Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 1bbec38..840e125 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -27,7 +27,6 @@
 	depends on X86_LOCAL_APIC
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
-	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
 	select IRQ_BYPASS_MANAGER
@@ -42,6 +41,7 @@
 	select PERF_EVENTS
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select HAVE_KVM_NO_POLL
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_VFIO
 	select SRCU
@@ -98,6 +98,6 @@
 
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
-source drivers/vhost/Kconfig
+source "drivers/vhost/Kconfig"
 
 endif # VIRTUALIZATION
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index dc4f2fd..31ecf7a 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -2,10 +2,6 @@
 
 ccflags-y += -Iarch/x86/kvm
 
-CFLAGS_x86.o := -I.
-CFLAGS_svm.o := -I.
-CFLAGS_vmx.o := -I.
-
 KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
@@ -16,7 +12,7 @@
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
 			   hyperv.o page_track.o debugfs.o
 
-kvm-intel-y		+= vmx.o pmu_intel.o
+kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
 kvm-amd-y		+= svm.o pmu_amd.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 7bcfa61..f68c0c7 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Kernel-based Virtual Machine driver for Linux
  * cpuid support routines
@@ -6,10 +7,6 @@
  *
  * Copyright 2011 Red Hat, Inc. and/or its affiliates.
  * Copyright IBM Corporation, 2008
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #include <linux/kvm_host.h>
@@ -67,9 +64,6 @@
 
 #define F(x) bit(X86_FEATURE_##x)
 
-/* For scattered features from cpufeatures.h; we currently expose none */
-#define KF(x) bit(KVM_CPUID_BIT_##x)
-
 int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -140,6 +134,16 @@
 		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
 		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
 
+	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
+		best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+		if (best) {
+			if (vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT)
+				best->ecx |= F(MWAIT);
+			else
+				best->ecx &= ~F(MWAIT);
+		}
+	}
+
 	/* Update physical-address width */
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 	kvm_mmu_reset_context(vcpu);
@@ -282,19 +286,44 @@
 	*word &= boot_cpu_data.x86_capability[wordnum];
 }
 
-static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function,
 			   u32 index)
 {
 	entry->function = function;
 	entry->index = index;
+	entry->flags = 0;
+
 	cpuid_count(entry->function, entry->index,
 		    &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
-	entry->flags = 0;
+
+	switch (function) {
+	case 2:
+		entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
+		break;
+	case 4:
+	case 7:
+	case 0xb:
+	case 0xd:
+	case 0xf:
+	case 0x10:
+	case 0x12:
+	case 0x14:
+	case 0x17:
+	case 0x18:
+	case 0x1f:
+	case 0x8000001d:
+		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+		break;
+	}
 }
 
-static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
-				   u32 func, u32 index, int *nent, int maxnent)
+static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry,
+				    u32 func, int *nent, int maxnent)
 {
+	entry->function = func;
+	entry->index = 0;
+	entry->flags = 0;
+
 	switch (func) {
 	case 0:
 		entry->eax = 7;
@@ -306,21 +335,99 @@
 		break;
 	case 7:
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
-		if (index == 0)
-			entry->ecx = F(RDPID);
+		entry->eax = 0;
+		entry->ecx = F(RDPID);
 		++*nent;
 	default:
 		break;
 	}
 
-	entry->function = func;
-	entry->index = index;
-
 	return 0;
 }
 
-static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
-				 u32 index, int *nent, int maxnent)
+static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
+{
+	unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
+	unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
+	unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
+	unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
+	unsigned f_la57;
+
+	/* cpuid 7.0.ebx */
+	const u32 kvm_cpuid_7_0_ebx_x86_features =
+		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
+		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
+		F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
+		F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
+		F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | f_intel_pt;
+
+	/* cpuid 7.0.ecx*/
+	const u32 kvm_cpuid_7_0_ecx_x86_features =
+		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
+		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
+		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
+		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/;
+
+	/* cpuid 7.0.edx*/
+	const u32 kvm_cpuid_7_0_edx_x86_features =
+		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
+		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
+		F(MD_CLEAR);
+
+	/* cpuid 7.1.eax */
+	const u32 kvm_cpuid_7_1_eax_x86_features =
+		F(AVX512_BF16);
+
+	switch (index) {
+	case 0:
+		entry->eax = min(entry->eax, 1u);
+		entry->ebx &= kvm_cpuid_7_0_ebx_x86_features;
+		cpuid_mask(&entry->ebx, CPUID_7_0_EBX);
+		/* TSC_ADJUST is emulated */
+		entry->ebx |= F(TSC_ADJUST);
+
+		entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
+		f_la57 = entry->ecx & F(LA57);
+		cpuid_mask(&entry->ecx, CPUID_7_ECX);
+		/* Set LA57 based on hardware capability. */
+		entry->ecx |= f_la57;
+		entry->ecx |= f_umip;
+		/* PKU is not yet implemented for shadow paging. */
+		if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
+			entry->ecx &= ~F(PKU);
+
+		entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+		cpuid_mask(&entry->edx, CPUID_7_EDX);
+		if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS))
+			entry->edx |= F(SPEC_CTRL);
+		if (boot_cpu_has(X86_FEATURE_STIBP))
+			entry->edx |= F(INTEL_STIBP);
+		if (boot_cpu_has(X86_FEATURE_SSBD))
+			entry->edx |= F(SPEC_CTRL_SSBD);
+		/*
+		 * We emulate ARCH_CAPABILITIES in software even
+		 * if the host doesn't support it.
+		 */
+		entry->edx |= F(ARCH_CAPABILITIES);
+		break;
+	case 1:
+		entry->eax &= kvm_cpuid_7_1_eax_x86_features;
+		entry->ebx = 0;
+		entry->ecx = 0;
+		entry->edx = 0;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		entry->eax = 0;
+		entry->ebx = 0;
+		entry->ecx = 0;
+		entry->edx = 0;
+		break;
+	}
+}
+
+static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
+				  int *nent, int maxnent)
 {
 	int r;
 	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
@@ -333,10 +440,8 @@
 	unsigned f_lm = 0;
 #endif
 	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
-	unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
-	unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
 	unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
-	unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
+	unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
 
 	/* cpuid 1.edx */
 	const u32 kvm_cpuid_1_edx_x86_features =
@@ -380,8 +485,9 @@
 
 	/* cpuid 0x80000008.ebx */
 	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
-		F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
-		F(AMD_SSB_NO);
+		F(CLZERO) | F(XSAVEERPTR) |
+		F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
+		F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON);
 
 	/* cpuid 0xC0000001.edx */
 	const u32 kvm_cpuid_C000_0001_edx_x86_features =
@@ -389,30 +495,10 @@
 		F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) |
 		F(PMM) | F(PMM_EN);
 
-	/* cpuid 7.0.ebx */
-	const u32 kvm_cpuid_7_0_ebx_x86_features =
-		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
-		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
-		F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
-		F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
-		F(SHA_NI) | F(AVX512BW) | F(AVX512VL);
-
 	/* cpuid 0xD.1.eax */
 	const u32 kvm_cpuid_D_1_eax_x86_features =
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves;
 
