Merge 4.16-rc6 into staging-next

We want the staging fixes in here as well to handle merge/test issues.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

171 files changed, 1995 insertions, 1109 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index f3a80cf164cc..d76bf4a83740 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -484,7 +484,6 @@ config ARC_CURR_IN_REG
 
 config ARC_EMUL_UNALIGNED
 	bool "Emulate unaligned memory access (userspace only)"
-	default N
 	select SYSCTL_ARCH_UNALIGN_NO_WARN
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	depends on ISA_ARCOMPACT
diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts
index 70aec7d6ca60..626b694c7be7 100644
--- a/arch/arc/boot/dts/axs101.dts
+++ b/arch/arc/boot/dts/axs101.dts
@@ -17,6 +17,6 @@
 	compatible = "snps,axs101", "snps,arc-sdp";
 
 	chosen {
-		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60";
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60 print-fatal-signals=1";
 	};
 };
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index 74d070cd3c13..47b74fbc403c 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -214,13 +214,13 @@
 			};
 
 			eeprom@0x54{
-				compatible = "24c01";
+				compatible = "atmel,24c01";
 				reg = <0x54>;
 				pagesize = <0x8>;
 			};
 
 			eeprom@0x57{
-				compatible = "24c04";
+				compatible = "atmel,24c04";
 				reg = <0x57>;
 				pagesize = <0x8>;
 			};
diff --git a/arch/arc/boot/dts/haps_hs_idu.dts b/arch/arc/boot/dts/haps_hs_idu.dts
index 215cddd0b63b..0c603308aeb3 100644
--- a/arch/arc/boot/dts/haps_hs_idu.dts
+++ b/arch/arc/boot/dts/haps_hs_idu.dts
@@ -22,7 +22,7 @@
 	};
 
 	chosen {
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index 5ee96b067c08..ff2f2c70c545 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -17,7 +17,7 @@
 	interrupt-parent = <&core_intc>;
 
 	chosen {
-		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8";
+		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts
index 8d787b251f73..8e2489b16b0a 100644
--- a/arch/arc/boot/dts/nsim_hs.dts
+++ b/arch/arc/boot/dts/nsim_hs.dts
@@ -24,7 +24,7 @@
 	};
 
 	chosen {
-		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8";
+		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts
index 4f98ebf71fd8..ed12f494721d 100644
--- a/arch/arc/boot/dts/nsim_hs_idu.dts
+++ b/arch/arc/boot/dts/nsim_hs_idu.dts
@@ -15,7 +15,7 @@
 	interrupt-parent = <&core_intc>;
 
 	chosen {
-		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8";
+		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index 3c391ba565ed..7842e5eb4ab5 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -20,7 +20,7 @@
 		/* this is for console on PGU */
 		/* bootargs = "console=tty0 consoleblank=0"; */
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 14a727cbf4c9..b8838cf2b4ec 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -20,7 +20,7 @@
 		/* this is for console on PGU */
 		/* bootargs = "console=tty0 consoleblank=0"; */
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index 5052917d4a99..72a2c723f1f7 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -18,7 +18,7 @@
 
 	chosen {
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index 257a68f3c2fe..309f4e6721b3 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -184,7 +184,7 @@
 .macro FAKE_RET_FROM_EXCPN
 	lr      r9, [status32]
 	bic     r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK)
-	or      r9, r9, (STATUS_L_MASK|STATUS_IE_MASK)
+	or      r9, r9, STATUS_IE_MASK
 	kflag   r9
 .endm
 
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index f61a52b01625..5fe84e481654 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -22,10 +22,79 @@ static DEFINE_RAW_SPINLOCK(mcip_lock);
 
 static char smp_cpuinfo_buf[128];
 
+/*
+ * Set mask to halt GFRC if any online core in SMP cluster is halted.
+ * Only works for ARC HS v3.0+, on earlier versions has no effect.
+ */
+static void mcip_update_gfrc_halt_mask(int cpu)
+{
+	struct bcr_generic gfrc;
+	unsigned long flags;
+	u32 gfrc_halt_mask;
+
+	READ_BCR(ARC_REG_GFRC_BUILD, gfrc);
+
+	/*
+	 * CMD_GFRC_SET_CORE and CMD_GFRC_READ_CORE commands were added in
+	 * GFRC 0x3 version.
+	 */
+	if (gfrc.ver < 0x3)
+		return;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	__mcip_cmd(CMD_GFRC_READ_CORE, 0);
+	gfrc_halt_mask = read_aux_reg(ARC_REG_MCIP_READBACK);
+	gfrc_halt_mask |= BIT(cpu);
+	__mcip_cmd_data(CMD_GFRC_SET_CORE, 0, gfrc_halt_mask);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void mcip_update_debug_halt_mask(int cpu)
+{
+	u32 mcip_mask = 0;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	/*
+	 * mcip_mask is same for CMD_DEBUG_SET_SELECT and CMD_DEBUG_SET_MASK
+	 * commands. So read it once instead of reading both CMD_DEBUG_READ_MASK
+	 * and CMD_DEBUG_READ_SELECT.
+	 */
+	__mcip_cmd(CMD_DEBUG_READ_SELECT, 0);
+	mcip_mask = read_aux_reg(ARC_REG_MCIP_READBACK);
+
+	mcip_mask |= BIT(cpu);
+
+	__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, mcip_mask);
+	/*
+	 * Parameter specified halt cause:
+	 * STATUS32[H]/actionpoint/breakpoint/self-halt
+	 * We choose all of them (0xF).
+	 */
+	__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xF, mcip_mask);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
 static void mcip_setup_per_cpu(int cpu)
 {
+	struct mcip_bcr mp;
+
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+
 	smp_ipi_irq_setup(cpu, IPI_IRQ);
 	smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ);
+
+	/* Update GFRC halt mask as new CPU came online */
+	if (mp.gfrc)
+		mcip_update_gfrc_halt_mask(cpu);
+
+	/* Update MCIP debug mask as new CPU came online */
+	if (mp.dbg)
+		mcip_update_debug_halt_mask(cpu);
 }
 
 static void mcip_ipi_send(int cpu)
@@ -101,11 +170,6 @@ static void mcip_probe_n_setup(void)
 		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	cpuinfo_arc700[0].extn.gfrc = mp.gfrc;
-
-	if (mp.dbg) {
-		__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf);
-		__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf);
-	}
 }
 
 struct plat_smp_ops plat_smp_ops = {
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index ec12fe1c2f07..b2cae79a25d7 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -51,7 +51,7 @@ static const struct id_to_str arc_cpu_rel[] = {
 	{ 0x51, "R2.0" },
 	{ 0x52, "R2.1" },
 	{ 0x53, "R3.0" },
-	{ 0x54, "R4.0" },
+	{ 0x54, "R3.10a" },
 #endif
 	{ 0x00, NULL   }
 };
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index efe8b4200a67..21d86c36692b 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -24,6 +24,7 @@
 #include <linux/reboot.h>
 #include <linux/irqdomain.h>
 #include <linux/export.h>
+#include <linux/of_fdt.h>
 
 #include <asm/processor.h>
 #include <asm/setup.h>
@@ -47,6 +48,42 @@ void __init smp_prepare_boot_cpu(void)
 {
 }
 
+static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask)
+{
+	unsigned long dt_root = of_get_flat_dt_root();
+	const char *buf;
+
+	buf = of_get_flat_dt_prop(dt_root, name, NULL);
+	if (!buf)
+		return -EINVAL;
+
+	if (cpulist_parse(buf, cpumask))
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Read from DeviceTree and setup cpu possible mask. If there is no
+ * "possible-cpus" property in DeviceTree pretend all [0..NR_CPUS-1] exist.
+ */
+static void __init arc_init_cpu_possible(void)
+{
+	struct cpumask cpumask;
+
+	if (arc_get_cpu_map("possible-cpus", &cpumask)) {
+		pr_warn("Failed to get possible-cpus from dtb, pretending all %u cpus exist\n",
+			NR_CPUS);
+
+		cpumask_setall(&cpumask);
+	}
+
+	if (!cpumask_test_cpu(0, &cpumask))
+		panic("Master cpu (cpu[0]) is missed in cpu possible mask!");
+
+	init_cpu_possible(&cpumask);
+}
+
 /*
  * Called from setup_arch() before calling setup_processor()
  *
@@ -58,10 +95,7 @@ void __init smp_prepare_boot_cpu(void)
  */
 void __init smp_init_cpus(void)
 {
-	unsigned int i;
-
-	for (i = 0; i < NR_CPUS; i++)
-		set_cpu_possible(i, true);
+	arc_init_cpu_possible();
 
 	if (plat_smp_ops.init_early_smp)
 		plat_smp_ops.init_early_smp();
@@ -70,16 +104,12 @@ void __init smp_init_cpus(void)
 /* called from init ( ) =>  process 1 */
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	int i;
-
 	/*
 	 * if platform didn't set the present map already, do it now
 	 * boot cpu is set to present already by init/main.c
 	 */
-	if (num_present_cpus() <= 1) {
-		for (i = 0; i < max_cpus; i++)
-			set_cpu_present(i, true);
-	}
+	if (num_present_cpus() <= 1)
+		init_cpu_present(cpu_possible_mask);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index eee924dfffa6..2072f3451e9c 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -780,7 +780,10 @@ noinline static void slc_entire_op(const int op)
 
 	write_aux_reg(r, ctrl);
 
-	write_aux_reg(ARC_REG_SLC_INVALIDATE, 1);
+	if (op & OP_INV)	/* Inv or flush-n-inv use same cmd reg */
+		write_aux_reg(ARC_REG_SLC_INVALIDATE, 0x1);
+	else
+		write_aux_reg(ARC_REG_SLC_FLUSH, 0x1);
 
 	/* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */
 	read_aux_reg(r);
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index 18045c38bcf1..db7cded1b7ad 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -55,7 +55,7 @@
 		      <0x3ff00100 0x100>;
 	};
 
-	smc@0x3404c000 {
+	smc@3404c000 {
 		compatible = "brcm,bcm11351-smc", "brcm,kona-smc";
 		reg = <0x3404c000 0x400>; /* 1 KiB in SRAM */
 	};
diff --git a/arch/arm/boot/dts/bcm21664.dtsi b/arch/arm/boot/dts/bcm21664.dtsi
index 6dde95f21cef..266f2611dc22 100644
--- a/arch/arm/boot/dts/bcm21664.dtsi
+++ b/arch/arm/boot/dts/bcm21664.dtsi
@@ -55,7 +55,7 @@
 		      <0x3ff00100 0x100>;
 	};
 
-	smc@0x3404e000 {
+	smc@3404e000 {
 		compatible = "brcm,bcm21664-smc", "brcm,kona-smc";
 		reg = <0x3404e000 0x400>; /* 1 KiB in SRAM */
 	};
diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi
index 0e3d2a5ff208..a5c3824c8056 100644
--- a/arch/arm/boot/dts/bcm2835.dtsi
+++ b/arch/arm/boot/dts/bcm2835.dtsi
@@ -18,10 +18,10 @@
 	soc {
 		ranges = <0x7e000000 0x20000000 0x02000000>;
 		dma-ranges = <0x40000000 0x00000000 0x20000000>;
+	};
 
-		arm-pmu {
-			compatible = "arm,arm1176-pmu";
-		};
+	arm-pmu {
+		compatible = "arm,arm1176-pmu";
 	};
 };
 
diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi
index 1dfd76442777..c933e8413884 100644
--- a/arch/arm/boot/dts/bcm2836.dtsi
+++ b/arch/arm/boot/dts/bcm2836.dtsi
@@ -9,19 +9,19 @@
 			 <0x40000000 0x40000000 0x00001000>;
 		dma-ranges = <0xc0000000 0x00000000 0x3f000000>;
 
-		local_intc: local_intc {
+		local_intc: local_intc@40000000 {
 			compatible = "brcm,bcm2836-l1-intc";
 			reg = <0x40000000 0x100>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 			interrupt-parent = <&local_intc>;
 		};
+	};
 
-		arm-pmu {
-			compatible = "arm,cortex-a7-pmu";
-			interrupt-parent = <&local_intc>;
-			interrupts = <9 IRQ_TYPE_LEVEL_HIGH>;
-		};
+	arm-pmu {
+		compatible = "arm,cortex-a7-pmu";
+		interrupt-parent = <&local_intc>;
+		interrupts = <9 IRQ_TYPE_LEVEL_HIGH>;
 	};
 
 	timer {
diff --git a/arch/arm/boot/dts/bcm2837.dtsi b/arch/arm/boot/dts/bcm2837.dtsi
index efa7d3387ab2..7704bb029605 100644
--- a/arch/arm/boot/dts/bcm2837.dtsi
+++ b/arch/arm/boot/dts/bcm2837.dtsi
@@ -8,7 +8,7 @@
 			 <0x40000000 0x40000000 0x00001000>;
 		dma-ranges = <0xc0000000 0x00000000 0x3f000000>;
 
-		local_intc: local_intc {
+		local_intc: local_intc@40000000 {
 			compatible = "brcm,bcm2836-l1-intc";
 			reg = <0x40000000 0x100>;
 			interrupt-controller;
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 18db25a5a66e..9d293decf8d3 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -465,7 +465,7 @@
 			status = "disabled";
 		};
 
-		aux: aux@0x7e215000 {
+		aux: aux@7e215000 {
 			compatible = "brcm,bcm2835-aux";
 			#clock-cells = <1>;
 			reg = <0x7e215000 0x8>;
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
index 6a44b8021702..f0e2008f7490 100644
--- a/arch/arm/boot/dts/bcm958625hr.dts
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -49,7 +49,7 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0x60000000 0x80000000>;
+		reg = <0x60000000 0x20000000>;
 	};
 
 	gpio-restart {
diff --git a/arch/arm/boot/dts/gemini-dlink-dns-313.dts b/arch/arm/boot/dts/gemini-dlink-dns-313.dts
index 08568ce24d06..da8bb9d60f99 100644
--- a/arch/arm/boot/dts/gemini-dlink-dns-313.dts
+++ b/arch/arm/boot/dts/gemini-dlink-dns-313.dts
@@ -269,7 +269,7 @@
 
 		sata: sata@46000000 {
 			/* The ROM uses this muxmode */
-			cortina,gemini-ata-muxmode = <3>;
+			cortina,gemini-ata-muxmode = <0>;
 			cortina,gemini-enable-sata-bridge;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/imx6dl-icore-rqs.dts b/arch/arm/boot/dts/imx6dl-icore-rqs.dts
index cf42c2f5cdc7..1281bc39b7ab 100644
--- a/arch/arm/boot/dts/imx6dl-icore-rqs.dts
+++ b/arch/arm/boot/dts/imx6dl-icore-rqs.dts
@@ -42,7 +42,7 @@
 
 /dts-v1/;
 
-#include "imx6q.dtsi"
+#include "imx6dl.dtsi"
 #include "imx6qdl-icore-rqs.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index c1aa7a4518fb..a30ee9fcb3ae 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -71,6 +71,8 @@
 };
 
 &i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <2600000>;
 
 	twl: twl@48 {
@@ -189,7 +191,12 @@
 		>;
 	};
 
-
+	i2c1_pins: pinmux_i2c1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0)        /* i2c1_scl.i2c1_scl */
+			OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0)        /* i2c1_sda.i2c1_sda */
+		>;
+	};
 };
 
 &omap3_pmx_wkup {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index b50b796e15c7..47915447a826 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -66,6 +66,8 @@
 };
 
 &i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <2600000>;
 
 	twl: twl@48 {
@@ -136,6 +138,12 @@
 			OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT | MUX_MODE0)	/* hsusb0_data7.hsusb0_data7 */
 		>;
 	};
+	i2c1_pins: pinmux_i2c1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0)        /* i2c1_scl.i2c1_scl */
+			OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0)        /* i2c1_sda.i2c1_sda */
+		>;
+	};
 };
 
 &uart2 {
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index ec2c8baef62a..592e17fd4eeb 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -47,7 +47,7 @@
 			gpios = <&gpio3 19 GPIO_ACTIVE_LOW>;	/* gpio3_83 */
 			wakeup-source;
 			autorepeat;
-			debounce_interval = <50>;
+			debounce-interval = <50>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi
index 3b704cfed69a..a97458112ff6 100644
--- a/arch/arm/boot/dts/rk3036.dtsi
+++ b/arch/arm/boot/dts/rk3036.dtsi
@@ -280,7 +280,7 @@
 		max-frequency = <37500000>;
 		clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>,
 			 <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
 		resets = <&cru SRST_SDIO>;
@@ -298,7 +298,7 @@
 		max-frequency = <37500000>;
 		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		default-sample-phase = <158>;
 		disable-wp;
 		dmas = <&pdma 12>;
diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi
index 780ec3a99b21..341deaf62ff6 100644
--- a/arch/arm/boot/dts/rk322x.dtsi
+++ b/arch/arm/boot/dts/rk322x.dtsi
@@ -621,7 +621,7 @@
 		interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>,
 			 <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_bus4>;
@@ -634,7 +634,7 @@
 		interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>,
 			 <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&sdio_clk &sdio_cmd &sdio_bus4>;
@@ -649,7 +649,7 @@
 		max-frequency = <37500000>;
 		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		bus-width = <8>;
 		default-sample-phase = <158>;
 		fifo-depth = <0x100>;
diff --git a/arch/arm/boot/dts/rk3288-phycore-som.dtsi b/arch/arm/boot/dts/rk3288-phycore-som.dtsi
index 99cfae875e12..5eae4776ffde 100644
--- a/arch/arm/boot/dts/rk3288-phycore-som.dtsi
+++ b/arch/arm/boot/dts/rk3288-phycore-som.dtsi
@@ -110,26 +110,6 @@
 	};
 };
 
-&cpu0 {
-	cpu0-supply = <&vdd_cpu>;
-	operating-points = <
-		/* KHz    uV */
-		1800000	1400000
-		1608000	1350000
-		1512000 1300000
-		1416000 1200000
-		1200000 1100000
-		1008000 1050000
-		 816000 1000000
-		 696000  950000
-		 600000  900000
-		 408000  900000
-		 312000  900000
-		 216000  900000
-		 126000  900000
-	>;
-};
-
 &emmc {
 	status = "okay";
 	bus-width = <8>;
diff --git a/arch/arm/boot/dts/zx296702.dtsi b/arch/arm/boot/dts/zx296702.dtsi
index 8a74efdb6360..240e7a23d81f 100644
--- a/arch/arm/boot/dts/zx296702.dtsi
+++ b/arch/arm/boot/dts/zx296702.dtsi
@@ -56,7 +56,7 @@
 			clocks = <&topclk ZX296702_A9_PERIPHCLK>;
 		};
 
-		l2cc: l2-cache-controller@0x00c00000 {
+		l2cc: l2-cache-controller@c00000 {
 			compatible = "arm,pl310-cache";
 			reg = <0x00c00000 0x1000>;
 			cache-unified;
@@ -67,30 +67,30 @@
 			arm,double-linefill-incr = <0>;
 		};
 
-		pcu: pcu@0xa0008000 {
+		pcu: pcu@a0008000 {
 			compatible = "zte,zx296702-pcu";
 			reg = <0xa0008000 0x1000>;
 		};
 
-		topclk: topclk@0x09800000 {
+		topclk: topclk@9800000 {
 			compatible = "zte,zx296702-topcrm-clk";
 			reg = <0x09800000 0x1000>;
 			#clock-cells = <1>;
 		};
 
-		lsp1clk: lsp1clk@0x09400000 {
+		lsp1clk: lsp1clk@9400000 {
 			compatible = "zte,zx296702-lsp1crpm-clk";
 			reg = <0x09400000 0x1000>;
 			#clock-cells = <1>;
 		};
 
-		lsp0clk: lsp0clk@0x0b000000 {
+		lsp0clk: lsp0clk@b000000 {
 			compatible = "zte,zx296702-lsp0crpm-clk";
 			reg = <0x0b000000 0x1000>;
 			#clock-cells = <1>;
 		};
 
-		uart0: serial@0x09405000 {
+		uart0: serial@9405000 {
 			compatible = "zte,zx296702-uart";
 			reg = <0x09405000 0x1000>;
 			interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
@@ -98,7 +98,7 @@
 			status = "disabled";
 		};
 
-		uart1: serial@0x09406000 {
+		uart1: serial@9406000 {
 			compatible = "zte,zx296702-uart";
 			reg = <0x09406000 0x1000>;
 			interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
@@ -106,7 +106,7 @@
 			status = "disabled";
 		};
 
-		mmc0: mmc@0x09408000 {
+		mmc0: mmc@9408000 {
 			compatible = "snps,dw-mshc";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -119,7 +119,7 @@
 			status = "disabled";
 		};
 
-		mmc1: mmc@0x0b003000 {
+		mmc1: mmc@b003000 {
 			compatible = "snps,dw-mshc";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -132,7 +132,7 @@
 			status = "disabled";
 		};
 
-		sysctrl: sysctrl@0xa0007000 {
+		sysctrl: sysctrl@a0007000 {
 			compatible = "zte,sysctrl", "syscon";
 			reg = <0xa0007000 0x1000>;
 		};
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 2f145c4af93a..92674f247a12 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -319,7 +319,7 @@ CONFIG_MEDIA_CAMERA_SUPPORT=y
 CONFIG_RC_CORE=m
 CONFIG_MEDIA_CONTROLLER=y
 CONFIG_VIDEO_V4L2_SUBDEV_API=y
-CONFIG_LIRC=m
+CONFIG_LIRC=y
 CONFIG_RC_DEVICES=y
 CONFIG_IR_RX51=m
 CONFIG_V4L_PLATFORM_DRIVERS=y
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 5638ce0c9524..63d6b404d88e 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -7,6 +7,8 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
 
 KVM=../../../../virt/kvm
 
+CFLAGS_ARMV7VE		   :=$(call cc-option, -march=armv7ve)
+
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
@@ -15,7 +17,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
 obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += vfp.o
 obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o
+CFLAGS_banked-sr.o	   += $(CFLAGS_ARMV7VE)
+
 obj-$(CONFIG_KVM_ARM_HOST) += entry.o
 obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
 obj-$(CONFIG_KVM_ARM_HOST) += switch.o
+CFLAGS_switch.o		   += $(CFLAGS_ARMV7VE)
 obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c
index 111bda8cdebd..be4b8b0a40ad 100644
--- a/arch/arm/kvm/hyp/banked-sr.c
+++ b/arch/arm/kvm/hyp/banked-sr.c
@@ -20,6 +20,10 @@
 
 #include <asm/kvm_hyp.h>
 
+/*
+ * gcc before 4.9 doesn't understand -march=armv7ve, so we have to
+ * trick the assembler.
+ */
 __asm__(".arch_extension     virt");
 
 void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt)
diff --git a/arch/arm/mach-clps711x/board-dt.c b/arch/arm/mach-clps711x/board-dt.c
index ee1f83b1a332..4c89a8e9a2e3 100644
--- a/arch/arm/mach-clps711x/board-dt.c
+++ b/arch/arm/mach-clps711x/board-dt.c
@@ -69,7 +69,7 @@ static void clps711x_restart(enum reboot_mode mode, const char *cmd)
 	soft_restart(0);
 }
 
-static const char *clps711x_compat[] __initconst = {
+static const char *const clps711x_compat[] __initconst = {
 	"cirrus,ep7209",
 	NULL
 };
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index e457f299cd44..d6b11907380c 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -368,7 +368,7 @@ static struct spi_eeprom at25640a = {
 	.flags		= EE_ADDR2,
 };
 
-static struct spi_board_info dm355_evm_spi_info[] __initconst = {
+static const struct spi_board_info dm355_evm_spi_info[] __initconst = {
 	{
 		.modalias	= "at25",
 		.platform_data	= &at25640a,
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index be997243447b..fad9a5611a5d 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -217,7 +217,7 @@ static struct spi_eeprom at25640a = {
 	.flags		= EE_ADDR2,
 };
 
-static struct spi_board_info dm355_leopard_spi_info[] __initconst = {
+static const struct spi_board_info dm355_leopard_spi_info[] __initconst = {
 	{
 		.modalias	= "at25",
 		.platform_data	= &at25640a,
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index e75741fb2c1d..e3780986d2a3 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -726,7 +726,7 @@ static struct spi_eeprom at25640 = {
 	.flags		= EE_ADDR2,
 };
 
-static struct spi_board_info dm365_evm_spi_info[] __initconst = {
+static const struct spi_board_info dm365_evm_spi_info[] __initconst = {
 	{
 		.modalias	= "at25",
 		.platform_data	= &at25640,
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 6b32dc527edc..2c20599cc350 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -41,7 +41,7 @@ config MACH_ARMADA_375
 	depends on ARCH_MULTI_V7
 	select ARMADA_370_XP_IRQ
 	select ARM_ERRATA_720789
-	select ARM_ERRATA_753970
+	select PL310_ERRATA_753970
 	select ARM_GIC
 	select ARMADA_375_CLK
 	select HAVE_ARM_SCU
@@ -57,7 +57,7 @@ config MACH_ARMADA_38X
 	bool "Marvell Armada 380/385 boards"
 	depends on ARCH_MULTI_V7
 	select ARM_ERRATA_720789
-	select ARM_ERRATA_753970
+	select PL310_ERRATA_753970
 	select ARM_GIC
 	select ARM_GLOBAL_TIMER
 	select CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c
index 43e3e188f521..fa512413a471 100644
--- a/arch/arm/mach-omap1/clock.c
+++ b/arch/arm/mach-omap1/clock.c
@@ -1011,17 +1011,17 @@ static int clk_debugfs_register_one(struct clk *c)
 		return -ENOMEM;
 	c->dent = d;
 
