOAD) : { BYTE(0) }
+	.plt 0 : { BYTE(0) }
+	.init.plt 0 : { BYTE(0) }
+	.text.ftrace_trampoline 0 : { BYTE(0) }
 #endif
 
 #ifdef CONFIG_KASAN_SW_TAGS
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index 86e0cc9b9c68..aa3d3607d5c8 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -67,7 +67,8 @@ struct bp_hardening_data {
 
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
-static inline void arm64_apply_bp_hardening(void)
+/* Called during entry so must be __always_inline */
+static __always_inline void arm64_apply_bp_hardening(void)
 {
 	struct bp_hardening_data *d;
 
diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h
index f64613a96d53..bc9a2145f419 100644
--- a/arch/arm64/include/asm/vectors.h
+++ b/arch/arm64/include/asm/vectors.h
@@ -56,14 +56,14 @@ enum arm64_bp_harden_el1_vectors {
 DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector);
 
 #ifndef CONFIG_UNMAP_KERNEL_AT_EL0
-#define TRAMP_VALIAS	0
+#define TRAMP_VALIAS	0ul
 #endif
 
 static inline const char *
 arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot)
 {
 	if (arm64_kernel_unmapped_at_el0())
-		return (char *)TRAMP_VALIAS + SZ_2K * slot;
+		return (char *)(TRAMP_VALIAS + SZ_2K * slot);
 
 	WARN_ON_ONCE(slot == EL1_VECTOR_KPTI);
 
diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c
index 771f543464e0..33e0fabc0b79 100644
--- a/arch/arm64/kernel/patching.c
+++ b/arch/arm64/kernel/patching.c
@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 	int i, ret = 0;
 	struct aarch64_insn_patch *pp = arg;
 
-	/* The first CPU becomes master */
-	if (atomic_inc_return(&pp->cpu_count) == 1) {
+	/* The last CPU becomes master */
+	if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) {
 		for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
 			ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
 							     pp->new_insns[i]);
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index 6d45c63c6454..40be3a7c2c53 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -233,17 +233,20 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn)
 	__this_cpu_write(bp_hardening_data.slot, HYP_VECTOR_SPECTRE_DIRECT);
 }
 
-static void call_smc_arch_workaround_1(void)
+/* Called during entry so must be noinstr */
+static noinstr void call_smc_arch_workaround_1(void)
 {
 	arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
 }
 
-static void call_hvc_arch_workaround_1(void)
+/* Called during entry so must be noinstr */
+static noinstr void call_hvc_arch_workaround_1(void)
 {
 	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
 }
 
-static void qcom_link_stack_sanitisation(void)
+/* Called during entry so must be noinstr */
+static noinstr void qcom_link_stack_sanitisation(void)
 {
 	u64 tmp;
 
@@ -850,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope)
 	if (scope == SCOPE_LOCAL_CPU) {
 		static const struct midr_range spectre_bhb_k32_list[] = {
 			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
 			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
 			MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
 			MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index c287b9407f28..981f0c4157c2 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -577,10 +577,12 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 {
 	int err;
 
-	err = sigframe_alloc(user, &user->fpsimd_offset,
-			     sizeof(struct fpsimd_context));
-	if (err)
-		return err;
+	if (system_supports_fpsimd()) {
+		err = sigframe_alloc(user, &user->fpsimd_offset,
+				     sizeof(struct fpsimd_context));
+		if (err)
+			return err;
+	}
 
 	/* fault information, if valid */
 	if (add_all || current->thread.fault_code) {
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 6f6ff072acbd..3beaa6640ab3 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void)
 	 * Log the CPU info before it is marked online and might get read.
 	 */
 	cpuinfo_store_cpu();
+	store_cpu_topology(cpu);
 
 	/*
 	 * Enable GIC and timers.
@@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void)
 
 	ipi_setup(cpu);
 
-	store_cpu_topology(cpu);
 	numa_add_cpu(cpu);
 
 	/*
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 37a81754d9b6..c59cb2efd554 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -61,8 +61,34 @@ EXPORT_SYMBOL(memstart_addr);
  * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
  * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
  * otherwise it is empty.
+ *
+ * Memory reservation for crash kernel either done early or deferred
+ * depending on DMA memory zones configs (ZONE_DMA) --
+ *
+ * In absence of ZONE_DMA configs arm64_dma_phys_limit initialized
+ * here instead of max_zone_phys().  This lets early reservation of
+ * crash kernel memory which has a dependency on arm64_dma_phys_limit.
+ * Reserving memory early for crash kernel allows linear creation of block
+ * mappings (greater than page-granularity) for all the memory bank rangs.
+ * In this scheme a comparatively quicker boot is observed.
+ *
+ * If ZONE_DMA configs are defined, crash kernel memory reservation
+ * is delayed until DMA zone memory range size initilazation performed in
+ * zone_sizes_init().  The defer is necessary to steer clear of DMA zone
+ * memory range to avoid overlap allocation.  So crash kernel memory boundaries
+ * are not known when mapping all bank memory ranges, which otherwise means
+ * not possible to exclude crash kernel range from creating block mappings
+ * so page-granularity mappings are created for the entire memory range.
+ * Hence a slightly slower boot is observed.
+ *
+ * Note: Page-granularity mapppings are necessary for crash kernel memory
+ * range for shrinking its size via /sys/kernel/kexec_crash_size interface.
  */
-phys_addr_t arm64_dma_phys_limit __ro_after_init;
+#if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32)
+phys_addr_t __ro_after_init arm64_dma_phys_limit;
+#else
+phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
+#endif
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -153,8 +179,6 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	if (!arm64_dma_phys_limit)
 		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
-	if (!arm64_dma_phys_limit)
-		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -352,6 +376,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
+	if (!IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32))
+		reserve_crashkernel();
+
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 }
 
@@ -398,7 +425,8 @@ void __init bootmem_init(void)
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
-	reserve_crashkernel();
+	if (IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32))
+		reserve_crashkernel();
 
 	memblock_dump_all();
 }
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 9d0380631690..6680689242df 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -63,6 +63,7 @@ static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
 static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
 
 static DEFINE_SPINLOCK(swapper_pgdir_lock);
+static DEFINE_MUTEX(fixmap_lock);
 
 void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
 {
@@ -328,6 +329,12 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	}
 	BUG_ON(p4d_bad(p4d));
 
+	/*
+	 * No need for locking during early boot. And it doesn't work as
+	 * expected with KASLR enabled.
+	 */
+	if (system_state != SYSTEM_BOOTING)
+		mutex_lock(&fixmap_lock);
 	pudp = pud_set_fixmap_offset(p4dp, addr);
 	do {
 		pud_t old_pud = READ_ONCE(*pudp);
@@ -358,6 +365,8 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	} while (pudp++, addr = next, addr != end);
 
 	pud_clear_fixmap();
+	if (system_state != SYSTEM_BOOTING)
+		mutex_unlock(&fixmap_lock);
 }
 
 static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
@@ -516,7 +525,7 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end));
 
-	if (can_set_direct_map() || crash_mem_map || IS_ENABLED(CONFIG_KFENCE))
+	if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	/*
@@ -527,6 +536,17 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
 
+#ifdef CONFIG_KEXEC_CORE
+	if (crash_mem_map) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA) ||
+		    IS_ENABLED(CONFIG_ZONE_DMA32))
+			flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+		else if (crashk_res.end)
+			memblock_mark_nomap(crashk_res.start,
+			    resource_size(&crashk_res));
+	}
+#endif
+
 	/* map all the memory banks */
 	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
@@ -553,6 +573,25 @@ static void __init map_mem(pgd_t *pgdp)
 	__map_memblock(pgdp, kernel_start, kernel_end,
 		       PAGE_KERNEL, NO_CONT_MAPPINGS);
 	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
+
+	/*
+	 * Use page-level mappings here so that we can shrink the region
+	 * in page granularity and put back unused memory to buddy system
+	 * through /sys/kernel/kexec_crash_size interface.
+	 */
+#ifdef CONFIG_KEXEC_CORE
+	if (crash_mem_map &&
+	    !IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32)) {
+		if (crashk_res.end) {
+			__map_memblock(pgdp, crashk_res.start,
+				       crashk_res.end + 1,
+				       PAGE_KERNEL,
+				       NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+			memblock_clear_nomap(crashk_res.start,
+					     resource_size(&crashk_res));
+		}
+	}
+#endif
 }
 
 void mark_rodata_ro(void)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 465c44d0c72f..b56e7bd96594 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1042,15 +1042,18 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto out_off;
 	}
 
-	/* 1. Initial fake pass to compute ctx->idx. */
-
-	/* Fake pass to fill in ctx->offset. */
-	if (build_body(&ctx, extra_pass)) {
+	/*
+	 * 1. Initial fake pass to compute ctx->idx and ctx->offset.
+	 *
+	 * BPF line info needs ctx->offset[i] to be the offset of
+	 * instruction[i] in jited image, so build prologue first.
+	 */
+	if (build_prologue(&ctx, was_classic)) {
 		prog = orig_prog;
 		goto out_off;
 	}
 
-	if (build_prologue(&ctx, was_classic)) {
+	if (build_body(&ctx, extra_pass)) {
 		prog = orig_prog;
 		goto out_off;
 	}
@@ -1123,6 +1126,11 @@ skip_init_ctx:
 	prog->jited_len = prog_size;
 
 	if (!prog->is_func || extra_pass) {
+		int i;
+
+		/* offset[prog->len] is the size of program */
+		for (i = 0; i <= prog->len; i++)
+			ctx.offset[i] *= AARCH64_INSN_SIZE;
 		bpf_prog_fill_jited_linfo(prog, ctx.offset + 1);
 out_off:
 		kfree(ctx.offset);
diff --git a/arch/csky/include/asm/uaccess.h b/arch/csky/include/asm/uaccess.h
index c40f06ee8d3e..ac5a54f57d40 100644
--- a/arch/csky/include/asm/uaccess.h
+++ b/arch/csky/include/asm/uaccess.h
@@ -3,14 +3,13 @@
 #ifndef __ASM_CSKY_UACCESS_H
 #define __ASM_CSKY_UACCESS_H
 
-#define user_addr_max() \
-	(uaccess_kernel() ? KERNEL_DS.seg : get_fs().seg)
+#define user_addr_max() (current_thread_info()->addr_limit.seg)
 
 static inline int __access_ok(unsigned long addr, unsigned long size)
 {
-	unsigned long limit = current_thread_info()->addr_limit.seg;
+	unsigned long limit = user_addr_max();
 
-	return ((addr < limit) && ((addr + size) < limit));
+	return (size <= limit) && (addr <= (limit - size));
 }
 #define __access_ok __access_ok
 
diff --git a/arch/csky/kernel/perf_callchain.c b/arch/csky/kernel/perf_callchain.c
index 35318a635a5f..75e1f9df5f60 100644
--- a/arch/csky/kernel/perf_callchain.c
+++ b/arch/csky/kernel/perf_callchain.c
@@ -49,7 +49,7 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
 {
 	struct stackframe buftail;
 	unsigned long lr = 0;
-	unsigned long *user_frame_tail = (unsigned long *)fp;
+	unsigned long __user *user_frame_tail = (unsigned long __user *)fp;
 
 	/* Check accessibility of one struct frame_tail beyond */
 	if (!access_ok(user_frame_tail, sizeof(buftail)))
diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c
index c7b763d2f526..8867ddf3e6c7 100644
--- a/arch/csky/kernel/signal.c
+++ b/arch/csky/kernel/signal.c
@@ -136,7 +136,7 @@ static inline void __user *get_sigframe(struct ksignal *ksig,
 static int
 setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
 {
-	struct rt_sigframe *frame;
+	struct rt_sigframe __user *frame;
 	int err = 0;
 
 	frame = get_sigframe(ksig, regs, sizeof(*frame));
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index ef5bfef8d490..719ba3f3c45c 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -25,17 +25,17 @@
  * Returns true (nonzero) if the memory block *may* be valid, false (zero)
  * if it is definitely invalid.
  *
- * User address space in Hexagon, like x86, goes to 0xbfffffff, so the
- * simple MSB-based tests used by MIPS won't work.  Some further
- * optimization is probably possible here, but for now, keep it
- * reasonably simple and not *too* slow.  After all, we've got the
- * MMU for backup.
  */
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
+#define user_addr_max() (uaccess_kernel() ? ~0UL : TASK_SIZE)
 
-#define __access_ok(addr, size) \
-	((get_fs().seg == KERNEL_DS.seg) || \
-	(((unsigned long)addr < get_fs().seg) && \
-	  (unsigned long)size < (get_fs().seg - (unsigned long)addr)))
+static inline int __access_ok(unsigned long addr, unsigned long size)
+{
+	unsigned long limit = TASK_SIZE;
+
+	return (size <= limit) && (addr <= (limit - size));
+}
+#define __access_ok __access_ok
 
 /*
  * When a kernel-mode page fault is taken, the faulting instruction
diff --git a/arch/m68k/coldfire/device.c b/arch/m68k/coldfire/device.c
index 0386252e9d04..4218750414bb 100644
--- a/arch/m68k/coldfire/device.c
+++ b/arch/m68k/coldfire/device.c
@@ -480,7 +480,7 @@ static struct platform_device mcf_i2c5 = {
 #endif /* MCFI2C_BASE5 */
 #endif /* IS_ENABLED(CONFIG_I2C_IMX) */
 
-#if IS_ENABLED(CONFIG_MCF_EDMA)
+#ifdef MCFEDMA_BASE
 
 static const struct dma_slave_map mcf_edma_map[] = {
 	{ "dreq0", "rx-tx", MCF_EDMA_FILTER_PARAM(0) },
@@ -552,7 +552,7 @@ static struct platform_device mcf_edma = {
 		.platform_data = &mcf_edma_data,
 	}
 };
-#endif /* IS_ENABLED(CONFIG_MCF_EDMA) */
+#endif /* MCFEDMA_BASE */
 
 #ifdef MCFSDHC_BASE
 static struct mcf_esdhc_platform_data mcf_esdhc_data = {
@@ -651,7 +651,7 @@ static struct platform_device *mcf_devices[] __initdata = {
 	&mcf_i2c5,
 #endif
 #endif
-#if IS_ENABLED(CONFIG_MCF_EDMA)
+#ifdef MCFEDMA_BASE
 	&mcf_edma,
 #endif
 #ifdef MCFSDHC_BASE
diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h
index ba670523885c..60b786eb2254 100644
--- a/arch/m68k/include/asm/uaccess.h
+++ b/arch/m68k/include/asm/uaccess.h
@@ -12,14 +12,17 @@
 #include <asm/extable.h>
 
 /* We let the MMU do all checking */
-static inline int access_ok(const void __user *addr,
+static inline int access_ok(const void __user *ptr,
 			    unsigned long size)
 {
-	/*
-	 * XXX: for !CONFIG_CPU_HAS_ADDRESS_SPACES this really needs to check
-	 * for TASK_SIZE!
-	 */
-	return 1;
+	unsigned long limit = TASK_SIZE;
+	unsigned long addr = (unsigned long)ptr;
+
+	if (IS_ENABLED(CONFIG_CPU_HAS_ADDRESS_SPACES) ||
+	    !IS_ENABLED(CONFIG_MMU))
+		return 1;
+
+	return (size <= limit) && (addr <= (limit - size));
 }
 
 /*
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index d2a8ef9f8978..3fe96979d2c6 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -39,24 +39,13 @@
 
 # define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
-static inline int access_ok(const void __user *addr, unsigned long size)
+static inline int __access_ok(unsigned long addr, unsigned long size)
 {
-	if (!size)
-		goto ok;
+	unsigned long limit = user_addr_max();
 
-	if ((get_fs().seg < ((unsigned long)addr)) ||
-			(get_fs().seg < ((unsigned long)addr + size - 1))) {
-		pr_devel("ACCESS fail at 0x%08x (size 0x%x), seg 0x%08x\n",
-			(__force u32)addr, (u32)size,
-			(u32)get_fs().seg);
-		return 0;
-	}
-ok:
-	pr_devel("ACCESS OK at 0x%08x (size 0x%x), seg 0x%08x\n",
-			(__force u32)addr, (u32)size,
-			(u32)get_fs().seg);
-	return 1;
+	return (size <= limit) && (addr <= (limit - size));
 }
+#define access_ok(addr, size) __access_ok((unsigned long)addr, size)
 
 # define __FIXUP_SECTION	".section .fixup,\"ax\"\n"
 # define __EX_TABLE_SECTION	".section __ex_table,\"a\"\n"
@@ -141,27 +130,27 @@ extern long __user_bad(void);
 
