Merge "Merge android-4.4.110 (5cc8c2e) into msm-4.4"

127 files changed, 2063 insertions, 717 deletions

diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h
index 4c51c05333c6..4cafffa80e2c 100644
--- a/arch/alpha/include/asm/mmu_context.h
+++ b/arch/alpha/include/asm/mmu_context.h
@@ -7,6 +7,7 @@
  * Copyright (C) 1996, Linus Torvalds
  */
 
+#include <linux/sched.h>
 #include <asm/machvec.h>
 #include <asm/compiler.h>
 #include <asm-generic/mm_hooks.h>
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 89442e98a837..3af570517903 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -668,6 +668,7 @@
 	ti,non-removable;
 	bus-width = <4>;
 	cap-power-off-card;
+	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_pins>;
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index c2a03c740e79..02bd6312d1d9 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -227,6 +227,7 @@
 				device_type = "pci";
 				ranges = <0x81000000 0 0          0x03000 0 0x00010000
 					  0x82000000 0 0x20013000 0x13000 0 0xffed000>;
+				bus-range = <0x00 0xff>;
 				#interrupt-cells = <1>;
 				num-lanes = <1>;
 				ti,hwmods = "pcie1";
@@ -262,6 +263,7 @@
 				device_type = "pci";
 				ranges = <0x81000000 0 0          0x03000 0 0x00010000
 					  0x82000000 0 0x30013000 0x13000 0 0xffed000>;
+				bus-range = <0x00 0xff>;
 				#interrupt-cells = <1>;
 				num-lanes = <1>;
 				ti,hwmods = "pcie2";
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index b2bc8e11471d..2c16d9e7c03c 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -512,4 +512,22 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.macro	bug, msg, line
+#ifdef CONFIG_THUMB2_KERNEL
+1:	.inst	0xde02
+#else
+1:	.inst	0xe7f001f2
+#endif
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+	.pushsection .rodata.str, "aMS", %progbits, 1
+2:	.asciz	"\msg"
+	.popsection
+	.pushsection __bug_table, "aw"
+	.align	2
+	.word	1b, 2b
+	.hword	\line
+	.popsection
+#endif
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h
index 5abaf5bbd985..bf1991263d2d 100644
--- a/arch/arm/include/asm/exception.h
+++ b/arch/arm/include/asm/exception.h
@@ -7,7 +7,7 @@
 #ifndef __ASM_ARM_EXCEPTION_H
 #define __ASM_ARM_EXCEPTION_H
 
-#include <linux/ftrace.h>
+#include <linux/interrupt.h>
 
 #define __exception	__attribute__((section(".exception.text")))
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index e22089fb44dc..98d6de177b7a 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -161,8 +161,7 @@
 #else
 #define VTTBR_X		(5 - KVM_T0SZ)
 #endif
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X)
 #define VTTBR_VMID_SHIFT  _AC(48, ULL)
 #define VTTBR_VMID_MASK(size)	(_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
@@ -209,6 +208,7 @@
 #define HSR_EC_IABT_HYP	(0x21)
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
+#define HSR_EC_MAX	(0x3f)
 
 #define HSR_WFI_IS_WFE		(_AC(1, UL) << 0)
 
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 9b32f76bb0dd..10f662498eb7 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -61,6 +61,7 @@ static inline void check_and_switch_context(struct mm_struct *mm,
 		cpu_switch_mm(mm->pgd, mm);
 }
 
+#ifndef MODULE
 #define finish_arch_post_lock_switch \
 	finish_arch_post_lock_switch
 static inline void finish_arch_post_lock_switch(void)
@@ -82,6 +83,7 @@ static inline void finish_arch_post_lock_switch(void)
 		preempt_enable_no_resched();
 	}
 }
+#endif /* !MODULE */
 
 #endif	/* CONFIG_MMU */
 
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index f9e412b97fbf..24a47af4d05f 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -18,7 +18,6 @@ struct undef_hook {
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static inline int __in_irqentry_text(unsigned long ptr)
 {
 	extern char __irqentry_text_start[];
@@ -27,12 +26,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
 	return ptr >= (unsigned long)&__irqentry_text_start &&
 	       ptr < (unsigned long)&__irqentry_text_end;
 }
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
-	return 0;
-}
-#endif
 
 static inline int in_exception_text(unsigned long ptr)
 {
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 0d22ad206d52..6d243e830516 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -295,6 +295,8 @@
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
+	tst	r1, #PSR_I_BIT | 0x0f
+	bne	1f
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -309,6 +311,7 @@
 						@ after ldm {}^
 	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
+1:	bug	"Returning to usermode but unexpected PSR bits set?", \@
 #elif defined(CONFIG_CPU_V7M)
 	@ V7M restore.
 	@ Note that we don't need to do clrex here as clearing the local
@@ -324,6 +327,8 @@
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [sp, #\offset + S_PC]	@ get pc
 	add	sp, sp, #\offset + S_SP
+	tst	r1, #PSR_I_BIT | 0x0f
+	bne	1f
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -336,6 +341,7 @@
 	.endif
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
+1:	bug	"Returning to usermode but unexpected PSR bits set?", \@
 #endif	/* !CONFIG_THUMB2_KERNEL */
 	.endm
 
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index be2ab6d3b91f..b2e234468cb5 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -105,6 +105,7 @@ SECTIONS
 			*(.exception.text)
 			__exception_text_end = .;
 			IRQENTRY_TEXT
+			SOFTIRQENTRY_TEXT
 			TEXT_TEXT
 			SCHED_TEXT
 			LOCK_TEXT
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 95f12b2ccdcb..f36b5b1acd1f 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -100,7 +100,19 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	kvm_pr_unimpl("Unknown exception class: hsr: %#08x\n",
+		      hsr);
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
+	[0 ... HSR_EC_MAX]	= kvm_handle_unknown_ec,
 	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
@@ -122,13 +134,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 {
 	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
 
-	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
-	    !arm_exit_handlers[hsr_ec]) {
-		kvm_err("Unknown exception class: hsr: %#08x\n",
-			(unsigned int)kvm_vcpu_get_hsr(vcpu));
-		BUG();
-	}
-
 	return arm_exit_handlers[hsr_ec];
 }
 
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 8633c703546a..2944af820558 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -367,7 +367,7 @@ static int gpmc_onenand_setup(void __iomem *onenand_base, int *freq_ptr)
 	return ret;
 }
 
-void gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
+int gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
 {
 	int err;
 	struct device *dev = &gpmc_onenand_device.dev;
@@ -393,15 +393,17 @@ void gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
 	if (err < 0) {
 		dev_err(dev, "Cannot request GPMC CS %d, error %d\n",
 			gpmc_onenand_data->cs, err);
-		return;
+		return err;
 	}
 
 	gpmc_onenand_resource.end = gpmc_onenand_resource.start +
 							ONENAND_IO_SIZE - 1;
 
-	if (platform_device_register(&gpmc_onenand_device) < 0) {
+	err = platform_device_register(&gpmc_onenand_device);
+	if (err) {
 		dev_err(dev, "Unable to register OneNAND device\n");
 		gpmc_cs_free(gpmc_onenand_data->cs);
-		return;
 	}
+
+	return err;
 }
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 131f8967589b..13e22a4a5a20 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -3885,16 +3885,20 @@ static struct omap_hwmod_ocp_if *omap3xxx_dss_hwmod_ocp_ifs[] __initdata = {
  * Return: 0 if device named @dev_name is not likely to be accessible,
  * or 1 if it is likely to be accessible.
  */
-static int __init omap3xxx_hwmod_is_hs_ip_block_usable(struct device_node *bus,
-						       const char *dev_name)
+static bool __init omap3xxx_hwmod_is_hs_ip_block_usable(struct device_node *bus,
+							const char *dev_name)
 {
+	struct device_node *node;
+	bool available;
+
 	if (!bus)
-		return (omap_type() == OMAP2_DEVICE_TYPE_GP) ? 1 : 0;
+		return omap_type() == OMAP2_DEVICE_TYPE_GP;
 
-	if (of_device_is_available(of_find_node_by_name(bus, dev_name)))
-		return 1;
+	node = of_get_child_by_name(bus, dev_name);
+	available = of_device_is_available(node);
+	of_node_put(node);
 
-	return 0;
+	return available;
 }
 
 int __init omap3xxx_hwmod_init(void)
@@ -3963,15 +3967,20 @@ int __init omap3xxx_hwmod_init(void)
 
 	if (h_sham && omap3xxx_hwmod_is_hs_ip_block_usable(bus, "sham")) {
 		r = omap_hwmod_register_links(h_sham);
-		if (r < 0)
+		if (r < 0) {
+			of_node_put(bus);
 			return r;
+		}
 	}
 
 	if (h_aes && omap3xxx_hwmod_is_hs_ip_block_usable(bus, "aes")) {
 		r = omap_hwmod_register_links(h_aes);
-		if (r < 0)
+		if (r < 0) {
+			of_node_put(bus);
 			return r;
+		}
 	}
+	of_node_put(bus);
 
 	/*
 	 * Register hwmod links specific to certain ES levels of a
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7708d83f16ac..4cee11317048 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -918,13 +918,31 @@ static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_add
 	__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
 }
 
+/*
+ * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
+ * that the intention is to allow exporting memory allocated via the
+ * coherent DMA APIs through the dma_buf API, which only accepts a
+ * scattertable.  This presents a couple of problems:
+ * 1. Not all memory allocated via the coherent DMA APIs is backed by
+ *    a struct page
+ * 2. Passing coherent DMA memory into the streaming APIs is not allowed
+ *    as we will try to flush the memory through a different alias to that
+ *    actually being used (and the flushes are redundant.)
+ */
 int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 		 void *cpu_addr, dma_addr_t handle, size_t size,
 		 struct dma_attrs *attrs)
 {
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+	unsigned long pfn = dma_to_pfn(dev, handle);
+	struct page *page;
 	int ret;
 
+	/* If the PFN is not valid, we do not have a struct page */
+	if (!pfn_valid(pfn))
+		return -ENXIO;
+
+	page = pfn_to_page(pfn);
+
 	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
 	if (unlikely(ret))
 		return ret;
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index a4ec240ee7ba..3eb018fa1a1f 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -433,6 +433,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+	kprobe_opcode_t *correct_ret_addr = NULL;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -455,14 +456,34 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			/* another task is sharing our hash bucket */
 			continue;
 
+		orig_ret_address = (unsigned long)ri->ret_addr;
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
 			__this_cpu_write(current_kprobe, NULL);
 		}
 
-		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri, &empty_rp);
 
 		if (orig_ret_address != trampoline_address)
@@ -474,7 +495,6 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			break;
 	}
 
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c
index 9775de22e2ff..a48354de1aa1 100644
--- a/arch/arm/probes/kprobes/test-core.c
+++ b/arch/arm/probes/kprobes/test-core.c
@@ -976,7 +976,10 @@ static void coverage_end(void)
 void __naked __kprobes_test_case_start(void)
 {
 	__asm__ __volatile__ (
-		"stmdb	sp!, {r4-r11}				\n\t"
+		"mov	r2, sp					\n\t"
+		"bic	r3, r2, #7				\n\t"
+		"mov	sp, r3					\n\t"
+		"stmdb	sp!, {r2-r11}				\n\t"
 		"sub	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
 		"bic	r0, lr, #1  @ r0 = inline data		\n\t"
 		"mov	r1, sp					\n\t"
@@ -996,7 +999,8 @@ void __naked __kprobes_test_case_end_32(void)
 		"movne	pc, r0					\n\t"
 		"mov	r0, r4					\n\t"
 		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
-		"ldmia	sp!, {r4-r11}				\n\t"
+		"ldmia	sp!, {r2-r11}				\n\t"
+		"mov	sp, r2					\n\t"
 		"mov	pc, r0					\n\t"
 	);
 }
@@ -1012,7 +1016,8 @@ void __naked __kprobes_test_case_end_16(void)
 		"bxne	r0					\n\t"
 		"mov	r0, r4					\n\t"
 		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
-		"ldmia	sp!, {r4-r11}				\n\t"
+		"ldmia	sp!, {r2-r11}				\n\t"
+		"mov	sp, r2					\n\t"
 		"bx	r0					\n\t"
 	);
 }
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 6cb7e1a6bc02..0c2eec490abf 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -18,7 +18,7 @@
 #ifndef __ASM_EXCEPTION_H
 #define __ASM_EXCEPTION_H
 
-#include <linux/ftrace.h>
+#include <linux/interrupt.h>
 
 #define __exception	__attribute__((section(".exception.text")))
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 8b709f53f874..6a889e943f4e 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -154,8 +154,7 @@
 #define VTTBR_X		(37 - VTCR_EL2_T0SZ_40B)
 #endif
 
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
 #define VTTBR_VMID_SHIFT  (UL(48))
 #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 915b2422d9d0..279978e1a070 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -148,6 +148,11 @@ extern u64			kimage_vaddr;
 /* the offset between the kernel virtual and physical mappings */
 extern u64			kimage_voffset;
 
+static inline unsigned long kaslr_offset(void)
+{
+	return kimage_vaddr - KIMAGE_VADDR;
+}
+
 /*
  * Allow all memory at the discovery stage. We will clip it later.
  */
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 3184cb05ea46..1d60ab1b3b11 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -34,7 +34,6 @@ struct undef_hook {
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static inline int __in_irqentry_text(unsigned long ptr)
 {
 	extern char __irqentry_text_start[];
@@ -43,12 +42,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
 	return ptr >= (unsigned long)&__irqentry_text_start &&
 	       ptr < (unsigned long)&__irqentry_text_end;
 }
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
-	return 0;
-}
-#endif
 
 static inline int in_exception_text(unsigned long ptr)
 {
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 9918489f5af3..6d9203c78dc7 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -326,6 +326,15 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
+	/*
+	 * In case p was allocated the same task_struct pointer as some
+	 * other recently-exited task, make sure p is disassociated from
+	 * any cpu that may have run that now-exited task recently.
+	 * Otherwise we could erroneously skip reloading the FPSIMD
+	 * registers for p.
+	 */
+	fpsimd_flush_task_state(p);
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 0b93365e8cf0..01f259ec5700 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -429,11 +429,11 @@ void arch_setup_pdev_archdata(struct platform_device *pdev)
 static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
 			      void *p)
 {
-	u64 const kaslr_offset = kimage_vaddr - KIMAGE_VADDR;
+	const unsigned long offset = kaslr_offset();
 
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset > 0) {
-		pr_emerg("Kernel Offset: 0x%llx from 0x%lx\n",
-			 kaslr_offset, KIMAGE_VADDR);
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && offset > 0) {
+		pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
+			 offset, KIMAGE_VADDR);
 	} else {
 		pr_emerg("Kernel Offset: disabled\n");
 	}
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 9e3cb29e4c50..a1ccef018538 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -131,7 +131,7 @@ ENTRY(_cpu_resume)
 
 #ifdef CONFIG_KASAN
 	mov	x0, sp
-	bl	kasan_unpoison_remaining_stack
+	bl	kasan_unpoison_task_stack_below
 #endif
 
 	ldp	x19, x20, [x29, #16]
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index b94ad40ecf7b..96765dc2e449 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -120,6 +120,7 @@ SECTIONS
 			__exception_text_end = .;
 			IRQENTRY_TEXT
 			ENTRY_TEXT
+			SOFTIRQENTRY_TEXT
 			TEXT_TEXT
 			SCHED_TEXT
 			LOCK_TEXT
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 25006a7a5316..e47f9bc71079 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -122,7 +122,19 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return ret;
 }
 
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
+		      hsr, esr_get_class_string(hsr));
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
 	[ESR_ELx_EC_CP15_32]	= kvm_handle_cp15_32,
 	[ESR_ELx_EC_CP15_64]	= kvm_handle_cp15_64,
@@ -148,13 +160,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	u8 hsr_ec = hsr >> ESR_ELx_EC_SHIFT;
 
-	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
-	    !arm_exit_handlers[hsr_ec]) {
-		kvm_err("Unknown exception class: hsr: %#08x -- %s\n",
-			hsr, esr_get_class_string(hsr));
-		BUG();
-	}
-
 	return arm_exit_handlers[hsr_ec];
 }
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 30f1a600a7c9..9930190a4929 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -255,6 +255,7 @@ void __init arm64_memblock_init(void)
 		arm64_dma_phys_limit = max_zone_dma_phys();
 	else
 		arm64_dma_phys_limit = PHYS_MASK + 1;
+	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();
@@ -279,7 +280,6 @@ void __init bootmem_init(void)
 	sparse_init();
 	zone_sizes_init(min, max);
 
-	high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
 	max_pfn = max_low_pfn = max;
 }
 
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index af76634f8d98..934573cc1134 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -318,11 +318,14 @@ config BF53x
 
 config GPIO_ADI
 	def_bool y
+	depends on !PINCTRL
 	depends on (BF51x || BF52x || BF53x || BF538 || BF539 || BF561)
 