-	d = debugfs_create_u8("usecount", S_IRUGO, c->dent, (u8 *)&c->usecount);
+	d = debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount);
 	if (!d) {
 		err = -ENOMEM;
 		goto err_out;
 	}
-	d = debugfs_create_u32("rate", S_IRUGO, c->dent, (u32 *)&c->rate);
+	d = debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate);
 	if (!d) {
 		err = -ENOMEM;
 		goto err_out;
 	}
-	d = debugfs_create_x32("flags", S_IRUGO, c->dent, (u32 *)&c->flags);
+	d = debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags);
 	if (!d) {
 		err = -ENOMEM;
 		goto err_out;
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index 4bb6751864a5..fc5fb776a710 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -299,8 +299,6 @@ static void irq_save_context(void)
 	if (soc_is_dra7xx())
 		return;
 
-	if (!sar_base)
-		sar_base = omap4_get_sar_ram_base();
 	if (wakeupgen_ops && wakeupgen_ops->save_context)
 		wakeupgen_ops->save_context();
 }
@@ -598,6 +596,8 @@ static int __init wakeupgen_init(struct device_node *node,
 	irq_hotplug_init();
 	irq_pm_init();
 
+	sar_base = omap4_get_sar_ram_base();
+
 	return 0;
 }
 IRQCHIP_DECLARE(ti_wakeupgen, "ti,omap4-wugen-mpu", wakeupgen_init);
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 124f9af34a15..34156eca8e23 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -977,6 +977,9 @@ static int _enable_clocks(struct omap_hwmod *oh)
 
 	pr_debug("omap_hwmod: %s: enabling clocks\n", oh->name);
 
+	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+		_enable_optional_clocks(oh);
+
 	if (oh->_clk)
 		clk_enable(oh->_clk);
 
@@ -985,9 +988,6 @@ static int _enable_clocks(struct omap_hwmod *oh)
 			clk_enable(os->_clk);
 	}
 
-	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
-		_enable_optional_clocks(oh);
-
 	/* The opt clocks are controlled by the device driver. */
 
 	return 0;
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 366158a54fcd..6f68576e5695 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -186,7 +186,7 @@ static void omap_pm_end(void)
 	cpu_idle_poll_ctrl(false);
 }
 
-static void omap_pm_finish(void)
+static void omap_pm_wake(void)
 {
 	if (soc_is_omap34xx())
 		omap_prcm_irq_complete();
@@ -196,7 +196,7 @@ static const struct platform_suspend_ops omap_pm_ops = {
 	.begin		= omap_pm_begin,
 	.end		= omap_pm_end,
 	.enter		= omap_pm_enter,
-	.finish		= omap_pm_finish,
+	.wake		= omap_pm_wake,
 	.valid		= suspend_valid_only_mem,
 };
 
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index ece09c9461f7..d61fbd7a2840 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -156,12 +156,6 @@ static struct clock_event_device clockevent_gpt = {
 	.tick_resume		= omap2_gp_timer_shutdown,
 };
 
-static struct property device_disabled = {
-	.name = "status",
-	.length = sizeof("disabled"),
-	.value = "disabled",
-};
-
 static const struct of_device_id omap_timer_match[] __initconst = {
 	{ .compatible = "ti,omap2420-timer", },
 	{ .compatible = "ti,omap3430-timer", },
@@ -203,8 +197,17 @@ static struct device_node * __init omap_get_timer_dt(const struct of_device_id *
 				  of_get_property(np, "ti,timer-secure", NULL)))
 			continue;
 
-		if (!of_device_is_compatible(np, "ti,omap-counter32k"))
-			of_add_property(np, &device_disabled);
+		if (!of_device_is_compatible(np, "ti,omap-counter32k")) {
+			struct property *prop;
+
+			prop = kzalloc(sizeof(*prop), GFP_KERNEL);
+			if (!prop)
+				return NULL;
+			prop->name = "status";
+			prop->value = "disabled";
+			prop->length = strlen(prop->value);
+			of_add_property(np, prop);
+		}
 		return np;
 	}
 
diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig
index 2a7bb6ccdcb7..a810f4dd34b1 100644
--- a/arch/arm/mach-orion5x/Kconfig
+++ b/arch/arm/mach-orion5x/Kconfig
@@ -58,7 +58,6 @@ config MACH_KUROBOX_PRO
 
 config MACH_DNS323
 	bool "D-Link DNS-323"
-	select GENERIC_NET_UTILS
 	select I2C_BOARDINFO if I2C
 	help
 	  Say 'Y' here if you want your kernel to support the
@@ -66,7 +65,6 @@ config MACH_DNS323
 
 config MACH_TS209
 	bool "QNAP TS-109/TS-209"
-	select GENERIC_NET_UTILS
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  QNAP TS-109/TS-209 platform.
@@ -101,7 +99,6 @@ config MACH_LINKSTATION_LS_HGL
 
 config MACH_TS409
 	bool "QNAP TS-409"
-	select GENERIC_NET_UTILS
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  QNAP TS-409 platform.
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index cd483bfb5ca8..d13344b2ddcd 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -173,10 +173,42 @@ static struct mv643xx_eth_platform_data dns323_eth_data = {
 	.phy_addr = MV643XX_ETH_PHY_ADDR(8),
 };
 
+/* dns323_parse_hex_*() taken from tsx09-common.c; should a common copy of these
+ * functions be kept somewhere?
+ */
+static int __init dns323_parse_hex_nibble(char n)
+{
+	if (n >= '0' && n <= '9')
+		return n - '0';
+
+	if (n >= 'A' && n <= 'F')
+		return n - 'A' + 10;
+
+	if (n >= 'a' && n <= 'f')
+		return n - 'a' + 10;
+
+	return -1;
+}
+
+static int __init dns323_parse_hex_byte(const char *b)
+{
+	int hi;
+	int lo;
+
+	hi = dns323_parse_hex_nibble(b[0]);
+	lo = dns323_parse_hex_nibble(b[1]);
+
+	if (hi < 0 || lo < 0)
+		return -1;
+
+	return (hi << 4) | lo;
+}
+
 static int __init dns323_read_mac_addr(void)
 {
 	u_int8_t addr[6];
-	void __iomem *mac_page;
+	int i;
+	char *mac_page;
 
 	/* MAC address is stored as a regular ol' string in /dev/mtdblock4
 	 * (0x007d0000-0x00800000) starting at offset 196480 (0x2ff80).
@@ -185,8 +217,23 @@ static int __init dns323_read_mac_addr(void)
 	if (!mac_page)
 		return -ENOMEM;
 
-	if (!mac_pton((__force const char *) mac_page, addr))
-		goto error_fail;
+	/* Sanity check the string we're looking at */
+	for (i = 0; i < 5; i++) {
+		if (*(mac_page + (i * 3) + 2) != ':') {
+			goto error_fail;
+		}
+	}
+
+	for (i = 0; i < 6; i++)	{
+		int byte;
+
+		byte = dns323_parse_hex_byte(mac_page + (i * 3));
+		if (byte < 0) {
+			goto error_fail;
+		}
+
+		addr[i] = byte;
+	}
 
 	iounmap(mac_page);
 	printk("DNS-323: Found ethernet MAC address: %pM\n", addr);
diff --git a/arch/arm/mach-orion5x/tsx09-common.c b/arch/arm/mach-orion5x/tsx09-common.c
index 89774985d380..905d4f2dd0b8 100644
--- a/arch/arm/mach-orion5x/tsx09-common.c
+++ b/arch/arm/mach-orion5x/tsx09-common.c
@@ -53,12 +53,53 @@ struct mv643xx_eth_platform_data qnap_tsx09_eth_data = {
 	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
 };
 
+static int __init qnap_tsx09_parse_hex_nibble(char n)
+{
+	if (n >= '0' && n <= '9')
+		return n - '0';
+
+	if (n >= 'A' && n <= 'F')
+		return n - 'A' + 10;
+
+	if (n >= 'a' && n <= 'f')
+		return n - 'a' + 10;
+
+	return -1;
+}
+
+static int __init qnap_tsx09_parse_hex_byte(const char *b)
+{
+	int hi;
+	int lo;
+
+	hi = qnap_tsx09_parse_hex_nibble(b[0]);
+	lo = qnap_tsx09_parse_hex_nibble(b[1]);
+
+	if (hi < 0 || lo < 0)
+		return -1;
+
+	return (hi << 4) | lo;
+}
+
 static int __init qnap_tsx09_check_mac_addr(const char *addr_str)
 {
 	u_int8_t addr[6];
+	int i;
 
-	if (!mac_pton(addr_str, addr))
-		return -1;
+	for (i = 0; i < 6; i++) {
+		int byte;
+
+		/*
+		 * Enforce "xx:xx:xx:xx:xx:xx\n" format.
+		 */
+		if (addr_str[(i * 3) + 2] != ((i < 5) ? ':' : '\n'))
+			return -1;
+
+		byte = qnap_tsx09_parse_hex_byte(addr_str + (i * 3));
+		if (byte < 0)
+			return -1;
+		addr[i] = byte;
+	}
 
 	printk(KERN_INFO "tsx09: found ethernet mac address %pM\n", addr);
 
@@ -77,12 +118,12 @@ void __init qnap_tsx09_find_mac_addr(u32 mem_base, u32 size)
 	unsigned long addr;
 
 	for (addr = mem_base; addr < (mem_base + size); addr += 1024) {
-		void __iomem *nor_page;
+		char *nor_page;
 		int ret = 0;
 
 		nor_page = ioremap(addr, 1024);
 		if (nor_page != NULL) {
-			ret = qnap_tsx09_check_mac_addr((__force const char *)nor_page);
+			ret = qnap_tsx09_check_mac_addr(nor_page);
 			iounmap(nor_page);
 		}
 
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index aff6994950ba..a2399fd66e97 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -472,28 +472,27 @@ void __init orion_ge11_init(struct mv643xx_eth_platform_data *eth_data,
 /*****************************************************************************
  * Ethernet switch
  ****************************************************************************/
-static __initconst const char *orion_ge00_mvmdio_bus_name = "orion-mii";
-static __initdata struct mdio_board_info
-		  orion_ge00_switch_board_info;
+static __initdata struct mdio_board_info orion_ge00_switch_board_info = {
+	.bus_id   = "orion-mii",
+	.modalias = "mv88e6085",
+};
 
 void __init orion_ge00_switch_init(struct dsa_chip_data *d)
 {
-	struct mdio_board_info *bd;
 	unsigned int i;
 
 	if (!IS_BUILTIN(CONFIG_PHYLIB))
 		return;
 
-	for (i = 0; i < ARRAY_SIZE(d->port_names); i++)
-		if (!strcmp(d->port_names[i], "cpu"))
+	for (i = 0; i < ARRAY_SIZE(d->port_names); i++) {
+		if (!strcmp(d->port_names[i], "cpu")) {
+			d->netdev[i] = &orion_ge00.dev;
 			break;
+		}
+	}
 
-	bd = &orion_ge00_switch_board_info;
-	bd->bus_id = orion_ge00_mvmdio_bus_name;
-	bd->mdio_addr = d->sw_addr;
-	d->netdev[i] = &orion_ge00.dev;
-	strcpy(bd->modalias, "mv88e6085");
-	bd->platform_data = d;
+	orion_ge00_switch_board_info.mdio_addr = d->sw_addr;
+	orion_ge00_switch_board_info.platform_data = d;
 
 	mdiobus_register_board_info(&orion_ge00_switch_board_info, 1);
 }
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index a80632641b39..70c776ef7aa7 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -165,14 +165,14 @@
 
 			uart_A: serial@24000 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart";
-				reg = <0x0 0x24000 0x0 0x14>;
+				reg = <0x0 0x24000 0x0 0x18>;
 				interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
 			uart_B: serial@23000 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart";
-				reg = <0x0 0x23000 0x0 0x14>;
+				reg = <0x0 0x23000 0x0 0x18>;
 				interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 6cb3c2a52baf..4ee2e7951482 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -235,14 +235,14 @@
 
 			uart_A: serial@84c0 {
 				compatible = "amlogic,meson-gx-uart";
-				reg = <0x0 0x84c0 0x0 0x14>;
+				reg = <0x0 0x84c0 0x0 0x18>;
 				interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
 			uart_B: serial@84dc {
 				compatible = "amlogic,meson-gx-uart";
-				reg = <0x0 0x84dc 0x0 0x14>;
+				reg = <0x0 0x84dc 0x0 0x18>;
 				interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
@@ -287,7 +287,7 @@
 
 			uart_C: serial@8700 {
 				compatible = "amlogic,meson-gx-uart";
-				reg = <0x0 0x8700 0x0 0x14>;
+				reg = <0x0 0x8700 0x0 0x18>;
 				interrupts = <GIC_SPI 93 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
@@ -404,14 +404,14 @@
 
 			uart_AO: serial@4c0 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart";
-				reg = <0x0 0x004c0 0x0 0x14>;
+				reg = <0x0 0x004c0 0x0 0x18>;
 				interrupts = <GIC_SPI 193 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
 			uart_AO_B: serial@4e0 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart";
-				reg = <0x0 0x004e0 0x0 0x14>;
+				reg = <0x0 0x004e0 0x0 0x18>;
 				interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 4f355f17eed6..c8514110b9da 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -631,6 +631,7 @@
 
 			internal_phy: ethernet-phy@8 {
 				compatible = "ethernet-phy-id0181.4400", "ethernet-phy-ieee802.3-c22";
+				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <8>;
 				max-speed = <100>;
 			};
diff --git a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi
index 4220fbdcb24a..ff5c4c47b22b 100644
--- a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi
+++ b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi
@@ -98,7 +98,7 @@
 		clock-output-names = "clk125mhz";
 	};
 
-	pci {
+	pcie@30000000 {
 		compatible = "pci-host-ecam-generic";
 		device_type = "pci";
 		#interrupt-cells = <1>;
@@ -118,6 +118,7 @@
 		ranges =
 		  <0x02000000    0 0x40000000    0 0x40000000    0 0x20000000
 		   0x43000000 0x40 0x00000000 0x40 0x00000000 0x20 0x00000000>;
+		bus-range = <0 0xff>;
 		interrupt-map-mask = <0 0 0 7>;
 		interrupt-map =
 		      /* addr  pin  ic   icaddr  icintr */
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index e94fa1a53192..047641fe294c 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -51,7 +51,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		ramoops@0x21f00000 {
+		ramoops@21f00000 {
 			compatible = "ramoops";
 			reg = <0x0 0x21f00000 0x0 0x00100000>;
 			record-size	= <0x00020000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 9fbe4705ee88..94597e33c806 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -341,7 +341,7 @@
 			reg = <0 0x10005000 0 0x1000>;
 		};
 
-		pio: pinctrl@0x10005000 {
+		pio: pinctrl@10005000 {
 			compatible = "mediatek,mt8173-pinctrl";
 			reg = <0 0x1000b000 0 0x1000>;
 			mediatek,pctl-regmap = <&syscfg_pctl_a>;
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
index 492a011f14f6..1c8f1b86472d 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
@@ -140,16 +140,16 @@
 		};
 
 		agnoc@0 {
-			qcom,pcie@00600000 {
+			qcom,pcie@600000 {
 				perst-gpio = <&msmgpio 35 GPIO_ACTIVE_LOW>;
 			};
 
-			qcom,pcie@00608000 {
+			qcom,pcie@608000 {
 				status = "okay";
 				perst-gpio = <&msmgpio 130 GPIO_ACTIVE_LOW>;
 			};
 
-			qcom,pcie@00610000 {
+			qcom,pcie@610000 {
 				status = "okay";
 				perst-gpio = <&msmgpio 114 GPIO_ACTIVE_LOW>;
 			};
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 4b2afcc4fdf4..0a6f7952bbb1 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -840,7 +840,7 @@
 			#size-cells = <1>;
 			ranges;
 
-			pcie0: qcom,pcie@00600000 {
+			pcie0: qcom,pcie@600000 {
 				compatible = "qcom,pcie-msm8996", "snps,dw-pcie";
 				status = "disabled";
 				power-domains = <&gcc PCIE0_GDSC>;
@@ -893,7 +893,7 @@
 
 			};
 
-			pcie1: qcom,pcie@00608000 {
+			pcie1: qcom,pcie@608000 {
 				compatible = "qcom,pcie-msm8996", "snps,dw-pcie";
 				power-domains = <&gcc PCIE1_GDSC>;
 				bus-range = <0x00 0xff>;
@@ -946,7 +946,7 @@
 						"bus_slave";
 			};
 
-			pcie2: qcom,pcie@00610000 {
+			pcie2: qcom,pcie@610000 {
 				compatible = "qcom,pcie-msm8996", "snps,dw-pcie";
 				power-domains = <&gcc PCIE2_GDSC>;
 				bus-range = <0x00 0xff>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index 3890468678ce..28257724a56e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -132,17 +132,16 @@
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>;
 	clock_in_out = "input";
-	/* shows instability at 1GBit right now */
-	max-speed = <100>;
 	phy-supply = <&vcc_io>;
 	phy-mode = "rgmii";
 	pinctrl-names = "default";
 	pinctrl-0 = <&rgmiim1_pins>;
+	snps,force_thresh_dma_mode;
 	snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>;
 	snps,reset-active-low;
 	snps,reset-delays-us = <0 10000 50000>;
-	tx_delay = <0x26>;
-	rx_delay = <0x11>;
+	tx_delay = <0x24>;
+	rx_delay = <0x18>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index a037ee56fead..cae341554486 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -730,7 +730,7 @@
 		interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>,
 			 <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		status = "disabled";
 	};
@@ -741,7 +741,7 @@
 		interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>,
 			 <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		status = "disabled";
 	};
@@ -752,7 +752,7 @@
 		interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		status = "disabled";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index aa4d07046a7b..03458ac44201 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -257,7 +257,7 @@
 		max-frequency = <150000000>;
 		clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>,
 			 <&cru SCLK_SDIO0_DRV>, <&cru SCLK_SDIO0_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
 		resets = <&cru SRST_SDIO0>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
index 0f873c897d0d..ce592a4c0c4c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
@@ -457,7 +457,7 @@
 	assigned-clocks = <&cru SCLK_PCIEPHY_REF>;
 	assigned-clock-parents = <&cru SCLK_PCIEPHY_REF100M>;
 	assigned-clock-rates = <100000000>;
-	ep-gpios = <&gpio3 RK_PB5 GPIO_ACTIVE_HIGH>;
+	ep-gpios = <&gpio2 RK_PA4 GPIO_ACTIVE_HIGH>;
 	num-lanes = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie_clkreqn_cpm>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 7aa2144e0d47..2605118d4b4c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -1739,8 +1739,8 @@
 		compatible = "rockchip,rk3399-edp";
 		reg = <0x0 0xff970000 0x0 0x8000>;
 		interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH 0>;
-		clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>;
-		clock-names = "dp", "pclk";
+		clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>, <&cru PCLK_VIO_GRF>;
+		clock-names = "dp", "pclk", "grf";
 		pinctrl-names = "default";
 		pinctrl-0 = <&edp_hpd>;
 		power-domains = <&power RK3399_PD_EDP>;
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 52f15cd896e1..b5a28336c077 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -178,7 +178,7 @@ static int enable_smccc_arch_workaround_1(void *data)
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if (res.a0)
+		if ((int)res.a0 < 0)
 			return 0;
 		cb = call_hvc_arch_workaround_1;
 		smccc_start = __smccc_workaround_1_hvc_start;
@@ -188,7 +188,7 @@ static int enable_smccc_arch_workaround_1(void *data)
 	case PSCI_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if (res.a0)
+		if ((int)res.a0 < 0)
 			return 0;
 		cb = call_smc_arch_workaround_1;
 		smccc_start = __smccc_workaround_1_smc_start;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index d7e3299a7734..959e50d2588c 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -363,8 +363,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 {
 	int ret = 0;
 
-	vcpu_load(vcpu);
-
 	trace_kvm_set_guest_debug(vcpu, dbg->control);
 
 	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) {
@@ -386,7 +384,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	}
 
 out:
-	vcpu_put(vcpu);
 	return ret;
 }
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 84a019f55022..8c704f1e53c2 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -108,7 +108,7 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
 	 * The following mapping attributes may be updated in live
 	 * kernel mappings without the need for break-before-make.
 	 */
-	static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE;
+	static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
 
 	/* creating or taking down mappings is always safe */
 	if (old == 0 || new == 0)
@@ -118,9 +118,9 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
 	if ((old | new) & PTE_CONT)
 		return false;
 
-	/* Transitioning from Global to Non-Global is safe */
-	if (((old ^ new) == PTE_NG) && (new & PTE_NG))
-		return true;
+	/* Transitioning from Non-Global to Global is unsafe */
+	if (old & ~new & PTE_NG)
+		return false;
 
 	return ((old ^ new) & ~mask) == 0;
 }
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 762eeb0fcc1d..2524fb60fbc2 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -66,38 +66,35 @@ ATOMIC_OPS(add, +)
 ATOMIC_OPS(sub, -)
 
 #ifdef __OPTIMIZE__
-#define __ia64_atomic_const(i)	__builtin_constant_p(i) ?		\
+#define __ia64_atomic_const(i)						\
+	static const int __ia64_atomic_p = __builtin_constant_p(i) ?	\
 		((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 ||	\
-		 (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0
+		 (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0;\
+	__ia64_atomic_p
+#else
+#define __ia64_atomic_const(i)	0
+#endif
 
-#define atomic_add_return(i, v)						\
+#define atomic_add_return(i,v)						\
 ({									\
-	int __i = (i);							\
-	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
-	__ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) :	\
-				ia64_atomic_add(__i, v);		\
+	int __ia64_aar_i = (i);						\
+	__ia64_atomic_const(i)						\
+		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
+		: ia64_atomic_add(__ia64_aar_i, v);			\
 })
 
-#define atomic_sub_return(i, v)						\
+#define atomic_sub_return(i,v)						\
 ({									\
-	int __i = (i);							\
-	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
-	__ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) :	\
-				ia64_atomic_sub(__i, v);		\
+	int __ia64_asr_i = (i);						\
+	__ia64_atomic_const(i)						\
+		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
+		: ia64_atomic_sub(__ia64_asr_i, v);			\
 })
-#else
-#define atomic_add_return(i, v)	ia64_atomic_add(i, v)
-#define atomic_sub_return(i, v)	ia64_atomic_sub(i, v)
-#endif
 
 #define atomic_fetch_add(i,v)						\
 ({									\
 	int __ia64_aar_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
 		: ia64_atomic_fetch_add(__ia64_aar_i, v);		\
 })
@@ -105,11 +102,7 @@ ATOMIC_OPS(sub, -)
 #define atomic_fetch_sub(i,v)						\
 ({									\
 	int __ia64_asr_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
 		: ia64_atomic_fetch_sub(__ia64_asr_i, v);		\
 })
@@ -170,11 +163,7 @@ ATOMIC64_OPS(sub, -)
 #define atomic64_add_return(i,v)					\
 ({									\
 	long __ia64_aar_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
 		: ia64_atomic64_add(__ia64_aar_i, v);			\
 })
@@ -182,11 +171,7 @@ ATOMIC64_OPS(sub, -)
 #define atomic64_sub_return(i,v)					\
 ({									\
 	long __ia64_asr_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
 		: ia64_atomic64_sub(__ia64_asr_i, v);			\
 })
@@ -194,11 +179,7 @@ ATOMIC64_OPS(sub, -)
 #define atomic64_fetch_add(i,v)						\
 ({									\
 	long __ia64_aar_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
 		: ia64_atomic64_fetch_add(__ia64_aar_i, v);		\
 })
@@ -206,11 +187,7 @@ ATOMIC64_OPS(sub, -)
 #define atomic64_fetch_sub(i,v)						\
 ({									\
 	long __ia64_asr_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
 		: ia64_atomic64_fetch_sub(__ia64_asr_i, v);		\
 })
diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c
index 85bba43e7d5d..8b5b8e6bc9d9 100644
--- a/arch/ia64/kernel/err_inject.c
+++ b/arch/ia64/kernel/err_inject.c
@@ -117,7 +117,7 @@ store_call_start(struct device *dev, struct device_attribute *attr,
 
 #ifdef ERR_INJ_DEBUG
 	printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]);
-	printk(KERN_DEBUG "capapbilities=%lx,\n", capabilities[cpu]);
+	printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]);
 	printk(KERN_DEBUG "resources=%lx\n", resources[cpu]);
 #endif
 	return size;
@@ -142,7 +142,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
 	u64 virt_addr=simple_strtoull(buf, NULL, 16);
 	int ret;
 