 #define __get_user(x, ptr)						\
 ({									\
-	unsigned long __gu_val = 0;					\
 	long __gu_err;							\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
-		__get_user_asm("lbu", (ptr), __gu_val, __gu_err);	\
+		__get_user_asm("lbu", (ptr), x, __gu_err);		\
 		break;							\
 	case 2:								\
-		__get_user_asm("lhu", (ptr), __gu_val, __gu_err);	\
+		__get_user_asm("lhu", (ptr), x, __gu_err);		\
 		break;							\
 	case 4:								\
-		__get_user_asm("lw", (ptr), __gu_val, __gu_err);	\
+		__get_user_asm("lw", (ptr), x, __gu_err);		\
 		break;							\
-	case 8:								\
-		__gu_err = __copy_from_user(&__gu_val, ptr, 8);		\
-		if (__gu_err)						\
-			__gu_err = -EFAULT;				\
+	case 8: {							\
+		__u64 __x = 0;						\
+		__gu_err = raw_copy_from_user(&__x, ptr, 8) ?		\
+							-EFAULT : 0;	\
+		(x) = (typeof(x))(typeof((x) - (x)))__x;		\
 		break;							\
+	}								\
 	default:							\
 		/* __gu_val = 0; __gu_err = -EINVAL;*/ __gu_err = __user_bad();\
 	}								\
-	x = (__force __typeof__(*(ptr))) __gu_val;			\
 	__gu_err;							\
 })
 
diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index 9e34f433b9b5..efbbddaf0fde 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -450,7 +450,7 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
-			eth0_addr: eth-mac-addr@0x22 {
+			eth0_addr: eth-mac-addr@22 {
 				reg = <0x22 0x6>;
 			};
 		};
diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S
index ea5b5a83f1e1..011d1d678840 100644
--- a/arch/mips/dec/int-handler.S
+++ b/arch/mips/dec/int-handler.S
@@ -131,7 +131,7 @@
 		 */
 		mfc0	t0,CP0_CAUSE		# get pending interrupts
 		mfc0	t1,CP0_STATUS
-#ifdef CONFIG_32BIT
+#if defined(CONFIG_32BIT) && defined(CONFIG_MIPS_FP_SUPPORT)
 		lw	t2,cpu_fpu_mask
 #endif
 		andi	t0,ST0_IM		# CAUSE.CE may be non-zero!
@@ -139,7 +139,7 @@
 
 		beqz	t0,spurious
 
-#ifdef CONFIG_32BIT
+#if defined(CONFIG_32BIT) && defined(CONFIG_MIPS_FP_SUPPORT)
 		 and	t2,t0
 		bnez	t2,fpu			# handle FPU immediately
 #endif
@@ -280,7 +280,7 @@ handle_it:
 		j	dec_irq_dispatch
 		 nop
 
-#ifdef CONFIG_32BIT
+#if defined(CONFIG_32BIT) && defined(CONFIG_MIPS_FP_SUPPORT)
 fpu:
 		lw	t0,fpu_kstat_irq
 		nop
diff --git a/arch/mips/dec/prom/Makefile b/arch/mips/dec/prom/Makefile
index d95016016b42..2bad87551203 100644
--- a/arch/mips/dec/prom/Makefile
+++ b/arch/mips/dec/prom/Makefile
@@ -6,4 +6,4 @@
 
 lib-y			+= init.o memory.o cmdline.o identify.o console.o
 
-lib-$(CONFIG_32BIT)	+= locore.o
+lib-$(CONFIG_CPU_R3000)	+= locore.o
diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c
index eaad0ed4b523..99b9b29750db 100644
--- a/arch/mips/dec/setup.c
+++ b/arch/mips/dec/setup.c
@@ -746,7 +746,8 @@ void __init arch_init_irq(void)
 		dec_interrupt[DEC_IRQ_HALT] = -1;
 
 	/* Register board interrupts: FPU and cascade. */
-	if (dec_interrupt[DEC_IRQ_FPU] >= 0 && cpu_has_fpu) {
+	if (IS_ENABLED(CONFIG_MIPS_FP_SUPPORT) &&
+	    dec_interrupt[DEC_IRQ_FPU] >= 0 && cpu_has_fpu) {
 		struct irq_desc *desc_fpu;
 		int irq_fpu;
 
diff --git a/arch/mips/include/asm/dec/prom.h b/arch/mips/include/asm/dec/prom.h
index 62c7dfb90e06..1e1247add1cf 100644
--- a/arch/mips/include/asm/dec/prom.h
+++ b/arch/mips/include/asm/dec/prom.h
@@ -43,16 +43,11 @@
  */
 #define REX_PROM_MAGIC		0x30464354
 
-#ifdef CONFIG_64BIT
-
-#define prom_is_rex(magic)	1	/* KN04 and KN05 are REX PROMs.  */
-
-#else /* !CONFIG_64BIT */
-
-#define prom_is_rex(magic)	((magic) == REX_PROM_MAGIC)
-
-#endif /* !CONFIG_64BIT */
-
+/* KN04 and KN05 are REX PROMs, so only do the check for R3k systems.  */
+static inline bool prom_is_rex(u32 magic)
+{
+	return !IS_ENABLED(CONFIG_CPU_R3000) || magic == REX_PROM_MAGIC;
+}
 
 /*
  * 3MIN/MAXINE PROM entry points for DS5000/1xx's, DS5000/xx's and
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index c7925d0e9874..867e9c3db76e 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -15,6 +15,7 @@
 
 #define __HAVE_ARCH_PMD_ALLOC_ONE
 #define __HAVE_ARCH_PUD_ALLOC_ONE
+#define __HAVE_ARCH_PGD_FREE
 #include <asm-generic/pgalloc.h>
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
@@ -48,6 +49,11 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 extern void pgd_init(unsigned long page);
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	free_pages((unsigned long)pgd, PGD_ORDER);
+}
+
 #define __pte_free_tlb(tlb,pte,address)			\
 do {							\
 	pgtable_pte_page_dtor(pte);			\
diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h
index bb36a400203d..8c56b862fd9c 100644
--- a/arch/mips/include/asm/setup.h
+++ b/arch/mips/include/asm/setup.h
@@ -16,7 +16,7 @@ static inline void setup_8250_early_printk_port(unsigned long base,
 	unsigned int reg_shift, unsigned int timeout) {}
 #endif
 
-extern void set_handler(unsigned long offset, void *addr, unsigned long len);
+void set_handler(unsigned long offset, const void *addr, unsigned long len);
 extern void set_uncached_handler(unsigned long offset, void *addr, unsigned long len);
 
 typedef void (*vi_handler_t)(void);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 6f07362de5ce..edd93430b954 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2085,19 +2085,19 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 		 * If no shadow set is selected then use the default handler
 		 * that does normal register saving and standard interrupt exit
 		 */
-		extern char except_vec_vi, except_vec_vi_lui;
-		extern char except_vec_vi_ori, except_vec_vi_end;
-		extern char rollback_except_vec_vi;
-		char *vec_start = using_rollback_handler() ?
-			&rollback_except_vec_vi : &except_vec_vi;
+		extern const u8 except_vec_vi[], except_vec_vi_lui[];
+		extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
+		extern const u8 rollback_except_vec_vi[];
+		const u8 *vec_start = using_rollback_handler() ?
+				      rollback_except_vec_vi : except_vec_vi;
 #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
-		const int lui_offset = &except_vec_vi_lui - vec_start + 2;
-		const int ori_offset = &except_vec_vi_ori - vec_start + 2;
+		const int lui_offset = except_vec_vi_lui - vec_start + 2;
+		const int ori_offset = except_vec_vi_ori - vec_start + 2;
 #else
-		const int lui_offset = &except_vec_vi_lui - vec_start;
-		const int ori_offset = &except_vec_vi_ori - vec_start;
+		const int lui_offset = except_vec_vi_lui - vec_start;
+		const int ori_offset = except_vec_vi_ori - vec_start;
 #endif
-		const int handler_len = &except_vec_vi_end - vec_start;
+		const int handler_len = except_vec_vi_end - vec_start;
 
 		if (handler_len > VECTORSPACING) {
 			/*
@@ -2305,7 +2305,7 @@ void per_cpu_trap_init(bool is_boot_cpu)
 }
 
 /* Install CPU exception handler */
-void set_handler(unsigned long offset, void *addr, unsigned long size)
+void set_handler(unsigned long offset, const void *addr, unsigned long size)
 {
 #ifdef CONFIG_CPU_MICROMIPS
 	memcpy((void *)(ebase + offset), ((unsigned char *)addr - 1), size);
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 9adad24c2e65..046d51a454af 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -2167,16 +2167,14 @@ static void build_r4000_tlb_load_handler(void)
 		uasm_i_tlbr(&p);
 
 		switch (current_cpu_type()) {
-		default:
-			if (cpu_has_mips_r2_exec_hazard) {
-				uasm_i_ehb(&p);
-			fallthrough;
-
 		case CPU_CAVIUM_OCTEON:
 		case CPU_CAVIUM_OCTEON_PLUS:
 		case CPU_CAVIUM_OCTEON2:
-				break;
-			}
+			break;
+		default:
+			if (cpu_has_mips_r2_exec_hazard)
+				uasm_i_ehb(&p);
+			break;
 		}
 
 		/* Examine  entrylo 0 or 1 based on ptr. */
@@ -2243,15 +2241,14 @@ static void build_r4000_tlb_load_handler(void)
 		uasm_i_tlbr(&p);
 
 		switch (current_cpu_type()) {
-		default:
-			if (cpu_has_mips_r2_exec_hazard) {
-				uasm_i_ehb(&p);
-
 		case CPU_CAVIUM_OCTEON:
 		case CPU_CAVIUM_OCTEON_PLUS:
 		case CPU_CAVIUM_OCTEON2:
-				break;
-			}
+			break;
+		default:
+			if (cpu_has_mips_r2_exec_hazard)
+				uasm_i_ehb(&p);
+			break;
 		}
 
 		/* Examine  entrylo 0 or 1 based on ptr. */
diff --git a/arch/mips/ralink/ill_acc.c b/arch/mips/ralink/ill_acc.c
index bdf53807d7c2..bea857c9da8b 100644
--- a/arch/mips/ralink/ill_acc.c
+++ b/arch/mips/ralink/ill_acc.c
@@ -61,6 +61,7 @@ static int __init ill_acc_of_setup(void)
 	pdev = of_find_device_by_node(np);
 	if (!pdev) {
 		pr_err("%pOFn: failed to lookup pdev\n", np);
+		of_node_put(np);
 		return -EINVAL;
 	}
 
diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c
index 04684990e28e..b7f6f782d9a1 100644
--- a/arch/mips/rb532/devices.c
+++ b/arch/mips/rb532/devices.c
@@ -301,11 +301,9 @@ static int __init plat_setup_devices(void)
 static int __init setup_kmac(char *s)
 {
 	printk(KERN_INFO "korina mac = %s\n", s);
-	if (!mac_pton(s, korina_dev0_data.mac)) {
+	if (!mac_pton(s, korina_dev0_data.mac))
 		printk(KERN_ERR "Invalid mac\n");
-		return -EINVAL;
-	}
-	return 0;
+	return 1;
 }
 
 __setup("kmac=", setup_kmac);
diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h
index d4cbf069dc22..37a40981deb3 100644
--- a/arch/nds32/include/asm/uaccess.h
+++ b/arch/nds32/include/asm/uaccess.h
@@ -70,9 +70,7 @@ static inline void set_fs(mm_segment_t fs)
  * versions are void (ie, don't return a value as such).
  */
 
-#define get_user	__get_user					\
-
-#define __get_user(x, ptr)						\
+#define get_user(x, ptr)						\
 ({									\
 	long __gu_err = 0;						\
 	__get_user_check((x), (ptr), __gu_err);				\
@@ -85,6 +83,14 @@ static inline void set_fs(mm_segment_t fs)
 	(void)0;							\
 })
 
+#define __get_user(x, ptr)						\
+({									\
+	long __gu_err = 0;						\
+	const __typeof__(*(ptr)) __user *__p = (ptr);			\
+	__get_user_err((x), __p, (__gu_err));				\
+	__gu_err;							\
+})
+
 #define __get_user_check(x, ptr, err)					\
 ({									\
 	const __typeof__(*(ptr)) __user *__p = (ptr);			\
@@ -165,12 +171,18 @@ do {									\
 		: "r"(addr), "i"(-EFAULT)				\
 		: "cc")
 
-#define put_user	__put_user					\
+#define put_user(x, ptr)						\
+({									\
+	long __pu_err = 0;						\
+	__put_user_check((x), (ptr), __pu_err);				\
+	__pu_err;							\
+})
 
 #define __put_user(x, ptr)						\
 ({									\
 	long __pu_err = 0;						\
-	__put_user_err((x), (ptr), __pu_err);				\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	__put_user_err((x), __p, __pu_err);				\
 	__pu_err;							\
 })
 
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index ba9340e96fd4..ca9285a915ef 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -88,6 +88,7 @@ extern __must_check long strnlen_user(const char __user *s, long n);
 /* Optimized macros */
 #define __get_user_asm(val, insn, addr, err)				\
 {									\
+	unsigned long __gu_val;						\
 	__asm__ __volatile__(						\
 	"       movi    %0, %3\n"					\
 	"1:   " insn " %1, 0(%2)\n"					\
@@ -96,14 +97,20 @@ extern __must_check long strnlen_user(const char __user *s, long n);
 	"       .section __ex_table,\"a\"\n"				\
 	"       .word 1b, 2b\n"						\
 	"       .previous"						\
-	: "=&r" (err), "=r" (val)					\
+	: "=&r" (err), "=r" (__gu_val)					\
 	: "r" (addr), "i" (-EFAULT));					\
+	val = (__force __typeof__(*(addr)))__gu_val;			\
 }
 
-#define __get_user_unknown(val, size, ptr, err) do {			\
+extern void __get_user_unknown(void);
+
+#define __get_user_8(val, ptr, err) do {				\
+	u64 __val = 0;							\
 	err = 0;							\
-	if (__copy_from_user(&(val), ptr, size)) {			\
+	if (raw_copy_from_user(&(__val), ptr, sizeof(val))) {		\
 		err = -EFAULT;						\
+	} else {							\
+		val = (typeof(val))(typeof((val) - (val)))__val;	\
 	}								\
 	} while (0)
 
@@ -119,8 +126,11 @@ do {									\
 	case 4:								\
 		__get_user_asm(val, "ldw", ptr, err);			\
 		break;							\
+	case 8:								\
+		__get_user_8(val, ptr, err);				\
+		break;							\
 	default:							\
-		__get_user_unknown(val, size, ptr, err);		\
+		__get_user_unknown();					\
 		break;							\
 	}								\
 } while (0)
@@ -129,9 +139,7 @@ do {									\
 	({								\
 	long __gu_err = -EFAULT;					\
 	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
-	unsigned long __gu_val = 0;					\
-	__get_user_common(__gu_val, sizeof(*(ptr)), __gu_ptr, __gu_err);\
-	(x) = (__force __typeof__(x))__gu_val;				\
+	__get_user_common(x, sizeof(*(ptr)), __gu_ptr, __gu_err);	\
 	__gu_err;							\
 	})
 
@@ -139,11 +147,9 @@ do {									\
 ({									\
 	long __gu_err = -EFAULT;					\
 	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
-	unsigned long __gu_val = 0;					\
 	if (access_ok( __gu_ptr, sizeof(*__gu_ptr)))	\
-		__get_user_common(__gu_val, sizeof(*__gu_ptr),		\
+		__get_user_common(x, sizeof(*__gu_ptr),			\
 			__gu_ptr, __gu_err);				\
-	(x) = (__force __typeof__(x))__gu_val;				\
 	__gu_err;							\
 })
 
diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c
index 2009ae2d3c3b..386e46443b60 100644
--- a/arch/nios2/kernel/signal.c
+++ b/arch/nios2/kernel/signal.c
@@ -36,10 +36,10 @@ struct rt_sigframe {
 
 static inline int rt_restore_ucontext(struct pt_regs *regs,
 					struct switch_stack *sw,
-					struct ucontext *uc, int *pr2)
+					struct ucontext __user *uc, int *pr2)
 {
 	int temp;
-	unsigned long *gregs = uc->uc_mcontext.gregs;
+	unsigned long __user *gregs = uc->uc_mcontext.gregs;
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -102,10 +102,11 @@ asmlinkage int do_rt_sigreturn(struct switch_stack *sw)
 {
 	struct pt_regs *regs = (struct pt_regs *)(sw + 1);
 	/* Verify, can we follow the stack back */
-	struct rt_sigframe *frame = (struct rt_sigframe *) regs->sp;
+	struct rt_sigframe __user *frame;
 	sigset_t set;
 	int rval;
 
+	frame = (struct rt_sigframe __user *) regs->sp;
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
 
@@ -124,10 +125,10 @@ badframe:
 	return 0;
 }
 
-static inline int rt_setup_ucontext(struct ucontext *uc, struct pt_regs *regs)
+static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs *regs)
 {
 	struct switch_stack *sw = (struct switch_stack *)regs - 1;
-	unsigned long *gregs = uc->uc_mcontext.gregs;
+	unsigned long __user *gregs = uc->uc_mcontext.gregs;
 	int err = 0;
 
 	err |= __put_user(MCONTEXT_VERSION, &uc->uc_mcontext.version);
@@ -162,8 +163,9 @@ static inline int rt_setup_ucontext(struct ucontext *uc, struct pt_regs *regs)
 	return err;
 }
 
