Merge tag 'v4.4.177' into toradex_vf_4.4-nextColibri-VF_LXDE-Image_2.8b6.183-20190331

This is the 4.4.177 stable release

108 files changed, 1271 insertions, 625 deletions

diff --git a/arch/alpha/include/asm/irq.h b/arch/alpha/include/asm/irq.h
index 06377400dc09..469642801a68 100644
--- a/arch/alpha/include/asm/irq.h
+++ b/arch/alpha/include/asm/irq.h
@@ -55,15 +55,15 @@
 
 #elif defined(CONFIG_ALPHA_DP264) || \
       defined(CONFIG_ALPHA_LYNX)  || \
-      defined(CONFIG_ALPHA_SHARK) || \
-      defined(CONFIG_ALPHA_EIGER)
+      defined(CONFIG_ALPHA_SHARK)
 # define NR_IRQS	64
 
 #elif defined(CONFIG_ALPHA_TITAN)
 #define NR_IRQS		80
 
 #elif defined(CONFIG_ALPHA_RAWHIDE) || \
-	defined(CONFIG_ALPHA_TAKARA)
+      defined(CONFIG_ALPHA_TAKARA) || \
+      defined(CONFIG_ALPHA_EIGER)
 # define NR_IRQS	128
 
 #elif defined(CONFIG_ALPHA_WILDFIRE)
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 4a905bd667e2..0f68f0de9b5e 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -77,7 +77,7 @@ __load_new_mm_context(struct mm_struct *next_mm)
 /* Macro for exception fixup code to access integer registers.  */
 #define dpf_reg(r)							\
 	(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 :	\
-				 (r) <= 18 ? (r)+8 : (r)-10])
+				 (r) <= 18 ? (r)+10 : (r)-10])
 
 asmlinkage void
 do_page_fault(unsigned long address, unsigned long mmcsr,
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 0352fb8d21b9..9623ae002f5b 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -286,7 +286,7 @@ static inline __attribute__ ((const)) int __fls(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long word)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long word)
 {
 	if (!word)
 		return word;
@@ -346,9 +346,9 @@ static inline __attribute__ ((const)) int ffs(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
 {
-	int n;
+	unsigned long n;
 
 	asm volatile(
 	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index cb69299a492e..f120d823e8c2 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <asm/page.h>
+#include <asm/unaligned.h>
 
 #ifdef CONFIG_ISA_ARCV2
 #include <asm/barrier.h>
@@ -85,6 +86,42 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 	return w;
 }
 
+/*
+ * {read,write}s{b,w,l}() repeatedly access the same IO address in
+ * native endianness in 8-, 16-, 32-bit chunks {into,from} memory,
+ * @count times
+ */
+#define __raw_readsx(t,f) \
+static inline void __raw_reads##f(const volatile void __iomem *addr,	\
+				  void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			*buf++ = x;					\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			put_unaligned(x, buf++);			\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_readsb __raw_readsb
+__raw_readsx(8, b)
+#define __raw_readsw __raw_readsw
+__raw_readsx(16, w)
+#define __raw_readsl __raw_readsl
+__raw_readsx(32, l)
+
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
 {
@@ -117,6 +154,35 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 
 }
 
+#define __raw_writesx(t,f)						\
+static inline void __raw_writes##f(volatile void __iomem *addr, 	\
+				   const void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	const u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			__raw_write##f(*buf++, addr);			\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			__raw_write##f(get_unaligned(buf++), addr);	\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_writesb __raw_writesb
+__raw_writesx(8, b)
+#define __raw_writesw __raw_writesw
+__raw_writesx(16, w)
+#define __raw_writesl __raw_writesl
+__raw_writesx(32, l)
+
 /*
  * MMIO can also get buffered/optimized in micro-arch, so barriers needed
  * Based on ARM model for the typical use case
@@ -132,10 +198,16 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 #define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
 #define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
 #define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+#define readsb(p,d,l)		({ __raw_readsb(p,d,l); __iormb(); })
+#define readsw(p,d,l)		({ __raw_readsw(p,d,l); __iormb(); })
+#define readsl(p,d,l)		({ __raw_readsl(p,d,l); __iormb(); })
 
 #define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
 #define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
 #define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
+#define writesb(p,d,l)		({ __iowmb(); __raw_writesb(p,d,l); })
+#define writesw(p,d,l)		({ __iowmb(); __raw_writesw(p,d,l); })
+#define writesl(p,d,l)		({ __iowmb(); __raw_writesl(p,d,l); })
 
 /*
  * Relaxed API for drivers which can handle barrier ordering themselves
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 5f071762fb1c..6a2ae61748e4 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -103,7 +103,8 @@ static const char * const arc_pmu_ev_hw_map[] = {
 
 	/* counts condition */
 	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
+	/* All jump instructions that are taken */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
 	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
 #ifdef CONFIG_ISA_ARCV2
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index 57387b567f34..f077a419cb51 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -209,7 +209,7 @@ __arc_copy_from_user(void *to, const void __user *from, unsigned long n)
 		*/
 		  "=&r" (tmp), "+r" (to), "+r" (from)
 		:
-		: "lp_count", "lp_start", "lp_end", "memory");
+		: "lp_count", "memory");
 
 		return n;
 	}
@@ -438,7 +438,7 @@ __arc_copy_to_user(void __user *to, const void *from, unsigned long n)
 		 */
 		  "=&r" (tmp), "+r" (to), "+r" (from)
 		:
-		: "lp_count", "lp_start", "lp_end", "memory");
+		: "lp_count", "memory");
 
 		return n;
 	}
@@ -658,7 +658,7 @@ static inline unsigned long __arc_clear_user(void __user *to, unsigned long n)
 	"	.previous			\n"
 	: "+r"(d_char), "+r"(res)
 	: "i"(0)
-	: "lp_count", "lp_start", "lp_end", "memory");
+	: "lp_count", "memory");
 
 	return res;
 }
@@ -691,7 +691,7 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 	"	.previous			\n"
 	: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
 	: "g"(-EFAULT), "r"(count)
-	: "lp_count", "lp_start", "lp_end", "memory");
+	: "lp_count", "memory");
 
 	return res;
 }
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 689dd867fdff..cd64cb4ef7b0 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -17,6 +17,7 @@
 #include <asm/entry.h>
 #include <asm/arcregs.h>
 #include <asm/cache.h>
+#include <asm/irqflags.h>
 
 .macro CPU_EARLY_SETUP
 
@@ -47,6 +48,15 @@
 	sr	r5, [ARC_REG_DC_CTRL]
 
 1:
+
+#ifdef CONFIG_ISA_ARCV2
+	; Unaligned access is disabled at reset, so re-enable early as
+	; gcc 7.3.1 (ARC GNU 2018.03) onwards generates unaligned access
+	; by default
+	lr	r5, [status32]
+	bset	r5, r5, STATUS_AD_BIT
+	kflag	r5
+#endif
 .endm
 
 	.section .init.text, "ax",@progbits
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 34e1569a11ee..3a0277c6c060 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1475,6 +1475,7 @@ config NR_CPUS
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
 	depends on SMP
+	select GENERIC_IRQ_MIGRATION
 	help
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts
index 6881757b03e8..67369f284b91 100644
--- a/arch/arm/boot/dts/da850-evm.dts
+++ b/arch/arm/boot/dts/da850-evm.dts
@@ -147,7 +147,7 @@
 
 	sound {
 		compatible = "simple-audio-card";
-		simple-audio-card,name = "DA850/OMAP-L138 EVM";
+		simple-audio-card,name = "DA850-OMAPL138 EVM";
 		simple-audio-card,widgets =
 			"Line", "Line In",
 			"Line", "Line Out";
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 2f30d632f1cc..e81a27214188 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -150,6 +150,9 @@
 			interrupt-controller;
 			#interrupt-cells = <3>;
 			interrupt-parent = <&gic>;
+			clock-names = "clkout8";
+			clocks = <&cmu CLK_FIN_PLL>;
+			#clock-cells = <1>;
 		};
 
 		mipi_phy: video-phy@10020710 {
diff --git a/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi b/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi
new file mode 100644
index 000000000000..c8771c660550
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5420-tmu-sensor-conf.dtsi
@@ -0,0 +1,25 @@
+/*
+ * Device tree sources for Exynos5420 TMU sensor configuration
+ *
+ * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
+ * Copyright (c) 2017 Krzysztof Kozlowski <krzk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <dt-bindings/thermal/thermal_exynos.h>
+
+#thermal-sensor-cells = <0>;
+samsung,tmu_gain = <8>;
+samsung,tmu_reference_voltage = <16>;
+samsung,tmu_noise_cancel_mode = <4>;
+samsung,tmu_efuse_value = <55>;
+samsung,tmu_min_efuse_value = <0>;
+samsung,tmu_max_efuse_value = <100>;
+samsung,tmu_first_point_trim = <25>;
+samsung,tmu_second_point_trim = <85>;
+samsung,tmu_default_temp_offset = <50>;
+samsung,tmu_cal_type = <TYPE_ONE_POINT_TRIMMING>;
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 1b3d6c769a3c..d5edb7766942 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -777,7 +777,7 @@
 		interrupts = <0 65 0>;
 		clocks = <&clock CLK_TMU>;
 		clock-names = "tmu_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#include "exynos5420-tmu-sensor-conf.dtsi"
 	};
 
 	tmu_cpu1: tmu@10064000 {
@@ -786,7 +786,7 @@
 		interrupts = <0 183 0>;
 		clocks = <&clock CLK_TMU>;
 		clock-names = "tmu_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#include "exynos5420-tmu-sensor-conf.dtsi"
 	};
 
 	tmu_cpu2: tmu@10068000 {
@@ -795,7 +795,7 @@
 		interrupts = <0 184 0>;
 		clocks = <&clock CLK_TMU>, <&clock CLK_TMU>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#include "exynos5420-tmu-sensor-conf.dtsi"
 	};
 
 	tmu_cpu3: tmu@1006c000 {
@@ -804,7 +804,7 @@
 		interrupts = <0 185 0>;
 		clocks = <&clock CLK_TMU>, <&clock CLK_TMU_GPU>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#include "exynos5420-tmu-sensor-conf.dtsi"
 	};
 
 	tmu_gpu: tmu@100a0000 {
@@ -813,7 +813,7 @@
 		interrupts = <0 215 0>;
 		clocks = <&clock CLK_TMU_GPU>, <&clock CLK_TMU>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
+		#include "exynos5420-tmu-sensor-conf.dtsi"
 	};
 
 	thermal-zones {
diff --git a/arch/arm/boot/dts/kirkwood-dnskw.dtsi b/arch/arm/boot/dts/kirkwood-dnskw.dtsi
index 113dcf056dcf..1b2dacfa6132 100644
--- a/arch/arm/boot/dts/kirkwood-dnskw.dtsi
+++ b/arch/arm/boot/dts/kirkwood-dnskw.dtsi
@@ -35,8 +35,8 @@
 		compatible = "gpio-fan";
 		pinctrl-0 = <&pmx_fan_high_speed &pmx_fan_low_speed>;
 		pinctrl-names = "default";
-		gpios = <&gpio1 14 GPIO_ACTIVE_LOW
-			 &gpio1 13 GPIO_ACTIVE_LOW>;
+		gpios = <&gpio1 14 GPIO_ACTIVE_HIGH
+			 &gpio1 13 GPIO_ACTIVE_HIGH>;
 		gpio-fan,speed-map = <0    0
 				      3000 1
 				      6000 2>;
diff --git a/arch/arm/boot/dts/mmp2.dtsi b/arch/arm/boot/dts/mmp2.dtsi
index 766bbb8495b6..47e5b63339d1 100644
--- a/arch/arm/boot/dts/mmp2.dtsi
+++ b/arch/arm/boot/dts/mmp2.dtsi
@@ -220,12 +220,15 @@
 				status = "disabled";
 			};
 
-			twsi2: i2c@d4025000 {
+			twsi2: i2c@d4031000 {
 				compatible = "mrvl,mmp-twsi";
-				reg = <0xd4025000 0x1000>;
-				interrupts = <58>;
+				reg = <0xd4031000 0x1000>;
+				interrupt-parent = <&intcmux17>;
+				interrupts = <0>;
 				clocks = <&soc_clocks MMP2_CLK_TWSI1>;
 				resets = <&soc_clocks MMP2_CLK_TWSI1>;
+				#address-cells = <1>;
+				#size-cells = <0>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts
index f0bdc41f8eff..235d1493f8aa 100644
--- a/arch/arm/boot/dts/omap4-sdp.dts
+++ b/arch/arm/boot/dts/omap4-sdp.dts
@@ -33,6 +33,7 @@
 		gpio = <&gpio2 16 GPIO_ACTIVE_HIGH>;  /* gpio line 48 */
 		enable-active-high;
 		regulator-boot-on;
+		startup-delay-us = <25000>;
 	};
 
 	vbat: fixedregulator-vbat {
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 1bd9510de1b9..cae4df39f02e 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -24,7 +24,6 @@
 #ifndef __ASSEMBLY__
 struct irqaction;
 struct pt_regs;
-extern void migrate_irqs(void);
 
 extern void asm_do_IRQ(unsigned int, struct pt_regs *);
 void handle_IRQ(unsigned int, struct pt_regs *);
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index ece04a457486..5b07c7a31c31 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -31,7 +31,6 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/seq_file.h>
-#include <linux/ratelimit.h>
 #include <linux/errno.h>
 #include <linux/list.h>
 #include <linux/kallsyms.h>
@@ -119,64 +118,3 @@ int __init arch_probe_nr_irqs(void)
 	return nr_irqs;
 }
 #endif
-
-#ifdef CONFIG_HOTPLUG_CPU
-static bool migrate_one_irq(struct irq_desc *desc)
-{
-	struct irq_data *d = irq_desc_get_irq_data(desc);
-	const struct cpumask *affinity = irq_data_get_affinity_mask(d);
-	struct irq_chip *c;
-	bool ret = false;
-
-	/*
-	 * If this is a per-CPU interrupt, or the affinity does not
-	 * include this CPU, then we have nothing to do.
-	 */
-	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
-		return false;
-
-	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
-		affinity = cpu_online_mask;
-		ret = true;
-	}
-
-	c = irq_data_get_irq_chip(d);
-	if (!c->irq_set_affinity)
-		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
-		cpumask_copy(irq_data_get_affinity_mask(d), affinity);
-
-	return ret;
-}
-
-/*
- * The current CPU has been marked offline.  Migrate IRQs off this CPU.
- * If the affinity settings do not allow other CPUs, force them onto any
- * available CPU.
- *
- * Note: we must iterate over all IRQs, whether they have an attached
- * action structure or not, as we need to get chained interrupts too.
- */
-void migrate_irqs(void)
-{
-	unsigned int i;
-	struct irq_desc *desc;
-	unsigned long flags;
-
-	local_irq_save(flags);
-
-	for_each_irq_desc(i, desc) {
-		bool affinity_broken;
-
-		raw_spin_lock(&desc->lock);
-		affinity_broken = migrate_one_irq(desc);
-		raw_spin_unlock(&desc->lock);
-
-		if (affinity_broken)
-			pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
-				i, smp_processor_id());
-	}
-
-	local_irq_restore(flags);
-}
-#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b26361355dae..08ce9e36dc5a 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -218,7 +218,7 @@ int __cpu_disable(void)
 	/*
 	 * OK - migrate IRQs away from this CPU
 	 */
-	migrate_irqs();
+	irq_migrate_all_off_this_cpu();
 
 	/*
 	 * Flush user cache and TLB mappings, and then remove this CPU
@@ -687,6 +687,21 @@ void smp_send_stop(void)
 		pr_warn("SMP: failed to stop secondary CPUs\n");
 }
 