-	ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL);
+	ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL);
 	if (ret<=0) {
 #ifdef ERR_INJ_DEBUG
 		printk("Virtual address %lx is not existing.\n",virt_addr);
diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py
index 89f3a1480a63..c55276e31b6b 100644
--- a/arch/ia64/scripts/unwcheck.py
+++ b/arch/ia64/scripts/unwcheck.py
@@ -16,7 +16,7 @@ import re
 import sys
 
 if len(sys.argv) != 2:
-    print "Usage: %s FILE" % sys.argv[0]
+    print("Usage: %s FILE" % sys.argv[0])
     sys.exit(2)
 
 readelf = os.getenv("READELF", "readelf")
@@ -29,7 +29,7 @@ def check_func (func, slots, rlen_sum):
         global num_errors
         num_errors += 1
         if not func: func = "[%#x-%#x]" % (start, end)
-        print "ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum)
+        print("ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum))
     return
 
 num_funcs = 0
@@ -43,23 +43,23 @@ for line in os.popen("%s -u %s" % (readelf, sys.argv[1])):
         check_func(func, slots, rlen_sum)
 
         func  = m.group(1)
-        start = long(m.group(2), 16)
-        end   = long(m.group(3), 16)
+        start = int(m.group(2), 16)
+        end   = int(m.group(3), 16)
         slots = 3 * (end - start) / 16
-        rlen_sum = 0L
+        rlen_sum = 0
         num_funcs += 1
     else:
         m = rlen_pattern.match(line)
         if m:
-            rlen_sum += long(m.group(1))
+            rlen_sum += int(m.group(1))
 check_func(func, slots, rlen_sum)
 
 if num_errors == 0:
-    print "No errors detected in %u functions." % num_funcs
+    print("No errors detected in %u functions." % num_funcs)
 else:
     if num_errors > 1:
         err="errors"
     else:
         err="error"
-    print "%u %s detected in %u functions." % (num_errors, err, num_funcs)
+    print("%u %s detected in %u functions." % (num_errors, err, num_funcs))
     sys.exit(1)
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 4f798aa671dd..3817a3e2146c 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -24,6 +24,7 @@ config MICROBLAZE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
+	select NO_BOOTMEM
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_OPROFILE
diff --git a/arch/microblaze/Kconfig.platform b/arch/microblaze/Kconfig.platform
index 6996f397c16c..f7f1739c11b9 100644
--- a/arch/microblaze/Kconfig.platform
+++ b/arch/microblaze/Kconfig.platform
@@ -8,7 +8,6 @@ menu "Platform options"
 
 config OPT_LIB_FUNCTION
 	bool "Optimalized lib function"
-	depends on CPU_LITTLE_ENDIAN
 	default y
 	help
 	  Allows turn on optimalized library function (memcpy and memmove).
@@ -21,6 +20,7 @@ config OPT_LIB_FUNCTION
 config OPT_LIB_ASM
 	bool "Optimalized lib function ASM"
 	depends on OPT_LIB_FUNCTION && (XILINX_MICROBLAZE0_USE_BARREL = 1)
+	depends on CPU_BIG_ENDIAN
 	default n
 	help
 	  Allows turn on optimalized library function (memcpy and memmove).
diff --git a/arch/microblaze/include/asm/setup.h b/arch/microblaze/include/asm/setup.h
index be84a4d3917f..7c968c1d1729 100644
--- a/arch/microblaze/include/asm/setup.h
+++ b/arch/microblaze/include/asm/setup.h
@@ -44,7 +44,6 @@ void machine_shutdown(void);
 void machine_halt(void);
 void machine_power_off(void);
 
-extern void *alloc_maybe_bootmem(size_t size, gfp_t mask);
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
 # endif /* __ASSEMBLY__ */
diff --git a/arch/microblaze/lib/fastcopy.S b/arch/microblaze/lib/fastcopy.S
index 62021d7e249e..fdc48bb065d8 100644
--- a/arch/microblaze/lib/fastcopy.S
+++ b/arch/microblaze/lib/fastcopy.S
@@ -29,10 +29,6 @@
  *	between mem locations with size of xfer spec'd in bytes
  */
 
-#ifdef __MICROBLAZEEL__
-#error Microblaze LE not support ASM optimized lib func. Disable OPT_LIB_ASM.
-#endif
-
 #include <linux/linkage.h>
 	.text
 	.globl	memcpy
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 434639f9a3a6..df6de7ccdc2e 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -32,9 +32,6 @@ int mem_init_done;
 #ifndef CONFIG_MMU
 unsigned int __page_offset;
 EXPORT_SYMBOL(__page_offset);
-
-#else
-static int init_bootmem_done;
 #endif /* CONFIG_MMU */
 
 char *klimit = _end;
@@ -117,7 +114,6 @@ static void __init paging_init(void)
 
 void __init setup_memory(void)
 {
-	unsigned long map_size;
 	struct memblock_region *reg;
 
 #ifndef CONFIG_MMU
@@ -174,17 +170,6 @@ void __init setup_memory(void)
 	pr_info("%s: max_low_pfn: %#lx\n", __func__, max_low_pfn);
 	pr_info("%s: max_pfn: %#lx\n", __func__, max_pfn);
 
-	/*
-	 * Find an area to use for the bootmem bitmap.
-	 * We look for the first area which is at least
-	 * 128kB in length (128kB is enough for a bitmap
-	 * for 4GB of memory, using 4kB pages), plus 1 page
-	 * (in case the address isn't page-aligned).
-	 */
-	map_size = init_bootmem_node(NODE_DATA(0),
-		PFN_UP(TOPHYS((u32)klimit)), min_low_pfn, max_low_pfn);
-	memblock_reserve(PFN_UP(TOPHYS((u32)klimit)) << PAGE_SHIFT, map_size);
-
 	/* Add active regions with valid PFNs */
 	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
@@ -196,32 +181,9 @@ void __init setup_memory(void)
 				  &memblock.memory, 0);
 	}
 
-	/* free bootmem is whole main memory */
-	free_bootmem_with_active_regions(0, max_low_pfn);
-
-	/* reserve allocate blocks */
-	for_each_memblock(reserved, reg) {
-		unsigned long top = reg->base + reg->size - 1;
-
-		pr_debug("reserved - 0x%08x-0x%08x, %lx, %lx\n",
-			 (u32) reg->base, (u32) reg->size, top,
-						memory_start + lowmem_size - 1);
-
-		if (top <= (memory_start + lowmem_size - 1)) {
-			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
-		} else if (reg->base < (memory_start + lowmem_size - 1)) {
-			unsigned long trunc_size = memory_start + lowmem_size -
-								reg->base;
-			reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
-		}
-	}
-
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
 
-#ifdef CONFIG_MMU
-	init_bootmem_done = 1;
-#endif
 	paging_init();
 }
 
@@ -398,30 +360,16 @@ asmlinkage void __init mmu_init(void)
 /* This is only called until mem_init is done. */
 void __init *early_get_page(void)
 {
-	void *p;
-	if (init_bootmem_done) {
-		p = alloc_bootmem_pages(PAGE_SIZE);
-	} else {
-		/*
-		 * Mem start + kernel_tlb -> here is limit
-		 * because of mem mapping from head.S
-		 */
-		p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
-					memory_start + kernel_tlb));
-	}
-	return p;
+	/*
+	 * Mem start + kernel_tlb -> here is limit
+	 * because of mem mapping from head.S
+	 */
+	return __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
+				memory_start + kernel_tlb));
 }
 
 #endif /* CONFIG_MMU */
 
-void * __ref alloc_maybe_bootmem(size_t size, gfp_t mask)
-{
-	if (mem_init_done)
-		return kmalloc(size, mask);
-	else
-		return alloc_bootmem(size);
-}
-
 void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
 {
 	void *p;
diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c
index 9ab48ff80c1c..6d11ae581ea7 100644
--- a/arch/mips/ath25/board.c
+++ b/arch/mips/ath25/board.c
@@ -135,6 +135,8 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size)
 	}
 
 	board_data = kzalloc(BOARD_CONFIG_BUFSZ, GFP_KERNEL);
+	if (!board_data)
+		goto error;
 	ath25_board.config = (struct ath25_boarddata *)board_data;
 	memcpy_fromio(board_data, bcfg, 0x100);
 	if (broken_boarddata) {
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 5b3a3f6a9ad3..d99f5242169e 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -2277,6 +2277,8 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node,
 	}
 
 	host_data = kzalloc(sizeof(*host_data), GFP_KERNEL);
+	if (!host_data)
+		return -ENOMEM;
 	raw_spin_lock_init(&host_data->lock);
 
 	addr = of_get_address(ciu_node, 0, NULL, NULL);
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 9d41732a9146..159e83add4bb 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -168,11 +168,11 @@ static void bmips_prepare_cpus(unsigned int max_cpus)
 		return;
 	}
 
-	if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
-			"smp_ipi0", NULL))
+	if (request_irq(IPI0_IRQ, bmips_ipi_interrupt,
+			IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi0", NULL))
 		panic("Can't request IPI0 interrupt");
-	if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
-			"smp_ipi1", NULL))
+	if (request_irq(IPI1_IRQ, bmips_ipi_interrupt,
+			IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi1", NULL))
 		panic("Can't request IPI1 interrupt");
 }
 
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index bc2fdbfa8223..72af0c183969 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -7,6 +7,8 @@ choice
 config LEMOTE_FULOONG2E
 	bool "Lemote Fuloong(2e) mini-PC"
 	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
 	select CEVT_R4K
 	select CSRC_R4K
 	select SYS_HAS_CPU_LOONGSON2E
@@ -33,6 +35,8 @@ config LEMOTE_FULOONG2E
 config LEMOTE_MACH2F
 	bool "Lemote Loongson 2F family machines"
 	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
 	select BOARD_SCACHE
 	select BOOT_ELF32
 	select CEVT_R4K if ! MIPS_EXTERNAL_TIMER
@@ -62,6 +66,8 @@ config LEMOTE_MACH2F
 config LOONGSON_MACH3X
 	bool "Generic Loongson 3 family machines"
 	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select BOOT_ELF32
 	select BOARD_SCACHE
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 3742508cc534..bd5ce31936f5 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -26,6 +26,7 @@ void flush_user_icache_range_asm(unsigned long, unsigned long);
 void flush_kernel_icache_range_asm(unsigned long, unsigned long);
 void flush_user_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_range_asm(unsigned long, unsigned long);
+void purge_kernel_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_page_asm(void *);
 void flush_kernel_icache_page(void *);
 
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 0e6ab6e4a4e9..2dbe5580a1a4 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -316,6 +316,8 @@ extern int _parisc_requires_coherency;
 #define parisc_requires_coherency()	(0)
 #endif
 
+extern int running_on_qemu;
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_PARISC_PROCESSOR_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 19c0c141bc3f..e3b45546d589 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -465,10 +465,10 @@ EXPORT_SYMBOL(copy_user_page);
 int __flush_tlb_range(unsigned long sid, unsigned long start,
 		      unsigned long end)
 {
-	unsigned long flags, size;
+	unsigned long flags;
 
-	size = (end - start);
-	if (size >= parisc_tlb_flush_threshold) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    end - start >= parisc_tlb_flush_threshold) {
 		flush_tlb_all();
 		return 1;
 	}
@@ -539,13 +539,12 @@ void flush_cache_mm(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	pgd_t *pgd;
 
-	/* Flush the TLB to avoid speculation if coherency is required. */
-	if (parisc_requires_coherency())
-		flush_tlb_all();
-
 	/* Flushing the whole cache on each cpu takes forever on
 	   rp3440, etc.  So, avoid it if the mm isn't too big.  */
-	if (mm_total_size(mm) >= parisc_cache_flush_threshold) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    mm_total_size(mm) >= parisc_cache_flush_threshold) {
+		if (mm->context)
+			flush_tlb_all();
 		flush_cache_all();
 		return;
 	}
@@ -553,9 +552,9 @@ void flush_cache_mm(struct mm_struct *mm)
 	if (mm->context == mfsp(3)) {
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			flush_user_dcache_range_asm(vma->vm_start, vma->vm_end);
-			if ((vma->vm_flags & VM_EXEC) == 0)
-				continue;
-			flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+			if (vma->vm_flags & VM_EXEC)
+				flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+			flush_tlb_range(vma, vma->vm_start, vma->vm_end);
 		}
 		return;
 	}
@@ -573,6 +572,8 @@ void flush_cache_mm(struct mm_struct *mm)
 			pfn = pte_pfn(*ptep);
 			if (!pfn_valid(pfn))
 				continue;
+			if (unlikely(mm->context))
+				flush_tlb_page(vma, addr);
 			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
 		}
 	}
@@ -581,30 +582,45 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
-	BUG_ON(!vma->vm_mm->context);
-
-	/* Flush the TLB to avoid speculation if coherency is required. */
-	if (parisc_requires_coherency())
-		flush_tlb_range(vma, start, end);
+	pgd_t *pgd;
+	unsigned long addr;
 
-	if ((end - start) >= parisc_cache_flush_threshold
-	    || vma->vm_mm->context != mfsp(3)) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    end - start >= parisc_cache_flush_threshold) {
+		if (vma->vm_mm->context)
+			flush_tlb_range(vma, start, end);
 		flush_cache_all();
 		return;
 	}
 
-	flush_user_dcache_range_asm(start, end);
-	if (vma->vm_flags & VM_EXEC)
-		flush_user_icache_range_asm(start, end);
+	if (vma->vm_mm->context == mfsp(3)) {
+		flush_user_dcache_range_asm(start, end);
+		if (vma->vm_flags & VM_EXEC)
+			flush_user_icache_range_asm(start, end);
+		flush_tlb_range(vma, start, end);
+		return;
+	}
+
+	pgd = vma->vm_mm->pgd;
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
+		unsigned long pfn;
+		pte_t *ptep = get_ptep(pgd, addr);
+		if (!ptep)
+			continue;
+		pfn = pte_pfn(*ptep);
+		if (pfn_valid(pfn)) {
+			if (unlikely(vma->vm_mm->context))
+				flush_tlb_page(vma, addr);
+			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+		}
+	}
 }
 
 void
 flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
 {
-	BUG_ON(!vma->vm_mm->context);
-
 	if (pfn_valid(pfn)) {
-		if (parisc_requires_coherency())
+		if (likely(vma->vm_mm->context))
 			flush_tlb_page(vma, vmaddr);
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
@@ -613,21 +629,33 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 void flush_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
+	unsigned long end = start + size;
 
-	if ((unsigned long)size > parisc_cache_flush_threshold)
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    (unsigned long)size >= parisc_cache_flush_threshold) {
+		flush_tlb_kernel_range(start, end);
 		flush_data_cache();
-	else
-		flush_kernel_dcache_range_asm(start, start + size);
+		return;
+	}
+
+	flush_kernel_dcache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(flush_kernel_vmap_range);
 
 void invalidate_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
+	unsigned long end = start + size;
 
-	if ((unsigned long)size > parisc_cache_flush_threshold)
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    (unsigned long)size >= parisc_cache_flush_threshold) {
+		flush_tlb_kernel_range(start, end);
 		flush_data_cache();
-	else
-		flush_kernel_dcache_range_asm(start, start + size);
+		return;
+	}
+
+	purge_kernel_dcache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index bbbe360b458f..fbb4e43fda05 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -138,6 +138,16 @@ $pgt_fill_loop:
 	std		%dp,0x18(%r10)
 #endif
 
+#ifdef CONFIG_64BIT
+	/* Get PDCE_PROC for monarch CPU. */
+#define MEM_PDC_LO 0x388
+#define MEM_PDC_HI 0x35C
+	ldw             MEM_PDC_LO(%r0),%r3
+	ldw             MEM_PDC_HI(%r0),%r10
+	depd            %r10, 31, 32, %r3        /* move to upper word */
+#endif
+
+
 #ifdef CONFIG_SMP
 	/* Set the smp rendezvous address into page zero.
 	** It would be safer to do this in init_smp_config() but
@@ -196,12 +206,6 @@ common_stext:
         ** Someday, palo might not do this for the Monarch either.
         */
 2:
-#define MEM_PDC_LO 0x388
-#define MEM_PDC_HI 0x35C
-	ldw             MEM_PDC_LO(%r0),%r3
-	ldw             MEM_PDC_HI(%r0),%r6
-	depd            %r6, 31, 32, %r3        /* move to upper word */
-
 	mfctl		%cr30,%r6		/* PCX-W2 firmware bug */
 
 	ldo             PDC_PSW(%r0),%arg0              /* 21 */
@@ -268,6 +272,8 @@ $install_iva:
 aligned_rfi:
 	pcxt_ssm_bug
 
+	copy		%r3, %arg0	/* PDCE_PROC for smp_callin() */
+
 	rsm		PSW_SM_QUIET,%r0	/* off troublesome PSW bits */
 	/* Don't need NOPs, have 8 compliant insn before rfi */
 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 2d40c4ff3f69..67b0f7532e83 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -1110,6 +1110,28 @@ ENTRY_CFI(flush_kernel_dcache_range_asm)
 	.procend
 ENDPROC_CFI(flush_kernel_dcache_range_asm)
 
+ENTRY_CFI(purge_kernel_dcache_range_asm)
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil		L%dcache_stride, %r1
+	ldw		R%dcache_stride(%r1), %r23
+	ldo		-1(%r23), %r21
+	ANDCM		%r26, %r21, %r26
+
+1:      cmpb,COND(<<),n	%r26, %r25,1b
+	pdc,m		%r23(%r26)
+
+	sync
+	syncdma
+	bv		%r0(%r2)
+	nop
+	.exit
+
+	.procend
+ENDPROC_CFI(purge_kernel_dcache_range_asm)
+
 ENTRY_CFI(flush_user_icache_range_asm)
 	.proc
 	.callinfo NO_CALLS
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 30c28ab14540..4065b5e48c9d 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -292,10 +292,15 @@ smp_cpu_init(int cpunum)
  * Slaves start using C here. Indirectly called from smp_slave_stext.
  * Do what start_kernel() and main() do for boot strap processor (aka monarch)
  */
-void __init smp_callin(void)
+void __init smp_callin(unsigned long pdce_proc)
 {
 	int slave_id = cpu_now_booting;
 
+#ifdef CONFIG_64BIT
+	WARN_ON(((unsigned long)(PAGE0->mem_pdc_hi) << 32
+			| PAGE0->mem_pdc) != pdce_proc);
+#endif
+
 	smp_cpu_init(slave_id);
 	preempt_disable();
 
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 4b8fd6dc22da..f7e684560186 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -76,10 +76,10 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 	next_tick = cpuinfo->it_value;
 
 	/* Calculate how many ticks have elapsed. */
+	now = mfctl(16);
 	do {
 		++ticks_elapsed;
 		next_tick += cpt;
-		now = mfctl(16);
 	} while (next_tick - now > cpt);
 
 	/* Store (in CR16 cycles) up to when we are accounting right now. */
@@ -103,16 +103,17 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 	 * if one or the other wrapped. If "now" is "bigger" we'll end up
 	 * with a very large unsigned number.
 	 */
-	while (next_tick - mfctl(16) > cpt)
+	now = mfctl(16);
+	while (next_tick - now > cpt)
 		next_tick += cpt;
 
 	/* Program the IT when to deliver the next interrupt.
 	 * Only bottom 32-bits of next_tick are writable in CR16!
 	 * Timer interrupt will be delivered at least a few hundred cycles
-	 * after the IT fires, so if we are too close (<= 500 cycles) to the
+	 * after the IT fires, so if we are too close (<= 8000 cycles) to the
 	 * next cycle, simply skip it.
 	 */
-	if (next_tick - mfctl(16) <= 500)
+	if (next_tick - now <= 8000)
 		next_tick += cpt;
 	mtctl(next_tick, 16);
 
@@ -248,7 +249,7 @@ static int __init init_cr16_clocksource(void)
 	 * different sockets, so mark them unstable and lower rating on
 	 * multi-socket SMP systems.
 	 */
-	if (num_online_cpus() > 1) {
+	if (num_online_cpus() > 1 && !running_on_qemu) {
 		int cpu;
 		unsigned long cpu0_loc;
 		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 48f41399fc0b..cab32ee824d2 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -629,7 +629,12 @@ void __init mem_init(void)
 #endif
 
 	mem_init_print_info(NULL);
-#ifdef CONFIG_DEBUG_KERNEL /* double-sanity-check paranoia */
+
+#if 0
+	/*
+	 * Do not expose the virtual kernel memory layout to userspace.
+	 * But keep code for debugging purposes.
+	 */
 	printk("virtual kernel memory layout:\n"
 	       "    vmalloc : 0x%px - 0x%px   (%4ld MB)\n"
 	       "    memory  : 0x%px - 0x%px   (%4ld MB)\n"
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index ef6549e57157..26d5d2a5b8e9 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -101,7 +101,8 @@ $(addprefix $(obj)/,$(zlib-y)): \
 libfdt       := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c
 libfdtheader := fdt.h libfdt.h libfdt_internal.h
 
-$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \
+$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o \
+	treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \
 	$(addprefix $(obj)/,$(libfdtheader))
 
 src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index d22c41c26bb3..acf4b2e0530c 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -874,7 +874,6 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
 		.mmu = 0,
 		.hash_ext = 0,
 		.radix_ext = 0,
-		.byte22 = 0,
 	},
 
 	/* option vector 6: IBM PAPR hints */
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 0c854816e653..5cb4e4687107 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -195,6 +195,12 @@ static void kvmppc_pte_free(pte_t *ptep)
 	kmem_cache_free(kvm_pte_cache, ptep);
 }
 
+/* Like pmd_huge() and pmd_large(), but works regardless of config options */
+static inline int pmd_is_leaf(pmd_t pmd)
+{
+	return !!(pmd_val(pmd) & _PAGE_PTE);
+}
+
 static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 			     unsigned int level, unsigned long mmu_seq)
 {
@@ -219,7 +225,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 	else
 		new_pmd = pmd_alloc_one(kvm->mm, gpa);
 
-	if (level == 0 && !(pmd && pmd_present(*pmd)))
+	if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd)))
 		new_ptep = kvmppc_pte_alloc();
 
 	/* Check if we might have been invalidated; let the guest retry if so */
@@ -244,12 +250,30 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 		new_pmd = NULL;
 	}
 	pmd = pmd_offset(pud, gpa);
-	if (pmd_large(*pmd)) {
-		/* Someone else has instantiated a large page here; retry */
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
-	if (level == 1 && !pmd_none(*pmd)) {
+	if (pmd_is_leaf(*pmd)) {
+		unsigned long lgpa = gpa & PMD_MASK;
+
+		/*
+		 * If we raced with another CPU which has just put
+		 * a 2MB pte in after we saw a pte page, try again.
+		 */
+		if (level == 0 && !new_ptep) {
+			ret = -EAGAIN;
+			goto out_unlock;
+		}
+		/* Valid 2MB page here already, remove it */
+		old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
+					      ~0UL, 0, lgpa, PMD_SHIFT);
+		kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT);
+		if (old & _PAGE_DIRTY) {
+			unsigned long gfn = lgpa >> PAGE_SHIFT;
+			struct kvm_memory_slot *memslot;
+			memslot = gfn_to_memslot(kvm, gfn);
+			if (memslot && memslot->dirty_bitmap)
+				kvmppc_update_dirty_map(memslot,
+							gfn, PMD_SIZE);
+		}
+	} else if (level == 1 && !pmd_none(*pmd)) {
 		/*
 		 * There's a page table page here, but we wanted
 		 * to install a large page.  Tell the caller and let
@@ -412,28 +436,24 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	} else {
 		page = pages[0];
 		pfn = page_to_pfn(page);
-		if (PageHuge(page)) {
-			page = compound_head(page);
-			pte_size <<= compound_order(page);
+		if (PageCompound(page)) {
+			pte_size <<= compound_order(compound_head(page));
 			/* See if we can insert a 2MB large-page PTE here */
 			if (pte_size >= PMD_SIZE &&
-			    (gpa & PMD_MASK & PAGE_MASK) ==
-			    (hva & PMD_MASK & PAGE_MASK)) {
+			    (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+			    (hva & (PMD_SIZE - PAGE_SIZE))) {
 				level = 1;
 				pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
 			}
 		}
 		/* See if we can provide write access */
 		if (writing) {
-			/*
-			 * We assume gup_fast has set dirty on the host PTE.
-			 */
 			pgflags |= _PAGE_WRITE;
 		} else {
 			local_irq_save(flags);
 			ptep = find_current_mm_pte(current->mm->pgd,
 						   hva, NULL, NULL);
-			if (ptep && pte_write(*ptep) && pte_dirty(*ptep))
+			if (ptep && pte_write(*ptep))
 				pgflags |= _PAGE_WRITE;
 			local_irq_restore(flags);
 		}
@@ -459,18 +479,15 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte = pfn_pte(pfn, __pgprot(pgflags));
 		ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
 	}
-	if (ret == 0 || ret == -EAGAIN)
-		ret = RESUME_GUEST;
 
 	if (page) {
-		/*
-		 * We drop pages[0] here, not page because page might
-		 * have been set to the head page of a compound, but
-		 * we have to drop the reference on the correct tail
-		 * page to match the get inside gup()
-		 */
-		put_page(pages[0]);
+		if (!ret && (pgflags & _PAGE_WRITE))
+			set_page_dirty_lock(page);
+		put_page(page);
 	}
+
+	if (ret == 0 || ret == -EAGAIN)
+		ret = RESUME_GUEST;
 	return ret;
 }
 
@@ -644,7 +661,7 @@ void kvmppc_free_radix(struct kvm *kvm)
 				continue;
 			pmd = pmd_offset(pud, 0);
 			for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) {
-				if (pmd_huge(*pmd)) {
+				if (pmd_is_leaf(*pmd)) {
 					pmd_clear(pmd);
 					continue;
 				}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 89707354c2ef..9cb9448163c4 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2885,7 +2885,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	trace_hardirqs_on();
 
-	guest_enter();
+	guest_enter_irqoff();
 
 	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
 
@@ -2893,8 +2893,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 
 	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
 
-	guest_exit();
-
 	trace_hardirqs_off();
 	set_irq_happened(trap);
 
@@ -2937,6 +2935,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	kvmppc_set_host_core(pcpu);
 
 	local_irq_enable();
+	guest_exit();
 
 	/* Let secondaries go back to the offline loop */
 	for (i = 0; i < controlled_threads; ++i) {
@@ -3656,15 +3655,17 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		goto up_out;
 
 	psize = vma_kernel_pagesize(vma);
-	porder = __ilog2(psize);
 
 	up_read(&current->mm->mmap_sem);
 
 	/* We can handle 4k, 64k or 16M pages in the VRMA */
-	err = -EINVAL;
-	if (!(psize == 0x1000 || psize == 0x10000 ||
-	      psize == 0x1000000))
-		goto out_srcu;
+	if (psize >= 0x1000000)
+		psize = 0x1000000;
+	else if (psize >= 0x10000)
+		psize = 0x10000;
+	else
+		psize = 0x1000;
+	porder = __ilog2(psize);
 
 	senc = slb_pgsize_encoding(psize);
 	kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index f31f357b8c5a..d33264697a31 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -320,7 +320,6 @@ kvm_novcpu_exit:
 	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_commence_exit
 	nop
-	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	kvmhv_switch_to_host
 