-static inline void *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
-				 size_t frame_size)
+static inline void __user *get_sigframe(struct ksignal *ksig,
+					struct pt_regs *regs,
+					size_t frame_size)
 {
 	unsigned long usp;
 
@@ -174,13 +176,13 @@ static inline void *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 	usp = sigsp(usp, ksig);
 
 	/* Verify, is it 32 or 64 bit aligned */
-	return (void *)((usp - frame_size) & -8UL);
+	return (void __user *)((usp - frame_size) & -8UL);
 }
 
 static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 			  struct pt_regs *regs)
 {
-	struct rt_sigframe *frame;
+	struct rt_sigframe __user *frame;
 	int err = 0;
 
 	frame = get_sigframe(ksig, regs, sizeof(*frame));
diff --git a/arch/parisc/include/asm/traps.h b/arch/parisc/include/asm/traps.h
index 8ecc1f0c0483..d0e090a2c000 100644
--- a/arch/parisc/include/asm/traps.h
+++ b/arch/parisc/include/asm/traps.h
@@ -17,6 +17,7 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err);
 const char *trap_name(unsigned long code);
 void do_page_fault(struct pt_regs *regs, unsigned long code,
 		unsigned long address);
+int handle_nadtlb_fault(struct pt_regs *regs);
 #endif
 
 #endif
diff --git a/arch/parisc/kernel/patch.c b/arch/parisc/kernel/patch.c
index 80a0ab372802..e59574f65e64 100644
--- a/arch/parisc/kernel/patch.c
+++ b/arch/parisc/kernel/patch.c
@@ -40,10 +40,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags,
 
 	*need_unmap = 1;
 	set_fixmap(fixmap, page_to_phys(page));
-	if (flags)
-		raw_spin_lock_irqsave(&patch_lock, *flags);
-	else
-		__acquire(&patch_lock);
+	raw_spin_lock_irqsave(&patch_lock, *flags);
 
 	return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK));
 }
@@ -52,10 +49,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
 {
 	clear_fixmap(fixmap);
 
-	if (flags)
-		raw_spin_unlock_irqrestore(&patch_lock, *flags);
-	else
-		__release(&patch_lock);
+	raw_spin_unlock_irqrestore(&patch_lock, *flags);
 }
 
 void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len)
@@ -67,8 +61,9 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len)
 	int mapped;
 
 	/* Make sure we don't have any aliases in cache */
-	flush_kernel_vmap_range(addr, len);
-	flush_icache_range(start, end);
+	flush_kernel_dcache_range_asm(start, end);
+	flush_kernel_icache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 
 	p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, &mapped);
 
@@ -81,8 +76,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len)
 			 * We're crossing a page boundary, so
 			 * need to remap
 			 */
-			flush_kernel_vmap_range((void *)fixmap,
-						(p-fixmap) * sizeof(*p));
+			flush_kernel_dcache_range_asm((unsigned long)fixmap,
+						      (unsigned long)p);
+			flush_tlb_kernel_range((unsigned long)fixmap,
+					       (unsigned long)p);
 			if (mapped)
 				patch_unmap(FIX_TEXT_POKE0, &flags);
 			p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags,
@@ -90,10 +87,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len)
 		}
 	}
 
-	flush_kernel_vmap_range((void *)fixmap, (p-fixmap) * sizeof(*p));
+	flush_kernel_dcache_range_asm((unsigned long)fixmap, (unsigned long)p);
+	flush_tlb_kernel_range((unsigned long)fixmap, (unsigned long)p);
 	if (mapped)
 		patch_unmap(FIX_TEXT_POKE0, &flags);
-	flush_icache_range(start, end);
 }
 
 void __kprobes __patch_text(void *addr, u32 insn)
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index afe8b902a8fc..6fe5a3e98edc 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -661,6 +661,8 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 			 by hand. Technically we need to emulate:
 			 fdc,fdce,pdc,"fic,4f",prober,probeir,probew, probeiw
 		*/
+		if (code == 17 && handle_nadtlb_fault(regs))
+			return;
 		fault_address = regs->ior;
 		fault_space = regs->isr;
 		break;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 716960f5d92e..5faa3cff4738 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -424,3 +424,92 @@ no_context:
 		goto no_context;
 	pagefault_out_of_memory();
 }
+
+/* Handle non-access data TLB miss faults.
+ *
+ * For probe instructions, accesses to userspace are considered allowed
+ * if they lie in a valid VMA and the access type matches. We are not
+ * allowed to handle MM faults here so there may be situations where an
+ * actual access would fail even though a probe was successful.
+ */
+int
+handle_nadtlb_fault(struct pt_regs *regs)
+{
+	unsigned long insn = regs->iir;
+	int breg, treg, xreg, val = 0;
+	struct vm_area_struct *vma, *prev_vma;
+	struct task_struct *tsk;
+	struct mm_struct *mm;
+	unsigned long address;
+	unsigned long acc_type;
+
+	switch (insn & 0x380) {
+	case 0x280:
+		/* FDC instruction */
+		fallthrough;
+	case 0x380:
+		/* PDC and FIC instructions */
+		if (printk_ratelimit()) {
+			pr_warn("BUG: nullifying cache flush/purge instruction\n");
+			show_regs(regs);
+		}
+		if (insn & 0x20) {
+			/* Base modification */
+			breg = (insn >> 21) & 0x1f;
+			xreg = (insn >> 16) & 0x1f;
+			if (breg && xreg)
+				regs->gr[breg] += regs->gr[xreg];
+		}
+		regs->gr[0] |= PSW_N;
+		return 1;
+
+	case 0x180:
+		/* PROBE instruction */
+		treg = insn & 0x1f;
+		if (regs->isr) {
+			tsk = current;
+			mm = tsk->mm;
+			if (mm) {
+				/* Search for VMA */
+				address = regs->ior;
+				mmap_read_lock(mm);
+				vma = find_vma_prev(mm, address, &prev_vma);
+				mmap_read_unlock(mm);
+
+				/*
+				 * Check if access to the VMA is okay.
+				 * We don't allow for stack expansion.
+				 */
+				acc_type = (insn & 0x40) ? VM_WRITE : VM_READ;
+				if (vma
+				    && address >= vma->vm_start
+				    && (vma->vm_flags & acc_type) == acc_type)
+					val = 1;
+			}
+		}
+		if (treg)
+			regs->gr[treg] = val;
+		regs->gr[0] |= PSW_N;
+		return 1;
+
+	case 0x300:
+		/* LPA instruction */
+		if (insn & 0x20) {
+			/* Base modification */
+			breg = (insn >> 21) & 0x1f;
+			xreg = (insn >> 16) & 0x1f;
+			if (breg && xreg)
+				regs->gr[breg] += regs->gr[xreg];
+		}
+		treg = insn & 0x1f;
+		if (treg)
+			regs->gr[treg] = 0;
+		regs->gr[0] |= PSW_N;
+		return 1;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index aa6808e70647..72610e2d6176 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -173,7 +173,7 @@ else
 CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power7,$(call cc-option,-mtune=power5))
 CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mcpu=power5,-mcpu=power4)
 endif
-else
+else ifdef CONFIG_PPC_BOOK3E_64
 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64
 endif
 
diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts
new file mode 100644
index 000000000000..73f8c998c64d
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * T1040RDB-REV-A Device Tree Source
+ *
+ * Copyright 2014 - 2015 Freescale Semiconductor Inc.
+ *
+ */
+
+#include "t1040rdb.dts"
+
+/ {
+	model = "fsl,T1040RDB-REV-A";
+	compatible = "fsl,T1040RDB-REV-A";
+};
+
+&seville_port0 {
+	label = "ETH5";
+};
+
+&seville_port2 {
+	label = "ETH7";
+};
+
+&seville_port4 {
+	label = "ETH9";
+};
+
+&seville_port6 {
+	label = "ETH11";
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
index af0c8a6f5613..b6733e7e6580 100644
--- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
@@ -119,7 +119,7 @@
 	managed = "in-band-status";
 	phy-handle = <&phy_qsgmii_0>;
 	phy-mode = "qsgmii";
-	label = "ETH5";
+	label = "ETH3";
 	status = "okay";
 };
 
@@ -135,7 +135,7 @@
 	managed = "in-band-status";
 	phy-handle = <&phy_qsgmii_2>;
 	phy-mode = "qsgmii";
-	label = "ETH7";
+	label = "ETH5";
 	status = "okay";
 };
 
@@ -151,7 +151,7 @@
 	managed = "in-band-status";
 	phy-handle = <&phy_qsgmii_4>;
 	phy-mode = "qsgmii";
-	label = "ETH9";
+	label = "ETH7";
 	status = "okay";
 };
 
@@ -167,7 +167,7 @@
 	managed = "in-band-status";
 	phy-handle = <&phy_qsgmii_6>;
 	phy-mode = "qsgmii";
-	label = "ETH11";
+	label = "ETH9";
 	status = "okay";
 };
 
diff --git a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
index 099a598c74c0..bfe1ed5be337 100644
--- a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
@@ -139,12 +139,12 @@
 		fman@400000 {
 			ethernet@e6000 {
 				phy-handle = <&phy_rgmii_0>;
-				phy-connection-type = "rgmii";
+				phy-connection-type = "rgmii-id";
 			};
 
 			ethernet@e8000 {
 				phy-handle = <&phy_rgmii_1>;
-				phy-connection-type = "rgmii";
+				phy-connection-type = "rgmii-id";
 			};
 
 			mdio0: mdio@fc000 {
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index a1d238255f07..a07960066b5f 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -567,7 +567,7 @@ DECLARE_INTERRUPT_HANDLER_RAW(do_slb_fault);
 DECLARE_INTERRUPT_HANDLER(do_bad_slb_fault);
 
 /* hash_utils.c */
-DECLARE_INTERRUPT_HANDLER_RAW(do_hash_fault);
+DECLARE_INTERRUPT_HANDLER(do_hash_fault);
 
 /* fault.c */
 DECLARE_INTERRUPT_HANDLER(do_page_fault);
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index f130783c8301..a4fe1292909e 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -359,25 +359,37 @@ static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr)
  */
 static inline void __raw_rm_writeb(u8 val, volatile void __iomem *paddr)
 {
-	__asm__ __volatile__("stbcix %0,0,%1"
+	__asm__ __volatile__(".machine push;   \
+			      .machine power6; \
+			      stbcix %0,0,%1;  \
+			      .machine pop;"
 		: : "r" (val), "r" (paddr) : "memory");
 }
 
 static inline void __raw_rm_writew(u16 val, volatile void __iomem *paddr)
 {
-	__asm__ __volatile__("sthcix %0,0,%1"
+	__asm__ __volatile__(".machine push;   \
+			      .machine power6; \
+			      sthcix %0,0,%1;  \
+			      .machine pop;"
 		: : "r" (val), "r" (paddr) : "memory");
 }
 
 static inline void __raw_rm_writel(u32 val, volatile void __iomem *paddr)
 {
-	__asm__ __volatile__("stwcix %0,0,%1"
+	__asm__ __volatile__(".machine push;   \
+			      .machine power6; \
+			      stwcix %0,0,%1;  \
+			      .machine pop;"
 		: : "r" (val), "r" (paddr) : "memory");
 }
 
 static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
 {
-	__asm__ __volatile__("stdcix %0,0,%1"
+	__asm__ __volatile__(".machine push;   \
+			      .machine power6; \
+			      stdcix %0,0,%1;  \
+			      .machine pop;"
 		: : "r" (val), "r" (paddr) : "memory");
 }
 
@@ -389,7 +401,10 @@ static inline void __raw_rm_writeq_be(u64 val, volatile void __iomem *paddr)
 static inline u8 __raw_rm_readb(volatile void __iomem *paddr)
 {
 	u8 ret;
-	__asm__ __volatile__("lbzcix %0,0, %1"
+	__asm__ __volatile__(".machine push;   \
+			      .machine power6; \
+			      lbzcix %0,0, %1; \
+			      .machine pop;"
 			     : "=r" (ret) : "r" (paddr) : "memory");
 	return ret;
 }
@@ -397,7 +412,10 @@ static inline u8 __raw_rm_readb(volatile void __iomem *paddr)
 static inline u16 __raw_rm_readw(volatile void __iomem *paddr)
 {
 	u16 ret;
-	__asm__ __volatile__("lhzcix %0,0, %1"
+	__asm__ __volatile__(".machine push;   \
+			      .machine power6; \
+			      lhzcix %0,0, %1; \
+			      .machine pop;"
 			     : "=r" (ret) : "r" (paddr) : "memory");
 	return ret;
 }
@@ -405,7 +423,10 @@ static inline u16 __raw_rm_readw(volatile void __iomem *paddr)
 static inline u32 __raw_rm_readl(volatile void __iomem *paddr)
 {
 	u32 ret;
-	__asm__ __volatile__("lwzcix %0,0, %1"
+	__asm__ __volatile__(".machine push;   \
+			      .machine power6; \
+			      lwzcix %0,0, %1; \
+			      .machine pop;"
 			     : "=r" (ret) : "r" (paddr) : "memory");
 	return ret;
 }
@@ -413,7 +434,10 @@ static inline u32 __raw_rm_readl(volatile void __iomem *paddr)
 static inline u64 __raw_rm_readq(volatile void __iomem *paddr)
 {
 	u64 ret;
-	__asm__ __volatile__("ldcix %0,0, %1"
+	__asm__ __volatile__(".machine push;   \
+			      .machine power6; \
+			      ldcix %0,0, %1;  \
+			      .machine pop;"
 			     : "=r" (ret) : "r" (paddr) : "memory");
 	return ret;
 }
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 254687258f42..f2c5c26869f1 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn)
 #define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 
-#define virt_addr_valid(kaddr)	pfn_valid(virt_to_pfn(kaddr))
+#define virt_addr_valid(vaddr)	({					\
+	unsigned long _addr = (unsigned long)vaddr;			\
+	_addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory &&	\
+	pfn_valid(virt_to_pfn(_addr));					\
+})
 
 /*
  * On Book-E parts we need __va to parse the device tree and we can't
diff --git a/arch/powerpc/include/asm/set_memory.h b/arch/powerpc/include/asm/set_memory.h
index b040094f7920..7ebc807aa8cc 100644
--- a/arch/powerpc/include/asm/set_memory.h
+++ b/arch/powerpc/include/asm/set_memory.h
@@ -6,6 +6,8 @@
 #define SET_MEMORY_RW	1
 #define SET_MEMORY_NX	2
 #define SET_MEMORY_X	3
+#define SET_MEMORY_NP	4	/* Set memory non present */
+#define SET_MEMORY_P	5	/* Set memory present */
 
 int change_memory_attr(unsigned long addr, int numpages, long action);
 
@@ -29,6 +31,14 @@ static inline int set_memory_x(unsigned long addr, int numpages)
 	return change_memory_attr(addr, numpages, SET_MEMORY_X);
 }
 
-int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot);
+static inline int set_memory_np(unsigned long addr, int numpages)
+{
+	return change_memory_attr(addr, numpages, SET_MEMORY_NP);
+}
+
+static inline int set_memory_p(unsigned long addr, int numpages)
+{
+	return change_memory_attr(addr, numpages, SET_MEMORY_P);
+}
 
 #endif
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 22c79ab40006..b2680070d65d 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -125,8 +125,11 @@ do {								\
  */
 #define __get_user_atomic_128_aligned(kaddr, uaddr, err)		\
 	__asm__ __volatile__(				\
+		".machine push\n"			\
+		".machine altivec\n"			\
 		"1:	lvx  0,0,%1	# get user\n"	\
 		" 	stvx 0,0,%2	# put kernel\n"	\
+		".machine pop\n"			\
 		"2:\n"					\
 		".section .fixup,\"ax\"\n"		\
 		"3:	li %0,%3\n"			\
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 617eba82531c..d89cf802d9aa 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -669,7 +669,7 @@ static void __init kvm_use_magic_page(void)
 	on_each_cpu(kvm_map_magic_page, &features, 1);
 
 	/* Quick self-test to see if the mapping works */
-	if (!fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) {
+	if (fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) {
 		kvm_patching_worked = false;
 		return;
 	}
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index ff80bbad22a5..e18a725a8e5d 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1235,6 +1235,12 @@ int __init early_init_dt_scan_rtas(unsigned long node,
 	entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL);
 	sizep  = of_get_flat_dt_prop(node, "rtas-size", NULL);
 
+#ifdef CONFIG_PPC64
+	/* need this feature to decide the crashkernel offset */
+	if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL))
+		powerpc_firmware_features |= FW_FEATURE_LPAR;
+#endif
+
 	if (basep && entryp && sizep) {
 		rtas.base = *basep;
 		rtas.entry = *entryp;
diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c
index a0a78aba2083..1ee4640a2641 100644
--- a/arch/powerpc/kernel/secvar-sysfs.c
+++ b/arch/powerpc/kernel/secvar-sysfs.c
@@ -26,15 +26,18 @@ static ssize_t format_show(struct kobject *kobj, struct kobj_attribute *attr,
 	const char *format;
 
 	node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend");
-	if (!of_device_is_available(node))
-		return -ENODEV;
+	if (!of_device_is_available(node)) {
+		rc = -ENODEV;
+		goto out;
+	}
 
 	rc = of_property_read_string(node, "format", &format);
 	if (rc)
-		return rc;
+		goto out;
 
 	rc = sprintf(buf, "%s\n", format);
 