-config PINCTRL
+config PINCTRL_BLACKFIN_ADI2
 	def_bool y
-	depends on BF54x || BF60x
+	depends on (BF54x || BF60x)
+	select PINCTRL
+	select PINCTRL_ADI2
 
 config MEM_MT48LC64M4A2FB_7E
 	bool
diff --git a/arch/blackfin/Kconfig.debug b/arch/blackfin/Kconfig.debug
index f3337ee03621..a93cf06a4d6f 100644
--- a/arch/blackfin/Kconfig.debug
+++ b/arch/blackfin/Kconfig.debug
@@ -17,6 +17,7 @@ config DEBUG_VERBOSE
 
 config DEBUG_MMRS
 	tristate "Generate Blackfin MMR tree"
+	depends on !PINCTRL
 	select DEBUG_FS
 	help
 	  Create a tree of Blackfin MMRs via the debugfs tree.  If
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index c9eec84aa258..d920b959ff3a 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -35,6 +35,7 @@ SECTIONS
 #endif
 		LOCK_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		KPROBES_TEXT
 #ifdef CONFIG_ROMKERNEL
 		__sinittext = .;
diff --git a/arch/c6x/kernel/vmlinux.lds.S b/arch/c6x/kernel/vmlinux.lds.S
index 5a6e141d1641..50bc10f97bcb 100644
--- a/arch/c6x/kernel/vmlinux.lds.S
+++ b/arch/c6x/kernel/vmlinux.lds.S
@@ -72,6 +72,7 @@ SECTIONS
 		SCHED_TEXT
 		LOCK_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		KPROBES_TEXT
 		*(.fixup)
 		*(.gnu.warning)
diff --git a/arch/metag/kernel/vmlinux.lds.S b/arch/metag/kernel/vmlinux.lds.S
index e12055e88bfe..150ace92c7ad 100644
--- a/arch/metag/kernel/vmlinux.lds.S
+++ b/arch/metag/kernel/vmlinux.lds.S
@@ -24,6 +24,7 @@ SECTIONS
 	LOCK_TEXT
 	KPROBES_TEXT
 	IRQENTRY_TEXT
+	SOFTIRQENTRY_TEXT
 	*(.text.*)
 	*(.gnu.warning)
 	}
diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S
index be9488d69734..0a47f0410554 100644
--- a/arch/microblaze/kernel/vmlinux.lds.S
+++ b/arch/microblaze/kernel/vmlinux.lds.S
@@ -36,6 +36,7 @@ SECTIONS {
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		. = ALIGN (4) ;
 		_etext = . ;
 	}
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 2026203c41e2..261b2ce579bb 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -58,6 +58,7 @@ SECTIONS
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.text.*)
 		*(.fixup)
 		*(.gnu.warning)
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index dd058aa8a3b5..89d05de8040a 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1777,7 +1777,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			SPFROMREG(fd, MIPSInst_FD(ir));
 			rv.s = ieee754sp_maddf(fd, fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmsubf_op: {
@@ -1790,7 +1790,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			SPFROMREG(fd, MIPSInst_FD(ir));
 			rv.s = ieee754sp_msubf(fd, fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case frint_op: {
@@ -1814,7 +1814,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.w = ieee754sp_2008class(fs);
 			rfmt = w_fmt;
-			break;
+			goto copcsr;
 		}
 
 		case fmin_op: {
@@ -1826,7 +1826,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPFROMREG(ft, MIPSInst_FT(ir));
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fmin(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmina_op: {
@@ -1838,7 +1838,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPFROMREG(ft, MIPSInst_FT(ir));
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fmina(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmax_op: {
@@ -1850,7 +1850,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPFROMREG(ft, MIPSInst_FT(ir));
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fmax(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmaxa_op: {
@@ -1862,7 +1862,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPFROMREG(ft, MIPSInst_FT(ir));
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fmaxa(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fabs_op:
@@ -2095,7 +2095,7 @@ copcsr:
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			DPFROMREG(fd, MIPSInst_FD(ir));
 			rv.d = ieee754dp_maddf(fd, fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmsubf_op: {
@@ -2108,7 +2108,7 @@ copcsr:
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			DPFROMREG(fd, MIPSInst_FD(ir));
 			rv.d = ieee754dp_msubf(fd, fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case frint_op: {
@@ -2132,7 +2132,7 @@ copcsr:
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.w = ieee754dp_2008class(fs);
 			rfmt = w_fmt;
-			break;
+			goto copcsr;
 		}
 
 		case fmin_op: {
@@ -2144,7 +2144,7 @@ copcsr:
 			DPFROMREG(ft, MIPSInst_FT(ir));
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fmin(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmina_op: {
@@ -2156,7 +2156,7 @@ copcsr:
 			DPFROMREG(ft, MIPSInst_FT(ir));
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fmina(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmax_op: {
@@ -2168,7 +2168,7 @@ copcsr:
 			DPFROMREG(ft, MIPSInst_FT(ir));
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fmax(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmaxa_op: {
@@ -2180,7 +2180,7 @@ copcsr:
 			DPFROMREG(ft, MIPSInst_FT(ir));
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fmaxa(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fabs_op:
diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S
index 326fab40a9de..e23e89539967 100644
--- a/arch/nios2/kernel/vmlinux.lds.S
+++ b/arch/nios2/kernel/vmlinux.lds.S
@@ -39,6 +39,7 @@ SECTIONS
 		SCHED_TEXT
 		LOCK_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		KPROBES_TEXT
 	} =0
 	_etext = .;
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index 5cc6b4f1b795..1a836afb636d 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -215,7 +215,7 @@ do {									\
 	case 1: __get_user_asm(x, ptr, retval, "l.lbz"); break;		\
 	case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break;		\
 	case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break;		\
-	case 8: __get_user_asm2(x, ptr, retval);			\
+	case 8: __get_user_asm2(x, ptr, retval); break;			\
 	default: (x) = __get_user_bad();				\
 	}								\
 } while (0)
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 3a08b55609b6..341fc086bc17 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -52,6 +52,7 @@ SECTIONS
 	  LOCK_TEXT
 	  KPROBES_TEXT
 	  IRQENTRY_TEXT
+	  SOFTIRQENTRY_TEXT
 	  *(.fixup)
 	  *(.text.__*)
 	  _etext = .;
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 60771df10fde..75304af9f742 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -72,6 +72,7 @@ SECTIONS
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.text.do_softirq)
 		*(.text.sys_exit)
 		*(.text.do_sigaltstack)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index d41fd0af8980..2dd91f79de05 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -55,6 +55,7 @@ SECTIONS
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 
 #ifdef CONFIG_PPC32
 		*(.got1)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index d1e65ce545b3..b2ab164a8094 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -401,8 +401,12 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	int ret;
 	__u64 target;
 
-	if (is_kernel_addr(addr))
-		return branch_target((unsigned int *)addr);
+	if (is_kernel_addr(addr)) {
+		if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+			return 0;
+
+		return branch_target(&instr);
+	}
 
 	/* Userspace: need copy instruction here then translate it */
 	pagefault_disable();
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 9f9dfda9ed2c..e8ca0fad2e69 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -514,7 +514,7 @@ static int memord(const void *d1, size_t s1, const void *d2, size_t s2)
 {
 	if (s1 < s2)
 		return 1;
-	if (s2 > s1)
+	if (s1 > s2)
 		return -1;
 
 	return memcmp(d1, d2, s1);
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
index bdc8c0c71d15..4c00b37b09bc 100644
--- a/arch/powerpc/platforms/powernv/opal-async.c
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -39,18 +39,18 @@ int __opal_async_get_token(void)
 	int token;
 
 	spin_lock_irqsave(&opal_async_comp_lock, flags);
-	token = find_first_bit(opal_async_complete_map, opal_max_async_tokens);
+	token = find_first_zero_bit(opal_async_token_map, opal_max_async_tokens);
 	if (token >= opal_max_async_tokens) {
 		token = -EBUSY;
 		goto out;
 	}
 
-	if (__test_and_set_bit(token, opal_async_token_map)) {
+	if (!__test_and_clear_bit(token, opal_async_complete_map)) {
 		token = -EBUSY;
 		goto out;
 	}
 
-	__clear_bit(token, opal_async_complete_map);
+	__set_bit(token, opal_async_token_map);
 
 out:
 	spin_unlock_irqrestore(&opal_async_comp_lock, flags);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index e40d0714679e..ecb7f3220355 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2270,6 +2270,9 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 	level_shift = entries_shift + 3;
 	level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
 
+	if ((level_shift - 3) * levels + page_shift >= 60)
+		return -EINVAL;
+
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
 			levels, tce_table_size, &offset, &total_allocated);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index a9a8fa37a555..f48afc06ba14 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -295,7 +295,7 @@ static unsigned long pnv_get_proc_freq(unsigned int cpu)
 {
 	unsigned long ret_freq;
 
-	ret_freq = cpufreq_quick_get(cpu) * 1000ul;
+	ret_freq = cpufreq_get(cpu) * 1000ul;
 
 	/*
 	 * If the backend cpufreq driver does not exist,
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 7a399b4d60a0..566e8fc341f3 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -276,7 +276,9 @@ failed:
 			if (bank->disk->major > 0)
 				unregister_blkdev(bank->disk->major,
 						bank->disk->disk_name);
-			del_gendisk(bank->disk);
+			if (bank->disk->flags & GENHD_FL_UP)
+				del_gendisk(bank->disk);
+			put_disk(bank->disk);
 		}
 		device->dev.platform_data = NULL;
 		if (bank->io_addr != 0)
@@ -301,6 +303,7 @@ axon_ram_remove(struct platform_device *device)
 	device_remove_file(&device->dev, &dev_attr_ecc);
 	free_irq(bank->irq_id, device);
 	del_gendisk(bank->disk);
+	put_disk(bank->disk);
 	iounmap((void __iomem *) bank->io_addr);
 	kfree(bank);
 
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index f76ee39cb337..800a591695c0 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -845,12 +845,12 @@ void ipic_disable_mcp(enum ipic_mcp_irq mcp_irq)
 
 u32 ipic_get_mcp_status(void)
 {
-	return ipic_read(primary_ipic->regs, IPIC_SERMR);
+	return ipic_read(primary_ipic->regs, IPIC_SERSR);
 }
 
 void ipic_clear_mcp_status(u32 mask)
 {
-	ipic_write(primary_ipic->regs, IPIC_SERMR, mask);
+	ipic_write(primary_ipic->regs, IPIC_SERSR, mask);
 }
 
 /* Return an interrupt vector or NO_IRQ if no interrupt is pending. */
diff --git a/arch/s390/include/asm/asm-prototypes.h b/arch/s390/include/asm/asm-prototypes.h
deleted file mode 100644
index 2c3413b0ca52..000000000000
--- a/arch/s390/include/asm/asm-prototypes.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _ASM_S390_PROTOTYPES_H
-
-#include <linux/kvm_host.h>
-#include <linux/ftrace.h>
-#include <asm/fpu/api.h>
-#include <asm-generic/asm-prototypes.h>
-
-#endif /* _ASM_S390_PROTOTYPES_H */
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index dde6b52359c5..ff2fbdafe689 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -29,17 +29,16 @@ static inline void restore_access_regs(unsigned int *acrs)
 }
 
 #define switch_to(prev,next,last) do {					\
-	if (prev->mm) {							\
-		save_fpu_regs();					\
-		save_access_regs(&prev->thread.acrs[0]);		\
-		save_ri_cb(prev->thread.ri_cb);				\
-	}								\
+	/* save_fpu_regs() sets the CIF_FPU flag, which enforces	\
+	 * a restore of the floating point / vector registers as	\
+	 * soon as the next task returns to user space			\
+	 */								\
+	save_fpu_regs();						\
+	save_access_regs(&prev->thread.acrs[0]);			\
+	save_ri_cb(prev->thread.ri_cb);					\
 	update_cr_regs(next);						\
-	if (next->mm) {							\
-		set_cpu_flag(CIF_FPU);					\
-		restore_access_regs(&next->thread.acrs[0]);		\
-		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
-	}								\
+	restore_access_regs(&next->thread.acrs[0]);			\
+	restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);		\
 	prev = __switch_to(prev,next);					\
 } while (0)
 
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 5378c3ea1b98..a1eeaa0db8b7 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -369,10 +369,10 @@ SYSCALL(sys_recvmmsg,compat_sys_recvmmsg)
 SYSCALL(sys_sendmmsg,compat_sys_sendmmsg)
 SYSCALL(sys_socket,sys_socket)
 SYSCALL(sys_socketpair,compat_sys_socketpair)		/* 360 */
-SYSCALL(sys_bind,sys_bind)
-SYSCALL(sys_connect,sys_connect)
+SYSCALL(sys_bind,compat_sys_bind)
+SYSCALL(sys_connect,compat_sys_connect)
 SYSCALL(sys_listen,sys_listen)
-SYSCALL(sys_accept4,sys_accept4)
+SYSCALL(sys_accept4,compat_sys_accept4)
 SYSCALL(sys_getsockopt,compat_sys_getsockopt)		/* 365 */
 SYSCALL(sys_setsockopt,compat_sys_setsockopt)
 SYSCALL(sys_getsockname,compat_sys_getsockname)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 445657fe658c..0f41a8286378 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -28,6 +28,7 @@ SECTIONS
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
 	} :text = 0x0700
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index db88cbf9eafd..235a4101999f 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -39,6 +39,7 @@ SECTIONS
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
 		_etext = .;		/* End of text section */
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 4a41d412dd3d..7d02b1fef025 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -52,6 +52,7 @@ SECTIONS
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.gnu.warning)
 	} = 0
 	_etext = .;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 384aba109d7c..c2f376ce443b 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2402,10 +2402,17 @@ void __init mem_init(void)
 {
 	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
 
-	register_page_bootmem_info();
 	free_all_bootmem();
 
 	/*
+	 * Must be done after boot memory is put on freelist, because here we
+	 * might set fields in deferred struct pages that have not yet been
+	 * initialized, and free_all_bootmem() initializes all the reserved
+	 * deferred pages for us.
+	 */
+	register_page_bootmem_info();
+
+	/*
 	 * Set up the zero page, mark it reserved, so that page count
 	 * is not manipulated when freeing the page from user ptes.
 	 */
diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S
index 0e059a0101ea..378f5d8d1ec8 100644
--- a/arch/tile/kernel/vmlinux.lds.S
+++ b/arch/tile/kernel/vmlinux.lds.S
@@ -45,6 +45,7 @@ SECTIONS
     LOCK_TEXT
     KPROBES_TEXT
     IRQENTRY_TEXT
+    SOFTIRQENTRY_TEXT
     __fix_text_end = .;   /* tile-cpack won't rearrange before this */
     ALIGN_FUNCTION();
     *(.hottext*)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f37e01e6b7f2..6cc76d687c69 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -27,6 +27,7 @@ config X86
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_MMIO_FLUSH
 	select ARCH_HAS_SG_CHAIN
@@ -43,7 +44,7 @@ config X86
 	select ARCH_USE_CMPXCHG_LOCKREF		if X86_64
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
-	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP
+	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_IPC_PARSE_VERSION	if X86_32
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 4a3a140f26bf..d99b919c8812 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -11,6 +11,13 @@
 
 KASAN_SANITIZE := n
 
+# Kernel does not boot with kcov instrumentation here.
+# One of the problems observed was insertion of __sanitizer_cov_trace_pc()
+# callback into middle of per-cpu data enabling code. Thus the callback observed
+# inconsistent state and crashed. We are interested mostly in syscall coverage,
+# so boot code is not interesting anyway.
+KCOV_INSTRUMENT		:= n
+
 # If you want to preset the SVGA mode, uncomment the next line and
 # set SVGA_MODE to whatever number you want.
 # Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 7f6c157e5da5..6862464e0012 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -18,6 +18,9 @@
 
 KASAN_SANITIZE := n
 
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT		:= n
+
 targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
 
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 3783dc3e10b3..4abb284a5b9c 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -9,6 +9,7 @@
  */
 #undef CONFIG_PARAVIRT
 #undef CONFIG_PARAVIRT_SPINLOCKS
+#undef CONFIG_PAGE_TABLE_ISOLATION
 #undef CONFIG_KASAN
 
 #include <linux/linkage.h>
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index 399a29d067d6..cb91a64a99e7 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -59,13 +59,6 @@ static int encrypt(struct blkcipher_desc *desc,
 
 	salsa20_ivsetup(ctx, walk.iv);
 
-	if (likely(walk.nbytes == nbytes))
-	{
-		salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
-				      walk.dst.virt.addr, nbytes);
-		return blkcipher_walk_done(desc, &walk, 0);
-	}
-
 	while (walk.nbytes >= 64) {
 		salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
 				      walk.dst.virt.addr,
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index cc0f2f5da19b..db42a6766995 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -35,6 +35,7 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/pgtable_types.h>
+#include <asm/kaiser.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -135,6 +136,7 @@ ENTRY(entry_SYSCALL_64)
 	 * it is too small to ever cause noticeable irq latency.
 	 */
 	SWAPGS_UNSAFE_STACK
+	SWITCH_KERNEL_CR3_NO_STACK
 	/*
 	 * A hypervisor implementation might want to use a label
 	 * after the swapgs, so that it can do the swapgs
@@ -207,9 +209,17 @@ entry_SYSCALL_64_fastpath:
 	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
 	jnz	int_ret_from_sys_call_irqs_off	/* Go to the slow path */
 
-	RESTORE_C_REGS_EXCEPT_RCX_R11
 	movq	RIP(%rsp), %rcx
 	movq	EFLAGS(%rsp), %r11
+	RESTORE_C_REGS_EXCEPT_RCX_R11
+	/*
+	 * This opens a window where we have a user CR3, but are
+	 * running in the kernel.  This makes using the CS
+	 * register useless for telling whether or not we need to
+	 * switch CR3 in NMIs.  Normal interrupts are OK because
+	 * they are off here.
+	 */
+	SWITCH_USER_CR3
 	movq	RSP(%rsp), %rsp
 	/*
 	 * 64-bit SYSRET restores rip from rcx,
@@ -347,10 +357,26 @@ GLOBAL(int_ret_from_sys_call)
 syscall_return_via_sysret:
 	/* rcx and r11 are already restored (see code above) */
 	RESTORE_C_REGS_EXCEPT_RCX_R11
+	/*
+	 * This opens a window where we have a user CR3, but are
+	 * running in the kernel.  This makes using the CS
+	 * register useless for telling whether or not we need to
+	 * switch CR3 in NMIs.  Normal interrupts are OK because
+	 * they are off here.
+	 */
+	SWITCH_USER_CR3
 	movq	RSP(%rsp), %rsp
 	USERGS_SYSRET64
 
 opportunistic_sysret_failed:
+	/*
+	 * This opens a window where we have a user CR3, but are
+	 * running in the kernel.  This makes using the CS
+	 * register useless for telling whether or not we need to
+	 * switch CR3 in NMIs.  Normal interrupts are OK because
+	 * they are off here.
+	 */
+	SWITCH_USER_CR3
 	SWAPGS
 	jmp	restore_c_regs_and_iret
 END(entry_SYSCALL_64)
@@ -509,6 +535,7 @@ END(irq_entries_start)
 	 * tracking that we're in kernel mode.
 	 */
 	SWAPGS
+	SWITCH_KERNEL_CR3
 
 	/*
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
@@ -568,6 +595,7 @@ GLOBAL(retint_user)
 	mov	%rsp,%rdi
 	call	prepare_exit_to_usermode
 	TRACE_IRQS_IRETQ
+	SWITCH_USER_CR3
 	SWAPGS
 	jmp	restore_regs_and_iret
 
@@ -625,6 +653,7 @@ native_irq_return_ldt:
 	pushq	%rax
 	pushq	%rdi
 	SWAPGS
+	SWITCH_KERNEL_CR3
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
 	movq	%rax, (0*8)(%rdi)		/* RAX */
 	movq	(2*8)(%rsp), %rax		/* RIP */
@@ -640,6 +669,7 @@ native_irq_return_ldt:
 	andl	$0xffff0000, %eax
 	popq	%rdi
 	orq	PER_CPU_VAR(espfix_stack), %rax
+	SWITCH_USER_CR3
 	SWAPGS
 	movq	%rax, %rsp
 	popq	%rax
@@ -672,9 +702,15 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym)
 .endm
 #endif
 
+/* Make sure APIC interrupt handlers end up in the irqentry section: */
+#define PUSH_SECTION_IRQENTRY	.pushsection .irqentry.text, "ax"
+#define POP_SECTION_IRQENTRY	.popsection
+
 .macro apicinterrupt num sym do_sym
+PUSH_SECTION_IRQENTRY
 apicinterrupt3 \num \sym \do_sym
 trace_apicinterrupt \num \sym
+POP_SECTION_IRQENTRY
 .endm
 