 /*
@@ -1220,6 +1219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 secondary_too_late:
 	li	r12, 0
+	stw	r12, STACK_SLOT_TRAP(r1)
 	cmpdi	r4, 0
 	beq	11f
 	stw	r12, VCPU_TRAP(r4)
@@ -1558,12 +1558,12 @@ mc_cont:
 3:	stw	r5,VCPU_SLB_MAX(r9)
 
 guest_bypass:
+	stw	r12, STACK_SLOT_TRAP(r1)
 	mr 	r3, r12
 	/* Increment exit count, poke other threads to exit */
 	bl	kvmhv_commence_exit
 	nop
 	ld	r9, HSTATE_KVM_VCPU(r13)
-	lwz	r12, VCPU_TRAP(r9)
 
 	/* Stop others sending VCPU interrupts to this physical CPU */
 	li	r0, -1
@@ -1898,6 +1898,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
 	 * have to coordinate the hardware threads.
+	 * Here STACK_SLOT_TRAP(r1) contains the trap number.
 	 */
 kvmhv_switch_to_host:
 	/* Secondary threads wait for primary to do partition switch */
@@ -1950,12 +1951,12 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* If HMI, call kvmppc_realmode_hmi_handler() */
+	lwz	r12, STACK_SLOT_TRAP(r1)
 	cmpwi	r12, BOOK3S_INTERRUPT_HMI
 	bne	27f
 	bl	kvmppc_realmode_hmi_handler
 	nop
 	cmpdi	r3, 0
-	li	r12, BOOK3S_INTERRUPT_HMI
 	/*
 	 * At this point kvmppc_realmode_hmi_handler may have resync-ed
 	 * the TB, and if it has, we must not subtract the guest timebase
@@ -2008,10 +2009,8 @@ BEGIN_FTR_SECTION
 	lwz	r8, KVM_SPLIT_DO_RESTORE(r3)
 	cmpwi	r8, 0
 	beq	47f
-	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_p9_restore_lpcr
 	nop
-	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	48f
 47:
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
@@ -2049,6 +2048,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
 
+	lwz	r12, STACK_SLOT_TRAP(r1)	/* return trap # in r12 */
 	ld	r0, SFS+PPC_LR_STKOFF(r1)
 	addi	r1, r1, SFS
 	mtlr	r0
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 403e642c78f5..52c205373986 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1345,7 +1345,7 @@ static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu,
 int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		unsigned int rt, int is_default_endian)
 {
-	enum emulation_result emulated;
+	enum emulation_result emulated = EMULATE_DONE;
 
 	while (vcpu->arch.mmio_vmx_copy_nums) {
 		emulated = __kvmppc_handle_load(run, vcpu, rt, 8,
@@ -1608,7 +1608,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	kvm_sigset_deactivate(vcpu);
 
+#ifdef CONFIG_ALTIVEC
 out:
+#endif
 	vcpu_put(vcpu);
 	return r;
 }
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 0a34b0cec7b7..0ef3d9580e98 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -240,6 +240,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	 *   goto out;
 	 */
 	PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries));
+	PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31);
 	PPC_CMPLW(b2p_index, b2p[TMP_REG_1]);
 	PPC_BCC(COND_GE, out);
 
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index c0319cbf1eec..5510366d169a 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -34,9 +34,9 @@
 #define wmb()		RISCV_FENCE(ow,ow)
 
 /* These barriers do not need to enforce ordering on devices, just memory. */
-#define smp_mb()	RISCV_FENCE(rw,rw)
-#define smp_rmb()	RISCV_FENCE(r,r)
-#define smp_wmb()	RISCV_FENCE(w,w)
+#define __smp_mb()	RISCV_FENCE(rw,rw)
+#define __smp_rmb()	RISCV_FENCE(r,r)
+#define __smp_wmb()	RISCV_FENCE(w,w)
 
 /*
  * This is a very specific barrier: it's currently only used in two places in
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 65154eaa3714..6c8ce15cde7b 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -63,6 +63,7 @@ static inline int init_new_context(struct task_struct *tsk,
 				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
 		/* pgd_alloc() did not account this pmd */
 		mm_inc_nr_pmds(mm);
+		mm_inc_nr_puds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 13a133a6015c..a5621ea6d123 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -14,6 +14,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/ctl_reg.h>
+#include <asm/dwarf.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -230,7 +231,7 @@ _PIF_WORK	= (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
 	.hidden \name
 	.type \name,@function
 \name:
-	.cfi_startproc
+	CFI_STARTPROC
 #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
 	exrl	0,0f
 #else
@@ -239,7 +240,7 @@ _PIF_WORK	= (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
 #endif
 	j	.
 0:	br	\reg
-	.cfi_endproc
+	CFI_ENDPROC
 	.endm
 
 	GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1
@@ -426,13 +427,13 @@ ENTRY(system_call)
 	UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
 	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
 	stmg	%r0,%r7,__PT_R0(%r11)
-	# clear user controlled register to prevent speculative use
-	xgr	%r0,%r0
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	mvc	__PT_PSW(16,%r11),__LC_SVC_OLD_PSW
 	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC
 	stg	%r14,__PT_FLAGS(%r11)
 .Lsysc_do_svc:
+	# clear user controlled register to prevent speculative use
+	xgr	%r0,%r0
 	# load address of system call table
 	lg	%r10,__THREAD_sysc_table(%r13,%r12)
 	llgh	%r8,__PT_INT_CODE+2(%r11)
@@ -1439,6 +1440,7 @@ cleanup_critical:
 	stg	%r15,__LC_SYSTEM_TIMER
 0:	# update accounting time stamp
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
+	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
 	# set up saved register r11
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r9,STACK_FRAME_OVERHEAD(%r15)
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index 69d7fcf48158..9aff72d3abda 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -2,8 +2,8 @@
 #include <linux/module.h>
 #include <asm/nospec-branch.h>
 
-int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF);
-int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL);
+int nospec_call_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);
+int nospec_return_disable = !IS_ENABLED(CONFIG_EXPOLINE_FULL);
 
 static int __init nospectre_v2_setup_early(char *str)
 {
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 9c7d70715862..07c6e81163bf 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -22,22 +22,6 @@
 #include "trace.h"
 #include "trace-s390.h"
 
-
-static const intercept_handler_t instruction_handlers[256] = {
-	[0x01] = kvm_s390_handle_01,
-	[0x82] = kvm_s390_handle_lpsw,
-	[0x83] = kvm_s390_handle_diag,
-	[0xaa] = kvm_s390_handle_aa,
-	[0xae] = kvm_s390_handle_sigp,
-	[0xb2] = kvm_s390_handle_b2,
-	[0xb6] = kvm_s390_handle_stctl,
-	[0xb7] = kvm_s390_handle_lctl,
-	[0xb9] = kvm_s390_handle_b9,
-	[0xe3] = kvm_s390_handle_e3,
-	[0xe5] = kvm_s390_handle_e5,
-	[0xeb] = kvm_s390_handle_eb,
-};
-
 u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
@@ -129,16 +113,39 @@ static int handle_validity(struct kvm_vcpu *vcpu)
 
 static int handle_instruction(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
 	vcpu->stat.exit_instruction++;
 	trace_kvm_s390_intercept_instruction(vcpu,
 					     vcpu->arch.sie_block->ipa,
 					     vcpu->arch.sie_block->ipb);
-	handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8];
-	if (handler)
-		return handler(vcpu);
-	return -EOPNOTSUPP;
+
+	switch (vcpu->arch.sie_block->ipa >> 8) {
+	case 0x01:
+		return kvm_s390_handle_01(vcpu);
+	case 0x82:
+		return kvm_s390_handle_lpsw(vcpu);
+	case 0x83:
+		return kvm_s390_handle_diag(vcpu);
+	case 0xaa:
+		return kvm_s390_handle_aa(vcpu);
+	case 0xae:
+		return kvm_s390_handle_sigp(vcpu);
+	case 0xb2:
+		return kvm_s390_handle_b2(vcpu);
+	case 0xb6:
+		return kvm_s390_handle_stctl(vcpu);
+	case 0xb7:
+		return kvm_s390_handle_lctl(vcpu);
+	case 0xb9:
+		return kvm_s390_handle_b9(vcpu);
+	case 0xe3:
+		return kvm_s390_handle_e3(vcpu);
+	case 0xe5:
+		return kvm_s390_handle_e5(vcpu);
+	case 0xeb:
+		return kvm_s390_handle_eb(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index aabf46f5f883..b04616b57a94 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -169,8 +169,15 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
 
 static int ckc_irq_pending(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm))
+	const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+	const u64 ckc = vcpu->arch.sie_block->ckc;
+
+	if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) {
+		if ((s64)ckc >= (s64)now)
+			return 0;
+	} else if (ckc >= now) {
 		return 0;
+	}
 	return ckc_interrupts_enabled(vcpu);
 }
 
@@ -187,12 +194,6 @@ static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
 	return kvm_s390_get_cpu_timer(vcpu) >> 63;
 }
 
-static inline int is_ioirq(unsigned long irq_type)
-{
-	return ((irq_type >= IRQ_PEND_IO_ISC_7) &&
-		(irq_type <= IRQ_PEND_IO_ISC_0));
-}
-
 static uint64_t isc_to_isc_bits(int isc)
 {
 	return (0x80 >> isc) << 24;
@@ -236,10 +237,15 @@ static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gis
 	return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
 }
 
-static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
+static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.float_int.pending_irqs |
-		vcpu->arch.local_int.pending_irqs |
+		vcpu->arch.local_int.pending_irqs;
+}
+
+static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
+{
+	return pending_irqs_no_gisa(vcpu) |
 		kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7;
 }
 
@@ -337,7 +343,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 
 static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
 {
-	if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK))
+	if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_IO_MASK))
 		return;
 	else if (psw_ioint_disabled(vcpu))
 		kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT);
@@ -1011,24 +1017,6 @@ out:
 	return rc;
 }
 
-typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu);
-
-static const deliver_irq_t deliver_irq_funcs[] = {
-	[IRQ_PEND_MCHK_EX]        = __deliver_machine_check,
-	[IRQ_PEND_MCHK_REP]       = __deliver_machine_check,
-	[IRQ_PEND_PROG]           = __deliver_prog,
-	[IRQ_PEND_EXT_EMERGENCY]  = __deliver_emergency_signal,
-	[IRQ_PEND_EXT_EXTERNAL]   = __deliver_external_call,
-	[IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc,
-	[IRQ_PEND_EXT_CPU_TIMER]  = __deliver_cpu_timer,
-	[IRQ_PEND_RESTART]        = __deliver_restart,
-	[IRQ_PEND_SET_PREFIX]     = __deliver_set_prefix,
-	[IRQ_PEND_PFAULT_INIT]    = __deliver_pfault_init,
-	[IRQ_PEND_EXT_SERVICE]    = __deliver_service,
-	[IRQ_PEND_PFAULT_DONE]    = __deliver_pfault_done,
-	[IRQ_PEND_VIRTIO]         = __deliver_virtio,
-};
-
 /* Check whether an external call is pending (deliverable or not) */
 int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
 {
@@ -1066,13 +1054,19 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 
 static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
 {
-	u64 now, cputm, sltime = 0;
+	const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+	const u64 ckc = vcpu->arch.sie_block->ckc;
+	u64 cputm, sltime = 0;
 
 	if (ckc_interrupts_enabled(vcpu)) {
-		now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
-		sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-		/* already expired or overflow? */
-		if (!sltime || vcpu->arch.sie_block->ckc <= now)
+		if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) {
+			if ((s64)now < (s64)ckc)
+				sltime = tod_to_ns((s64)ckc - (s64)now);
+		} else if (now < ckc) {
+			sltime = tod_to_ns(ckc - now);
+		}
+		/* already expired */
+		if (!sltime)
 			return 0;
 		if (cpu_timer_interrupts_enabled(vcpu)) {
 			cputm = kvm_s390_get_cpu_timer(vcpu);
@@ -1192,7 +1186,6 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
 int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	deliver_irq_t func;
 	int rc = 0;
 	unsigned long irq_type;
 	unsigned long irqs;
@@ -1212,16 +1205,57 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 	while ((irqs = deliverable_irqs(vcpu)) && !rc) {
 		/* bits are in the reverse order of interrupt priority */
 		irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT);
-		if (is_ioirq(irq_type)) {
+		switch (irq_type) {
+		case IRQ_PEND_IO_ISC_0:
+		case IRQ_PEND_IO_ISC_1:
+		case IRQ_PEND_IO_ISC_2:
+		case IRQ_PEND_IO_ISC_3:
+		case IRQ_PEND_IO_ISC_4:
+		case IRQ_PEND_IO_ISC_5:
+		case IRQ_PEND_IO_ISC_6:
+		case IRQ_PEND_IO_ISC_7:
 			rc = __deliver_io(vcpu, irq_type);
-		} else {
-			func = deliver_irq_funcs[irq_type];
-			if (!func) {
-				WARN_ON_ONCE(func == NULL);
-				clear_bit(irq_type, &li->pending_irqs);
-				continue;
-			}
-			rc = func(vcpu);
+			break;
+		case IRQ_PEND_MCHK_EX:
+		case IRQ_PEND_MCHK_REP:
+			rc = __deliver_machine_check(vcpu);
+			break;
+		case IRQ_PEND_PROG:
+			rc = __deliver_prog(vcpu);
+			break;
+		case IRQ_PEND_EXT_EMERGENCY:
+			rc = __deliver_emergency_signal(vcpu);
+			break;
+		case IRQ_PEND_EXT_EXTERNAL:
+			rc = __deliver_external_call(vcpu);
+			break;
+		case IRQ_PEND_EXT_CLOCK_COMP:
+			rc = __deliver_ckc(vcpu);
+			break;
+		case IRQ_PEND_EXT_CPU_TIMER:
+			rc = __deliver_cpu_timer(vcpu);
+			break;
+		case IRQ_PEND_RESTART:
+			rc = __deliver_restart(vcpu);
+			break;
+		case IRQ_PEND_SET_PREFIX:
+			rc = __deliver_set_prefix(vcpu);
+			break;
+		case IRQ_PEND_PFAULT_INIT:
+			rc = __deliver_pfault_init(vcpu);
+			break;
+		case IRQ_PEND_EXT_SERVICE:
+			rc = __deliver_service(vcpu);
+			break;
+		case IRQ_PEND_PFAULT_DONE:
+			rc = __deliver_pfault_done(vcpu);
+			break;
+		case IRQ_PEND_VIRTIO:
+			rc = __deliver_virtio(vcpu);
+			break;
+		default:
+			WARN_ONCE(1, "Unknown pending irq type %ld", irq_type);
+			clear_bit(irq_type, &li->pending_irqs);
 		}
 	}
 
@@ -1701,7 +1735,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type)
 		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT);
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
+		if (!(type & KVM_S390_INT_IO_AI_MASK && kvm->arch.gisa))
+			kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
 		break;
 	default:
 		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ba4c7092335a..339ac0964590 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -86,6 +86,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
 	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
 	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
+	{ "deliver_io_interrupt", VCPU_STAT(deliver_io_int) },
 	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
 	{ "instruction_epsw", VCPU_STAT(instruction_epsw) },
 	{ "instruction_gs", VCPU_STAT(instruction_gs) },
@@ -179,6 +180,28 @@ int kvm_arch_hardware_enable(void)
 static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
 			      unsigned long end);
 
+static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta)
+{
+	u8 delta_idx = 0;
+
+	/*
+	 * The TOD jumps by delta, we have to compensate this by adding
+	 * -delta to the epoch.
+	 */
+	delta = -delta;
+
+	/* sign-extension - we're adding to signed values below */
+	if ((s64)delta < 0)
+		delta_idx = -1;
+
+	scb->epoch += delta;
+	if (scb->ecd & ECD_MEF) {
+		scb->epdx += delta_idx;
+		if (scb->epoch < delta)
+			scb->epdx += 1;
+	}
+}
+
 /*
  * This callback is executed during stop_machine(). All CPUs are therefore
  * temporarily stopped. In order not to change guest behavior, we have to
@@ -194,13 +217,17 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
 	unsigned long long *delta = v;
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		kvm->arch.epoch -= *delta;
 		kvm_for_each_vcpu(i, vcpu, kvm) {
-			vcpu->arch.sie_block->epoch -= *delta;
+			kvm_clock_sync_scb(vcpu->arch.sie_block, *delta);
+			if (i == 0) {
+				kvm->arch.epoch = vcpu->arch.sie_block->epoch;
+				kvm->arch.epdx = vcpu->arch.sie_block->epdx;
+			}
 			if (vcpu->arch.cputm_enabled)
 				vcpu->arch.cputm_start += *delta;
 			if (vcpu->arch.vsie_block)
-				vcpu->arch.vsie_block->epoch -= *delta;
+				kvm_clock_sync_scb(vcpu->arch.vsie_block,
+						   *delta);
 		}
 	}
 	return NOTIFY_OK;
@@ -902,12 +929,9 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
 	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
 		return -EFAULT;
 
-	if (test_kvm_facility(kvm, 139))
-		kvm_s390_set_tod_clock_ext(kvm, &gtod);
-	else if (gtod.epoch_idx == 0)
-		kvm_s390_set_tod_clock(kvm, gtod.tod);
-	else
+	if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx)
 		return -EINVAL;
+	kvm_s390_set_tod_clock(kvm, &gtod);
 
 	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
 		gtod.epoch_idx, gtod.tod);
@@ -932,13 +956,14 @@ static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 
 static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 {
-	u64 gtod;
+	struct kvm_s390_vm_tod_clock gtod = { 0 };
 
-	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
+	if (copy_from_user(&gtod.tod, (void __user *)attr->addr,
+			   sizeof(gtod.tod)))
 		return -EFAULT;
 
-	kvm_s390_set_tod_clock(kvm, gtod);
-	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod);
+	kvm_s390_set_tod_clock(kvm, &gtod);
+	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod);
 	return 0;
 }
 
@@ -2122,6 +2147,7 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu)
 		/* we still need the basic sca for the ipte control */
 		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+		return;
 	}
 	read_lock(&vcpu->kvm->arch.sca_lock);
 	if (vcpu->kvm->arch.use_esca) {
@@ -2389,6 +2415,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	mutex_lock(&vcpu->kvm->lock);
 	preempt_disable();
 	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
+	vcpu->arch.sie_block->epdx = vcpu->kvm->arch.epdx;
 	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
 	if (!kvm_is_ucontrol(vcpu->kvm)) {
@@ -3021,8 +3048,8 @@ retry:
 	return 0;
 }
 
-void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
-				 const struct kvm_s390_vm_tod_clock *gtod)
+void kvm_s390_set_tod_clock(struct kvm *kvm,
+			    const struct kvm_s390_vm_tod_clock *gtod)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_s390_tod_clock_ext htod;
@@ -3034,10 +3061,12 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
 	get_tod_clock_ext((char *)&htod);
 
 	kvm->arch.epoch = gtod->tod - htod.tod;
-	kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;
-
-	if (kvm->arch.epoch > gtod->tod)
-		kvm->arch.epdx -= 1;
+	kvm->arch.epdx = 0;
+	if (test_kvm_facility(kvm, 139)) {
+		kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;
+		if (kvm->arch.epoch > gtod->tod)
+			kvm->arch.epdx -= 1;
+	}
 
 	kvm_s390_vcpu_block_all(kvm);
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -3050,22 +3079,6 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
 	mutex_unlock(&kvm->lock);
 }
 
-void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod)
-{
-	struct kvm_vcpu *vcpu;
-	int i;
-
-	mutex_lock(&kvm->lock);
-	preempt_disable();
-	kvm->arch.epoch = tod - get_tod_clock();
-	kvm_s390_vcpu_block_all(kvm);
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		vcpu->arch.sie_block->epoch = kvm->arch.epoch;
-	kvm_s390_vcpu_unblock_all(kvm);
-	preempt_enable();
-	mutex_unlock(&kvm->lock);
-}
-
 /**
  * kvm_arch_fault_in_page - fault-in guest page if necessary
  * @vcpu: The corresponding virtual cpu
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index bd31b37b0e6f..f55ac0ef99ea 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -19,8 +19,6 @@
 #include <asm/processor.h>
 #include <asm/sclp.h>
 
-typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
-
 /* Transactional Memory Execution related macros */
 #define IS_TE_ENABLED(vcpu)	((vcpu->arch.sie_block->ecb & ECB_TE))
 #define TDB_FORMAT1		1
@@ -283,9 +281,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 
 /* implemented in kvm-s390.c */
-void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
-				 const struct kvm_s390_vm_tod_clock *gtod);
-void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod);
+void kvm_s390_set_tod_clock(struct kvm *kvm,
+			    const struct kvm_s390_vm_tod_clock *gtod);
 long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index c4c4e157c036..f0b4185158af 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -85,9 +85,10 @@ int kvm_s390_handle_e3(struct kvm_vcpu *vcpu)
 /* Handle SCK (SET CLOCK) interception */
 static int handle_set_clock(struct kvm_vcpu *vcpu)
 {
+	struct kvm_s390_vm_tod_clock gtod = { 0 };
 	int rc;
 	u8 ar;
-	u64 op2, val;
+	u64 op2;
 
 	vcpu->stat.instruction_sck++;
 
@@ -97,12 +98,12 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
 	op2 = kvm_s390_get_base_disp_s(vcpu, &ar);
 	if (op2 & 7)	/* Operand must be on a doubleword boundary */
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	rc = read_guest(vcpu, op2, ar, &val, sizeof(val));
+	rc = read_guest(vcpu, op2, ar, &gtod.tod, sizeof(gtod.tod));
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val);
-	kvm_s390_set_tod_clock(vcpu->kvm, val);
+	VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod);
+	kvm_s390_set_tod_clock(vcpu->kvm, &gtod);
 
 	kvm_s390_set_psw_cc(vcpu, 0);
 	return 0;
@@ -795,55 +796,60 @@ out:
 	return rc;
 }
 
-static const intercept_handler_t b2_handlers[256] = {
-	[0x02] = handle_stidp,
-	[0x04] = handle_set_clock,
-	[0x10] = handle_set_prefix,
-	[0x11] = handle_store_prefix,
-	[0x12] = handle_store_cpu_address,
-	[0x14] = kvm_s390_handle_vsie,
-	[0x21] = handle_ipte_interlock,
-	[0x29] = handle_iske,
-	[0x2a] = handle_rrbe,
-	[0x2b] = handle_sske,
-	[0x2c] = handle_test_block,
-	[0x30] = handle_io_inst,
-	[0x31] = handle_io_inst,
-	[0x32] = handle_io_inst,
-	[0x33] = handle_io_inst,
-	[0x34] = handle_io_inst,
-	[0x35] = handle_io_inst,
-	[0x36] = handle_io_inst,
-	[0x37] = handle_io_inst,
-	[0x38] = handle_io_inst,
-	[0x39] = handle_io_inst,
-	[0x3a] = handle_io_inst,
-	[0x3b] = handle_io_inst,
-	[0x3c] = handle_io_inst,
-	[0x50] = handle_ipte_interlock,
-	[0x56] = handle_sthyi,
-	[0x5f] = handle_io_inst,
-	[0x74] = handle_io_inst,
-	[0x76] = handle_io_inst,
-	[0x7d] = handle_stsi,
-	[0xb1] = handle_stfl,
-	[0xb2] = handle_lpswe,
-};
-
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
-	/*
-	 * A lot of B2 instructions are priviledged. Here we check for
-	 * the privileged ones, that we can handle in the kernel.
-	 * Anything else goes to userspace.
-	 */
-	handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
-	if (handler)
-		return handler(vcpu);
-
-	return -EOPNOTSUPP;
+	switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+	case 0x02:
+		return handle_stidp(vcpu);
+	case 0x04:
+		return handle_set_clock(vcpu);
+	case 0x10:
+		return handle_set_prefix(vcpu);
+	case 0x11:
+		return handle_store_prefix(vcpu);
+	case 0x12:
+		return handle_store_cpu_address(vcpu);
+	case 0x14:
+		return kvm_s390_handle_vsie(vcpu);
+	case 0x21:
+	case 0x50:
+		return handle_ipte_interlock(vcpu);
+	case 0x29:
+		return handle_iske(vcpu);
+	case 0x2a:
+		return handle_rrbe(vcpu);
+	case 0x2b:
+		return handle_sske(vcpu);
+	case 0x2c:
+		return handle_test_block(vcpu);
+	case 0x30:
+	case 0x31:
+	case 0x32:
+	case 0x33:
+	case 0x34:
+	case 0x35:
+	case 0x36:
+	case 0x37:
+	case 0x38:
+	case 0x39:
+	case 0x3a:
+	case 0x3b:
+	case 0x3c:
+	case 0x5f:
+	case 0x74:
+	case 0x76:
+		return handle_io_inst(vcpu);
+	case 0x56:
+		return handle_sthyi(vcpu);
+	case 0x7d:
+		return handle_stsi(vcpu);
+	case 0xb1:
+		return handle_stfl(vcpu);
+	case 0xb2:
+		return handle_lpswe(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int handle_epsw(struct kvm_vcpu *vcpu)
@@ -1105,25 +1111,22 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static const intercept_handler_t b9_handlers[256] = {
-	[0x8a] = handle_ipte_interlock,
-	[0x8d] = handle_epsw,
-	[0x8e] = handle_ipte_interlock,
-	[0x8f] = handle_ipte_interlock,
-	[0xab] = handle_essa,
-	[0xaf] = handle_pfmf,
-};
-
 int kvm_s390_handle_b9(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
-	/* This is handled just as for the B2 instructions. */
-	handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
-	if (handler)
-		return handler(vcpu);
-
-	return -EOPNOTSUPP;
+	switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+	case 0x8a:
+	case 0x8e:
+	case 0x8f:
+		return handle_ipte_interlock(vcpu);
+	case 0x8d:
+		return handle_epsw(vcpu);
+	case 0xab:
+		return handle_essa(vcpu);
+	case 0xaf:
+		return handle_pfmf(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
@@ -1271,22 +1274,20 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
 	return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0;
 }
 