+/* In case panic() and panic() called at the same time on CPU1 and CPU2,
+ * and CPU 1 calls panic_smp_self_stop() before crash_smp_send_stop()
+ * CPU1 can't receive the ipi irqs from CPU2, CPU1 will be always online,
+ * kdump fails. So split out the panic_smp_self_stop() and add
+ * set_cpu_online(smp_processor_id(), false).
+ */
+void panic_smp_self_stop(void)
+{
+	pr_debug("CPU %u will stop doing anything useful since another CPU has paniced\n",
+	         smp_processor_id());
+	set_cpu_online(smp_processor_id(), false);
+	while (1)
+		cpu_relax();
+}
+
 /*
  * not supported here
  */
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 387ee2a11e36..ae61e2ea7255 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -87,11 +87,10 @@ static unsigned long mmio_read_buf(char *buf, unsigned int len)
 
 /**
  * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
+ *			     or in-kernel IO emulation
+ *
  * @vcpu: The VCPU pointer
  * @run:  The VCPU run struct containing the mmio data
- *
- * This should only be called after returning from userspace for MMIO load
- * emulation.
  */
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
@@ -118,6 +117,12 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
 	}
 
+	/*
+	 * The MMIO instruction is emulated and should not be re-executed
+	 * in the guest.
+	 */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 0;
 }
 
@@ -151,11 +156,6 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
 	vcpu->arch.mmio_decode.sign_extend = sign_extend;
 	vcpu->arch.mmio_decode.rt = rt;
 
-	/*
-	 * The MMIO instruction is emulated and should not be re-executed
-	 * in the guest.
-	 */
-	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 	return 0;
 }
 
@@ -206,14 +206,17 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	run->mmio.is_write	= is_write;
 	run->mmio.phys_addr	= fault_ipa;
 	run->mmio.len		= len;
-	memcpy(run->mmio.data, data_buf, len);
 
 	if (!ret) {
 		/* We handled the access successfully in the kernel. */
+		if (!is_write)
+			memcpy(run->mmio.data, data_buf, len);
 		kvm_handle_mmio_return(vcpu, run);
 		return 1;
 	}
 
+	if (is_write)
+		memcpy(run->mmio.data, data_buf, len);
 	run->exit_reason	= KVM_EXIT_MMIO;
 	return 0;
 }
diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c
index 318394ed5c7a..5e11ad3164e0 100644
--- a/arch/arm/mach-cns3xxx/pcie.c
+++ b/arch/arm/mach-cns3xxx/pcie.c
@@ -83,7 +83,7 @@ static void __iomem *cns3xxx_pci_map_bus(struct pci_bus *bus,
 	} else /* remote PCI bus */
 		base = cnspci->cfg1_regs + ((busno & 0xf) << 20);
 
-	return base + (where & 0xffc) + (devfn << 12);
+	return base + where + (devfn << 12);
 }
 
 static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn,
diff --git a/arch/arm/mach-imx/cpuidle-imx6sx.c b/arch/arm/mach-imx/cpuidle-imx6sx.c
index 3c6672b3796b..7f5df8992008 100644
--- a/arch/arm/mach-imx/cpuidle-imx6sx.c
+++ b/arch/arm/mach-imx/cpuidle-imx6sx.c
@@ -97,7 +97,7 @@ int __init imx6sx_cpuidle_init(void)
 	 * except for power up sw2iso which need to be
 	 * larger than LDO ramp up time.
 	 */
-	imx_gpc_set_arm_power_up_timing(2, 1);
+	imx_gpc_set_arm_power_up_timing(0xf, 1);
 	imx_gpc_set_arm_power_down_timing(1, 1);
 
 	return cpuidle_register(&imx6sx_cpuidle_driver, NULL);
diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c
index 38b0da300dd5..423a88ff908c 100644
--- a/arch/arm/mach-integrator/impd1.c
+++ b/arch/arm/mach-integrator/impd1.c
@@ -394,7 +394,11 @@ static int __init_refok impd1_probe(struct lm_device *dev)
 					      sizeof(*lookup) + 3 * sizeof(struct gpiod_lookup),
 					      GFP_KERNEL);
 			chipname = devm_kstrdup(&dev->dev, devname, GFP_KERNEL);
-			mmciname = kasprintf(GFP_KERNEL, "lm%x:00700", dev->id);
+			mmciname = devm_kasprintf(&dev->dev, GFP_KERNEL,
+						  "lm%x:00700", dev->id);
+			if (!lookup || !chipname || !mmciname)
+				return -ENOMEM;
+
 			lookup->dev_id = mmciname;
 			/*
 			 * Offsets on GPIO block 1:
diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c
index c1cd80ecc219..a904244264ce 100644
--- a/arch/arm/mach-iop32x/n2100.c
+++ b/arch/arm/mach-iop32x/n2100.c
@@ -75,8 +75,7 @@ void __init n2100_map_io(void)
 /*
  * N2100 PCI.
  */
-static int __init
-n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq;
 
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index a95499ea8706..fa1d41edce68 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -511,6 +511,9 @@ static void modem_pm(struct uart_port *port, unsigned int state, unsigned old)
 {
 	struct modem_private_data *priv = port->private_data;
 
+	if (!priv)
+		return;
+
 	if (IS_ERR(priv->regulator))
 		return;
 
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 6ab13d18c636..cde86d1199cf 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -115,6 +115,7 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
 	u32 enable_mask, enable_shift;
 	u32 pipd_mask, pipd_shift;
 	u32 reg;
+	int ret;
 
 	if (dsi_id == 0) {
 		enable_mask = OMAP4_DSI1_LANEENABLE_MASK;
@@ -130,7 +131,11 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
 		return -ENODEV;
 	}
 
-	regmap_read(omap4_dsi_mux_syscon, OMAP4_DSIPHY_SYSCON_OFFSET, &reg);
+	ret = regmap_read(omap4_dsi_mux_syscon,
+					  OMAP4_DSIPHY_SYSCON_OFFSET,
+					  &reg);
+	if (ret)
+		return ret;
 
 	reg &= ~enable_mask;
 	reg &= ~pipd_mask;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 147c90e70b2e..36706d32d656 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2526,7 +2526,7 @@ static int __init _init(struct omap_hwmod *oh, void *data)
  * a stub; implementing this properly requires iclk autoidle usecounting in
  * the clock code.   No return value.
  */
-static void __init _setup_iclk_autoidle(struct omap_hwmod *oh)
+static void _setup_iclk_autoidle(struct omap_hwmod *oh)
 {
 	struct omap_hwmod_ocp_if *os;
 	struct list_head *p;
@@ -2561,7 +2561,7 @@ static void __init _setup_iclk_autoidle(struct omap_hwmod *oh)
  * reset.  Returns 0 upon success or a negative error code upon
  * failure.
  */
-static int __init _setup_reset(struct omap_hwmod *oh)
+static int _setup_reset(struct omap_hwmod *oh)
 {
 	int r;
 
@@ -2622,7 +2622,7 @@ static int __init _setup_reset(struct omap_hwmod *oh)
  *
  * No return value.
  */
-static void __init _setup_postsetup(struct omap_hwmod *oh)
+static void _setup_postsetup(struct omap_hwmod *oh)
 {
 	u8 postsetup_state;
 
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index 30768003f854..8c505284bc0c 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -344,7 +344,7 @@ static void omap44xx_prm_reconfigure_io_chain(void)
  * to occur, WAKEUPENABLE bits must be set in the pad mux registers, and
  * omap44xx_prm_reconfigure_io_chain() must be called.  No return value.
  */
-static void __init omap44xx_prm_enable_io_wakeup(void)
+static void omap44xx_prm_enable_io_wakeup(void)
 {
 	s32 inst = omap4_prmst_get_prm_dev_inst();
 
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index a7dae60810e8..307fc18edede 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -547,7 +547,7 @@ static struct pxa3xx_u2d_platform_data cm_x300_u2d_platform_data = {
 	.exit		= cm_x300_u2d_exit,
 };
 
-static void cm_x300_init_u2d(void)
+static void __init cm_x300_init_u2d(void)
 {
 	pxa3xx_set_u2d_info(&cm_x300_u2d_platform_data);
 }
diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c
index 5d665588c7eb..05aa7071efd6 100644
--- a/arch/arm/mach-pxa/littleton.c
+++ b/arch/arm/mach-pxa/littleton.c
@@ -183,7 +183,7 @@ static struct pxafb_mach_info littleton_lcd_info = {
 	.lcd_conn		= LCD_COLOR_TFT_16BPP,
 };
 
-static void littleton_init_lcd(void)
+static void __init littleton_init_lcd(void)
 {
 	pxa_set_fb_info(NULL, &littleton_lcd_info);
 }
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index d757cfb5f8a6..4da2458d7f32 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -558,7 +558,7 @@ static struct pxaohci_platform_data zeus_ohci_platform_data = {
 	.flags		= ENABLE_PORT_ALL | POWER_SENSE_LOW,
 };
 
-static void zeus_register_ohci(void)
+static void __init zeus_register_ohci(void)
 {
 	/* Port 2 is shared between host and client interface. */
 	UP2OCR = UP2OCR_HXOE | UP2OCR_HXS | UP2OCR_DMPDE | UP2OCR_DPPDE;
diff --git a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
index ce2db235dbaf..5e8a306163de 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
@@ -70,16 +70,16 @@ static int osiris_dvs_notify(struct notifier_block *nb,
 
 	switch (val) {
 	case CPUFREQ_PRECHANGE:
-		if (old_dvs & !new_dvs ||
-		    cur_dvs & !new_dvs) {
+		if ((old_dvs && !new_dvs) ||
+		    (cur_dvs && !new_dvs)) {
 			pr_debug("%s: exiting dvs\n", __func__);
 			cur_dvs = false;
 			gpio_set_value(OSIRIS_GPIO_DVS, 1);
 		}
 		break;
 	case CPUFREQ_POSTCHANGE:
-		if (!old_dvs & new_dvs ||
-		    !cur_dvs & new_dvs) {
+		if ((!old_dvs && new_dvs) ||
+		    (!cur_dvs && new_dvs)) {
 			pr_debug("entering dvs\n");
 			cur_dvs = true;
 			gpio_set_value(OSIRIS_GPIO_DVS, 0);
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index a134d8a13d00..11d699af30ed 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -359,14 +359,16 @@ v7_dma_inv_range:
 	ALT_UP(W(nop))
 #endif
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
+	addne	r0, r0, r2
 
 	tst	r1, r3
 	bic	r1, r1, r3
 	mcrne	p15, 0, r1, c7, c14, 1		@ clean & invalidate D / U line
-1:
-	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D / U line
-	add	r0, r0, r2
 	cmp	r0, r1
+1:
+	mcrlo	p15, 0, r0, c7, c6, 1		@ invalidate D / U line
+	addlo	r0, r0, r2
+	cmplo	r0, r1
 	blo	1b
 	dsb	st
 	ret	lr
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index daa1a65f2eb7..6748827c2ec8 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -238,8 +238,6 @@ static int pxa_ssp_remove(struct platform_device *pdev)
 	if (ssp == NULL)
 		return -ENODEV;
 
-	iounmap(ssp->mmio_base);
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	release_mem_region(res->start, resource_size(res));
 
@@ -249,7 +247,6 @@ static int pxa_ssp_remove(struct platform_device *pdev)
 	list_del(&ssp->node);
 	mutex_unlock(&ssp_lock);
 
-	kfree(ssp);
 	return 0;
 }
 
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index 3363560c79b7..7bc459d9235c 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -74,12 +74,13 @@ ENTRY(ce_aes_ccm_auth_data)
 	beq	10f
 	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
 	b	7b
-8:	mov	w7, w8
+8:	cbz	w8, 91f
+	mov	w7, w8
 	add	w8, w8, #16
 9:	ext	v1.16b, v1.16b, v1.16b, #1
 	adds	w7, w7, #1
 	bne	9b
-	eor	v0.16b, v0.16b, v1.16b
+91:	eor	v0.16b, v0.16b, v1.16b
 	st1	{v0.16b}, [x0]
 10:	str	w8, [x3]
 	ret
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index ef8e13d379cb..d7e7cf56e8d6 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,8 @@
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
+#define HCR_API		(UL(1) << 41)
+#define HCR_APK		(UL(1) << 40)
 #define HCR_ID		(UL(1) << 33)
 #define HCR_CD		(UL(1) << 32)
 #define HCR_RW_SHIFT	31
@@ -81,6 +83,7 @@
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
 #define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
+#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
 
 
 /* Hyp System Control Register (SCTLR_EL2) bits */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 0f03a8fe2314..d18d15810d19 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -78,7 +78,6 @@
 	.macro mcount_get_lr reg
 	ldr	\reg, [x29]
 	ldr	\reg, [\reg, #8]
-	mcount_adjust_addr	\reg, \reg
 	.endm
 
 	.macro mcount_get_lr_addr reg
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index d019c3a58cc2..6299a8a361ee 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -30,6 +30,7 @@
 #include <asm/cache.h>
 #include <asm/cputype.h>
 #include <asm/kernel-pgtable.h>
+#include <asm/kvm_arm.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
@@ -464,7 +465,7 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	ret
 
 	/* Hyp configuration. */
-2:	mov	x0, #(1 << 31)			// 64-bit EL1
+2:	mov_q	x0, HCR_HOST_NVHE_FLAGS
 	msr	hcr_el2, x0
 
 	/* Generic timers. */
@@ -477,8 +478,7 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	/* GICv3 system register access */
 	mrs	x0, id_aa64pfr0_el1
 	ubfx	x0, x0, #24, #4
-	cmp	x0, #1
-	b.ne	3f
+	cbz	x0, 3f
 
 	mrs_s	x0, ICC_SRE_EL2
 	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index a272f335c289..096e957aecb0 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -26,6 +26,8 @@
 #include <asm/virt.h>
 
 	.text
+	.pushsection	.hyp.text, "ax"
+
 	.align 11
 
 ENTRY(__hyp_stub_vectors)
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 62d3dc60ca09..e99a0ed7e66b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -670,6 +670,7 @@ static struct platform_driver armv8_pmu_driver = {
 	.driver		= {
 		.name	= "armv8-pmu",
 		.of_match_table = armv8_pmu_of_device_ids,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= armv8_pmu_device_probe,
 };
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 86c289832272..8d3da858c257 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -494,7 +494,7 @@
 .endm
 
 .macro deactivate_traps
-	mov	x2, #HCR_RW
+	mov_q	x2, HCR_HOST_NVHE_FLAGS
 	msr	hcr_el2, x2
 	msr	hstr_el2, xzr
 
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index c26b804015e8..a90615baa529 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -70,10 +70,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 {
 	struct page *page = pte_page(pte);
 
-	/* no flushing needed for anonymous pages */
-	if (!page_mapping(page))
-		return;
-
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags)) {
 		__flush_dcache_area(page_address(page),
 				PAGE_SIZE << compound_order(page));
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index 877da1908234..98e2a5dbcfda 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -2724,7 +2724,6 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 			     (unsigned long int)(oper.indata + prev_ix),
 			     noinpages,
 			     0,  /* read access only for in data */
-			     0, /* no force */
 			     inpages,
 			     NULL);
 
@@ -2740,8 +2739,7 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 				     current->mm,
 				     (unsigned long int)oper.cipher_outdata,
 				     nooutpages,
-				     1, /* write access for out data */
-				     0, /* no force */
+				     FOLL_WRITE, /* write access for out data */
 				     outpages,
 				     NULL);
 		up_read(&current->mm->mmap_sem);
diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c
index 0c161ed6d18e..8205b456de7a 100644
--- a/arch/ia64/kernel/err_inject.c
+++ b/arch/ia64/kernel/err_inject.c
@@ -143,7 +143,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
 	int ret;
 
         ret = get_user_pages(current, current->mm, virt_addr,
-                        1, VM_READ, 0, NULL, NULL);
+			     1, FOLL_WRITE, NULL, NULL);
 	if (ret<=0) {
 #ifdef ERR_INJ_DEBUG
 		printk("Virtual address %lx is not existing.\n",virt_addr);
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 0b29dcfef69f..0c736ed58abd 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -59,7 +59,10 @@ cpuflags-$(CONFIG_M5206e)	:= $(call cc-option,-mcpu=5206e,-m5200)
 cpuflags-$(CONFIG_M5206)	:= $(call cc-option,-mcpu=5206,-m5200)
 
