Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

There were quite a few overlapping sets of changes here.

Daniel's bug fix for off-by-ones in the new BPF branch instructions,
along with the added allowances for "data_end > ptr + x" forms
collided with the metadata additions.

Along with those three changes came veritifer test cases, which in
their final form I tried to group together properly.  If I had just
trimmed GIT's conflict tags as-is, this would have split up the
meta tests unnecessarily.

In the socketmap code, a set of preemption disabling changes
overlapped with the rename of bpf_compute_data_end() to
bpf_compute_data_pointers().

Changes were made to the mv88e6060.c driver set addr method
which got removed in net-next.

The hyperv transport socket layer had a locking change in 'net'
which overlapped with a change of socket state macro usage
in 'net-next'.

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

64 files changed, 507 insertions, 224 deletions

diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 47d3a1ab08d2..817e5cfef83a 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -131,7 +131,7 @@ endif
 KBUILD_CFLAGS	+=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm
 KBUILD_AFLAGS	+=$(CFLAGS_ABI) $(AFLAGS_ISA) $(arch-y) $(tune-y) -include asm/unified.h -msoft-float
 
-CHECKFLAGS	+= -D__arm__
+CHECKFLAGS	+= -D__arm__ -m32
 
 #Default value
 head-y		:= arch/arm/kernel/head$(MMUEXT).o
diff --git a/arch/arm/boot/compressed/debug.S b/arch/arm/boot/compressed/debug.S
index 5392ee63338f..8f6e37177de1 100644
--- a/arch/arm/boot/compressed/debug.S
+++ b/arch/arm/boot/compressed/debug.S
@@ -23,7 +23,11 @@ ENTRY(putc)
 	strb	r0, [r1]
 	mov	r0, #0x03		@ SYS_WRITEC
    ARM(	svc	#0x123456	)
+#ifdef CONFIG_CPU_V7M
+ THUMB(	bkpt	#0xab		)
+#else
  THUMB(	svc	#0xab		)
+#endif
 	mov	pc, lr
 	.align	2
 1:	.word	_GLOBAL_OFFSET_TABLE_ - .
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 7ff0811e61db..4960722aab32 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -178,7 +178,7 @@
 			};
 
 			i2c0: i2c@11000 {
-				compatible = "marvell,mv64xxx-i2c";
+				compatible = "marvell,mv78230-a0-i2c", "marvell,mv64xxx-i2c";
 				reg = <0x11000 0x20>;
 				#address-cells = <1>;
 				#size-cells = <0>;
@@ -189,7 +189,7 @@
 			};
 
 			i2c1: i2c@11100 {
-				compatible = "marvell,mv64xxx-i2c";
+				compatible = "marvell,mv78230-a0-i2c", "marvell,mv64xxx-i2c";
 				reg = <0x11100 0x20>;
 				#address-cells = <1>;
 				#size-cells = <0>;
diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
index 63a5af898165..cf0087b4c9e1 100644
--- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
+++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
@@ -67,8 +67,8 @@
 				pinctrl-0 = <&pinctrl_macb0_default>;
 				phy-mode = "rmii";
 
-				ethernet-phy@1 {
-					reg = <0x1>;
+				ethernet-phy@0 {
+					reg = <0x0>;
 					interrupt-parent = <&pioA>;
 					interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>;
 					pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index c7e9ccf2bc87..cbc26001247b 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -309,7 +309,7 @@
 				vddana-supply = <&vdd_3v3_lp_reg>;
 				vref-supply = <&vdd_3v3_lp_reg>;
 				pinctrl-names = "default";
-				pinctrl-0 = <&pinctrl_adc_default>;
+				pinctrl-0 = <&pinctrl_adc_default &pinctrl_adtrg_default>;
 				status = "okay";
 			};
 
@@ -340,6 +340,20 @@
 					bias-disable;
 				};
 
+				/*
+				 * The ADTRG pin can work on any edge type.
+				 * In here it's being pulled up, so need to
+				 * connect it to ground to get an edge e.g.
+				 * Trigger can be configured on falling, rise
+				 * or any edge, and the pull-up can be changed
+				 * to pull-down or left floating according to
+				 * needs.
+				 */
+				pinctrl_adtrg_default: adtrg_default {
+					pinmux = <PIN_PD31__ADTRG>;
+					bias-pull-up;
+				};
+
 				pinctrl_charger_chglev: charger_chglev {
 					pinmux = <PIN_PA12__GPIO>;
 					bias-disable;
diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
index 82651c3eb682..b8565fc33eea 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
@@ -18,12 +18,9 @@
 	compatible = "raspberrypi,model-zero-w", "brcm,bcm2835";
 	model = "Raspberry Pi Zero W";
 
-	/* Needed by firmware to properly init UARTs */
-	aliases {
-		uart0 = "/soc/serial@7e201000";
-		uart1 = "/soc/serial@7e215040";
-		serial0 = "/soc/serial@7e201000";
-		serial1 = "/soc/serial@7e215040";
+	chosen {
+		/* 8250 auxiliary UART instead of pl011 */
+		stdout-path = "serial1:115200n8";
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
index 20725ca487f3..c71a0d73d2a2 100644
--- a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
+++ b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts
@@ -8,6 +8,11 @@
 	compatible = "raspberrypi,3-model-b", "brcm,bcm2837";
 	model = "Raspberry Pi 3 Model B";
 
+	chosen {
+		/* 8250 auxiliary UART instead of pl011 */
+		stdout-path = "serial1:115200n8";
+	};
+
 	memory {
 		reg = <0 0x40000000>;
 	};
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 431dcfc900c0..013431e3d7c3 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -20,8 +20,13 @@
 	#address-cells = <1>;
 	#size-cells = <1>;
 
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
 	chosen {
-		bootargs = "earlyprintk console=ttyAMA0";
+		stdout-path = "serial0:115200n8";
 	};
 
 	thermal-zones {
diff --git a/arch/arm/boot/dts/gemini.dtsi b/arch/arm/boot/dts/gemini.dtsi
index c68e8d430234..f0d178c77153 100644
--- a/arch/arm/boot/dts/gemini.dtsi
+++ b/arch/arm/boot/dts/gemini.dtsi
@@ -145,11 +145,12 @@
 		};
 
 		watchdog@41000000 {
-			compatible = "cortina,gemini-watchdog";
+			compatible = "cortina,gemini-watchdog", "faraday,ftwdt010";
 			reg = <0x41000000 0x1000>;
 			interrupts = <3 IRQ_TYPE_LEVEL_HIGH>;
 			resets = <&syscon GEMINI_RESET_WDOG>;
 			clocks = <&syscon GEMINI_CLK_APB>;
+			clock-names = "PCLK";
 		};
 
 		uart0: serial@42000000 {
diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi
index f46814a7ea44..4d308d17f040 100644
--- a/arch/arm/boot/dts/imx7d.dtsi
+++ b/arch/arm/boot/dts/imx7d.dtsi
@@ -144,10 +144,10 @@
 		interrupt-names = "msi";
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0x7>;
-		interrupt-map = <0 0 0 1 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 2 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 3 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 4 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-map = <0 0 0 1 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 2 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 3 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 4 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&clks IMX7D_PCIE_CTRL_ROOT_CLK>,
 			 <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>,
 			 <&clks IMX7D_PCIE_PHY_ROOT_CLK>;
diff --git a/arch/arm/boot/dts/moxart.dtsi b/arch/arm/boot/dts/moxart.dtsi
index 1f4c795d3f72..da7b3237bfe9 100644
--- a/arch/arm/boot/dts/moxart.dtsi
+++ b/arch/arm/boot/dts/moxart.dtsi
@@ -87,9 +87,10 @@
 		};
 
 		watchdog: watchdog@98500000 {
-			compatible = "moxa,moxart-watchdog";
+			compatible = "moxa,moxart-watchdog", "faraday,ftwdt010";
 			reg = <0x98500000 0x10>;
 			clocks = <&clk_apb>;
+			clock-names = "PCLK";
 		};
 
 		sdhci: sdhci@98e00000 {
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index 38d2216c7ead..b1a26b42d190 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -1430,6 +1430,7 @@
 				atmel,min-sample-rate-hz = <200000>;
 				atmel,max-sample-rate-hz = <20000000>;
 				atmel,startup-time-ms = <4>;
+				atmel,trigger-edge-type = <IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index b147cb0dc14b..eef072a21acc 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -311,8 +311,8 @@
 					#size-cells = <0>;
 					reg = <0>;
 