-static const intercept_handler_t eb_handlers[256] = {
-	[0x2f] = handle_lctlg,
-	[0x25] = handle_stctg,
-	[0x60] = handle_ri,
-	[0x61] = handle_ri,
-	[0x62] = handle_ri,
-};
-
 int kvm_s390_handle_eb(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
-	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
-	if (handler)
-		return handler(vcpu);
-	return -EOPNOTSUPP;
+	switch (vcpu->arch.sie_block->ipb & 0x000000ff) {
+	case 0x25:
+		return handle_stctg(vcpu);
+	case 0x2f:
+		return handle_lctlg(vcpu);
+	case 0x60:
+	case 0x61:
+	case 0x62:
+		return handle_ri(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int handle_tprot(struct kvm_vcpu *vcpu)
@@ -1346,10 +1347,12 @@ out_unlock:
 
 int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)
 {
-	/* For e5xx... instructions we only handle TPROT */
-	if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01)
+	switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+	case 0x01:
 		return handle_tprot(vcpu);
-	return -EOPNOTSUPP;
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int handle_sckpf(struct kvm_vcpu *vcpu)
@@ -1380,17 +1383,14 @@ static int handle_ptff(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static const intercept_handler_t x01_handlers[256] = {
-	[0x04] = handle_ptff,
-	[0x07] = handle_sckpf,
-};
-
 int kvm_s390_handle_01(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
-	handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
-	if (handler)
-		return handler(vcpu);
-	return -EOPNOTSUPP;
+	switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+	case 0x04:
+		return handle_ptff(vcpu);
+	case 0x07:
+		return handle_sckpf(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index ec772700ff96..8961e3970901 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -821,6 +821,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	int guest_bp_isolation;
 	int rc;
 
 	handle_last_fault(vcpu, vsie_page);
@@ -831,6 +832,20 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		s390_handle_mcck();
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+
+	/* save current guest state of bp isolation override */
+	guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST);
+
+	/*
+	 * The guest is running with BPBC, so we have to force it on for our
+	 * nested guest. This is done by enabling BPBC globally, so the BPBC
+	 * control in the SCB (which the nested guest can modify) is simply
+	 * ignored.
+	 */
+	if (test_kvm_facility(vcpu->kvm, 82) &&
+	    vcpu->arch.sie_block->fpf & FPF_BPBC)
+		set_thread_flag(TIF_ISOLATE_BP_GUEST);
+
 	local_irq_disable();
 	guest_enter_irqoff();
 	local_irq_enable();
@@ -840,6 +855,11 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	local_irq_disable();
 	guest_exit_irqoff();
 	local_irq_enable();
+
+	/* restore guest state for bp isolation override */
+	if (!guest_bp_isolation)
+		clear_thread_flag(TIF_ISOLATE_BP_GUEST);
+
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	if (rc == -EINTR) {
diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile
index 715def00a436..01d0f7fb14cc 100644
--- a/arch/sh/boot/dts/Makefile
+++ b/arch/sh/boot/dts/Makefile
@@ -1 +1,3 @@
-obj-$(CONFIG_USE_BUILTIN_DTB) += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o
+ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"")
+obj-y += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o
+endif
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 847ddffbf38a..b5cfab711651 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -163,13 +163,10 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 	pte_unmap(pte);
 }
 
-void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-		pmd_t *pmdp, pmd_t pmd)
-{
-	pmd_t orig = *pmdp;
-
-	*pmdp = pmd;
 
+static void __set_pmd_acct(struct mm_struct *mm, unsigned long addr,
+			   pmd_t orig, pmd_t pmd)
+{
 	if (mm == &init_mm)
 		return;
 
@@ -219,6 +216,15 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmdp, pmd_t pmd)
+{
+	pmd_t orig = *pmdp;
+
+	*pmdp = pmd;
+	__set_pmd_acct(mm, addr, orig, pmd);
+}
+
 static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmdp, pmd_t pmd)
 {
@@ -227,6 +233,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 	do {
 		old = *pmdp;
 	} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+	__set_pmd_acct(vma->vm_mm, address, old, pmd);
 
 	return old;
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c1236b187824..0fa71a78ec99 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -430,6 +430,7 @@ config GOLDFISH
 config RETPOLINE
 	bool "Avoid speculative indirect branches in kernel"
 	default y
+	select STACK_VALIDATION if HAVE_STACK_VALIDATION
 	help
 	  Compile kernel with the retpoline compiler options to guard against
 	  kernel-to-user data leaks by avoiding speculative indirect
@@ -2306,7 +2307,7 @@ choice
 	  it can be used to assist security vulnerability exploitation.
 
 	  This setting can be changed at boot time via the kernel command
-	  line parameter vsyscall=[native|emulate|none].
+	  line parameter vsyscall=[emulate|none].
 
 	  On a system with recent enough glibc (2.14 or newer) and no
 	  static binaries, you can say None without a performance penalty
@@ -2314,15 +2315,6 @@ choice
 
 	  If unsure, select "Emulate".
 
-	config LEGACY_VSYSCALL_NATIVE
-		bool "Native"
-		help
-		  Actual executable code is located in the fixed vsyscall
-		  address mapping, implementing time() efficiently. Since
-		  this makes the mapping executable, it can be used during
-		  security vulnerability exploitation (traditionally as
-		  ROP gadgets). This configuration is not recommended.
-
 	config LEGACY_VSYSCALL_EMULATE
 		bool "Emulate"
 		help
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index fad55160dcb9..498c1b812300 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -232,10 +232,9 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 
 # Avoid indirect branches in kernel to deal with Spectre
 ifdef CONFIG_RETPOLINE
-    RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
-    ifneq ($(RETPOLINE_CFLAGS),)
-        KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
-    endif
+ifneq ($(RETPOLINE_CFLAGS),)
+  KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
+endif
 endif
 
 archscripts: scripts_basic
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index dce7092ab24a..be63330c5511 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -97,7 +97,7 @@ For 32-bit we have the following conventions - kernel is built with
 
 #define SIZEOF_PTREGS	21*8
 
-.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
 	/*
 	 * Push registers and sanitize registers of values that a
 	 * speculation attack might otherwise want to exploit. The
@@ -105,32 +105,41 @@ For 32-bit we have the following conventions - kernel is built with
 	 * could be put to use in a speculative execution gadget.
 	 * Interleave XOR with PUSH for better uop scheduling:
 	 */
+	.if \save_ret
+	pushq	%rsi		/* pt_regs->si */
+	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
+	movq	%rdi, 8(%rsp)	/* pt_regs->di (overwriting original return address) */
+	.else
 	pushq   %rdi		/* pt_regs->di */
 	pushq   %rsi		/* pt_regs->si */
+	.endif
 	pushq	\rdx		/* pt_regs->dx */
 	pushq   %rcx		/* pt_regs->cx */
 	pushq   \rax		/* pt_regs->ax */
 	pushq   %r8		/* pt_regs->r8 */
-	xorq    %r8, %r8	/* nospec   r8 */
+	xorl	%r8d, %r8d	/* nospec   r8 */
 	pushq   %r9		/* pt_regs->r9 */
-	xorq    %r9, %r9	/* nospec   r9 */
+	xorl	%r9d, %r9d	/* nospec   r9 */
 	pushq   %r10		/* pt_regs->r10 */
-	xorq    %r10, %r10	/* nospec   r10 */
+	xorl	%r10d, %r10d	/* nospec   r10 */
 	pushq   %r11		/* pt_regs->r11 */
-	xorq    %r11, %r11	/* nospec   r11*/
+	xorl	%r11d, %r11d	/* nospec   r11*/
 	pushq	%rbx		/* pt_regs->rbx */
 	xorl    %ebx, %ebx	/* nospec   rbx*/
 	pushq	%rbp		/* pt_regs->rbp */
 	xorl    %ebp, %ebp	/* nospec   rbp*/
 	pushq	%r12		/* pt_regs->r12 */
-	xorq    %r12, %r12	/* nospec   r12*/
+	xorl	%r12d, %r12d	/* nospec   r12*/
 	pushq	%r13		/* pt_regs->r13 */
-	xorq    %r13, %r13	/* nospec   r13*/
+	xorl	%r13d, %r13d	/* nospec   r13*/
 	pushq	%r14		/* pt_regs->r14 */
-	xorq    %r14, %r14	/* nospec   r14*/
+	xorl	%r14d, %r14d	/* nospec   r14*/
 	pushq	%r15		/* pt_regs->r15 */
-	xorq    %r15, %r15	/* nospec   r15*/
+	xorl	%r15d, %r15d	/* nospec   r15*/
 	UNWIND_HINT_REGS
+	.if \save_ret
+	pushq	%rsi		/* return address on top of stack */
+	.endif
 .endm
 
 .macro POP_REGS pop_rdi=1 skip_r11rcx=0
@@ -172,12 +181,7 @@ For 32-bit we have the following conventions - kernel is built with
  */
 .macro ENCODE_FRAME_POINTER ptregs_offset=0
 #ifdef CONFIG_FRAME_POINTER
-	.if \ptregs_offset
-		leaq \ptregs_offset(%rsp), %rbp
-	.else
-		mov %rsp, %rbp
-	.endif
-	orq	$0x1, %rbp
+	leaq 1+\ptregs_offset(%rsp), %rbp
 #endif
 .endm
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 16c2c022540d..6ad064c8cf35 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -252,8 +252,7 @@ ENTRY(__switch_to_asm)
 	 * exist, overwrite the RSB with entries which capture
 	 * speculative execution to prevent attack.
 	 */
-	/* Clobbers %ebx */
-	FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
 #endif
 
 	/* restore callee-saved registers */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8971bd64d515..805f52703ee3 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -55,7 +55,7 @@ END(native_usergs_sysret64)
 
 .macro TRACE_IRQS_FLAGS flags:req
 #ifdef CONFIG_TRACE_IRQFLAGS
-	bt	$9, \flags		/* interrupts off? */
+	btl	$9, \flags		/* interrupts off? */
 	jnc	1f
 	TRACE_IRQS_ON
 1:
@@ -364,8 +364,7 @@ ENTRY(__switch_to_asm)
 	 * exist, overwrite the RSB with entries which capture
 	 * speculative execution to prevent attack.
 	 */
-	/* Clobbers %rbx */
-	FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+	FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
 #endif
 
 	/* restore callee-saved registers */
@@ -449,9 +448,19 @@ END(irq_entries_start)
  *
  * The invariant is that, if irq_count != -1, then the IRQ stack is in use.
  */
-.macro ENTER_IRQ_STACK regs=1 old_rsp
+.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0
 	DEBUG_ENTRY_ASSERT_IRQS_OFF
+
+	.if \save_ret
+	/*
+	 * If save_ret is set, the original stack contains one additional
+	 * entry -- the return address. Therefore, move the address one
+	 * entry below %rsp to \old_rsp.
+	 */
+	leaq	8(%rsp), \old_rsp
+	.else
 	movq	%rsp, \old_rsp
+	.endif
 
 	.if \regs
 	UNWIND_HINT_REGS base=\old_rsp
@@ -497,6 +506,15 @@ END(irq_entries_start)
 	.if \regs
 	UNWIND_HINT_REGS indirect=1
 	.endif
+
+	.if \save_ret
+	/*
+	 * Push the return address to the stack. This return address can
+	 * be found at the "real" original RSP, which was offset by 8 at
+	 * the beginning of this macro.
+	 */
+	pushq	-8(\old_rsp)
+	.endif
 .endm
 
 /*
@@ -520,27 +538,65 @@ END(irq_entries_start)
 .endm
 
 /*
- * Interrupt entry/exit.
- *
- * Interrupt entry points save only callee clobbered registers in fast path.
+ * Interrupt entry helper function.
  *
- * Entry runs with interrupts off.
+ * Entry runs with interrupts off. Stack layout at entry:
+ * +----------------------------------------------------+
+ * | regs->ss						|
+ * | regs->rsp						|
+ * | regs->eflags					|
+ * | regs->cs						|
+ * | regs->ip						|
+ * +----------------------------------------------------+
+ * | regs->orig_ax = ~(interrupt number)		|
+ * +----------------------------------------------------+
+ * | return address					|
+ * +----------------------------------------------------+
  */
-
-/* 0(%rsp): ~(interrupt number) */
-	.macro interrupt func
+ENTRY(interrupt_entry)
+	UNWIND_HINT_FUNC
+	ASM_CLAC
 	cld
 
-	testb	$3, CS-ORIG_RAX(%rsp)
+	testb	$3, CS-ORIG_RAX+8(%rsp)
 	jz	1f
 	SWAPGS
-	call	switch_to_thread_stack
+
+	/*
+	 * Switch to the thread stack. The IRET frame and orig_ax are
+	 * on the stack, as well as the return address. RDI..R12 are
+	 * not (yet) on the stack and space has not (yet) been
+	 * allocated for them.
+	 */
+	pushq	%rdi
+
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+	 /*
+	  * We have RDI, return address, and orig_ax on the stack on
+	  * top of the IRET frame. That means offset=24
+	  */
+	UNWIND_HINT_IRET_REGS base=%rdi offset=24
+
+	pushq	7*8(%rdi)		/* regs->ss */
+	pushq	6*8(%rdi)		/* regs->rsp */
+	pushq	5*8(%rdi)		/* regs->eflags */
+	pushq	4*8(%rdi)		/* regs->cs */
+	pushq	3*8(%rdi)		/* regs->ip */
+	pushq	2*8(%rdi)		/* regs->orig_ax */
+	pushq	8(%rdi)			/* return address */
+	UNWIND_HINT_FUNC
+
+	movq	(%rdi), %rdi
 1:
 
-	PUSH_AND_CLEAR_REGS
-	ENCODE_FRAME_POINTER
+	PUSH_AND_CLEAR_REGS save_ret=1
+	ENCODE_FRAME_POINTER 8
 
-	testb	$3, CS(%rsp)
+	testb	$3, CS+8(%rsp)
 	jz	1f
 
 	/*
@@ -548,7 +604,7 @@ END(irq_entries_start)
 	 *
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
-	 * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
+	 * (which can take locks).  Since TRACE_IRQS_OFF is idempotent,
 	 * the simplest way to handle it is to just call it twice if
 	 * we enter from user mode.  There's no reason to optimize this since
 	 * TRACE_IRQS_OFF is a no-op if lockdep is off.
@@ -558,12 +614,15 @@ END(irq_entries_start)
 	CALL_enter_from_user_mode
 
 1:
-	ENTER_IRQ_STACK old_rsp=%rdi
+	ENTER_IRQ_STACK old_rsp=%rdi save_ret=1
 	/* We entered an interrupt context - irqs are off: */
 	TRACE_IRQS_OFF
 
-	call	\func	/* rdi points to pt_regs */
-	.endm
+	ret
+END(interrupt_entry)
+
+
+/* Interrupt entry/exit. */
 
 	/*
 	 * The interrupt stubs push (~vector+0x80) onto the stack and
@@ -571,9 +630,10 @@ END(irq_entries_start)
 	 */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
-	ASM_CLAC
 	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
-	interrupt do_IRQ
+	call	interrupt_entry
+	UNWIND_HINT_REGS indirect=1
+	call	do_IRQ	/* rdi points to pt_regs */
 	/* 0(%rsp): old RSP */
 ret_from_intr:
 	DISABLE_INTERRUPTS(CLBR_ANY)
@@ -766,10 +826,11 @@ END(common_interrupt)
 .macro apicinterrupt3 num sym do_sym
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS
-	ASM_CLAC
 	pushq	$~(\num)
 .Lcommon_\sym:
-	interrupt \do_sym
+	call	interrupt_entry
+	UNWIND_HINT_REGS indirect=1
+	call	\do_sym	/* rdi points to pt_regs */
 	jmp	ret_from_intr
 END(\sym)
 .endm
@@ -832,34 +893,6 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  */
 #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
 
-/*
- * Switch to the thread stack.  This is called with the IRET frame and
- * orig_ax on the stack.  (That is, RDI..R12 are not on the stack and
- * space has not been allocated for them.)
- */
-ENTRY(switch_to_thread_stack)
-	UNWIND_HINT_FUNC
-
-	pushq	%rdi
-	/* Need to switch before accessing the thread stack. */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-	movq	%rsp, %rdi
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-	UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
-
-	pushq	7*8(%rdi)		/* regs->ss */
-	pushq	6*8(%rdi)		/* regs->rsp */
-	pushq	5*8(%rdi)		/* regs->eflags */
-	pushq	4*8(%rdi)		/* regs->cs */
-	pushq	3*8(%rdi)		/* regs->ip */
-	pushq	2*8(%rdi)		/* regs->orig_ax */
-	pushq	8(%rdi)			/* return address */
-	UNWIND_HINT_FUNC
-
-	movq	(%rdi), %rdi
-	ret
-END(switch_to_thread_stack)
-
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
@@ -875,12 +908,8 @@ ENTRY(\sym)
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	.endif
 
-	/* Save all registers in pt_regs */
-	PUSH_AND_CLEAR_REGS
-	ENCODE_FRAME_POINTER
-
 	.if \paranoid < 2
-	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
+	testb	$3, CS-ORIG_RAX(%rsp)		/* If coming from userspace, switch stacks */
 	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
 
@@ -1130,13 +1159,15 @@ idtentry machine_check		do_mce			has_error_code=0	paranoid=1
 #endif
 
 /*
- * Switch gs if needed.
+ * Save all registers in pt_regs, and switch gs if needed.
  * Use slow, but surefire "are we in kernel?" check.
  * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
  */
 ENTRY(paranoid_entry)
 	UNWIND_HINT_FUNC
 	cld
+	PUSH_AND_CLEAR_REGS save_ret=1
+	ENCODE_FRAME_POINTER 8
 	movl	$1, %ebx
 	movl	$MSR_GS_BASE, %ecx
 	rdmsr
@@ -1181,12 +1212,14 @@ ENTRY(paranoid_exit)
 END(paranoid_exit)
 
 /*
- * Switch gs if needed.
+ * Save all registers in pt_regs, and switch GS if needed.
  * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
-	UNWIND_HINT_REGS offset=8
+	UNWIND_HINT_FUNC
 	cld
+	PUSH_AND_CLEAR_REGS save_ret=1
+	ENCODE_FRAME_POINTER 8
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
 
@@ -1577,8 +1610,6 @@ end_repeat_nmi:
 	 * frame to point back to repeat_nmi.
 	 */
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
-	PUSH_AND_CLEAR_REGS
-	ENCODE_FRAME_POINTER
 
 	/*
 	 * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index fd65e016e413..08425c42f8b7 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -85,25 +85,25 @@ ENTRY(entry_SYSENTER_compat)
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
-	xorq	%r8, %r8		/* nospec   r8 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
-	xorq	%r9, %r9		/* nospec   r9 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
-	xorq	%r10, %r10		/* nospec   r10 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
-	xorq	%r11, %r11		/* nospec   r11 */
+	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
 	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
-	xorq	%r12, %r12		/* nospec   r12 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
-	xorq	%r13, %r13		/* nospec   r13 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
-	xorq	%r14, %r14		/* nospec   r14 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
-	xorq	%r15, %r15		/* nospec   r15 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 	cld
 
 	/*
@@ -224,25 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
-	xorq	%r8, %r8		/* nospec   r8 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
-	xorq	%r9, %r9		/* nospec   r9 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
-	xorq	%r10, %r10		/* nospec   r10 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
-	xorq	%r11, %r11		/* nospec   r11 */
+	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
 	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
-	xorq	%r12, %r12		/* nospec   r12 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
-	xorq	%r13, %r13		/* nospec   r13 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
-	xorq	%r14, %r14		/* nospec   r14 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
-	xorq	%r15, %r15		/* nospec   r15 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -298,9 +298,9 @@ sysret32_from_system_call:
 	 */
 	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
 
-	xorq	%r8, %r8
-	xorq	%r9, %r9
-	xorq	%r10, %r10
+	xorl	%r8d, %r8d
+	xorl	%r9d, %r9d
+	xorl	%r10d, %r10d
 	swapgs
 	sysretl
 END(entry_SYSCALL_compat)
@@ -347,36 +347,47 @@ ENTRY(entry_INT80_compat)
 	 */
 	movl	%eax, %eax
 
+	/* switch to thread stack expects orig_ax and rdi to be pushed */
 	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
 
-	/* switch to thread stack expects orig_ax to be pushed */
-	call	switch_to_thread_stack
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
-	pushq	%rdi			/* pt_regs->di */
+	pushq	6*8(%rdi)		/* regs->ss */
+	pushq	5*8(%rdi)		/* regs->rsp */
+	pushq	4*8(%rdi)		/* regs->eflags */
+	pushq	3*8(%rdi)		/* regs->cs */
+	pushq	2*8(%rdi)		/* regs->ip */
+	pushq	1*8(%rdi)		/* regs->orig_ax */
+
+	pushq	(%rdi)			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
-	xorq	%r8, %r8		/* nospec   r8 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
-	xorq	%r9, %r9		/* nospec   r9 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
-	xorq	%r10, %r10		/* nospec   r10 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
-	xorq	%r11, %r11		/* nospec   r11 */
+	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
 	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp */
 	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   %r12                    /* pt_regs->r12 */
-	xorq	%r12, %r12		/* nospec   r12 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   %r13                    /* pt_regs->r13 */
-	xorq	%r13, %r13		/* nospec   r13 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   %r14                    /* pt_regs->r14 */
-	xorq	%r14, %r14		/* nospec   r14 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   %r15                    /* pt_regs->r15 */
-	xorq	%r15, %r15		/* nospec   r15 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 	cld
 
 	/*
@@ -393,15 +404,3 @@ ENTRY(entry_INT80_compat)
 	TRACE_IRQS_ON
 	jmp	swapgs_restore_regs_and_return_to_usermode
 END(entry_INT80_compat)
-
-ENTRY(stub32_clone)
-	/*
-	 * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
-	 * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
-	 *
-	 * The native 64-bit kernel's sys_clone() implements the latter,
-	 * so we need to swap arguments here before calling it:
-	 */
-	xchg	%r8, %rcx
-	jmp	sys_clone
-ENDPROC(stub32_clone)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 448ac2161112..2a5e99cff859 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -8,12 +8,12 @@
 #
 0	i386	restart_syscall		sys_restart_syscall
 1	i386	exit			sys_exit
-2	i386	fork			sys_fork			sys_fork
+2	i386	fork			sys_fork
 3	i386	read			sys_read
 4	i386	write			sys_write
 5	i386	open			sys_open			compat_sys_open
 6	i386	close			sys_close
-7	i386	waitpid			sys_waitpid			sys32_waitpid
+7	i386	waitpid			sys_waitpid			compat_sys_x86_waitpid
 8	i386	creat			sys_creat
 9	i386	link			sys_link
 10	i386	unlink			sys_unlink
@@ -78,7 +78,7 @@
 69	i386	ssetmask		sys_ssetmask
 70	i386	setreuid		sys_setreuid16
 71	i386	setregid		sys_setregid16
-72	i386	sigsuspend		sys_sigsuspend			sys_sigsuspend
+72	i386	sigsuspend		sys_sigsuspend
 73	i386	sigpending		sys_sigpending			compat_sys_sigpending
 74	i386	sethostname		sys_sethostname
 75	i386	setrlimit		sys_setrlimit			compat_sys_setrlimit
@@ -96,7 +96,7 @@
 87	i386	swapon			sys_swapon
 88	i386	reboot			sys_reboot
 89	i386	readdir			sys_old_readdir			compat_sys_old_readdir
-90	i386	mmap			sys_old_mmap			sys32_mmap
+90	i386	mmap			sys_old_mmap			compat_sys_x86_mmap
 91	i386	munmap			sys_munmap
 92	i386	truncate		sys_truncate			compat_sys_truncate
 93	i386	ftruncate		sys_ftruncate			compat_sys_ftruncate
@@ -126,7 +126,7 @@
 117	i386	ipc			sys_ipc				compat_sys_ipc
 118	i386	fsync			sys_fsync
 119	i386	sigreturn		sys_sigreturn			sys32_sigreturn
-120	i386	clone			sys_clone			stub32_clone
+120	i386	clone			sys_clone			compat_sys_x86_clone
 121	i386	setdomainname		sys_setdomainname
 122	i386	uname			sys_newuname
 123	i386	modify_ldt		sys_modify_ldt
@@ -186,8 +186,8 @@
 177	i386	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait
 178	i386	rt_sigqueueinfo		sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
 179	i386	rt_sigsuspend		sys_rt_sigsuspend
-180	i386	pread64			sys_pread64			sys32_pread
-181	i386	pwrite64		sys_pwrite64			sys32_pwrite
+180	i386	pread64			sys_pread64			compat_sys_x86_pread
+181	i386	pwrite64		sys_pwrite64			compat_sys_x86_pwrite
 182	i386	chown			sys_chown16
 183	i386	getcwd			sys_getcwd
 184	i386	capget			sys_capget
@@ -196,14 +196,14 @@
 187	i386	sendfile		sys_sendfile			compat_sys_sendfile
 188	i386	getpmsg
 189	i386	putpmsg
-190	i386	vfork			sys_vfork			sys_vfork
+190	i386	vfork			sys_vfork
 191	i386	ugetrlimit		sys_getrlimit			compat_sys_getrlimit
 192	i386	mmap2			sys_mmap_pgoff
-193	i386	truncate64		sys_truncate64			sys32_truncate64
-194	i386	ftruncate64		sys_ftruncate64			sys32_ftruncate64
-195	i386	stat64			sys_stat64			sys32_stat64
-196	i386	lstat64			sys_lstat64			sys32_lstat64
-197	i386	fstat64			sys_fstat64			sys32_fstat64
+193	i386	truncate64		sys_truncate64			compat_sys_x86_truncate64
+194	i386	ftruncate64		sys_ftruncate64			compat_sys_x86_ftruncate64
+195	i386	stat64			sys_stat64			compat_sys_x86_stat64
+196	i386	lstat64			sys_lstat64			compat_sys_x86_lstat64
+197	i386	fstat64			sys_fstat64			compat_sys_x86_fstat64
 198	i386	lchown32		sys_lchown
 199	i386	getuid32		sys_getuid
 200	i386	getgid32		sys_getgid
@@ -231,7 +231,7 @@
 # 222 is unused
 # 223 is unused
 224	i386	gettid			sys_gettid
-225	i386	readahead		sys_readahead			sys32_readahead
+225	i386	readahead		sys_readahead			compat_sys_x86_readahead
 226	i386	setxattr		sys_setxattr
 227	i386	lsetxattr		sys_lsetxattr
 228	i386	fsetxattr		sys_fsetxattr
@@ -256,7 +256,7 @@
 247	i386	io_getevents		sys_io_getevents		compat_sys_io_getevents
 248	i386	io_submit		sys_io_submit			compat_sys_io_submit
 249	i386	io_cancel		sys_io_cancel
-250	i386	fadvise64		sys_fadvise64			sys32_fadvise64
+250	i386	fadvise64		sys_fadvise64			compat_sys_x86_fadvise64
 # 251 is available for reuse (was briefly sys_set_zone_reclaim)
 252	i386	exit_group		sys_exit_group
 253	i386	lookup_dcookie		sys_lookup_dcookie		compat_sys_lookup_dcookie
@@ -278,7 +278,7 @@
 269	i386	fstatfs64		sys_fstatfs64			compat_sys_fstatfs64
 270	i386	tgkill			sys_tgkill
 271	i386	utimes			sys_utimes			compat_sys_utimes
-272	i386	fadvise64_64		sys_fadvise64_64		sys32_fadvise64_64
+272	i386	fadvise64_64		sys_fadvise64_64		compat_sys_x86_fadvise64_64
 273	i386	vserver
 274	i386	mbind			sys_mbind
 275	i386	get_mempolicy		sys_get_mempolicy		compat_sys_get_mempolicy
@@ -306,7 +306,7 @@
 297	i386	mknodat			sys_mknodat
 298	i386	fchownat		sys_fchownat
 299	i386	futimesat		sys_futimesat			compat_sys_futimesat
-300	i386	fstatat64		sys_fstatat64			sys32_fstatat
+300	i386	fstatat64		sys_fstatat64			compat_sys_x86_fstatat
 301	i386	unlinkat		sys_unlinkat
 302	i386	renameat		sys_renameat
 303	i386	linkat			sys_linkat
@@ -320,7 +320,7 @@
 311	i386	set_robust_list		sys_set_robust_list		compat_sys_set_robust_list
 312	i386	get_robust_list		sys_get_robust_list		compat_sys_get_robust_list
 313	i386	splice			sys_splice
-314	i386	sync_file_range		sys_sync_file_range		sys32_sync_file_range
+314	i386	sync_file_range		sys_sync_file_range		compat_sys_x86_sync_file_range
 315	i386	tee			sys_tee
 316	i386	vmsplice		sys_vmsplice			compat_sys_vmsplice
 317	i386	move_pages		sys_move_pages			compat_sys_move_pages
@@ -330,7 +330,7 @@
 321	i386	signalfd		sys_signalfd			compat_sys_signalfd
 322	i386	timerfd_create		sys_timerfd_create
 323	i386	eventfd			sys_eventfd
-324	i386	fallocate		sys_fallocate			sys32_fallocate
+324	i386	fallocate		sys_fallocate			compat_sys_x86_fallocate
 325	i386	timerfd_settime		sys_timerfd_settime		compat_sys_timerfd_settime
 326	i386	timerfd_gettime		sys_timerfd_gettime		compat_sys_timerfd_gettime
 327	i386	signalfd4		sys_signalfd4			compat_sys_signalfd4
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 577fa8adb785..8560ef68a9d6 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -42,10 +42,8 @@
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
 