+out:
 	of_node_put(node);
 
 	return rc;
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 48525e8b5730..71b1bfdadd76 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -147,11 +147,18 @@ void __init reserve_crashkernel(void)
 	if (!crashk_res.start) {
 #ifdef CONFIG_PPC64
 		/*
-		 * On 64bit we split the RMO in half but cap it at half of
-		 * a small SLB (128MB) since the crash kernel needs to place
-		 * itself and some stacks to be in the first segment.
+		 * On the LPAR platform place the crash kernel to mid of
+		 * RMA size (512MB or more) to ensure the crash kernel
+		 * gets enough space to place itself and some stack to be
+		 * in the first segment. At the same time normal kernel
+		 * also get enough space to allocate memory for essential
+		 * system resource in the first segment. Keep the crash
+		 * kernel starts at 128MB offset on other platforms.
 		 */
-		crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2));
+		if (firmware_has_feature(FW_FEATURE_LPAR))
+			crashk_res.start = ppc64_rma_size / 2;
+		else
+			crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2));
 #else
 		crashk_res.start = KDUMP_KERNELBASE;
 #endif
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 983b8c18bc31..a644003603da 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -407,10 +407,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
 	 */
 	ld	r10,HSTATE_SCRATCH0(r13)
 	cmpwi	r10,BOOK3S_INTERRUPT_MACHINE_CHECK
-	beq	machine_check_common
+	beq	.Lcall_machine_check_common
 
 	cmpwi	r10,BOOK3S_INTERRUPT_SYSTEM_RESET
-	beq	system_reset_common
+	beq	.Lcall_system_reset_common
 
 	b	.
+
+.Lcall_machine_check_common:
+	b	machine_check_common
+
+.Lcall_system_reset_common:
+	b	system_reset_common
 #endif
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a2fd1db29f7e..7fa685711669 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -6101,8 +6101,11 @@ static int kvmppc_book3s_init_hv(void)
 	if (r)
 		return r;
 
-	if (kvmppc_radix_possible())
+	if (kvmppc_radix_possible()) {
 		r = kvmppc_radix_init();
+		if (r)
+			return r;
+	}
 
 	r = kvmppc_uvmem_init();
 	if (r < 0)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index b4e6f70b97b9..ee305455bd8d 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1507,7 +1507,7 @@ int kvmppc_handle_vmx_load(struct kvm_vcpu *vcpu,
 {
 	enum emulation_result emulated = EMULATE_DONE;
 
-	if (vcpu->arch.mmio_vsx_copy_nums > 2)
+	if (vcpu->arch.mmio_vmx_copy_nums > 2)
 		return EMULATE_FAIL;
 
 	while (vcpu->arch.mmio_vmx_copy_nums) {
@@ -1604,7 +1604,7 @@ int kvmppc_handle_vmx_store(struct kvm_vcpu *vcpu,
 	unsigned int index = rs & KVM_MMIO_REG_MASK;
 	enum emulation_result emulated = EMULATE_DONE;
 
-	if (vcpu->arch.mmio_vsx_copy_nums > 2)
+	if (vcpu->arch.mmio_vmx_copy_nums > 2)
 		return EMULATE_FAIL;
 
 	vcpu->arch.io_gpr = rs;
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index d8cc49f39fe4..2d39b7c246e3 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -112,9 +112,9 @@ static nokprobe_inline long address_ok(struct pt_regs *regs,
 {
 	if (!user_mode(regs))
 		return 1;
-	if (__access_ok(ea, nb))
+	if (access_ok((void __user *)ea, nb))
 		return 1;
-	if (__access_ok(ea, 1))
+	if (access_ok((void __user *)ea, 1))
 		/* Access overlaps the end of the user region */
 		regs->dar = TASK_SIZE_MAX - 1;
 	else
@@ -1014,7 +1014,10 @@ NOKPROBE_SYMBOL(emulate_dcbz);
 
 #define __put_user_asmx(x, addr, err, op, cr)		\
 	__asm__ __volatile__(				\
+		".machine push\n"			\
+		".machine power8\n"			\
 		"1:	" op " %2,0,%3\n"		\
+		".machine pop\n"			\
 		"	mfcr	%1\n"			\
 		"2:\n"					\
 		".section .fixup,\"ax\"\n"		\
@@ -1027,7 +1030,10 @@ NOKPROBE_SYMBOL(emulate_dcbz);
 
 #define __get_user_asmx(x, addr, err, op)		\
 	__asm__ __volatile__(				\
+		".machine push\n"			\
+		".machine power8\n"			\
 		"1:	"op" %1,0,%2\n"			\
+		".machine pop\n"			\
 		"2:\n"					\
 		".section .fixup,\"ax\"\n"		\
 		"3:	li	%0,%3\n"		\
@@ -3306,7 +3312,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 			__put_user_asmx(op->val, ea, err, "stbcx.", cr);
 			break;
 		case 2:
-			__put_user_asmx(op->val, ea, err, "stbcx.", cr);
+			__put_user_asmx(op->val, ea, err, "sthcx.", cr);
 			break;
 #endif
 		case 4:
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index c145776d3ae5..7bfd88c4b547 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1522,8 +1522,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
-DECLARE_INTERRUPT_HANDLER(__do_hash_fault);
-DEFINE_INTERRUPT_HANDLER(__do_hash_fault)
+DEFINE_INTERRUPT_HANDLER(do_hash_fault)
 {
 	unsigned long ea = regs->dar;
 	unsigned long dsisr = regs->dsisr;
@@ -1582,35 +1581,6 @@ DEFINE_INTERRUPT_HANDLER(__do_hash_fault)
 	}
 }
 
-/*
- * The _RAW interrupt entry checks for the in_nmi() case before
- * running the full handler.
- */
-DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
-{
-	/*
-	 * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
-	 * don't call hash_page, just fail the fault. This is required to
-	 * prevent re-entrancy problems in the hash code, namely perf
-	 * interrupts hitting while something holds H_PAGE_BUSY, and taking a
-	 * hash fault. See the comment in hash_preload().
-	 *
-	 * We come here as a result of a DSI at a point where we don't want
-	 * to call hash_page, such as when we are accessing memory (possibly
-	 * user memory) inside a PMU interrupt that occurred while interrupts
-	 * were soft-disabled.  We want to invoke the exception handler for
-	 * the access, or panic if there isn't a handler.
-	 */
-	if (unlikely(in_nmi())) {
-		do_bad_page_fault_segv(regs);
-		return 0;
-	}
-
-	__do_hash_fault(regs);
-
-	return 0;
-}
-
 #ifdef CONFIG_PPC_MM_SLICES
 static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
 {
@@ -1677,26 +1647,18 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
 #endif /* CONFIG_PPC_64K_PAGES */
 
 	/*
-	 * __hash_page_* must run with interrupts off, as it sets the
-	 * H_PAGE_BUSY bit. It's possible for perf interrupts to hit at any
-	 * time and may take a hash fault reading the user stack, see
-	 * read_user_stack_slow() in the powerpc/perf code.
-	 *
-	 * If that takes a hash fault on the same page as we lock here, it
-	 * will bail out when seeing H_PAGE_BUSY set, and retry the access
-	 * leading to an infinite loop.
+	 * __hash_page_* must run with interrupts off, including PMI interrupts
+	 * off, as it sets the H_PAGE_BUSY bit.
 	 *
-	 * Disabling interrupts here does not prevent perf interrupts, but it
-	 * will prevent them taking hash faults (see the NMI test in
-	 * do_hash_page), then read_user_stack's copy_from_user_nofault will
-	 * fail and perf will fall back to read_user_stack_slow(), which
-	 * walks the Linux page tables.
+	 * It's otherwise possible for perf interrupts to hit at any time and
+	 * may take a hash fault reading the user stack, which could take a
+	 * hash miss and deadlock on the same H_PAGE_BUSY bit.
 	 *
 	 * Interrupts must also be off for the duration of the
 	 * mm_is_thread_local test and update, to prevent preempt running the
 	 * mm on another CPU (XXX: this may be racy vs kthread_use_mm).
 	 */
-	local_irq_save(flags);
+	powerpc_local_irq_pmu_save(flags);
 
 	/* Is that local to this CPU ? */
 	if (mm_is_thread_local(mm))
@@ -1721,7 +1683,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
 				   mm_ctx_user_psize(&mm->context),
 				   pte_val(*ptep));
 
-	local_irq_restore(flags);
+	powerpc_local_irq_pmu_restore(flags);
 }
 
 /*
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index a8d0ce85d39a..4a15172dfef2 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -568,18 +568,24 @@ NOKPROBE_SYMBOL(hash__do_page_fault);
 static void __bad_page_fault(struct pt_regs *regs, int sig)
 {
 	int is_write = page_fault_is_write(regs->dsisr);
+	const char *msg;
 
 	/* kernel has accessed a bad area */
 
+	if (regs->dar < PAGE_SIZE)
+		msg = "Kernel NULL pointer dereference";
+	else
+		msg = "Unable to handle kernel data access";
+
 	switch (TRAP(regs)) {
 	case INTERRUPT_DATA_STORAGE:
-	case INTERRUPT_DATA_SEGMENT:
 	case INTERRUPT_H_DATA_STORAGE:
-		pr_alert("BUG: %s on %s at 0x%08lx\n",
-			 regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" :
-			 "Unable to handle kernel data access",
+		pr_alert("BUG: %s on %s at 0x%08lx\n", msg,
 			 is_write ? "write" : "read", regs->dar);
 		break;
+	case INTERRUPT_DATA_SEGMENT:
+		pr_alert("BUG: %s at 0x%08lx\n", msg, regs->dar);
+		break;
 	case INTERRUPT_INST_STORAGE:
 	case INTERRUPT_INST_SEGMENT:
 		pr_alert("BUG: Unable to handle kernel instruction fetch%s",
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index cf8770b1a692..f3e4d069e0ba 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -83,13 +83,12 @@ void __init
 kasan_update_early_region(unsigned long k_start, unsigned long k_end, pte_t pte)
 {
 	unsigned long k_cur;
-	phys_addr_t pa = __pa(kasan_early_shadow_page);
 
 	for (k_cur = k_start; k_cur != k_end; k_cur += PAGE_SIZE) {
 		pmd_t *pmd = pmd_off_k(k_cur);
 		pte_t *ptep = pte_offset_kernel(pmd, k_cur);
 
-		if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
+		if (pte_page(*ptep) != virt_to_page(lm_alias(kasan_early_shadow_page)))
 			continue;
 
 		__set_pte_at(&init_mm, k_cur, ptep, pte, 0);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 59d3cfcd7887..5fb829256b59 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -956,7 +956,9 @@ static int __init parse_numa_properties(void)
 			of_node_put(cpu);
 		}
 
-		node_set_online(nid);
+		/* node_set_online() is an UB if 'nid' is negative */
+		if (likely(nid >= 0))
+			node_set_online(nid);
 	}
 
 	get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);
diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
index edea388e9d3f..85753e32a4de 100644
--- a/arch/powerpc/mm/pageattr.c
+++ b/arch/powerpc/mm/pageattr.c
@@ -15,12 +15,14 @@
 #include <asm/pgtable.h>
 
 
+static pte_basic_t pte_update_delta(pte_t *ptep, unsigned long addr,
+				    unsigned long old, unsigned long new)
+{
+	return pte_update(&init_mm, addr, ptep, old & ~new, new & ~old, 0);
+}
+
 /*
- * Updates the attributes of a page in three steps:
- *
- * 1. take the page_table_lock
- * 2. install the new entry with the updated attributes
- * 3. flush the TLB
+ * Updates the attributes of a page atomically.
  *
  * This sequence is safe against concurrent updates, and also allows updating the
  * attributes of a page currently being executed or accessed.
@@ -28,41 +30,39 @@
 static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 {
 	long action = (long)data;
-	pte_t pte;
 
-	spin_lock(&init_mm.page_table_lock);
-
-	pte = ptep_get(ptep);
-
-	/* modify the PTE bits as desired, then apply */
+	/* modify the PTE bits as desired */
 	switch (action) {
 	case SET_MEMORY_RO:
-		pte = pte_wrprotect(pte);
+		/* Don't clear DIRTY bit */
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_RO);
 		break;
 	case SET_MEMORY_RW:
-		pte = pte_mkwrite(pte_mkdirty(pte));
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_RW);
 		break;
 	case SET_MEMORY_NX:
-		pte = pte_exprotect(pte);
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_ROX, _PAGE_KERNEL_RO);
 		break;
 	case SET_MEMORY_X:
-		pte = pte_mkexec(pte);
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_ROX);
+		break;
+	case SET_MEMORY_NP:
+		pte_update(&init_mm, addr, ptep, _PAGE_PRESENT, 0, 0);
+		break;
+	case SET_MEMORY_P:
+		pte_update(&init_mm, addr, ptep, 0, _PAGE_PRESENT, 0);
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;
 	}
 
-	pte_update(&init_mm, addr, ptep, ~0UL, pte_val(pte), 0);
-
 	/* See ptesync comment in radix__set_pte_at() */
 	if (radix_enabled())
 		asm volatile("ptesync": : :"memory");
 
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 
-	spin_unlock(&init_mm.page_table_lock);
-
 	return 0;
 }
 
@@ -96,36 +96,3 @@ int change_memory_attr(unsigned long addr, int numpages, long action)
 	return apply_to_existing_page_range(&init_mm, start, size,
 					    change_page_attr, (void *)action);
 }
-
-/*
- * Set the attributes of a page:
- *
- * This function is used by PPC32 at the end of init to set final kernel memory
- * protection. It includes changing the maping of the page it is executing from
- * and data pages it is using.
- */
-static int set_page_attr(pte_t *ptep, unsigned long addr, void *data)
-{
-	pgprot_t prot = __pgprot((unsigned long)data);
-
-	spin_lock(&init_mm.page_table_lock);
-
-	set_pte_at(&init_mm, addr, ptep, pte_modify(*ptep, prot));
-	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
-
-	spin_unlock(&init_mm.page_table_lock);
-
-	return 0;
-}
-
-int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot)
-{
-	unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
-	unsigned long sz = numpages * PAGE_SIZE;
-
-	if (numpages <= 0)
-		return 0;
-
-	return apply_to_existing_page_range(&init_mm, start, sz, set_page_attr,
-					    (void *)pgprot_val(prot));
-}
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index fde1ed445ca4..f28859771440 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -138,10 +138,12 @@ void mark_initmem_nx(void)
 	unsigned long numpages = PFN_UP((unsigned long)_einittext) -
 				 PFN_DOWN((unsigned long)_sinittext);
 
-	if (v_block_mapped((unsigned long)_sinittext))
+	if (v_block_mapped((unsigned long)_sinittext)) {
 		mmu_mark_initmem_nx();
-	else
-		set_memory_attr((unsigned long)_sinittext, numpages, PAGE_KERNEL);
+	} else {
+		set_memory_nx((unsigned long)_sinittext, numpages);
+		set_memory_rw((unsigned long)_sinittext, numpages);
+	}
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
@@ -155,18 +157,14 @@ void mark_rodata_ro(void)
 		return;
 	}
 
-	numpages = PFN_UP((unsigned long)_etext) -
-		   PFN_DOWN((unsigned long)_stext);
-
-	set_memory_attr((unsigned long)_stext, numpages, PAGE_KERNEL_ROX);
 	/*
-	 * mark .rodata as read only. Use __init_begin rather than __end_rodata
-	 * to cover NOTES and EXCEPTION_TABLE.
+	 * mark .text and .rodata as read only. Use __init_begin rather than
+	 * __end_rodata to cover NOTES and EXCEPTION_TABLE.
 	 */
 	numpages = PFN_UP((unsigned long)__init_begin) -
-		   PFN_DOWN((unsigned long)__start_rodata);
+		   PFN_DOWN((unsigned long)_stext);
 
-	set_memory_attr((unsigned long)__start_rodata, numpages, PAGE_KERNEL_RO);
+	set_memory_ro((unsigned long)_stext, numpages);
 
 	// mark_initmem_nx() should have already run by now
 	ptdump_check_wx();
@@ -182,8 +180,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 		return;
 
 	if (enable)
-		set_memory_attr(addr, numpages, PAGE_KERNEL);
+		set_memory_p(addr, numpages);
 	else
-		set_memory_attr(addr, numpages, __pgprot(0));
+		set_memory_np(addr, numpages);
 }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h
index d6fa6e25234f..19a8d051ddf1 100644
--- a/arch/powerpc/perf/callchain.h
+++ b/arch/powerpc/perf/callchain.h
@@ -2,7 +2,6 @@
 #ifndef _POWERPC_PERF_CALLCHAIN_H
 #define _POWERPC_PERF_CALLCHAIN_H
 