-					tcon1_in_drc1: endpoint@0 {
-						reg = <0>;
+					tcon1_in_drc1: endpoint@1 {
+						reg = <1>;
 						remote-endpoint = <&drc1_out_tcon1>;
 					};
 				};
@@ -1012,8 +1012,8 @@
 					#size-cells = <0>;
 					reg = <1>;
 
-					be1_out_drc1: endpoint@0 {
-						reg = <0>;
+					be1_out_drc1: endpoint@1 {
+						reg = <1>;
 						remote-endpoint = <&drc1_in_be1>;
 					};
 				};
@@ -1042,8 +1042,8 @@
 					#size-cells = <0>;
 					reg = <0>;
 
-					drc1_in_be1: endpoint@0 {
-						reg = <0>;
+					drc1_in_be1: endpoint@1 {
+						reg = <1>;
 						remote-endpoint = <&be1_out_drc1>;
 					};
 				};
@@ -1053,8 +1053,8 @@
 					#size-cells = <0>;
 					reg = <1>;
 
-					drc1_out_tcon1: endpoint@0 {
-						reg = <0>;
+					drc1_out_tcon1: endpoint@1 {
+						reg = <1>;
 						remote-endpoint = <&tcon1_in_drc1>;
 					};
 				};
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index ea9646cc2a0e..0a498cb3fad8 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -115,7 +115,11 @@ ENTRY(printascii)
 		mov	r1, r0
 		mov	r0, #0x04		@ SYS_WRITE0
 	ARM(	svc	#0x123456	)
+#ifdef CONFIG_CPU_V7M
+	THUMB(	bkpt	#0xab		)
+#else
 	THUMB(	svc	#0xab		)
+#endif
 		ret	lr
 ENDPROC(printascii)
 
@@ -124,7 +128,11 @@ ENTRY(printch)
 		strb	r0, [r1]
 		mov	r0, #0x03		@ SYS_WRITEC
 	ARM(	svc	#0x123456	)
+#ifdef CONFIG_CPU_V7M
+	THUMB(	bkpt	#0xab		)
+#else
 	THUMB(	svc	#0xab		)
+#endif
 		ret	lr
 ENDPROC(printch)
 
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 71a34e8c345a..57058ac46f49 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -32,6 +32,7 @@
 #include <asm/mach/arch.h>
 
 #include "db8500-regs.h"
+#include "pm_domains.h"
 
 static int __init ux500_l2x0_unlock(void)
 {
@@ -157,6 +158,9 @@ static const struct of_device_id u8500_local_bus_nodes[] = {
 
 static void __init u8500_init_machine(void)
 {
+	/* Initialize ux500 power domains */
+	ux500_pm_domains_init();
+
 	/* automatically probe child nodes of dbx5x0 devices */
 	if (of_machine_is_compatible("st-ericsson,u8540"))
 		of_platform_populate(NULL, u8500_local_bus_nodes,
diff --git a/arch/arm/mach-ux500/pm.c b/arch/arm/mach-ux500/pm.c
index a970e7fcba9e..f6c33a0c1c61 100644
--- a/arch/arm/mach-ux500/pm.c
+++ b/arch/arm/mach-ux500/pm.c
@@ -19,7 +19,6 @@
 #include <linux/of_address.h>
 
 #include "db8500-regs.h"
-#include "pm_domains.h"
 
 /* ARM WFI Standby signal register */
 #define PRCM_ARM_WFI_STANDBY    (prcmu_base + 0x130)
@@ -203,7 +202,4 @@ void __init ux500_pm_init(u32 phy_base, u32 size)
 
 	/* Set up ux500 suspend callbacks. */
 	suspend_set_ops(UX500_SUSPEND_OPS);
-
-	/* Initialize ux500 power domains */
-	ux500_pm_domains_init();
 }
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 3b8e728cc944..91537d90f5f5 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -344,6 +344,11 @@ void __init arm_mm_memblock_reserve(void)
 	 * reserved here.
 	 */
 #endif
+	/*
+	 * In any case, always ensure address 0 is never used as many things
+	 * get very confused if 0 is returned as a legitimate address.
+	 */
+	memblock_reserve(0, 1);
 }
 
 void __init adjust_lowmem_bounds(void)
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
index caf8b6fbe5e3..d06e34b5d192 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
@@ -61,13 +61,6 @@
 	chosen {
 		stdout-path = "serial0:115200n8";
 	};
-
-	reg_vcc3v3: vcc3v3 {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-	};
 };
 
 &ehci0 {
@@ -91,7 +84,7 @@
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>;
 	cd-inverted;
 	disable-wp;
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index 8263a8a504a8..f2aa2a81de4d 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -336,7 +336,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xf6000000 0  0xf6000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
 			num-lanes = <1>;
 			clocks = <&cpm_clk 1 13>;
@@ -362,7 +362,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xf7000000 0  0xf7000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
 
 			num-lanes = <1>;
@@ -389,7 +389,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xf8000000 0  0xf8000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cpm_icu 0 ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cpm_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
 
 			num-lanes = <1>;
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index b71ee6c83668..4fe70323abb3 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -335,7 +335,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xfa000000 0  0xfa000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 22 IRQ_TYPE_LEVEL_HIGH>;
 			num-lanes = <1>;
 			clocks = <&cps_clk 1 13>;
@@ -361,7 +361,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xfb000000 0  0xfb000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 24 IRQ_TYPE_LEVEL_HIGH>;
 
 			num-lanes = <1>;
@@ -388,7 +388,7 @@
 				/* non-prefetchable memory */
 				0x82000000 0 0xfc000000 0  0xfc000000 0 0xf00000>;
 			interrupt-map-mask = <0 0 0 0>;
-			interrupt-map = <0 0 0 0 &cps_icu 0 ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 0 &cps_icu ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
 			interrupts = <ICU_GRP_NSR 23 IRQ_TYPE_LEVEL_HIGH>;
 
 			num-lanes = <1>;
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index 4786c67b5e65..d9d885006a8e 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -62,6 +62,7 @@
 		brightness-levels = <256 128 64 16 8 4 0>;
 		default-brightness-level = <6>;
 
+		power-supply = <&reg_12v>;
 		enable-gpios = <&gpio6 7 GPIO_ACTIVE_HIGH>;
 	};
 
@@ -83,6 +84,15 @@
 		regulator-always-on;
 	};
 