-static enum { EMULATE, NATIVE, NONE } vsyscall_mode =
-#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE)
-	NATIVE;
-#elif defined(CONFIG_LEGACY_VSYSCALL_NONE)
+static enum { EMULATE, NONE } vsyscall_mode =
+#ifdef CONFIG_LEGACY_VSYSCALL_NONE
 	NONE;
 #else
 	EMULATE;
@@ -56,8 +54,6 @@ static int __init vsyscall_setup(char *str)
 	if (str) {
 		if (!strcmp("emulate", str))
 			vsyscall_mode = EMULATE;
-		else if (!strcmp("native", str))
-			vsyscall_mode = NATIVE;
 		else if (!strcmp("none", str))
 			vsyscall_mode = NONE;
 		else
@@ -139,10 +135,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	WARN_ON_ONCE(address != regs->ip);
 
-	/* This should be unreachable in NATIVE mode. */
-	if (WARN_ON(vsyscall_mode == NATIVE))
-		return false;
-
 	if (vsyscall_mode == NONE) {
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall attempted with vsyscall=none");
@@ -370,9 +362,7 @@ void __init map_vsyscall(void)
 
 	if (vsyscall_mode != NONE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
-			     vsyscall_mode == NATIVE
-			     ? PAGE_KERNEL_VSYSCALL
-			     : PAGE_KERNEL_VVAR);
+			     PAGE_KERNEL_VVAR);
 		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
 	}
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 6d8044ab1060..22ec65bc033a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3606,7 +3606,7 @@ static struct intel_uncore_type skx_uncore_imc = {
 };
 
 static struct attribute *skx_upi_uncore_formats_attr[] = {
-	&format_attr_event_ext.attr,
+	&format_attr_event.attr,
 	&format_attr_umask_ext.attr,
 	&format_attr_edge.attr,
 	&format_attr_inv.attr,
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 96cd33bbfc85..6512498bbef6 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -51,15 +51,14 @@
 #define AA(__x)		((unsigned long)(__x))
 
 
-asmlinkage long sys32_truncate64(const char __user *filename,
-				 unsigned long offset_low,
-				 unsigned long offset_high)
+COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename,
+		       unsigned long, offset_low, unsigned long, offset_high)
 {
        return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low);
 }
 
-asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low,
-				  unsigned long offset_high)
+COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd,
+		       unsigned long, offset_low, unsigned long, offset_high)
 {
        return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low);
 }
@@ -96,8 +95,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
 	return 0;
 }
 
-asmlinkage long sys32_stat64(const char __user *filename,
-			     struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename,
+		       struct stat64 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_stat(filename, &stat);
@@ -107,8 +106,8 @@ asmlinkage long sys32_stat64(const char __user *filename,
 	return ret;
 }
 
-asmlinkage long sys32_lstat64(const char __user *filename,
-			      struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename,
+		       struct stat64 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_lstat(filename, &stat);
@@ -117,7 +116,8 @@ asmlinkage long sys32_lstat64(const char __user *filename,
 	return ret;
 }
 
-asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd,
+		       struct stat64 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_fstat(fd, &stat);
@@ -126,8 +126,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
 	return ret;
 }
 
-asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename,
-			      struct stat64 __user *statbuf, int flag)
+COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd,
+		       const char __user *, filename,
+		       struct stat64 __user *, statbuf, int, flag)
 {
 	struct kstat stat;
 	int error;
@@ -153,7 +154,7 @@ struct mmap_arg_struct32 {
 	unsigned int offset;
 };
 
-asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg)
+COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg)
 {
 	struct mmap_arg_struct32 a;
 
@@ -167,22 +168,22 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg)
 			       a.offset>>PAGE_SHIFT);
 }
 
-asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr,
-			      int options)
+COMPAT_SYSCALL_DEFINE3(x86_waitpid, compat_pid_t, pid, unsigned int __user *,
+		       stat_addr, int, options)
 {
 	return compat_sys_wait4(pid, stat_addr, options, NULL);
 }
 
 /* warning: next two assume little endian */
-asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count,
-			    u32 poslo, u32 poshi)
+COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf,
+		       u32, count, u32, poslo, u32, poshi)
 {
 	return sys_pread64(fd, ubuf, count,
 			 ((loff_t)AA(poshi) << 32) | AA(poslo));
 }
 
-asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf,
-			     u32 count, u32 poslo, u32 poshi)
+COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf,
+		       u32, count, u32, poslo, u32, poshi)
 {
 	return sys_pwrite64(fd, ubuf, count,
 			  ((loff_t)AA(poshi) << 32) | AA(poslo));
@@ -193,8 +194,9 @@ asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf,
  * Some system calls that need sign extended arguments. This could be
  * done by a generic wrapper.
  */
-long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
-			__u32 len_low, __u32 len_high, int advice)
+COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low,
+		       __u32, offset_high, __u32, len_low, __u32, len_high,
+		       int, advice)
 {
 	return sys_fadvise64_64(fd,
 			       (((u64)offset_high)<<32) | offset_low,
@@ -202,31 +204,43 @@ long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
 				advice);
 }
 
-asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi,
-				   size_t count)
+COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo,
+		       unsigned int, off_hi, size_t, count)
 {
 	return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count);
 }
 
-asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi,
-				      unsigned n_low, unsigned n_hi,  int flags)
+COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low,
+		       unsigned int, off_hi, unsigned int, n_low,
+		       unsigned int, n_hi, int, flags)
 {
 	return sys_sync_file_range(fd,
 				   ((u64)off_hi << 32) | off_low,
 				   ((u64)n_hi << 32) | n_low, flags);
 }
 
-asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi,
-				size_t len, int advice)
+COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo,
+		       unsigned int, offset_hi, size_t, len, int, advice)
 {
 	return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
 				len, advice);
 }
 
-asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo,
-				unsigned offset_hi, unsigned len_lo,
-				unsigned len_hi)
+COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode,
+		       unsigned int, offset_lo, unsigned int, offset_hi,
+		       unsigned int, len_lo, unsigned int, len_hi)
 {
 	return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
 			     ((u64)len_hi << 32) | len_lo);
 }
+
+/*
+ * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS
+ */
+COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
+		       unsigned long, newsp, int __user *, parent_tidptr,
+		       unsigned long, tls_val, int __user *, child_tidptr)
+{
+	return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr,
+			tls_val);
+}
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index 4d4015ddcf26..c356098b6fb9 100644
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -7,6 +7,8 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H
 
+#include <asm/nospec-branch.h>
+
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -32,6 +34,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -44,6 +47,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 }
 
 static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -56,6 +60,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -68,6 +73,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 	return error;
 }
 
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 4d111616524b..1908214b9125 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -38,7 +38,4 @@ INDIRECT_THUNK(dx)
 INDIRECT_THUNK(si)
 INDIRECT_THUNK(di)
 INDIRECT_THUNK(bp)
-asmlinkage void __fill_rsb(void);
-asmlinkage void __clear_rsb(void);
-
 #endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 3fa039855b8f..9f645ba57dbb 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -78,7 +78,7 @@ set_bit(long nr, volatile unsigned long *addr)
 			: "iq" ((u8)CONST_MASK(nr))
 			: "memory");
 	} else {
-		asm volatile(LOCK_PREFIX "bts %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
 			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
 	}
 }
@@ -94,7 +94,7 @@ set_bit(long nr, volatile unsigned long *addr)
  */
 static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
+	asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
 
 /**
@@ -115,7 +115,7 @@ clear_bit(long nr, volatile unsigned long *addr)
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" ((u8)~CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX "btr %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
 			: BITOP_ADDR(addr)
 			: "Ir" (nr));
 	}
@@ -137,7 +137,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad
 
 static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr));
 }
 
 static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
@@ -182,7 +182,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *
  */
 static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr));
 }
 
 /**
@@ -201,7 +201,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" ((u8)CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX "btc %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
 			: BITOP_ADDR(addr)
 			: "Ir" (nr));
 	}
@@ -217,7 +217,8 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
  */
 static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -246,7 +247,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
 {
 	bool oldbit;
 
-	asm("bts %2,%1"
+	asm(__ASM_SIZE(bts) " %2,%1"
 	    CC_SET(c)
 	    : CC_OUT(c) (oldbit), ADDR
 	    : "Ir" (nr));
@@ -263,7 +264,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
  */
 static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -286,7 +288,7 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
 {
 	bool oldbit;
 
-	asm volatile("btr %2,%1"
+	asm volatile(__ASM_SIZE(btr) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr));
@@ -298,7 +300,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
 {
 	bool oldbit;
 
-	asm volatile("btc %2,%1"
+	asm volatile(__ASM_SIZE(btc) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr) : "memory");
@@ -316,7 +318,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
  */
 static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
@@ -329,7 +332,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 {
 	bool oldbit;
 
-	asm volatile("bt %2,%1"
+	asm volatile(__ASM_SIZE(bt) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 0dfe4d3f74e2..d554c11e01ff 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -213,6 +213,7 @@
 #define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
 
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -315,6 +316,7 @@
 #define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
 #define X86_FEATURE_AVX512_VNNI		(16*32+11) /* Vector Neural Network Instructions */
 #define X86_FEATURE_AVX512_BITALG	(16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_TME			(16*32+13) /* Intel Total Memory Encryption */
 #define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
@@ -327,6 +329,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 85f6ccb80b91..a399c1ebf6f0 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -6,6 +6,7 @@
 #include <asm/pgtable.h>
 #include <asm/processor-flags.h>
 #include <asm/tlb.h>
+#include <asm/nospec-branch.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -36,8 +37,18 @@
 
 extern asmlinkage unsigned long efi_call_phys(void *, ...);
 
-#define arch_efi_call_virt_setup()	kernel_fpu_begin()
-#define arch_efi_call_virt_teardown()	kernel_fpu_end()
+#define arch_efi_call_virt_setup()					\
+({									\
+	kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
+})
+
+#define arch_efi_call_virt_teardown()					\
+({									\
+	firmware_restrict_branch_speculation_end();			\
+	kernel_fpu_end();						\
+})
+
 
 /*
  * Wrap all the virtual calls in a way that forces the parameters on the stack.
@@ -73,6 +84,7 @@ struct efi_scratch {
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 									\
 	if (efi_scratch.use_pgd) {					\
 		efi_scratch.prev_cr3 = __read_cr3();			\
@@ -91,6 +103,7 @@ struct efi_scratch {
 		__flush_tlb_all();					\
 	}								\
 									\
+	firmware_restrict_branch_speculation_end();			\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 })
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dd6f57a54a26..b605a5b6a30c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -507,6 +507,7 @@ struct kvm_vcpu_arch {
 	u64 smi_count;
 	bool tpr_access_reporting;
 	u64 ia32_xss;
+	u64 microcode_version;
 
 	/*
 	 * Paging state of the vcpu
@@ -1095,6 +1096,8 @@ struct kvm_x86_ops {
 	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
 	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+
+	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 };
 
 struct kvm_arch_async_pf {
@@ -1464,7 +1467,4 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define put_smstate(type, buf, offset, val)                      \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
-void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end);
-
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 55520cec8b27..6cf0e4cb7b97 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -37,7 +37,13 @@ struct cpu_signature {
 
 struct device;
 
-enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
+enum ucode_state {
+	UCODE_OK	= 0,
+	UCODE_NEW,
+	UCODE_UPDATED,
+	UCODE_NFOUND,
+	UCODE_ERROR,
+};
 
 struct microcode_ops {
 	enum ucode_state (*request_microcode_user) (int cpu,
@@ -54,7 +60,7 @@ struct microcode_ops {
 	 * are being called.
 	 * See also the "Synchronization" section in microcode_core.c.
 	 */
-	int (*apply_microcode) (int cpu);
+	enum ucode_state (*apply_microcode) (int cpu);
 	int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 };
 
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index c931b88982a0..1de72ce514cd 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -74,6 +74,7 @@ static inline void *ldt_slot_va(int slot)
 	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
 #else
 	BUG();
+	return (void *)fix_to_virt(FIX_HOLE);
 #endif
 }
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 81a1be326571..f928ad9b143f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -8,6 +8,50 @@
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 
+/*
+ * Fill the CPU return stack buffer.
+ *
+ * Each entry in the RSB, if used for a speculative 'ret', contains an
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * We define a CPP macro such that it can be used from both .S files and
+ * inline assembly. It's possible to do a .macro and then include that
+ * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
+ */
+
+#define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
+#define RSB_FILL_LOOPS		16	/* To avoid underflow */
+
+/*
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version — two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
+	mov	$(nr/2), reg;			\
+771:						\
+	call	772f;				\
+773:	/* speculation trap */			\
+	pause;					\
+	lfence;					\
+	jmp	773b;				\
+772:						\
+	call	774f;				\
+775:	/* speculation trap */			\
+	pause;					\
+	lfence;					\
+	jmp	775b;				\
+774:						\
+	dec	reg;				\
+	jnz	771b;				\
+	add	$(BITS_PER_LONG/8) * nr, sp;
+
 #ifdef __ASSEMBLY__
 
 /*
@@ -24,6 +68,18 @@
 .endm
 
 /*
+ * This should be used immediately before an indirect jump/call. It tells
+ * objtool the subsequent indirect jump/call is vouched safe for retpoline
+ * builds.
+ */
+.macro ANNOTATE_RETPOLINE_SAFE
+	.Lannotate_\@:
+	.pushsection .discard.retpoline_safe
+	_ASM_PTR .Lannotate_\@
+	.popsection
+.endm
+
+/*
  * These are the bare retpoline primitives for indirect jmp and call.
  * Do not use these directly; they only exist to make the ALTERNATIVE
  * invocation below less ugly.
@@ -59,9 +115,9 @@
 .macro JMP_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
 	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE_2 __stringify(jmp *\reg),				\
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg),	\
 		__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE,	\
-		__stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
 #else
 	jmp	*\reg
 #endif
@@ -70,18 +126,25 @@
 .macro CALL_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
 	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE_2 __stringify(call *\reg),				\
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg),	\
 		__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
-		__stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD
+		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD
 #else
 	call	*\reg
 #endif
 .endm
 
-/* This clobbers the BX register */
-.macro FILL_RETURN_BUFFER nr:req ftr:req
+ /*
+  * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
+  * monstrosity above, manually.
+  */
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
 #ifdef CONFIG_RETPOLINE
-	ALTERNATIVE "", "call __clear_rsb", \ftr
+	ANNOTATE_NOSPEC_ALTERNATIVE
+	ALTERNATIVE "jmp .Lskip_rsb_\@",				\
+		__stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP))	\
+		\ftr
+.Lskip_rsb_\@:
 #endif
 .endm
 
@@ -93,6 +156,12 @@
 	".long 999b - .\n\t"					\
 	".popsection\n\t"
 
+#define ANNOTATE_RETPOLINE_SAFE					\
+	"999:\n\t"						\
+	".pushsection .discard.retpoline_safe\n\t"		\
+	_ASM_PTR " 999b\n\t"					\
+	".popsection\n\t"
+
 #if defined(CONFIG_X86_64) && defined(RETPOLINE)
 
 /*
@@ -102,6 +171,7 @@
 # define CALL_NOSPEC						\
 	ANNOTATE_NOSPEC_ALTERNATIVE				\
 	ALTERNATIVE(						\
+	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
 	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
 	X86_FEATURE_RETPOLINE)
@@ -113,7 +183,10 @@
  * otherwise we'll run out of registers. We don't care about CET
  * here, anyway.
  */
-# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n",	\
+# define CALL_NOSPEC						\
+	ALTERNATIVE(						\
+	ANNOTATE_RETPOLINE_SAFE					\
+	"call *%[thunk_target]\n",				\
 	"       jmp    904f;\n"					\
 	"       .align 16\n"					\
 	"901:	call   903f;\n"					\
@@ -156,26 +229,54 @@ extern char __indirect_thunk_end[];
 static inline void vmexit_fill_RSB(void)
 {
 #ifdef CONFIG_RETPOLINE
-	alternative_input("",
-			  "call __fill_rsb",
-			  X86_FEATURE_RETPOLINE,
-			  ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory"));
+	unsigned long loops;
+
+	asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
+		      ALTERNATIVE("jmp 910f",
+				  __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
+				  X86_FEATURE_RETPOLINE)
+		      "910:"
+		      : "=r" (loops), ASM_CALL_CONSTRAINT
+		      : : "memory" );
 #endif
 }
 
+#define alternative_msr_write(_msr, _val, _feature)		\
+	asm volatile(ALTERNATIVE("",				\
+				 "movl %[msr], %%ecx\n\t"	\
+				 "movl %[val], %%eax\n\t"	\
+				 "movl $0, %%edx\n\t"		\
+				 "wrmsr",			\
+				 _feature)			\
+		     : : [msr] "i" (_msr), [val] "i" (_val)	\
+		     : "eax", "ecx", "edx", "memory")
+
 static inline void indirect_branch_prediction_barrier(void)
 {
-	asm volatile(ALTERNATIVE("",
-				 "movl %[msr], %%ecx\n\t"
-				 "movl %[val], %%eax\n\t"
-				 "movl $0, %%edx\n\t"
-				 "wrmsr",
-				 X86_FEATURE_USE_IBPB)
-		     : : [msr] "i" (MSR_IA32_PRED_CMD),
-			 [val] "i" (PRED_CMD_IBPB)
-		     : "eax", "ecx", "edx", "memory");
+	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
+			      X86_FEATURE_USE_IBPB);
 }
 
+/*
+ * With retpoline, we must use IBRS to restrict branch prediction
+ * before calling into firmware.
+ *
+ * (Implemented as CPP macros due to header hell.)
+ */
+#define firmware_restrict_branch_speculation_start()			\
+do {									\
+	preempt_disable();						\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,	\
+			      X86_FEATURE_USE_IBRS_FW);			\
+} while (0)
+
+#define firmware_restrict_branch_speculation_end()			\
+do {									\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,			\
+			      X86_FEATURE_USE_IBRS_FW);			\
+	preempt_enable();						\
+} while (0)
+
 #endif /* __ASSEMBLY__ */
 
 /*
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 554841fab717..c83a2f418cea 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -7,6 +7,7 @@
 #ifdef CONFIG_PARAVIRT
 #include <asm/pgtable_types.h>
 #include <asm/asm.h>
+#include <asm/nospec-branch.h>
 
 #include <asm/paravirt_types.h>
 
@@ -879,23 +880,27 @@ extern void default_banner(void);
 
 #define INTERRUPT_RETURN						\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,	\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);)
 
 #define DISABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
 		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);	\
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #define ENABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
 		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #ifdef CONFIG_X86_32
 #define GET_CR0_INTO_EAX				\
 	push %ecx; push %edx;				\
+	ANNOTATE_RETPOLINE_SAFE;				\
 	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
 	pop %edx; pop %ecx
 #else	/* !CONFIG_X86_32 */
@@ -917,21 +922,25 @@ extern void default_banner(void);
  */
 #define SWAPGS								\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
-		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs)		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);		\
 		 )
 
 #define GET_CR2_INTO_RAX				\
-	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2)
+	ANNOTATE_RETPOLINE_SAFE;				\
+	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);
 
 #define USERGS_SYSRET64							\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
 		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);)
 
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(clobbers)                                        \
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
 		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
+		  ANNOTATE_RETPOLINE_SAFE;				    \
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl);    \
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 #endif
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index f624f1f10316..180bc0bff0fb 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -43,6 +43,7 @@
 #include <asm/desc_defs.h>
 #include <asm/kmap_types.h>
 #include <asm/pgtable_types.h>
+#include <asm/nospec-branch.h>
 
 struct page;
 struct thread_struct;
@@ -392,7 +393,9 @@ int paravirt_disable_iospace(void);
  * offset into the paravirt_patch_template structure, and can therefore be
  * freely converted back into a structure offset.
  */
-#define PARAVIRT_CALL	"call *%c[paravirt_opptr];"
+#define PARAVIRT_CALL					\
+	ANNOTATE_RETPOLINE_SAFE				\
+	"call *%c[paravirt_opptr];"
 
 /*
  * These macros are intended to wrap calls through one of the paravirt
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ba3c523aaf16..a06b07399d17 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -526,7 +526,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr,
 {
 	bool oldbit;
 
-	asm volatile("bt "__percpu_arg(2)",%1"
+	asm volatile("btl "__percpu_arg(2)",%1"
 			CC_SET(c)
 			: CC_OUT(c) (oldbit)
 			: "m" (*(unsigned long __percpu *)addr), "Ir" (nr));
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 63c2552b6b65..b444d83cfc95 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -350,14 +350,14 @@ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
 {
 	pmdval_t v = native_pmd_val(pmd);
 
-	return __pmd(v | set);
+	return native_make_pmd(v | set);
 }
 
 static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
 {
 	pmdval_t v = native_pmd_val(pmd);
 
-	return __pmd(v & ~clear);
+	return native_make_pmd(v & ~clear);
 }
 
 static inline pmd_t pmd_mkold(pmd_t pmd)
@@ -409,14 +409,14 @@ static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
 {
 	pudval_t v = native_pud_val(pud);
 
-	return __pud(v | set);
+	return native_make_pud(v | set);
 }
 
 static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
 {
 	pudval_t v = native_pud_val(pud);
 
-	return __pud(v & ~clear);
+	return native_make_pud(v & ~clear);
 }
 
 static inline pud_t pud_mkold(pud_t pud)
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index e55466760ff8..b3ec519e3982 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -32,6 +32,7 @@ extern pmd_t initial_pg_pmd[];
 static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
 void paging_init(void);
+void sync_initial_page_table(void);
 
 /*
  * Define this if things work differently on an i386 and an i486:
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 81462e9a34f6..1149d2112b2e 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -28,6 +28,7 @@ extern pgd_t init_top_pgt[];
 #define swapper_pg_dir init_top_pgt
 
 extern void paging_init(void);
+static inline void sync_initial_page_table(void) { }
 
 #define pte_ERROR(e)					\
 	pr_err("%s:%d: bad pte %p(%016lx)\n",		\
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 3696398a9475..acfe755562a6 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -174,7 +174,6 @@ enum page_cache_mode {
 #define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
 #define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
 #define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_NOCACHE)
-#define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
 #define __PAGE_KERNEL_VVAR		(__PAGE_KERNEL_RO | _PAGE_USER)
 #define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
@@ -206,7 +205,6 @@ enum page_cache_mode {
 #define PAGE_KERNEL_NOCACHE	__pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC)
 #define PAGE_KERNEL_LARGE	__pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC)
 #define PAGE_KERNEL_LARGE_EXEC	__pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC)
-#define PAGE_KERNEL_VSYSCALL	__pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC)
 #define PAGE_KERNEL_VVAR	__pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC)
 