 #ifdef CONFIG_SMP
@@ -995,7 +1031,11 @@ idtentry machine_check					has_error_code=0	paranoid=1 do_sym=*machine_check_vec
 /*
  * Save all registers in pt_regs, and switch gs if needed.
  * Use slow, but surefire "are we in kernel?" check.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ *
+ * Return: ebx=0: needs swapgs but not SWITCH_USER_CR3 in paranoid_exit
+ *         ebx=1: needs neither swapgs nor SWITCH_USER_CR3 in paranoid_exit
+ *         ebx=2: needs both swapgs and SWITCH_USER_CR3 in paranoid_exit
+ *         ebx=3: needs SWITCH_USER_CR3 but not swapgs in paranoid_exit
  */
 ENTRY(paranoid_entry)
 	cld
@@ -1008,7 +1048,26 @@ ENTRY(paranoid_entry)
 	js	1f				/* negative -> in kernel */
 	SWAPGS
 	xorl	%ebx, %ebx
-1:	ret
+1:
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/*
+	 * We might have come in between a swapgs and a SWITCH_KERNEL_CR3
+	 * on entry, or between a SWITCH_USER_CR3 and a swapgs on exit.
+	 * Do a conditional SWITCH_KERNEL_CR3: this could safely be done
+	 * unconditionally, but we need to find out whether the reverse
+	 * should be done on return (conveyed to paranoid_exit in %ebx).
+	 */
+	ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
+	testl	$KAISER_SHADOW_PGD_OFFSET, %eax
+	jz	2f
+	orl	$2, %ebx
+	andq	$(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
+	/* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */
+	ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
+	movq	%rax, %cr3
+2:
+#endif
+	ret
 END(paranoid_entry)
 
 /*
@@ -1021,19 +1080,26 @@ END(paranoid_entry)
  * be complicated.  Fortunately, we there's no good reason
  * to try to handle preemption here.
  *
- * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
+ * On entry: ebx=0: needs swapgs but not SWITCH_USER_CR3
+ *           ebx=1: needs neither swapgs nor SWITCH_USER_CR3
+ *           ebx=2: needs both swapgs and SWITCH_USER_CR3
+ *           ebx=3: needs SWITCH_USER_CR3 but not swapgs
  */
 ENTRY(paranoid_exit)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF_DEBUG
-	testl	%ebx, %ebx			/* swapgs needed? */
+	TRACE_IRQS_IRETQ_DEBUG
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/* No ALTERNATIVE for X86_FEATURE_KAISER: paranoid_entry sets %ebx */
+	testl	$2, %ebx			/* SWITCH_USER_CR3 needed? */
+	jz	paranoid_exit_no_switch
+	SWITCH_USER_CR3
+paranoid_exit_no_switch:
+#endif
+	testl	$1, %ebx			/* swapgs needed? */
 	jnz	paranoid_exit_no_swapgs
-	TRACE_IRQS_IRETQ
 	SWAPGS_UNSAFE_STACK
-	jmp	paranoid_exit_restore
 paranoid_exit_no_swapgs:
-	TRACE_IRQS_IRETQ_DEBUG
-paranoid_exit_restore:
 	RESTORE_EXTRA_REGS
 	RESTORE_C_REGS
 	REMOVE_PT_GPREGS_FROM_STACK 8
@@ -1048,6 +1114,13 @@ ENTRY(error_entry)
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
+	/*
+	 * error_entry() always returns with a kernel gsbase and
+	 * CR3.  We must also have a kernel CR3/gsbase before
+	 * calling TRACE_IRQS_*.  Just unconditionally switch to
+	 * the kernel CR3 here.
+	 */
+	SWITCH_KERNEL_CR3
 	xorl	%ebx, %ebx
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
@@ -1210,6 +1283,10 @@ ENTRY(nmi)
 	 */
 
 	SWAPGS_UNSAFE_STACK
+	/*
+	 * percpu variables are mapped with user CR3, so no need
+	 * to switch CR3 here.
+	 */
 	cld
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
@@ -1243,12 +1320,34 @@ ENTRY(nmi)
 
 	movq	%rsp, %rdi
 	movq	$-1, %rsi
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/* Unconditionally use kernel CR3 for do_nmi() */
+	/* %rax is saved above, so OK to clobber here */
+	ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
+	/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
+	ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
+	pushq	%rax
+	/* mask off "user" bit of pgd address and 12 PCID bits: */
+	andq	$(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
+	movq	%rax, %cr3
+2:
+#endif
 	call	do_nmi
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/*
+	 * Unconditionally restore CR3.  I know we return to
+	 * kernel code that needs user CR3, but do we ever return
+	 * to "user mode" where we need the kernel CR3?
+	 */
+	ALTERNATIVE "", "popq %rax; movq %rax, %cr3", X86_FEATURE_KAISER
+#endif
+
 	/*
 	 * Return back to user mode.  We must *not* do the normal exit
-	 * work, because we don't want to enable interrupts.  Fortunately,
-	 * do_nmi doesn't modify pt_regs.
+	 * work, because we don't want to enable interrupts.  Do not
+	 * switch to user CR3: we might be going back to kernel code
+	 * that had a user CR3 set.
 	 */
 	SWAPGS
 	jmp	restore_c_regs_and_iret
@@ -1445,22 +1544,55 @@ end_repeat_nmi:
 	ALLOC_PT_GPREGS_ON_STACK
 
 	/*
-	 * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
-	 * as we should not be calling schedule in NMI context.
-	 * Even with normal interrupts enabled. An NMI should not be
-	 * setting NEED_RESCHED or anything that normal interrupts and
-	 * exceptions might do.
+	 * Use the same approach as paranoid_entry to handle SWAPGS, but
+	 * without CR3 handling since we do that differently in NMIs.  No
+	 * need to use paranoid_exit as we should not be calling schedule
+	 * in NMI context.  Even with normal interrupts enabled. An NMI
+	 * should not be setting NEED_RESCHED or anything that normal
+	 * interrupts and exceptions might do.
 	 */
-	call	paranoid_entry
-
-	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
+	cld
+	SAVE_C_REGS
+	SAVE_EXTRA_REGS
+	movl	$1, %ebx
+	movl	$MSR_GS_BASE, %ecx
+	rdmsr
+	testl	%edx, %edx
+	js	1f				/* negative -> in kernel */
+	SWAPGS
+	xorl	%ebx, %ebx
+1:
 	movq	%rsp, %rdi
 	movq	$-1, %rsi
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/* Unconditionally use kernel CR3 for do_nmi() */
+	/* %rax is saved above, so OK to clobber here */
+	ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
+	/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
+	ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
+	pushq	%rax
+	/* mask off "user" bit of pgd address and 12 PCID bits: */
+	andq	$(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
+	movq	%rax, %cr3
+2:
+#endif
+
+	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
 	call	do_nmi
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/*
+	 * Unconditionally restore CR3.  We might be returning to
+	 * kernel code that needs user CR3, like just just before
+	 * a sysret.
+	 */
+	ALTERNATIVE "", "popq %rax; movq %rax, %cr3", X86_FEATURE_KAISER
+#endif
+
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	nmi_restore
 nmi_swapgs:
+	/* We fixed up CR3 above, so no need to switch it here */
 	SWAPGS_UNSAFE_STACK
 nmi_restore:
 	RESTORE_EXTRA_REGS
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 15cfebaa7688..d03bf0e28b8b 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -13,6 +13,8 @@
 #include <asm/irqflags.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
+#include <asm/pgtable_types.h>
+#include <asm/kaiser.h>
 #include <linux/linkage.h>
 #include <linux/err.h>
 
@@ -50,6 +52,7 @@ ENDPROC(native_usergs_sysret32)
 ENTRY(entry_SYSENTER_compat)
 	/* Interrupts are off on entry. */
 	SWAPGS_UNSAFE_STACK
+	SWITCH_KERNEL_CR3_NO_STACK
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/*
@@ -161,6 +164,7 @@ ENDPROC(entry_SYSENTER_compat)
 ENTRY(entry_SYSCALL_compat)
 	/* Interrupts are off on entry. */
 	SWAPGS_UNSAFE_STACK
+	SWITCH_KERNEL_CR3_NO_STACK
 
 	/* Stash user ESP and switch to the kernel stack. */
 	movl	%esp, %r8d
@@ -208,6 +212,7 @@ ENTRY(entry_SYSCALL_compat)
 	/* Opportunistic SYSRET */
 sysret32_from_system_call:
 	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+	SWITCH_USER_CR3
 	movq	RBX(%rsp), %rbx		/* pt_regs->rbx */
 	movq	RBP(%rsp), %rbp		/* pt_regs->rbp */
 	movq	EFLAGS(%rsp), %r11	/* pt_regs->flags (in r11) */
@@ -269,6 +274,7 @@ ENTRY(entry_INT80_compat)
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	ASM_CLAC			/* Do this early to minimize exposure */
 	SWAPGS
+	SWITCH_KERNEL_CR3_NO_STACK
 
 	/*
 	 * User tracing code (ptrace or signal handlers) might assume that
@@ -311,6 +317,7 @@ ENTRY(entry_INT80_compat)
 
 	/* Go back to user mode. */
 	TRACE_IRQS_ON
+	SWITCH_USER_CR3
 	SWAPGS
 	jmp	restore_regs_and_iret
 END(entry_INT80_compat)
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 7af017a8958f..fddeb1f4dcd2 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -5,6 +5,9 @@
 KBUILD_CFLAGS += $(DISABLE_LTO)
 KASAN_SANITIZE := n
 
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT		:= n
+
 VDSO64-$(CONFIG_X86_64)		:= y
 VDSOX32-$(CONFIG_X86_X32_ABI)	:= y
 VDSO32-$(CONFIG_X86_32)		:= y
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index ca94fa649251..5dd363d54348 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -36,6 +36,11 @@ static notrace cycle_t vread_hpet(void)
 }
 #endif
 
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern u8 pvclock_page
+	__attribute__((visibility("hidden")));
+#endif
+
 #ifndef BUILD_VDSO32
 
 #include <linux/kernel.h>
@@ -62,63 +67,65 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 
 #ifdef CONFIG_PARAVIRT_CLOCK
 
-static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
+static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
 {
-	const struct pvclock_vsyscall_time_info *pvti_base;
-	int idx = cpu / (PAGE_SIZE/PVTI_SIZE);
-	int offset = cpu % (PAGE_SIZE/PVTI_SIZE);
-
-	BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END);
-
-	pvti_base = (struct pvclock_vsyscall_time_info *)
-		    __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx);
-
-	return &pvti_base[offset];
+	return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
 }
 
 static notrace cycle_t vread_pvclock(int *mode)
 {
-	const struct pvclock_vsyscall_time_info *pvti;
+	const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
 	cycle_t ret;
-	u64 last;
-	u32 version;
-	u8 flags;
-	unsigned cpu, cpu1;
-
+	u64 tsc, pvti_tsc;
+	u64 last, delta, pvti_system_time;
+	u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift;
 
 	/*
-	 * Note: hypervisor must guarantee that:
-	 * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
-	 * 2. that per-CPU pvclock time info is updated if the
-	 *    underlying CPU changes.
-	 * 3. that version is increased whenever underlying CPU
-	 *    changes.
+	 * Note: The kernel and hypervisor must guarantee that cpu ID
+	 * number maps 1:1 to per-CPU pvclock time info.
+	 *
+	 * Because the hypervisor is entirely unaware of guest userspace
+	 * preemption, it cannot guarantee that per-CPU pvclock time
+	 * info is updated if the underlying CPU changes or that that
+	 * version is increased whenever underlying CPU changes.
 	 *
+	 * On KVM, we are guaranteed that pvti updates for any vCPU are
+	 * atomic as seen by *all* vCPUs.  This is an even stronger
+	 * guarantee than we get with a normal seqlock.
+	 *
+	 * On Xen, we don't appear to have that guarantee, but Xen still
+	 * supplies a valid seqlock using the version field.
+
+	 * We only do pvclock vdso timing at all if
+	 * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+	 * mean that all vCPUs have matching pvti and that the TSC is
+	 * synced, so we can just look at vCPU 0's pvti.
 	 */
-	do {
-		cpu = __getcpu() & VGETCPU_CPU_MASK;
-		/* TODO: We can put vcpu id into higher bits of pvti.version.
-		 * This will save a couple of cycles by getting rid of
-		 * __getcpu() calls (Gleb).
-		 */
-
-		pvti = get_pvti(cpu);
-
-		version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
-
-		/*
-		 * Test we're still on the cpu as well as the version.
-		 * We could have been migrated just after the first
-		 * vgetcpu but before fetching the version, so we
-		 * wouldn't notice a version change.
-		 */
-		cpu1 = __getcpu() & VGETCPU_CPU_MASK;
-	} while (unlikely(cpu != cpu1 ||
-			  (pvti->pvti.version & 1) ||
-			  pvti->pvti.version != version));
-
-	if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
+
+	if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
 		*mode = VCLOCK_NONE;
+		return 0;
+	}
+
+	do {
+		version = pvti->version;
+
+		/* This is also a read barrier, so we'll read version first. */
+		tsc = rdtsc_ordered();
+
+		pvti_tsc_to_system_mul = pvti->tsc_to_system_mul;
+		pvti_tsc_shift = pvti->tsc_shift;
+		pvti_system_time = pvti->system_time;
+		pvti_tsc = pvti->tsc_timestamp;
+
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
+	} while (unlikely((version & 1) || version != pvti->version));
+
+	delta = tsc - pvti_tsc;
+	ret = pvti_system_time +
+		pvclock_scale_delta(delta, pvti_tsc_to_system_mul,
+				    pvti_tsc_shift);
 
 	/* refer to tsc.c read_tsc() comment for rationale */
 	last = gtod->cycle_last;
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index de2c921025f5..4158acc17df0 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -25,7 +25,7 @@ SECTIONS
 	 * segment.
 	 */
 
-	vvar_start = . - 2 * PAGE_SIZE;
+	vvar_start = . - 3 * PAGE_SIZE;
 	vvar_page = vvar_start;
 
 	/* Place all vvars at the offsets in asm/vvar.h. */
@@ -36,6 +36,7 @@ SECTIONS
 #undef EMIT_VVAR
 
 	hpet_page = vvar_start + PAGE_SIZE;
+	pvclock_page = vvar_start + 2 * PAGE_SIZE;
 
 	. = SIZEOF_HEADERS;
 
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 785d9922b106..491020b2826d 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -73,6 +73,7 @@ enum {
 	sym_vvar_start,
 	sym_vvar_page,
 	sym_hpet_page,
+	sym_pvclock_page,
 	sym_VDSO_FAKE_SECTION_TABLE_START,
 	sym_VDSO_FAKE_SECTION_TABLE_END,
 };
@@ -80,6 +81,7 @@ enum {
 const int special_pages[] = {
 	sym_vvar_page,
 	sym_hpet_page,
+	sym_pvclock_page,
 };
 
 struct vdso_sym {
@@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = {
 	[sym_vvar_start] = {"vvar_start", true},
 	[sym_vvar_page] = {"vvar_page", true},
 	[sym_hpet_page] = {"hpet_page", true},
+	[sym_pvclock_page] = {"pvclock_page", true},
 	[sym_VDSO_FAKE_SECTION_TABLE_START] = {
 		"VDSO_FAKE_SECTION_TABLE_START", false
 	},
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 64df47148160..aa828191c654 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -100,6 +100,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 		.name = "[vvar]",
 		.pages = no_pages,
 	};
+	struct pvclock_vsyscall_time_info *pvti;
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,
@@ -169,6 +170,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	}
 #endif
 
+	pvti = pvclock_pvti_cpu0_va();
+	if (pvti && image->sym_pvclock_page) {
+		ret = remap_pfn_range(vma,
+				      text_start + image->sym_pvclock_page,
+				      __pa(pvti) >> PAGE_SHIFT,
+				      PAGE_SIZE,
+				      PAGE_READONLY);
+
+		if (ret)
+			goto up_fail;
+	}
+
 up_fail:
 	if (ret)
 		current->mm->context.vdso = NULL;
diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h
index e01f7f7ccb0c..84ae170bc3d0 100644
--- a/arch/x86/include/asm/cmdline.h
+++ b/arch/x86/include/asm/cmdline.h
@@ -2,5 +2,7 @@
 #define _ASM_X86_CMDLINE_H
 
 int cmdline_find_option_bool(const char *cmdline_ptr, const char *option);
+int cmdline_find_option(const char *cmdline_ptr, const char *option,
+			char *buffer, int bufsize);
 
 #endif /* _ASM_X86_CMDLINE_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index f7ba9fbf12ee..f6605712ca90 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -187,6 +187,7 @@
 #define X86_FEATURE_ARAT	( 7*32+ 1) /* Always Running APIC Timer */
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 4) /* Effectively INVPCID && CR4.PCIDE=1 */
 #define X86_FEATURE_PLN		( 7*32+ 5) /* Intel Power Limit Notification */
 #define X86_FEATURE_PTS		( 7*32+ 6) /* Intel Package Thermal Status */
 #define X86_FEATURE_DTHERM	( 7*32+ 7) /* Digital Thermal Sensor */
@@ -199,6 +200,9 @@
 #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
 
+/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
+#define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
+
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
 #define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 4e10d73cf018..880db91d9457 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -43,7 +43,7 @@ struct gdt_page {
 	struct desc_struct gdt[GDT_ENTRIES];
 } __attribute__((aligned(PAGE_SIZE)));
 
-DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
+DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page);
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 {
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index f226df064660..8b17c2ad1048 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -21,11 +21,13 @@
 # define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
 # define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
 # define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
+# define DISABLE_PCID		0
 #else
 # define DISABLE_VME		0
 # define DISABLE_K6_MTRR	0
 # define DISABLE_CYRIX_ARR	0
 # define DISABLE_CENTAUR_MCR	0
+# define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
 #endif /* CONFIG_X86_64 */
 
 /*
@@ -35,7 +37,7 @@
 #define DISABLED_MASK1	0
 #define DISABLED_MASK2	0
 #define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4	0
+#define DISABLED_MASK4	(DISABLE_PCID)
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	0
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index c9e6eab2075b..08b1f2f6ea50 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,7 +3,6 @@
 
 #include <asm/fpu/api.h>
 #include <asm/pgtable.h>
-#include <asm/tlb.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -67,17 +66,6 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 
 #define efi_call_phys(f, args...)		efi_call((f), args)
 
-/*
- * Scratch space used for switching the pagetable in the EFI stub
- */
-struct efi_scratch {
-	u64	r15;
-	u64	prev_cr3;
-	pgd_t	*efi_pgt;
-	bool	use_pgd;
-	u64	phys_stack;
-} __packed;
-
 #define efi_call_virt(f, ...)						\
 ({									\
 	efi_status_t __s;						\
@@ -85,20 +73,7 @@ struct efi_scratch {
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
-									\
-	if (efi_scratch.use_pgd) {					\
-		efi_scratch.prev_cr3 = read_cr3();			\
-		write_cr3((unsigned long)efi_scratch.efi_pgt);		\
-		__flush_tlb_all();					\
-	}								\
-									\
 	__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__);	\
-									\
-	if (efi_scratch.use_pgd) {					\
-		write_cr3(efi_scratch.prev_cr3);			\
-		__flush_tlb_all();					\
-	}								\
-									\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 	__s;								\
@@ -138,7 +113,6 @@ extern void __init efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
 extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
-extern int __init efi_alloc_page_tables(void);
 extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init old_map_region(efi_memory_desc_t *md);
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 7178043b0e1d..9b76cd331990 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -22,12 +22,8 @@ typedef struct {
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
-	/*
-	 * irq_tlb_count is double-counted in irq_call_count, so it must be
-	 * subtracted from irq_call_count when displaying irq_call_count
-	 */
-	unsigned int irq_tlb_count;
 #endif
+	unsigned int irq_tlb_count;
 #ifdef CONFIG_X86_THERMAL_VECTOR
 	unsigned int irq_thermal_count;
 #endif
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 59caa55fb9b5..ee52ff858699 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -187,7 +187,7 @@ extern char irq_entries_start[];
 #define VECTOR_RETRIGGERED	((void *)~0UL)
 
 typedef struct irq_desc* vector_irq_t[NR_VECTORS];
-DECLARE_PER_CPU(vector_irq_t, vector_irq);
+DECLARE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq);
 