-	/* cpuid 7.0.ecx*/
-	const u32 kvm_cpuid_7_0_ecx_x86_features =
-		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
-		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
-		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
-		F(CLDEMOTE);
-
-	/* cpuid 7.0.edx*/
-	const u32 kvm_cpuid_7_0_edx_x86_features =
-		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
-		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES);
-
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -421,12 +507,13 @@
 	if (*nent >= maxnent)
 		goto out;
 
-	do_cpuid_1_ent(entry, function, index);
+	do_host_cpuid(entry, function, 0);
 	++*nent;
 
 	switch (function) {
 	case 0:
-		entry->eax = min(entry->eax, (u32)0xd);
+		/* Limited to the highest leaf implemented in KVM. */
+		entry->eax = min(entry->eax, 0x1fU);
 		break;
 	case 1:
 		entry->edx &= kvm_cpuid_1_edx_x86_features;
@@ -444,23 +531,21 @@
 	case 2: {
 		int t, times = entry->eax & 0xff;
 
-		entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
 		entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
 		for (t = 1; t < times; ++t) {
 			if (*nent >= maxnent)
 				goto out;
 
-			do_cpuid_1_ent(&entry[t], function, 0);
-			entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
+			do_host_cpuid(&entry[t], function, 0);
 			++*nent;
 		}
 		break;
 	}
-	/* function 4 has additional index. */
-	case 4: {
+	/* functions 4 and 0x8000001d have additional index. */
+	case 4:
+	case 0x8000001d: {
 		int i, cache_type;
 
-		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		/* read more entries until cache_type is zero */
 		for (i = 1; ; ++i) {
 			if (*nent >= maxnent)
@@ -469,9 +554,7 @@
 			cache_type = entry[i - 1].eax & 0x1f;
 			if (!cache_type)
 				break;
-			do_cpuid_1_ent(&entry[i], function, i);
-			entry[i].flags |=
-			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+			do_host_cpuid(&entry[i], function, i);
 			++*nent;
 		}
 		break;
@@ -482,33 +565,21 @@
 		entry->ecx = 0;
 		entry->edx = 0;
 		break;
+	/* function 7 has additional index. */
 	case 7: {
-		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
-		/* Mask ebx against host capability word 9 */
-		if (index == 0) {
-			entry->ebx &= kvm_cpuid_7_0_ebx_x86_features;
-			cpuid_mask(&entry->ebx, CPUID_7_0_EBX);
-			// TSC_ADJUST is emulated
-			entry->ebx |= F(TSC_ADJUST);
-			entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
-			cpuid_mask(&entry->ecx, CPUID_7_ECX);
-			entry->ecx |= f_umip;
-			/* PKU is not yet implemented for shadow paging. */
-			if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
-				entry->ecx &= ~F(PKU);
-			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
-			cpuid_mask(&entry->edx, CPUID_7_EDX);
-			/*
-			 * We emulate ARCH_CAPABILITIES in software even
-			 * if the host doesn't support it.
-			 */
-			entry->edx |= F(ARCH_CAPABILITIES);
-		} else {
-			entry->ebx = 0;
-			entry->ecx = 0;
-			entry->edx = 0;
+		int i;
+
+		for (i = 0; ; ) {
+			do_cpuid_7_mask(&entry[i], i);
+			if (i == entry->eax)
+				break;
+			if (*nent >= maxnent)
+				goto out;
+
+			++i;
+			do_host_cpuid(&entry[i], function, i);
+			++*nent;
 		}
-		entry->eax = 0;
 		break;
 	}
 	case 9:
@@ -542,22 +613,27 @@
 		entry->edx = edx.full;
 		break;
 	}
-	/* function 0xb has additional index. */
+	/*
+	 * Per Intel's SDM, the 0x1f is a superset of 0xb,
+	 * thus they can be handled by common code.
+	 */
+	case 0x1f:
 	case 0xb: {
-		int i, level_type;
+		int i;
 
-		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
-		/* read more entries until level_type is zero */
-		for (i = 1; ; ++i) {
+		/*
+		 * We filled in entry[0] for CPUID(EAX=<function>,
+		 * ECX=00H) above.  If its level type (ECX[15:8]) is
+		 * zero, then the leaf is unimplemented, and we're
+		 * done.  Otherwise, continue to populate entries
+		 * until the level type (ECX[15:8]) of the previously
+		 * added entry is zero.
+		 */
+		for (i = 1; entry[i - 1].ecx & 0xff00; ++i) {
 			if (*nent >= maxnent)
 				goto out;
 
-			level_type = entry[i - 1].ecx & 0xff00;
-			if (!level_type)
-				break;
-			do_cpuid_1_ent(&entry[i], function, i);
-			entry[i].flags |=
-			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+			do_host_cpuid(&entry[i], function, i);
 			++*nent;
 		}
 		break;
@@ -570,7 +646,6 @@
 		entry->ebx = xstate_required_size(supported, false);
 		entry->ecx = entry->ebx;
 		entry->edx &= supported >> 32;
-		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		if (!supported)
 			break;
 
@@ -579,7 +654,7 @@
 			if (*nent >= maxnent)
 				goto out;
 
-			do_cpuid_1_ent(&entry[i], function, idx);
+			do_host_cpuid(&entry[i], function, idx);
 			if (idx == 1) {
 				entry[i].eax &= kvm_cpuid_D_1_eax_x86_features;
 				cpuid_mask(&entry[i].eax, CPUID_D_1_EAX);
@@ -596,13 +671,26 @@
 			}
 			entry[i].ecx = 0;
 			entry[i].edx = 0;
-			entry[i].flags |=
-			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 			++*nent;
 			++i;
 		}
 		break;
 	}
+	/* Intel PT */
+	case 0x14: {
+		int t, times = entry->eax;
+
+		if (!f_intel_pt)
+			break;
+
+		for (t = 1; t <= times; ++t) {
+			if (*nent >= maxnent)
+				goto out;
+			do_host_cpuid(&entry[t], function, t);
+			++*nent;
+		}
+		break;
+	}
 	case KVM_CPUID_SIGNATURE: {
 		static const char signature[12] = "KVMKVMKVM\0\0";
 		const u32 *sigptr = (const u32 *)signature;
@@ -622,7 +710,9 @@
 			     (1 << KVM_FEATURE_PV_UNHALT) |
 			     (1 << KVM_FEATURE_PV_TLB_FLUSH) |
 			     (1 << KVM_FEATURE_ASYNC_PF_VMEXIT) |
-			     (1 << KVM_FEATURE_PV_SEND_IPI);
+			     (1 << KVM_FEATURE_PV_SEND_IPI) |
+			     (1 << KVM_FEATURE_POLL_CONTROL) |
+			     (1 << KVM_FEATURE_PV_SCHED_YIELD);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
@@ -656,19 +746,24 @@
 			g_phys_as = phys_as;
 		entry->eax = g_phys_as | (virt_as << 8);
 		entry->edx = 0;
-		/*
-		 * IBRS, IBPB and VIRT_SSBD aren't necessarily present in
-		 * hardware cpuid
-		 */
-		if (boot_cpu_has(X86_FEATURE_AMD_IBPB))
-			entry->ebx |= F(AMD_IBPB);
-		if (boot_cpu_has(X86_FEATURE_AMD_IBRS))
-			entry->ebx |= F(AMD_IBRS);
-		if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
-			entry->ebx |= F(VIRT_SSBD);
 		entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
 		cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX);
 		/*
+		 * AMD has separate bits for each SPEC_CTRL bit.
+		 * arch/x86/kernel/cpu/bugs.c is kind enough to
+		 * record that in cpufeatures so use them.
+		 */
+		if (boot_cpu_has(X86_FEATURE_IBPB))
+			entry->ebx |= F(AMD_IBPB);
+		if (boot_cpu_has(X86_FEATURE_IBRS))
+			entry->ebx |= F(AMD_IBRS);
+		if (boot_cpu_has(X86_FEATURE_STIBP))
+			entry->ebx |= F(AMD_STIBP);
+		if (boot_cpu_has(X86_FEATURE_SSBD))
+			entry->ebx |= F(AMD_SSBD);
+		if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+			entry->ebx |= F(AMD_SSB_NO);
+		/*
 		 * The preference is to use SPEC CTRL MSR instead of the
 		 * VIRT_SPEC MSR.
 		 */
@@ -681,8 +776,7 @@
 		entry->ecx = entry->edx = 0;
 		break;
 	case 0x8000001a:
-		break;
-	case 0x8000001d:
+	case 0x8000001e:
 		break;
 	/*Add support for Centaur's CPUID instruction*/
 	case 0xC0000000:
@@ -713,21 +807,19 @@
 	return r;
 }
 