 #define PAGE_KERNEL_IO		__pgprot(__PAGE_KERNEL_IO)
@@ -323,6 +321,11 @@ static inline pudval_t native_pud_val(pud_t pud)
 #else
 #include <asm-generic/pgtable-nopud.h>
 
+static inline pud_t native_make_pud(pudval_t val)
+{
+	return (pud_t) { .p4d.pgd = native_make_pgd(val) };
+}
+
 static inline pudval_t native_pud_val(pud_t pud)
 {
 	return native_pgd_val(pud.p4d.pgd);
@@ -344,6 +347,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 #else
 #include <asm-generic/pgtable-nopmd.h>
 
+static inline pmd_t native_make_pmd(pmdval_t val)
+{
+	return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) };
+}
+
 static inline pmdval_t native_pmd_val(pmd_t pmd)
 {
 	return native_pgd_val(pmd.pud.p4d.pgd);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 1bd9ed87606f..b0ccd4847a58 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -977,4 +977,5 @@ bool xen_set_default_idle(void);
 
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
+void microcode_check(void);
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 4e44250e7d0d..4cf11d88d3b3 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -17,7 +17,7 @@
 #define _REFCOUNT_EXCEPTION				\
 	".pushsection .text..refcount\n"		\
 	"111:\tlea %[counter], %%" _ASM_CX "\n"		\
-	"112:\t" ASM_UD0 "\n"				\
+	"112:\t" ASM_UD2 "\n"				\
 	ASM_UNREACHABLE					\
 	".popsection\n"					\
 	"113:\n"					\
@@ -67,13 +67,13 @@ static __always_inline __must_check
 bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 {
 	GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
-				  r->refs.counter, "er", i, "%0", e);
+				  r->refs.counter, "er", i, "%0", e, "cx");
 }
 
 static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
 	GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
-				 r->refs.counter, "%0", e);
+				 r->refs.counter, "%0", e, "cx");
 }
 
 static __always_inline __must_check
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index f91c365e57c3..4914a3e7c803 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -2,8 +2,7 @@
 #ifndef _ASM_X86_RMWcc
 #define _ASM_X86_RMWcc
 
-#define __CLOBBERS_MEM		"memory"
-#define __CLOBBERS_MEM_CC_CX	"memory", "cc", "cx"
+#define __CLOBBERS_MEM(clb...)	"memory", ## clb
 
 #if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
 
@@ -40,18 +39,19 @@ do {									\
 #endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
 
 #define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
-	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM)
+	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
 
-#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc)		\
+#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\
 	__GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc,			\
-		    __CLOBBERS_MEM_CC_CX)
+		    __CLOBBERS_MEM(clobbers))
 
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc,		\
-		    __CLOBBERS_MEM, vcon (val))
+		    __CLOBBERS_MEM(), vcon (val))
 
-#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc)	\
+#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc,	\
+				  clobbers...)				\
 	__GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc,	\
-		    __CLOBBERS_MEM_CC_CX, vcon (val))
+		    __CLOBBERS_MEM(clobbers), vcon (val))
 
 #endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index d6baf23782bc..5c019d23d06b 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -10,6 +10,7 @@ extern struct exception_table_entry __stop___ex_table[];
 
 #if defined(CONFIG_X86_64)
 extern char __end_rodata_hpage_align[];
+extern char __entry_trampoline_start[], __entry_trampoline_end[];
 #endif
 
 #endif	/* _ASM_X86_SECTIONS_H */
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 82c34ee25a65..906794aa034e 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -20,31 +20,43 @@
 #include <asm/ia32.h>
 
 /* ia32/sys_ia32.c */
-asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long);
-asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long);
+asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long,
+					  unsigned long);
+asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long,
+					   unsigned long);
 
-asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *);
-asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *);
-asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *);
-asmlinkage long sys32_fstatat(unsigned int, const char __user *,
+asmlinkage long compat_sys_x86_stat64(const char __user *,
+				      struct stat64 __user *);
+asmlinkage long compat_sys_x86_lstat64(const char __user *,
+				       struct stat64 __user *);
+asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *);
+asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *,
 			      struct stat64 __user *, int);
 struct mmap_arg_struct32;
-asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *);
+asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *);
 
-asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int);
+asmlinkage long compat_sys_x86_waitpid(compat_pid_t, unsigned int __user *,
+				       int);
 
-asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32);
-asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32);
+asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32,
+				     u32);
+asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32,
+				      u32, u32);
 
-long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int);
-long sys32_vm86_warning(void);
+asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32,
+					    int);
 
-asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t);
-asmlinkage long sys32_sync_file_range(int, unsigned, unsigned,
-				      unsigned, unsigned, int);
-asmlinkage long sys32_fadvise64(int, unsigned, unsigned, size_t, int);
-asmlinkage long sys32_fallocate(int, int, unsigned,
-				unsigned, unsigned, unsigned);
+asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int,
+					    size_t);
+asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int,
+					       unsigned int, unsigned int,
+					       int);
+asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int,
+					 size_t, int);
+asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int,
+					 unsigned int, unsigned int);
+asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *,
+				     unsigned long, int __user *);
 
 /* ia32/ia32_signal.c */
 asmlinkage long sys32_sigreturn(void);
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 7a2ade4aa235..6cfa9c8cb7d6 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -26,6 +26,7 @@
 #define KVM_FEATURE_PV_EOI		6
 #define KVM_FEATURE_PV_UNHALT		7
 #define KVM_FEATURE_PV_TLB_FLUSH	9
+#define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 91723461dc1f..435db58a7bad 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -30,6 +30,7 @@ struct mce {
 	__u64 synd;	/* MCA_SYND MSR: only valid on SMCA systems */
 	__u64 ipid;	/* MCA_IPID MSR: only valid on SMCA systems */
 	__u64 ppin;	/* Protected Processor Inventory Number */
+	__u32 microcode;/* Microcode revision */
 };
 
 #define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 8ad2e410974f..7c5538769f7e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1603,7 +1603,7 @@ static void __init delay_with_tsc(void)
 	do {
 		rep_nop();
 		now = rdtsc();
-	} while ((now - start) < 40000000000UL / HZ &&
+	} while ((now - start) < 40000000000ULL / HZ &&
 		time_before_eq(jiffies, end));
 }
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d71c8b54b696..bfca937bdcc3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -300,6 +300,15 @@ retpoline_auto:
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
 	}
+
+	/*
+	 * Retpoline means the kernel is safe because it has no indirect
+	 * branches. But firmware isn't, so use IBRS to protect that.
+	 */
+	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
+		pr_info("Enabling Restricted Speculation for firmware calls\n");
+	}
 }
 
 #undef pr_fmt
@@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");
 
-	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+	return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
 		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
 		       spectre_v2_module_string());
 }
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 824aee0117bb..348cf4821240 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1749,3 +1749,33 @@ static int __init init_cpu_syscore(void)
 	return 0;
 }
 core_initcall(init_cpu_syscore);
+
+/*
+ * The microcode loader calls this upon late microcode load to recheck features,
+ * only when microcode has been updated. Caller holds microcode_mutex and CPU
+ * hotplug lock.
+ */
+void microcode_check(void)
+{
+	struct cpuinfo_x86 info;
+
+	perf_check_microcode();
+
+	/* Reload CPUID max function as it might've changed. */
+	info.cpuid_level = cpuid_eax(0);
+
+	/*
+	 * Copy all capability leafs to pick up the synthetic ones so that
+	 * memcmp() below doesn't fail on that. The ones coming from CPUID will
+	 * get overwritten in get_cpu_cap().
+	 */
+	memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability));
+
+	get_cpu_cap(&info);
+
+	if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)))
+		return;
+
+	pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
+	pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
+}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d19e903214b4..c3af167d0a70 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -105,7 +105,7 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
 /*
  * Early microcode releases for the Spectre v2 mitigation were broken.
  * Information taken from;
- * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf
+ * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-update-guidance.pdf
  * - https://kb.vmware.com/s/article/52345
  * - Microcode revisions observed in the wild
  * - Release note from 20180108 microcode release
@@ -123,7 +123,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = {
 	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x80 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
-	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
 	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },
@@ -144,6 +143,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 {
 	int i;
 
+	/*
+	 * We know that the hypervisor lie to us on the microcode version so
+	 * we may as well hope that it is running the correct version.
+	 */
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return false;
+
 	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
 		if (c->x86_model == spectre_bad_microcodes[i].model &&
 		    c->x86_stepping == spectre_bad_microcodes[i].stepping)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8ff94d1e2dce..466f47301334 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -56,6 +56,9 @@
 
 static DEFINE_MUTEX(mce_log_mutex);
 
+/* sysfs synchronization */
+static DEFINE_MUTEX(mce_sysfs_mutex);
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
 
@@ -130,6 +133,8 @@ void mce_setup(struct mce *m)
 
 	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
 		rdmsrl(MSR_PPIN, m->ppin);
+
+	m->microcode = boot_cpu_data.microcode;
 }
 
 DEFINE_PER_CPU(struct mce, injectm);
@@ -262,7 +267,7 @@ static void __print_mce(struct mce *m)
 	 */
 	pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
 		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
-		cpu_data(m->extcpu).microcode);
+		m->microcode);
 }
 
 static void print_mce(struct mce *m)
@@ -2086,6 +2091,7 @@ static ssize_t set_ignore_ce(struct device *s,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.ignore_ce ^ !!new) {
 		if (new) {
 			/* disable ce features */
@@ -2098,6 +2104,8 @@ static ssize_t set_ignore_ce(struct device *s,
 			on_each_cpu(mce_enable_ce, (void *)1, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 
@@ -2110,6 +2118,7 @@ static ssize_t set_cmci_disabled(struct device *s,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.cmci_disabled ^ !!new) {
 		if (new) {
 			/* disable cmci */
@@ -2121,6 +2130,8 @@ static ssize_t set_cmci_disabled(struct device *s,
 			on_each_cpu(mce_enable_ce, NULL, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 
@@ -2128,8 +2139,19 @@ static ssize_t store_int_with_restart(struct device *s,
 				      struct device_attribute *attr,
 				      const char *buf, size_t size)
 {
-	ssize_t ret = device_store_int(s, attr, buf, size);
+	unsigned long old_check_interval = check_interval;
+	ssize_t ret = device_store_ulong(s, attr, buf, size);
+
+	if (check_interval == old_check_interval)
+		return ret;
+
+	if (check_interval < 1)
+		check_interval = 1;
+
+	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return ret;
 }
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 330b8462d426..48179928ff38 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -339,7 +339,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 		return -EINVAL;
 
 	ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
-	if (ret != UCODE_OK)
+	if (ret > UCODE_UPDATED)
 		return -EINVAL;
 
 	return 0;
@@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 	return patch_size;
 }
 
-static int apply_microcode_amd(int cpu)
+static enum ucode_state apply_microcode_amd(int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_amd *mc_amd;
@@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu)
 
 	p = find_patch(cpu);
 	if (!p)
-		return 0;
+		return UCODE_NFOUND;
 
 	mc_amd  = p->data;
 	uci->mc = p->data;
@@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu)
 	if (rev >= mc_amd->hdr.patch_id) {
 		c->microcode = rev;
 		uci->cpu_sig.rev = rev;
-		return 0;
+		return UCODE_OK;
 	}
 
 	if (__apply_microcode_amd(mc_amd)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
-		return -1;
+		return UCODE_ERROR;
 	}
 	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
 		mc_amd->hdr.patch_id);
@@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu)
 	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
 	c->microcode = mc_amd->hdr.patch_id;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static int install_equiv_cpu_table(const u8 *buf)
@@ -683,27 +683,35 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 static enum ucode_state
 load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 {
+	struct ucode_patch *p;
 	enum ucode_state ret;
 
 	/* free old equiv table */
 	free_equiv_cpu_table();
 
 	ret = __load_microcode_amd(family, data, size);
-
-	if (ret != UCODE_OK)
+	if (ret != UCODE_OK) {
 		cleanup();
+		return ret;
+	}
 
-#ifdef CONFIG_X86_32
-	/* save BSP's matching patch for early load */
-	if (save) {
-		struct ucode_patch *p = find_patch(0);
-		if (p) {
-			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
-			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
-							       PATCH_MAX_SIZE));
-		}
+	p = find_patch(0);
+	if (!p) {
+		return ret;
+	} else {
+		if (boot_cpu_data.microcode == p->patch_id)
+			return ret;
+
+		ret = UCODE_NEW;
 	}
-#endif
+
+	/* save BSP's matching patch for early load */
+	if (!save)
+		return ret;
+
+	memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
+	memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE));
+
 	return ret;
 }
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 319dd65f98a2..10c4fc2c91f8 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -22,13 +22,16 @@
 #define pr_fmt(fmt) "microcode: " fmt
 
 #include <linux/platform_device.h>
+#include <linux/stop_machine.h>
 #include <linux/syscore_ops.h>
 #include <linux/miscdevice.h>
 #include <linux/capability.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
+#include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/cpu.h>
+#include <linux/nmi.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 
@@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
+/*
+ * Serialize late loading so that CPUs get updated one-by-one.
+ */
+static DEFINE_SPINLOCK(update_lock);
+
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu)
 	return ret;
 }
 
-struct apply_microcode_ctx {
-	int err;
-};
-
 static void apply_microcode_local(void *arg)
 {
-	struct apply_microcode_ctx *ctx = arg;
+	enum ucode_state *err = arg;
 
-	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+	*err = microcode_ops->apply_microcode(smp_processor_id());
 }
 
 static int apply_microcode_on_target(int cpu)
 {
-	struct apply_microcode_ctx ctx = { .err = 0 };
+	enum ucode_state err;
 	int ret;
 
-	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
-	if (!ret)
-		ret = ctx.err;
-
+	ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1);
+	if (!ret) {
+		if (err == UCODE_ERROR)
+			ret = 1;
+	}
 	return ret;
 }
 
@@ -489,31 +494,124 @@ static void __exit microcode_dev_exit(void)
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
-static int reload_for_cpu(int cpu)
+/*
+ * Late loading dance. Why the heavy-handed stomp_machine effort?
+ *
+ * - HT siblings must be idle and not execute other code while the other sibling
+ *   is loading microcode in order to avoid any negative interactions caused by
+ *   the loading.
+ *
+ * - In addition, microcode update on the cores must be serialized until this
+ *   requirement can be relaxed in the future. Right now, this is conservative
+ *   and good.
+ */
+#define SPINUNIT 100 /* 100 nsec */
+
+static int check_online_cpus(void)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	enum ucode_state ustate;
-	int err = 0;
+	if (num_online_cpus() == num_present_cpus())
+		return 0;
 
-	if (!uci->valid)
-		return err;
+	pr_err("Not all CPUs online, aborting microcode update.\n");
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
-	if (ustate == UCODE_OK)
-		apply_microcode_on_target(cpu);
-	else
-		if (ustate == UCODE_ERROR)
-			err = -EINVAL;
-	return err;
+	return -EINVAL;
+}
+
+static atomic_t late_cpus_in;
+static atomic_t late_cpus_out;
+
+static int __wait_for_cpus(atomic_t *t, long long timeout)
+{
+	int all_cpus = num_online_cpus();
+
+	atomic_inc(t);
+
+	while (atomic_read(t) < all_cpus) {
+		if (timeout < SPINUNIT) {
+			pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+				all_cpus - atomic_read(t));
+			return 1;
+		}
+
+		ndelay(SPINUNIT);
+		timeout -= SPINUNIT;
+
+		touch_nmi_watchdog();
+	}
+	return 0;
+}
+
+/*
+ * Returns:
+ * < 0 - on error
+ *   0 - no update done
+ *   1 - microcode was updated
+ */
+static int __reload_late(void *info)
+{
+	int cpu = smp_processor_id();
+	enum ucode_state err;
+	int ret = 0;
+
+	/*
+	 * Wait for all CPUs to arrive. A load will not be attempted unless all
+	 * CPUs show up.
+	 * */
+	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
+		return -1;
+
+	spin_lock(&update_lock);
+	apply_microcode_local(&err);
+	spin_unlock(&update_lock);
+
+	if (err > UCODE_NFOUND) {
+		pr_warn("Error reloading microcode on CPU %d\n", cpu);
+		return -1;
+	/* siblings return UCODE_OK because their engine got updated already */
+	} else if (err == UCODE_UPDATED || err == UCODE_OK) {
+		ret = 1;
+	} else {
+		return ret;
+	}
+
+	/*
+	 * Increase the wait timeout to a safe value here since we're
+	 * serializing the microcode update and that could take a while on a
+	 * large number of CPUs. And that is fine as the *actual* timeout will
+	 * be determined by the last CPU finished updating and thus cut short.
+	 */
+	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
+		panic("Timeout during microcode update!\n");
+
+	return ret;
+}
+
+/*
+ * Reload microcode late on all CPUs. Wait for a sec until they
+ * all gather together.
+ */
+static int microcode_reload_late(void)
+{
+	int ret;
+
+	atomic_set(&late_cpus_in,  0);
+	atomic_set(&late_cpus_out, 0);
+
+	ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+	if (ret > 0)
+		microcode_check();
+
+	return ret;
 }
 
 static ssize_t reload_store(struct device *dev,
 			    struct device_attribute *attr,
 			    const char *buf, size_t size)
 {
+	enum ucode_state tmp_ret = UCODE_OK;
+	int bsp = boot_cpu_data.cpu_index;
 	unsigned long val;
-	int cpu;
-	ssize_t ret = 0, tmp_ret;
+	ssize_t ret = 0;
 
 	ret = kstrtoul(buf, 0, &val);
 	if (ret)
@@ -522,23 +620,24 @@ static ssize_t reload_store(struct device *dev,
 	if (val != 1)
 		return size;
 
+	tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
+	if (tmp_ret != UCODE_NEW)
+		return size;
+
 	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-	for_each_online_cpu(cpu) {
-		tmp_ret = reload_for_cpu(cpu);
-		if (tmp_ret != 0)
-			pr_warn("Error reloading microcode on CPU %d\n", cpu);
 
-		/* save retval of the first encountered reload error */
-		if (!ret)
-			ret = tmp_ret;
-	}
-	if (!ret)
-		perf_check_microcode();
+	ret = check_online_cpus();
+	if (ret)
+		goto put;
+
+	mutex_lock(&microcode_mutex);
+	ret = microcode_reload_late();
 	mutex_unlock(&microcode_mutex);
+
+put:
 	put_online_cpus();
 
-	if (!ret)
+	if (ret >= 0)
 		ret = size;
 
 	return ret;
@@ -606,10 +705,8 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
 	if (system_state != SYSTEM_RUNNING)
 		return UCODE_NFOUND;
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev,
-						     refresh_fw);
-
-	if (ustate == UCODE_OK) {
+	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, refresh_fw);
+	if (ustate == UCODE_NEW) {
 		pr_debug("CPU%d updated upon init\n", cpu);
 		apply_microcode_on_target(cpu);
 	}
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a15db2b4e0d6..32b8e5724f96 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (!mc)
 		return 0;
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -772,27 +789,44 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 	return 0;
 }
 
-static int apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_intel(int cpu)
 {
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_intel *mc;
-	struct ucode_cpu_info *uci;
-	struct cpuinfo_x86 *c;
 	static int prev_rev;
 	u32 rev;
 
 	/* We should bind the task to the CPU */
 	if (WARN_ON(raw_smp_processor_id() != cpu))
-		return -1;
+		return UCODE_ERROR;
 
-	uci = ucode_cpu_info + cpu;
-	mc = uci->mc;
+	/* Look for a newer patch in our cache: */
+	mc = find_patch(uci);
 	if (!mc) {
-		/* Look for a newer patch in our cache: */
-		mc = find_patch(uci);
+		mc = uci->mc;
 		if (!mc)
-			return 0;
+			return UCODE_NFOUND;
 	}
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		c->microcode = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -801,7 +835,7 @@ static int apply_microcode_intel(int cpu)
 	if (rev != mc->hdr.rev) {
 		pr_err("CPU%d update to revision 0x%x failed\n",
 		       cpu, mc->hdr.rev);
-		return -1;
+		return UCODE_ERROR;
 	}
 
 	if (rev != prev_rev) {
@@ -813,12 +847,10 @@ static int apply_microcode_intel(int cpu)
 		prev_rev = rev;
 	}
 
-	c = &cpu_data(cpu);
-
 	uci->cpu_sig.rev = rev;
 	c->microcode = rev;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
@@ -830,6 +862,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	unsigned int leftover = size;
 	unsigned int curr_mc_size = 0, new_mc_size = 0;
 	unsigned int csig, cpf;
+	enum ucode_state ret = UCODE_OK;
 
 	while (leftover) {
 		struct microcode_header_intel mc_header;
@@ -871,6 +904,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			new_mc  = mc;
 			new_mc_size = mc_size;
 			mc = NULL;	/* trigger new vmalloc */
+			ret = UCODE_NEW;
 		}
 
 		ucode_ptr += mc_size;
@@ -900,7 +934,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
 		 cpu, new_rev, uci->cpu_sig.rev);
 
-	return UCODE_OK;
+	return ret;
 }
 
 static int get_ucode_fw(void *to, const void *from, size_t n)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 04a625f0fcda..0f545b3cf926 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -23,6 +23,7 @@
 #include <asm/nops.h>
 #include "../entry/calling.h"
 #include <asm/export.h>
+#include <asm/nospec-branch.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -134,6 +135,7 @@ ENTRY(secondary_startup_64)
 
 	/* Ensure I am executing from virtual addresses */
 	movq	$1f, %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp	*%rax
 1:
 	UNWIND_HINT_EMPTY
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 2f723301eb58..38deafebb21b 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -23,7 +23,7 @@
 /*
  * this changes the io permissions bitmap in the current task.
  */
-asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
 {
 	struct thread_struct *t = &current->thread;
 	struct tss_struct *tss;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index bd36f3c33cd0..0715f827607c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler);
 
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
+	bool is_in_entry_trampoline_section = false;
+
+#ifdef CONFIG_X86_64
+	is_in_entry_trampoline_section =
+		(addr >= (unsigned long)__entry_trampoline_start &&
+		 addr < (unsigned long)__entry_trampoline_end);
+#endif
 	return  (addr >= (unsigned long)__kprobes_text_start &&
 		 addr < (unsigned long)__kprobes_text_end) ||
 		(addr >= (unsigned long)__entry_text_start &&
-		 addr < (unsigned long)__entry_text_end);
+		 addr < (unsigned long)__entry_text_end) ||
+		is_in_entry_trampoline_section;
 }
 
 int __init arch_init_kprobes(void)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4e37d1a851a6..bc1a27280c4b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -49,7 +49,7 @@
 
 static int kvmapf = 1;
 
-static int parse_no_kvmapf(char *arg)
+static int __init parse_no_kvmapf(char *arg)
 {
         kvmapf = 0;
         return 0;
@@ -58,7 +58,7 @@ static int parse_no_kvmapf(char *arg)
 early_param("no-kvmapf", parse_no_kvmapf);
 
 static int steal_acc = 1;
-static int parse_no_stealacc(char *arg)
+static int __init parse_no_stealacc(char *arg)
 {
         steal_acc = 0;
         return 0;
@@ -67,7 +67,7 @@ static int parse_no_stealacc(char *arg)
 early_param("no-steal-acc", parse_no_stealacc);
 
 static int kvmclock_vsyscall = 1;
-static int parse_no_kvmclock_vsyscall(char *arg)
+static int __init parse_no_kvmclock_vsyscall(char *arg)
 {
         kvmclock_vsyscall = 0;
         return 0;
@@ -341,10 +341,10 @@ static void kvm_guest_cpu_init(void)
 #endif
 		pa |= KVM_ASYNC_PF_ENABLED;
 
-		/* Async page fault support for L1 hypervisor is optional */
-		if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN,
-			(pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0)
-			wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
+		if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
+			pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
+
+		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
 		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
@@ -545,7 +545,8 @@ static void __init kvm_guest_init(void)
 		pv_time_ops.steal_clock = kvm_steal_clock;
 	}
 
-	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH))
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
 		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -633,7 +634,8 @@ static __init int kvm_setup_pv_tlb_flush(void)
 {
 	int cpu;
 
-	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) {
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		for_each_possible_cpu(cpu) {
 			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
 				GFP_KERNEL, cpu_to_node(cpu));
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1ae67e982af7..4c616be28506 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1204,20 +1204,13 @@ void __init setup_arch(char **cmdline_p)
 
 	kasan_init();
 
-#ifdef CONFIG_X86_32
-	/* sync back kernel address range */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
 	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
+	 * Sync back kernel address range.
+	 *
+	 * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+	 * this call?
 	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+	sync_initial_page_table();
 
 	tboot_probe();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 497aa766fab3..ea554f812ee1 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void)
 	/* Setup cpu initialized, callin, callout masks */
 	setup_cpu_local_masks();
 