+	reg_12v: regulator2 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-12V";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	rsnd_ak4613: sound {
 		compatible = "simple-audio-card";
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 6d615cb6e64d..41d61840fb99 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -582,7 +582,7 @@
 	vop_mmu: iommu@ff373f00 {
 		compatible = "rockchip,iommu";
 		reg = <0x0 0xff373f00 0x0 0x100>;
-		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "vop_mmu";
 		#iommu-cells = <0>;
 		status = "disabled";
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index 19fbaa5e7bdd..1070c8264c13 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -740,7 +740,7 @@
 	iep_mmu: iommu@ff900800 {
 		compatible = "rockchip,iommu";
 		reg = <0x0 0xff900800 0x0 0x100>;
-		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "iep_mmu";
 		#iommu-cells = <0>;
 		status = "disabled";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
index 7fd4bfcaa38e..fef82274a39d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts
@@ -371,10 +371,10 @@
 				regulator-always-on;
 				regulator-boot-on;
 				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-max-microvolt = <3000000>;
 				regulator-state-mem {
 					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <3300000>;
+					regulator-suspend-microvolt = <3000000>;
 				};
 			};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index 53ff3d191a1d..910628d18add 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -325,12 +325,12 @@
 			vcc_sd: LDO_REG4 {
 				regulator-name = "vcc_sd";
 				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-max-microvolt = <3000000>;
 				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <3300000>;
+					regulator-suspend-microvolt = <3000000>;
 				};
 			};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
index 6c30bb02210d..0f873c897d0d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
@@ -315,10 +315,10 @@
 				regulator-always-on;
 				regulator-boot-on;
 				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-max-microvolt = <3000000>;
 				regulator-state-mem {
 					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <3300000>;
+					regulator-suspend-microvolt = <3000000>;
 				};
 			};
 
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 903f3bf48419..7e25c5cc353a 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -155,14 +155,16 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 		return __cmpxchg_small(ptr, old, new, size);
 
 	case 4:
-		return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new);
+		return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr,
+				     (u32)old, new);
 
 	case 8:
 		/* lld/scd are only available for MIPS64 */
 		if (!IS_ENABLED(CONFIG_64BIT))
 			return __cmpxchg_called_with_bad_pointer();
 
-		return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, old, new);
+		return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr,
+				     (u64)old, new);
 
 	default:
 		return __cmpxchg_called_with_bad_pointer();
diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c
index 100f23dfa438..ac584c5823d0 100644
--- a/arch/mips/loongson32/common/platform.c
+++ b/arch/mips/loongson32/common/platform.c
@@ -183,18 +183,20 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv)
 }
 
 static struct plat_stmmacenet_data ls1x_eth0_pdata = {
-	.bus_id		= 0,
-	.phy_addr	= -1,
+	.bus_id			= 0,
+	.phy_addr		= -1,
 #if defined(CONFIG_LOONGSON1_LS1B)
-	.interface	= PHY_INTERFACE_MODE_MII,
+	.interface		= PHY_INTERFACE_MODE_MII,
 #elif defined(CONFIG_LOONGSON1_LS1C)
-	.interface	= PHY_INTERFACE_MODE_RMII,
+	.interface		= PHY_INTERFACE_MODE_RMII,
 #endif
-	.mdio_bus_data	= &ls1x_mdio_bus_data,
-	.dma_cfg	= &ls1x_eth_dma_cfg,
-	.has_gmac	= 1,
-	.tx_coe		= 1,
-	.init		= ls1x_eth_mux_init,
+	.mdio_bus_data		= &ls1x_mdio_bus_data,
+	.dma_cfg		= &ls1x_eth_dma_cfg,
+	.has_gmac		= 1,
+	.tx_coe			= 1,
+	.rx_queues_to_use	= 1,
+	.tx_queues_to_use	= 1,
+	.init			= ls1x_eth_mux_init,
 };
 
 static struct resource ls1x_eth0_resources[] = {
@@ -222,14 +224,16 @@ struct platform_device ls1x_eth0_pdev = {
 
 #ifdef CONFIG_LOONGSON1_LS1B
 static struct plat_stmmacenet_data ls1x_eth1_pdata = {
-	.bus_id		= 1,
-	.phy_addr	= -1,
-	.interface	= PHY_INTERFACE_MODE_MII,
-	.mdio_bus_data	= &ls1x_mdio_bus_data,
-	.dma_cfg	= &ls1x_eth_dma_cfg,
-	.has_gmac	= 1,
-	.tx_coe		= 1,
-	.init		= ls1x_eth_mux_init,
+	.bus_id			= 1,
+	.phy_addr		= -1,
+	.interface		= PHY_INTERFACE_MODE_MII,
+	.mdio_bus_data		= &ls1x_mdio_bus_data,
+	.dma_cfg		= &ls1x_eth_dma_cfg,
+	.has_gmac		= 1,
+	.tx_coe			= 1,
+	.rx_queues_to_use	= 1,
+	.tx_queues_to_use	= 1,
+	.init			= ls1x_eth_mux_init,
 };
 
 static struct resource ls1x_eth1_resources[] = {
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 192542dbd972..16d9ef5a78c5 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -2558,7 +2558,6 @@ dcopuop:
 					break;
 				default:
 					/* Reserved R6 ops */
-					pr_err("Reserved MIPS R6 CMP.condn.S operation\n");
 					return SIGILL;
 				}
 			}
@@ -2719,7 +2718,6 @@ dcopuop:
 					break;
 				default:
 					/* Reserved R6 ops */
-					pr_err("Reserved MIPS R6 CMP.condn.D operation\n");
 					return SIGILL;
 				}
 			}
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 7646891c4e9b..01b7a87ea678 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -667,7 +667,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 {
 	int src, dst, r, td, ts, mem_off, b_off;
 	bool need_swap, did_move, cmp_eq;
-	unsigned int target;
+	unsigned int target = 0;
 	u64 t64;
 	s64 t64s;
 	int bpf_op = BPF_OP(insn->code);
diff --git a/arch/mips/tools/generic-board-config.sh b/arch/mips/tools/generic-board-config.sh
index 5c4f93687039..654d652d7fa1 100755
--- a/arch/mips/tools/generic-board-config.sh
+++ b/arch/mips/tools/generic-board-config.sh
@@ -30,8 +30,6 @@ cfg="$4"
 boards_origin="$5"
 shift 5
 
-cd "${srctree}"
-
 # Only print Skipping... lines if the user explicitly specified BOARDS=. In the
 # general case it only serves to obscure the useful output about what actually
 # was included.
@@ -48,7 +46,7 @@ environment*)
 esac
 
 for board in $@; do
-	board_cfg="arch/mips/configs/generic/board-${board}.config"
+	board_cfg="${srctree}/arch/mips/configs/generic/board-${board}.config"
 	if [ ! -f "${board_cfg}" ]; then
 		echo "WARNING: Board config '${board_cfg}' not found"
 		continue
@@ -84,7 +82,7 @@ for board in $@; do
 	done || continue
 
 	# Merge this board config fragment into our final config file
-	./scripts/kconfig/merge_config.sh \
+	${srctree}/scripts/kconfig/merge_config.sh \
 		-m -O ${objtree} ${cfg} ${board_cfg} \
 		| grep -Ev '^(#|Using)'
 done
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index c6d6272a934f..7baa2265d439 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -35,12 +35,12 @@ EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(__xchg8);
 EXPORT_SYMBOL(__xchg32);
 EXPORT_SYMBOL(__cmpxchg_u32);
+EXPORT_SYMBOL(__cmpxchg_u64);
 #ifdef CONFIG_SMP
 EXPORT_SYMBOL(__atomic_hash);
 #endif
 #ifdef CONFIG_64BIT
 EXPORT_SYMBOL(__xchg64);
-EXPORT_SYMBOL(__cmpxchg_u64);
 #endif
 