-static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
-			u32 idx, int *nent, int maxnent, unsigned int type)
+static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func,
+			 int *nent, int maxnent, unsigned int type)
 {
 	if (type == KVM_GET_EMULATED_CPUID)
-		return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);
+		return __do_cpuid_func_emulated(entry, func, nent, maxnent);
 
-	return __do_cpuid_ent(entry, func, idx, nent, maxnent);
+	return __do_cpuid_func(entry, func, nent, maxnent);
 }
 
 #undef F
 
 struct kvm_cpuid_param {
 	u32 func;
-	u32 idx;
-	bool has_leaf_count;
 	bool (*qualifier)(const struct kvm_cpuid_param *param);
 };
 
@@ -771,11 +863,10 @@
 	int limit, nent = 0, r = -E2BIG, i;
 	u32 func;
 	static const struct kvm_cpuid_param param[] = {
-		{ .func = 0, .has_leaf_count = true },
-		{ .func = 0x80000000, .has_leaf_count = true },
-		{ .func = 0xC0000000, .qualifier = is_centaur_cpu, .has_leaf_count = true },
+		{ .func = 0 },
+		{ .func = 0x80000000 },
+		{ .func = 0xC0000000, .qualifier = is_centaur_cpu },
 		{ .func = KVM_CPUID_SIGNATURE },
-		{ .func = KVM_CPUID_FEATURES },
 	};
 
 	if (cpuid->nent < 1)
@@ -799,19 +890,16 @@
 		if (ent->qualifier && !ent->qualifier(ent))
 			continue;
 
-		r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
-				&nent, cpuid->nent, type);
+		r = do_cpuid_func(&cpuid_entries[nent], ent->func,
+				  &nent, cpuid->nent, type);
 
 		if (r)
 			goto out_free;
 
-		if (!ent->has_leaf_count)
-			continue;
-
 		limit = cpuid_entries[nent - 1].eax;
 		for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
-			r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
-				     &nent, cpuid->nent, type);
+			r = do_cpuid_func(&cpuid_entries[nent], func,
+				          &nent, cpuid->nent, type);
 
 		if (r)
 			goto out_free;
@@ -886,53 +974,66 @@
 EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
 
 /*
- * If no match is found, check whether we exceed the vCPU's limit
- * and return the content of the highest valid _standard_ leaf instead.
- * This is to satisfy the CPUID specification.
+ * If the basic or extended CPUID leaf requested is higher than the
+ * maximum supported basic or extended leaf, respectively, then it is
+ * out of range.
  */
-static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
-                                                  u32 function, u32 index)
+static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function)
 {
-	struct kvm_cpuid_entry2 *maxlevel;
+	struct kvm_cpuid_entry2 *max;
 
-	maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
-	if (!maxlevel || maxlevel->eax >= function)
-		return NULL;
-	if (function & 0x80000000) {
-		maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
-		if (!maxlevel)
-			return NULL;
-	}
-	return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
+	max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
+	return max && function <= max->eax;
 }
 
 bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 	       u32 *ecx, u32 *edx, bool check_limit)
 {
 	u32 function = *eax, index = *ecx;
-	struct kvm_cpuid_entry2 *best;
-	bool entry_found = true;
+	struct kvm_cpuid_entry2 *entry;
+	struct kvm_cpuid_entry2 *max;
+	bool found;
 
-	best = kvm_find_cpuid_entry(vcpu, function, index);
-
-	if (!best) {
-		entry_found = false;
-		if (!check_limit)
-			goto out;
-
-		best = check_cpuid_limit(vcpu, function, index);
+	entry = kvm_find_cpuid_entry(vcpu, function, index);
+	found = entry;
+	/*
+	 * Intel CPUID semantics treats any query for an out-of-range
+	 * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were
+	 * requested. AMD CPUID semantics returns all zeroes for any
+	 * undefined leaf, whether or not the leaf is in range.
+	 */
+	if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) &&
+	    !cpuid_function_in_range(vcpu, function)) {
+		max = kvm_find_cpuid_entry(vcpu, 0, 0);
+		if (max) {
+			function = max->eax;
+			entry = kvm_find_cpuid_entry(vcpu, function, index);
+		}
 	}
-
-out:
-	if (best) {
-		*eax = best->eax;
-		*ebx = best->ebx;
-		*ecx = best->ecx;
-		*edx = best->edx;
-	} else
+	if (entry) {
+		*eax = entry->eax;
+		*ebx = entry->ebx;
+		*ecx = entry->ecx;
+		*edx = entry->edx;
+	} else {
 		*eax = *ebx = *ecx = *edx = 0;
-	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found);
-	return entry_found;
+		/*
+		 * When leaf 0BH or 1FH is defined, CL is pass-through
+		 * and EDX is always the x2APIC ID, even for undefined
+		 * subleaves. Index 1 will exist iff the leaf is
+		 * implemented, so we pass through CL iff leaf 1
+		 * exists. EDX can be copied from any existing index.
+		 */
+		if (function == 0xb || function == 0x1f) {
+			entry = kvm_find_cpuid_entry(vcpu, function, 1);
+			if (entry) {
+				*ecx = index & 0xff;
+				*edx = entry->edx;
+			}
+		}
+	}
+	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found);
+	return found;
 }
 EXPORT_SYMBOL_GPL(kvm_cpuid);
 
@@ -943,13 +1044,13 @@
 	if (cpuid_fault_enabled(vcpu) && !kvm_require_cpl(vcpu, 0))
 		return 1;
 