 #endif /* !ASSEMBLY_ */
 
diff --git a/arch/x86/include/asm/kaiser.h b/arch/x86/include/asm/kaiser.h
new file mode 100644
index 000000000000..802bbbdfe143
--- /dev/null
+++ b/arch/x86/include/asm/kaiser.h
@@ -0,0 +1,141 @@
+#ifndef _ASM_X86_KAISER_H
+#define _ASM_X86_KAISER_H
+
+#include <uapi/asm/processor-flags.h> /* For PCID constants */
+
+/*
+ * This file includes the definitions for the KAISER feature.
+ * KAISER is a counter measure against x86_64 side channel attacks on
+ * the kernel virtual memory.  It has a shadow pgd for every process: the
+ * shadow pgd has a minimalistic kernel-set mapped, but includes the whole
+ * user memory. Within a kernel context switch, or when an interrupt is handled,
+ * the pgd is switched to the normal one. When the system switches to user mode,
+ * the shadow pgd is enabled. By this, the virtual memory caches are freed,
+ * and the user may not attack the whole kernel memory.
+ *
+ * A minimalistic kernel mapping holds the parts needed to be mapped in user
+ * mode, such as the entry/exit functions of the user space, or the stacks.
+ */
+
+#define KAISER_SHADOW_PGD_OFFSET 0x1000
+
+#ifdef __ASSEMBLY__
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+.macro _SWITCH_TO_KERNEL_CR3 reg
+movq %cr3, \reg
+andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
+/* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */
+ALTERNATIVE "", "bts $63, \reg", X86_FEATURE_PCID
+movq \reg, %cr3
+.endm
+
+.macro _SWITCH_TO_USER_CR3 reg regb
+/*
+ * regb must be the low byte portion of reg: because we have arranged
+ * for the low byte of the user PCID to serve as the high byte of NOFLUSH
+ * (0x80 for each when PCID is enabled, or 0x00 when PCID and NOFLUSH are
+ * not enabled): so that the one register can update both memory and cr3.
+ */
+movq %cr3, \reg
+orq  PER_CPU_VAR(x86_cr3_pcid_user), \reg
+js   9f
+/* If PCID enabled, FLUSH this time, reset to NOFLUSH for next time */
+movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7)
+9:
+movq \reg, %cr3
+.endm
+
+.macro SWITCH_KERNEL_CR3
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
+_SWITCH_TO_KERNEL_CR3 %rax
+popq %rax
+8:
+.endm
+
+.macro SWITCH_USER_CR3
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
+_SWITCH_TO_USER_CR3 %rax %al
+popq %rax
+8:
+.endm
+
+.macro SWITCH_KERNEL_CR3_NO_STACK
+ALTERNATIVE "jmp 8f", \
+	__stringify(movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)), \
+	X86_FEATURE_KAISER
+_SWITCH_TO_KERNEL_CR3 %rax
+movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
+8:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION */
+
+.macro SWITCH_KERNEL_CR3
+.endm
+.macro SWITCH_USER_CR3
+.endm
+.macro SWITCH_KERNEL_CR3_NO_STACK
+.endm
+
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Upon kernel/user mode switch, it may happen that the address
+ * space has to be switched before the registers have been
+ * stored.  To change the address space, another register is
+ * needed.  A register therefore has to be stored/restored.
+*/
+DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+
+DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user);
+
+extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
+
+extern int kaiser_enabled;
+extern void __init kaiser_check_boottime_disable(void);
+#else
+#define kaiser_enabled	0
+static inline void __init kaiser_check_boottime_disable(void) {}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Kaiser function prototypes are needed even when CONFIG_PAGE_TABLE_ISOLATION is not set,
+ * so as to build with tests on kaiser_enabled instead of #ifdefs.
+ */
+
+/**
+ *  kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping
+ *  @addr: the start address of the range
+ *  @size: the size of the range
+ *  @flags: The mapping flags of the pages
+ *
+ *  The mapping is done on a global scope, so no bigger
+ *  synchronization has to be done.  the pages have to be
+ *  manually unmapped again when they are not needed any longer.
+ */
+extern int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags);
+
+/**
+ *  kaiser_remove_mapping - unmap a virtual memory part of the shadow mapping
+ *  @addr: the start address of the range
+ *  @size: the size of the range
+ */
+extern void kaiser_remove_mapping(unsigned long start, unsigned long size);
+
+/**
+ *  kaiser_init - Initialize the shadow mapping
+ *
+ *  Most parts of the shadow mapping can be mapped upon boot
+ *  time.  Only per-process things like the thread stacks
+ *  or a new LDT have to be mapped at runtime.  These boot-
+ *  time mappings are permanent and never unmapped.
+ */
+extern void kaiser_init(void);
+
+#endif /* __ASSEMBLY */
+
+#endif /* _ASM_X86_KAISER_H */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 55234d5e7160..7680b76adafc 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -24,12 +24,6 @@ typedef struct {
 	atomic_t perf_rdpmc_allowed;	/* nonzero if rdpmc is allowed */
 } mm_context_t;
 
-#ifdef CONFIG_SMP
 void leave_mm(int cpu);
-#else
-static inline void leave_mm(int cpu)
-{
-}
-#endif
 
 #endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index bfd9b2a35a0b..9bfc5fd77015 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -98,109 +98,16 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
-#ifdef CONFIG_SMP
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
 }
 
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
-
-	if (likely(prev != next)) {
-#ifdef CONFIG_SMP
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		this_cpu_write(cpu_tlbstate.active_mm, next);
-#endif
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-
-		/*
-		 * Re-load page tables.
-		 *
-		 * This logic has an ordering constraint:
-		 *
-		 *  CPU 0: Write to a PTE for 'next'
-		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
-		 *  CPU 1: set bit 1 in next's mm_cpumask
-		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
-		 *
-		 * We need to prevent an outcome in which CPU 1 observes
-		 * the new PTE value and CPU 0 observes bit 1 clear in
-		 * mm_cpumask.  (If that occurs, then the IPI will never
-		 * be sent, and CPU 0's TLB will contain a stale entry.)
-		 *
-		 * The bad outcome can occur if either CPU's load is
-		 * reordered before that CPU's store, so both CPUs must
-		 * execute full barriers to prevent this from happening.
-		 *
-		 * Thus, switch_mm needs a full barrier between the
-		 * store to mm_cpumask and any operation that could load
-		 * from next->pgd.  TLB fills are special and can happen
-		 * due to instruction fetches or for no reason at all,
-		 * and neither LOCK nor MFENCE orders them.
-		 * Fortunately, load_cr3() is serializing and gives the
-		 * ordering guarantee we need.
-		 *
-		 */
-		load_cr3(next->pgd);
-
-		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-
-		/* Stop flush ipis for the previous mm */
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+		      struct task_struct *tsk);
 
-		/* Load per-mm CR4 state */
-		load_mm_cr4(next);
-
-#ifdef CONFIG_MODIFY_LDT_SYSCALL
-		/*
-		 * Load the LDT, if the LDT is different.
-		 *
-		 * It's possible that prev->context.ldt doesn't match
-		 * the LDT register.  This can happen if leave_mm(prev)
-		 * was called and then modify_ldt changed
-		 * prev->context.ldt but suppressed an IPI to this CPU.
-		 * In this case, prev->context.ldt != NULL, because we
-		 * never set context.ldt to NULL while the mm still
-		 * exists.  That means that next->context.ldt !=
-		 * prev->context.ldt, because mms never share an LDT.
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_mm_ldt(next);
-#endif
-	}
-#ifdef CONFIG_SMP
-	  else {
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
-
-		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
-			/*
-			 * On established mms, the mm_cpumask is only changed
-			 * from irq context, from ptep_clear_flush() while in
-			 * lazy tlb mode, and here. Irqs are blocked during
-			 * schedule, protecting us from simultaneous changes.
-			 */
-			cpumask_set_cpu(cpu, mm_cpumask(next));
-
-			/*
-			 * We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 *
-			 * As above, load_cr3() is serializing and orders TLB
-			 * fills with respect to the mm_cpumask write.
-			 */
-			load_cr3(next->pgd);
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-			load_mm_cr4(next);
-			load_mm_ldt(next);
-		}
-	}
-#endif
-}
+extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			       struct task_struct *tsk);
+#define switch_mm_irqs_off switch_mm_irqs_off
 
 #define activate_mm(prev, next)			\
 do {						\
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 6ec0c8b2e9df..84c62d950023 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -18,6 +18,12 @@
 #ifndef __ASSEMBLY__
 #include <asm/x86_init.h>
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern int kaiser_enabled;
+#else
+#define kaiser_enabled 0
+#endif
+
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
 void ptdump_walk_pgd_level_checkwx(void);
 
@@ -653,7 +659,17 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
 
 static inline int pgd_bad(pgd_t pgd)
 {
-	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	pgdval_t ignore_flags = _PAGE_USER;
+	/*
+	 * We set NX on KAISER pgds that map userspace memory so
+	 * that userspace can not meaningfully use the kernel
+	 * page table by accident; it will fault on the first
+	 * instruction it tries to run.  See native_set_pgd().
+	 */
+	if (kaiser_enabled)
+		ignore_flags |= _PAGE_NX;
+
+	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
 }
 
 static inline int pgd_none(pgd_t pgd)
@@ -855,7 +871,15 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
  */
 static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 {
-       memcpy(dst, src, count * sizeof(pgd_t));
+	memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (kaiser_enabled) {
+		/* Clone the shadow pgd part as well */
+		memcpy(native_get_shadow_pgd(dst),
+			native_get_shadow_pgd(src),
+			count * sizeof(pgd_t));
+	}
+#endif
 }
 
 #define PTE_SHIFT ilog2(PTRS_PER_PTE)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 2ee781114d34..c810226e741a 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -106,9 +106,32 @@ static inline void native_pud_clear(pud_t *pud)
 	native_set_pud(pud, native_make_pud(0));
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd);
+
+static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
+{
+#ifdef CONFIG_DEBUG_VM
+	/* linux/mmdebug.h may not have been included at this point */
+	BUG_ON(!kaiser_enabled);
+#endif
+	return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE);
+}
+#else
+static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
+{
+	BUILD_BUG_ON(1);
+	return NULL;
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
-	*pgdp = pgd;
+	*pgdp = kaiser_set_shadow_pgd(pgdp, pgd);
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 79c91853e50e..8dba273da25a 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -89,7 +89,7 @@
 #define _PAGE_NX	(_AT(pteval_t, 0))
 #endif
 
-#define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
+#define _PAGE_PROTNONE  (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
 #define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
 			 _PAGE_ACCESSED | _PAGE_DIRTY)
@@ -102,6 +102,33 @@
 			 _PAGE_SOFT_DIRTY)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
+/* The ASID is the lower 12 bits of CR3 */
+#define X86_CR3_PCID_ASID_MASK  (_AC((1<<12)-1,UL))
+
+/* Mask for all the PCID-related bits in CR3: */
+#define X86_CR3_PCID_MASK       (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_MASK)
+#define X86_CR3_PCID_ASID_KERN  (_AC(0x0,UL))
+
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && defined(CONFIG_X86_64)
+/* Let X86_CR3_PCID_ASID_USER be usable for the X86_CR3_PCID_NOFLUSH bit */
+#define X86_CR3_PCID_ASID_USER	(_AC(0x80,UL))
+
+#define X86_CR3_PCID_KERN_FLUSH		(X86_CR3_PCID_ASID_KERN)
+#define X86_CR3_PCID_USER_FLUSH		(X86_CR3_PCID_ASID_USER)
+#define X86_CR3_PCID_KERN_NOFLUSH	(X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_KERN)
+#define X86_CR3_PCID_USER_NOFLUSH	(X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_USER)
+#else
+#define X86_CR3_PCID_ASID_USER  (_AC(0x0,UL))
+/*
+ * PCIDs are unsupported on 32-bit and none of these bits can be
+ * set in CR3:
+ */
+#define X86_CR3_PCID_KERN_FLUSH		(0)
+#define X86_CR3_PCID_USER_FLUSH		(0)
+#define X86_CR3_PCID_KERN_NOFLUSH	(0)
+#define X86_CR3_PCID_USER_NOFLUSH	(0)
+#endif
+
 /*
  * The cache modes defined here are used to translate between pure SW usage
  * and the HW defined cache mode bits and/or PAT entries.
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2d5a50cb61a2..f3bdaed0188f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -305,7 +305,7 @@ struct tss_struct {
 
 } ____cacheline_aligned;
 
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, cpu_tss);
 
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index baad72e4c100..6045cef376c2 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -4,6 +4,15 @@
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
 
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
+#else
+static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+	return NULL;
+}
+#endif
+
 /* some helper functions for xen and kvm pv clock sources */
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6433e28dc9c8..a691b66cc40a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -6,6 +6,55 @@
 
 #include <asm/processor.h>
 #include <asm/special_insns.h>
+#include <asm/smp.h>
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
@@ -16,10 +65,8 @@
 #endif
 
 struct tlb_state {
-#ifdef CONFIG_SMP
 	struct mm_struct *active_mm;
 	int state;
-#endif
 
 	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
@@ -84,6 +131,24 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 	cr4_set_bits(mask);
 }
 
+/*
+ * Declare a couple of kaiser interfaces here for convenience,
+ * to avoid the need for asm/kaiser.h in unexpected places.
+ */
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern int kaiser_enabled;
+extern void kaiser_setup_pcid(void);
+extern void kaiser_flush_tlb_on_return_to_user(void);
+#else
+#define kaiser_enabled 0
+static inline void kaiser_setup_pcid(void)
+{
+}
+static inline void kaiser_flush_tlb_on_return_to_user(void)
+{
+}
+#endif
+
 static inline void __native_flush_tlb(void)
 {
 	/*
@@ -92,6 +157,8 @@ static inline void __native_flush_tlb(void)
 	 * back:
 	 */
 	preempt_disable();
+	if (kaiser_enabled)
+		kaiser_flush_tlb_on_return_to_user();
 	native_write_cr3(native_read_cr3());
 	preempt_enable();
 }
@@ -101,39 +168,84 @@ static inline void __native_flush_tlb_global_irq_disabled(void)
 	unsigned long cr4;
 
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	/* clear PGE */
-	native_write_cr4(cr4 & ~X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
+	if (cr4 & X86_CR4_PGE) {
+		/* clear PGE and flush TLB of all entries */
+		native_write_cr4(cr4 & ~X86_CR4_PGE);
+		/* restore PGE as it was before */
+		native_write_cr4(cr4);
+	} else {
+		/* do it with cr3, letting kaiser flush user PCID */
+		__native_flush_tlb();
+	}
 }
 
 static inline void __native_flush_tlb_global(void)
 {
 	unsigned long flags;
 
+	if (this_cpu_has(X86_FEATURE_INVPCID)) {
+		/*
+		 * Using INVPCID is considerably faster than a pair of writes
+		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 *
+	 	 * Note, this works with CR4.PCIDE=0 or 1.
+		 */
+		invpcid_flush_all();
+		return;
+	}
+
 	/*
 	 * Read-modify-write to CR4 - protect it from preemption and
 	 * from interrupts. (Use the raw variant because this code can
 	 * be called from deep inside debugging code.)
 	 */
 	raw_local_irq_save(flags);
-
 	__native_flush_tlb_global_irq_disabled();
-
 	raw_local_irq_restore(flags);
 }
 
 static inline void __native_flush_tlb_single(unsigned long addr)
 {
-	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+	/*
+	 * SIMICS #GP's if you run INVPCID with type 2/3
+	 * and X86_CR4_PCIDE clear.  Shame!
+	 *
+	 * The ASIDs used below are hard-coded.  But, we must not
+	 * call invpcid(type=1/2) before CR4.PCIDE=1.  Just call
+	 * invlpg in the case we are called early.
+	 */
+
+	if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
+		if (kaiser_enabled)
+			kaiser_flush_tlb_on_return_to_user();
+		asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+		return;
+	}
+	/* Flush the address out of both PCIDs. */
+	/*
+	 * An optimization here might be to determine addresses
+	 * that are only kernel-mapped and only flush the kernel
+	 * ASID.  But, userspace flushes are probably much more
+	 * important performance-wise.
+	 *
+	 * Make sure to do only a single invpcid when KAISER is
+	 * disabled and we have only a single ASID.
+	 */
+	if (kaiser_enabled)
+		invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
+	invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
 }
 
 static inline void __flush_tlb_all(void)
 {
-	if (cpu_has_pge)
-		__flush_tlb_global();
-	else
-		__flush_tlb();
+	__flush_tlb_global();
+	/*
+	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
+	 * we'd end up flushing kernel translations for the current ASID but
+	 * we might fail to flush kernel translations for other cached ASIDs.
+	 *
+	 * To avoid this issue, we force PCID off if PGE is off.
+	 */
 }
 
 static inline void __flush_tlb_one(unsigned long addr)
@@ -147,7 +259,6 @@ static inline void __flush_tlb_one(unsigned long addr)
 /*
  * TLB flushing:
  *
- *  - flush_tlb() flushes the current mm struct TLBs
  *  - flush_tlb_all() flushes all processes TLBs
  *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
  *  - flush_tlb_page(vma, vmaddr) flushes one page
@@ -159,84 +270,6 @@ static inline void __flush_tlb_one(unsigned long addr)
  * and page-granular flushes are available only on i486 and up.
  */
 
-#ifndef CONFIG_SMP
-
-/* "_up" is for UniProcessor.
- *
- * This is a helper for other header functions.  *Not* intended to be called
- * directly.  All global TLB flushes need to either call this, or to bump the
- * vm statistics themselves.
- */
-static inline void __flush_tlb_up(void)
-{
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	__flush_tlb();
-}
-
-static inline void flush_tlb_all(void)
-{
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	__flush_tlb_all();
-}
-
-static inline void flush_tlb(void)
-{
-	__flush_tlb_up();
-}
-
-static inline void local_flush_tlb(void)
-{
-	__flush_tlb_up();
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	if (mm == current->active_mm)
-		__flush_tlb_up();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-				  unsigned long addr)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb_one(addr);
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb_up();
-}
-
-static inline void flush_tlb_mm_range(struct mm_struct *mm,
-	   unsigned long start, unsigned long end, unsigned long vmflag)
-{
-	if (mm == current->active_mm)
-		__flush_tlb_up();
-}
-
-static inline void native_flush_tlb_others(const struct cpumask *cpumask,
-					   struct mm_struct *mm,
-					   unsigned long start,
-					   unsigned long end)
-{
-}
-
-static inline void reset_lazy_tlbstate(void)
-{
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start,
-					  unsigned long end)
-{
-	flush_tlb_all();
-}
-
-#else  /* SMP */
-
-#include <asm/smp.h>
-
 #define local_flush_tlb() __flush_tlb()
 