 #include <linux/uaccess.h>
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 23de307c3052..41e60a9c7db2 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -742,7 +742,7 @@ lws_compare_and_swap_2:
 10:	ldd	0(%r25), %r25
 11:	ldd	0(%r24), %r24
 #else
-	/* Load new value into r22/r23 - high/low */
+	/* Load old value into r22/r23 - high/low */
 10:	ldw	0(%r25), %r22
 11:	ldw	4(%r25), %r23
 	/* Load new value into fr4 for atomic store later */
@@ -834,11 +834,11 @@ cas2_action:
 	copy	%r0, %r28
 #else
 	/* Compare first word */
-19:	ldw,ma	0(%r26), %r29
+19:	ldw	0(%r26), %r29
 	sub,=	%r29, %r22, %r0
 	b,n	cas2_end
 	/* Compare second word */
-20:	ldw,ma	4(%r26), %r29
+20:	ldw	4(%r26), %r29
 	sub,=	%r29, %r23, %r0
 	b,n	cas2_end
 	/* Perform the store */
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 2d956aa0a38a..8c0105a49839 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -253,7 +253,10 @@ static int __init init_cr16_clocksource(void)
 		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
 
 		for_each_online_cpu(cpu) {
-			if (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)
+			if (cpu == 0)
+				continue;
+			if ((cpu0_loc != 0) &&
+			    (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc))
 				continue;
 
 			clocksource_cr16.name = "cr16_unstable";
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index c98e90b4ea7b..b4e2b7165f79 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -181,34 +181,25 @@ _GLOBAL(ftrace_stub)
 	 *  - we have no stack frame and can not allocate one
 	 *  - LR points back to the original caller (in A)
 	 *  - CTR holds the new NIP in C
-	 *  - r0 & r12 are free
-	 *
-	 * r0 can't be used as the base register for a DS-form load or store, so
-	 * we temporarily shuffle r1 (stack pointer) into r0 and then put it back.
+	 *  - r0, r11 & r12 are free
 	 */
 livepatch_handler:
 	CURRENT_THREAD_INFO(r12, r1)
 
-	/* Save stack pointer into r0 */
-	mr	r0, r1
-
 	/* Allocate 3 x 8 bytes */
-	ld	r1, TI_livepatch_sp(r12)
-	addi	r1, r1, 24
-	std	r1, TI_livepatch_sp(r12)
+	ld	r11, TI_livepatch_sp(r12)
+	addi	r11, r11, 24
+	std	r11, TI_livepatch_sp(r12)
 
 	/* Save toc & real LR on livepatch stack */
-	std	r2,  -24(r1)
+	std	r2,  -24(r11)
 	mflr	r12
-	std	r12, -16(r1)
+	std	r12, -16(r11)
 
 	/* Store stack end marker */
 	lis     r12, STACK_END_MAGIC@h
 	ori     r12, r12, STACK_END_MAGIC@l
-	std	r12, -8(r1)
-
-	/* Restore real stack pointer */
-	mr	r1, r0
+	std	r12, -8(r11)
 
 	/* Put ctr in r12 for global entry and branch there */
 	mfctr	r12
@@ -216,36 +207,30 @@ livepatch_handler:
 
 	/*
 	 * Now we are returning from the patched function to the original
-	 * caller A. We are free to use r0 and r12, and we can use r2 until we
+	 * caller A. We are free to use r11, r12 and we can use r2 until we
 	 * restore it.
 	 */
 
 	CURRENT_THREAD_INFO(r12, r1)
 
-	/* Save stack pointer into r0 */
-	mr	r0, r1
-
-	ld	r1, TI_livepatch_sp(r12)
+	ld	r11, TI_livepatch_sp(r12)
 
 	/* Check stack marker hasn't been trashed */
 	lis     r2,  STACK_END_MAGIC@h
 	ori     r2,  r2, STACK_END_MAGIC@l
-	ld	r12, -8(r1)
+	ld	r12, -8(r11)
 1:	tdne	r12, r2
 	EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
 
 	/* Restore LR & toc from livepatch stack */
-	ld	r12, -16(r1)
+	ld	r12, -16(r11)
 	mtlr	r12
-	ld	r2,  -24(r1)
+	ld	r2,  -24(r11)
 
 	/* Pop livepatch stack frame */
-	CURRENT_THREAD_INFO(r12, r0)
-	subi	r1, r1, 24
-	std	r1, TI_livepatch_sp(r12)
-
-	/* Restore real stack pointer */
-	mr	r1, r0
+	CURRENT_THREAD_INFO(r12, r1)
+	subi	r11, r11, 24
+	std	r11, TI_livepatch_sp(r12)
 
 	/* Return to original caller of live patched function */
 	blr
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 5e8418c28bd8..f208f560aecd 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1684,11 +1684,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
  * Logical instructions
  */
 		case 26:	/* cntlzw */
-			op->val = __builtin_clz((unsigned int) regs->gpr[rd]);
+			val = (unsigned int) regs->gpr[rd];
+			op->val = ( val ? __builtin_clz(val) : 32 );
 			goto logical_done;
 #ifdef __powerpc64__
 		case 58:	/* cntlzd */
-			op->val = __builtin_clzl(regs->gpr[rd]);
+			val = regs->gpr[rd];
+			op->val = ( val ? __builtin_clzl(val) : 64 );
 			goto logical_done;
 #endif
 		case 28:	/* and */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b95c584ce19d..a51df9ef529d 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1438,7 +1438,6 @@ out:
 
 int arch_update_cpu_topology(void)
 {
-	lockdep_assert_cpus_held();
 	return numa_update_cpu_topology(true);
 }
 
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 9ccac86f3463..88126245881b 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -399,6 +399,20 @@ static void nest_imc_counters_release(struct perf_event *event)
 
 	/* Take the mutex lock for this node and then decrement the reference count */
 	mutex_lock(&ref->lock);
+	if (ref->refc == 0) {
+		/*
+		 * The scenario where this is true is, when perf session is
+		 * started, followed by offlining of all cpus in a given node.
+		 *
+		 * In the cpuhotplug offline path, ppc_nest_imc_cpu_offline()
+		 * function set the ref->count to zero, if the cpu which is
+		 * about to offline is the last cpu in a given node and make
+		 * an OPAL call to disable the engine in that node.
+		 *
+		 */
+		mutex_unlock(&ref->lock);
+		return;
+	}
 	ref->refc--;
 	if (ref->refc == 0) {
 		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
@@ -523,8 +537,8 @@ static int core_imc_mem_init(int cpu, int size)
 
 	/* We need only vbase for core counters */
 	mem_info->vbase = page_address(alloc_pages_node(phys_id,
-					  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
-					  get_order(size)));
+					  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
+					  __GFP_NOWARN, get_order(size)));
 	if (!mem_info->vbase)
 		return -ENOMEM;
 