-	eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
+	eax = kvm_rax_read(vcpu);
+	ecx = kvm_rcx_read(vcpu);
 	kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, true);
-	kvm_register_write(vcpu, VCPU_REGS_RAX, eax);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, ebx);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, ecx);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, edx);
+	kvm_rax_write(vcpu, eax);
+	kvm_rbx_write(vcpu, ebx);
+	kvm_rcx_write(vcpu, ecx);
+	kvm_rdx_write(vcpu, edx);
 	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 9a327d5..d78a614 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -47,8 +47,6 @@
 	[CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
 	[CPUID_7_0_EBX]       = {         7, 0, CPUID_EBX},
 	[CPUID_D_1_EAX]       = {       0xd, 1, CPUID_EAX},
-	[CPUID_F_0_EDX]       = {       0xf, 0, CPUID_EDX},
-	[CPUID_F_1_EDX]       = {       0xf, 1, CPUID_EDX},
 	[CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX},
 	[CPUID_6_EAX]         = {         6, 0, CPUID_EAX},
 	[CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX},
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index c19c7ed..018aebc 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -1,20 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Kernel-based Virtual Machine driver for Linux
  *
  * Copyright 2016 Red Hat, Inc. and/or its affiliates.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 #include <linux/kvm_host.h>
 #include <linux/debugfs.h>
+#include "lapic.h"
 
-bool kvm_arch_has_vcpu_debugfs(void)
+static int vcpu_get_timer_advance_ns(void *data, u64 *val)
 {
-	return true;
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
+	*val = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+	return 0;
 }
 
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_timer_advance_ns_fops, vcpu_get_timer_advance_ns, NULL, "%llu\n");
+
 static int vcpu_get_tsc_offset(void *data, u64 *val)
 {
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
@@ -41,29 +43,22 @@
 
 DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_frac_fops, vcpu_get_tsc_scaling_frac_bits, NULL, "%llu\n");
 
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 {
-	struct dentry *ret;
+	debugfs_create_file("tsc-offset", 0444, vcpu->debugfs_dentry, vcpu,
+			    &vcpu_tsc_offset_fops);
 
-	ret = debugfs_create_file("tsc-offset", 0444,
-							vcpu->debugfs_dentry,
-							vcpu, &vcpu_tsc_offset_fops);
-	if (!ret)
-		return -ENOMEM;
+	if (lapic_in_kernel(vcpu))
+		debugfs_create_file("lapic_timer_advance_ns", 0444,
+				    vcpu->debugfs_dentry, vcpu,
+				    &vcpu_timer_advance_ns_fops);
 
 	if (kvm_has_tsc_control) {
-		ret = debugfs_create_file("tsc-scaling-ratio", 0444,
-							vcpu->debugfs_dentry,
-							vcpu, &vcpu_tsc_scaling_fops);
-		if (!ret)
-			return -ENOMEM;
-		ret = debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444,
-							vcpu->debugfs_dentry,
-							vcpu, &vcpu_tsc_scaling_frac_fops);
-		if (!ret)
-			return -ENOMEM;
-
+		debugfs_create_file("tsc-scaling-ratio", 0444,
+				    vcpu->debugfs_dentry, vcpu,
+				    &vcpu_tsc_scaling_fops);
+		debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444,
+				    vcpu->debugfs_dentry, vcpu,
+				    &vcpu_tsc_scaling_frac_fops);
 	}
-
-	return 0;
 }
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 106482d..698efb8 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /******************************************************************************
  * emulate.c
  *
@@ -14,9 +15,6 @@
  *   Avi Kivity <avi@qumranet.com>
  *   Yaniv Kamay <yaniv@qumranet.com>
  *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4
  */
 
@@ -314,29 +312,42 @@
 
 static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 
-#define FOP_FUNC(name) \
+#define __FOP_FUNC(name) \
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
 	".type " name ", @function \n\t" \
 	name ":\n\t"
 
-#define FOP_RET   "ret \n\t"
+#define FOP_FUNC(name) \
+	__FOP_FUNC(#name)
+
+#define __FOP_RET(name) \
+	"ret \n\t" \
+	".size " name ", .-" name "\n\t"
+
+#define FOP_RET(name) \
+	__FOP_RET(#name)
 
 #define FOP_START(op) \
 	extern void em_##op(struct fastop *fake); \
 	asm(".pushsection .text, \"ax\" \n\t" \
 	    ".global em_" #op " \n\t" \
-	    FOP_FUNC("em_" #op)
+	    ".align " __stringify(FASTOP_SIZE) " \n\t" \
+	    "em_" #op ":\n\t"
 
 #define FOP_END \
 	    ".popsection")
 
+#define __FOPNOP(name) \
+	__FOP_FUNC(name) \
+	__FOP_RET(name)
+
 #define FOPNOP() \
-	FOP_FUNC(__stringify(__UNIQUE_ID(nop))) \
-	FOP_RET
+	__FOPNOP(__stringify(__UNIQUE_ID(nop)))
 
 #define FOP1E(op,  dst) \
-	FOP_FUNC(#op "_" #dst) \
-	"10: " #op " %" #dst " \n\t" FOP_RET
+	__FOP_FUNC(#op "_" #dst) \
+	"10: " #op " %" #dst " \n\t" \
+	__FOP_RET(#op "_" #dst)
 
 #define FOP1EEX(op,  dst) \
 	FOP1E(op, dst) _ASM_EXTABLE(10b, kvm_fastop_exception)
@@ -368,8 +379,9 @@
 	FOP_END
 
 #define FOP2E(op,  dst, src)	   \
-	FOP_FUNC(#op "_" #dst "_" #src) \
-	#op " %" #src ", %" #dst " \n\t" FOP_RET
+	__FOP_FUNC(#op "_" #dst "_" #src) \
+	#op " %" #src ", %" #dst " \n\t" \
+	__FOP_RET(#op "_" #dst "_" #src)
 
 #define FASTOP2(op) \
 	FOP_START(op) \
@@ -407,8 +419,9 @@
 	FOP_END
 
 #define FOP3E(op,  dst, src, src2) \
-	FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \
-	#op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
+	__FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \
+	#op " %" #src2 ", %" #src ", %" #dst " \n\t"\
+	__FOP_RET(#op "_" #dst "_" #src "_" #src2)
 
 /* 3-operand, word-only, src2=cl */
 #define FASTOP3WCL(op) \
@@ -425,7 +438,7 @@
 	".type " #op ", @function \n\t" \
 	#op ": \n\t" \
 	#op " %al \n\t" \
-	FOP_RET
+	__FOP_RET(#op)
 
 asm(".pushsection .fixup, \"ax\"\n"
     ".global kvm_fastop_exception \n"
@@ -451,12 +464,15 @@
 FOP_SETCC(setnle)
 FOP_END;
 
-FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET
+FOP_START(salc)
+FOP_FUNC(salc)
+"pushf; sbb %al, %al; popf \n\t"
+FOP_RET(salc)
 FOP_END;
 
 /*
  * XXX: inoutclob user must know where the argument is being expanded.
- *      Relying on CC_HAVE_ASM_GOTO would allow us to remove _fault.
+ *      Relying on CONFIG_CC_HAS_ASM_GOTO would allow us to remove _fault.
  */
 #define asm_safe(insn, inoutclob...) \
 ({ \
@@ -1509,7 +1525,7 @@
 		return emulate_gp(ctxt, index << 3 | 0x2);
 
 	addr = dt.address + index * 8;
-	return linear_read_system(ctxt, addr, desc, sizeof *desc);
+	return linear_read_system(ctxt, addr, desc, sizeof(*desc));
 }
 
 static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt,
@@ -1522,7 +1538,7 @@
 		struct desc_struct desc;
 		u16 sel;
 