-#ifdef CONFIG_X86_32
 	/*
 	 * Sync back kernel address range again.  We already did this in
 	 * setup_arch(), but percpu data also needs to be available in
 	 * the smpboot asm.  We can't reliably pick up percpu mappings
 	 * using vmalloc_fault(), because exception dispatch needs
 	 * percpu data.
+	 *
+	 * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+	 * this call?
 	 */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
-	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
-	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+	sync_initial_page_table();
 }
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index ac057f9b0763..0d930d8987cc 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -43,6 +43,13 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int));
 #define CHECK_CSI_OFFSET(name)	  BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name))
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_code)  != 8);
+
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code)  != 8);
 	 /*
 	 * Ensure that the size of each si_field never changes.
 	 * If it does, it is a sign that the
@@ -63,36 +70,94 @@ static inline void signal_compat_build_tests(void)
 	CHECK_CSI_SIZE  (_kill, 2*sizeof(int));
 	CHECK_SI_SIZE   (_kill, 2*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10);
+
 	CHECK_CSI_OFFSET(_timer);
 	CHECK_CSI_SIZE  (_timer, 3*sizeof(int));
 	CHECK_SI_SIZE   (_timer, 6*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_tid)     != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_value)   != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid)     != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value)   != 0x14);
+
 	CHECK_CSI_OFFSET(_rt);
 	CHECK_CSI_SIZE  (_rt, 3*sizeof(int));
 	CHECK_SI_SIZE   (_rt, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)   != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid)   != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid)   != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid)   != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14);
+
 	CHECK_CSI_OFFSET(_sigchld);
 	CHECK_CSI_SIZE  (_sigchld, 5*sizeof(int));
 	CHECK_SI_SIZE   (_sigchld, 8*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)    != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid)    != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_utime)  != 0x20);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_stime)  != 0x28);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid)    != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid)    != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime)  != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime)  != 0x1C);
+
 #ifdef CONFIG_X86_X32_ABI
 	CHECK_CSI_OFFSET(_sigchld_x32);
 	CHECK_CSI_SIZE  (_sigchld_x32, 7*sizeof(int));
 	/* no _sigchld_x32 in the generic siginfo_t */
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime)  != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime)  != 0x20);
 #endif
 
 	CHECK_CSI_OFFSET(_sigfault);
 	CHECK_CSI_SIZE  (_sigfault, 4*sizeof(int));
 	CHECK_SI_SIZE   (_sigfault, 8*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14);
+
 	CHECK_CSI_OFFSET(_sigpoll);
 	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
 	CHECK_SI_SIZE   (_sigpoll, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_fd)     != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd)   != 0x10);
+
 	CHECK_CSI_OFFSET(_sigsys);
 	CHECK_CSI_SIZE  (_sigsys, 3*sizeof(int));
 	CHECK_SI_SIZE   (_sigsys, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_syscall)   != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_arch)      != 0x1C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall)   != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch)      != 0x14);
+
 	/* any new si_fields should be added here */
 }
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 1f9188f5357c..feb28fee6cea 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -5,7 +5,6 @@
 #include <asm/unwind.h>
 #include <asm/orc_types.h>
 #include <asm/orc_lookup.h>
-#include <asm/sections.h>
 
 #define orc_warn(fmt, ...) \
 	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
@@ -148,7 +147,7 @@ static struct orc_entry *orc_find(unsigned long ip)
 	}
 
 	/* vmlinux .init slow lookup: */
-	if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext)
+	if (init_kernel_text(ip))
 		return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
 				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
 
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 5edb27f1a2c4..9d0b5af7db91 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -727,7 +727,8 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
 	return;
 
 check_vip:
-	if (VEFLAGS & X86_EFLAGS_VIP) {
+	if ((VEFLAGS & (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) ==
+	    (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) {
 		save_v86_state(regs, VM86_STI);
 		return;
 	}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9b138a06c1a4..b854ebf5851b 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -118,9 +118,11 @@ SECTIONS
 
 #ifdef CONFIG_X86_64
 		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(__entry_trampoline_start) = .;
 		_entry_trampoline = .;
 		*(.entry_trampoline)
 		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(__entry_trampoline_end) = .;
 		ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
 #endif
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a0c5a69bc7c4..b671fc2d0422 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -607,7 +607,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			     (1 << KVM_FEATURE_PV_EOI) |
 			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
 			     (1 << KVM_FEATURE_PV_UNHALT) |
-			     (1 << KVM_FEATURE_PV_TLB_FLUSH);
+			     (1 << KVM_FEATURE_PV_TLB_FLUSH) |
+			     (1 << KVM_FEATURE_ASYNC_PF_VMEXIT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 924ac8ce9d50..391dda8d43b7 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2002,14 +2002,13 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 
 void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
-	struct kvm_lapic *apic;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 	int i;
 
-	apic_debug("%s\n", __func__);
+	if (!apic)
+		return;
 
-	ASSERT(vcpu);
-	apic = vcpu->arch.apic;
-	ASSERT(apic != NULL);
+	apic_debug("%s\n", __func__);
 
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
@@ -2165,7 +2164,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	 */
 	vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
 	static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
-	kvm_lapic_reset(vcpu, false);
 	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
 
 	return 0;
@@ -2569,7 +2567,6 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 
 	pe = xchg(&apic->pending_events, 0);
 	if (test_bit(KVM_APIC_INIT, &pe)) {
-		kvm_lapic_reset(vcpu, true);
 		kvm_vcpu_reset(vcpu, true);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
 			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 46ff304140c7..763bb3bade63 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2770,8 +2770,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	else
 		pte_access &= ~ACC_WRITE_MASK;
 
+	if (!kvm_is_mmio_pfn(pfn))
+		spte |= shadow_me_mask;
+
 	spte |= (u64)pfn << PAGE_SHIFT;
-	spte |= shadow_me_mask;
 
 	if (pte_access & ACC_WRITE_MASK) {
 
@@ -3029,7 +3031,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
 		return RET_PF_RETRY;
 	}
 
-	return -EFAULT;
+	return RET_PF_EMULATE;
 }
 
 static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b3e488a74828..be9c839e2c89 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -49,6 +49,7 @@
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
 #include <asm/irq_remapping.h>
+#include <asm/microcode.h>
 #include <asm/nospec-branch.h>
 
 #include <asm/virtext.h>
@@ -178,6 +179,8 @@ struct vcpu_svm {
 	uint64_t sysenter_eip;
 	uint64_t tsc_aux;
 
+	u64 msr_decfg;
+
 	u64 next_rip;
 
 	u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
@@ -300,6 +303,8 @@ module_param(vgif, int, 0444);
 static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
 module_param(sev, int, 0444);
 
+static u8 rsm_ins_bytes[] = "\x0f\xaa";
+
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
@@ -1383,6 +1388,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 	set_intercept(svm, INTERCEPT_SKINIT);
 	set_intercept(svm, INTERCEPT_WBINVD);
 	set_intercept(svm, INTERCEPT_XSETBV);
+	set_intercept(svm, INTERCEPT_RSM);
 
 	if (!kvm_mwait_in_guest()) {
 		set_intercept(svm, INTERCEPT_MONITOR);
@@ -1902,6 +1908,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	u32 dummy;
 	u32 eax = 1;
 
+	vcpu->arch.microcode_version = 0x01000065;
 	svm->spec_ctrl = 0;
 
 	if (!init_event) {
@@ -3699,6 +3706,12 @@ static int emulate_on_interception(struct vcpu_svm *svm)
 	return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
 }
 
+static int rsm_interception(struct vcpu_svm *svm)
+{
+	return x86_emulate_instruction(&svm->vcpu, 0, 0,
+				       rsm_ins_bytes, 2) == EMULATE_DONE;
+}
+
 static int rdpmc_interception(struct vcpu_svm *svm)
 {
 	int err;
@@ -3860,6 +3873,22 @@ static int cr8_write_interception(struct vcpu_svm *svm)
 	return 0;
 }
 
+static int svm_get_msr_feature(struct kvm_msr_entry *msr)
+{
+	msr->data = 0;
+
+	switch (msr->index) {
+	case MSR_F10H_DECFG:
+		if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC))
+			msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE;
+		break;
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
 static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3935,9 +3964,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		msr_info->data = svm->spec_ctrl;
 		break;
-	case MSR_IA32_UCODE_REV:
-		msr_info->data = 0x01000065;
-		break;
 	case MSR_F15H_IC_CFG: {
 
 		int family, model;
@@ -3955,6 +3981,9 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			msr_info->data = 0x1E;
 		}
 		break;
+	case MSR_F10H_DECFG:
+		msr_info->data = svm->msr_decfg;
+		break;
 	default:
 		return kvm_get_msr_common(vcpu, msr_info);
 	}
@@ -4133,6 +4162,24 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
+	case MSR_F10H_DECFG: {
+		struct kvm_msr_entry msr_entry;
+
+		msr_entry.index = msr->index;
+		if (svm_get_msr_feature(&msr_entry))
+			return 1;
+
+		/* Check the supported bits */
+		if (data & ~msr_entry.data)
+			return 1;
+
+		/* Don't allow the guest to change a bit, #GP */
+		if (!msr->host_initiated && (data ^ msr_entry.data))
+			return 1;
+
+		svm->msr_decfg = data;
+		break;
+	}
 	case MSR_IA32_APICBASE:
 		if (kvm_vcpu_apicv_active(vcpu))
 			avic_update_vapic_bar(to_svm(vcpu), data);
@@ -4541,7 +4588,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_NPF]				= npf_interception,
-	[SVM_EXIT_RSM]                          = emulate_on_interception,
+	[SVM_EXIT_RSM]                          = rsm_interception,
 	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
 	[SVM_EXIT_AVIC_UNACCELERATED_ACCESS]	= avic_unaccelerated_access_interception,
 };
@@ -5355,7 +5402,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 * being speculatively taken.
 	 */
 	if (svm->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
 
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
@@ -5464,11 +5511,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
 	 * save it.
 	 */
-	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
-		rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
 	if (svm->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
@@ -6236,16 +6283,18 @@ e_free:
 
 static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
+	void __user *measure = (void __user *)(uintptr_t)argp->data;
 	struct kvm_sev_info *sev = &kvm->arch.sev_info;
 	struct sev_data_launch_measure *data;
 	struct kvm_sev_launch_measure params;
+	void __user *p = NULL;
 	void *blob = NULL;
 	int ret;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
-	if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+	if (copy_from_user(&params, measure, sizeof(params)))
 		return -EFAULT;
 
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
@@ -6256,17 +6305,13 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (!params.len)
 		goto cmd;
 
-	if (params.uaddr) {
+	p = (void __user *)(uintptr_t)params.uaddr;
+	if (p) {
 		if (params.len > SEV_FW_BLOB_MAX_SIZE) {
 			ret = -EINVAL;
 			goto e_free;
 		}
 
-		if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) {
-			ret = -EFAULT;
-			goto e_free;
-		}
-
 		ret = -ENOMEM;
 		blob = kmalloc(params.len, GFP_KERNEL);
 		if (!blob)
@@ -6290,13 +6335,13 @@ cmd:
 		goto e_free_blob;
 
 	if (blob) {
-		if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len))
+		if (copy_to_user(p, blob, params.len))
 			ret = -EFAULT;
 	}
 
 done:
 	params.len = data->len;
-	if (copy_to_user((void __user *)(uintptr_t)argp->data, &params, sizeof(params)))
+	if (copy_to_user(measure, &params, sizeof(params)))
 		ret = -EFAULT;
 e_free_blob:
 	kfree(blob);
@@ -6597,7 +6642,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	struct page **pages;
 	void *blob, *hdr;
 	unsigned long n;
-	int ret;
+	int ret, offset;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
@@ -6623,6 +6668,10 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (!data)
 		goto e_unpin_memory;
 
+	offset = params.guest_uaddr & (PAGE_SIZE - 1);
+	data->guest_address = __sme_page_pa(pages[0]) + offset;
+	data->guest_len = params.guest_len;
+
 	blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len);
 	if (IS_ERR(blob)) {
 		ret = PTR_ERR(blob);
@@ -6637,8 +6686,8 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		ret = PTR_ERR(hdr);
 		goto e_free_blob;
 	}
-	data->trans_address = __psp_pa(blob);
-	data->trans_len = params.trans_len;
+	data->hdr_address = __psp_pa(hdr);
+	data->hdr_len = params.hdr_len;
 
 	data->handle = sev->handle;
 	ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error);
@@ -6821,6 +6870,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.vcpu_unblocking = svm_vcpu_unblocking,
 
 	.update_bp_intercept = update_bp_intercept,
+	.get_msr_feature = svm_get_msr_feature,
 	.get_msr = svm_get_msr,
 	.set_msr = svm_set_msr,
 	.get_segment_base = svm_get_segment_base,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3dec126aa302..051dab74e4e9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,6 +51,7 @@
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/mmu_context.h>
+#include <asm/microcode.h>
 #include <asm/nospec-branch.h>
 
 #include "trace.h"
@@ -3226,6 +3227,11 @@ static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu,
 	return !(val & ~valid_bits);
 }
 
+static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
+{
+	return 1;
+}
+
 /*
  * Reads an msr value (of 'msr_index') into 'pdata'.
  * Returns 0 on success, non-0 otherwise.
@@ -4485,7 +4491,8 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 			      SECONDARY_EXEC_DESC);
 		hw_cr4 &= ~X86_CR4_UMIP;
-	} else
+	} else if (!is_guest_mode(vcpu) ||
+	           !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
 		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
 				SECONDARY_EXEC_DESC);
 
@@ -5765,6 +5772,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx->rmode.vm86_active = 0;
 	vmx->spec_ctrl = 0;
 
+	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
 	kvm_set_cr8(vcpu, 0);
 
@@ -9452,7 +9460,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * being speculatively taken.
 	 */
 	if (vmx->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
@@ -9587,11 +9595,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
 	 * save it.
 	 */
-	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
-		rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
 	if (vmx->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
@@ -11199,7 +11207,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (ret)
 		return ret;
 
-	if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT)
+	/*
+	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
+	 * by event injection, halt vcpu.
+	 */
+	if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
+	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK))
 		return kvm_vcpu_halt(vcpu);
 
 	vmx->nested.nested_run_pending = 1;
@@ -12290,6 +12303,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.vcpu_put = vmx_vcpu_put,
 
 	.update_bp_intercept = update_exception_bitmap,
+	.get_msr_feature = vmx_get_msr_feature,
 	.get_msr = vmx_get_msr,
 	.set_msr = vmx_set_msr,
 	.get_segment_base = vmx_get_segment_base,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c8a0b545ac20..18b5ca7a3197 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1049,6 +1049,45 @@ static u32 emulated_msrs[] = {
 
 static unsigned num_emulated_msrs;
 
+/*
+ * List of msr numbers which are used to expose MSR-based features that
+ * can be used by a hypervisor to validate requested CPU features.
+ */
+static u32 msr_based_features[] = {
+	MSR_F10H_DECFG,
+	MSR_IA32_UCODE_REV,
+};
+
+static unsigned int num_msr_based_features;
+
+static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
+{
+	switch (msr->index) {
+	case MSR_IA32_UCODE_REV:
+		rdmsrl(msr->index, msr->data);
+		break;
+	default:
+		if (kvm_x86_ops->get_msr_feature(msr))
+			return 1;
+	}
+	return 0;
+}
+
+static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
+{
+	struct kvm_msr_entry msr;
+	int r;
+
+	msr.index = index;
+	r = kvm_get_msr_feature(&msr);
+	if (r)
+		return r;
+
+	*data = msr.data;
+
+	return 0;
+}
+
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & efer_reserved_bits)
@@ -2222,7 +2261,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 	switch (msr) {
 	case MSR_AMD64_NB_CFG:
-	case MSR_IA32_UCODE_REV:
 	case MSR_IA32_UCODE_WRITE:
 	case MSR_VM_HSAVE_PA:
 	case MSR_AMD64_PATCH_LOADER:
@@ -2230,6 +2268,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_AMD64_DC_CFG:
 		break;
 
+	case MSR_IA32_UCODE_REV:
+		if (msr_info->host_initiated)
+			vcpu->arch.microcode_version = data;
+		break;
 	case MSR_EFER:
 		return set_efer(vcpu, data);
 	case MSR_K7_HWCR:
@@ -2525,7 +2567,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = 0;
 		break;
 	case MSR_IA32_UCODE_REV:
-		msr_info->data = 0x100000000ULL;
+		msr_info->data = vcpu->arch.microcode_version;
 		break;
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
@@ -2680,13 +2722,11 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
 		    int (*do_msr)(struct kvm_vcpu *vcpu,
 				  unsigned index, u64 *data))
 {
-	int i, idx;
+	int i;
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	for (i = 0; i < msrs->nmsrs; ++i)
 		if (do_msr(vcpu, entries[i].index, &entries[i].data))
 			break;
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 	return i;
 }
@@ -2785,6 +2825,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SET_BOOT_CPU_ID:
  	case KVM_CAP_SPLIT_IRQCHIP:
 	case KVM_CAP_IMMEDIATE_EXIT:
+	case KVM_CAP_GET_MSR_FEATURES:
 		r = 1;
 		break;
 	case KVM_CAP_ADJUST_CLOCK:
@@ -2899,6 +2940,31 @@ long kvm_arch_dev_ioctl(struct file *filp,
 			goto out;
 		r = 0;
 		break;
+	case KVM_GET_MSR_FEATURE_INDEX_LIST: {
+		struct kvm_msr_list __user *user_msr_list = argp;
+		struct kvm_msr_list msr_list;
+		unsigned int n;
+
+		r = -EFAULT;
+		if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list)))
+			goto out;
+		n = msr_list.nmsrs;
+		msr_list.nmsrs = num_msr_based_features;
+		if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list)))
+			goto out;
+		r = -E2BIG;
+		if (n < msr_list.nmsrs)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(user_msr_list->indices, &msr_based_features,
+				 num_msr_based_features * sizeof(u32)))
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_GET_MSRS:
+		r = msr_io(NULL, argp, do_get_msr_feature, 1);
+		break;
 	}
 	default:
 		r = -EINVAL;
@@ -3636,12 +3702,18 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
-	case KVM_GET_MSRS:
+	case KVM_GET_MSRS: {
+		int idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = msr_io(vcpu, argp, do_get_msr, 1);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
-	case KVM_SET_MSRS:
+	}
+	case KVM_SET_MSRS: {
+		int idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = msr_io(vcpu, argp, do_set_msr, 0);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
+	}
 	case KVM_TPR_ACCESS_REPORTING: {
 		struct kvm_tpr_access_ctl tac;
 
@@ -4464,6 +4536,19 @@ static void kvm_init_msr_list(void)
 		j++;
 	}
 	num_emulated_msrs = j;
+
+	for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+		struct kvm_msr_entry msr;
+
+		msr.index = msr_based_features[i];
+		if (kvm_get_msr_feature(&msr))
+			continue;
+
+		if (j < i)
+			msr_based_features[j] = msr_based_features[i];
+		j++;
+	}
+	num_msr_based_features = j;
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -8017,6 +8102,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
+	kvm_lapic_reset(vcpu, init_event);
+
 	vcpu->arch.hflags = 0;
 
 	vcpu->arch.smi_pending = 0;
@@ -8460,10 +8547,8 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 			return r;
 	}
 
-	if (!size) {
-		r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
-		WARN_ON(r < 0);
-	}
+	if (!size)
+		vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
 
 	return 0;
 }
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 91e9700cc6dc..25a972c61b0a 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -28,7 +28,6 @@ lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
 lib-$(CONFIG_RETPOLINE) += retpoline.o
-OBJECT_FILES_NON_STANDARD_retpoline.o :=y
 
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 480edc3a5e03..c909961e678a 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -7,7 +7,6 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
-#include <asm/bitsperlong.h>
 
 .macro THUNK reg
 	.section .text.__x86.indirect_thunk
@@ -47,58 +46,3 @@ GENERATE_THUNK(r13)
 GENERATE_THUNK(r14)
 GENERATE_THUNK(r15)
 #endif
-
-/*
- * Fill the CPU return stack buffer.
- *
- * Each entry in the RSB, if used for a speculative 'ret', contains an
- * infinite 'pause; lfence; jmp' loop to capture speculative execution.
- *
- * This is required in various cases for retpoline and IBRS-based
- * mitigations for the Spectre variant 2 vulnerability. Sometimes to
- * eliminate potentially bogus entries from the RSB, and sometimes
- * purely to ensure that it doesn't get empty, which on some CPUs would
- * allow predictions from other (unwanted!) sources to be used.
- *
- * Google experimented with loop-unrolling and this turned out to be
- * the optimal version - two calls, each with their own speculation
- * trap should their return address end up getting used, in a loop.
- */
-.macro STUFF_RSB nr:req sp:req
-	mov	$(\nr / 2), %_ASM_BX
-	.align 16
-771:
-	call	772f
-773:						/* speculation trap */
-	pause
-	lfence
-	jmp	773b
-	.align 16
-772:
-	call	774f
-775:						/* speculation trap */
-	pause
-	lfence
-	jmp	775b
-	.align 16
-774:
-	dec	%_ASM_BX
-	jnz	771b
-	add	$((BITS_PER_LONG/8) * \nr), \sp
-.endm
-
-#define RSB_FILL_LOOPS		16	/* To avoid underflow */
-
-ENTRY(__fill_rsb)
-	STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP
-	ret
-END(__fill_rsb)
-EXPORT_SYMBOL_GPL(__fill_rsb)
-
-#define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
-
-ENTRY(__clear_rsb)
-	STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP
-	ret
-END(__clear_rsb)
-EXPORT_SYMBOL_GPL(__clear_rsb)
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index b9283cc27622..476d810639a8 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -163,4 +163,10 @@ void __init setup_cpu_entry_areas(void)
 
 	for_each_possible_cpu(cpu)
 		setup_cpu_entry_area(cpu);
+
+	/*
+	 * This is the last essential update to swapper_pgdir which needs
+	 * to be synchronized to initial_page_table on 32bit.
+	 */
+	sync_initial_page_table();
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 800de815519c..25a30b5d6582 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -330,7 +330,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
-	if (pmd_huge(*pmd_k))
+	if (pmd_large(*pmd_k))
 		return 0;
 
 	pte_k = pte_offset_kernel(pmd_k, address);
@@ -475,7 +475,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
 		BUG();
 
-	if (pud_huge(*pud))
+	if (pud_large(*pud))
 		return 0;
 
 	pmd = pmd_offset(pud, address);
@@ -486,7 +486,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
 		BUG();
 
-	if (pmd_huge(*pmd))
+	if (pmd_large(*pmd))
 		return 0;
 
 	pte_ref = pte_offset_kernel(pmd_ref, address);
@@ -1248,10 +1248,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	tsk = current;
 	mm = tsk->mm;
 
-	/*
-	 * Detect and handle instructions that would cause a page fault for
-	 * both a tracked kernel page and a userspace page.
-	 */
 	prefetchw(&mm->mmap_sem);
 
 	if (unlikely(kmmio_fault(regs, address)))
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 79cb066f40c0..396e1f0151ac 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -453,6 +453,21 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base)
 }
 #endif /* CONFIG_HIGHMEM */
 
+void __init sync_initial_page_table(void)
+{
+	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			KERNEL_PGD_PTRS);
+
+	/*
+	 * sync back low identity map too.  It is used for example
+	 * in the 32-bit EFI stub.
+	 */
+	clone_pgd_range(initial_page_table,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+}
+
 void __init native_pagetable_init(void)
 {
 	unsigned long pfn, va;
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 01f682cf77a8..40a6085063d6 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -15,6 +15,7 @@
 #include <asm/page.h>
 #include <asm/processor-flags.h>
 #include <asm/msr-index.h>
+#include <asm/nospec-branch.h>
 
 	.text
 	.code64
@@ -59,6 +60,7 @@ ENTRY(sme_encrypt_execute)
 	movq	%rax, %r8		/* Workarea encryption routine */
 	addq	$PAGE_SIZE, %r8		/* Workarea intermediate copy buffer */
 
+	ANNOTATE_RETPOLINE_SAFE
 	call	*%rax			/* Call the encryption routine */
 
 	pop	%r12
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index ce38f165489b..631507f0c198 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -332,7 +332,7 @@ static void __init pti_clone_user_shared(void)
 }
 
 /*
- * Clone the ESPFIX P4D into the user space visinble page table
+ * Clone the ESPFIX P4D into the user space visible page table
  */
 static void __init pti_setup_espfix64(void)
 {
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 2c67bae6bb53..fb1df9488e98 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -79,7 +79,7 @@ static void intel_mid_power_off(void)
 
 static void intel_mid_reboot(void)
 {
-	intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
+	intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
 }
 
 static unsigned long __init intel_mid_calibrate_tsc(void)
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index de53bd15df5a..24bb7598774e 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -102,7 +102,7 @@ ENTRY(startup_32)
 	 * don't we'll eventually crash trying to execute encrypted
 	 * instructions.
 	 */
-	bt	$TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags
+	btl	$TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags
 	jnc	.Ldone
 	movl	$MSR_K8_SYSCFG, %ecx
 	rdmsr
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index c047f42552e1..3c2c2530737e 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1376,8 +1376,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	if (!xen_initial_domain()) {
 		add_preferred_console("xenboot", 0, NULL);
-		add_preferred_console("tty", 0, NULL);
-		add_preferred_console("hvc", 0, NULL);
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
 	} else {
@@ -1410,6 +1408,10 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 		xen_boot_params_init_edd();
 	}
+
+	add_preferred_console("tty", 0, NULL);
+	add_preferred_console("hvc", 0, NULL);
+
 #ifdef CONFIG_PCI
 	/* PCI BIOS service won't work from a PV guest. */
 	pci_probe &= ~PCI_PROBE_BIOS;
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index d9f96cc5d743..1d83152c761b 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -1,12 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <linux/tick.h>
+#include <linux/percpu-defs.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <xen/grant_table.h>
 #include <xen/events.h>
 
+#include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 #include <asm/fixmap.h>
@@ -15,6 +18,8 @@
 #include "mmu.h"
 #include "pmu.h"
 
+static DEFINE_PER_CPU(u64, spec_ctrl);
+
 void xen_arch_pre_suspend(void)
 {
 	xen_save_time_memory_area();
@@ -35,6 +40,9 @@ void xen_arch_post_suspend(int cancelled)
 
 static void xen_vcpu_notify_restore(void *data)
 {
+	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+		wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
+
 	/* Boot processor notified via generic timekeeping_resume() */
 	if (smp_processor_id() == 0)
 		return;
@@ -44,7 +52,15 @@ static void xen_vcpu_notify_restore(void *data)
 
 static void xen_vcpu_notify_suspend(void *data)
 {
+	u64 tmp;
+
 	tick_suspend_local();
+
+	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) {
+		rdmsrl(MSR_IA32_SPEC_CTRL, tmp);
+		this_cpu_write(spec_ctrl, tmp);
+		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+	}
 }
 
 void xen_arch_resume(void)