-int read_user_stack_slow(const void __user *ptr, void *buf, int nb);
 void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 			    struct pt_regs *regs);
 void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
@@ -26,17 +25,11 @@ static inline int __read_user_stack(const void __user *ptr, void *ret,
 				    size_t size)
 {
 	unsigned long addr = (unsigned long)ptr;
-	int rc;
 
 	if (addr > TASK_SIZE - size || (addr & (size - 1)))
 		return -EFAULT;
 
-	rc = copy_from_user_nofault(ret, ptr, size);
-
-	if (IS_ENABLED(CONFIG_PPC64) && !radix_enabled() && rc)
-		return read_user_stack_slow(ptr, ret, size);
-
-	return rc;
+	return copy_from_user_nofault(ret, ptr, size);
 }
 
 #endif /* _POWERPC_PERF_CALLCHAIN_H */
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 8d0df4226328..488e8a21a11e 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -18,33 +18,6 @@
 
 #include "callchain.h"
 
-/*
- * On 64-bit we don't want to invoke hash_page on user addresses from
- * interrupt context, so if the access faults, we read the page tables
- * to find which page (if any) is mapped and access it directly. Radix
- * has no need for this so it doesn't use read_user_stack_slow.
- */
-int read_user_stack_slow(const void __user *ptr, void *buf, int nb)
-{
-
-	unsigned long addr = (unsigned long) ptr;
-	unsigned long offset;
-	struct page *page;
-	void *kaddr;
-
-	if (get_user_page_fast_only(addr, FOLL_WRITE, &page)) {
-		kaddr = page_address(page);
-
-		/* align address to page boundary */
-		offset = addr & ~PAGE_MASK;
-
-		memcpy(buf, kaddr + offset, nb);
-		put_page(page);
-		return 0;
-	}
-	return -EFAULT;
-}
-
 static int read_user_stack_64(const unsigned long __user *ptr, unsigned long *ret)
 {
 	return __read_user_stack(ptr, ret, sizeof(*ret));
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index e106909ff9c3..e7583fbcc8fa 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -1457,7 +1457,11 @@ static int trace_imc_event_init(struct perf_event *event)
 
 	event->hw.idx = -1;
 
-	event->pmu->task_ctx_nr = perf_hw_context;
+	/*
+	 * There can only be a single PMU for perf_hw_context events which is assigned to
+	 * core PMU. Hence use "perf_sw_context" for trace_imc.
+	 */
+	event->pmu->task_ctx_nr = perf_sw_context;
 	event->destroy = reset_global_refc;
 	return 0;
 }
diff --git a/arch/powerpc/platforms/8xx/pic.c b/arch/powerpc/platforms/8xx/pic.c
index f2ba837249d6..04a6abf14c29 100644
--- a/arch/powerpc/platforms/8xx/pic.c
+++ b/arch/powerpc/platforms/8xx/pic.c
@@ -153,6 +153,7 @@ int __init mpc8xx_pic_init(void)
 	if (mpc8xx_pic_host == NULL) {
 		printk(KERN_ERR "MPC8xx PIC: failed to allocate irq host!\n");
 		ret = -ENOMEM;
+		goto out;
 	}
 
 	ret = 0;
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index a208997ade88..87a95cbff2f3 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -111,6 +111,7 @@ config PPC_BOOK3S_64
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"
+	select PPC_FSL_BOOK3E
 	select PPC_FPU # Make it a choice ?
 	select PPC_SMP_MUXED_IPI
 	select PPC_DOORBELL
@@ -287,7 +288,7 @@ config FSL_BOOKE
 config PPC_FSL_BOOK3E
 	bool
 	select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64
-	select FSL_EMB_PERFMON
+	imply FSL_EMB_PERFMON
 	select PPC_SMP_MUXED_IPI
 	select PPC_DOORBELL
 	default y if FSL_BOOKE
diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c
index 72c25295c1c2..69c344c8884f 100644
--- a/arch/powerpc/platforms/powernv/rng.c
+++ b/arch/powerpc/platforms/powernv/rng.c
@@ -43,7 +43,11 @@ static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val)
 	unsigned long parity;
 
 	/* Calculate the parity of the value */
-	asm ("popcntd %0,%1" : "=r" (parity) : "r" (val));
+	asm (".machine push;   \
+	      .machine power7; \
+	      popcntd %0,%1;   \
+	      .machine pop;"
+	     : "=r" (parity) : "r" (val));
 
 	/* xor our value with the previous mask */
 	val ^= rng->mask;
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 90c9d3531694..4ba824568119 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -78,6 +78,9 @@ int remove_phb_dynamic(struct pci_controller *phb)
 
 	pseries_msi_free_domains(phb);
 
+	/* Keep a reference so phb isn't freed yet */
+	get_device(&host_bridge->dev);
+
 	/* Remove the PCI bus and unregister the bridge device from sysfs */
 	phb->bus = NULL;
 	pci_remove_bus(b);
@@ -101,6 +104,7 @@ int remove_phb_dynamic(struct pci_controller *phb)
 	 * the pcibios_free_controller_deferred() callback;
 	 * see pseries_root_bridge_prepare().
 	 */
+	put_device(&host_bridge->dev);
 
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c
index 8963eaffb1b7..39186ad6b3c3 100644
--- a/arch/powerpc/sysdev/fsl_gtm.c
+++ b/arch/powerpc/sysdev/fsl_gtm.c
@@ -86,7 +86,7 @@ static LIST_HEAD(gtms);
  */
 struct gtm_timer *gtm_get_timer16(void)
 {
-	struct gtm *gtm = NULL;
+	struct gtm *gtm;
 	int i;
 
 	list_for_each_entry(gtm, &gtms, list_node) {
@@ -103,7 +103,7 @@ struct gtm_timer *gtm_get_timer16(void)
 		spin_unlock_irq(&gtm->lock);
 	}
 
-	if (gtm)
+	if (!list_empty(&gtms))
 		return ERR_PTR(-EBUSY);
 	return ERR_PTR(-ENODEV);
 }
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
index 0bcaf35045e7..82e7f8069ae7 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
@@ -203,6 +203,8 @@
 		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
 		m25p,fast-read;
 		broken-flash-reset;
 	};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
index ac8a03f5867a..8d335233853a 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
@@ -205,6 +205,8 @@
 		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
 		m25p,fast-read;
 		broken-flash-reset;
 	};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
index 623998194bc1..6703cfc05588 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
@@ -213,6 +213,8 @@
 		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
 		m25p,fast-read;
 		broken-flash-reset;
 	};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
index cf605ba0d67e..ac0b56f7d2c9 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
@@ -178,6 +178,8 @@
 		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
 		m25p,fast-read;
 		broken-flash-reset;
 	};
diff --git a/arch/riscv/include/asm/module.lds.h b/arch/riscv/include/asm/module.lds.h
index 4254ff2ff049..1075beae1ac6 100644
--- a/arch/riscv/include/asm/module.lds.h
+++ b/arch/riscv/include/asm/module.lds.h
@@ -2,8 +2,8 @@
 /* Copyright (C) 2017 Andes Technology Corporation */
 #ifdef CONFIG_MODULE_SECTIONS
 SECTIONS {
-	.plt (NOLOAD) : { BYTE(0) }
-	.got (NOLOAD) : { BYTE(0) }
-	.got.plt (NOLOAD) : { BYTE(0) }
+	.plt : { BYTE(0) }
+	.got : { BYTE(0) }
+	.got.plt : { BYTE(0) }
 }
 #endif
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 60da0dcacf14..74d888c8d631 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -11,11 +11,17 @@
 #include <asm/page.h>
 #include <linux/const.h>
 
+#ifdef CONFIG_KASAN
+#define KASAN_STACK_ORDER 1
+#else
+#define KASAN_STACK_ORDER 0
+#endif
+
 /* thread information allocation */
 #ifdef CONFIG_64BIT
-#define THREAD_SIZE_ORDER	(2)
+#define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
 #else
-#define THREAD_SIZE_ORDER	(1)
+#define THREAD_SIZE_ORDER	(1 + KASAN_STACK_ORDER)
 #endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
index 8ecfc4c128bc..357f985041cb 100644
--- a/arch/riscv/kernel/perf_callchain.c
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -15,8 +15,8 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
 {
 	struct stackframe buftail;
 	unsigned long ra = 0;
-	unsigned long *user_frame_tail =
-			(unsigned long *)(fp - sizeof(struct stackframe));
+	unsigned long __user *user_frame_tail =
+		(unsigned long __user *)(fp - sizeof(struct stackframe));
 
 	/* Check accessibility of one struct frame_tail beyond */
 	if (!access_ok(user_frame_tail, sizeof(buftail)))
@@ -73,7 +73,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 
 static bool fill_callchain(void *entry, unsigned long pc)
 {
-	return perf_callchain_store(entry, pc);
+	return perf_callchain_store(entry, pc) == 0;
 }
 
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
index 07d1d2152ba5..e0609e1f0864 100644
--- a/arch/riscv/lib/memmove.S
+++ b/arch/riscv/lib/memmove.S
@@ -1,64 +1,316 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 Michael T. Kloos <michael@michaelkloos.com>
+ */
 
 #include <linux/linkage.h>
 #include <asm/asm.h>
 
-ENTRY(__memmove)
-WEAK(memmove)
-        move    t0, a0
-        move    t1, a1
-
-        beq     a0, a1, exit_memcpy
-        beqz    a2, exit_memcpy
-        srli    t2, a2, 0x2
-
-        slt     t3, a0, a1
-        beqz    t3, do_reverse
-
-        andi    a2, a2, 0x3
-        li      t4, 1
-        beqz    t2, byte_copy
-
-word_copy:
-        lw      t3, 0(a1)
-        addi    t2, t2, -1
-        addi    a1, a1, 4
-        sw      t3, 0(a0)
-        addi    a0, a0, 4
-        bnez    t2, word_copy
-        beqz    a2, exit_memcpy
-        j       byte_copy
-
-do_reverse:
-        add     a0, a0, a2
-        add     a1, a1, a2
-        andi    a2, a2, 0x3
-        li      t4, -1
-        beqz    t2, reverse_byte_copy
-
-reverse_word_copy:
-        addi    a1, a1, -4
-        addi    t2, t2, -1
-        lw      t3, 0(a1)
-        addi    a0, a0, -4
-        sw      t3, 0(a0)
-        bnez    t2, reverse_word_copy
-        beqz    a2, exit_memcpy
-
-reverse_byte_copy:
-        addi    a0, a0, -1
-        addi    a1, a1, -1
+SYM_FUNC_START(__memmove)
+SYM_FUNC_START_WEAK(memmove)
+	/*
+	 * Returns
+	 *   a0 - dest
+	 *
+	 * Parameters
+	 *   a0 - Inclusive first byte of dest
+	 *   a1 - Inclusive first byte of src
+	 *   a2 - Length of copy n
+	 *
+	 * Because the return matches the parameter register a0,
+	 * we will not clobber or modify that register.
+	 *
+	 * Note: This currently only works on little-endian.
+	 * To port to big-endian, reverse the direction of shifts
+	 * in the 2 misaligned fixup copy loops.
+	 */
 
+	/* Return if nothing to do */
+	beq a0, a1, return_from_memmove
+	beqz a2, return_from_memmove
+
+	/*
+	 * Register Uses
+	 *      Forward Copy: a1 - Index counter of src
+	 *      Reverse Copy: a4 - Index counter of src
+	 *      Forward Copy: t3 - Index counter of dest
+	 *      Reverse Copy: t4 - Index counter of dest
+	 *   Both Copy Modes: t5 - Inclusive first multibyte/aligned of dest
+	 *   Both Copy Modes: t6 - Non-Inclusive last multibyte/aligned of dest
+	 *   Both Copy Modes: t0 - Link / Temporary for load-store
+	 *   Both Copy Modes: t1 - Temporary for load-store
+	 *   Both Copy Modes: t2 - Temporary for load-store
+	 *   Both Copy Modes: a5 - dest to src alignment offset
+	 *   Both Copy Modes: a6 - Shift ammount
+	 *   Both Copy Modes: a7 - Inverse Shift ammount
+	 *   Both Copy Modes: a2 - Alternate breakpoint for unrolled loops
+	 */
+
+	/*
+	 * Solve for some register values now.
+	 * Byte copy does not need t5 or t6.
+	 */
+	mv   t3, a0
+	add  t4, a0, a2
+	add  a4, a1, a2
+
+	/*
+	 * Byte copy if copying less than (2 * SZREG) bytes. This can
+	 * cause problems with the bulk copy implementation and is
+	 * small enough not to bother.
+	 */
+	andi t0, a2, -(2 * SZREG)
+	beqz t0, byte_copy
+
+	/*
+	 * Now solve for t5 and t6.
+	 */
+	andi t5, t3, -SZREG
+	andi t6, t4, -SZREG
+	/*
+	 * If dest(Register t3) rounded down to the nearest naturally
+	 * aligned SZREG address, does not equal dest, then add SZREG
+	 * to find the low-bound of SZREG alignment in the dest memory
+	 * region.  Note that this could overshoot the dest memory
+	 * region if n is less than SZREG.  This is one reason why
+	 * we always byte copy if n is less than SZREG.
+	 * Otherwise, dest is already naturally aligned to SZREG.
+	 */
+	beq  t5, t3, 1f
+		addi t5, t5, SZREG
+	1:
+
+	/*
+	 * If the dest and src are co-aligned to SZREG, then there is
+	 * no need for the full rigmarole of a full misaligned fixup copy.
+	 * Instead, do a simpler co-aligned copy.
+	 */
+	xor  t0, a0, a1
+	andi t1, t0, (SZREG - 1)
+	beqz t1, coaligned_copy
+	/* Fall through to misaligned fixup copy */
+
+misaligned_fixup_copy:
+	bltu a1, a0, misaligned_fixup_copy_reverse
+
+misaligned_fixup_copy_forward:
+	jal  t0, byte_copy_until_aligned_forward
+
+	andi a5, a1, (SZREG - 1) /* Find the alignment offset of src (a1) */
+	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
+	sub  a5, a1, t3 /* Find the difference between src and dest */
+	andi a1, a1, -SZREG /* Align the src pointer */
+	addi a2, t6, SZREG /* The other breakpoint for the unrolled loop*/
+
+	/*
+	 * Compute The Inverse Shift
+	 * a7 = XLEN - a6 = XLEN + -a6
+	 * 2s complement negation to find the negative: -a6 = ~a6 + 1
+	 * Add that to XLEN.  XLEN = SZREG * 8.
+	 */
+	not  a7, a6
+	addi a7, a7, (SZREG * 8 + 1)
+
+	/*
+	 * Fix Misalignment Copy Loop - Forward
+	 * load_val0 = load_ptr[0];
+	 * do {
+	 * 	load_val1 = load_ptr[1];
+	 * 	store_ptr += 2;
+	 * 	store_ptr[0 - 2] = (load_val0 >> {a6}) | (load_val1 << {a7});
+	 *
+	 * 	if (store_ptr == {a2})
+	 * 		break;
+	 *
+	 * 	load_val0 = load_ptr[2];
+	 * 	load_ptr += 2;
+	 * 	store_ptr[1 - 2] = (load_val1 >> {a6}) | (load_val0 << {a7});
+	 *
+	 * } while (store_ptr != store_ptr_end);
+	 * store_ptr = store_ptr_end;
+	 */
+
+	REG_L t0, (0 * SZREG)(a1)
+	1:
+	REG_L t1, (1 * SZREG)(a1)
+	addi  t3, t3, (2 * SZREG)
+	srl   t0, t0, a6
+	sll   t2, t1, a7
+	or    t2, t0, t2
+	REG_S t2, ((0 * SZREG) - (2 * SZREG))(t3)
+
+	beq   t3, a2, 2f
+
+	REG_L t0, (2 * SZREG)(a1)
+	addi  a1, a1, (2 * SZREG)
+	srl   t1, t1, a6
+	sll   t2, t0, a7
+	or    t2, t1, t2
+	REG_S t2, ((1 * SZREG) - (2 * SZREG))(t3)
+
+	bne   t3, t6, 1b
+	2:
+	mv    t3, t6 /* Fix the dest pointer in case the loop was broken */
+
+	add  a1, t3, a5 /* Restore the src pointer */
+	j byte_copy_forward /* Copy any remaining bytes */
+
+misaligned_fixup_copy_reverse:
+	jal  t0, byte_copy_until_aligned_reverse
+
+	andi a5, a4, (SZREG - 1) /* Find the alignment offset of src (a4) */
+	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
+	sub  a5, a4, t4 /* Find the difference between src and dest */
+	andi a4, a4, -SZREG /* Align the src pointer */
+	addi a2, t5, -SZREG /* The other breakpoint for the unrolled loop*/
+
+	/*
+	 * Compute The Inverse Shift
+	 * a7 = XLEN - a6 = XLEN + -a6
+	 * 2s complement negation to find the negative: -a6 = ~a6 + 1
+	 * Add that to XLEN.  XLEN = SZREG * 8.
+	 */
+	not  a7, a6
+	addi a7, a7, (SZREG * 8 + 1)
+
+	/*
+	 * Fix Misalignment Copy Loop - Reverse
+	 * load_val1 = load_ptr[0];
+	 * do {
+	 * 	load_val0 = load_ptr[-1];
+	 * 	store_ptr -= 2;
+	 * 	store_ptr[1] = (load_val0 >> {a6}) | (load_val1 << {a7});
+	 *
+	 * 	if (store_ptr == {a2})
+	 * 		break;
+	 *
+	 * 	load_val1 = load_ptr[-2];
+	 * 	load_ptr -= 2;
+	 * 	store_ptr[0] = (load_val1 >> {a6}) | (load_val0 << {a7});
+	 *
+	 * } while (store_ptr != store_ptr_end);
+	 * store_ptr = store_ptr_end;
+	 */
+
+	REG_L t1, ( 0 * SZREG)(a4)
+	1:
+	REG_L t0, (-1 * SZREG)(a4)
+	addi  t4, t4, (-2 * SZREG)
+	sll   t1, t1, a7
+	srl   t2, t0, a6
+	or    t2, t1, t2
+	REG_S t2, ( 1 * SZREG)(t4)
+
+	beq   t4, a2, 2f
+
+	REG_L t1, (-2 * SZREG)(a4)
+	addi  a4, a4, (-2 * SZREG)
+	sll   t0, t0, a7
+	srl   t2, t1, a6
+	or    t2, t0, t2
+	REG_S t2, ( 0 * SZREG)(t4)
+
+	bne   t4, t5, 1b
+	2:
+	mv    t4, t5 /* Fix the dest pointer in case the loop was broken */
+
+	add  a4, t4, a5 /* Restore the src pointer */
+	j byte_copy_reverse /* Copy any remaining bytes */
+
+/*
+ * Simple copy loops for SZREG co-aligned memory locations.
+ * These also make calls to do byte copies for any unaligned
+ * data at their terminations.
+ */
+coaligned_copy:
+	bltu a1, a0, coaligned_copy_reverse
+
+coaligned_copy_forward:
+	jal t0, byte_copy_until_aligned_forward
+
+	1:
+	REG_L t1, ( 0 * SZREG)(a1)
+	addi  a1, a1, SZREG
+	addi  t3, t3, SZREG
+	REG_S t1, (-1 * SZREG)(t3)
+	bne   t3, t6, 1b
+
+	j byte_copy_forward /* Copy any remaining bytes */
+
+coaligned_copy_reverse:
+	jal t0, byte_copy_until_aligned_reverse
+
+	1:
+	REG_L t1, (-1 * SZREG)(a4)
+	addi  a4, a4, -SZREG
+	addi  t4, t4, -SZREG
+	REG_S t1, ( 0 * SZREG)(t4)
+	bne   t4, t5, 1b
+
+	j byte_copy_reverse /* Copy any remaining bytes */
+
+/*
+ * These are basically sub-functions within the function.  They
+ * are used to byte copy until the dest pointer is in alignment.
+ * At which point, a bulk copy method can be used by the
+ * calling code.  These work on the same registers as the bulk
+ * copy loops.  Therefore, the register values can be picked
+ * up from where they were left and we avoid code duplication
+ * without any overhead except the call in and return jumps.
+ */
+byte_copy_until_aligned_forward:
+	beq  t3, t5, 2f
+	1:
+	lb   t1,  0(a1)
+	addi a1, a1, 1
+	addi t3, t3, 1
+	sb   t1, -1(t3)
+	bne  t3, t5, 1b
+	2:
+	jalr zero, 0x0(t0) /* Return to multibyte copy loop */
+
+byte_copy_until_aligned_reverse:
+	beq  t4, t6, 2f
+	1:
+	lb   t1, -1(a4)
+	addi a4, a4, -1
+	addi t4, t4, -1
+	sb   t1,  0(t4)
+	bne  t4, t6, 1b
+	2:
+	jalr zero, 0x0(t0) /* Return to multibyte copy loop */
+
+/*
+ * Simple byte copy loops.
+ * These will byte copy until they reach the end of data to copy.
+ * At that point, they will call to return from memmove.
+ */
 byte_copy:
-        lb      t3, 0(a1)
-        addi    a2, a2, -1
-        sb      t3, 0(a0)
-        add     a1, a1, t4
-        add     a0, a0, t4
-        bnez    a2, byte_copy
-
-exit_memcpy:
-        move a0, t0
-        move a1, t1
-        ret
-END(__memmove)
+	bltu a1, a0, byte_copy_reverse
+
+byte_copy_forward:
+	beq  t3, t4, 2f
+	1:
+	lb   t1,  0(a1)
+	addi a1, a1, 1
+	addi t3, t3, 1
+	sb   t1, -1(t3)
+	bne  t3, t4, 1b
+	2:
+	ret
+
+byte_copy_reverse:
+	beq  t4, t3, 2f
+	1:
+	lb   t1, -1(a4)
+	addi a4, a4, -1
+	addi t4, t4, -1
+	sb   t1,  0(t4)
+	bne  t4, t3, 1b
+	2:
+
+return_from_memmove:
+	ret
+
+SYM_FUNC_END(memmove)
+SYM_FUNC_END(__memmove)
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index ffab16369bea..74f80443b195 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -65,7 +65,7 @@ struct rt_signal_frame {
  */
 static inline bool invalid_frame_pointer(void __user *fp, int fplen)
 {
-	if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen))
+	if ((((unsigned long) fp) & 15) || !access_ok(fp, fplen))
 		return true;
 