-		memset (dt, 0, sizeof *dt);
+		memset(dt, 0, sizeof(*dt));
 		if (!ops->get_segment(ctxt, &sel, &desc, &base3,
 				      VCPU_SREG_LDTR))
 			return;
@@ -1586,7 +1602,7 @@
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	return linear_write_system(ctxt, addr, desc, sizeof *desc);
+	return linear_write_system(ctxt, addr, desc, sizeof(*desc));
 }
 
 static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
@@ -1604,7 +1620,7 @@
 	u16 dummy;
 	u32 base3 = 0;
 
-	memset(&seg_desc, 0, sizeof seg_desc);
+	memset(&seg_desc, 0, sizeof(seg_desc));
 
 	if (ctxt->mode == X86EMUL_MODE_REAL) {
 		/* set real mode segment descriptor (keep limit etc. for
@@ -2331,24 +2347,18 @@
 
 static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
 {
+#ifdef CONFIG_X86_64
 	u32 eax, ebx, ecx, edx;
 
 	eax = 0x80000001;
 	ecx = 0;
 	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
 	return edx & bit(X86_FEATURE_LM);
+#else
+	return false;
+#endif
 }
 
-#define GET_SMSTATE(type, smbase, offset)				  \
-	({								  \
-	 type __val;							  \
-	 int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val,      \
-				      sizeof(__val));			  \
-	 if (r != X86EMUL_CONTINUE)					  \
-		 return X86EMUL_UNHANDLEABLE;				  \
-	 __val;								  \
-	})
-
 static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
 {
 	desc->g    = (flags >> 23) & 1;
@@ -2361,27 +2371,30 @@
 	desc->type = (flags >>  8) & 15;
 }
 
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+			   int n)
 {
 	struct desc_struct desc;
 	int offset;
 	u16 selector;
 
-	selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+	selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
 
 	if (n < 3)
 		offset = 0x7f84 + n * 12;
 	else
 		offset = 0x7f2c + (n - 3) * 12;
 
-	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
-	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
-	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smstate, offset + 8));
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smstate, offset + 4));
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
 	return X86EMUL_CONTINUE;
 }
 
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+#ifdef CONFIG_X86_64
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+			   int n)
 {
 	struct desc_struct desc;
 	int offset;
@@ -2390,15 +2403,16 @@
 
 	offset = 0x7e00 + n * 16;
 
-	selector =                GET_SMSTATE(u16, smbase, offset);
-	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
-	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
-	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
-	base3 =                   GET_SMSTATE(u32, smbase, offset + 12);
+	selector =                GET_SMSTATE(u16, smstate, offset);
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smstate, offset + 4));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smstate, offset + 8));
+	base3 =                   GET_SMSTATE(u32, smstate, offset + 12);
 
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
 	return X86EMUL_CONTINUE;
 }
+#endif
 
 static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
 				    u64 cr0, u64 cr3, u64 cr4)
@@ -2445,7 +2459,8 @@
 	return X86EMUL_CONTINUE;
 }
 
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+			     const char *smstate)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
@@ -2453,53 +2468,55 @@
 	u32 val, cr0, cr3, cr4;
 	int i;
 
-	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
-	cr3 =                      GET_SMSTATE(u32, smbase, 0x7ff8);
-	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
-	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
+	cr0 =                      GET_SMSTATE(u32, smstate, 0x7ffc);
+	cr3 =                      GET_SMSTATE(u32, smstate, 0x7ff8);
+	ctxt->eflags =             GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
+	ctxt->_eip =               GET_SMSTATE(u32, smstate, 0x7ff0);
 
 	for (i = 0; i < 8; i++)
-		*reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
-	val = GET_SMSTATE(u32, smbase, 0x7fcc);
+	val = GET_SMSTATE(u32, smstate, 0x7fcc);
 	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
-	val = GET_SMSTATE(u32, smbase, 0x7fc8);
+	val = GET_SMSTATE(u32, smstate, 0x7fc8);
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
-	selector =                 GET_SMSTATE(u32, smbase, 0x7fc4);
-	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f64));
-	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f60));
-	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f5c));
+	selector =                 GET_SMSTATE(u32, smstate, 0x7fc4);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f64));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smstate, 0x7f60));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smstate, 0x7f5c));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
 
-	selector =                 GET_SMSTATE(u32, smbase, 0x7fc0);
-	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f80));
-	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f7c));
-	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f78));
+	selector =                 GET_SMSTATE(u32, smstate, 0x7fc0);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f80));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smstate, 0x7f7c));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smstate, 0x7f78));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
 
-	dt.address =               GET_SMSTATE(u32, smbase, 0x7f74);
-	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f70);
+	dt.address =               GET_SMSTATE(u32, smstate, 0x7f74);
+	dt.size =                  GET_SMSTATE(u32, smstate, 0x7f70);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
-	dt.address =               GET_SMSTATE(u32, smbase, 0x7f58);
-	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f54);
+	dt.address =               GET_SMSTATE(u32, smstate, 0x7f58);
+	dt.size =                  GET_SMSTATE(u32, smstate, 0x7f54);
 	ctxt->ops->set_idt(ctxt, &dt);
 
 	for (i = 0; i < 6; i++) {
-		int r = rsm_load_seg_32(ctxt, smbase, i);
+		int r = rsm_load_seg_32(ctxt, smstate, i);
 		if (r != X86EMUL_CONTINUE)
 			return r;
 	}
 
-	cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+	cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
 
-	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
 
 	return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 }
 
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+			     const char *smstate)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
@@ -2509,43 +2526,43 @@
 	int i, r;
 
 	for (i = 0; i < 16; i++)
-		*reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+		*reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
 
-	ctxt->_eip   = GET_SMSTATE(u64, smbase, 0x7f78);
-	ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+	ctxt->_eip   = GET_SMSTATE(u64, smstate, 0x7f78);
+	ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
 
-	val = GET_SMSTATE(u32, smbase, 0x7f68);
+	val = GET_SMSTATE(u32, smstate, 0x7f68);
 	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
-	val = GET_SMSTATE(u32, smbase, 0x7f60);
+	val = GET_SMSTATE(u32, smstate, 0x7f60);
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
-	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
-	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);
+	cr0 =                       GET_SMSTATE(u64, smstate, 0x7f58);
+	cr3 =                       GET_SMSTATE(u64, smstate, 0x7f50);
+	cr4 =                       GET_SMSTATE(u64, smstate, 0x7f48);
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
+	val =                       GET_SMSTATE(u64, smstate, 0x7ed0);
 	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
 
-	selector =                  GET_SMSTATE(u32, smbase, 0x7e90);
-	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e92) << 8);
-	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e94));
-	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e98));
-	base3 =                     GET_SMSTATE(u32, smbase, 0x7e9c);
+	selector =                  GET_SMSTATE(u32, smstate, 0x7e90);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e92) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smstate, 0x7e94));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smstate, 0x7e98));
+	base3 =                     GET_SMSTATE(u32, smstate, 0x7e9c);
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
 
-	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e84);
-	dt.address =                GET_SMSTATE(u64, smbase, 0x7e88);
+	dt.size =                   GET_SMSTATE(u32, smstate, 0x7e84);
+	dt.address =                GET_SMSTATE(u64, smstate, 0x7e88);
 	ctxt->ops->set_idt(ctxt, &dt);
 