 #define flush_tlb_mm(mm)	flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
@@ -245,13 +278,14 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 		flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
 
 extern void flush_tlb_all(void);
-extern void flush_tlb_current_task(void);
-extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
-#define flush_tlb()	flush_tlb_current_task()
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
+{
+	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE);
+}
 
 void native_flush_tlb_others(const struct cpumask *cpumask,
 				struct mm_struct *mm,
@@ -266,14 +300,6 @@ static inline void reset_lazy_tlbstate(void)
 	this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
 }
 
-#endif	/* SMP */
-
-/* Not inlined due to inc_irq_stat not being defined yet */
-#define flush_tlb_local() {		\
-	inc_irq_stat(irq_tlb_count);	\
-	local_flush_tlb();		\
-}
-
 #ifndef CONFIG_PARAVIRT
 #define flush_tlb_others(mask, mm, start, end)	\
 	native_flush_tlb_others(mask, mm, start, end)
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 756de9190aec..deabaf9759b6 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -22,6 +22,7 @@ struct vdso_image {
 
 	long sym_vvar_page;
 	long sym_hpet_page;
+	long sym_pvclock_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 79887abcb5e1..1361779f44fe 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -77,7 +77,8 @@
 #define X86_CR3_PWT		_BITUL(X86_CR3_PWT_BIT)
 #define X86_CR3_PCD_BIT		4 /* Page Cache Disable */
 #define X86_CR3_PCD		_BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK	_AC(0x00000fff,UL) /* PCID Mask */
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH    _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
 
 /*
  * Intel CPU features in CR4
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b1b78ffe01d0..616ebd22ef9a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -16,9 +16,21 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
-KASAN_SANITIZE_head$(BITS).o := n
-KASAN_SANITIZE_dumpstack.o := n
-KASAN_SANITIZE_dumpstack_$(BITS).o := n
+KASAN_SANITIZE_head$(BITS).o				:= n
+KASAN_SANITIZE_dumpstack.o				:= n
+KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
+KASAN_SANITIZE_stacktrace.o := n
+
+OBJECT_FILES_NON_STANDARD_head_$(BITS).o		:= y
+OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o	:= y
+OBJECT_FILES_NON_STANDARD_mcount_$(BITS).o		:= y
+OBJECT_FILES_NON_STANDARD_test_nx.o			:= y
+
+# If instrumentation of this dir is enabled, boot hangs during first second.
+# Probably could be more selective here, but note that files related to irqs,
+# boot, dumpstack/stacktrace, etc are either non-interesting or can lead to
+# non-deterministic coverage.
+KCOV_INSTRUMENT		:= n
 
 CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 8c35df468104..48e3979d174a 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -107,6 +107,15 @@ ENTRY(do_suspend_lowlevel)
 	movq	pt_regs_r14(%rax), %r14
 	movq	pt_regs_r15(%rax), %r15
 
+#ifdef CONFIG_KASAN
+	/*
+	 * The suspend path may have poisoned some areas deeper in the stack,
+	 * which we now need to unpoison.
+	 */
+	movq	%rsp, %rdi
+	call	kasan_unpoison_task_stack_below
+#endif
+
 	xorl	%eax, %eax
 	addq	$8, %rsp
 	jmp	restore_processor_state
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 8bb12ddc5db8..8e63ebdcbd0b 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -2,6 +2,10 @@
 # Makefile for local APIC drivers and for the IO-APIC code
 #
 
+# Leads to non-deterministic coverage that is not a function of syscall inputs.
+# In particualr, smp_apic_timer_interrupt() is called in random places.
+KCOV_INSTRUMENT		:= n
+
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o ipi.o vector.o
 obj-y				+= hw_nmi.o
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 58031303e304..c108683bb32c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -8,6 +8,10 @@ CFLAGS_REMOVE_common.o = -pg
 CFLAGS_REMOVE_perf_event.o = -pg
 endif
 
+# If these files are instrumented, boot hangs during the first second.
+KCOV_INSTRUMENT_common.o := n
+KCOV_INSTRUMENT_perf_event.o := n
+
 # Make sure load_percpu_segment has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_common.o		:= $(nostackp)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bd17db15a2c1..0b6124315441 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -19,6 +19,14 @@
 
 void __init check_bugs(void)
 {
+#ifdef CONFIG_X86_32
+	/*
+	 * Regardless of whether PCID is enumerated, the SDM says
+	 * that it can't be enabled in 32-bit mode.
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_PCID);
+#endif
+
 	identify_boot_cpu();
 #ifndef CONFIG_SMP
 	pr_info("CPU: ");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 637ca414d431..cc154ac64f00 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -92,7 +92,7 @@ static const struct cpu_dev default_cpu = {
 
 static const struct cpu_dev *this_cpu = &default_cpu;
 
-DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
+DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page) = { .gdt = {
 #ifdef CONFIG_X86_64
 	/*
 	 * We need valid kernel segments for data and code in long mode too
@@ -162,6 +162,40 @@ static int __init x86_mpx_setup(char *s)
 }
 __setup("nompx", x86_mpx_setup);
 
+#ifdef CONFIG_X86_64
+static int __init x86_pcid_setup(char *s)
+{
+	/* require an exact match without trailing characters */
+	if (strlen(s))
+		return 0;
+
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_PCID))
+		return 1;
+
+	setup_clear_cpu_cap(X86_FEATURE_PCID);
+	pr_info("nopcid: PCID feature disabled\n");
+	return 1;
+}
+__setup("nopcid", x86_pcid_setup);
+#endif
+
+static int __init x86_noinvpcid_setup(char *s)
+{
+	/* noinvpcid doesn't accept parameters */
+	if (s)
+		return -EINVAL;
+
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_INVPCID))
+		return 0;
+
+	setup_clear_cpu_cap(X86_FEATURE_INVPCID);
+	pr_info("noinvpcid: INVPCID feature disabled\n");
+	return 0;
+}
+early_param("noinvpcid", x86_noinvpcid_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
 static int disable_x86_serial_nr = 1;
@@ -287,6 +321,39 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 	}
 }
 
+static void setup_pcid(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_PCID)) {
+		if (cpu_has(c, X86_FEATURE_PGE) || kaiser_enabled) {
+			cr4_set_bits(X86_CR4_PCIDE);
+			/*
+			 * INVPCID has two "groups" of types:
+			 * 1/2: Invalidate an individual address
+			 * 3/4: Invalidate all contexts
+			 *
+			 * 1/2 take a PCID, but 3/4 do not.  So, 3/4
+			 * ignore the PCID argument in the descriptor.
+			 * But, we have to be careful not to call 1/2
+			 * with an actual non-zero PCID in them before
+			 * we do the above cr4_set_bits().
+			 */
+			if (cpu_has(c, X86_FEATURE_INVPCID))
+				set_cpu_cap(c, X86_FEATURE_INVPCID_SINGLE);
+		} else {
+			/*
+			 * flush_tlb_all(), as currently implemented, won't
+			 * work if PCID is on but PGE is not.  Since that
+			 * combination doesn't exist on real hardware, there's
+			 * no reason to try to fully support it, but it's
+			 * polite to avoid corrupting data if we're on
+			 * an improperly configured VM.
+			 */
+			clear_cpu_cap(c, X86_FEATURE_PCID);
+		}
+	}
+	kaiser_setup_pcid();
+}
+
 /*
  * Some CPU features depend on higher CPUID levels, which may not always
  * be available due to CPUID level capping or broken virtualization
@@ -918,6 +985,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	setup_smep(c);
 	setup_smap(c);
 
+	/* Set up PCID */
+	setup_pcid(c);
+
 	/*
 	 * The vendor-specific functions might have changed features.
 	 * Now we do "generic changes."
@@ -1173,7 +1243,7 @@ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
 	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
 };
 
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(char, exception_stacks
 	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
 
 /* May not be marked __init: used by software suspend */
@@ -1336,6 +1406,14 @@ void cpu_init(void)
 	 * try to read it.
 	 */
 	cr4_init_shadow();
+	if (!kaiser_enabled) {
+		/*
+		 * secondary_startup_64() deferred setting PGE in cr4:
+		 * probe_page_size_mask() sets it on the boot cpu,
+		 * but it needs to be set on each secondary cpu.
+		 */
+		cr4_set_bits(X86_CR4_PGE);
+	}
 
 	/*
 	 * Load microcode on this cpu if a valid microcode is available.
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 1e7de3cefc9c..f01b3a12dce0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -2,11 +2,15 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 
+#include <asm/kaiser.h>
 #include <asm/perf_event.h>
 #include <asm/insn.h>
 
 #include "perf_event.h"
 
+static
+DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct debug_store, cpu_debug_store);
+
 /* The size of a BTS record in bytes: */
 #define BTS_RECORD_SIZE		24
 
@@ -268,6 +272,39 @@ void fini_debug_store_on_cpu(int cpu)
 
 static DEFINE_PER_CPU(void *, insn_buffer);
 
+static void *dsalloc(size_t size, gfp_t flags, int node)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	unsigned int order = get_order(size);
+	struct page *page;
+	unsigned long addr;
+
+	page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+	if (!page)
+		return NULL;
+	addr = (unsigned long)page_address(page);
+	if (kaiser_add_mapping(addr, size, __PAGE_KERNEL) < 0) {
+		__free_pages(page, order);
+		addr = 0;
+	}
+	return (void *)addr;
+#else
+	return kmalloc_node(size, flags | __GFP_ZERO, node);
+#endif
+}
+
+static void dsfree(const void *buffer, size_t size)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (!buffer)
+		return;
+	kaiser_remove_mapping((unsigned long)buffer, size);
+	free_pages((unsigned long)buffer, get_order(size));
+#else
+	kfree(buffer);
+#endif
+}
+
 static int alloc_pebs_buffer(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -278,7 +315,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+	buffer = dsalloc(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -289,7 +326,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (x86_pmu.intel_cap.pebs_format < 2) {
 		ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
 		if (!ibuffer) {
-			kfree(buffer);
+			dsfree(buffer, x86_pmu.pebs_buffer_size);
 			return -ENOMEM;
 		}
 		per_cpu(insn_buffer, cpu) = ibuffer;
@@ -315,7 +352,8 @@ static void release_pebs_buffer(int cpu)
 	kfree(per_cpu(insn_buffer, cpu));
 	per_cpu(insn_buffer, cpu) = NULL;
 
-	kfree((void *)(unsigned long)ds->pebs_buffer_base);
+	dsfree((void *)(unsigned long)ds->pebs_buffer_base,
+			x86_pmu.pebs_buffer_size);
 	ds->pebs_buffer_base = 0;
 }
 
@@ -329,7 +367,7 @@ static int alloc_bts_buffer(int cpu)
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	buffer = dsalloc(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
 	if (unlikely(!buffer)) {
 		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
@@ -355,19 +393,15 @@ static void release_bts_buffer(int cpu)
 	if (!ds || !x86_pmu.bts)
 		return;
 
-	kfree((void *)(unsigned long)ds->bts_buffer_base);
+	dsfree((void *)(unsigned long)ds->bts_buffer_base, BTS_BUFFER_SIZE);
 	ds->bts_buffer_base = 0;
 }
 
 static int alloc_ds_buffer(int cpu)
 {
-	int node = cpu_to_node(cpu);
-	struct debug_store *ds;
-
-	ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
-	if (unlikely(!ds))
-		return -ENOMEM;
+	struct debug_store *ds = per_cpu_ptr(&cpu_debug_store, cpu);
 
+	memset(ds, 0, sizeof(*ds));
 	per_cpu(cpu_hw_events, cpu).ds = ds;
 
 	return 0;
@@ -381,7 +415,6 @@ static void release_ds_buffer(int cpu)
 		return;
 
 	per_cpu(cpu_hw_events, cpu).ds = NULL;
-	kfree(ds);
 }
 
 void release_ds_buffers(void)
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 4d38416e2a7f..b02cb2ec6726 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -41,6 +41,7 @@
 #include <asm/pgalloc.h>
 #include <asm/setup.h>
 #include <asm/espfix.h>
+#include <asm/kaiser.h>
 
 /*
  * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
@@ -126,6 +127,15 @@ void __init init_espfix_bsp(void)
 	/* Install the espfix pud into the kernel page directory */
 	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
 	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+	/*
+	 * Just copy the top-level PGD that is mapping the espfix
+	 * area to ensure it is mapped into the shadow user page
+	 * tables.
+	 */
+	if (kaiser_enabled) {
+		set_pgd(native_get_shadow_pgd(pgd_p),
+			__pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page)));
+	}
 
 	/* Randomize the locations */
 	init_espfix_random();
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index ffdc0e860390..4034e905741a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -183,8 +183,8 @@ ENTRY(secondary_startup_64)
 	movq	$(init_level4_pgt - __START_KERNEL_map), %rax
 1:
 
-	/* Enable PAE mode and PGE */
-	movl	$(X86_CR4_PAE | X86_CR4_PGE), %ecx
+	/* Enable PAE and PSE, but defer PGE until kaiser_enabled is decided */
+	movl	$(X86_CR4_PAE | X86_CR4_PSE), %ecx
 	movq	%rcx, %cr4
 
 	/* Setup early boot stage 4 level pagetables. */
@@ -441,6 +441,27 @@ early_idt_ripmsg:
 	.balign	PAGE_SIZE; \
 GLOBAL(name)
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Each PGD needs to be 8k long and 8k aligned.  We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define KAISER_USER_PGD_FILL	512
+/* This ensures they are 8k-aligned: */
+#define NEXT_PGD_PAGE(name) \
+	.balign 2 * PAGE_SIZE; \
+GLOBAL(name)
+#else
+#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define KAISER_USER_PGD_FILL	0
+#endif
+
 /* Automate the creation of 1 to 1 mapping pmd entries */
 #define PMDS(START, PERM, COUNT)			\
 	i = 0 ;						\
@@ -450,9 +471,10 @@ GLOBAL(name)
 	.endr
 
 	__INITDATA
-NEXT_PAGE(early_level4_pgt)
+NEXT_PGD_PAGE(early_level4_pgt)
 	.fill	511,8,0
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -460,16 +482,18 @@ NEXT_PAGE(early_dynamic_pgts)
 	.data
 
 #ifndef CONFIG_XEN
-NEXT_PAGE(init_level4_pgt)
+NEXT_PGD_PAGE(init_level4_pgt)
 	.fill	512,8,0
+	.fill	KAISER_USER_PGD_FILL,8,0
 #else
-NEXT_PAGE(init_level4_pgt)
+NEXT_PGD_PAGE(init_level4_pgt)
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
 	.org    init_level4_pgt + L4_PAGE_OFFSET*8, 0
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
 	.org    init_level4_pgt + L4_START_KERNEL*8, 0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
 	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(level3_ident_pgt)
 	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
@@ -480,6 +504,7 @@ NEXT_PAGE(level2_ident_pgt)
 	 */
 	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
 #endif
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(level3_kernel_pgt)
 	.fill	L3_START_KERNEL,8,0
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index acc9b8f19ca8..f48eb8eeefe2 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -353,7 +353,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 
 		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-		disable_irq(hdev->irq);
+		disable_hardirq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 		enable_irq(hdev->irq);
 	}
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 61521dc19c10..9f669fdd2010 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_puts(p, "  Rescheduling interrupts\n");
 	seq_printf(p, "%*s: ", prec, "CAL");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
-					irq_stats(j)->irq_tlb_count);
+		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
 	seq_puts(p, "  Function call interrupts\n");
 	seq_printf(p, "%*s: ", prec, "TLB");
 	for_each_online_cpu(j)
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 1423ab1b0312..f480b38a03c3 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -51,7 +51,7 @@ static struct irqaction irq2 = {
 	.flags = IRQF_NO_THREAD,
 };
 
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
+DEFINE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq) = {
 	[0 ... NR_VECTORS - 1] = VECTOR_UNUSED,
 };
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 99d293ea2b49..3eb804335458 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -49,7 +49,7 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
-
+#include <linux/kasan.h>
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
@@ -1078,6 +1078,9 @@ void jprobe_return(void)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
+	/* Unpoison stack redzones in the frames we are going to jump over. */
+	kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
+
 	asm volatile (
 #ifdef CONFIG_X86_64
 			"       xchg   %%rbx,%%rsp	\n"
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2bd81e302427..ec1b06dc82d2 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock);
 static struct pvclock_vsyscall_time_info *hv_clock;
 static struct pvclock_wall_clock wall_clock;
 
+struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+	return hv_clock;
+}
+
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * have elapsed since the hypervisor wrote the data. So we try to account for
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index d6279593bcdd..bc429365b72a 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <linux/kaiser.h>
 
 #include <asm/ldt.h>
 #include <asm/desc.h>
@@ -34,11 +35,21 @@ static void flush_ldt(void *current_mm)
 	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
 
+static void __free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		free_page((unsigned long)ldt->entries);
+	kfree(ldt);
+}
+
 /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
 static struct ldt_struct *alloc_ldt_struct(int size)
 {
 	struct ldt_struct *new_ldt;
 	int alloc_size;
+	int ret;
 
 	if (size > LDT_ENTRIES)
 		return NULL;
@@ -66,7 +77,13 @@ static struct ldt_struct *alloc_ldt_struct(int size)
 		return NULL;
 	}
 
+	ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
+				 __PAGE_KERNEL);
 	new_ldt->size = size;
+	if (ret) {
+		__free_ldt_struct(new_ldt);
+		return NULL;
+	}
 	return new_ldt;
 }
 
@@ -92,12 +109,10 @@ static void free_ldt_struct(struct ldt_struct *ldt)
 	if (likely(!ldt))
 		return;
 
+	kaiser_remove_mapping((unsigned long)ldt->entries,
+			      ldt->size * LDT_ENTRY_SIZE);
 	paravirt_free_ldt(ldt->entries, ldt->size);
-	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
-		vfree(ldt->entries);
-	else
-		free_page((unsigned long)ldt->entries);
-	kfree(ldt);
+	__free_ldt_struct(ldt);
 }
 
 /*
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 8aa05583bc42..0677bf8d3a42 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -9,7 +9,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
 
@@ -62,7 +61,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
 		PATCH_SITE(pv_cpu_ops, clts);
-		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
 #if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
 		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 57eca132962f..c1b21d61b769 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -39,7 +39,7 @@
  * section. Since TSS's are completely CPU-local, we want them
  * on exact cacheline boundaries, to eliminate cacheline ping-pong.
  */
-__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
+__visible DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, cpu_tss) = {
 	.x86_tss = {
 		.sp0 = TOP_OF_INIT_STACK,
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f660d63f40fe..9a16932c7258 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -93,6 +93,10 @@ void __noreturn machine_real_restart(unsigned int type)
 	load_cr3(initial_page_table);
 #else
 	write_cr3(real_mode_header->trampoline_pgd);
+
+	/* Exiting long mode will fail if CR4.PCIDE is set. */
+	if (static_cpu_has(X86_FEATURE_PCID))
+		cr4_clear_bits(X86_CR4_PCIDE);
 #endif
 