 KBUILD_AFLAGS += $(cpuflags-y)
-KBUILD_CFLAGS += $(cpuflags-y) -pipe
+KBUILD_CFLAGS += $(cpuflags-y)
+
+KBUILD_CFLAGS += -pipe -ffreestanding
+
 ifdef CONFIG_MMU
 # without -fno-strength-reduce the 53c7xx.c driver fails ;-(
 KBUILD_CFLAGS += -fno-strength-reduce -ffixed-a2
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 8b0424abc84c..333ea0389adb 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -760,6 +760,7 @@ config SIBYTE_SWARM
 	select SYS_SUPPORTS_HIGHMEM
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select ZONE_DMA32 if 64BIT
+	select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
 
 config SIBYTE_LITTLESUR
 	bool "Sibyte BCM91250C2-LittleSur"
@@ -782,6 +783,7 @@ config SIBYTE_SENTOSA
 	select SYS_HAS_CPU_SB1
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
 
 config SIBYTE_BIGSUR
 	bool "Sibyte BCM91480B-BigSur"
@@ -795,6 +797,7 @@ config SIBYTE_BIGSUR
 	select SYS_SUPPORTS_HIGHMEM
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select ZONE_DMA32 if 64BIT
+	select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
 
 config SNI_RM
 	bool "SNI RM200/300/400"
@@ -2972,6 +2975,7 @@ config MIPS32_O32
 config MIPS32_N32
 	bool "Kernel support for n32 binaries"
 	depends on 64BIT
+	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select COMPAT
 	select MIPS32_COMPAT
 	select SYSVIPC_COMPAT if SYSVIPC
diff --git a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
index 37fe58c19a90..542c3ede9722 100644
--- a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
+++ b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
@@ -13,6 +13,7 @@
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include "../../../../include/linux/sizes.h"
 
 int main(int argc, char *argv[])
 {
@@ -45,11 +46,11 @@ int main(int argc, char *argv[])
 	vmlinuz_load_addr = vmlinux_load_addr + vmlinux_size;
 
 	/*
-	 * Align with 16 bytes: "greater than that used for any standard data
-	 * types by a MIPS compiler." -- See MIPS Run Linux (Second Edition).
+	 * Align with 64KB: KEXEC needs load sections to be aligned to PAGE_SIZE,
+	 * which may be as large as 64KB depending on the kernel configuration.
 	 */
 
-	vmlinuz_load_addr += (16 - vmlinux_size % 16);
+	vmlinuz_load_addr += (SZ_64K - vmlinux_size % SZ_64K);
 
 	printf("0x%llx\n", vmlinuz_load_addr);
 
diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig
index 134879c1310a..4ed369c0ec6a 100644
--- a/arch/mips/configs/ath79_defconfig
+++ b/arch/mips/configs/ath79_defconfig
@@ -74,6 +74,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 # CONFIG_SERIAL_8250_PCI is not set
 CONFIG_SERIAL_8250_NR_UARTS=1
 CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AR933X=y
 CONFIG_SERIAL_AR933X_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index cf661a2fb141..16fade4f49dd 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -189,6 +189,11 @@ static inline int pmd_bad(pmd_t pmd)
 
 static inline int pmd_present(pmd_t pmd)
 {
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
+	if (unlikely(pmd_val(pmd) & _PAGE_HUGE))
+		return pmd_val(pmd) & _PAGE_PRESENT;
+#endif
+
 	return pmd_val(pmd) != (unsigned long) invalid_pte_table;
 }
 
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index 1b6f2f219298..9db764b51ffe 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -290,8 +290,8 @@ enum mm_32a_minor_op {
 	mm_ext_op = 0x02c,
 	mm_pool32axf_op = 0x03c,
 	mm_srl32_op = 0x040,
+	mm_srlv32_op = 0x050,
 	mm_sra_op = 0x080,
-	mm_srlv32_op = 0x090,
 	mm_rotr_op = 0x0c0,
 	mm_lwxs_op = 0x118,
 	mm_addu32_op = 0x150,
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index db6f5afff4ff..ea897912bc71 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -71,14 +71,15 @@ static int __init vdma_init(void)
 						    get_order(VDMA_PGTBL_SIZE));
 	BUG_ON(!pgtbl);
 	dma_cache_wback_inv((unsigned long)pgtbl, VDMA_PGTBL_SIZE);
-	pgtbl = (VDMA_PGTBL_ENTRY *)KSEG1ADDR(pgtbl);
+	pgtbl = (VDMA_PGTBL_ENTRY *)CKSEG1ADDR((unsigned long)pgtbl);
 
 	/*
 	 * Clear the R4030 translation table
 	 */
 	vdma_pgtbl_init();
 
-	r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE, CPHYSADDR(pgtbl));
+	r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE,
+			  CPHYSADDR((unsigned long)pgtbl));
 	r4030_write_reg32(JAZZ_R4030_TRSTBL_LIM, VDMA_PGTBL_SIZE);
 	r4030_write_reg32(JAZZ_R4030_TRSTBL_INV, 0);
 
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index dc1180a8bfa1..66736397af9f 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -52,6 +52,7 @@ asmlinkage void spurious_interrupt(void)
 void __init init_IRQ(void)
 {
 	int i;
+	unsigned int order = get_order(IRQ_STACK_SIZE);
 
 	for (i = 0; i < NR_IRQS; i++)
 		irq_set_noprobe(i);
@@ -59,8 +60,7 @@ void __init init_IRQ(void)
 	arch_init_irq();
 
 	for_each_possible_cpu(i) {
-		int irq_pages = IRQ_STACK_SIZE / PAGE_SIZE;
-		void *s = (void *)__get_free_pages(GFP_KERNEL, irq_pages);
+		void *s = (void *)__get_free_pages(GFP_KERNEL, order);
 
 		irq_stack[i] = s;
 		pr_debug("CPU%d IRQ stack at 0x%p - 0x%p\n", i,
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index 1448c1f43d4e..76f18c56141c 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -424,5 +424,5 @@ void mips_cm_error_report(void)
 	}
 
 	/* reprime cause register */
-	write_gcr_error_cause(0);
+	write_gcr_error_cause(cm_error);
 }
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index ebd8a715fe38..e6102775892d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -339,7 +339,7 @@ static inline int is_sp_move_ins(union mips_instruction *ip)
 static int get_frame_info(struct mips_frame_info *info)
 {
 	bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS);
-	union mips_instruction insn, *ip, *ip_end;
+	union mips_instruction insn, *ip;
 	const unsigned int max_insns = 128;
 	unsigned int last_insn_size = 0;
 	unsigned int i;
@@ -351,10 +351,9 @@ static int get_frame_info(struct mips_frame_info *info)
 	if (!ip)
 		goto err;
 
-	ip_end = (void *)ip + info->func_size;
-
-	for (i = 0; i < max_insns && ip < ip_end; i++) {
+	for (i = 0; i < max_insns; i++) {
 		ip = (void *)ip + last_insn_size;
+
 		if (is_mmips && mm_insn_16bit(ip->halfword[0])) {
 			insn.halfword[0] = 0;
 			insn.halfword[1] = ip->halfword[0];
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
index 349995d19c7f..e596e0a1cecc 100644
--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -303,7 +303,7 @@ slow_irqon:
 
 	ret = get_user_pages_unlocked(current, mm, start,
 				      (end - start) >> PAGE_SHIFT,
-				      write, 0, pages);
+				      pages, write ? FOLL_WRITE : 0);
 
 	/* Have to be a bit careful with return values */
 	if (nr > 0) {
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index 2a5bb849b10e..288b58b00dc8 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -369,7 +369,9 @@ int __init octeon_msi_initialize(void)
 	int irq;
 	struct irq_chip *msi;
 
-	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
+	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) {
+		return 0;
+	} else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
 		msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0;
 		msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1;
 		msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2;
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index c258cd406fbb..b36bbda31058 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -571,6 +571,11 @@ static int __init octeon_pci_setup(void)
 	if (octeon_has_feature(OCTEON_FEATURE_PCIE))
 		return 0;
 
+	if (!octeon_is_pci_host()) {
+		pr_notice("Not in host mode, PCI Controller not initialized\n");
+		return 0;
+	}
+
 	/* Point pcibios_map_irq() to the PCI version of it */
 	octeon_pcibios_map_irq = octeon_pci_pcibios_map_irq;
 
@@ -582,11 +587,6 @@ static int __init octeon_pci_setup(void)
 	else
 		octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_BIG;
 
-	if (!octeon_is_pci_host()) {
-		pr_notice("Not in host mode, PCI Controller not initialized\n");
-		return 0;
-	}
-
 	/* PCI I/O and PCI MEM values */
 	set_io_port_base(OCTEON_PCI_IOSPACE_BASE);
 	ioport_resource.start = 0;
diff --git a/arch/mips/sibyte/common/Makefile b/arch/mips/sibyte/common/Makefile
index b3d6bf23a662..3ef3fb658136 100644
--- a/arch/mips/sibyte/common/Makefile
+++ b/arch/mips/sibyte/common/Makefile
@@ -1,4 +1,5 @@
 obj-y := cfe.o
+obj-$(CONFIG_SWIOTLB)			+= dma.o
 obj-$(CONFIG_SIBYTE_BUS_WATCHER)	+= bus_watcher.o
 obj-$(CONFIG_SIBYTE_CFE_CONSOLE)	+= cfe_console.o
 obj-$(CONFIG_SIBYTE_TBPROF)		+= sb_tbprof.o
diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c
new file mode 100644
index 000000000000..eb47a94f3583
--- /dev/null
+++ b/arch/mips/sibyte/common/dma.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *	DMA support for Broadcom SiByte platforms.
+ *
+ *	Copyright (c) 2018  Maciej W. Rozycki
+ */
+
+#include <linux/swiotlb.h>
+#include <asm/bootinfo.h>
+
+void __init plat_swiotlb_setup(void)
+{
+	swiotlb_init(1);
+}
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 6c7d78546eee..886005b1e87d 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -107,7 +107,7 @@ $(obj)/%-o32.o: $(src)/%.c FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := -mabi=32
+$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=32
 $(obj)/vdso-o32.lds: $(src)/vdso.lds.S FORCE
 	$(call if_changed_dep,cpp_lds_S)
 
@@ -143,7 +143,7 @@ $(obj)/%-n32.o: $(src)/%.c FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := -mabi=n32
+$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=n32
 $(obj)/vdso-n32.lds: $(src)/vdso.lds.S FORCE
 	$(call if_changed_dep,cpp_lds_S)
 
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 99e4487248ff..57003d1bd243 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -70,7 +70,8 @@ $(addprefix $(obj)/,$(zlib) cuboot-c2k.o gunzip_util.o main.o): \
 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): \
+$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o \
+	treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \
 	$(addprefix $(obj)/,$(libfdtheader))
 
 src-wlib-y := string.S crt0.S crtsavres.S stdio.c main.c \
diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S
index 5c2199857aa8..a3550e8f1a77 100644
--- a/arch/powerpc/boot/crt0.S
+++ b/arch/powerpc/boot/crt0.S
@@ -15,7 +15,7 @@
 RELA = 7
 RELACOUNT = 0x6ffffff9
 
-	.text
+	.data
 	/* A procedure descriptor used when booting this as a COFF file.
 	 * When making COFF, this comes first in the link and we're
 	 * linked at 0x500000.
@@ -23,6 +23,8 @@ RELACOUNT = 0x6ffffff9
 	.globl	_zimage_start_opd
 _zimage_start_opd:
 	.long	0x500000, 0, 0, 0
+	.text
+	b	_zimage_start
 
 #ifdef __powerpc64__
 .balign 8
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index 334459ad145b..90863245df53 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -508,7 +508,7 @@ static unsigned long epapr_hypercall(unsigned long *in,
 
 static inline long epapr_hypercall0_1(unsigned int nr, unsigned long *r2)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 	unsigned long r;
 
@@ -520,7 +520,7 @@ static inline long epapr_hypercall0_1(unsigned int nr, unsigned long *r2)
 
 static inline long epapr_hypercall0(unsigned int nr)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	return epapr_hypercall(in, out, nr);
@@ -528,7 +528,7 @@ static inline long epapr_hypercall0(unsigned int nr)
 
 static inline long epapr_hypercall1(unsigned int nr, unsigned long p1)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	in[0] = p1;
@@ -538,7 +538,7 @@ static inline long epapr_hypercall1(unsigned int nr, unsigned long p1)
 static inline long epapr_hypercall2(unsigned int nr, unsigned long p1,
 				    unsigned long p2)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	in[0] = p1;
@@ -549,7 +549,7 @@ static inline long epapr_hypercall2(unsigned int nr, unsigned long p1,
 static inline long epapr_hypercall3(unsigned int nr, unsigned long p1,
 				    unsigned long p2, unsigned long p3)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	in[0] = p1;
@@ -562,7 +562,7 @@ static inline long epapr_hypercall4(unsigned int nr, unsigned long p1,
 				    unsigned long p2, unsigned long p3,
 				    unsigned long p4)
 {
-	unsigned long in[8];
+	unsigned long in[8] = {0};
 	unsigned long out[8];
 
 	in[0] = p1;
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index a5ffe0207c16..05f1389228d2 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -59,7 +59,7 @@
 #endif
 
 #define access_ok(type, addr, size)		\
-	(__chk_user_ptr(addr),			\
+	(__chk_user_ptr(addr), (void)(type),		\
 	 __access_ok((__force unsigned long)(addr), (size), get_fs()))
 
 /*
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 2405631e91a2..3728e617e17e 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -685,6 +685,9 @@ fast_exception_return:
 	mtcr	r10
 	lwz	r10,_LINK(r11)
 	mtlr	r10
+	/* Clear the exception_marker on the stack to avoid confusing stacktrace */
+	li	r10, 0
+	stw	r10, 8(r11)
 	REST_GPR(10, r11)
 	mtspr	SPRN_SRR1,r9
 	mtspr	SPRN_SRR0,r12
@@ -915,6 +918,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	mtcrf	0xFF,r10
 	mtlr	r11
 
+	/* Clear the exception_marker on the stack to avoid confusing stacktrace */
+	li	r10, 0
+	stw	r10, 8(r1)
 	/*
 	 * Once we put values in SRR0 and SRR1, we are in a state
 	 * where exceptions are not recoverable, since taking an
@@ -952,6 +958,9 @@ exc_exit_restart_end:
 	mtlr	r11
 	lwz	r10,_CCR(r1)
 	mtcrf	0xff,r10
+	/* Clear the exception_marker on the stack to avoid confusing stacktrace */
+	li	r10, 0
+	stw	r10, 8(r1)
 	REST_2GPRS(9, r1)
 	.globl exc_exit_restart
 exc_exit_restart:
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index dab616a33b8d..f2197654be07 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -34,5 +34,10 @@ void arch_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct pci_controller *phb = pci_bus_to_host(dev->bus);
 
-	phb->controller_ops.teardown_msi_irqs(dev);
+	/*
+	 * We can be called even when arch_setup_msi_irqs() returns -ENOSYS,
+	 * so check the pointer again.
+	 */
+	if (phb->controller_ops.teardown_msi_irqs)
+		phb->controller_ops.teardown_msi_irqs(dev);
 }
diff --git a/arch/powerpc/platforms/83xx/suspend-asm.S b/arch/powerpc/platforms/83xx/suspend-asm.S
index 3d1ecd211776..8137f77abad5 100644
--- a/arch/powerpc/platforms/83xx/suspend-asm.S
+++ b/arch/powerpc/platforms/83xx/suspend-asm.S
@@ -26,13 +26,13 @@
 #define SS_MSR		0x74
 #define SS_SDR1		0x78
 #define SS_LR		0x7c
-#define SS_SPRG		0x80 /* 4 SPRGs */
-#define SS_DBAT		0x90 /* 8 DBATs */
-#define SS_IBAT		0xd0 /* 8 IBATs */
-#define SS_TB		0x110
-#define SS_CR		0x118
-#define SS_GPREG	0x11c /* r12-r31 */
-#define STATE_SAVE_SIZE 0x16c
+#define SS_SPRG		0x80 /* 8 SPRGs */
+#define SS_DBAT		0xa0 /* 8 DBATs */
+#define SS_IBAT		0xe0 /* 8 IBATs */
+#define SS_TB		0x120
+#define SS_CR		0x128
+#define SS_GPREG	0x12c /* r12-r31 */
+#define STATE_SAVE_SIZE 0x17c
 