-	selector =                  GET_SMSTATE(u32, smbase, 0x7e70);
-	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e72) << 8);
-	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e74));
-	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e78));
-	base3 =                     GET_SMSTATE(u32, smbase, 0x7e7c);
+	selector =                  GET_SMSTATE(u32, smstate, 0x7e70);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e72) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smstate, 0x7e74));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smstate, 0x7e78));
+	base3 =                     GET_SMSTATE(u32, smstate, 0x7e7c);
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
 
-	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e64);
-	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
+	dt.size =                   GET_SMSTATE(u32, smstate, 0x7e64);
+	dt.address =                GET_SMSTATE(u64, smstate, 0x7e68);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
 	r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
@@ -2553,37 +2570,49 @@
 		return r;
 
 	for (i = 0; i < 6; i++) {
-		r = rsm_load_seg_64(ctxt, smbase, i);
+		r = rsm_load_seg_64(ctxt, smstate, i);
 		if (r != X86EMUL_CONTINUE)
 			return r;
 	}
 
 	return X86EMUL_CONTINUE;
 }
+#endif
 
 static int em_rsm(struct x86_emulate_ctxt *ctxt)
 {
 	unsigned long cr0, cr4, efer;
+	char buf[512];
 	u64 smbase;
 	int ret;
 
 	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
 		return emulate_ud(ctxt);
 
+	smbase = ctxt->ops->get_smbase(ctxt);
+
+	ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+	if (ret != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+		ctxt->ops->set_nmi_mask(ctxt, false);
+
+	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
+
 	/*
 	 * Get back to real mode, to prepare a safe state in which to load
 	 * CR0/CR3/CR4/EFER.  It's all a bit more complicated if the vCPU
 	 * supports long mode.
 	 */
-	cr4 = ctxt->ops->get_cr(ctxt, 4);
 	if (emulator_has_longmode(ctxt)) {
 		struct desc_struct cs_desc;
 
 		/* Zero CR4.PCIDE before CR0.PG.  */
-		if (cr4 & X86_CR4_PCIDE) {
+		cr4 = ctxt->ops->get_cr(ctxt, 4);
+		if (cr4 & X86_CR4_PCIDE)
 			ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
-			cr4 &= ~X86_CR4_PCIDE;
-		}
 
 		/* A 32-bit code segment is required to clear EFER.LMA.  */
 		memset(&cs_desc, 0, sizeof(cs_desc));
@@ -2597,39 +2626,39 @@
 	if (cr0 & X86_CR0_PE)
 		ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
 
-	/* Now clear CR4.PAE (which must be done before clearing EFER.LME).  */
-	if (cr4 & X86_CR4_PAE)
-		ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
+	if (emulator_has_longmode(ctxt)) {
+		/* Clear CR4.PAE before clearing EFER.LME. */
+		cr4 = ctxt->ops->get_cr(ctxt, 4);
+		if (cr4 & X86_CR4_PAE)
+			ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
 
-	/* And finally go back to 32-bit mode.  */
-	efer = 0;
-	ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
-
-	smbase = ctxt->ops->get_smbase(ctxt);
+		/* And finally go back to 32-bit mode.  */
+		efer = 0;
+		ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+	}
 
 	/*
 	 * Give pre_leave_smm() a chance to make ISA-specific changes to the
 	 * vCPU state (e.g. enter guest mode) before loading state from the SMM
 	 * state-save area.
 	 */
-	if (ctxt->ops->pre_leave_smm(ctxt, smbase))
+	if (ctxt->ops->pre_leave_smm(ctxt, buf))
 		return X86EMUL_UNHANDLEABLE;
 
+#ifdef CONFIG_X86_64
 	if (emulator_has_longmode(ctxt))
-		ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+		ret = rsm_load_state_64(ctxt, buf);
 	else
-		ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+#endif
+		ret = rsm_load_state_32(ctxt, buf);
 
 	if (ret != X86EMUL_CONTINUE) {
 		/* FIXME: should triple fault */
 		return X86EMUL_UNHANDLEABLE;
 	}
 
-	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
-		ctxt->ops->set_nmi_mask(ctxt, false);
+	ctxt->ops->post_leave_smm(ctxt);
 
-	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
-		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
 	return X86EMUL_CONTINUE;
 }
 
@@ -2711,7 +2740,16 @@
 	    edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx)
 		return true;
 
-	/* default: (not Intel, not AMD), apply Intel's stricter rules... */
+	/* Hygon ("HygonGenuine") */
+	if (ebx == X86EMUL_CPUID_VENDOR_HygonGenuine_ebx &&
+	    ecx == X86EMUL_CPUID_VENDOR_HygonGenuine_ecx &&
+	    edx == X86EMUL_CPUID_VENDOR_HygonGenuine_edx)
+		return true;
+
+	/*
+	 * default: (not Intel, not AMD, not Hygon), apply Intel's
+	 * stricter rules...
+	 */
 	return false;
 }
 
@@ -3066,17 +3104,17 @@
 	int ret;
 	u32 new_tss_base = get_desc_base(new_desc);
 
-	ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg);
+	ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof(tss_seg));
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
 	save_state_to_tss16(ctxt, &tss_seg);
 
-	ret = linear_write_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg);
+	ret = linear_write_system(ctxt, old_tss_base, &tss_seg, sizeof(tss_seg));
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
-	ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof tss_seg);
+	ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof(tss_seg));
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
@@ -3085,7 +3123,7 @@
 
 		ret = linear_write_system(ctxt, new_tss_base,
 					  &tss_seg.prev_task_link,
-					  sizeof tss_seg.prev_task_link);
+					  sizeof(tss_seg.prev_task_link));
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
 	}
@@ -3207,7 +3245,7 @@
 	u32 eip_offset = offsetof(struct tss_segment_32, eip);
 	u32 ldt_sel_offset = offsetof(struct tss_segment_32, ldt_selector);
 
-	ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg);
+	ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof(tss_seg));
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
@@ -3219,7 +3257,7 @@
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
-	ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof tss_seg);
+	ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof(tss_seg));
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
@@ -3228,7 +3266,7 @@
 
 		ret = linear_write_system(ctxt, new_tss_base,
 					  &tss_seg.prev_task_link,
-					  sizeof tss_seg.prev_task_link);
+					  sizeof(tss_seg.prev_task_link));
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
 	}
@@ -4118,6 +4156,20 @@
 	return rc;
 }
 
+static int em_xsetbv(struct x86_emulate_ctxt *ctxt)
+{
+	u32 eax, ecx, edx;
+
+	eax = reg_read(ctxt, VCPU_REGS_RAX);
+	edx = reg_read(ctxt, VCPU_REGS_RDX);
+	ecx = reg_read(ctxt, VCPU_REGS_RCX);
+
+	if (ctxt->ops->set_xcr(ctxt, ecx, ((u64)edx << 32) | eax))
+		return emulate_gp(ctxt, 0);
+
+	return X86EMUL_CONTINUE;
+}
+
 static bool valid_cr(int nr)
 {
 	switch (nr) {
@@ -4238,7 +4290,7 @@
 		ulong dr6;
 
 		ctxt->ops->get_dr(ctxt, 6, &dr6);
-		dr6 &= ~15;
+		dr6 &= ~DR_TRAP_BITS;
 		dr6 |= DR6_BD | DR6_RTM;
 		ctxt->ops->set_dr(ctxt, 6, dr6);
 		return emulate_db(ctxt);
@@ -4371,6 +4423,12 @@
 	N, N, N, N, N, N,
 };
 