@@ -646,6 +660,20 @@ static void core_imc_counters_release(struct perf_event *event)
 		return;
 
 	mutex_lock(&ref->lock);
+	if (ref->refc == 0) {
+		/*
+		 * The scenario where this is true is, when perf session is
+		 * started, followed by offlining of all cpus in a given core.
+		 *
+		 * In the cpuhotplug offline path, ppc_core_imc_cpu_offline()
+		 * function set the ref->count to zero, if the cpu which is
+		 * about to offline is the last cpu in a given core and make
+		 * an OPAL call to disable the engine in that core.
+		 *
+		 */
+		mutex_unlock(&ref->lock);
+		return;
+	}
 	ref->refc--;
 	if (ref->refc == 0) {
 		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
@@ -763,8 +791,8 @@ static int thread_imc_mem_alloc(int cpu_id, int size)
 		 * free the memory in cpu offline path.
 		 */
 		local_mem = page_address(alloc_pages_node(phys_id,
-				  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
-				  get_order(size)));
+				  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
+				  __GFP_NOWARN, get_order(size)));
 		if (!local_mem)
 			return -ENOMEM;
 
@@ -1148,7 +1176,8 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 	}
 
 	/* Only free the attr_groups which are dynamically allocated  */
-	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
+	if (pmu_ptr->attr_groups[IMC_EVENT_ATTR])
+		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
 	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
 	kfree(pmu_ptr);
 	return;
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index afa46a7406ea..04e042edbab7 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -27,6 +27,7 @@ CONFIG_NET=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_BLK_DEV_RAM=y
 # CONFIG_BLK_DEV_XPRAM is not set
 # CONFIG_DCSSBLK is not set
 # CONFIG_DASD is not set
@@ -59,6 +60,7 @@ CONFIG_CONFIGFS_FS=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_PANIC_ON_OOPS=y
 # CONFIG_SCHED_DEBUG is not set
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 1cee6753d47a..495ff6959dec 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -293,7 +293,10 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
 	lc->lpp = LPP_MAGIC;
 	lc->current_pid = tsk->pid;
 	lc->user_timer = tsk->thread.user_timer;
+	lc->guest_timer = tsk->thread.guest_timer;
 	lc->system_timer = tsk->thread.system_timer;
+	lc->hardirq_timer = tsk->thread.hardirq_timer;
+	lc->softirq_timer = tsk->thread.softirq_timer;
 	lc->steal_timer = 0;
 }
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 8a13d468635a..50e0d2bc4528 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -176,7 +176,7 @@
 /*
  * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
  * frame pointer is replaced with an encoded pointer to pt_regs.  The encoding
- * is just setting the LSB, which makes it an invalid stack address and is also
+ * is just clearing the MSB, which makes it an invalid stack address and is also
  * a signal to the unwinder that it's a pt_regs pointer in disguise.
  *
  * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the
@@ -185,7 +185,7 @@
 .macro ENCODE_FRAME_POINTER
 #ifdef CONFIG_FRAME_POINTER
 	mov %esp, %ebp
-	orl $0x1, %ebp
+	andl $0x7fffffff, %ebp
 #endif
 .endm
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 1c5390f1cf09..d45e06346f14 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -822,7 +822,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 		pmus[i].type	= type;
 		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
 		if (!pmus[i].boxes)
-			return -ENOMEM;
+			goto err;
 	}
 
 	type->pmus = pmus;
@@ -836,7 +836,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 		attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
 					sizeof(*attr_group), GFP_KERNEL);
 		if (!attr_group)
-			return -ENOMEM;
+			goto err;
 
 		attrs = (struct attribute **)(attr_group + 1);
 		attr_group->name = "events";
@@ -849,7 +849,15 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	}
 
 	type->pmu_group = &uncore_pmu_attr_group;
+
 	return 0;
+
+err:
+	for (i = 0; i < type->num_boxes; i++)
+		kfree(pmus[i].boxes);
+	kfree(pmus);
+
+	return -ENOMEM;
 }
 
 static int __init
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 1a8eb550c40f..a5db63f728a2 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -85,6 +85,8 @@ EXPORT_SYMBOL_GPL(hyperv_cs);
 u32 *hv_vp_index;
 EXPORT_SYMBOL_GPL(hv_vp_index);
 
+u32 hv_max_vp_index;
+
 static int hv_cpu_init(unsigned int cpu)
 {
 	u64 msr_vp_index;
@@ -93,6 +95,9 @@ static int hv_cpu_init(unsigned int cpu)
 
 	hv_vp_index[smp_processor_id()] = msr_vp_index;
 
+	if (msr_vp_index > hv_max_vp_index)
+		hv_max_vp_index = msr_vp_index;
+
 	return 0;
 }
 
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 39e7f6e50919..9cc9e1c1e2db 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -36,9 +36,9 @@ struct hv_flush_pcpu_ex {
 /* Each gva in gva_list encodes up to 4096 pages to flush */
 #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
 
-static struct hv_flush_pcpu __percpu *pcpu_flush;
+static struct hv_flush_pcpu __percpu **pcpu_flush;
 
-static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex;
+static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex;
 
 /*
  * Fills in gva_list starting from offset. Returns the number of items added.
@@ -76,6 +76,18 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush,
 {
 	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
 
+	/* valid_bank_mask can represent up to 64 banks */
+	if (hv_max_vp_index / 64 >= 64)
+		return 0;
+
+	/*
+	 * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
+	 * structs are not cleared between calls, we risk flushing unneeded
+	 * vCPUs otherwise.
+	 */
+	for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
+		flush->hv_vp_set.bank_contents[vcpu_bank] = 0;
+
 	/*
 	 * Some banks may end up being empty but this is acceptable.
 	 */
@@ -83,11 +95,6 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush,
 		vcpu = hv_cpu_number_to_vp_number(cpu);
 		vcpu_bank = vcpu / 64;
 		vcpu_offset = vcpu % 64;
-
-		/* valid_bank_mask can represent up to 64 banks */
-		if (vcpu_bank >= 64)
-			return 0;
-
 		__set_bit(vcpu_offset, (unsigned long *)
 			  &flush->hv_vp_set.bank_contents[vcpu_bank]);
 		if (vcpu_bank >= nr_bank)
@@ -102,6 +109,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 				    const struct flush_tlb_info *info)
 {
 	int cpu, vcpu, gva_n, max_gvas;
+	struct hv_flush_pcpu **flush_pcpu;
 	struct hv_flush_pcpu *flush;
 	u64 status = U64_MAX;
 	unsigned long flags;
@@ -116,7 +124,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 
 	local_irq_save(flags);
 
-	flush = this_cpu_ptr(pcpu_flush);
+	flush_pcpu = this_cpu_ptr(pcpu_flush);
+
+	if (unlikely(!*flush_pcpu))
+		*flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+
+	flush = *flush_pcpu;
+
+	if (unlikely(!flush)) {
+		local_irq_restore(flags);
+		goto do_native;
+	}
 
 	if (info->mm) {
 		flush->address_space = virt_to_phys(info->mm->pgd);
@@ -173,6 +191,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 				       const struct flush_tlb_info *info)
 {
 	int nr_bank = 0, max_gvas, gva_n;
+	struct hv_flush_pcpu_ex **flush_pcpu;
 	struct hv_flush_pcpu_ex *flush;
 	u64 status = U64_MAX;
 	unsigned long flags;
@@ -187,7 +206,17 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 
 	local_irq_save(flags);
 