 	.section .data
 	.align	5
@@ -103,6 +103,16 @@ _GLOBAL(mpc83xx_enter_deep_sleep)
 	stw	r7, SS_SPRG+12(r3)
 	stw	r8, SS_SDR1(r3)
 
+	mfspr	r4, SPRN_SPRG4
+	mfspr	r5, SPRN_SPRG5
+	mfspr	r6, SPRN_SPRG6
+	mfspr	r7, SPRN_SPRG7
+
+	stw	r4, SS_SPRG+16(r3)
+	stw	r5, SS_SPRG+20(r3)
+	stw	r6, SS_SPRG+24(r3)
+	stw	r7, SS_SPRG+28(r3)
+
 	mfspr	r4, SPRN_DBAT0U
 	mfspr	r5, SPRN_DBAT0L
 	mfspr	r6, SPRN_DBAT1U
@@ -493,6 +503,16 @@ mpc83xx_deep_resume:
 	mtspr	SPRN_IBAT7U, r6
 	mtspr	SPRN_IBAT7L, r7
 
+	lwz	r4, SS_SPRG+16(r3)
+	lwz	r5, SS_SPRG+20(r3)
+	lwz	r6, SS_SPRG+24(r3)
+	lwz	r7, SS_SPRG+28(r3)
+
+	mtspr	SPRN_SPRG4, r4
+	mtspr	SPRN_SPRG5, r5
+	mtspr	SPRN_SPRG6, r6
+	mtspr	SPRN_SPRG7, r7
+
 	lwz	r4, SS_SPRG+0(r3)
 	lwz	r5, SS_SPRG+4(r3)
 	lwz	r6, SS_SPRG+8(r3)
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 352592d3e44e..7fd19a480422 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -104,6 +104,10 @@ unsigned long __init wii_mmu_mapin_mem2(unsigned long top)
 	/* MEM2 64MB@0x10000000 */
 	delta = wii_hole_start + wii_hole_size;
 	size = top - delta;
+
+	if (__map_without_bats)
+		return delta;
+
 	for (bl = 128<<10; bl < max_size; bl <<= 1) {
 		if (bl * 2 > size)
 			break;
diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c
index 44ed78af1a0d..9021b7272889 100644
--- a/arch/powerpc/platforms/powernv/opal-msglog.c
+++ b/arch/powerpc/platforms/powernv/opal-msglog.c
@@ -92,7 +92,7 @@ out:
 }
 
 static struct bin_attribute opal_msglog_attr = {
-	.attr = {.name = "msglog", .mode = 0444},
+	.attr = {.name = "msglog", .mode = 0400},
 	.read = opal_msglog_read
 };
 
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 96536c969c9c..a8efed3b4691 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -280,6 +280,8 @@ int dlpar_detach_node(struct device_node *dn)
 	if (rc)
 		return rc;
 
+	of_node_put(dn);
+
 	return 0;
 }
 
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 8eccead675d4..cc7b450a7766 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -224,10 +224,10 @@ static noinline __init void detect_machine_type(void)
 	if (stsi(vmms, 3, 2, 2) || !vmms->count)
 		return;
 
-	/* Running under KVM? If not we assume z/VM */
+	/* Detect known hypervisors */
 	if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_KVM;
-	else
+	else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
 }
 
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 929c147e07b4..1b69bfdf59f9 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -344,6 +344,8 @@ static int __hw_perf_event_init(struct perf_event *event)
 		break;
 
 	case PERF_TYPE_HARDWARE:
+		if (is_sampling_event(event))	/* No sampling support */
+			return -ENOENT;
 		ev = attr->config;
 		/* Count user space (problem-state) only */
 		if (!attr->exclude_user && attr->exclude_kernel) {
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index e7a43a30e3ff..47692c78d09c 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -833,6 +833,8 @@ void __init setup_arch(char **cmdline_p)
 		pr_info("Linux is running under KVM in 64-bit mode\n");
 	else if (MACHINE_IS_LPAR)
 		pr_info("Linux is running natively in 64-bit mode\n");
+	else
+		pr_info("Linux is running as a guest in 64-bit mode\n");
 
 	/* Have one command line that is parsed and saved in /proc/cmdline */
 	/* boot_command_line has been already set up in early.c */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 77f4f334a465..29e5409c0d48 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -360,9 +360,13 @@ void smp_call_online_cpu(void (*func)(void *), void *data)
  */
 void smp_call_ipl_cpu(void (*func)(void *), void *data)
 {
+	struct _lowcore *lc = pcpu_devices->lowcore;
+
+	if (pcpu_devices[0].address == stap())
+		lc = &S390_lowcore;
+
 	pcpu_delegate(&pcpu_devices[0], func, data,
-		      pcpu_devices->lowcore->panic_stack -
-		      PANIC_FRAME_OFFSET + PAGE_SIZE);
+		      lc->panic_stack - PANIC_FRAME_OFFSET + PAGE_SIZE);
 }
 
 int smp_find_processor_id(u16 address)
@@ -1152,7 +1156,11 @@ static ssize_t __ref rescan_store(struct device *dev,
 {
 	int rc;
 
+	rc = lock_device_hotplug_sysfs();
+	if (rc)
+		return rc;
 	rc = smp_rescan_cpus();
+	unlock_device_hotplug();
 	return rc ? rc : count;
 }
 static DEVICE_ATTR(rescan, 0200, NULL, rescan_store);
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 12bbf0e8478f..7ad41be8b373 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -242,7 +242,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	start += nr << PAGE_SHIFT;
 	pages += nr;
 	ret = get_user_pages_unlocked(current, mm, start,
-			     nr_pages - nr, write, 0, pages);
+			     nr_pages - nr, pages, write ? FOLL_WRITE : 0);
 	/* Have to be a bit careful with return values */
 	if (nr > 0)
 		ret = (ret < 0) ? nr : ret + nr;
diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c
index e7af6a65baab..8c51a0e94854 100644
--- a/arch/sh/mm/gup.c
+++ b/arch/sh/mm/gup.c
@@ -258,7 +258,8 @@ slow_irqon:
 		pages += nr;
 
 		ret = get_user_pages_unlocked(current, mm, start,
-			(end - start) >> PAGE_SHIFT, write, 0, pages);
+			(end - start) >> PAGE_SHIFT, pages,
+			write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index 2e5c4fc2daa9..150f48303fb0 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -250,7 +250,8 @@ slow:
 		pages += nr;
 
 		ret = get_user_pages_unlocked(current, mm, start,
-			(end - start) >> PAGE_SHIFT, write, 0, pages);
+			(end - start) >> PAGE_SHIFT, pages,
+			write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index 18eb9924dda3..aeb430212947 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -197,12 +197,17 @@ static inline pte_t pte_mkold(pte_t pte)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 { 
-	pte_clear_bits(pte, _PAGE_RW);
+	if (likely(pte_get_bits(pte, _PAGE_RW)))
+		pte_clear_bits(pte, _PAGE_RW);
+	else
+		return pte;
 	return(pte_mknewprot(pte)); 
 }
 
 static inline pte_t pte_mkread(pte_t pte)
 { 
+	if (unlikely(pte_get_bits(pte, _PAGE_USER)))
+		return pte;
 	pte_set_bits(pte, _PAGE_USER);
 	return(pte_mknewprot(pte)); 
 }
@@ -221,6 +226,8 @@ static inline pte_t pte_mkyoung(pte_t pte)
 
 static inline pte_t pte_mkwrite(pte_t pte)	
 {
+	if (unlikely(pte_get_bits(pte,  _PAGE_RW)))
+		return pte;
 	pte_set_bits(pte, _PAGE_RW);
 	return(pte_mknewprot(pte)); 
 }
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 31dab2135188..21332b431f10 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -25,8 +25,8 @@ static inline u16 i8254(void)
 	u16 status, timer;
 
 	do {
-		outb(I8254_PORT_CONTROL,
-		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0,
+		     I8254_PORT_CONTROL);
 		status = inb(I8254_PORT_COUNTER0);
 		timer  = inb(I8254_PORT_COUNTER0);
 		timer |= inb(I8254_PORT_COUNTER0) << 8;
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 8baaff5af0b5..75b9d43069f1 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -77,6 +77,7 @@ static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
 	err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
 
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index ae6aad1d24f7..b348c4641312 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -50,7 +50,7 @@ static unsigned long get_dr(int n)
 /*
  * fill in the user structure for a core dump..
  */
-static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
+static void fill_dump(struct pt_regs *regs, struct user32 *dump)
 {
 	u32 fs, gs;
 	memset(dump, 0, sizeof(*dump));
@@ -156,10 +156,12 @@ static int aout_core_dump(struct coredump_params *cprm)
 	fs = get_fs();
 	set_fs(KERNEL_DS);
 	has_dumped = 1;
+
+	fill_dump(cprm->regs, &dump);
+
 	strncpy(dump.u_comm, current->comm, sizeof(current->comm));
 	dump.u_ar0 = offsetof(struct user32, regs);
 	dump.signal = cprm->siginfo->si_signo;
-	dump_thread32(cprm->regs, &dump);
 
 	/*
 	 * If the size of the dump file exceeds the rlimit, then see
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 16825dda18dc..66a5e60f60c4 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -94,6 +94,9 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 #define user_insn(insn, output, input...)				\
 ({									\
 	int err;							\
+									\
+	might_fault();							\
+									\
 	asm volatile(ASM_STAC "\n"					\
 		     "1:" #insn "\n\t"					\
 		     "2: " ASM_CLAC "\n"				\
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3a37cdbdfbaa..2cb49ac1b2b2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -765,7 +765,7 @@ struct kvm_x86_ops {
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
-	bool (*cpu_has_high_real_mode_segbase)(void);
+	bool (*has_emulated_msr)(int index);
 	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	/* Create, but do not attach this VCPU */
@@ -1200,7 +1200,7 @@ asmlinkage void kvm_spurious_fault(void);
 	"cmpb $0, kvm_rebooting \n\t"	      \
 	"jne 668b \n\t"      		      \
 	__ASM_SIZE(push) " $666b \n\t"	      \
-	"call kvm_spurious_fault \n\t"	      \
+	"jmp kvm_spurious_fault \n\t"	      \
 	".popsection \n\t" \
 	_ASM_EXTABLE(666b, 667b)
 
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 4928cf0d5af0..fb1251946b45 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -2,7 +2,11 @@
 #define _ASM_X86_PAGE_64_DEFS_H
 
 #ifdef CONFIG_KASAN
+#ifdef CONFIG_KASAN_EXTRA
+#define KASAN_STACK_ORDER 2
+#else
 #define KASAN_STACK_ORDER 1
+#endif
 #else
 #define KASAN_STACK_ORDER 0
 #endif
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index d788b0cdc0ad..ac6932bf1a01 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -144,6 +144,14 @@ extern int __get_user_4(void);
 extern int __get_user_8(void);
 extern int __get_user_bad(void);
 
+#define __uaccess_begin() stac()
+#define __uaccess_end()   clac()
+#define __uaccess_begin_nospec()	\
+({					\
+	stac();				\
+	barrier_nospec();		\
+})
+
 /*
  * This is a type: either unsigned long, if the argument fits into
  * that type, or otherwise unsigned long long.
@@ -203,10 +211,10 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 
 #ifdef CONFIG_X86_32
 #define __put_user_asm_u64(x, addr, err, errret)			\
-	asm volatile(ASM_STAC "\n"					\
+	asm volatile("\n"						\
 		     "1:	movl %%eax,0(%2)\n"			\
 		     "2:	movl %%edx,4(%2)\n"			\
-		     "3: " ASM_CLAC "\n"				\
+		     "3:"						\
 		     ".section .fixup,\"ax\"\n"				\
 		     "4:	movl %3,%0\n"				\
 		     "	jmp 3b\n"					\
@@ -217,10 +225,10 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 		     : "A" (x), "r" (addr), "i" (errret), "0" (err))
 
 #define __put_user_asm_ex_u64(x, addr)					\
-	asm volatile(ASM_STAC "\n"					\
+	asm volatile("\n"						\
 		     "1:	movl %%eax,0(%1)\n"			\
 		     "2:	movl %%edx,4(%1)\n"			\
-		     "3: " ASM_CLAC "\n"				\
+		     "3:"						\
 		     _ASM_EXTABLE_EX(1b, 2b)				\
 		     _ASM_EXTABLE_EX(2b, 3b)				\
 		     : : "A" (x), "r" (addr))
@@ -306,14 +314,17 @@ do {									\
 		__put_user_asm(x, ptr, retval, "l", "k", "ir", errret);	\
 		break;							\
 	case 8:								\
-		__put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval,	\
-				   errret);				\
+		__put_user_asm_u64(x, ptr, retval, errret);		\
 		break;							\
 	default:							\
 		__put_user_bad();					\
 	}								\
 } while (0)
 
+/*
+ * This doesn't do __uaccess_begin/end - the exception handling
+ * around it must do that.
+ */
 #define __put_user_size_ex(x, ptr, size)				\
 do {									\
 	__chk_user_ptr(ptr);						\
@@ -368,9 +379,9 @@ do {									\
 } while (0)
 
 #define __get_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
-	asm volatile(ASM_STAC "\n"					\
+	asm volatile("\n"						\
 		     "1:	mov"itype" %2,%"rtype"1\n"		\
-		     "2: " ASM_CLAC "\n"				\
+		     "2:\n"						\
 		     ".section .fixup,\"ax\"\n"				\
 		     "3:	mov %3,%0\n"				\
 		     "	xor"itype" %"rtype"1,%"rtype"1\n"		\
@@ -380,6 +391,10 @@ do {									\
 		     : "=r" (err), ltype(x)				\
 		     : "m" (__m(addr)), "i" (errret), "0" (err))
 
+/*
+ * This doesn't do __uaccess_begin/end - the exception handling
+ * around it must do that.
+ */
 #define __get_user_size_ex(x, ptr, size)				\
 do {									\
 	__chk_user_ptr(ptr);						\
@@ -410,7 +425,11 @@ do {									\
 #define __put_user_nocheck(x, ptr, size)			\
 ({								\
 	int __pu_err;						\
-	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
+	__typeof__(*(ptr)) __pu_val;				\
+	__pu_val = x;						\
+	__uaccess_begin();					\
+	__put_user_size(__pu_val, (ptr), (size), __pu_err, -EFAULT);\
+	__uaccess_end();					\
 	__builtin_expect(__pu_err, 0);				\
 })
 
@@ -418,7 +437,9 @@ do {									\
 ({									\
 	int __gu_err;							\
 	unsigned long __gu_val;						\
+	__uaccess_begin_nospec();					\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
+	__uaccess_end();						\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 	__builtin_expect(__gu_err, 0);					\
 })
@@ -433,9 +454,9 @@ struct __large_struct { unsigned long buf[100]; };
  * aliasing issues.
  */
 #define __put_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
-	asm volatile(ASM_STAC "\n"					\
+	asm volatile("\n"						\
 		     "1:	mov"itype" %"rtype"1,%2\n"		\
-		     "2: " ASM_CLAC "\n"				\
+		     "2:\n"						\
 		     ".section .fixup,\"ax\"\n"				\
 		     "3:	mov %3,%0\n"				\
 		     "	jmp 2b\n"					\
@@ -455,11 +476,15 @@ struct __large_struct { unsigned long buf[100]; };
  */
 #define uaccess_try	do {						\
 	current_thread_info()->uaccess_err = 0;				\
-	stac();								\
+	__uaccess_begin();						\
 	barrier();
 
+#define uaccess_try_nospec do {						\
+	current_thread_info()->uaccess_err = 0;				\
+	__uaccess_begin_nospec();					\
+
 #define uaccess_catch(err)						\
-	clac();								\
+	__uaccess_end();						\
 	(err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0);	\
 } while (0)
 
@@ -522,7 +547,7 @@ struct __large_struct { unsigned long buf[100]; };
  *	get_user_ex(...);
  * } get_user_catch(err)
  */
-#define get_user_try		uaccess_try
+#define get_user_try		uaccess_try_nospec
 #define get_user_catch(err)	uaccess_catch(err)
 