 	return false;
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 6ead1e240457..8ca67a692683 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -224,7 +224,7 @@ void mconsole_go(struct mc_request *req)
 
 void mconsole_stop(struct mc_request *req)
 {
-	deactivate_fd(req->originating_fd, MCONSOLE_IRQ);
+	block_signals();
 	os_set_fd_block(req->originating_fd, 1);
 	mconsole_reply(req, "stopped", 0, 0);
 	for (;;) {
@@ -247,6 +247,7 @@ void mconsole_stop(struct mc_request *req)
 	}
 	os_set_fd_block(req->originating_fd, 0);
 	mconsole_reply(req, "", 0, 0);
+	unblock_signals();
 }
 
 static DEFINE_SPINLOCK(mc_devices_lock);
diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h
index f512704a9ec7..22b39de73c24 100644
--- a/arch/um/include/asm/xor.h
+++ b/arch/um/include/asm/xor.h
@@ -4,8 +4,10 @@
 
 #ifdef CONFIG_64BIT
 #undef CONFIG_X86_32
+#define TT_CPU_INF_XOR_DEFAULT (AVX_SELECT(&xor_block_sse_pf64))
 #else
 #define CONFIG_X86_32 1
+#define TT_CPU_INF_XOR_DEFAULT (AVX_SELECT(&xor_block_8regs))
 #endif
 
 #include <asm/cpufeature.h>
@@ -16,7 +18,7 @@
 #undef XOR_SELECT_TEMPLATE
 /* pick an arbitrary one - measuring isn't possible with inf-cpu */
 #define XOR_SELECT_TEMPLATE(x)	\
-	(time_travel_mode == TT_MODE_INFCPU ? &xor_block_8regs : NULL)
+	(time_travel_mode == TT_MODE_INFCPU ? TT_CPU_INF_XOR_DEFAULT : x))
 #endif
 
 #endif
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1f96809606ac..819f8c2e2c67 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2798,6 +2798,11 @@ config IA32_AOUT
 config X86_X32
 	bool "x32 ABI for 64-bit mode"
 	depends on X86_64
+	# llvm-objcopy does not convert x86_64 .note.gnu.property or
+	# compressed debug sections to x86_x32 properly:
+	# https://github.com/ClangBuiltLinux/linux/issues/514
+	# https://github.com/ClangBuiltLinux/linux/issues/1141
+	depends on $(success,$(OBJCOPY) --version | head -n1 | grep -qv llvm)
 	help
 	  Include code to run binaries for the x32 native 32-bit ABI
 	  for 64-bit processors.  An x32 process gets access to the
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 97ede6fb15f2..265cb203d9d5 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -281,7 +281,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
 	INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
 	INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
-	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE),
 	INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE),
 	INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE),
 	EVENT_EXTRA_END
@@ -5466,7 +5466,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con
 			/* Disabled fixed counters which are not in CPUID */
 			c->idxmsk64 &= intel_ctrl;
 
-			if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES)
+			/*
+			 * Don't extend the pseudo-encoding to the
+			 * generic counters
+			 */
+			if (!use_fixed_pseudo_encoding(c->code))
 				c->idxmsk64 |= (1ULL << num_counters) - 1;
 		}
 		c->idxmsk64 &=
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 2d33bba9a144..215aed65e978 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -472,7 +472,7 @@ static u64 pt_config_filters(struct perf_event *event)
 			pt->filters.filter[range].msr_b = filter->msr_b;
 		}
 
-		rtit_ctl |= filter->config << pt_address_ranges[range].reg_off;
+		rtit_ctl |= (u64)filter->config << pt_address_ranges[range].reg_off;
 	}
 
 	return rtit_ctl;
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index bab883c0b6fe..66570e95af39 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -77,9 +77,9 @@ do {								\
  */
 #define __WARN_FLAGS(flags)					\
 do {								\
-	__auto_type f = BUGFLAG_WARNING|(flags);		\
+	__auto_type __flags = BUGFLAG_WARNING|(flags);		\
 	instrumentation_begin();				\
-	_BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE);			\
+	_BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE);		\
 	instrumentation_end();					\
 } while (0)
 
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 8d55bd11848c..e087cd7837c3 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -99,7 +99,8 @@
 }
 
 #define ASM_CALL_ARG0							\
-	"call %P[__func]				\n"
+	"call %P[__func]				\n"		\
+	ASM_REACHABLE
 
 #define ASM_CALL_ARG1							\
 	"movq	%[arg1], %%rdi				\n"		\
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 01759199d723..d9bb5cdb5db2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -505,6 +505,7 @@ struct kvm_pmu {
 	u64 global_ctrl_mask;
 	u64 global_ovf_ctrl_mask;
 	u64 reserved_bits;
+	u64 raw_event_mask;
 	u8 version;
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
index b85147d75626..d71c7e8b738d 100644
--- a/arch/x86/include/asm/msi.h
+++ b/arch/x86/include/asm/msi.h
@@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 /* Structs and defines for the X86 specific MSI message format */
 
 typedef struct x86_msi_data {
-	u32	vector			:  8,
-		delivery_mode		:  3,
-		dest_mode_logical	:  1,
-		reserved		:  2,
-		active_low		:  1,
-		is_level		:  1;
-
-	u32	dmar_subhandle;
+	union {
+		struct {
+			u32	vector			:  8,
+				delivery_mode		:  3,
+				dest_mode_logical	:  1,
+				reserved		:  2,
+				active_low		:  1,
+				is_level		:  1;
+		};
+		u32	dmar_subhandle;
+	};
 } __attribute__ ((packed)) arch_msi_msg_data_t;
 #define arch_msi_msg_data	x86_msi_data
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8fc1b5003713..a2b6626c681f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -241,6 +241,11 @@ struct x86_pmu_capability {
 #define INTEL_PMC_IDX_FIXED_SLOTS	(INTEL_PMC_IDX_FIXED + 3)
 #define INTEL_PMC_MSK_FIXED_SLOTS	(1ULL << INTEL_PMC_IDX_FIXED_SLOTS)
 
+static inline bool use_fixed_pseudo_encoding(u64 code)
+{
+	return !(code & 0xff);
+}
+
 /*
  * We model BTS tracing as another fixed-mode PMC.
  *
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 14bcd59bcdee..94ac7402c1ac 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1319,6 +1319,17 @@ static int __init disable_acpi_pci(const struct dmi_system_id *d)
 	return 0;
 }
 
+static int __init disable_acpi_xsdt(const struct dmi_system_id *d)
+{
+	if (!acpi_force) {
+		pr_notice("%s detected: force use of acpi=rsdt\n", d->ident);
+		acpi_gbl_do_not_use_xsdt = TRUE;
+	} else {
+		pr_notice("Warning: DMI blacklist says broken, but acpi XSDT forced\n");
+	}
+	return 0;
+}
+
 static int __init dmi_disable_acpi(const struct dmi_system_id *d)
 {
 	if (!acpi_force) {
@@ -1442,6 +1453,19 @@ static const struct dmi_system_id acpi_dmi_table[] __initconst = {
 		     DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"),
 		     },
 	 },
+	/*
+	 * Boxes that need ACPI XSDT use disabled due to corrupted tables
+	 */
+	{
+	 .callback = disable_acpi_xsdt,
+	 .ident = "Advantech DAC-BJ01",
+	 .matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "Bearlake CRB Board"),
+		     DMI_MATCH(DMI_BIOS_VERSION, "V1.12"),
+		     DMI_MATCH(DMI_BIOS_DATE, "02/01/2011"),
+		     },
+	 },
 	{}
 };
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 882213df3713..71f336425e58 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1435,8 +1435,12 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 	hpet_rtc_timer_reinit();
 	memset(&curr_time, 0, sizeof(struct rtc_time));
 
-	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
-		mc146818_get_time(&curr_time);
+	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) {
+		if (unlikely(mc146818_get_time(&curr_time) < 0)) {
+			pr_err_ratelimited("unable to read current time from RTC\n");
+			return IRQ_HANDLED;
+		}
+	}
 
 	if (hpet_rtc_flags & RTC_UIE &&
 	    curr_time.tm_sec != hpet_prev_update_sec) {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 811c7aaf23aa..bd7b65081eb0 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -510,7 +510,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 		} else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) {
 			ipi_bitmap <<= min - apic_id;
 			min = apic_id;
-		} else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
+		} else if (apic_id > min && apic_id < min + KVM_IPI_CLUSTER_SIZE) {
 			max = apic_id < max ? max : apic_id;
 		} else {
 			ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index ea028e736831..3d68dfb10aaa 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -12,10 +12,9 @@ enum insn_type {
 };
 
 /*
- * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax
- * The REX.W cancels the effect of any data16.
+ * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax
  */
-static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 };
+static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 };
 
 static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
 {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9a144ca8e146..3747a754a8e8 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1614,11 +1614,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 		goto exception;
 	}
 
-	if (!seg_desc.p) {
-		err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
-		goto exception;
-	}
-
 	dpl = seg_desc.dpl;
 
 	switch (seg) {
@@ -1658,6 +1653,10 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	case VCPU_SREG_TR:
 		if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9))
 			goto exception;
+		if (!seg_desc.p) {
+			err_vec = NP_VECTOR;
+			goto exception;
+		}
 		old_desc = seg_desc;
 		seg_desc.type |= 2; /* busy */
 		ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc,
@@ -1682,6 +1681,11 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 		break;
 	}
 
+	if (!seg_desc.p) {
+		err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
+		goto exception;
+	}
+
 	if (seg_desc.s) {
 		/* mark segment as accessed */
 		if (!(seg_desc.type & 1)) {
@@ -3510,8 +3514,10 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt)
 {
 	u64 tsc_aux = 0;
 
-	if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux))
+	if (!ctxt->ops->guest_has_rdpid(ctxt))
 		return emulate_ud(ctxt);
+
+	ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux);
 	ctxt->dst.val = tsc_aux;
 	return X86EMUL_CONTINUE;
 }
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 2092834efba1..762b43f0d919 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -236,7 +236,7 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
 	struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic);
 	int ret;
 
-	if (!synic->active && !host)
+	if (!synic->active && (!host || data))
 		return 1;
 
 	trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host);
@@ -282,6 +282,9 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
 	case HV_X64_MSR_EOM: {
 		int i;
 
+		if (!synic->active)
+			break;
+
 		for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
 			kvm_hv_notify_acked_sint(vcpu, i);
 		break;
@@ -446,6 +449,9 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
 	struct kvm_lapic_irq irq;
 	int ret, vector;
 
+	if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm))
+		return -EINVAL;
+
 	if (sint >= ARRAY_SIZE(synic->sint))
 		return -EINVAL;
 
@@ -658,7 +664,7 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu);
 
-	if (!synic->active && !host)
+	if (!synic->active && (!host || config))
 		return 1;
 
 	if (unlikely(!host && hv_vcpu->enforce_cpuid && new_config.direct_mode &&
@@ -687,7 +693,7 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count,
 	struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer);
 	struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu);
 
-	if (!synic->active && !host)
+	if (!synic->active && (!host || count))
 		return 1;
 
 	trace_kvm_hv_stimer_set_count(hv_stimer_to_vcpu(stimer)->vcpu_id,
@@ -1749,7 +1755,7 @@ struct kvm_hv_hcall {
 	sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS];
 };
 
-static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex)
+static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 {
 	int i;
 	gpa_t gpa;
@@ -1765,7 +1771,8 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 	int sparse_banks_len;
 	bool all_cpus;
 