-	flush = this_cpu_ptr(pcpu_flush_ex);
+	flush_pcpu = this_cpu_ptr(pcpu_flush_ex);
+
+	if (unlikely(!*flush_pcpu))
+		*flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+
+	flush = *flush_pcpu;
+
+	if (unlikely(!flush)) {
+		local_irq_restore(flags);
+		goto do_native;
+	}
 
 	if (info->mm) {
 		flush->address_space = virt_to_phys(info->mm->pgd);
@@ -222,18 +251,18 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 		flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
 		status = hv_do_rep_hypercall(
 			HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
-			0, nr_bank + 2, flush, NULL);
+			0, nr_bank, flush, NULL);
 	} else if (info->end &&
 		   ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
 		status = hv_do_rep_hypercall(
 			HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
-			0, nr_bank + 2, flush, NULL);
+			0, nr_bank, flush, NULL);
 	} else {
 		gva_n = fill_gva_list(flush->gva_list, nr_bank,
 				      info->start, info->end);
 		status = hv_do_rep_hypercall(
 			HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX,
-			gva_n, nr_bank + 2, flush, NULL);
+			gva_n, nr_bank, flush, NULL);
 	}
 
 	local_irq_restore(flags);
@@ -266,7 +295,7 @@ void hyper_alloc_mmu(void)
 		return;
 
 	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-		pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE);
+		pcpu_flush = alloc_percpu(struct hv_flush_pcpu *);
 	else
-		pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE);
+		pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *);
 }
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index e7636bac7372..6c98821fef5e 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -62,8 +62,10 @@
 #define new_len2		145f-144f
 
 /*
- * max without conditionals. Idea adapted from:
+ * gas compatible max based on the idea from:
  * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ *
+ * The additional "-" is needed because gas uses a "true" value of -1.
  */
 #define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
 
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index c096624137ae..ccbe24e697c4 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -103,12 +103,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	alt_end_marker ":\n"
 
 /*
- * max without conditionals. Idea adapted from:
+ * gas compatible max based on the idea from:
  * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
  *
- * The additional "-" is needed because gas works with s32s.
+ * The additional "-" is needed because gas uses a "true" value of -1.
  */
-#define alt_max_short(a, b)	"((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))"
+#define alt_max_short(a, b)	"((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))"
 
 /*
  * Pad the second replacement alternative with additional NOPs if it is
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 181264989db5..8edac1de2e35 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -187,7 +187,6 @@ struct mca_msr_regs {
 
 extern struct mce_vendor_flags mce_flags;
 
-extern struct mca_config mca_cfg;
 extern struct mca_msr_regs msr_ops;
 
 enum mce_notifier_prios {
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index c120b5db178a..3c856a15b98e 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -126,13 +126,7 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 	DEBUG_LOCKS_WARN_ON(preemptible());
 }
 
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-	int cpu = smp_processor_id();
-
-	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))
-		cpumask_clear_cpu(cpu, mm_cpumask(mm));
-}
+void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 738503e1f80c..530f448fddaf 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -289,6 +289,7 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
  * to this information.
  */
 extern u32 *hv_vp_index;
+extern u32 hv_max_vp_index;
 
 /**
  * hv_cpu_number_to_vp_number() - Map CPU to VP.
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 4893abf7f74f..d362161d3291 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -83,6 +83,13 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 #endif
 
 /*
+ * If tlb_use_lazy_mode is true, then we try to avoid switching CR3 to point
+ * to init_mm when we switch to a kernel thread (e.g. the idle thread).  If
+ * it's false, then we immediately switch CR3 when entering a kernel thread.
+ */
+DECLARE_STATIC_KEY_TRUE(tlb_use_lazy_mode);
+
+/*
  * 6 because 6 should be plenty and struct tlb_state will fit in
  * two cache lines.
  */
@@ -105,6 +112,23 @@ struct tlb_state {
 	u16 next_asid;
 
 	/*
+	 * We can be in one of several states:
+	 *
+	 *  - Actively using an mm.  Our CPU's bit will be set in
+	 *    mm_cpumask(loaded_mm) and is_lazy == false;
+	 *
+	 *  - Not using a real mm.  loaded_mm == &init_mm.  Our CPU's bit
+	 *    will not be set in mm_cpumask(&init_mm) and is_lazy == false.
+	 *
+	 *  - Lazily using a real mm.  loaded_mm != &init_mm, our bit
+	 *    is set in mm_cpumask(loaded_mm), but is_lazy == true.
+	 *    We're heuristically guessing that the CR3 load we
+	 *    skipped more than makes up for the overhead added by
+	 *    lazy mode.
+	 */
+	bool is_lazy;
+
+	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
 	 * disabling interrupts when modifying either one.
 	 */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d705c769f77d..ff891772c9f8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -573,11 +573,21 @@ static u32 bdx_deadline_rev(void)
 	return ~0U;
 }
 
+static u32 skx_deadline_rev(void)
+{
+	switch (boot_cpu_data.x86_mask) {
+	case 0x03: return 0x01000136;
+	case 0x04: return 0x02000014;
+	}
+
+	return ~0U;
+}
+
 static const struct x86_cpu_id deadline_match[] = {
 	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X,	hsx_deadline_rev),
 	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X,	0x0b000020),
 	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D,	bdx_deadline_rev),
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X,	0x02000014),
+	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X,	skx_deadline_rev),
 
 	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE,	0x22),
 	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT,	0x20),
@@ -600,7 +610,8 @@ static void apic_check_deadline_errata(void)
 	const struct x86_cpu_id *m;
 	u32 rev;
 
-	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) ||
+	    boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return;
 
 	m = x86_match_cpu(deadline_match);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 098530a93bb7..debb974fd17d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -1,3 +1,6 @@
+#ifndef __X86_MCE_INTERNAL_H__
+#define __X86_MCE_INTERNAL_H__
+
 #include <linux/device.h>
 #include <asm/mce.h>
 
@@ -108,3 +111,7 @@ static inline void mce_work_trigger(void)	{ }
 static inline void mce_register_injector_chain(struct notifier_block *nb)	{ }
 static inline void mce_unregister_injector_chain(struct notifier_block *nb)	{ }
 #endif
+
+extern struct mca_config mca_cfg;
+
+#endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 40e28ed77fbf..486f640b02ef 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -28,6 +28,8 @@
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>
 
+#include "mce-internal.h"
+
 #define NR_BLOCKS         5
 #define THRESHOLD_MAX     0xFFF
 #define INT_TYPE_APIC     0x00020000
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 86e8f0b2537b..c4fa4a85d4cb 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -122,9 +122,6 @@ static bool __init check_loader_disabled_bsp(void)
 	bool *res = &dis_ucode_ldr;
 #endif
 
-	if (!have_cpuid_p())
-		return *res;
-
 	/*
 	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
 	 * completely accurate as xen pv guests don't see that CPUID bit set but
@@ -166,24 +163,36 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name)
 void __init load_ucode_bsp(void)
 {
 	unsigned int cpuid_1_eax;
+	bool intel = true;
 
-	if (check_loader_disabled_bsp())
+	if (!have_cpuid_p())
 		return;
 
 	cpuid_1_eax = native_cpuid_eax(1);
 
 	switch (x86_cpuid_vendor()) {
 	case X86_VENDOR_INTEL:
-		if (x86_family(cpuid_1_eax) >= 6)
-			load_ucode_intel_bsp();
+		if (x86_family(cpuid_1_eax) < 6)
+			return;
 		break;
+
 	case X86_VENDOR_AMD:
-		if (x86_family(cpuid_1_eax) >= 0x10)
-			load_ucode_amd_bsp(cpuid_1_eax);
+		if (x86_family(cpuid_1_eax) < 0x10)
+			return;
+		intel = false;
 		break;
+
 	default:
-		break;
+		return;
 	}
+
+	if (check_loader_disabled_bsp())
+		return;
+
+	if (intel)
+		load_ucode_intel_bsp();
+	else
+		load_ucode_amd_bsp(cpuid_1_eax);
 }
 
 static bool check_loader_disabled_ap(void)
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index db2182d63ed0..3fc0f9a794cb 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -3,6 +3,15 @@
 