 #define get_user_ex(x, ptr)	do {					\
@@ -557,12 +582,13 @@ extern void __cmpxchg_wrong_size(void)
 	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
+	__uaccess_begin_nospec();					\
 	switch (size) {							\
 	case 1:								\
 	{								\
-		asm volatile("\t" ASM_STAC "\n"				\
+		asm volatile("\n"					\
 			"1:\t" LOCK_PREFIX "cmpxchgb %4, %2\n"		\
-			"2:\t" ASM_CLAC "\n"				\
+			"2:\n"						\
 			"\t.section .fixup, \"ax\"\n"			\
 			"3:\tmov     %3, %0\n"				\
 			"\tjmp     2b\n"				\
@@ -576,9 +602,9 @@ extern void __cmpxchg_wrong_size(void)
 	}								\
 	case 2:								\
 	{								\
-		asm volatile("\t" ASM_STAC "\n"				\
+		asm volatile("\n"					\
 			"1:\t" LOCK_PREFIX "cmpxchgw %4, %2\n"		\
-			"2:\t" ASM_CLAC "\n"				\
+			"2:\n"						\
 			"\t.section .fixup, \"ax\"\n"			\
 			"3:\tmov     %3, %0\n"				\
 			"\tjmp     2b\n"				\
@@ -592,9 +618,9 @@ extern void __cmpxchg_wrong_size(void)
 	}								\
 	case 4:								\
 	{								\
-		asm volatile("\t" ASM_STAC "\n"				\
+		asm volatile("\n"					\
 			"1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"		\
-			"2:\t" ASM_CLAC "\n"				\
+			"2:\n"						\
 			"\t.section .fixup, \"ax\"\n"			\
 			"3:\tmov     %3, %0\n"				\
 			"\tjmp     2b\n"				\
@@ -611,9 +637,9 @@ extern void __cmpxchg_wrong_size(void)
 		if (!IS_ENABLED(CONFIG_X86_64))				\
 			__cmpxchg_wrong_size();				\
 									\
-		asm volatile("\t" ASM_STAC "\n"				\
+		asm volatile("\n"					\
 			"1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n"		\
-			"2:\t" ASM_CLAC "\n"				\
+			"2:\n"						\
 			"\t.section .fixup, \"ax\"\n"			\
 			"3:\tmov     %3, %0\n"				\
 			"\tjmp     2b\n"				\
@@ -628,6 +654,7 @@ extern void __cmpxchg_wrong_size(void)
 	default:							\
 		__cmpxchg_wrong_size();					\
 	}								\
+	__uaccess_end();						\
 	*__uval = __old;						\
 	__ret;								\
 })
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index f5dcb5204dcd..f575ee3aea5c 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin_nospec();
 			__put_user_size(*(u8 *)from, (u8 __user *)to,
 					1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin_nospec();
 			__put_user_size(*(u16 *)from, (u16 __user *)to,
 					2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin_nospec();
 			__put_user_size(*(u32 *)from, (u32 __user *)to,
 					4, ret, 4);
+			__uaccess_end();
 			return ret;
 		case 8:
+			__uaccess_begin_nospec();
 			__put_user_size(*(u64 *)from, (u64 __user *)to,
 					8, ret, 8);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -170,13 +190,19 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to,
 
 		switch (n) {
 		case 1:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index d83a55b95a48..dc2d00e7ced3 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -56,35 +56,49 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
 	if (!__builtin_constant_p(size))
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
-	case 1:__get_user_asm(*(u8 *)dst, (u8 __user *)src,
+	case 1:
+		__uaccess_begin_nospec();
+		__get_user_asm(*(u8 *)dst, (u8 __user *)src,
 			      ret, "b", "b", "=q", 1);
+		__uaccess_end();
 		return ret;
-	case 2:__get_user_asm(*(u16 *)dst, (u16 __user *)src,
+	case 2:
+		__uaccess_begin_nospec();
+		__get_user_asm(*(u16 *)dst, (u16 __user *)src,
 			      ret, "w", "w", "=r", 2);
+		__uaccess_end();
 		return ret;
-	case 4:__get_user_asm(*(u32 *)dst, (u32 __user *)src,
+	case 4:
+		__uaccess_begin_nospec();
+		__get_user_asm(*(u32 *)dst, (u32 __user *)src,
 			      ret, "l", "k", "=r", 4);
+		__uaccess_end();
 		return ret;
-	case 8:__get_user_asm(*(u64 *)dst, (u64 __user *)src,
+	case 8:
+		__uaccess_begin_nospec();
+		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			      ret, "q", "", "=r", 8);
+		__uaccess_end();
 		return ret;
 	case 10:
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 10);
-		if (unlikely(ret))
-			return ret;
-		__get_user_asm(*(u16 *)(8 + (char *)dst),
-			       (u16 __user *)(8 + (char __user *)src),
-			       ret, "w", "w", "=r", 2);
+		if (likely(!ret))
+			__get_user_asm(*(u16 *)(8 + (char *)dst),
+				       (u16 __user *)(8 + (char __user *)src),
+				       ret, "w", "w", "=r", 2);
+		__uaccess_end();
 		return ret;
 	case 16:
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 16);
-		if (unlikely(ret))
-			return ret;
-		__get_user_asm(*(u64 *)(8 + (char *)dst),
-			       (u64 __user *)(8 + (char __user *)src),
-			       ret, "q", "", "=r", 8);
+		if (likely(!ret))
+			__get_user_asm(*(u64 *)(8 + (char *)dst),
+				       (u64 __user *)(8 + (char __user *)src),
+				       ret, "q", "", "=r", 8);
+		__uaccess_end();
 		return ret;
 	default:
 		return copy_user_generic(dst, (__force void *)src, size);
@@ -106,35 +120,51 @@ int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size)
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst, src, size);
 	switch (size) {
-	case 1:__put_user_asm(*(u8 *)src, (u8 __user *)dst,
+	case 1:
+		__uaccess_begin();
+		__put_user_asm(*(u8 *)src, (u8 __user *)dst,
 			      ret, "b", "b", "iq", 1);
+		__uaccess_end();
 		return ret;
-	case 2:__put_user_asm(*(u16 *)src, (u16 __user *)dst,
+	case 2:
+		__uaccess_begin();
+		__put_user_asm(*(u16 *)src, (u16 __user *)dst,
 			      ret, "w", "w", "ir", 2);
+		__uaccess_end();
 		return ret;
-	case 4:__put_user_asm(*(u32 *)src, (u32 __user *)dst,
+	case 4:
+		__uaccess_begin();
+		__put_user_asm(*(u32 *)src, (u32 __user *)dst,
 			      ret, "l", "k", "ir", 4);
+		__uaccess_end();
 		return ret;
-	case 8:__put_user_asm(*(u64 *)src, (u64 __user *)dst,
+	case 8:
+		__uaccess_begin();
+		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
 			      ret, "q", "", "er", 8);
+		__uaccess_end();
 		return ret;
 	case 10:
+		__uaccess_begin();
 		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
 			       ret, "q", "", "er", 10);
-		if (unlikely(ret))
-			return ret;
-		asm("":::"memory");
-		__put_user_asm(4[(u16 *)src], 4 + (u16 __user *)dst,
-			       ret, "w", "w", "ir", 2);
+		if (likely(!ret)) {
+			asm("":::"memory");
+			__put_user_asm(4[(u16 *)src], 4 + (u16 __user *)dst,
+				       ret, "w", "w", "ir", 2);
+		}
+		__uaccess_end();
 		return ret;
 	case 16:
+		__uaccess_begin();
 		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
 			       ret, "q", "", "er", 16);
-		if (unlikely(ret))
-			return ret;
-		asm("":::"memory");
-		__put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst,
-			       ret, "q", "", "er", 8);
+		if (likely(!ret)) {
+			asm("":::"memory");
+			__put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst,
+				       ret, "q", "", "er", 8);
+		}
+		__uaccess_end();
 		return ret;
 	default:
 		return copy_user_generic((__force void *)dst, src, size);
@@ -160,39 +190,47 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	switch (size) {
 	case 1: {
 		u8 tmp;
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u8 __user *)src,
 			       ret, "b", "b", "=q", 1);
 		if (likely(!ret))
 			__put_user_asm(tmp, (u8 __user *)dst,
 				       ret, "b", "b", "iq", 1);
+		__uaccess_end();
 		return ret;
 	}
 	case 2: {
 		u16 tmp;
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u16 __user *)src,
 			       ret, "w", "w", "=r", 2);
 		if (likely(!ret))
 			__put_user_asm(tmp, (u16 __user *)dst,
 				       ret, "w", "w", "ir", 2);
+		__uaccess_end();
 		return ret;
 	}
 
 	case 4: {
 		u32 tmp;
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u32 __user *)src,
 			       ret, "l", "k", "=r", 4);
 		if (likely(!ret))
 			__put_user_asm(tmp, (u32 __user *)dst,
 				       ret, "l", "k", "ir", 4);
+		__uaccess_end();
 		return ret;
 	}
 	case 8: {
 		u64 tmp;
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u64 __user *)src,
 			       ret, "q", "", "=r", 8);
 		if (likely(!ret))
 			__put_user_asm(tmp, (u64 __user *)dst,
 				       ret, "q", "", "er", 8);
+		__uaccess_end();
 		return ret;
 	}
 	default:
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9f6151884249..e94e6f16172b 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -716,11 +716,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 static void init_amd_zn(struct cpuinfo_x86 *c)
 {
 	set_cpu_cap(c, X86_FEATURE_ZEN);
-	/*
-	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
-	 * all up to and including B1.
-	 */
-	if (c->x86_model <= 1 && c->x86_mask <= 1)
+
+	/* Fix erratum 1076: CPB feature bit not being set in CPUID. */
+	if (!cpu_has(c, X86_FEATURE_CPB))
 		set_cpu_cap(c, X86_FEATURE_CPB);
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b12c0287d6cf..e8b46f575306 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -693,7 +693,8 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
 		set_cpu_cap(c, X86_FEATURE_STIBP);
 
-	if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD))
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) ||
+	    cpu_has(c, X86_FEATURE_VIRT_SSBD))
 		set_cpu_cap(c, X86_FEATURE_SSBD);
 
 	if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7b8c8c838191..77f7580e22c6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -670,6 +670,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 		}
 
 		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			m->bank = i;
 			*msg = tmp;
 			ret = 1;
 		}
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index d76f13d6d8d6..ec894bf5eeb0 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -173,6 +173,8 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 	struct mtrr_gentry gentry;
 	void __user *arg = (void __user *) __arg;
 
+	memset(&gentry, 0, sizeof(gentry));
+
 	switch (cmd) {
 	case MTRRIOC_ADD_ENTRY:
 	case MTRRIOC_SET_ENTRY:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index f0f4fcba252e..947579425861 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -1081,6 +1081,8 @@ static struct pci_driver snbep_uncore_pci_driver = {
 	.id_table	= snbep_uncore_pci_ids,
 };
 
+#define NODE_ID_MASK	0x7
+
 /*
  * build pci bus to socket mapping
  */
@@ -1102,7 +1104,7 @@ static int snbep_pci2phy_map_init(int devid)
 		err = pci_read_config_dword(ubox_dev, 0x40, &config);
 		if (err)
 			break;
-		nodeid = config;
+		nodeid = config & NODE_ID_MASK;
 		/* get the Node ID mapping */
 		err = pci_read_config_dword(ubox_dev, 0x54, &config);
 		if (err)
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 0f8a6bbaaa44..0bf17576dd2a 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -168,6 +168,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr,
 	struct efi_info *current_ei = &boot_params.efi_info;
 	struct efi_info *ei = &params->efi_info;
 
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return 0;
+
 	if (!current_ei->efi_memmap_size)
 		return 0;
 
diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c
index d1d35ccffed3..579f8f813ce0 100644
--- a/arch/x86/kernel/livepatch.c
+++ b/arch/x86/kernel/livepatch.c
@@ -58,6 +58,7 @@ int klp_write_module_reloc(struct module *mod, unsigned long type,
 		val = (s32)value;
 		break;
 	case R_X86_64_PC32:
+	case R_X86_64_PLT32:
 		val = (u32)(value - loc);
 		break;
 	default:
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 338d13d4fd2f..b857bb9f6f23 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -341,6 +341,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) |
 		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
 
+	/* cpuid 0x80000008.ebx */
+	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
+		F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD);
+
 	/* cpuid 0xC0000001.edx */
 	const u32 kvm_supported_word5_x86_features =
 		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
@@ -358,6 +362,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	const u32 kvm_supported_word10_x86_features =
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves;
 
+	/* cpuid 7.0.edx*/
+	const u32 kvm_cpuid_7_0_edx_x86_features =
+		F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES);
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -435,11 +443,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			cpuid_mask(&entry->ebx, 9);
 			// TSC_ADJUST is emulated
 			entry->ebx |= F(TSC_ADJUST);
-		} else
+			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+			cpuid_mask(&entry->edx, CPUID_7_EDX);
+		} else {
 			entry->ebx = 0;
+			entry->edx = 0;
+		}
 		entry->eax = 0;
 		entry->ecx = 0;
-		entry->edx = 0;
 		break;
 	}
 	case 9:
@@ -583,7 +594,21 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		if (!g_phys_as)
 			g_phys_as = phys_as;
 		entry->eax = g_phys_as | (virt_as << 8);
-		entry->ebx = entry->edx = 0;
+		entry->edx = 0;
+		/*
+		 * IBRS, IBPB and VIRT_SSBD aren't necessarily present in
+		 * hardware cpuid
+		 */
+		if (boot_cpu_has(X86_FEATURE_AMD_IBPB))
+			entry->ebx |= F(AMD_IBPB);
+		if (boot_cpu_has(X86_FEATURE_AMD_IBRS))
+			entry->ebx |= F(AMD_IBRS);
+		if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
+		entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
+		cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX);
+		if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
 		break;
 	}
 	case 0x80000019:
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index d1534feefcfe..72f159f4d456 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -159,6 +159,46 @@ static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
 	return best && (best->edx & bit(X86_FEATURE_RDTSCP));
 }
 
+static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	if (best && (best->ebx & bit(X86_FEATURE_AMD_IBPB)))
+		return true;
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL));
+}
+
+static inline bool guest_cpuid_has_spec_ctrl(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	if (best && (best->ebx & bit(X86_FEATURE_AMD_IBRS)))
+		return true;
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->edx & (bit(X86_FEATURE_SPEC_CTRL) | bit(X86_FEATURE_SPEC_CTRL_SSBD)));
+}
+
+static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->edx & bit(X86_FEATURE_ARCH_CAPABILITIES));
+}
+
+static inline bool guest_cpuid_has_virt_ssbd(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	return best && (best->ebx & bit(X86_FEATURE_VIRT_SSBD));
+}
+
+
+
 /*
  * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3
  */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a1afd80a68aa..3c70f6c76d3a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -56,7 +56,7 @@
 #define APIC_BUS_CYCLE_NS 1
 
 /* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
-#define apic_debug(fmt, arg...)
+#define apic_debug(fmt, arg...) do {} while (0)
 
 #define APIC_LVT_NUM			6
 /* 14 is the version for Xeon and Pentium 8.4.8*/
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index df7827a981dd..acbde1249b6f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -37,6 +37,7 @@
 #include <asm/desc.h>
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
+#include <asm/microcode.h>
 #include <asm/spec-ctrl.h>
 
 #include <asm/virtext.h>
@@ -147,6 +148,14 @@ struct vcpu_svm {
 		u64 gs_base;
 	} host;
 
+	u64 spec_ctrl;
+	/*
+	 * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
+	 * translated into the appropriate L2_CFG bits on the host to
+	 * perform speculative control.
+	 */
+	u64 virt_spec_ctrl;
+
 	u32 *msrpm;
 
 	ulong nmi_iret_rip;
@@ -182,6 +191,8 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_CSTAR,				.always = true  },
 	{ .index = MSR_SYSCALL_MASK,			.always = true  },
 #endif
+	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
+	{ .index = MSR_IA32_PRED_CMD,			.always = false },
 	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
@@ -411,6 +422,7 @@ struct svm_cpu_data {
 	struct kvm_ldttss_desc *tss_desc;
 
 	struct page *save_area;
+	struct vmcb *current_vmcb;
 };
 
 static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
@@ -762,6 +774,25 @@ static bool valid_msr_intercept(u32 index)
 	return false;
 }
 