 	/* Jump to the identity-mapped low memory code */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index e67b834279b2..bbaae4cf9e8e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -112,6 +112,7 @@
 #include <asm/alternative.h>
 #include <asm/prom.h>
 #include <asm/microcode.h>
+#include <asm/kaiser.h>
 
 /*
  * max_low_pfn_mapped: highest direct mapped pfn under 4GB
@@ -1016,6 +1017,12 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	init_hypervisor_platform();
 
+	/*
+	 * This needs to happen right after XENPV is set on xen and
+	 * kaiser_enabled is checked below in cleanup_highmap().
+	 */
+	kaiser_check_boottime_disable();
+
 	x86_init.resources.probe_roms();
 
 	/* after parse_early_param, so could debug it */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fbabe4fcc7fb..fe89f938e0f0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -104,14 +104,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 	spin_lock_irqsave(&rtc_lock, flags);
 	CMOS_WRITE(0xa, 0xf);
 	spin_unlock_irqrestore(&rtc_lock, flags);
-	local_flush_tlb();
-	pr_debug("1.\n");
 	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
 							start_eip >> 4;
-	pr_debug("2.\n");
 	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
 							start_eip & 0xf;
-	pr_debug("3.\n");
 }
 
 static inline void smpboot_restore_warm_reset_vector(void)
@@ -119,11 +115,6 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	unsigned long flags;
 
 	/*
-	 * Install writable page 0 entry to set BIOS data area.
-	 */
-	local_flush_tlb();
-
-	/*
 	 * Paranoid:  Set warm reset code and vector here back
 	 * to default values.
 	 */
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
index 1c113db9ed57..2bb5ee464df3 100644
--- a/arch/x86/kernel/tracepoint.c
+++ b/arch/x86/kernel/tracepoint.c
@@ -9,10 +9,12 @@
 #include <linux/atomic.h>
 
 atomic_t trace_idt_ctr = ATOMIC_INIT(0);
+__aligned(PAGE_SIZE)
 struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1,
 				(unsigned long) trace_idt_table };
 
 /* No need to be aligned, but done to keep all IDTs defined the same way. */
+__aligned(PAGE_SIZE)
 gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss;
 
 static int trace_irq_vector_refcount;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 524619351961..510e80da7de4 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -187,7 +187,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	pte_unmap_unlock(pte, ptl);
 out:
 	up_write(&mm->mmap_sem);
-	flush_tlb();
+	flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL);
 }
 
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index fe133b710bef..1d0e36f909eb 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -101,6 +101,7 @@ SECTIONS
 		KPROBES_TEXT
 		ENTRY_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
 		/* End of text section */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 684edebb4a0c..00045499f6c2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2383,9 +2383,21 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
 }
 
 static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
-				     u64 cr0, u64 cr4)
+				    u64 cr0, u64 cr3, u64 cr4)
 {
 	int bad;
+	u64 pcid;
+
+	/* In order to later set CR4.PCIDE, CR3[11:0] must be zero.  */
+	pcid = 0;
+	if (cr4 & X86_CR4_PCIDE) {
+		pcid = cr3 & 0xfff;
+		cr3 &= ~0xfff;
+	}
+
+	bad = ctxt->ops->set_cr(ctxt, 3, cr3);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
 
 	/*
 	 * First enable PAE, long mode needs it before CR0.PG = 1 is set.
@@ -2404,6 +2416,12 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
 		bad = ctxt->ops->set_cr(ctxt, 4, cr4);
 		if (bad)
 			return X86EMUL_UNHANDLEABLE;
+		if (pcid) {
+			bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid);
+			if (bad)
+				return X86EMUL_UNHANDLEABLE;
+		}
+
 	}
 
 	return X86EMUL_CONTINUE;
@@ -2414,11 +2432,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	struct desc_struct desc;
 	struct desc_ptr dt;
 	u16 selector;
-	u32 val, cr0, cr4;
+	u32 val, cr0, cr3, cr4;
 	int i;
 
 	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
-	ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+	cr3 =                      GET_SMSTATE(u32, smbase, 0x7ff8);
 	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
 	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
 
@@ -2460,14 +2478,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
 
-	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+	return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 }
 
 static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
-	u64 val, cr0, cr4;
+	u64 val, cr0, cr3, cr4;
 	u32 base3;
 	u16 selector;
 	int i, r;
@@ -2484,7 +2502,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
 	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
-	ctxt->ops->set_cr(ctxt, 3,  GET_SMSTATE(u64, smbase, 0x7f50));
+	cr3 =                       GET_SMSTATE(u64, smbase, 0x7f50);
 	cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
 	val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
@@ -2512,7 +2530,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
-	r = rsm_enter_protected_mode(ctxt, cr0, cr4);
+	r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 	if (r != X86EMUL_CONTINUE)
 		return r;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 253a8c8207bb..d915185ada05 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1107,6 +1107,11 @@ static inline bool cpu_has_vmx_invvpid_global(void)
 	return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
 }
 
+static inline bool cpu_has_vmx_invvpid(void)
+{
+	return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
+}
+
 static inline bool cpu_has_vmx_ept(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -6182,12 +6187,7 @@ static __init int hardware_setup(void)
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
 
-	/*
-	 * Allow direct access to the PC debug port (it is often used for I/O
-	 * delays, but the vmexits simply slow things down).
-	 */
 	memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
-	clear_bit(0x80, vmx_io_bitmap_a);
 
 	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
@@ -6204,8 +6204,10 @@ static __init int hardware_setup(void)
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
 
-	if (!cpu_has_vmx_vpid())
+	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
+		!(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
+
 	if (!cpu_has_vmx_shadow_vmcs())
 		enable_shadow_vmcs = 0;
 	if (enable_shadow_vmcs)
@@ -6929,9 +6931,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
 static int handle_vmclear(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 zero = 0;
 	gpa_t vmptr;
-	struct vmcs12 *vmcs12;
-	struct page *page;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
@@ -6942,22 +6943,9 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 	if (vmptr == vmx->nested.current_vmptr)
 		nested_release_vmcs12(vmx);
 
-	page = nested_get_page(vcpu, vmptr);
-	if (page == NULL) {
-		/*
-		 * For accurate processor emulation, VMCLEAR beyond available
-		 * physical memory should do nothing at all. However, it is
-		 * possible that a nested vmx bug, not a guest hypervisor bug,
-		 * resulted in this case, so let's shut down before doing any
-		 * more damage:
-		 */
-		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		return 1;
-	}
-	vmcs12 = kmap(page);
-	vmcs12->launch_state = 0;
-	kunmap(page);
-	nested_release_page(page);
+	kvm_vcpu_write_guest(vcpu,
+			vmptr + offsetof(struct vmcs12, launch_state),
+			&zero, sizeof(zero));
 
 	nested_free_vmcs02(vmx, vmptr);
 
@@ -10574,8 +10562,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
  */
 static void vmx_leave_nested(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu))
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.nested_run_pending = 0;
 		nested_vmx_vmexit(vcpu, -1, 0, 0);
+	}
 	free_nested(to_vmx(vcpu));
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index df81717a92f3..ccf17dbfea09 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -759,7 +759,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 			return 1;
 
 		/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
-		if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu))
+		if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_ASID_MASK) ||
+		    !is_long_mode(vcpu))
 			return 1;
 	}
 
@@ -6941,7 +6942,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 #endif
 
 	kvm_rip_write(vcpu, regs->rip);
-	kvm_set_rflags(vcpu, regs->rflags);
+	kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);
 
 	vcpu->arch.exception.pending = false;
 
@@ -8230,11 +8231,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 
 	if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
 	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 11f59fdbd460..5e0c5a2a021d 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -2,6 +2,9 @@
 # Makefile for x86 specific library files.
 #
 
+# Produces uninteresting flaky coverage.
+KCOV_INSTRUMENT_delay.o	:= n
+
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
 inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
 quiet_cmd_inat_tables = GEN     $@
diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c
index 422db000d727..a744506856b1 100644
--- a/arch/x86/lib/cmdline.c
+++ b/arch/x86/lib/cmdline.c
@@ -82,3 +82,108 @@ int cmdline_find_option_bool(const char *cmdline, const char *option)
 
 	return 0;	/* Buffer overrun */
 }
+
+/*
+ * Find a non-boolean option (i.e. option=argument). In accordance with
+ * standard Linux practice, if this option is repeated, this returns the
+ * last instance on the command line.
+ *
+ * @cmdline: the cmdline string
+ * @max_cmdline_size: the maximum size of cmdline
+ * @option: option string to look for
+ * @buffer: memory buffer to return the option argument
+ * @bufsize: size of the supplied memory buffer
+ *
+ * Returns the length of the argument (regardless of if it was
+ * truncated to fit in the buffer), or -1 on not found.
+ */
+static int
+__cmdline_find_option(const char *cmdline, int max_cmdline_size,
+		      const char *option, char *buffer, int bufsize)
+{
+	char c;
+	int pos = 0, len = -1;
+	const char *opptr = NULL;
+	char *bufptr = buffer;
+	enum {
+		st_wordstart = 0,	/* Start of word/after whitespace */
+		st_wordcmp,	/* Comparing this word */
+		st_wordskip,	/* Miscompare, skip */
+		st_bufcpy,	/* Copying this to buffer */
+	} state = st_wordstart;
+
+	if (!cmdline)
+		return -1;      /* No command line */
+
+	/*
+	 * This 'pos' check ensures we do not overrun
+	 * a non-NULL-terminated 'cmdline'
+	 */
+	while (pos++ < max_cmdline_size) {
+		c = *(char *)cmdline++;
+		if (!c)
+			break;
+
+		switch (state) {
+		case st_wordstart:
+			if (myisspace(c))
+				break;
+
+			state = st_wordcmp;
+			opptr = option;
+			/* fall through */
+
+		case st_wordcmp:
+			if ((c == '=') && !*opptr) {
+				/*
+				 * We matched all the way to the end of the
+				 * option we were looking for, prepare to
+				 * copy the argument.
+				 */
+				len = 0;
+				bufptr = buffer;
+				state = st_bufcpy;
+				break;
+			} else if (c == *opptr++) {
+				/*
+				 * We are currently matching, so continue
+				 * to the next character on the cmdline.
+				 */
+				break;
+			}
+			state = st_wordskip;
+			/* fall through */
+
+		case st_wordskip:
+			if (myisspace(c))
+				state = st_wordstart;
+			break;
+
+		case st_bufcpy:
+			if (myisspace(c)) {
+				state = st_wordstart;
+			} else {
+				/*
+				 * Increment len, but don't overrun the
+				 * supplied buffer and leave room for the
+				 * NULL terminator.
+				 */
+				if (++len < bufsize)
+					*bufptr++ = c;
+			}
+			break;
+		}
+	}
+
+	if (bufsize)
+		*bufptr = '\0';
+
+	return len;
+}
+
+int cmdline_find_option(const char *cmdline, const char *option, char *buffer,
+			int bufsize)
+{
+	return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option,
+				     buffer, bufsize);
+}
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 65c47fda26fc..eaf852500be4 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,8 @@
+# Kernel does not boot with instrumentation of tlb.c.
+KCOV_INSTRUMENT_tlb.o	:= n
+
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o gup.o setup_nx.o
+	    pat.o pgtable.o physaddr.o gup.o setup_nx.o tlb.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
@@ -9,7 +12,6 @@ CFLAGS_setup_nx.o		:= $(nostackp)
 CFLAGS_fault.o := -I$(src)/../include/asm/trace
 
 obj-$(CONFIG_X86_PAT)		+= pat_rbtree.o
-obj-$(CONFIG_SMP)		+= tlb.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
@@ -33,3 +35,4 @@ obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
 obj-$(CONFIG_X86_INTEL_MPX)	+= mpx.o
+obj-$(CONFIG_PAGE_TABLE_ISOLATION)		+= kaiser.o
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 3aebbd6c6f5f..2bd45ae91eb3 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -165,7 +165,7 @@ static void __init probe_page_size_mask(void)
 		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
 	/* Enable PGE if available */
-	if (cpu_has_pge) {
+	if (cpu_has_pge && !kaiser_enabled) {
 		cr4_set_bits_and_update_boot(X86_CR4_PGE);
 		__supported_pte_mask |= _PAGE_GLOBAL;
 	} else
@@ -753,10 +753,8 @@ void __init zone_sizes_init(void)
 }
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
-#ifdef CONFIG_SMP
 	.active_mm = &init_mm,
 	.state = 0,
-#endif
 	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
 };
 EXPORT_SYMBOL_GPL(cpu_tlbstate);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e08d141844ee..97b6b0164dcb 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -395,6 +395,16 @@ void __init cleanup_highmap(void)
 			continue;
 		if (vaddr < (unsigned long) _text || vaddr > end)
 			set_pmd(pmd, __pmd(0));
+		else if (kaiser_enabled) {
+			/*
+			 * level2_kernel_pgt is initialized with _PAGE_GLOBAL:
+			 * clear that now.  This is not important, so long as
+			 * CR4.PGE remains clear, but it removes an anomaly.
+			 * Physical mapping setup below avoids _PAGE_GLOBAL
+			 * by use of massage_pgprot() inside pfn_pte() etc.
+			 */
+			set_pmd(pmd, pmd_clear_flags(*pmd, _PAGE_GLOBAL));
+		}
 	}
 }
 
diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c
new file mode 100644
index 000000000000..b0b3a69f1c7f
--- /dev/null
+++ b/arch/x86/mm/kaiser.c
@@ -0,0 +1,456 @@
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt
+
+#include <asm/kaiser.h>
+#include <asm/tlbflush.h>	/* to verify its kaiser declarations */
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/desc.h>
+#include <asm/cmdline.h>
+
+int kaiser_enabled __read_mostly = 1;
+EXPORT_SYMBOL(kaiser_enabled);	/* for inlined TLB flush functions */
+
+__visible
+DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+
+/*
+ * These can have bit 63 set, so we can not just use a plain "or"
+ * instruction to get their value or'd into CR3.  It would take
+ * another register.  So, we use a memory reference to these instead.
+ *
+ * This is also handy because systems that do not support PCIDs
+ * just end up or'ing a 0 into their CR3, which does no harm.
+ */
+DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user);
+
+/*
+ * At runtime, the only things we map are some things for CPU
+ * hotplug, and stacks for new processes.  No two CPUs will ever
+ * be populating the same addresses, so we only need to ensure
+ * that we protect between two CPUs trying to allocate and
+ * populate the same page table page.
+ *
+ * Only take this lock when doing a set_p[4um]d(), but it is not
+ * needed for doing a set_pte().  We assume that only the *owner*
+ * of a given allocation will be doing this for _their_
+ * allocation.
+ *
+ * This ensures that once a system has been running for a while
+ * and there have been stacks all over and these page tables
+ * are fully populated, there will be no further acquisitions of
+ * this lock.
+ */
+static DEFINE_SPINLOCK(shadow_table_allocation_lock);
+
+/*
+ * Returns -1 on error.
+ */
+static inline unsigned long get_pa_from_mapping(unsigned long vaddr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset_k(vaddr);
+	/*
+	 * We made all the kernel PGDs present in kaiser_init().
+	 * We expect them to stay that way.
+	 */
+	BUG_ON(pgd_none(*pgd));
+	/*
+	 * PGDs are either 512GB or 128TB on all x86_64
+	 * configurations.  We don't handle these.
+	 */
+	BUG_ON(pgd_large(*pgd));
+
+	pud = pud_offset(pgd, vaddr);
+	if (pud_none(*pud)) {
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+
+	if (pud_large(*pud))
+		return (pud_pfn(*pud) << PAGE_SHIFT) | (vaddr & ~PUD_PAGE_MASK);
+
+	pmd = pmd_offset(pud, vaddr);
+	if (pmd_none(*pmd)) {
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+
+	if (pmd_large(*pmd))
+		return (pmd_pfn(*pmd) << PAGE_SHIFT) | (vaddr & ~PMD_PAGE_MASK);
+
+	pte = pte_offset_kernel(pmd, vaddr);
+	if (pte_none(*pte)) {
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+
+	return (pte_pfn(*pte) << PAGE_SHIFT) | (vaddr & ~PAGE_MASK);
+}
+
+/*
+ * This is a relatively normal page table walk, except that it
+ * also tries to allocate page tables pages along the way.
+ *
+ * Returns a pointer to a PTE on success, or NULL on failure.
+ */
+static pte_t *kaiser_pagetable_walk(unsigned long address)
+{
+	pmd_t *pmd;
+	pud_t *pud;
+	pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address));
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+
+	if (pgd_none(*pgd)) {
+		WARN_ONCE(1, "All shadow pgds should have been populated");
+		return NULL;
+	}
+	BUILD_BUG_ON(pgd_large(*pgd) != 0);
+
+	pud = pud_offset(pgd, address);
+	/* The shadow page tables do not use large mappings: */
+	if (pud_large(*pud)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	if (pud_none(*pud)) {
+		unsigned long new_pmd_page = __get_free_page(gfp);
+		if (!new_pmd_page)
+			return NULL;
+		spin_lock(&shadow_table_allocation_lock);
+		if (pud_none(*pud)) {
+			set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+			__inc_zone_page_state(virt_to_page((void *)
+						new_pmd_page), NR_KAISERTABLE);
+		} else
+			free_page(new_pmd_page);
+		spin_unlock(&shadow_table_allocation_lock);
+	}
+
+	pmd = pmd_offset(pud, address);
+	/* The shadow page tables do not use large mappings: */
+	if (pmd_large(*pmd)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	if (pmd_none(*pmd)) {
+		unsigned long new_pte_page = __get_free_page(gfp);
+		if (!new_pte_page)
+			return NULL;
+		spin_lock(&shadow_table_allocation_lock);
+		if (pmd_none(*pmd)) {
+			set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+			__inc_zone_page_state(virt_to_page((void *)
+						new_pte_page), NR_KAISERTABLE);
+		} else
+			free_page(new_pte_page);
+		spin_unlock(&shadow_table_allocation_lock);
+	}
+
+	return pte_offset_kernel(pmd, address);
+}
+
+static int kaiser_add_user_map(const void *__start_addr, unsigned long size,
+			       unsigned long flags)
+{
+	int ret = 0;
+	pte_t *pte;
+	unsigned long start_addr = (unsigned long )__start_addr;
+	unsigned long address = start_addr & PAGE_MASK;
+	unsigned long end_addr = PAGE_ALIGN(start_addr + size);
+	unsigned long target_address;
+
+	/*
+	 * It is convenient for callers to pass in __PAGE_KERNEL etc,
+	 * and there is no actual harm from setting _PAGE_GLOBAL, so
+	 * long as CR4.PGE is not set.  But it is nonetheless troubling
+	 * to see Kaiser itself setting _PAGE_GLOBAL (now that "nokaiser"
+	 * requires that not to be #defined to 0): so mask it off here.
+	 */
+	flags &= ~_PAGE_GLOBAL;
+
+	for (; address < end_addr; address += PAGE_SIZE) {
+		target_address = get_pa_from_mapping(address);
+		if (target_address == -1) {
+			ret = -EIO;
+			break;
+		}
+		pte = kaiser_pagetable_walk(address);
+		if (!pte) {
+			ret = -ENOMEM;
+			break;
+		}
+		if (pte_none(*pte)) {
+			set_pte(pte, __pte(flags | target_address));
+		} else {
+			pte_t tmp;
+			set_pte(&tmp, __pte(flags | target_address));
+			WARN_ON_ONCE(!pte_same(*pte, tmp));
+		}
+	}
+	return ret;
+}
+
+static int kaiser_add_user_map_ptrs(const void *start, const void *end, unsigned long flags)
+{
+	unsigned long size = end - start;
+
+	return kaiser_add_user_map(start, size, flags);
+}
+
+/*
+ * Ensure that the top level of the (shadow) page tables are
+ * entirely populated.  This ensures that all processes that get
+ * forked have the same entries.  This way, we do not have to
+ * ever go set up new entries in older processes.
+ *
+ * Note: we never free these, so there are no updates to them
+ * after this.
+ */
+static void __init kaiser_init_all_pgds(void)
+{
+	pgd_t *pgd;
+	int i = 0;
+
+	pgd = native_get_shadow_pgd(pgd_offset_k((unsigned long )0));
+	for (i = PTRS_PER_PGD / 2; i < PTRS_PER_PGD; i++) {
+		pgd_t new_pgd;
+		pud_t *pud = pud_alloc_one(&init_mm,
+					   PAGE_OFFSET + i * PGDIR_SIZE);
+		if (!pud) {
+			WARN_ON(1);
+			break;
+		}
+		inc_zone_page_state(virt_to_page(pud), NR_KAISERTABLE);
+		new_pgd = __pgd(_KERNPG_TABLE |__pa(pud));
+		/*
+		 * Make sure not to stomp on some other pgd entry.
+		 */
+		if (!pgd_none(pgd[i])) {
+			WARN_ON(1);
+			continue;
+		}
+		set_pgd(pgd + i, new_pgd);
+	}
+}
+
+#define kaiser_add_user_map_early(start, size, flags) do {	\
+	int __ret = kaiser_add_user_map(start, size, flags);	\
+	WARN_ON(__ret);						\
+} while (0)
+
+#define kaiser_add_user_map_ptrs_early(start, end, flags) do {		\
+	int __ret = kaiser_add_user_map_ptrs(start, end, flags);	\
+	WARN_ON(__ret);							\
+} while (0)
+
+void __init kaiser_check_boottime_disable(void)
+{
+	bool enable = true;
+	char arg[5];
+	int ret;
+
+	if (boot_cpu_has(X86_FEATURE_XENPV))
+		goto silent_disable;
+
+	ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
+	if (ret > 0) {
+		if (!strncmp(arg, "on", 2))
+			goto enable;
+
+		if (!strncmp(arg, "off", 3))
+			goto disable;
+
+		if (!strncmp(arg, "auto", 4))
+			goto skip;
+	}
+
+	if (cmdline_find_option_bool(boot_command_line, "nopti"))
+		goto disable;
+
+skip:
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		goto disable;
+
+enable:
+	if (enable)
+		setup_force_cpu_cap(X86_FEATURE_KAISER);
+
+	return;
+
+disable:
+	pr_info("disabled\n");
+
+silent_disable:
+	kaiser_enabled = 0;
+	setup_clear_cpu_cap(X86_FEATURE_KAISER);
+}
+
+/*
+ * If anything in here fails, we will likely die on one of the
+ * first kernel->user transitions and init will die.  But, we
+ * will have most of the kernel up by then and should be able to
+ * get a clean warning out of it.  If we BUG_ON() here, we run
+ * the risk of being before we have good console output.
+ */
+void __init kaiser_init(void)
+{
+	int cpu;
+
+	if (!kaiser_enabled)
+		return;
+
+	kaiser_init_all_pgds();
+
+	for_each_possible_cpu(cpu) {
+		void *percpu_vaddr = __per_cpu_user_mapped_start +
+				     per_cpu_offset(cpu);
+		unsigned long percpu_sz = __per_cpu_user_mapped_end -
+					  __per_cpu_user_mapped_start;
+		kaiser_add_user_map_early(percpu_vaddr, percpu_sz,
+					  __PAGE_KERNEL);
+	}
+
+	/*
+	 * Map the entry/exit text section, which is needed at
+	 * switches from user to and from kernel.
+	 */
+	kaiser_add_user_map_ptrs_early(__entry_text_start, __entry_text_end,
+				       __PAGE_KERNEL_RX);
+
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
+	kaiser_add_user_map_ptrs_early(__irqentry_text_start,
+				       __irqentry_text_end,
+				       __PAGE_KERNEL_RX);
+#endif
+	kaiser_add_user_map_early((void *)idt_descr.address,
+				  sizeof(gate_desc) * NR_VECTORS,
+				  __PAGE_KERNEL_RO);
+#ifdef CONFIG_TRACING
+	kaiser_add_user_map_early(&trace_idt_descr,
+				  sizeof(trace_idt_descr),
+				  __PAGE_KERNEL);
+	kaiser_add_user_map_early(&trace_idt_table,
+				  sizeof(gate_desc) * NR_VECTORS,
+				  __PAGE_KERNEL);
+#endif
+	kaiser_add_user_map_early(&debug_idt_descr, sizeof(debug_idt_descr),
+				  __PAGE_KERNEL);
+	kaiser_add_user_map_early(&debug_idt_table,
+				  sizeof(gate_desc) * NR_VECTORS,
+				  __PAGE_KERNEL);
+
+	pr_info("enabled\n");
+}
+
+/* Add a mapping to the shadow mapping, and synchronize the mappings */
+int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
+{
+	if (!kaiser_enabled)
+		return 0;
+	return kaiser_add_user_map((const void *)addr, size, flags);
+}
+
+void kaiser_remove_mapping(unsigned long start, unsigned long size)
+{
+	extern void unmap_pud_range_nofree(pgd_t *pgd,
+				unsigned long start, unsigned long end);
+	unsigned long end = start + size;
+	unsigned long addr, next;
+	pgd_t *pgd;
+
+	if (!kaiser_enabled)
+		return;
+	pgd = native_get_shadow_pgd(pgd_offset_k(start));
+	for (addr = start; addr < end; pgd++, addr = next) {
+		next = pgd_addr_end(addr, end);
+		unmap_pud_range_nofree(pgd, addr, next);
+	}
+}
+
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ * This returns true for user pages that need to get copied into
+ * both the user and kernel copies of the page tables, and false
+ * for kernel pages that should only be in the kernel copy.
+ */
+static inline bool is_userspace_pgd(pgd_t *pgdp)
+{
+	return ((unsigned long)pgdp % PAGE_SIZE) < (PAGE_SIZE / 2);
+}
+
+pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	if (!kaiser_enabled)
+		return pgd;
+	/*
+	 * Do we need to also populate the shadow pgd?  Check _PAGE_USER to
+	 * skip cases like kexec and EFI which make temporary low mappings.
+	 */
+	if (pgd.pgd & _PAGE_USER) {
+		if (is_userspace_pgd(pgdp)) {
+			native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
+			/*
+			 * Even if the entry is *mapping* userspace, ensure
+			 * that userspace can not use it.  This way, if we
+			 * get out to userspace running on the kernel CR3,
+			 * userspace will crash instead of running.
+			 */
+			if (__supported_pte_mask & _PAGE_NX)
+				pgd.pgd |= _PAGE_NX;
+		}
+	} else if (!pgd.pgd) {
+		/*
+		 * pgd_clear() cannot check _PAGE_USER, and is even used to
+		 * clear corrupted pgd entries: so just rely on cases like
+		 * kexec and EFI never to be using pgd_clear().
+		 */
+		if (!WARN_ON_ONCE((unsigned long)pgdp & PAGE_SIZE) &&
+		    is_userspace_pgd(pgdp))
+			native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
+	}
+	return pgd;
+}
+
+void kaiser_setup_pcid(void)
+{
+	unsigned long user_cr3 = KAISER_SHADOW_PGD_OFFSET;
+
+	if (this_cpu_has(X86_FEATURE_PCID))
+		user_cr3 |= X86_CR3_PCID_USER_NOFLUSH;
+	/*
+	 * These variables are used by the entry/exit
+	 * code to change PCID and pgd and TLB flushing.
+	 */
+	this_cpu_write(x86_cr3_pcid_user, user_cr3);
+}
+
+/*
+ * Make a note that this cpu will need to flush USER tlb on return to user.
+ * If cpu does not have PCID, then the NOFLUSH bit will never have been set.
+ */
+void kaiser_flush_tlb_on_return_to_user(void)
+{
+	if (this_cpu_has(X86_FEATURE_PCID))
+		this_cpu_write(x86_cr3_pcid_user,
+			X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
+}
+EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 4e5ac46adc9d..81ec7c02f968 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -121,11 +121,16 @@ void __init kasan_init(void)
 	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
 			(void *)KASAN_SHADOW_END);
 
-	memset(kasan_zero_page, 0, PAGE_SIZE);
-
 	load_cr3(init_level4_pgt);
 	__flush_tlb_all();
-	init_task.kasan_depth = 0;
 
+	/*
+	 * kasan_zero_page has been used as early shadow memory, thus it may
+	 * contain some garbage. Now we can clear it, since after the TLB flush
+	 * no one should write to it.
+	 */
+	memset(kasan_zero_page, 0, PAGE_SIZE);
+
+	init_task.kasan_depth = 0;
 	pr_info("KernelAddressSanitizer initialized\n");
 }
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 1924bba0f3af..ac9c7797b632 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -52,6 +52,7 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_FLUSHTLB 1
 #define CPA_ARRAY 2
 #define CPA_PAGES_ARRAY 4
+#define CPA_FREE_PAGETABLES 8
 
 #ifdef CONFIG_PROC_FS
 static unsigned long direct_pages_count[PG_LEVEL_NUM];
@@ -723,10 +724,13 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
 	return 0;
 }
 
-static bool try_to_free_pte_page(pte_t *pte)
+static bool try_to_free_pte_page(struct cpa_data *cpa, pte_t *pte)
 {
 	int i;
 
+	if (!(cpa->flags & CPA_FREE_PAGETABLES))
+		return false;
+
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		if (!pte_none(pte[i]))
 			return false;
@@ -735,10 +739,13 @@ static bool try_to_free_pte_page(pte_t *pte)
 	return true;
 }
 
-static bool try_to_free_pmd_page(pmd_t *pmd)
+static bool try_to_free_pmd_page(struct cpa_data *cpa, pmd_t *pmd)
 {
 	int i;
 
+	if (!(cpa->flags & CPA_FREE_PAGETABLES))
+		return false;
+
 	for (i = 0; i < PTRS_PER_PMD; i++)
 		if (!pmd_none(pmd[i]))
 			return false;
@@ -759,7 +766,9 @@ static bool try_to_free_pud_page(pud_t *pud)
 	return true;
 }
 
-static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
+static bool unmap_pte_range(struct cpa_data *cpa, pmd_t *pmd,
+			    unsigned long start,
+			    unsigned long end)
 {
 	pte_t *pte = pte_offset_kernel(pmd, start);
 
@@ -770,22 +779,23 @@ static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
 		pte++;
 	}
 
-	if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) {
+	if (try_to_free_pte_page(cpa, (pte_t *)pmd_page_vaddr(*pmd))) {
 		pmd_clear(pmd);
 		return true;
 	}
 	return false;
 }
 
-static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
+static void __unmap_pmd_range(struct cpa_data *cpa, pud_t *pud, pmd_t *pmd,
 			      unsigned long start, unsigned long end)
 {
-	if (unmap_pte_range(pmd, start, end))
-		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+	if (unmap_pte_range(cpa, pmd, start, end))
+		if (try_to_free_pmd_page(cpa, (pmd_t *)pud_page_vaddr(*pud)))
 			pud_clear(pud);
 }
 
-static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
+static void unmap_pmd_range(struct cpa_data *cpa, pud_t *pud,
+			    unsigned long start, unsigned long end)
 {
 	pmd_t *pmd = pmd_offset(pud, start);
 
@@ -796,7 +806,7 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
 		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
 		unsigned long pre_end = min_t(unsigned long, end, next_page);
 
-		__unmap_pmd_range(pud, pmd, start, pre_end);
+		__unmap_pmd_range(cpa, pud, pmd, start, pre_end);
 
 		start = pre_end;
 		pmd++;
@@ -809,7 +819,8 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
 		if (pmd_large(*pmd))
 			pmd_clear(pmd);
 		else
-			__unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);
+			__unmap_pmd_range(cpa, pud, pmd,
+					  start, start + PMD_SIZE);
 
 		start += PMD_SIZE;
 		pmd++;
@@ -819,17 +830,19 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
 	 * 4K leftovers?
 	 */
 	if (start < end)
-		return __unmap_pmd_range(pud, pmd, start, end);
+		return __unmap_pmd_range(cpa, pud, pmd, start, end);
 
 	/*
 	 * Try again to free the PMD page if haven't succeeded above.
 	 */
 	if (!pud_none(*pud))
-		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+		if (try_to_free_pmd_page(cpa, (pmd_t *)pud_page_vaddr(*pud)))
 			pud_clear(pud);
 }
 
-static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+static void __unmap_pud_range(struct cpa_data *cpa, pgd_t *pgd,
+			      unsigned long start,
+			      unsigned long end)
 {
 	pud_t *pud = pud_offset(pgd, start);
 
@@ -840,7 +853,7 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
 		unsigned long pre_end	= min_t(unsigned long, end, next_page);
 
-		unmap_pmd_range(pud, start, pre_end);
+		unmap_pmd_range(cpa, pud, start, pre_end);
 
 		start = pre_end;
 		pud++;
@@ -854,7 +867,7 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 		if (pud_large(*pud))
 			pud_clear(pud);
 		else
-			unmap_pmd_range(pud, start, start + PUD_SIZE);
+			unmap_pmd_range(cpa, pud, start, start + PUD_SIZE);
 
 		start += PUD_SIZE;
 		pud++;
@@ -864,7 +877,7 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 	 * 2M leftovers?
 	 */
 	if (start < end)
-		unmap_pmd_range(pud, start, end);
+		unmap_pmd_range(cpa, pud, start, end);
 
 	/*
 	 * No need to try to free the PUD page because we'll free it in
@@ -872,6 +885,24 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 	 */
 }
 
+static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+{
+	struct cpa_data cpa = {
+		.flags = CPA_FREE_PAGETABLES,
+	};
+
+	__unmap_pud_range(&cpa, pgd, start, end);
+}
+
+void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end)
+{
+	struct cpa_data cpa = {
+		.flags = 0,
+	};
+
+	__unmap_pud_range(&cpa, pgd, start, end);
+}
+
 static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
 {
 	pgd_t *pgd_entry = root + pgd_index(addr);
@@ -911,10 +942,15 @@ static void populate_pte(struct cpa_data *cpa,
 	pte = pte_offset_kernel(pmd, start);
 
 	while (num_pages-- && start < end) {
-		set_pte(pte, pfn_pte(cpa->pfn, pgprot));
+
+		/* deal with the NX bit */
+		if (!(pgprot_val(pgprot) & _PAGE_NX))
+			cpa->pfn &= ~_PAGE_NX;
+
+		set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot));
 
 		start	 += PAGE_SIZE;
-		cpa->pfn++;
+		cpa->pfn += PAGE_SIZE;
 		pte++;
 	}
 }
@@ -970,11 +1006,11 @@ static int populate_pmd(struct cpa_data *cpa,
 
 		pmd = pmd_offset(pud, start);
 
-		set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
+		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE |
 				   massage_pgprot(pmd_pgprot)));
 
 		start	  += PMD_SIZE;
-		cpa->pfn  += PMD_SIZE >> PAGE_SHIFT;
+		cpa->pfn  += PMD_SIZE;
 		cur_pages += PMD_SIZE >> PAGE_SHIFT;
 	}
 
@@ -1043,11 +1079,11 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 	 * Map everything starting from the Gb boundary, possibly with 1G pages
 	 */
 	while (end - start >= PUD_SIZE) {
-		set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
+		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE |
 				   massage_pgprot(pud_pgprot)));
 
 		start	  += PUD_SIZE;
-		cpa->pfn  += PUD_SIZE >> PAGE_SHIFT;
+		cpa->pfn  += PUD_SIZE;
 		cur_pages += PUD_SIZE >> PAGE_SHIFT;
 		pud++;
 	}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index fb0a9dd1d6e4..dbc27a2b4ad5 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,7 +6,7 @@
 #include <asm/fixmap.h>
 #include <asm/mtrr.h>
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
 
 #ifdef CONFIG_HIGHPTE
 #define PGALLOC_USER_GFP __GFP_HIGHMEM
@@ -340,14 +340,24 @@ static inline void _pgd_free(pgd_t *pgd)
 		kmem_cache_free(pgd_cache, pgd);
 }
 #else
+
+/*
+ * Instead of one pgd, Kaiser acquires two pgds.  Being order-1, it is
+ * both 8k in size and 8k-aligned.  That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER	kaiser_enabled
+
 static inline pgd_t *_pgd_alloc(void)
 {
-	return (pgd_t *)__get_free_page(PGALLOC_GFP);
+	/* No __GFP_REPEAT: to avoid page allocation stalls in order-1 case */
+	return (pgd_t *)__get_free_pages(PGALLOC_GFP & ~__GFP_REPEAT,
+					 PGD_ALLOCATION_ORDER);
 }
 
 static inline void _pgd_free(pgd_t *pgd)
 {
-	free_page((unsigned long)pgd);
+	free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
 }
 #endif /* CONFIG_X86_PAE */
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5a760fd66bec..7cad01af6dcd 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -6,16 +6,17 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/cpu.h>
+#include <linux/debugfs.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/cache.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
-#include <linux/debugfs.h>
+#include <asm/kaiser.h>
 
 /*
- *	Smarter SMP flushing macros.
+ *	TLB flushing, formerly SMP-only
  *		c/o Linus Torvalds.
  *
  *	These mean you can really definitely utterly forget about
@@ -34,6 +35,36 @@ struct flush_tlb_info {
 	unsigned long flush_end;
 };
 