 /* Kprobes and Optprobes common header */
 
+#include <asm/asm.h>
+
+#ifdef CONFIG_FRAME_POINTER
+# define SAVE_RBP_STRING "	push %" _ASM_BP "\n" \
+			 "	mov  %" _ASM_SP ", %" _ASM_BP "\n"
+#else
+# define SAVE_RBP_STRING "	push %" _ASM_BP "\n"
+#endif
+
 #ifdef CONFIG_X86_64
 #define SAVE_REGS_STRING			\
 	/* Skip cs, ip, orig_ax. */		\
@@ -17,7 +26,7 @@
 	"	pushq %r10\n"			\
 	"	pushq %r11\n"			\
 	"	pushq %rbx\n"			\
-	"	pushq %rbp\n"			\
+	SAVE_RBP_STRING				\
 	"	pushq %r12\n"			\
 	"	pushq %r13\n"			\
 	"	pushq %r14\n"			\
@@ -48,7 +57,7 @@
 	"	pushl %es\n"			\
 	"	pushl %ds\n"			\
 	"	pushl %eax\n"			\
-	"	pushl %ebp\n"			\
+	SAVE_RBP_STRING				\
 	"	pushl %edi\n"			\
 	"	pushl %esi\n"			\
 	"	pushl %edx\n"			\
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index f0153714ddac..0742491cbb73 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1080,8 +1080,6 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	 * raw stack chunk with redzones:
 	 */
 	__memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
-	regs->flags &= ~X86_EFLAGS_IF;
-	trace_hardirqs_off();
 	regs->ip = (unsigned long)(jp->entry);
 
 	/*
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 54180fa6f66f..add33f600531 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -105,6 +105,10 @@ void __noreturn machine_real_restart(unsigned int type)
 	load_cr3(initial_page_table);
 #else
 	write_cr3(real_mode_header->trampoline_pgd);
+
+	/* Exiting long mode will fail if CR4.PCIDE is set. */
+	if (static_cpu_has(X86_FEATURE_PCID))
+		cr4_clear_bits(X86_CR4_PCIDE);
 #endif
 
 	/* Jump to the identity-mapped low memory code */
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index d145a0b1f529..3dc26f95d46e 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -44,7 +44,8 @@ static void unwind_dump(struct unwind_state *state)
 			state->stack_info.type, state->stack_info.next_sp,
 			state->stack_mask, state->graph_idx);
 
-	for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+	for (sp = PTR_ALIGN(state->orig_sp, sizeof(long)); sp;
+	     sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
 		if (get_stack_info(sp, state->task, &stack_info, &visit_mask))
 			break;
 
@@ -174,6 +175,7 @@ static bool is_last_task_frame(struct unwind_state *state)
  * This determines if the frame pointer actually contains an encoded pointer to
  * pt_regs on the stack.  See ENCODE_FRAME_POINTER.
  */
+#ifdef CONFIG_X86_64
 static struct pt_regs *decode_frame_pointer(unsigned long *bp)
 {
 	unsigned long regs = (unsigned long)bp;
@@ -183,6 +185,23 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp)
 
 	return (struct pt_regs *)(regs & ~0x1);
 }
+#else
+static struct pt_regs *decode_frame_pointer(unsigned long *bp)
+{
+	unsigned long regs = (unsigned long)bp;
+
+	if (regs & 0x80000000)
+		return NULL;
+
+	return (struct pt_regs *)(regs | 0x80000000);
+}
+#endif
+
+#ifdef CONFIG_X86_32
+#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long))
+#else
+#define KERNEL_REGS_SIZE (sizeof(struct pt_regs))
+#endif
 
 static bool update_stack_state(struct unwind_state *state,
 			       unsigned long *next_bp)
@@ -202,7 +221,7 @@ static bool update_stack_state(struct unwind_state *state,
 	regs = decode_frame_pointer(next_bp);
 	if (regs) {
 		frame = (unsigned long *)regs;
-		len = regs_size(regs);
+		len = KERNEL_REGS_SIZE;
 		state->got_irq = true;
 	} else {
 		frame = next_bp;
@@ -226,6 +245,14 @@ static bool update_stack_state(struct unwind_state *state,
 	    frame < prev_frame_end)
 		return false;
 
+	/*
+	 * On 32-bit with user mode regs, make sure the last two regs are safe
+	 * to access:
+	 */
+	if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) &&
+	    !on_stack(info, frame, len + 2*sizeof(long)))
+		return false;
+
 	/* Move state to the next frame: */
 	if (regs) {
 		state->regs = regs;
@@ -328,6 +355,13 @@ bad_address:
 	    state->regs->sp < (unsigned long)task_pt_regs(state->task))
 		goto the_end;
 
+	/*
+	 * There are some known frame pointer issues on 32-bit.  Disable
+	 * unwinder warnings on 32-bit until it gets objtool support.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		goto the_end;
+
 	if (state->regs) {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 106d4a029a8a..7a69cf053711 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3974,19 +3974,19 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu,
 				unsigned level, unsigned gpte)
 {
 	/*
-	 * PT_PAGE_TABLE_LEVEL always terminates.  The RHS has bit 7 set
-	 * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
-	 * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
-	 */
-	gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
-
-	/*
 	 * The RHS has bit 7 set iff level < mmu->last_nonleaf_level.
 	 * If it is clear, there are no large pages at this level, so clear
 	 * PT_PAGE_SIZE_MASK in gpte if that is the case.
 	 */
 	gpte &= level - mmu->last_nonleaf_level;
 
+	/*
+	 * PT_PAGE_TABLE_LEVEL always terminates.  The RHS has bit 7 set
+	 * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
+	 * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
+	 */
+	gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
+
 	return gpte & PT_PAGE_SIZE_MASK;
 }
 
@@ -4555,6 +4555,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 
 	update_permission_bitmask(vcpu, context, true);
 	update_pkru_bitmask(vcpu, context, true);
+	update_last_nonleaf_level(vcpu, context);
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 86b68dc5a649..f18d1f8d332b 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -334,10 +334,11 @@ retry_walk:
 		--walker->level;
 
 		index = PT_INDEX(addr, walker->level);
-
 		table_gfn = gpte_to_gfn(pte);
 		offset    = index * sizeof(pt_element_t);
 		pte_gpa   = gfn_to_gpa(table_gfn) + offset;
+
+		BUG_ON(walker->level < 1);
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a2b804e10c95..95a01609d7ee 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11297,7 +11297,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 
 	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
-	kvm_set_cr4(vcpu, vmcs12->host_cr4);
+	vmx_set_cr4(vcpu, vmcs12->host_cr4);
 
 	nested_ept_uninit_mmu_context(vcpu);
 