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
+{
+	u8 bit_write;
+	unsigned long tmp;
+	u32 offset;
+	u32 *msrpm;
+
+	msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm:
+				      to_svm(vcpu)->msrpm;
+
+	offset    = svm_msrpm_offset(msr);
+	bit_write = 2 * (msr & 0x0f) + 1;
+	tmp       = msrpm[offset];
+
+	BUG_ON(offset == MSR_INVALID);
+
+	return !!test_bit(bit_write,  &tmp);
+}
+
 static void set_msr_interception(u32 *msrpm, unsigned msr,
 				 int read, int write)
 {
@@ -1120,6 +1151,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	u32 dummy;
 	u32 eax = 1;
 
+	svm->spec_ctrl = 0;
+	svm->virt_spec_ctrl = 0;
+
 	if (!init_event) {
 		svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
 					   MSR_IA32_APICBASE_ENABLE;
@@ -1210,11 +1244,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
+	/*
+	 * The vmcb page can be recycled, causing a false negative in
+	 * svm_vcpu_load(). So do a full IBPB now.
+	 */
+	indirect_branch_prediction_barrier();
 }
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 	int i;
 
 	if (unlikely(cpu != vcpu->cpu)) {
@@ -1239,6 +1279,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
 		}
 	}
+	if (sd->current_vmcb != svm->vmcb) {
+		sd->current_vmcb = svm->vmcb;
+		indirect_branch_prediction_barrier();
+	}
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
@@ -2344,6 +2388,14 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	kvm_mmu_reset_context(&svm->vcpu);
 	kvm_mmu_load(&svm->vcpu);
 
+	/*
+	 * Drop what we picked up for L2 via svm_complete_interrupts() so it
+	 * doesn't end up in L1.
+	 */
+	svm->vcpu.arch.nmi_injected = false;
+	kvm_clear_exception_queue(&svm->vcpu);
+	kvm_clear_interrupt_queue(&svm->vcpu);
+
 	return 0;
 }
 
@@ -3051,6 +3103,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_VM_CR:
 		msr_info->data = svm->nested.vm_cr_msr;
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		msr_info->data = svm->spec_ctrl;
+		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_virt_ssbd(vcpu))
+			return 1;
+
+		msr_info->data = svm->virt_spec_ctrl;
+		break;
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = 0x01000065;
 		break;
@@ -3125,6 +3191,59 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr);
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		/* The STIBP bit doesn't fault even if it's not advertised */
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+			return 1;
+
+		svm->spec_ctrl = data;
+
+		if (!data)
+			break;
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_svm_vmrun_msrpm.
+		 * We update the L1 MSR bit as well since it will end up
+		 * touching the MSR anyway now.
+		 */
+		set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
+		break;
+	case MSR_IA32_PRED_CMD:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_ibpb(vcpu))
+			return 1;
+
+		if (data & ~PRED_CMD_IBPB)
+			return 1;
+
+		if (!data)
+			break;
+
+		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+		if (is_guest_mode(vcpu))
+			break;
+		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
+		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_virt_ssbd(vcpu))
+			return 1;
+
+		if (data & ~SPEC_CTRL_SSBD)
+			return 1;
+
+		svm->virt_spec_ctrl = data;
+		break;
 	case MSR_STAR:
 		svm->vmcb->save.star = data;
 		break;
@@ -3811,6 +3930,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	local_irq_enable();
 
+	/*
+	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
+	 * is no need to worry about the conditional branch over the wrmsr
+	 * being speculatively taken.
+	 */
+	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
+
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
 		"mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t"
@@ -3915,6 +4042,26 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 #endif
 
+	/*
+	 * We do not use IBRS in the kernel. If this vCPU has used the
+	 * SPEC_CTRL MSR it may have left it on; save the value and
+	 * turn it off. This is much more efficient than blindly adding
+	 * it to the atomic save/restore list. Especially as the former
+	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
+	 *
+	 * For non-nested case:
+	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 *
+	 * For nested case:
+	 * 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))
+		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
+
+	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
+
 	reload_tss(vcpu);
 
 	local_irq_disable();
@@ -4015,8 +4162,15 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
-static bool svm_has_high_real_mode_segbase(void)
+static bool svm_has_emulated_msr(int index)
 {
+	switch (index) {
+	case MSR_IA32_MCG_EXT_CTL:
+		return false;
+	default:
+		break;
+	}
+
 	return true;
 }
 
@@ -4299,7 +4453,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
 	.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
-	.cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
+	.has_emulated_msr = svm_has_emulated_msr,
 
 	.vcpu_create = svm_create_vcpu,
 	.vcpu_free = svm_free_vcpu,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c5a4b1978cbf..098be61a6b4c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -48,6 +48,7 @@
 #include <asm/kexec.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/microcode.h>
 #include <asm/spec-ctrl.h>
 
 #include "trace.h"
@@ -109,6 +110,14 @@ static u64 __read_mostly host_xss;
 static bool __read_mostly enable_pml = 1;
 module_param_named(pml, enable_pml, bool, S_IRUGO);
 
+#define MSR_TYPE_R	1
+#define MSR_TYPE_W	2
+#define MSR_TYPE_RW	3
+
+#define MSR_BITMAP_MODE_X2APIC		1
+#define MSR_BITMAP_MODE_X2APIC_APICV	2
+#define MSR_BITMAP_MODE_LM		4
+
 #define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL
 
 #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
@@ -172,7 +181,6 @@ module_param(ple_window_max, int, S_IRUGO);
 extern const ulong vmx_return;
 
 #define NR_AUTOLOAD_MSRS 8
-#define VMCS02_POOL_SIZE 1
 
 struct vmcs {
 	u32 revision_id;
@@ -189,6 +197,7 @@ struct loaded_vmcs {
 	struct vmcs *vmcs;
 	int cpu;
 	int launched;
+	unsigned long *msr_bitmap;
 	struct list_head loaded_vmcss_on_cpu_link;
 };
 
@@ -205,7 +214,7 @@ struct shared_msr_entry {
  * stored in guest memory specified by VMPTRLD, but is opaque to the guest,
  * which must access it using VMREAD/VMWRITE/VMCLEAR instructions.
  * More than one of these structures may exist, if L1 runs multiple L2 guests.
- * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the
+ * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the
  * underlying hardware which will be used to run L2.
  * This structure is packed to ensure that its layout is identical across
  * machines (necessary for live migration).
@@ -384,13 +393,6 @@ struct __packed vmcs12 {
  */
 #define VMCS12_SIZE 0x1000
 
-/* Used to remember the last vmcs02 used for some recently used vmcs12s */
-struct vmcs02_list {
-	struct list_head list;
-	gpa_t vmptr;
-	struct loaded_vmcs vmcs02;
-};
-
 /*
  * The nested_vmx structure is part of vcpu_vmx, and holds information we need
  * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -412,16 +414,16 @@ struct nested_vmx {
 	 */
 	bool sync_shadow_vmcs;
 
-	/* vmcs02_list cache of VMCSs recently used to run L2 guests */
-	struct list_head vmcs02_pool;
-	int vmcs02_num;
 	u64 vmcs01_tsc_offset;
 	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
+
+	struct loaded_vmcs vmcs02;
+
 	/*
-	 * Guest pages referred to in vmcs02 with host-physical pointers, so
-	 * we must keep them pinned while L2 runs.
+	 * Guest pages referred to in the vmcs02 with host-physical
+	 * pointers, so we must keep them pinned while L2 runs.
 	 */
 	struct page *apic_access_page;
 	struct page *virtual_apic_page;
@@ -531,6 +533,7 @@ struct vcpu_vmx {
 	unsigned long         host_rsp;
 	u8                    fail;
 	bool                  nmi_known_unmasked;
+	u8		      msr_bitmap_mode;
 	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
 	ulong                 rflags;
@@ -542,6 +545,10 @@ struct vcpu_vmx {
 	u64 		      msr_host_kernel_gs_base;
 	u64 		      msr_guest_kernel_gs_base;
 #endif
+
+	u64 		      arch_capabilities;
+	u64 		      spec_ctrl;
+
 	u32 vm_entry_controls_shadow;
 	u32 vm_exit_controls_shadow;
 	/*
@@ -889,6 +896,9 @@ static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static int alloc_identity_pagetable(struct kvm *kvm);
+static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
+static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+							  u32 msr, int type);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -908,11 +918,6 @@ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
 
 static unsigned long *vmx_io_bitmap_a;
 static unsigned long *vmx_io_bitmap_b;
-static unsigned long *vmx_msr_bitmap_legacy;
-static unsigned long *vmx_msr_bitmap_longmode;
-static unsigned long *vmx_msr_bitmap_legacy_x2apic;
-static unsigned long *vmx_msr_bitmap_longmode_x2apic;
-static unsigned long *vmx_msr_bitmap_nested;
 static unsigned long *vmx_vmread_bitmap;
 static unsigned long *vmx_vmwrite_bitmap;
 
@@ -1689,6 +1694,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
 
+/*
+ * Check if MSR is intercepted for currently loaded MSR bitmap.
+ */
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
+{
+	unsigned long *msr_bitmap;
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return true;
+
+	msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap;
+
+	if (msr <= 0x1fff) {
+		return !!test_bit(msr, msr_bitmap + 0x800 / f);
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+	}
+
+	return true;
+}
+
+/*
+ * Check if MSR is intercepted for L01 MSR bitmap.
+ */
+static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
+{
+	unsigned long *msr_bitmap;
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return true;
+
+	msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
+
+	if (msr <= 0x1fff) {
+		return !!test_bit(msr, msr_bitmap + 0x800 / f);
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+	}
+
+	return true;
+}
+
 static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 		unsigned long entry, unsigned long exit)
 {
@@ -2074,6 +2125,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
 		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
 		vmcs_load(vmx->loaded_vmcs->vmcs);
+		indirect_branch_prediction_barrier();
 	}
 
 	if (vmx->loaded_vmcs->cpu != cpu) {
@@ -2353,27 +2405,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
 	vmx->guest_msrs[from] = tmp;
 }
 
-static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
-{
-	unsigned long *msr_bitmap;
-
-	if (is_guest_mode(vcpu))
-		msr_bitmap = vmx_msr_bitmap_nested;
-	else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
-		if (is_long_mode(vcpu))
-			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
-		else
-			msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
-	} else {
-		if (is_long_mode(vcpu))
-			msr_bitmap = vmx_msr_bitmap_longmode;
-		else
-			msr_bitmap = vmx_msr_bitmap_legacy;
-	}
-
-	vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
-}
-
 /*
  * Set up the vmcs to automatically save and restore system
  * msrs.  Don't touch the 64-bit msrs if the guest is in legacy
@@ -2414,7 +2445,7 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 	vmx->save_nmsrs = save_nmsrs;
 
 	if (cpu_has_vmx_msr_bitmap())
-		vmx_set_msr_bitmap(&vmx->vcpu);
+		vmx_update_msr_bitmap(&vmx->vcpu);
 }
 
 /*
@@ -2828,6 +2859,19 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		msr_info->data = guest_read_tsc(vcpu);
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		msr_info->data = to_vmx(vcpu)->spec_ctrl;
+		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_arch_capabilities(vcpu))
+			return 1;
+		msr_info->data = to_vmx(vcpu)->arch_capabilities;
+		break;
 	case MSR_IA32_SYSENTER_CS:
 		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
 		break;
@@ -2927,6 +2971,68 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		/* The STIBP bit doesn't fault even if it's not advertised */
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+			return 1;
+
+		vmx->spec_ctrl = data;
+
+		if (!data)
+			break;
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_vmx_merge_msr_bitmap. We should not touch the
+		 * vmcs02.msr_bitmap here since it gets completely overwritten
+		 * in the merging. We update the vmcs01 here for L1 as well
+		 * since it will end up touching the MSR anyway now.
+		 */
+		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
+					      MSR_IA32_SPEC_CTRL,
+					      MSR_TYPE_RW);
+		break;
+	case MSR_IA32_PRED_CMD:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_ibpb(vcpu))
+			return 1;
+
+		if (data & ~PRED_CMD_IBPB)
+			return 1;
+
+		if (!data)
+			break;
+
+		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_vmx_merge_msr_bitmap. We should not touch the
+		 * vmcs02.msr_bitmap here since it gets completely overwritten
+		 * in the merging.
+		 */
+		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
+					      MSR_TYPE_W);
+		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated)
+			return 1;
+		vmx->arch_capabilities = data;
+		break;
 	case MSR_IA32_CR_PAT:
 		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
 			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
@@ -3352,11 +3458,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu)
 	return vmcs;
 }
 
-static struct vmcs *alloc_vmcs(void)
-{
-	return alloc_vmcs_cpu(raw_smp_processor_id());
-}
-
 static void free_vmcs(struct vmcs *vmcs)
 {
 	free_pages((unsigned long)vmcs, vmcs_config.order);
@@ -3372,6 +3473,34 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 	loaded_vmcs_clear(loaded_vmcs);
 	free_vmcs(loaded_vmcs->vmcs);
 	loaded_vmcs->vmcs = NULL;
+	if (loaded_vmcs->msr_bitmap)
+		free_page((unsigned long)loaded_vmcs->msr_bitmap);
+}
+
+static struct vmcs *alloc_vmcs(void)
+{
+	return alloc_vmcs_cpu(raw_smp_processor_id());
+}
+
+static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
+{
+	loaded_vmcs->vmcs = alloc_vmcs();
+	if (!loaded_vmcs->vmcs)
+		return -ENOMEM;
+
+	loaded_vmcs_init(loaded_vmcs);
+
+	if (cpu_has_vmx_msr_bitmap()) {
+		loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
+		if (!loaded_vmcs->msr_bitmap)
+			goto out_vmcs;
+		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
+	}
+	return 0;
+
+out_vmcs:
+	free_loaded_vmcs(loaded_vmcs);
+	return -ENOMEM;
 }
 
 static void free_kvm_area(void)
@@ -4370,10 +4499,8 @@ static void free_vpid(int vpid)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-#define MSR_TYPE_R	1
-#define MSR_TYPE_W	2
-static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
-						u32 msr, int type)
+static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+							  u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
 
@@ -4407,8 +4534,8 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
 	}
 }
 
-static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
-						u32 msr, int type)
+static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+							 u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
 
@@ -4488,37 +4615,78 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
 	}
 }
 
-static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
+static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
+			     			      u32 msr, int type, bool value)
 {
-	if (!longmode_only)
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
-						msr, MSR_TYPE_R | MSR_TYPE_W);
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
-						msr, MSR_TYPE_R | MSR_TYPE_W);
+	if (value)
+		vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
+	else
+		vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
 }
 
-static void vmx_enable_intercept_msr_read_x2apic(u32 msr)
+static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
 {
-	__vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-			msr, MSR_TYPE_R);
-	__vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-			msr, MSR_TYPE_R);
+	u8 mode = 0;
+
+	if (cpu_has_secondary_exec_ctrls() &&
+	    (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
+	     SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
+		mode |= MSR_BITMAP_MODE_X2APIC;
+		if (enable_apicv)
+			mode |= MSR_BITMAP_MODE_X2APIC_APICV;
+	}
+
+	if (is_long_mode(vcpu))
+		mode |= MSR_BITMAP_MODE_LM;
+
+	return mode;
 }
 
-static void vmx_disable_intercept_msr_read_x2apic(u32 msr)
+#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+
+static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
+					 u8 mode)
 {
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-			msr, MSR_TYPE_R);
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-			msr, MSR_TYPE_R);
+	int msr;
+
+	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+		unsigned word = msr / BITS_PER_LONG;
+		msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
+		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+	}
+
+	if (mode & MSR_BITMAP_MODE_X2APIC) {
+		/*
+		 * TPR reads and writes can be virtualized even if virtual interrupt
+		 * delivery is not in use.
+		 */
+		vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
+		if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
+			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_ID), MSR_TYPE_R);
+			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
+			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
+			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
+		}
+	}
 }
 