-	if (!ex) {
+	if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST ||
+	    hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE) {
 		if (hc->fast) {
 			flush.address_space = hc->ingpa;
 			flush.flags = hc->outgpa;
@@ -1819,7 +1826,8 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 
 		if (!all_cpus) {
 			if (hc->fast) {
-				if (sparse_banks_len > HV_HYPERCALL_MAX_XMM_REGISTERS - 1)
+				/* XMM0 is already consumed, each XMM holds two sparse banks. */
+				if (sparse_banks_len > 2 * (HV_HYPERCALL_MAX_XMM_REGISTERS - 1))
 					return HV_STATUS_INVALID_HYPERCALL_INPUT;
 				for (i = 0; i < sparse_banks_len; i += 2) {
 					sparse_banks[i] = sse128_lo(hc->xmm[i / 2 + 1]);
@@ -1874,7 +1882,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
 	}
 }
 
-static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex)
+static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct hv_send_ipi_ex send_ipi_ex;
@@ -1887,8 +1895,9 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 	int sparse_banks_len;
 	u32 vector;
 	bool all_cpus;
+	int i;
 
-	if (!ex) {
+	if (hc->code == HVCALL_SEND_IPI) {
 		if (!hc->fast) {
 			if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi,
 						    sizeof(send_ipi))))
@@ -1907,9 +1916,15 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 
 		trace_kvm_hv_send_ipi(vector, sparse_banks[0]);
 	} else {
-		if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex,
-					    sizeof(send_ipi_ex))))
-			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+		if (!hc->fast) {
+			if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex,
+						    sizeof(send_ipi_ex))))
+				return HV_STATUS_INVALID_HYPERCALL_INPUT;
+		} else {
+			send_ipi_ex.vector = (u32)hc->ingpa;
+			send_ipi_ex.vp_set.format = hc->outgpa;
+			send_ipi_ex.vp_set.valid_bank_mask = sse128_lo(hc->xmm[0]);
+		}
 
 		trace_kvm_hv_send_ipi_ex(send_ipi_ex.vector,
 					 send_ipi_ex.vp_set.format,
@@ -1917,8 +1932,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 
 		vector = send_ipi_ex.vector;
 		valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask;
-		sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
-			sizeof(sparse_banks[0]);
+		sparse_banks_len = bitmap_weight(&valid_bank_mask, 64);
 
 		all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
 
@@ -1928,12 +1942,27 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 		if (!sparse_banks_len)
 			goto ret_success;
 
-		if (kvm_read_guest(kvm,
-				   hc->ingpa + offsetof(struct hv_send_ipi_ex,
-							vp_set.bank_contents),
-				   sparse_banks,
-				   sparse_banks_len))
-			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+		if (!hc->fast) {
+			if (kvm_read_guest(kvm,
+					   hc->ingpa + offsetof(struct hv_send_ipi_ex,
+								vp_set.bank_contents),
+					   sparse_banks,
+					   sparse_banks_len * sizeof(sparse_banks[0])))
+				return HV_STATUS_INVALID_HYPERCALL_INPUT;
+		} else {
+			/*
+			 * The lower half of XMM0 is already consumed, each XMM holds
+			 * two sparse banks.
+			 */
+			if (sparse_banks_len > (2 * HV_HYPERCALL_MAX_XMM_REGISTERS - 1))
+				return HV_STATUS_INVALID_HYPERCALL_INPUT;
+			for (i = 0; i < sparse_banks_len; i++) {
+				if (i % 2)
+					sparse_banks[i] = sse128_lo(hc->xmm[(i + 1) / 2]);
+				else
+					sparse_banks[i] = sse128_hi(hc->xmm[i / 2]);
+			}
+		}
 	}
 
 check_and_send_ipi:
@@ -2095,6 +2124,7 @@ static bool is_xmm_fast_hypercall(struct kvm_hv_hcall *hc)
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX:
+	case HVCALL_SEND_IPI_EX:
 		return true;
 	}
 
@@ -2246,46 +2276,28 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 				kvm_hv_hypercall_complete_userspace;
 		return 0;
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST:
-		if (unlikely(!hc.rep_cnt || hc.rep_idx)) {
-			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
-			break;
-		}
-		ret = kvm_hv_flush_tlb(vcpu, &hc, false);
-		break;
-	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
-		if (unlikely(hc.rep)) {
-			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
-			break;
-		}
-		ret = kvm_hv_flush_tlb(vcpu, &hc, false);
-		break;
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
 		if (unlikely(!hc.rep_cnt || hc.rep_idx)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_flush_tlb(vcpu, &hc, true);
+		ret = kvm_hv_flush_tlb(vcpu, &hc);
 		break;
+	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
 	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX:
 		if (unlikely(hc.rep)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_flush_tlb(vcpu, &hc, true);
+		ret = kvm_hv_flush_tlb(vcpu, &hc);
 		break;
 	case HVCALL_SEND_IPI:
-		if (unlikely(hc.rep)) {
-			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
-			break;
-		}
-		ret = kvm_hv_send_ipi(vcpu, &hc, false);
-		break;
 	case HVCALL_SEND_IPI_EX:
-		if (unlikely(hc.fast || hc.rep)) {
+		if (unlikely(hc.rep)) {
 			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
-		ret = kvm_hv_send_ipi(vcpu, &hc, true);
+		ret = kvm_hv_send_ipi(vcpu, &hc);
 		break;
 	case HVCALL_POST_DEBUG_DATA:
 	case HVCALL_RETRIEVE_DEBUG_DATA:
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 68b420289d7e..fb09cd22cb7f 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -226,6 +226,7 @@ struct x86_emulate_ops {
 	bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt);
 	bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt);
 	bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt);
+	bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt);
 
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 91c2dc9f198d..4d92fb4fdf69 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -987,6 +987,10 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 	*r = -1;
 
 	if (irq->shorthand == APIC_DEST_SELF) {
+		if (KVM_BUG_ON(!src, kvm)) {
+			*r = 0;
+			return true;
+		}
 		*r = kvm_apic_set_irq(src->vcpu, irq, dest_map);
 		return true;
 	}
@@ -2242,10 +2246,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 
 void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
-
-	apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
-		     | (kvm_lapic_get_reg(apic, APIC_TASKPRI) & 4));
+	apic_set_tpr(vcpu->arch.apic, (cr8 & 0x0f) << 4);
 }
 
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index e9688a9f7b57..7bb165c23233 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -49,6 +49,7 @@
 			       X86_CR4_LA57)
 
 #define KVM_MMU_CR0_ROLE_BITS (X86_CR0_PG | X86_CR0_WP)
+#define KVM_MMU_EFER_ROLE_BITS (EFER_LME | EFER_NX)
 
 static __always_inline u64 rsvd_bits(int s, int e)
 {
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 913d52a7923e..a1811f51eda9 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -34,9 +34,8 @@
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) true
 	#ifdef CONFIG_X86_64
 	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
-	#define CMPXCHG cmpxchg
+	#define CMPXCHG "cmpxchgq"
 	#else
-	#define CMPXCHG cmpxchg64
 	#define PT_MAX_FULL_LEVELS 2
 	#endif
 #elif PTTYPE == 32
@@ -52,7 +51,7 @@
 	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
 	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) true
-	#define CMPXCHG cmpxchg
+	#define CMPXCHG "cmpxchgl"
 #elif PTTYPE == PTTYPE_EPT
 	#define pt_element_t u64
 	#define guest_walker guest_walkerEPT
@@ -65,7 +64,9 @@
 	#define PT_GUEST_DIRTY_SHIFT 9
 	#define PT_GUEST_ACCESSED_SHIFT 8
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad)
-	#define CMPXCHG cmpxchg64
+	#ifdef CONFIG_X86_64
+	#define CMPXCHG "cmpxchgq"
+	#endif
 	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
 #else
 	#error Invalid PTTYPE value
@@ -147,43 +148,39 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			       pt_element_t __user *ptep_user, unsigned index,
 			       pt_element_t orig_pte, pt_element_t new_pte)
 {
-	int npages;
-	pt_element_t ret;
-	pt_element_t *table;
-	struct page *page;
-
-	npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
-	if (likely(npages == 1)) {
-		table = kmap_atomic(page);
-		ret = CMPXCHG(&table[index], orig_pte, new_pte);
-		kunmap_atomic(table);
-
-		kvm_release_page_dirty(page);
-	} else {
-		struct vm_area_struct *vma;
-		unsigned long vaddr = (unsigned long)ptep_user & PAGE_MASK;
-		unsigned long pfn;
-		unsigned long paddr;
-
-		mmap_read_lock(current->mm);
-		vma = find_vma_intersection(current->mm, vaddr, vaddr + PAGE_SIZE);
-		if (!vma || !(vma->vm_flags & VM_PFNMAP)) {
-			mmap_read_unlock(current->mm);
-			return -EFAULT;
-		}
-		pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-		paddr = pfn << PAGE_SHIFT;
-		table = memremap(paddr, PAGE_SIZE, MEMREMAP_WB);
-		if (!table) {
-			mmap_read_unlock(current->mm);
-			return -EFAULT;
-		}
-		ret = CMPXCHG(&table[index], orig_pte, new_pte);
-		memunmap(table);
-		mmap_read_unlock(current->mm);
-	}
+	int r = -EFAULT;
+
+	if (!user_access_begin(ptep_user, sizeof(pt_element_t)))
+		return -EFAULT;
+
+#ifdef CMPXCHG
+	asm volatile("1:" LOCK_PREFIX CMPXCHG " %[new], %[ptr]\n"
+		     "mov $0, %[r]\n"
+		     "setnz %b[r]\n"
+		     "2:"
+		     _ASM_EXTABLE_UA(1b, 2b)
+		     : [ptr] "+m" (*ptep_user),
+		       [old] "+a" (orig_pte),
+		       [r] "+q" (r)
+		     : [new] "r" (new_pte)
+		     : "memory");
+#else
+	asm volatile("1:" LOCK_PREFIX "cmpxchg8b %[ptr]\n"
+		     "movl $0, %[r]\n"
+		     "jz 2f\n"
+		     "incl %[r]\n"
+		     "2:"
+		     _ASM_EXTABLE_UA(1b, 2b)
+		     : [ptr] "+m" (*ptep_user),
+		       [old] "+A" (orig_pte),
+		       [r] "+rm" (r)
+		     : [new_lo] "b" ((u32)new_pte),
+		       [new_hi] "c" ((u32)(new_pte >> 32))
+		     : "memory");
+#endif
 
-	return (ret != orig_pte);
+	user_access_end();
+	return r;
 }
 
 static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index d479b2b12125..853780eb033b 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -99,15 +99,18 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 }
 
 /*
- * Finds the next valid root after root (or the first valid root if root
- * is NULL), takes a reference on it, and returns that next root. If root
- * is not NULL, this thread should have already taken a reference on it, and
- * that reference will be dropped. If no valid root is found, this
- * function will return NULL.
+ * Returns the next root after @prev_root (or the first root if @prev_root is
+ * NULL).  A reference to the returned root is acquired, and the reference to
+ * @prev_root is released (the caller obviously must hold a reference to
+ * @prev_root if it's non-NULL).
+ *
+ * If @only_valid is true, invalid roots are skipped.
+ *
+ * Returns NULL if the end of tdp_mmu_roots was reached.
  */
 static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 					      struct kvm_mmu_page *prev_root,
-					      bool shared)
+					      bool shared, bool only_valid)
 {
 	struct kvm_mmu_page *next_root;
 
@@ -121,9 +124,14 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 		next_root = list_first_or_null_rcu(&kvm->arch.tdp_mmu_roots,
 						   typeof(*next_root), link);
 
-	while (next_root && !kvm_tdp_mmu_get_root(kvm, next_root))
+	while (next_root) {
+		if ((!only_valid || !next_root->role.invalid) &&
+		    kvm_tdp_mmu_get_root(kvm, next_root))
+			break;
+
 		next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
 				&next_root->link, typeof(*next_root), link);
+	}
 
 	rcu_read_unlock();
 
@@ -143,13 +151,19 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
  * mode. In the unlikely event that this thread must free a root, the lock
  * will be temporarily dropped and reacquired in write mode.
  */
-#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared)	\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared);		\
-	     _root;							\
-	     _root = tdp_mmu_next_root(_kvm, _root, _shared))		\
-		if (kvm_mmu_page_as_id(_root) != _as_id) {		\
+#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid);	\
+	     _root;								\
+	     _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid))	\
+		if (kvm_mmu_page_as_id(_root) != _as_id) {			\
 		} else
 
+#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared)	\
+	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
+
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared)		\
+	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, false)
+
 #define for_each_tdp_mmu_root(_kvm, _root, _as_id)				\
 	list_for_each_entry_rcu(_root, &_kvm->arch.tdp_mmu_roots, link,		\
 				lockdep_is_held_type(&kvm->mmu_lock, 0) ||	\
@@ -199,7 +213,10 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
 
 	role = page_role_for_level(vcpu, vcpu->arch.mmu->shadow_root_level);
 
-	/* Check for an existing root before allocating a new one. */
+	/*
+	 * Check for an existing root before allocating a new one.  Note, the
+	 * role check prevents consuming an invalid root.
+	 */
 	for_each_tdp_mmu_root(kvm, root, kvm_mmu_role_as_id(role)) {
 		if (root->role.word == role.word &&
 		    kvm_tdp_mmu_get_root(kvm, root))
@@ -1271,7 +1288,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
 		spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
 			     slot->base_gfn + slot->npages, min_level);
 
@@ -1299,6 +1316,9 @@ retry:
 		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
 
+		if (!is_shadow_present_pte(iter.old_spte))
+			continue;
+
 		if (spte_ad_need_write_protect(iter.old_spte)) {
 			if (is_writable_pte(iter.old_spte))
 				new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
@@ -1342,7 +1362,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
 		spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
 				slot->base_gfn + slot->npages);
 
@@ -1467,7 +1487,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+	for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
 		zap_collapsible_spte_range(kvm, root, slot);
 }
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index ba3681cd38ab..39468b637d2e 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -10,9 +10,6 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
 __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm *kvm,
 						     struct kvm_mmu_page *root)
 {
-	if (root->role.invalid)
-		return false;
-
 	return refcount_inc_not_zero(&root->tdp_mmu_root_count);
 }
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index f256f01056bd..62333f9756a3 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -96,8 +96,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 
 static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 				  u64 config, bool exclude_user,
-				  bool exclude_kernel, bool intr,
-				  bool in_tx, bool in_tx_cp)
+				  bool exclude_kernel, bool intr)
 {
 	struct perf_event *event;
 	struct perf_event_attr attr = {
@@ -113,16 +112,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 
 	attr.sample_period = get_sample_period(pmc, pmc->counter);
 
-	if (in_tx)
-		attr.config |= HSW_IN_TX;
-	if (in_tx_cp) {
+	if ((attr.config & HSW_IN_TX_CHECKPOINTED) &&
+	    guest_cpuid_is_intel(pmc->vcpu)) {
 		/*
 		 * HSW_IN_TX_CHECKPOINTED is not supported with nonzero
 		 * period. Just clear the sample period so at least
 		 * allocating the counter doesn't fail.
 		 */
 		attr.sample_period = 0;
-		attr.config |= HSW_IN_TX_CHECKPOINTED;
 	}
 
 	event = perf_event_create_kernel_counter(&attr, -1, current,
@@ -178,6 +175,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	struct kvm *kvm = pmc->vcpu->kvm;
 	struct kvm_pmu_event_filter *filter;
 	int i;
+	struct kvm_pmu *pmu = vcpu_to_pmu(pmc->vcpu);
 	bool allow_event = true;
 
 	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
@@ -217,7 +215,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	}
 
 	if (type == PERF_TYPE_RAW)
-		config = eventsel & AMD64_RAW_EVENT_MASK;
+		config = eventsel & pmu->raw_event_mask;
 
 	if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
 		return;
@@ -228,9 +226,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	pmc_reprogram_counter(pmc, type, config,
 			      !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
 			      !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-			      eventsel & ARCH_PERFMON_EVENTSEL_INT,
-			      (eventsel & HSW_IN_TX),
-			      (eventsel & HSW_IN_TX_CHECKPOINTED));
+			      eventsel & ARCH_PERFMON_EVENTSEL_INT);
 }
 EXPORT_SYMBOL_GPL(reprogram_gp_counter);
 
@@ -266,7 +262,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 			      kvm_x86_ops.pmu_ops->find_fixed_event(idx),
 			      !(en_field & 0x2), /* exclude user */
 			      !(en_field & 0x1), /* exclude kernel */
-			      pmi, false, false);
+			      pmi);
 }
 EXPORT_SYMBOL_GPL(reprogram_fixed_counter);
 
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index cdbb48e12745..3d3f8dfb8045 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -799,7 +799,7 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
-	int idx, ret = -EINVAL;
+	int idx, ret = 0;
 
 	if (!kvm_arch_has_assigned_device(kvm) ||
 	    !irq_remapping_cap(IRQ_POSTING_CAP))
@@ -810,7 +810,13 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	WARN_ON(guest_irq >= irq_rt->nr_rt_entries);
+
+	if (guest_irq >= irq_rt->nr_rt_entries ||
+		hlist_empty(&irq_rt->map[guest_irq])) {
+		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+			     guest_irq, irq_rt->nr_rt_entries);
+		goto out;
+	}
 