+static void load_new_mm_cr3(pgd_t *pgdir)
+{
+	unsigned long new_mm_cr3 = __pa(pgdir);
+
+	if (kaiser_enabled) {
+		/*
+		 * We reuse the same PCID for different tasks, so we must
+		 * flush all the entries for the PCID out when we change tasks.
+		 * Flush KERN below, flush USER when returning to userspace in
+		 * kaiser's SWITCH_USER_CR3 (_SWITCH_TO_USER_CR3) macro.
+		 *
+		 * invpcid_flush_single_context(X86_CR3_PCID_ASID_USER) could
+		 * do it here, but can only be used if X86_FEATURE_INVPCID is
+		 * available - and many machines support pcid without invpcid.
+		 *
+		 * If X86_CR3_PCID_KERN_FLUSH actually added something, then it
+		 * would be needed in the write_cr3() below - if PCIDs enabled.
+		 */
+		BUILD_BUG_ON(X86_CR3_PCID_KERN_FLUSH);
+		kaiser_flush_tlb_on_return_to_user();
+	}
+
+	/*
+	 * Caution: many callers of this function expect
+	 * that load_cr3() is serializing and orders TLB
+	 * fills with respect to the mm_cpumask writes.
+	 */
+	write_cr3(new_mm_cr3);
+}
+
 /*
  * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
@@ -45,7 +76,7 @@ void leave_mm(int cpu)
 		BUG();
 	if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
 		cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
-		load_cr3(swapper_pg_dir);
+		load_new_mm_cr3(swapper_pg_dir);
 		/*
 		 * This gets called in the idle path where RCU
 		 * functions differently.  Tracing normally
@@ -57,6 +88,109 @@ void leave_mm(int cpu)
 }
 EXPORT_SYMBOL_GPL(leave_mm);
 
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	       struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	switch_mm_irqs_off(prev, next, tsk);
+	local_irq_restore(flags);
+}
+
+void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			struct task_struct *tsk)
+{
+	unsigned cpu = smp_processor_id();
+
+	if (likely(prev != next)) {
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		this_cpu_write(cpu_tlbstate.active_mm, next);
+		cpumask_set_cpu(cpu, mm_cpumask(next));
+
+		/*
+		 * Re-load page tables.
+		 *
+		 * This logic has an ordering constraint:
+		 *
+		 *  CPU 0: Write to a PTE for 'next'
+		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
+		 *  CPU 1: set bit 1 in next's mm_cpumask
+		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
+		 *
+		 * We need to prevent an outcome in which CPU 1 observes
+		 * the new PTE value and CPU 0 observes bit 1 clear in
+		 * mm_cpumask.  (If that occurs, then the IPI will never
+		 * be sent, and CPU 0's TLB will contain a stale entry.)
+		 *
+		 * The bad outcome can occur if either CPU's load is
+		 * reordered before that CPU's store, so both CPUs must
+		 * execute full barriers to prevent this from happening.
+		 *
+		 * Thus, switch_mm needs a full barrier between the
+		 * store to mm_cpumask and any operation that could load
+		 * from next->pgd.  TLB fills are special and can happen
+		 * due to instruction fetches or for no reason at all,
+		 * and neither LOCK nor MFENCE orders them.
+		 * Fortunately, load_cr3() is serializing and gives the
+		 * ordering guarantee we need.
+		 *
+		 */
+		load_new_mm_cr3(next->pgd);
+
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+
+		/* Stop flush ipis for the previous mm */
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+
+		/* Load per-mm CR4 state */
+		load_mm_cr4(next);
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+		/*
+		 * Load the LDT, if the LDT is different.
+		 *
+		 * It's possible that prev->context.ldt doesn't match
+		 * the LDT register.  This can happen if leave_mm(prev)
+		 * was called and then modify_ldt changed
+		 * prev->context.ldt but suppressed an IPI to this CPU.
+		 * In this case, prev->context.ldt != NULL, because we
+		 * never set context.ldt to NULL while the mm still
+		 * exists.  That means that next->context.ldt !=
+		 * prev->context.ldt, because mms never share an LDT.
+		 */
+		if (unlikely(prev->context.ldt != next->context.ldt))
+			load_mm_ldt(next);
+#endif
+	} else {
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
+
+		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+			/*
+			 * On established mms, the mm_cpumask is only changed
+			 * from irq context, from ptep_clear_flush() while in
+			 * lazy tlb mode, and here. Irqs are blocked during
+			 * schedule, protecting us from simultaneous changes.
+			 */
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+
+			/*
+			 * We were in lazy tlb mode and leave_mm disabled
+			 * tlb flush IPI delivery. We must reload CR3
+			 * to make sure to use no freed page tables.
+			 *
+			 * As above, load_cr3() is serializing and orders TLB
+			 * fills with respect to the mm_cpumask write.
+			 */
+			load_new_mm_cr3(next->pgd);
+			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+			load_mm_cr4(next);
+			load_mm_ldt(next);
+		}
+	}
+}
+
 /*
  * The flush IPI assumes that a thread switch happens in this order:
  * [cpu0: the cpu that switches]
@@ -104,7 +238,7 @@ static void flush_tlb_func(void *info)
 
 	inc_irq_stat(irq_tlb_count);
 
-	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
+	if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -158,23 +292,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	smp_call_function_many(cpumask, flush_tlb_func, &info, 1);
 }
 
-void flush_tlb_current_task(void)
-{
-	struct mm_struct *mm = current->mm;
-
-	preempt_disable();
-
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-
-	/* This is an implicit full barrier that synchronizes with switch_mm. */
-	local_flush_tlb();
-
-	trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
-	preempt_enable();
-}
-
 /*
  * See Documentation/x86/tlb.txt for details.  We choose 33
  * because it is large enough to cover the vast majority (at
@@ -195,6 +312,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	unsigned long base_pages_to_flush = TLB_FLUSH_ALL;
 
 	preempt_disable();
+
+	if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
+		base_pages_to_flush = (end - start) >> PAGE_SHIFT;
+	if (base_pages_to_flush > tlb_single_page_flush_ceiling)
+		base_pages_to_flush = TLB_FLUSH_ALL;
+
 	if (current->active_mm != mm) {
 		/* Synchronize with switch_mm. */
 		smp_mb();
@@ -211,15 +334,11 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		goto out;
 	}
 
-	if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
-		base_pages_to_flush = (end - start) >> PAGE_SHIFT;
-
 	/*
 	 * Both branches below are implicit full barriers (MOV to CR or
 	 * INVLPG) that synchronize with switch_mm.
 	 */
-	if (base_pages_to_flush > tlb_single_page_flush_ceiling) {
-		base_pages_to_flush = TLB_FLUSH_ALL;
+	if (base_pages_to_flush == TLB_FLUSH_ALL) {
 		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
@@ -240,33 +359,6 @@ out:
 	preempt_enable();
 }
 
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
-{
-	struct mm_struct *mm = vma->vm_mm;
-
-	preempt_disable();
-
-	if (current->active_mm == mm) {
-		if (current->mm) {
-			/*
-			 * Implicit full barrier (INVLPG) that synchronizes
-			 * with switch_mm.
-			 */
-			__flush_tlb_one(start);
-		} else {
-			leave_mm(smp_processor_id());
-
-			/* Synchronize with switch_mm. */
-			smp_mb();
-		}
-	}
-
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
-
-	preempt_enable();
-}
-
 static void do_flush_tlb_all(void *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
index bb461cfd01ab..526536c81ddc 100644
--- a/arch/x86/pci/broadcom_bus.c
+++ b/arch/x86/pci/broadcom_bus.c
@@ -97,7 +97,7 @@ static int __init broadcom_postcore_init(void)
 	 * We should get host bridge information from ACPI unless the BIOS
 	 * doesn't support it.
 	 */
-	if (acpi_os_get_root_pointer())
+	if (!acpi_disabled && acpi_os_get_root_pointer())
 		return 0;
 #endif
 
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 3c1f3cd7b2ba..ad285404ea7f 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -869,7 +869,7 @@ static void __init kexec_enter_virtual_mode(void)
  * This function will switch the EFI runtime services to virtual mode.
  * Essentially, we look through the EFI memmap and map every region that
  * has the runtime attribute bit set in its memory descriptor into the
- * efi_pgd page table.
+ * ->trampoline_pgd page table using a top-down VA allocation scheme.
  *
  * The old method which used to update that memory descriptor with the
  * virtual address obtained from ioremap() is still supported when the
@@ -879,8 +879,8 @@ static void __init kexec_enter_virtual_mode(void)
  *
  * The new method does a pagetable switch in a preemption-safe manner
  * so that we're in a different address space when calling a runtime
- * function. For function arguments passing we do copy the PUDs of the
- * kernel page table into efi_pgd prior to each call.
+ * function. For function arguments passing we do copy the PGDs of the
+ * kernel page table into ->trampoline_pgd prior to each call.
  *
  * Specially for kexec boot, efi runtime maps in previous kernel should
  * be passed in via setup_data. In that case runtime ranges will be mapped
@@ -895,12 +895,6 @@ static void __init __efi_enter_virtual_mode(void)
 
 	efi.systab = NULL;
 
-	if (efi_alloc_page_tables()) {
-		pr_err("Failed to allocate EFI page tables\n");
-		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
-		return;
-	}
-
 	efi_merge_regions();
 	new_memmap = efi_map_regions(&count, &pg_shift);
 	if (!new_memmap) {
@@ -960,11 +954,28 @@ static void __init __efi_enter_virtual_mode(void)
 	efi_runtime_mkexec();
 
 	/*
-	 * We mapped the descriptor array into the EFI pagetable above
-	 * but we're not unmapping it here because if we're running in
-	 * EFI mixed mode we need all of memory to be accessible when
-	 * we pass parameters to the EFI runtime services in the
-	 * thunking code.
+	 * We mapped the descriptor array into the EFI pagetable above but we're
+	 * not unmapping it here. Here's why:
+	 *
+	 * We're copying select PGDs from the kernel page table to the EFI page
+	 * table and when we do so and make changes to those PGDs like unmapping
+	 * stuff from them, those changes appear in the kernel page table and we
+	 * go boom.
+	 *
+	 * From setup_real_mode():
+	 *
+	 * ...
+	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
+	 *
+	 * In this particular case, our allocation is in PGD 0 of the EFI page
+	 * table but we've copied that PGD from PGD[272] of the EFI page table:
+	 *
+	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
+	 *
+	 * where the direct memory mapping in kernel space is.
+	 *
+	 * new_memmap's VA comes from that direct mapping and thus clearing it,
+	 * it would get cleared in the kernel page table too.
 	 *
 	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
 	 */
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 58d669bc8250..ed5b67338294 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -38,11 +38,6 @@
  * say 0 - 3G.
  */
 
-int __init efi_alloc_page_tables(void)
-{
-	return 0;
-}
-
 void efi_sync_low_kernel_mappings(void) {}
 void __init efi_dump_pagetable(void) {}
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 18dfaad71c99..a0ac0f9c307f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -40,7 +40,6 @@
 #include <asm/fixmap.h>
 #include <asm/realmode.h>
 #include <asm/time.h>
-#include <asm/pgalloc.h>
 
 /*
  * We allocate runtime services regions bottom-up, starting from -4G, i.e.
@@ -48,7 +47,16 @@
  */
 static u64 efi_va = EFI_VA_START;
 
-struct efi_scratch efi_scratch;
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+	u64 r15;
+	u64 prev_cr3;
+	pgd_t *efi_pgt;
+	bool use_pgd;
+	u64 phys_stack;
+} __packed;
 
 static void __init early_code_mapping_set_exec(int executable)
 {
@@ -75,11 +83,8 @@ pgd_t * __init efi_call_phys_prolog(void)
 	int pgd;
 	int n_pgds;
 
-	if (!efi_enabled(EFI_OLD_MEMMAP)) {
-		save_pgd = (pgd_t *)read_cr3();
-		write_cr3((unsigned long)efi_scratch.efi_pgt);
-		goto out;
-	}
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return NULL;
 
 	early_code_mapping_set_exec(1);
 
@@ -91,7 +96,6 @@ pgd_t * __init efi_call_phys_prolog(void)
 		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
 		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
 	}
-out:
 	__flush_tlb_all();
 
 	return save_pgd;
@@ -105,11 +109,8 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	int pgd_idx;
 	int nr_pgds;
 
-	if (!efi_enabled(EFI_OLD_MEMMAP)) {
-		write_cr3((unsigned long)save_pgd);
-		__flush_tlb_all();
+	if (!save_pgd)
 		return;
-	}
 
 	nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
 
@@ -122,97 +123,27 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	early_code_mapping_set_exec(0);
 }
 
-static pgd_t *efi_pgd;
-
-/*
- * We need our own copy of the higher levels of the page tables
- * because we want to avoid inserting EFI region mappings (EFI_VA_END
- * to EFI_VA_START) into the standard kernel page tables. Everything
- * else can be shared, see efi_sync_low_kernel_mappings().
- */
-int __init efi_alloc_page_tables(void)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	gfp_t gfp_mask;
-
-	if (efi_enabled(EFI_OLD_MEMMAP))
-		return 0;
-
-	gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO;
-	efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
-	if (!efi_pgd)
-		return -ENOMEM;
-
-	pgd = efi_pgd + pgd_index(EFI_VA_END);
-
-	pud = pud_alloc_one(NULL, 0);
-	if (!pud) {
-		free_page((unsigned long)efi_pgd);
-		return -ENOMEM;
-	}
-
-	pgd_populate(NULL, pgd, pud);
-
-	return 0;
-}
-
 /*
  * Add low kernel mappings for passing arguments to EFI functions.
  */
 void efi_sync_low_kernel_mappings(void)
 {
-	unsigned num_entries;
-	pgd_t *pgd_k, *pgd_efi;
-	pud_t *pud_k, *pud_efi;
+	unsigned num_pgds;
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return;
 
-	/*
-	 * We can share all PGD entries apart from the one entry that
-	 * covers the EFI runtime mapping space.
-	 *
-	 * Make sure the EFI runtime region mappings are guaranteed to
-	 * only span a single PGD entry and that the entry also maps
-	 * other important kernel regions.
-	 */
-	BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END));
-	BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) !=
-			(EFI_VA_END & PGDIR_MASK));
-
-	pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET);
-	pgd_k = pgd_offset_k(PAGE_OFFSET);
+	num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET);
 
-	num_entries = pgd_index(EFI_VA_END) - pgd_index(PAGE_OFFSET);
-	memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries);
-
-	/*
-	 * We share all the PUD entries apart from those that map the
-	 * EFI regions. Copy around them.
-	 */
-	BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0);
-	BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0);
-
-	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
-	pud_efi = pud_offset(pgd_efi, 0);
-
-	pgd_k = pgd_offset_k(EFI_VA_END);
-	pud_k = pud_offset(pgd_k, 0);
-
-	num_entries = pud_index(EFI_VA_END);
-	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
-
-	pud_efi = pud_offset(pgd_efi, EFI_VA_START);
-	pud_k = pud_offset(pgd_k, EFI_VA_START);
-
-	num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START);
-	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
+	memcpy(pgd + pgd_index(PAGE_OFFSET),
+		init_mm.pgd + pgd_index(PAGE_OFFSET),
+		sizeof(pgd_t) * num_pgds);
 }
 
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	unsigned long pfn, text;
+	unsigned long text;
 	struct page *page;
 	unsigned npages;
 	pgd_t *pgd;
@@ -220,8 +151,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return 0;
 
-	efi_scratch.efi_pgt = (pgd_t *)__pa(efi_pgd);
-	pgd = efi_pgd;
+	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+	pgd = __va(efi_scratch.efi_pgt);
 
 	/*
 	 * It can happen that the physical address of new_memmap lands in memory
@@ -229,8 +160,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	 * and ident-map those pages containing the map before calling
 	 * phys_efi_set_virtual_address_map().
 	 */
-	pfn = pa_memmap >> PAGE_SHIFT;
-	if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, _PAGE_NX)) {
+	if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
 		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
 		return 1;
 	}
@@ -255,9 +185,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 
 	npages = (_end - _text) >> PAGE_SHIFT;
 	text = __pa(_text);
-	pfn = text >> PAGE_SHIFT;
 
-	if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, 0)) {
+	if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) {
 		pr_err("Failed to map kernel text 1:1\n");
 		return 1;
 	}
@@ -267,20 +196,20 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 
 void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	kernel_unmap_pages_in_pgd(efi_pgd, pa_memmap, num_pages);
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
 }
 
 static void __init __map_region(efi_memory_desc_t *md, u64 va)
 {
-	unsigned long flags = 0;
-	unsigned long pfn;
-	pgd_t *pgd = efi_pgd;
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+	unsigned long pf = 0;
 
 	if (!(md->attribute & EFI_MEMORY_WB))
-		flags |= _PAGE_PCD;
+		pf |= _PAGE_PCD;
 
-	pfn = md->phys_addr >> PAGE_SHIFT;
-	if (kernel_map_pages_in_pgd(pgd, pfn, va, md->num_pages, flags))
+	if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
 		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
 			   md->phys_addr, va);
 }
@@ -383,7 +312,9 @@ void __init efi_runtime_mkexec(void)
 void __init efi_dump_pagetable(void)
 {
 #ifdef CONFIG_EFI_PGT_DUMP
-	ptdump_walk_pgd_level(NULL, efi_pgd);
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	ptdump_walk_pgd_level(NULL, pgd);
 #endif
 }
 
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 32020cb8bb08..86d0f9e08dd9 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -38,6 +38,41 @@
 	mov %rsi, %cr0;			\
 	mov (%rsp), %rsp
 
+	/* stolen from gcc */
+	.macro FLUSH_TLB_ALL
+	movq %r15, efi_scratch(%rip)
+	movq %r14, efi_scratch+8(%rip)
+	movq %cr4, %r15
+	movq %r15, %r14
+	andb $0x7f, %r14b
+	movq %r14, %cr4
+	movq %r15, %cr4
+	movq efi_scratch+8(%rip), %r14
+	movq efi_scratch(%rip), %r15
+	.endm
+
+	.macro SWITCH_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 1f
+	movq %r15, efi_scratch(%rip)		# r15
+	# save previous CR3
+	movq %cr3, %r15
+	movq %r15, efi_scratch+8(%rip)		# prev_cr3
+	movq efi_scratch+16(%rip), %r15		# EFI pgt
+	movq %r15, %cr3
+	1:
+	.endm
+
+	.macro RESTORE_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 2f
+	movq efi_scratch+8(%rip), %r15
+	movq %r15, %cr3
+	movq efi_scratch(%rip), %r15
+	FLUSH_TLB_ALL
+	2:
+	.endm
+
 ENTRY(efi_call)
 	SAVE_XMM
 	mov (%rsp), %rax
@@ -48,8 +83,16 @@ ENTRY(efi_call)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
 ENDPROC(efi_call)
+
+	.data
+ENTRY(efi_scratch)
+	.fill 3,8,0
+	.byte 0
+	.quad 0
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index 3e75fcf6b836..7d3952eafec9 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -8,6 +8,9 @@
 #
 KASAN_SANITIZE := n
 
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT		:= n
+
 always := realmode.bin realmode.relocs
 
 wakeup-objs	:= wakeup_asm.o wakemain.o video-mode.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ffa41591bff9..cbef64b508e1 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -433,6 +433,12 @@ static void __init xen_init_cpuid_mask(void)
 		~((1 << X86_FEATURE_MTRR) |  /* disable MTRR */
 		  (1 << X86_FEATURE_ACC));   /* thermal monitoring */
 
+	/*
+	 * Xen PV would need some work to support PCID: CR3 handling as well
+	 * as xen_flush_tlb_others() would need updating.
+	 */
+	cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_PCID % 32));  /* disable PCID */
+
 	if (!xen_initial_domain())
 		cpuid_leaf1_edx_mask &=
 			~((1 << X86_FEATURE_ACPI));  /* disable ACPI */