-static void vmx_disable_intercept_msr_write_x2apic(u32 msr)
+static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
 {
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-			msr, MSR_TYPE_W);
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-			msr, MSR_TYPE_W);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	u8 mode = vmx_msr_bitmap_mode(vcpu);
+	u8 changed = mode ^ vmx->msr_bitmap_mode;
+
+	if (!changed)
+		return;
+
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW,
+				  !(mode & MSR_BITMAP_MODE_LM));
+
+	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
+		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
+
+	vmx->msr_bitmap_mode = mode;
 }
 
 static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
@@ -4526,6 +4694,28 @@ static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
 	return enable_apicv && lapic_in_kernel(vcpu);
 }
 
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	gfn_t gfn;
+
+	/*
+	 * Don't need to mark the APIC access page dirty; it is never
+	 * written to by the CPU during APIC virtualization.
+	 */
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+		gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+
+	if (nested_cpu_has_posted_intr(vmcs12)) {
+		gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+}
+
+
 static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4533,18 +4723,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	void *vapic_page;
 	u16 status;
 
-	if (vmx->nested.pi_desc &&
-	    vmx->nested.pi_pending) {
-		vmx->nested.pi_pending = false;
-		if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-			return;
-
-		max_irr = find_last_bit(
-			(unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+		return;
 
-		if (max_irr == 256)
-			return;
+	vmx->nested.pi_pending = false;
+	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+		return;
 
+	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (max_irr != 256) {
 		vapic_page = kmap(vmx->nested.virtual_apic_page);
 		__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
 		kunmap(vmx->nested.virtual_apic_page);
@@ -4556,6 +4743,8 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 			vmcs_write16(GUEST_INTR_STATUS, status);
 		}
 	}
+
+	nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
@@ -4818,7 +5007,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
 	}
 	if (cpu_has_vmx_msr_bitmap())
-		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));
+		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
 
 	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
 
@@ -4890,6 +5079,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
 
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 
@@ -4918,6 +5109,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	u64 cr0;
 
 	vmx->rmode.vm86_active = 0;
+	vmx->spec_ctrl = 0;
 
 	vmx->soft_vnmi_blocked = 0;
 
@@ -5382,6 +5574,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 static int handle_triple_fault(struct kvm_vcpu *vcpu)
 {
 	vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+	vcpu->mmio_needed = 0;
 	return 0;
 }
 
@@ -5973,9 +6166,24 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
-		skip_emulated_instruction(vcpu);
 		trace_kvm_fast_mmio(gpa);
-		return 1;
+		/*
+		* Doing kvm_skip_emulated_instruction() depends on undefined
+		* behavior: Intel's manual doesn't mandate
+		* VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG
+		* occurs and while on real hardware it was observed to be set,
+		* other hypervisors (namely Hyper-V) don't set it, we end up
+		* advancing IP with some random value. Disable fast mmio when
+		* running nested and keep it for real hardware in hope that
+		* VM_EXIT_INSTRUCTION_LEN will always be set correctly.
+		*/
+		if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) {
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		else
+			return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP,
+						       NULL, 0) == EMULATE_DONE;
 	}
 
 	ret = handle_mmio_page_fault(vcpu, gpa, true);
@@ -6159,7 +6367,7 @@ static void wakeup_handler(void)
 
 static __init int hardware_setup(void)
 {
-	int r = -ENOMEM, i, msr;
+	int r = -ENOMEM, i;
 
 	rdmsrl_safe(MSR_EFER, &host_efer);
 
@@ -6174,38 +6382,13 @@ static __init int hardware_setup(void)
 	if (!vmx_io_bitmap_b)
 		goto out;
 
-	vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_legacy)
-		goto out1;
-
-	vmx_msr_bitmap_legacy_x2apic =
-				(unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_legacy_x2apic)
-		goto out2;
-
-	vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_longmode)
-		goto out3;
-
-	vmx_msr_bitmap_longmode_x2apic =
-				(unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_longmode_x2apic)
-		goto out4;
-
-	if (nested) {
-		vmx_msr_bitmap_nested =
-			(unsigned long *)__get_free_page(GFP_KERNEL);
-		if (!vmx_msr_bitmap_nested)
-			goto out5;
-	}
-
 	vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_vmread_bitmap)
-		goto out6;
+		goto out1;
 
 	vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_vmwrite_bitmap)
-		goto out7;
+		goto out2;
 
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
@@ -6214,14 +6397,9 @@ static __init int hardware_setup(void)
 
 	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
-	memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
-	memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
-	if (nested)
-		memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE);
-
 	if (setup_vmcs_config(&vmcs_config) < 0) {
 		r = -EIO;
-		goto out8;
+		goto out3;
 	}
 
 	if (boot_cpu_has(X86_FEATURE_NX))
@@ -6287,38 +6465,8 @@ static __init int hardware_setup(void)
 		kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy;
 	}
 
-	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
-	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
-	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-
-	memcpy(vmx_msr_bitmap_legacy_x2apic,
-			vmx_msr_bitmap_legacy, PAGE_SIZE);
-	memcpy(vmx_msr_bitmap_longmode_x2apic,
-			vmx_msr_bitmap_longmode, PAGE_SIZE);
-
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
-	if (enable_apicv) {
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			vmx_disable_intercept_msr_read_x2apic(msr);
-
-		/* According SDM, in x2apic mode, the whole id reg is used.
-		 * But in KVM, it only use the highest eight bits. Need to
-		 * intercept it */
-		vmx_enable_intercept_msr_read_x2apic(0x802);
-		/* TMCCT */
-		vmx_enable_intercept_msr_read_x2apic(0x839);
-		/* TPR */
-		vmx_disable_intercept_msr_write_x2apic(0x808);
-		/* EOI */
-		vmx_disable_intercept_msr_write_x2apic(0x80b);
-		/* SELF-IPI */
-		vmx_disable_intercept_msr_write_x2apic(0x83f);
-	}
-
 	if (enable_ept) {
 		kvm_mmu_set_mask_ptes(0ull,
 			(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
@@ -6349,21 +6497,10 @@ static __init int hardware_setup(void)
 
 	return alloc_kvm_area();
 
-out8:
-	free_page((unsigned long)vmx_vmwrite_bitmap);
-out7:
-	free_page((unsigned long)vmx_vmread_bitmap);
-out6:
-	if (nested)
-		free_page((unsigned long)vmx_msr_bitmap_nested);
-out5:
-	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
-out4:
-	free_page((unsigned long)vmx_msr_bitmap_longmode);
 out3:
-	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
+	free_page((unsigned long)vmx_vmwrite_bitmap);
 out2:
-	free_page((unsigned long)vmx_msr_bitmap_legacy);
+	free_page((unsigned long)vmx_vmread_bitmap);
 out1:
 	free_page((unsigned long)vmx_io_bitmap_b);
 out:
@@ -6374,16 +6511,10 @@ out:
 
 static __exit void hardware_unsetup(void)
 {
-	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
-	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
-	free_page((unsigned long)vmx_msr_bitmap_legacy);
-	free_page((unsigned long)vmx_msr_bitmap_longmode);
 	free_page((unsigned long)vmx_io_bitmap_b);
 	free_page((unsigned long)vmx_io_bitmap_a);
 	free_page((unsigned long)vmx_vmwrite_bitmap);
 	free_page((unsigned long)vmx_vmread_bitmap);
-	if (nested)
-		free_page((unsigned long)vmx_msr_bitmap_nested);
 
 	free_kvm_area();
 }
@@ -6427,93 +6558,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu)
 }
 
 /*
- * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
- * We could reuse a single VMCS for all the L2 guests, but we also want the
- * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this
- * allows keeping them loaded on the processor, and in the future will allow
- * optimizations where prepare_vmcs02 doesn't need to set all the fields on
- * every entry if they never change.
- * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE
- * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first.
- *
- * The following functions allocate and free a vmcs02 in this pool.
- */
-
-/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */
-static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
-{
-	struct vmcs02_list *item;
-	list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
-		if (item->vmptr == vmx->nested.current_vmptr) {
-			list_move(&item->list, &vmx->nested.vmcs02_pool);
-			return &item->vmcs02;
-		}
-
-	if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
-		/* Recycle the least recently used VMCS. */
-		item = list_entry(vmx->nested.vmcs02_pool.prev,
-			struct vmcs02_list, list);
-		item->vmptr = vmx->nested.current_vmptr;
-		list_move(&item->list, &vmx->nested.vmcs02_pool);
-		return &item->vmcs02;
-	}
-
-	/* Create a new VMCS */
-	item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
-	if (!item)
-		return NULL;
-	item->vmcs02.vmcs = alloc_vmcs();
-	if (!item->vmcs02.vmcs) {
-		kfree(item);
-		return NULL;
-	}
-	loaded_vmcs_init(&item->vmcs02);
-	item->vmptr = vmx->nested.current_vmptr;
-	list_add(&(item->list), &(vmx->nested.vmcs02_pool));
-	vmx->nested.vmcs02_num++;
-	return &item->vmcs02;
-}
-
-/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */
-static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr)
-{
-	struct vmcs02_list *item;
-	list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
-		if (item->vmptr == vmptr) {
-			free_loaded_vmcs(&item->vmcs02);
-			list_del(&item->list);
-			kfree(item);
-			vmx->nested.vmcs02_num--;
-			return;
-		}
-}
-
-/*
- * Free all VMCSs saved for this vcpu, except the one pointed by
- * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs
- * must be &vmx->vmcs01.
- */
-static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
-{
-	struct vmcs02_list *item, *n;
-
-	WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01);
-	list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) {
-		/*
-		 * Something will leak if the above WARN triggers.  Better than
-		 * a use-after-free.
-		 */
-		if (vmx->loaded_vmcs == &item->vmcs02)
-			continue;
-
-		free_loaded_vmcs(&item->vmcs02);
-		list_del(&item->list);
-		kfree(item);
-		vmx->nested.vmcs02_num--;
-	}
-}
-
-/*
  * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
  * set the success or error code of an emulated VMX instruction, as specified
  * by Vol 2B, VMX Instruction Reference, "Conventions".
@@ -6613,6 +6657,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 	/* Addr = segment_base + offset */
 	/* offset = base + [index * scale] + displacement */
 	off = exit_qualification; /* holds the displacement */
+	if (addr_size == 1)
+		off = (gva_t)sign_extend64(off, 31);
+	else if (addr_size == 0)
+		off = (gva_t)sign_extend64(off, 15);
 	if (base_is_valid)
 		off += kvm_register_read(vcpu, base_reg);
 	if (index_is_valid)
@@ -6655,10 +6703,16 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
 		 */
 		exn = (s.unusable != 0);
-		/* Protected mode: #GP(0)/#SS(0) if the memory
-		 * operand is outside the segment limit.
+
+		/*
+		 * Protected mode: #GP(0)/#SS(0) if the memory operand is
+		 * outside the segment limit.  All CPUs that support VMX ignore
+		 * limit checks for flat segments, i.e. segments with base==0,
+		 * limit==0xffffffff and of type expand-up data or code.
 		 */
-		exn = exn || (off + sizeof(u64) > s.limit);
+		if (!(s.base == 0 && s.limit == 0xffffffff &&
+		     ((s.type & 8) || !(s.type & 4))))
+			exn = exn || (off + sizeof(u64) > s.limit);
 	}
 	if (exn) {
 		kvm_queue_exception_e(vcpu,
@@ -6786,6 +6840,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	struct vmcs *shadow_vmcs;
 	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
 		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	int r;
 
 	/* The Intel VMX Instruction Reference lists a bunch of bits that
 	 * are prerequisite to running VMXON, most notably cr4.VMXE must be
@@ -6825,10 +6880,14 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
+	r = alloc_loaded_vmcs(&vmx->nested.vmcs02);
+	if (r < 0)
+		goto out_vmcs02;
+
 	if (enable_shadow_vmcs) {
 		shadow_vmcs = alloc_vmcs();
 		if (!shadow_vmcs)
-			return -ENOMEM;
+			goto out_shadow_vmcs;
 		/* mark vmcs as shadow */
 		shadow_vmcs->revision_id |= (1u << 31);
 		/* init shadow vmcs */
@@ -6836,9 +6895,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		vmx->nested.current_shadow_vmcs = shadow_vmcs;
 	}
 
-	INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
-	vmx->nested.vmcs02_num = 0;
-
 	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_REL);
 	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
@@ -6850,6 +6906,12 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
 	return 1;
+
+out_shadow_vmcs:
+	free_loaded_vmcs(&vmx->nested.vmcs02);
+
+out_vmcs02:
+	return -ENOMEM;
 }
 
 /*
@@ -6916,12 +6978,13 @@ static void free_nested(struct vcpu_vmx *vmx)
 	if (!vmx->nested.vmxon)
 		return;
 
+	hrtimer_cancel(&vmx->nested.preemption_timer);
 	vmx->nested.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
 	nested_release_vmcs12(vmx);
 	if (enable_shadow_vmcs)
 		free_vmcs(vmx->nested.current_shadow_vmcs);
-	/* Unpin physical memory we referred to in current vmcs02 */
+	/* Unpin physical memory we referred to in the vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		nested_release_page(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
@@ -6937,7 +7000,7 @@ static void free_nested(struct vcpu_vmx *vmx)
 		vmx->nested.pi_desc = NULL;
 	}
 
-	nested_free_all_saved_vmcss(vmx);
+	free_loaded_vmcs(&vmx->nested.vmcs02);
 }
 
 /* Emulate the VMXOFF instruction */
@@ -6971,8 +7034,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 			vmptr + offsetof(struct vmcs12, launch_state),
 			&zero, sizeof(zero));
 
-	nested_free_vmcs02(vmx, vmptr);
-
 	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
 	return 1;
@@ -7757,6 +7818,19 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
+	/*
+	 * The host physical addresses of some pages of guest memory
+	 * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
+	 * Page). The CPU may write to these pages via their host
+	 * physical address while L2 is running, bypassing any
+	 * address-translation-based dirty tracking (e.g. EPT write
+	 * protection).
+	 *
+	 * Mark them dirty on every exit from L2 to prevent them from
+	 * getting out of sync with dirty tracking.
+	 */
+	nested_mark_vmcs12_pages_dirty(vcpu);
+
 	if (vmx->nested.nested_run_pending)
 		return false;
 
@@ -8244,7 +8318,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
-	vmx_set_msr_bitmap(vcpu);
+	vmx_update_msr_bitmap(vcpu);
 }
 
 static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
@@ -8413,9 +8487,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 		local_irq_enable();
 }
 
-static bool vmx_has_high_real_mode_segbase(void)
+static bool vmx_has_emulated_msr(int index)
 {
-	return enable_unrestricted_guest || emulate_invalid_guest_state;
+	switch (index) {
+	case MSR_IA32_SMBASE:
+		/*
+		 * We cannot do SMM unless we can run the guest in big
+		 * real mode.
+		 */
+		return enable_unrestricted_guest || emulate_invalid_guest_state;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		/* This is AMD only.  */
+		return false;
+	default:
+		return true;
+	}
 }
 
 static bool vmx_mpx_supported(void)
@@ -8607,7 +8693,16 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
 
+	/*
+	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
+	 * is no need to worry about the conditional branch over the wrmsr
+	 * being speculatively taken.
+	 */
+	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
+
 	vmx->__launched = vmx->loaded_vmcs->launched;
+
 	asm(
 		/* Store host registers */
 		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
@@ -8725,6 +8820,26 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 	      );
 
+	/*
+	 * We do not use IBRS in the kernel. If this vCPU has used the
+	 * SPEC_CTRL MSR it may have left it on; save the value and
+	 * turn it off. This is much more efficient than blindly adding
+	 * it to the atomic save/restore list. Especially as the former
+	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
+	 *
+	 * For non-nested case:
+	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 *
+	 * For nested case:
+	 * 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))
+		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
+
+	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
+
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
 