 	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
 		struct vcpu_data vcpu_info;
@@ -941,15 +947,10 @@ out:
 void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	u64 entry;
-	/* ID = 0xff (broadcast), ID > 0xff (reserved) */
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	/*
-	 * Since the host physical APIC id is 8 bits,
-	 * we can support host APIC ID upto 255.
-	 */
-	if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
+	if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
 		return;
 
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 06f8034f62e4..3faf1d9c6c91 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -261,12 +261,10 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	/* MSR_EVNTSELn */
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
 	if (pmc) {
-		if (data == pmc->eventsel)
-			return 0;
-		if (!(data & pmu->reserved_bits)) {
+		data &= ~pmu->reserved_bits;
+		if (data != pmc->eventsel)
 			reprogram_gp_counter(pmc, data);
-			return 0;
-		}
+		return 0;
 	}
 
 	return 1;
@@ -283,6 +281,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
 	pmu->reserved_bits = 0xfffffff000280000ull;
+	pmu->raw_event_mask = AMD64_RAW_EVENT_MASK;
 	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index ff0855c03c91..cf2d8365aeb4 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -22,6 +22,8 @@
 #include <asm/svm.h>
 #include <asm/sev-common.h>
 
+#include "kvm_cache_regs.h"
+
 #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
 
 #define	IOPM_SIZE PAGE_SIZE * 3
@@ -497,7 +499,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
 #define AVIC_LOGICAL_ID_ENTRY_VALID_BIT			31
 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK		(1 << 31)
 
-#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK	(0xFFULL)
+#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK	GENMASK_ULL(11, 0)
 #define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK	(0xFFFFFFFFFFULL << 12)
 #define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK		(1ULL << 62)
 #define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK		(1ULL << 63)
diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c
index 98aa981c04ec..8cdc62c74a96 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.c
+++ b/arch/x86/kvm/svm/svm_onhyperv.c
@@ -4,7 +4,6 @@
  */
 
 #include <linux/kvm_host.h>
-#include "kvm_cache_regs.h"
 
 #include <asm/mshyperv.h>
 
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 6427d95de01c..7abe77c8b5d0 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -396,6 +396,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	struct kvm_pmc *pmc;
 	u32 msr = msr_info->index;
 	u64 data = msr_info->data;
+	u64 reserved_bits;
 
 	switch (msr) {
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
@@ -451,7 +452,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)
 				return 0;
-			if (!(data & pmu->reserved_bits)) {
+			reserved_bits = pmu->reserved_bits;
+			if ((pmc->idx == 2) &&
+			    (pmu->raw_event_mask & HSW_IN_TX_CHECKPOINTED))
+				reserved_bits ^= HSW_IN_TX_CHECKPOINTED;
+			if (!(data & reserved_bits)) {
 				reprogram_gp_counter(pmc, data);
 				return 0;
 			}
@@ -478,6 +483,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->version = 0;
 	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->raw_event_mask = X86_RAW_EVENT_MASK;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
@@ -524,8 +530,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
 	if (entry &&
 	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
-	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
-		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) {
+		pmu->reserved_bits ^= HSW_IN_TX;
+		pmu->raw_event_mask |= (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED);
+	}
 
 	bitmap_set(pmu->all_valid_pmc_idx,
 		0, pmu->nr_arch_gp_counters);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 61bc54748f22..5e2983959f23 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1605,8 +1605,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return r;
 	}
 
-	/* Update reserved bits */
-	if ((efer ^ old_efer) & EFER_NX)
+	if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS)
 		kvm_mmu_reset_context(vcpu);
 
 	return 0;
@@ -7394,6 +7393,11 @@ static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt)
 	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR);
 }
 
+static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt)
+{
+	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID);
+}
+
 static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
 {
 	return kvm_register_read_raw(emul_to_vcpu(ctxt), reg);
@@ -7476,6 +7480,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.guest_has_long_mode = emulator_guest_has_long_mode,
 	.guest_has_movbe     = emulator_guest_has_movbe,
 	.guest_has_fxsr      = emulator_guest_has_fxsr,
+	.guest_has_rdpid     = emulator_guest_has_rdpid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
 	.get_hflags          = emulator_get_hflags,
 	.exiting_smm         = emulator_exiting_smm,
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 59ba2968af1b..511172d70825 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -854,13 +854,11 @@ done:
 			nr_invalidate);
 }
 
-static bool tlb_is_not_lazy(int cpu)
+static bool tlb_is_not_lazy(int cpu, void *data)
 {
 	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
 }
 
-static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
-
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
 EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);
 
@@ -889,36 +887,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	 * up on the new contents of what used to be page tables, while
 	 * doing a speculative memory access.
 	 */
-	if (info->freed_tables) {
+	if (info->freed_tables)
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
-	} else {
-		/*
-		 * Although we could have used on_each_cpu_cond_mask(),
-		 * open-coding it has performance advantages, as it eliminates
-		 * the need for indirect calls or retpolines. In addition, it
-		 * allows to use a designated cpumask for evaluating the
-		 * condition, instead of allocating one.
-		 *
-		 * This code works under the assumption that there are no nested
-		 * TLB flushes, an assumption that is already made in
-		 * flush_tlb_mm_range().
-		 *
-		 * cond_cpumask is logically a stack-local variable, but it is
-		 * more efficient to have it off the stack and not to allocate
-		 * it on demand. Preemption is disabled and this code is
-		 * non-reentrant.
-		 */
-		struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask);
-		int cpu;
-
-		cpumask_clear(cond_cpumask);
-
-		for_each_cpu(cpu, cpumask) {
-			if (tlb_is_not_lazy(cpu))
-				__cpumask_set_cpu(cpu, cond_cpumask);
-		}
-		on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true);
-	}
+	else
+		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
+				(void *)info, 1, cpumask);
 }
 
 void flush_tlb_multi(const struct cpumask *cpumask,
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 6665f8802098..736008f2fccc 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -40,7 +40,8 @@ static void msr_save_context(struct saved_context *ctxt)
 	struct saved_msr *end = msr + ctxt->saved_msrs.num;
 
 	while (msr < end) {
-		msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q);
+		if (msr->valid)
+			rdmsrl(msr->info.msr_no, msr->info.reg.q);
 		msr++;
 	}
 }
@@ -424,8 +425,10 @@ static int msr_build_context(const u32 *msr_id, const int num)
 	}
 
 	for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) {
+		u64 dummy;
+
 		msr_array[i].info.msr_no	= msr_id[j];
-		msr_array[i].valid		= false;
+		msr_array[i].valid		= !rdmsrl_safe(msr_id[j], &dummy);
 		msr_array[i].info.reg.q		= 0;
 	}
 	saved_msrs->num   = total_num;
@@ -500,10 +503,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c)
 	return ret;
 }
 
+static void pm_save_spec_msr(void)
+{
+	u32 spec_msr_id[] = {
+		MSR_IA32_SPEC_CTRL,
+		MSR_IA32_TSX_CTRL,
+		MSR_TSX_FORCE_ABORT,
+		MSR_IA32_MCU_OPT_CTRL,
+		MSR_AMD64_LS_CFG,
+	};
+
+	msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id));
+}
+
 static int pm_check_save_msr(void)
 {
 	dmi_check_system(msr_save_dmi_table);
 	pm_cpu_check(msr_save_cpu_table);
+	pm_save_spec_msr();
 
 	return 0;
 }
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index e13b0b49fcdf..d7249f4c90f1 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -512,10 +512,7 @@ irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
 	return ret;
 }
 
-bool is_xen_pmu(int cpu)
-{
-	return (get_xenpmu_data() != NULL);
-}
+bool is_xen_pmu;
 
 void xen_pmu_init(int cpu)
 {
@@ -526,7 +523,7 @@ void xen_pmu_init(int cpu)
 
 	BUILD_BUG_ON(sizeof(struct xen_pmu_data) > PAGE_SIZE);
 
-	if (xen_hvm_domain())
+	if (xen_hvm_domain() || (cpu != 0 && !is_xen_pmu))
 		return;
 
 	xenpmu_data = (struct xen_pmu_data *)get_zeroed_page(GFP_KERNEL);
@@ -547,7 +544,8 @@ void xen_pmu_init(int cpu)
 	per_cpu(xenpmu_shared, cpu).xenpmu_data = xenpmu_data;
 	per_cpu(xenpmu_shared, cpu).flags = 0;
 
-	if (cpu == 0) {
+	if (!is_xen_pmu) {
+		is_xen_pmu = true;
 		perf_register_guest_info_callbacks(&xen_guest_cbs);
 		xen_pmu_arch_init();
 	}
diff --git a/arch/x86/xen/pmu.h b/arch/x86/xen/pmu.h
index 0e83a160589b..65c58894fc79 100644
--- a/arch/x86/xen/pmu.h
+++ b/arch/x86/xen/pmu.h
@@ -4,6 +4,8 @@
 
 #include <xen/interface/xenpmu.h>
 
+extern bool is_xen_pmu;
+
 irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
 #ifdef CONFIG_XEN_HAVE_VPMU
 void xen_pmu_init(int cpu);
@@ -12,7 +14,6 @@ void xen_pmu_finish(int cpu);
 static inline void xen_pmu_init(int cpu) {}
 static inline void xen_pmu_finish(int cpu) {}
 #endif
-bool is_xen_pmu(int cpu);
 bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
 bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);
 int pmu_apic_update(uint32_t reg);
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index 6ff3c887e0b9..b70afdff419c 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -20,6 +20,12 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void)
 	xen_vcpu_setup(0);
 
 	/*
+	 * Called again in case the kernel boots on vcpu >= MAX_VIRT_CPUS.
+	 * Refer to comments in xen_hvm_init_time_ops().
+	 */
+	xen_hvm_init_time_ops();
+
+	/*
 	 * The alternative logic (which patches the unlock/lock) runs before
 	 * the smp bootup up code is activated. Hence we need to set this up
 	 * the core kernel is being patched. Otherwise we will have only
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 477c484eb202..cd5539fc5eb4 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -129,7 +129,7 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	per_cpu(xen_irq_work, cpu).irq = rc;
 	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 
-	if (is_xen_pmu(cpu)) {
+	if (is_xen_pmu) {
 		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
 		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
 					     xen_pmu_irq_handler,
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index d9c945ee1100..9ef0a5cca96e 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -558,6 +558,11 @@ static void xen_hvm_setup_cpu_clockevents(void)
 
 void __init xen_hvm_init_time_ops(void)
 {
+	static bool hvm_time_initialized;
+
+	if (hvm_time_initialized)
+		return;
+
 	/*
 	 * vector callback is needed otherwise we cannot receive interrupts
 	 * on cpu > 0 and at this point we don't know how many cpus are
@@ -567,7 +572,22 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
-		pr_info("Xen doesn't support pvclock on HVM, disable pv timer");
+		pr_info_once("Xen doesn't support pvclock on HVM, disable pv timer");
+		return;
+	}
+
+	/*
+	 * Only MAX_VIRT_CPUS 'vcpu_info' are embedded inside 'shared_info'.
+	 * The __this_cpu_read(xen_vcpu) is still NULL when Xen HVM guest
+	 * boots on vcpu >= MAX_VIRT_CPUS (e.g., kexec), To access
+	 * __this_cpu_read(xen_vcpu) via xen_clocksource_read() will panic.
+	 *
+	 * The xen_hvm_init_time_ops() should be called again later after
+	 * __this_cpu_read(xen_vcpu) is available.
+	 */
+	if (!__this_cpu_read(xen_vcpu)) {
+		pr_info("Delay xen_init_time_common() as kernel is running on vcpu=%d\n",
+			xen_vcpu_nr(0));
 		return;
 	}
 
@@ -577,6 +597,8 @@ void __init xen_hvm_init_time_ops(void)
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
 
 	x86_platform.set_wallclock = xen_set_wallclock;
+
+	hvm_time_initialized = true;
 }
 #endif
 
diff --git a/arch/xtensa/boot/dts/xtfpga-flash-128m.dtsi b/arch/xtensa/boot/dts/xtfpga-flash-128m.dtsi
index 9bf8bad1dd18..c33932568aa7 100644
--- a/arch/xtensa/boot/dts/xtfpga-flash-128m.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga-flash-128m.dtsi
@@ -8,19 +8,19 @@
 			reg = <0x00000000 0x08000000>;
 			bank-width = <2>;
 			device-width = <2>;
-			partition@0x0 {
+			partition@0 {
 				label = "data";
 				reg = <0x00000000 0x06000000>;
 			};
-			partition@0x6000000 {
+			partition@6000000 {
 				label = "boot loader area";
 				reg = <0x06000000 0x00800000>;
 			};
-			partition@0x6800000 {
+			partition@6800000 {
 				label = "kernel image";
 				reg = <0x06800000 0x017e0000>;
 			};
-			partition@0x7fe0000 {
+			partition@7fe0000 {
 				label = "boot environment";
 				reg = <0x07fe0000 0x00020000>;
 			};
diff --git a/arch/xtensa/boot/dts/xtfpga-flash-16m.dtsi b/arch/xtensa/boot/dts/xtfpga-flash-16m.dtsi
index 40c2f81f7cb6..7bde2ab2d6fb 100644
--- a/arch/xtensa/boot/dts/xtfpga-flash-16m.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga-flash-16m.dtsi
@@ -8,19 +8,19 @@
 			reg = <0x08000000 0x01000000>;
 			bank-width = <2>;
 			device-width = <2>;
-			partition@0x0 {
+			partition@0 {
 				label = "boot loader area";
 				reg = <0x00000000 0x00400000>;
 			};
-			partition@0x400000 {
+			partition@400000 {
 				label = "kernel image";
 				reg = <0x00400000 0x00600000>;
 			};
-			partition@0xa00000 {
+			partition@a00000 {
 				label = "data";
 				reg = <0x00a00000 0x005e0000>;
 			};
-			partition@0xfe0000 {
+			partition@fe0000 {
 				label = "boot environment";
 				reg = <0x00fe0000 0x00020000>;
 			};
diff --git a/arch/xtensa/boot/dts/xtfpga-flash-4m.dtsi b/arch/xtensa/boot/dts/xtfpga-flash-4m.dtsi
index fb8d3a9f33c2..0655b868749a 100644
--- a/arch/xtensa/boot/dts/xtfpga-flash-4m.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga-flash-4m.dtsi
@@ -8,11 +8,11 @@
 			reg = <0x08000000 0x00400000>;
 			bank-width = <2>;
 			device-width = <2>;
-			partition@0x0 {
+			partition@0 {
 				label = "boot loader area";
 				reg = <0x00000000 0x003f0000>;
 			};
-			partition@0x3f0000 {
+			partition@3f0000 {
 				label = "boot environment";
 				reg = <0x003f0000 0x00010000>;
 			};
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index bd5aeb795567..a63eca126657 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -411,6 +411,10 @@ extern  void update_mmu_cache(struct vm_area_struct * vma,
 
 typedef pte_t *pte_addr_t;
 
+void update_mmu_tlb(struct vm_area_struct *vma,
+		    unsigned long address, pte_t *ptep);
+#define __HAVE_ARCH_UPDATE_MMU_TLB
+
 #endif /* !defined (__ASSEMBLY__) */
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 7f63aca6a0d3..9dd4efe1bf0b 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -226,8 +226,8 @@ extern unsigned long get_wchan(struct task_struct *p);
 
 #define xtensa_set_sr(x, sr) \
 	({ \
-	 unsigned int v = (unsigned int)(x); \
-	 __asm__ __volatile__ ("wsr %0, "__stringify(sr) :: "a"(v)); \
+	 __asm__ __volatile__ ("wsr %0, "__stringify(sr) :: \
+			       "a"((unsigned int)(x))); \
 	 })
 
 #define xtensa_get_sr(sr) \
diff --git a/arch/xtensa/kernel/jump_label.c b/arch/xtensa/kernel/jump_label.c
index 61cf6497a646..0dde21e0d3de 100644
--- a/arch/xtensa/kernel/jump_label.c
+++ b/arch/xtensa/kernel/jump_label.c
@@ -61,7 +61,7 @@ static void patch_text(unsigned long addr, const void *data, size_t sz)
 			.data = data,
 		};
 		stop_machine_cpuslocked(patch_text_stop_machine,
-					&patch, NULL);
+					&patch, cpu_online_mask);
 	} else {
 		unsigned long flags;
 
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index f436cf2efd8b..27a477dae232 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -162,6 +162,12 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
+void update_mmu_tlb(struct vm_area_struct *vma,
+		    unsigned long address, pte_t *ptep)
+{
+	local_flush_tlb_page(vma, address);
+}
+
 #ifdef CONFIG_DEBUG_TLB_SANITY
 
 static unsigned get_pte_for_vaddr(unsigned vaddr)