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 72bf8c01c6e3..e1f095884386 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,12 @@
-# Kernel does not boot with instrumentation of tlb.c.
-KCOV_INSTRUMENT_tlb.o	:= n
+# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c
+KCOV_INSTRUMENT_tlb.o		:= n
+KCOV_INSTRUMENT_mem_encrypt.o	:= n
+
+KASAN_SANITIZE_mem_encrypt.o	:= n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_mem_encrypt.o	= -pg
+endif
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
 	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 49d9778376d7..658bf0090565 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -30,6 +30,8 @@
 
 atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
 
+DEFINE_STATIC_KEY_TRUE(tlb_use_lazy_mode);
+
 static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 			    u16 *new_asid, bool *need_flush)
 {
@@ -80,7 +82,7 @@ void leave_mm(int cpu)
 		return;
 
 	/* Warn if we're not lazy. */
-	WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm)));
+	WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy));
 
 	switch_mm(NULL, &init_mm, NULL);
 }
@@ -142,45 +144,24 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		__flush_tlb_all();
 	}
 #endif
+	this_cpu_write(cpu_tlbstate.is_lazy, false);
 
 	if (real_prev == next) {
 		VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
 			  next->context.ctx_id);
 
-		if (cpumask_test_cpu(cpu, mm_cpumask(next))) {
-			/*
-			 * There's nothing to do: we weren't lazy, and we
-			 * aren't changing our mm.  We don't need to flush
-			 * anything, nor do we need to update CR3, CR4, or
-			 * LDTR.
-			 */
-			return;
-		}
-
-		/* Resume remote flushes and then read tlb_gen. */
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
-
-		if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) <
-		    next_tlb_gen) {
-			/*
-			 * Ideally, we'd have a flush_tlb() variant that
-			 * takes the known CR3 value as input.  This would
-			 * be faster on Xen PV and on hypothetical CPUs
-			 * on which INVPCID is fast.
-			 */
-			this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen,
-				       next_tlb_gen);
-			write_cr3(build_cr3(next, prev_asid));
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
-					TLB_FLUSH_ALL);
-		}
-
 		/*
-		 * We just exited lazy mode, which means that CR4 and/or LDTR
-		 * may be stale.  (Changes to the required CR4 and LDTR states
-		 * are not reflected in tlb_gen.)
+		 * We don't currently support having a real mm loaded without
+		 * our cpu set in mm_cpumask().  We have all the bookkeeping
+		 * in place to figure out whether we would need to flush
+		 * if our cpu were cleared in mm_cpumask(), but we don't
+		 * currently use it.
 		 */
+		if (WARN_ON_ONCE(real_prev != &init_mm &&
+				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+
+		return;
 	} else {
 		u16 new_asid;
 		bool need_flush;
@@ -199,10 +180,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		}
 
 		/* Stop remote flushes for the previous mm */
-		if (cpumask_test_cpu(cpu, mm_cpumask(real_prev)))
-			cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
-
-		VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next)));
+		VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
+				real_prev != &init_mm);
+		cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
 
 		/*
 		 * Start remote flushes and then read tlb_gen.
@@ -233,6 +213,37 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 }
 
 /*
+ * enter_lazy_tlb() is a hint from the scheduler that we are entering a
+ * kernel thread or other context without an mm.  Acceptable implementations
+ * include doing nothing whatsoever, switching to init_mm, or various clever
+ * lazy tricks to try to minimize TLB flushes.
+ *
+ * The scheduler reserves the right to call enter_lazy_tlb() several times
+ * in a row.  It will notify us that we're going back to a real mm by
+ * calling switch_mm_irqs_off().
+ */
+void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
+		return;
+
+	if (static_branch_unlikely(&tlb_use_lazy_mode)) {
+		/*
+		 * There's a significant optimization that may be possible
+		 * here.  We have accurate enough TLB flush tracking that we
+		 * don't need to maintain coherence of TLB per se when we're
+		 * lazy.  We do, however, need to maintain coherence of
+		 * paging-structure caches.  We could, in principle, leave our
+		 * old mm loaded and only switch to init_mm when
+		 * tlb_remove_page() happens.
+		 */
+		this_cpu_write(cpu_tlbstate.is_lazy, true);
+	} else {
+		switch_mm(NULL, &init_mm, NULL);
+	}
+}
+
+/*
  * Call this when reinitializing a CPU.  It fixes the following potential
  * problems:
  *
@@ -303,16 +314,20 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 	/* This code cannot presently handle being reentered. */
 	VM_WARN_ON(!irqs_disabled());
 
+	if (unlikely(loaded_mm == &init_mm))
+		return;
+
 	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
 		   loaded_mm->context.ctx_id);
 
-	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) {
+	if (this_cpu_read(cpu_tlbstate.is_lazy)) {
 		/*
-		 * We're in lazy mode -- don't flush.  We can get here on
-		 * remote flushes due to races and on local flushes if a
-		 * kernel thread coincidentally flushes the mm it's lazily
-		 * still using.
+		 * We're in lazy mode.  We need to at least flush our
+		 * paging-structure cache to avoid speculatively reading
+		 * garbage into our TLB.  Since switching to init_mm is barely
+		 * slower than a minimal flush, just switch to init_mm.
 		 */
+		switch_mm_irqs_off(NULL, &init_mm, NULL);
 		return;
 	}
 
@@ -611,3 +626,57 @@ static int __init create_tlb_single_page_flush_ceiling(void)
 	return 0;
 }
 late_initcall(create_tlb_single_page_flush_ceiling);
+
+static ssize_t tlblazy_read_file(struct file *file, char __user *user_buf,
+				 size_t count, loff_t *ppos)
+{
+	char buf[2];
+
+	buf[0] = static_branch_likely(&tlb_use_lazy_mode) ? '1' : '0';
+	buf[1] = '\n';
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t tlblazy_write_file(struct file *file,
+		 const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	bool val;
+
+	if (kstrtobool_from_user(user_buf, count, &val))
+		return -EINVAL;
+
+	if (val)
+		static_branch_enable(&tlb_use_lazy_mode);
+	else
+		static_branch_disable(&tlb_use_lazy_mode);
+
+	return count;
+}
+
+static const struct file_operations fops_tlblazy = {
+	.read = tlblazy_read_file,
+	.write = tlblazy_write_file,
+	.llseek = default_llseek,
+};
+
+static int __init init_tlb_use_lazy_mode(void)
+{
+	if (boot_cpu_has(X86_FEATURE_PCID)) {
+		/*
+		 * Heuristic: with PCID on, switching to and from
+		 * init_mm is reasonably fast, but remote flush IPIs
+		 * as expensive as ever, so turn off lazy TLB mode.
+		 *
+		 * We can't do this in setup_pcid() because static keys
+		 * haven't been initialized yet, and it would blow up
+		 * badly.
+		 */
+		static_branch_disable(&tlb_use_lazy_mode);
+	}
+
+	debugfs_create_file("tlb_use_lazy_mode", S_IRUSR | S_IWUSR,
+			    arch_debugfs_dir, NULL, &fops_tlblazy);
+	return 0;
+}
+late_initcall(init_tlb_use_lazy_mode);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0e7ef69e8531..d669e9d89001 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -93,11 +93,11 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int),
 	int rc;
 
 	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
-				       "x86/xen/hvm_guest:prepare",
+				       "x86/xen/guest:prepare",
 				       cpu_up_prepare_cb, cpu_dead_cb);
 	if (rc >= 0) {
 		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					       "x86/xen/hvm_guest:online",
+					       "x86/xen/guest:online",
 					       xen_cpu_up_online, NULL);
 		if (rc < 0)
 			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);