@@ -8824,6 +8939,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 {
 	int err;
 	struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	unsigned long *msr_bitmap;
 	int cpu;
 
 	if (!vmx)
@@ -8856,16 +8972,24 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx->guest_msrs)
 		goto free_pml;
 
-	vmx->loaded_vmcs = &vmx->vmcs01;
-	vmx->loaded_vmcs->vmcs = alloc_vmcs();
-	if (!vmx->loaded_vmcs->vmcs)
-		goto free_msrs;
 	if (!vmm_exclusive)
 		kvm_cpu_vmxon(__pa(per_cpu(vmxarea, raw_smp_processor_id())));
-	loaded_vmcs_init(vmx->loaded_vmcs);
+	err = alloc_loaded_vmcs(&vmx->vmcs01);
 	if (!vmm_exclusive)
 		kvm_cpu_vmxoff();
+	if (err < 0)
+		goto free_msrs;
 
+	msr_bitmap = vmx->vmcs01.msr_bitmap;
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+	vmx->msr_bitmap_mode = 0;
+
+	vmx->loaded_vmcs = &vmx->vmcs01;
 	cpu = get_cpu();
 	vmx_vcpu_load(&vmx->vcpu, cpu);
 	vmx->vcpu.cpu = cpu;
@@ -9248,9 +9372,26 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 {
 	int msr;
 	struct page *page;
-	unsigned long *msr_bitmap;
+	unsigned long *msr_bitmap_l1;
+	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
+	/*
+	 * pred_cmd & spec_ctrl are trying to verify two things:
+	 *
+	 * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
+	 *    ensures that we do not accidentally generate an L02 MSR bitmap
+	 *    from the L12 MSR bitmap that is too permissive.
+	 * 2. That L1 or L2s have actually used the MSR. This avoids
+	 *    unnecessarily merging of the bitmap if the MSR is unused. This
+	 *    works properly because we only update the L01 MSR bitmap lazily.
+	 *    So even if L0 should pass L1 these MSRs, the L01 bitmap is only
+	 *    updated to reflect this when L1 (or its L2s) actually write to
+	 *    the MSR.
+	 */
+	bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
+	bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
 
-	if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
+	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+	    !pred_cmd && !spec_ctrl)
 		return false;
 
 	page = nested_get_page(vcpu, vmcs12->msr_bitmap);
@@ -9258,59 +9399,46 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 		WARN_ON(1);
 		return false;
 	}
-	msr_bitmap = (unsigned long *)kmap(page);
+	msr_bitmap_l1 = (unsigned long *)kmap(page);
+
+	memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
 
 	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
 		if (nested_cpu_has_apic_reg_virt(vmcs12))
 			for (msr = 0x800; msr <= 0x8ff; msr++)
 				nested_vmx_disable_intercept_for_msr(
-					msr_bitmap,
-					vmx_msr_bitmap_nested,
+					msr_bitmap_l1, msr_bitmap_l0,
 					msr, MSR_TYPE_R);
-		/* TPR is allowed */
-		nested_vmx_disable_intercept_for_msr(msr_bitmap,
-				vmx_msr_bitmap_nested,
+
+		nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
 				MSR_TYPE_R | MSR_TYPE_W);
+
 		if (nested_cpu_has_vid(vmcs12)) {
-			/* EOI and self-IPI are allowed */
 			nested_vmx_disable_intercept_for_msr(
-				msr_bitmap,
-				vmx_msr_bitmap_nested,
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_EOI >> 4),
 				MSR_TYPE_W);
 			nested_vmx_disable_intercept_for_msr(
-				msr_bitmap,
-				vmx_msr_bitmap_nested,
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
 				MSR_TYPE_W);
 		}
-	} else {
-		/*
-		 * Enable reading intercept of all the x2apic
-		 * MSRs. We should not rely on vmcs12 to do any
-		 * optimizations here, it may have been modified
-		 * by L1.
-		 */
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				msr,
-				MSR_TYPE_R);
-
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
-				MSR_TYPE_W);
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_EOI >> 4),
-				MSR_TYPE_W);
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
-				MSR_TYPE_W);
 	}
+
+	if (spec_ctrl)
+		nested_vmx_disable_intercept_for_msr(
+					msr_bitmap_l1, msr_bitmap_l0,
+					MSR_IA32_SPEC_CTRL,
+					MSR_TYPE_R | MSR_TYPE_W);
+
+	if (pred_cmd)
+		nested_vmx_disable_intercept_for_msr(
+					msr_bitmap_l1, msr_bitmap_l0,
+					MSR_IA32_PRED_CMD,
+					MSR_TYPE_W);
+
 	kunmap(page);
 	nested_release_page_clean(page);
 
@@ -9729,10 +9857,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
-		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
-		/* MSR_BITMAP will be set by following vmx_set_efer. */
-	} else
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
+	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
+		; /* MSR_BITMAP will be set by following vmx_set_efer. */
+	else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 
 	/*
@@ -9784,6 +9912,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	else
 		vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
 
+	if (cpu_has_vmx_msr_bitmap())
+		vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
+
 	if (enable_vpid) {
 		/*
 		 * There is no direct mapping between vpid02 and vpid12, the
@@ -9876,7 +10007,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int cpu;
-	struct loaded_vmcs *vmcs02;
 	bool ia32e;
 	u32 msr_entry_idx;
 
@@ -10016,10 +10146,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * the nested entry.
 	 */
 
-	vmcs02 = nested_get_current_vmcs02(vmx);
-	if (!vmcs02)
-		return -ENOMEM;
-
 	enter_guest_mode(vcpu);
 
 	vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
@@ -10028,7 +10154,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
 
 	cpu = get_cpu();
-	vmx->loaded_vmcs = vmcs02;
+	vmx->loaded_vmcs = &vmx->nested.vmcs02;
 	vmx_vcpu_put(vcpu);
 	vmx_vcpu_load(vcpu, cpu);
 	vcpu->cpu = cpu;
@@ -10489,7 +10615,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 
 	if (cpu_has_vmx_msr_bitmap())
-		vmx_set_msr_bitmap(vcpu);
+		vmx_update_msr_bitmap(vcpu);
 
 	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
 				vmcs12->vm_exit_msr_load_count))
@@ -10540,10 +10666,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vm_exit_controls_init(vmx, vmcs_read32(VM_EXIT_CONTROLS));
 	vmx_segment_cache_clear(vmx);
 
-	/* if no vmcs02 cache requested, remove the one we used */
-	if (VMCS02_POOL_SIZE == 0)
-		nested_free_vmcs02(vmx, vmx->nested.current_vmptr);
-
 	load_vmcs12_host_state(vcpu, vmcs12);
 
 	/* Update TSC_OFFSET if TSC was changed while L2 ran */
@@ -10871,7 +10993,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.hardware_enable = hardware_enable,
 	.hardware_disable = hardware_disable,
 	.cpu_has_accelerated_tpr = report_flexpriority,
-	.cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
+	.has_emulated_msr = vmx_has_emulated_msr,
 
 	.vcpu_create = vmx_create_vcpu,
 	.vcpu_free = vmx_free_vcpu,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e6ab034f0bc7..706c5d63a53f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -961,6 +961,7 @@ static u32 msrs_to_save[] = {
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
+	MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES
 };
 
 static unsigned num_msrs_to_save;
@@ -984,6 +985,7 @@ static u32 emulated_msrs[] = {
 	MSR_IA32_MCG_STATUS,
 	MSR_IA32_MCG_CTL,
 	MSR_IA32_SMBASE,
+	MSR_AMD64_VIRT_SPEC_CTRL,
 };
 
 static unsigned num_emulated_msrs;
@@ -2583,7 +2585,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * fringe case that is not enabled except via specific settings
 		 * of the module parameters.
 		 */
-		r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+		r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
 		break;
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
@@ -4072,14 +4074,8 @@ static void kvm_init_msr_list(void)
 	num_msrs_to_save = j;
 
 	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		switch (emulated_msrs[i]) {
-		case MSR_IA32_SMBASE:
-			if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
-				continue;
-			break;
-		default:
-			break;
-		}
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+			continue;
 
 		if (j < i)
 			emulated_msrs[j] = emulated_msrs[i];
@@ -4251,6 +4247,13 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
 					  exception);
 }
@@ -5440,7 +5443,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		 * handle watchpoints yet, those would be handled in
 		 * the emulate_ops.
 		 */
-		if (kvm_vcpu_check_breakpoint(vcpu, &r))
+		if (!(emulation_type & EMULTYPE_SKIP) &&
+		    kvm_vcpu_check_breakpoint(vcpu, &r))
 			return r;
 
 		ctxt->interruptibility = 0;
@@ -5527,8 +5531,7 @@ restart:
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE &&
-		    (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+		if (r == EMULATE_DONE && ctxt->tf)
 			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
@@ -6475,6 +6478,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+			vcpu->mmio_needed = 0;
 			r = 0;
 			goto out;
 		}
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 91d93b95bd86..0a6fcae404f8 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -570,12 +570,12 @@ do {									\
 unsigned long __copy_to_user_ll(void __user *to, const void *from,
 				unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
 		n = __copy_user_intel(to, from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_to_user_ll);
@@ -583,12 +583,12 @@ EXPORT_SYMBOL(__copy_to_user_ll);
 unsigned long __copy_from_user_ll(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user_zeroing(to, from, n);
 	else
 		n = __copy_user_zeroing_intel(to, from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll);
@@ -596,13 +596,13 @@ EXPORT_SYMBOL(__copy_from_user_ll);
 unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
 					 unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
 		n = __copy_user_intel((void __user *)to,
 				      (const void *)from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nozero);
@@ -610,7 +610,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero);
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -619,7 +619,7 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 #else
 	__copy_user_zeroing(to, from, n);
 #endif
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache);
@@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache);
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_intel_nocache(to, from, n);
@@ -636,7 +636,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr
 #else
 	__copy_user(to, from, n);
 #endif
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index ae9a37bf1371..7d2542ad346a 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -388,7 +388,7 @@ slow_irqon:
 
 		ret = get_user_pages_unlocked(current, mm, start,
 					      (end - start) >> PAGE_SHIFT,
-					      write, 0, pages);
+					      pages, write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 7ed47b1e6f42..7e94fc6f608a 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -536,10 +536,9 @@ static int mpx_resolve_fault(long __user *addr, int write)
 {
 	long gup_ret;
 	int nr_pages = 1;
-	int force = 0;
 
 	gup_ret = get_user_pages(current, current->mm, (unsigned long)addr,
-				 nr_pages, write, force, NULL, NULL);
+				 nr_pages, write ? FOLL_WRITE : 0, NULL, NULL);
 	/*
 	 * get_user_pages() returns number of pages gotten.
 	 * 0 means we failed to fault in and get anything,
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
index 526536c81ddc..ca1e8e6dccc8 100644
--- a/arch/x86/pci/broadcom_bus.c
+++ b/arch/x86/pci/broadcom_bus.c
@@ -50,8 +50,8 @@ static void __init cnb20le_res(u8 bus, u8 slot, u8 func)
 	word1 = read_pci_config_16(bus, slot, func, 0xc0);
 	word2 = read_pci_config_16(bus, slot, func, 0xc2);
 	if (word1 != word2) {
-		res.start = (word1 << 16) | 0x0000;
-		res.end   = (word2 << 16) | 0xffff;
+		res.start = ((resource_size_t) word1 << 16) | 0x0000;
+		res.end   = ((resource_size_t) word2 << 16) | 0xffff;
 		res.flags = IORESOURCE_MEM;
 		update_res(info, res.start, res.end, res.flags, 0);
 	}
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 524142117296..82324fc25d5e 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -179,7 +179,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num)
 			num--;
 		}
 
-		if (efi_x >= si->lfb_width) {
+		if (efi_x + font->width > si->lfb_width) {
 			efi_x = 0;
 			efi_y += font->height;
 		}
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 22eeacba37cc..199e05f85e89 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -35,6 +35,7 @@ CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX is not set
 # CONFIG_PCI is not set
+CONFIG_VECTORS_OFFSET=0x00002000
 CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug"
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index c7b3bedbfffe..e3823b4f9d08 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -286,12 +286,13 @@ should_never_return:
 
 	movi	a2, cpu_start_ccount
 1:
+	memw
 	l32i	a3, a2, 0
 	beqi	a3, 0, 1b
 	movi	a3, 0
 	s32i	a3, a2, 0
-	memw
 1:
+	memw
 	l32i	a3, a2, 0
 	beqi	a3, 0, 1b
 	wsr	a3, ccount
@@ -328,11 +329,13 @@ ENTRY(cpu_restart)
 	rsr	a0, prid
 	neg	a2, a0
 	movi	a3, cpu_start_id
+	memw
 	s32i	a2, a3, 0
 #if XCHAL_DCACHE_IS_WRITEBACK
 	dhwbi	a3, 0
 #endif
 1:
+	memw
 	l32i	a2, a3, 0
 	dhi	a3, 0
 	bne	a2, a0, 1b
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index 4d02e38514f5..54bb8e0473a0 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -80,7 +80,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned i;
 
-	for (i = 0; i < max_cpus; ++i)
+	for_each_possible_cpu(i)
 		set_cpu_present(i, true);
 }
 
@@ -93,6 +93,11 @@ void __init smp_init_cpus(void)
 	pr_info("%s: Core Count = %d\n", __func__, ncpus);
 	pr_info("%s: Core Id = %d\n", __func__, core_id);
 
+	if (ncpus > NR_CPUS) {
+		ncpus = NR_CPUS;
+		pr_info("%s: limiting core count by %d\n", __func__, ncpus);
+	}
+
 	for (i = 0; i < ncpus; ++i)
 		set_cpu_possible(i, true);
 }
@@ -192,9 +197,11 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
 	int i;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	cpu_start_id = cpu;
-	system_flush_invalidate_dcache_range(
-			(unsigned long)&cpu_start_id, sizeof(cpu_start_id));
+	WRITE_ONCE(cpu_start_id, cpu);
+	/* Pairs with the third memw in the cpu_restart */
+	mb();
+	system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id,
+					     sizeof(cpu_start_id));
 #endif
 	smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1);
 
@@ -203,18 +210,21 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
 			ccount = get_ccount();
 		while (!ccount);
 
-		cpu_start_ccount = ccount;
+		WRITE_ONCE(cpu_start_ccount, ccount);
 
-		while (time_before(jiffies, timeout)) {
+		do {
+			/*
+			 * Pairs with the first two memws in the
+			 * .Lboot_secondary.
+			 */
 			mb();
-			if (!cpu_start_ccount)
-				break;
-		}
+			ccount = READ_ONCE(cpu_start_ccount);
+		} while (ccount && time_before(jiffies, timeout));
 
-		if (cpu_start_ccount) {
+		if (ccount) {
 			smp_call_function_single(0, mx_cpu_stop,
-					(void *)cpu, 1);
-			cpu_start_ccount = 0;
+						 (void *)cpu, 1);
+			WRITE_ONCE(cpu_start_ccount, 0);
 			return -EIO;
 		}
 	}
@@ -234,6 +244,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n",
 			__func__, cpu, idle, start_info.stack);
 
+	init_completion(&cpu_running);
 	ret = boot_secondary(cpu, idle);
 	if (ret == 0) {
 		wait_for_completion_timeout(&cpu_running,
@@ -295,8 +306,10 @@ void __cpu_die(unsigned int cpu)
 	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
 	while (time_before(jiffies, timeout)) {
 		system_invalidate_dcache_range((unsigned long)&cpu_start_id,
-				sizeof(cpu_start_id));
-		if (cpu_start_id == -cpu) {
+					       sizeof(cpu_start_id));
+		/* Pairs with the second memw in the cpu_restart */
+		mb();
+		if (READ_ONCE(cpu_start_id) == -cpu) {
 			platform_cpu_kill(cpu);
 			return;
 		}
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index b9ad9feadc2d..a992cb6a47db 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -87,7 +87,7 @@ static int ccount_timer_shutdown(struct clock_event_device *evt)
 		container_of(evt, struct ccount_timer, evt);
 
 	if (timer->irq_enabled) {
-		disable_irq(evt->irq);
+		disable_irq_nosync(evt->irq);
 		timer->irq_enabled = 0;
 	}
 	return 0;