+static const struct opcode group7_rm2[] = {
+	N,
+	II(ImplicitOps | Priv,			em_xsetbv,	xsetbv),
+	N, N, N, N, N, N,
+};
+
 static const struct opcode group7_rm3[] = {
 	DIP(SrcNone | Prot | Priv,		vmrun,		check_svme_pa),
 	II(SrcNone  | Prot | EmulateOnUD,	em_hypercall,	vmmcall),
@@ -4460,7 +4518,8 @@
 }, {
 	EXT(0, group7_rm0),
 	EXT(0, group7_rm1),
-	N, EXT(0, group7_rm3),
+	EXT(0, group7_rm2),
+	EXT(0, group7_rm3),
 	II(SrcNone | DstMem | Mov,		em_smsw, smsw), N,
 	II(SrcMem16 | Mov | Priv,		em_lmsw, lmsw),
 	EXT(0, group7_rm7),
@@ -5106,7 +5165,7 @@
 	else {
 		rc = __do_insn_fetch_bytes(ctxt, 1);
 		if (rc != X86EMUL_CONTINUE)
-			return rc;
+			goto done;
 	}
 
 	switch (mode) {
@@ -5357,6 +5416,8 @@
 					ctxt->memopp->addr.mem.ea + ctxt->_eip);
 
 done:
+	if (rc == X86EMUL_PROPAGATE_FAULT)
+		ctxt->have_exception = true;
 	return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK;
 }
 
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 01d209a..23ff655 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * KVM Microsoft Hyper-V emulation
  *
@@ -15,10 +16,6 @@
  *   Amit Shah    <amit.shah@qumranet.com>
  *   Ben-Ami Yassour <benami@il.ibm.com>
  *   Andrey Smetanin <asmetanin@virtuozzo.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #include "x86.h"
@@ -26,6 +23,7 @@
 #include "ioapic.h"
 #include "hyperv.h"
 
+#include <linux/cpu.h>
 #include <linux/kvm_host.h>
 #include <linux/highmem.h>
 #include <linux/sched/cputime.h>
@@ -36,6 +34,11 @@
 
 #include "trace.h"
 
+#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64)
+
+static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer,
+				bool vcpu_kick);
+
 static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint)
 {
 	return atomic64_read(&synic->sint[sint]);
@@ -132,8 +135,10 @@
 	struct kvm_vcpu *vcpu = NULL;
 	int i;
 
-	if (vpidx < KVM_MAX_VCPUS)
-		vcpu = kvm_get_vcpu(kvm, vpidx);
+	if (vpidx >= KVM_MAX_VCPUS)
+		return NULL;
+
+	vcpu = kvm_get_vcpu(kvm, vpidx);
 	if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
 		return vcpu;
 	kvm_for_each_vcpu(i, vcpu, kvm)
@@ -154,59 +159,24 @@
 	return (synic->active) ? synic : NULL;
 }
 
-static void synic_clear_sint_msg_pending(struct kvm_vcpu_hv_synic *synic,
-					u32 sint)
-{
-	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
-	struct page *page;
-	gpa_t gpa;
-	struct hv_message *msg;
-	struct hv_message_page *msg_page;
-
-	gpa = synic->msg_page & PAGE_MASK;
-	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
-	if (is_error_page(page)) {
-		vcpu_err(vcpu, "Hyper-V SynIC can't get msg page, gpa 0x%llx\n",
-			 gpa);
-		return;
-	}
-	msg_page = kmap_atomic(page);
-
-	msg = &msg_page->sint_message[sint];
-	msg->header.message_flags.msg_pending = 0;
-
-	kunmap_atomic(msg_page);
-	kvm_release_page_dirty(page);
-	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
-}
-
 static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
 	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
 	struct kvm_vcpu_hv_stimer *stimer;
-	int gsi, idx, stimers_pending;
+	int gsi, idx;
 
 	trace_kvm_hv_notify_acked_sint(vcpu->vcpu_id, sint);
 
-	if (synic->msg_page & HV_SYNIC_SIMP_ENABLE)
-		synic_clear_sint_msg_pending(synic, sint);
-
 	/* Try to deliver pending Hyper-V SynIC timers messages */
-	stimers_pending = 0;
 	for (idx = 0; idx < ARRAY_SIZE(hv_vcpu->stimer); idx++) {
 		stimer = &hv_vcpu->stimer[idx];
-		if (stimer->msg_pending &&
-		    (stimer->config & HV_STIMER_ENABLE) &&
-		    HV_STIMER_SINT(stimer->config) == sint) {
-			set_bit(stimer->index,
-				hv_vcpu->stimer_pending_bitmap);
-			stimers_pending++;
-		}
+		if (stimer->msg_pending && stimer->config.enable &&
+		    !stimer->config.direct_mode &&
+		    stimer->config.sintx == sint)
+			stimer_mark_pending(stimer, false);
 	}
-	if (stimers_pending)
-		kvm_make_request(KVM_REQ_HV_STIMER, vcpu);
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	gsi = atomic_read(&synic->sint_to_gsi[sint]);
@@ -493,7 +463,7 @@
 	time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm);
 	ktime_now = ktime_get();
 
-	if (stimer->config & HV_STIMER_PERIODIC) {
+	if (stimer->config.periodic) {
 		if (stimer->exp_time) {
 			if (time_now >= stimer->exp_time) {
 				u64 remainder;
@@ -542,14 +512,21 @@
 static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
 			     bool host)
 {
+	union hv_stimer_config new_config = {.as_uint64 = config},
+		old_config = {.as_uint64 = stimer->config.as_uint64};
+
 	trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id,
 				       stimer->index, config, host);
 
 	stimer_cleanup(stimer);
-	if ((stimer->config & HV_STIMER_ENABLE) && HV_STIMER_SINT(config) == 0)
-		config &= ~HV_STIMER_ENABLE;
-	stimer->config = config;
-	stimer_mark_pending(stimer, false);
+	if (old_config.enable &&
+	    !new_config.direct_mode && new_config.sintx == 0)
+		new_config.enable = 0;
+	stimer->config.as_uint64 = new_config.as_uint64;
+
+	if (stimer->config.enable)
+		stimer_mark_pending(stimer, false);
+
 	return 0;
 }
 
@@ -562,16 +539,19 @@
 	stimer_cleanup(stimer);
 	stimer->count = count;
 	if (stimer->count == 0)
-		stimer->config &= ~HV_STIMER_ENABLE;
-	else if (stimer->config & HV_STIMER_AUTOENABLE)
-		stimer->config |= HV_STIMER_ENABLE;
-	stimer_mark_pending(stimer, false);
+		stimer->config.enable = 0;
+	else if (stimer->config.auto_enable)
+		stimer->config.enable = 1;
+
+	if (stimer->config.enable)
+		stimer_mark_pending(stimer, false);
+
 	return 0;
 }
 
 static int stimer_get_config(struct kvm_vcpu_hv_stimer *stimer, u64 *pconfig)
 {
-	*pconfig = stimer->config;
+	*pconfig = stimer->config.as_uint64;
 	return 0;
 }
 
@@ -582,44 +562,60 @@
 }
 
 static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint,
-			     struct hv_message *src_msg)
+			     struct hv_message *src_msg, bool no_retry)
 {
 	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
-	struct page *page;
-	gpa_t gpa;
-	struct hv_message *dst_msg;
+	int msg_off = offsetof(struct hv_message_page, sint_message[sint]);
+	gfn_t msg_page_gfn;
+	struct hv_message_header hv_hdr;
 	int r;
-	struct hv_message_page *msg_page;
 
 	if (!(synic->msg_page & HV_SYNIC_SIMP_ENABLE))
 		return -ENOENT;
 
-	gpa = synic->msg_page & PAGE_MASK;
-	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
-	if (is_error_page(page))
-		return -EFAULT;
+	msg_page_gfn = synic->msg_page >> PAGE_SHIFT;
 
-	msg_page = kmap_atomic(page);
-	dst_msg = &msg_page->sint_message[sint];
-	if (sync_cmpxchg(&dst_msg->header.message_type, HVMSG_NONE,
-			 src_msg->header.message_type) != HVMSG_NONE) {
-		dst_msg->header.message_flags.msg_pending = 1;
-		r = -EAGAIN;
-	} else {
-		memcpy(&dst_msg->u.payload, &src_msg->u.payload,
-		       src_msg->header.payload_size);
-		dst_msg->header.message_type = src_msg->header.message_type;
-		dst_msg->header.payload_size = src_msg->header.payload_size;
-		r = synic_set_irq(synic, sint);
-		if (r >= 1)
-			r = 0;
-		else if (r == 0)
-			r = -EFAULT;
+	/*
+	 * Strictly following the spec-mandated ordering would assume setting
+	 * .msg_pending before checking .message_type.  However, this function
+	 * is only called in vcpu context so the entire update is atomic from
+	 * guest POV and thus the exact order here doesn't matter.
+	 */
+	r = kvm_vcpu_read_guest_page(vcpu, msg_page_gfn, &hv_hdr.message_type,
+				     msg_off + offsetof(struct hv_message,
+							header.message_type),
+				     sizeof(hv_hdr.message_type));
+	if (r < 0)
+		return r;
+
+	if (hv_hdr.message_type != HVMSG_NONE) {
+		if (no_retry)
+			return 0;
+
+		hv_hdr.message_flags.msg_pending = 1;
+		r = kvm_vcpu_write_guest_page(vcpu, msg_page_gfn,
+					      &hv_hdr.message_flags,
+					      msg_off +
+					      offsetof(struct hv_message,
+						       header.message_flags),
+					      sizeof(hv_hdr.message_flags));
+		if (r < 0)
+			return r;
+		return -EAGAIN;
 	}
-	kunmap_atomic(msg_page);
-	kvm_release_page_dirty(page);
-	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
-	return r;
+
+	r = kvm_vcpu_write_guest_page(vcpu, msg_page_gfn, src_msg, msg_off,
+				      sizeof(src_msg->header) +
+				      src_msg->header.payload_size);
+	if (r < 0)
+		return r;
+
+	r = synic_set_irq(synic, sint);
+	if (r < 0)
+		return r;
+	if (r == 0)
+		return -EFAULT;
+	return 0;
 }
 
 static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer)
@@ -629,24 +625,47 @@
 	struct hv_timer_message_payload *payload =
 			(struct hv_timer_message_payload *)&msg->u.payload;
 
+	/*
+	 * To avoid piling up periodic ticks, don't retry message
+	 * delivery for them (within "lazy" lost ticks policy).
+	 */
+	bool no_retry = stimer->config.periodic;
+
 	payload->expiration_time = stimer->exp_time;
 	payload->delivery_time = get_time_ref_counter(vcpu->kvm);
 	return synic_deliver_msg(vcpu_to_synic(vcpu),
-				 HV_STIMER_SINT(stimer->config), msg);
+				 stimer->config.sintx, msg,
+				 no_retry);
+}
+
+static int stimer_notify_direct(struct kvm_vcpu_hv_stimer *stimer)
+{
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+	struct kvm_lapic_irq irq = {
+		.delivery_mode = APIC_DM_FIXED,
+		.vector = stimer->config.apic_vector
+	};
+
+	if (lapic_in_kernel(vcpu))
+		return !kvm_apic_set_irq(vcpu, &irq, NULL);
+	return 0;
 }
 
 static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer)
 {
-	int r;
+	int r, direct = stimer->config.direct_mode;
 
 	stimer->msg_pending = true;
-	r = stimer_send_msg(stimer);
+	if (!direct)
+		r = stimer_send_msg(stimer);
+	else
+		r = stimer_notify_direct(stimer);
 	trace_kvm_hv_stimer_expiration(stimer_to_vcpu(stimer)->vcpu_id,
-				       stimer->index, r);
+				       stimer->index, direct, r);
 	if (!r) {
 		stimer->msg_pending = false;
-		if (!(stimer->config & HV_STIMER_PERIODIC))
-			stimer->config &= ~HV_STIMER_ENABLE;
+		if (!(stimer->config.periodic))
+			stimer->config.enable = 0;
 	}
 }
 
@@ -660,7 +679,7 @@
 	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
 		if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) {
 			stimer = &hv_vcpu->stimer[i];
-			if (stimer->config & HV_STIMER_ENABLE) {
+			if (stimer->config.enable) {
 				exp_time = stimer->exp_time;
 
 				if (exp_time) {
@@ -670,7 +689,7 @@
 						stimer_expiration(stimer);
 				}
 
-				if ((stimer->config & HV_STIMER_ENABLE) &&
+				if ((stimer->config.enable) &&
 				    stimer->count) {
 					if (!stimer->msg_pending)
 						stimer_start(stimer);
@@ -689,6 +708,24 @@
 		stimer_cleanup(&hv_vcpu->stimer[i]);
 }
 
+bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE))
+		return false;
+	return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED;
+}
+EXPORT_SYMBOL_GPL(kvm_hv_assist_page_enabled);
+
+bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
+			    struct hv_vp_assist_page *assist_page)
+{
+	if (!kvm_hv_assist_page_enabled(vcpu))
+		return false;
+	return !kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data,
+				      assist_page, sizeof(*assist_page));
+}
+EXPORT_SYMBOL_GPL(kvm_hv_get_assist_page);
+
 static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer)
 {
 	struct hv_message *msg = &stimer->msg;
@@ -793,9 +830,9 @@
 	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
 
 	if (host)
-		hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY;
+		hv->hv_crash_ctl = data & HV_CRASH_CTL_CRASH_NOTIFY;
 
-	if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) {
+	if (!host && (data & HV_CRASH_CTL_CRASH_NOTIFY)) {
 
 		vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n",
 			  hv->hv_crash_param[0],
@@ -1040,21 +1077,41 @@
 
 static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 {
-	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+	struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
 
 	switch (msr) {
-	case HV_X64_MSR_VP_INDEX:
-		if (!host)
+	case HV_X64_MSR_VP_INDEX: {
+		struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+		int vcpu_idx = kvm_vcpu_get_idx(vcpu);
+		u32 new_vp_index = (u32)data;
+
+		if (!host || new_vp_index >= KVM_MAX_VCPUS)
 			return 1;
-		hv->vp_index = (u32)data;
+
+		if (new_vp_index == hv_vcpu->vp_index)
+			return 0;
+
+		/*
+		 * The VP index is initialized to vcpu_index by
+		 * kvm_hv_vcpu_postcreate so they initially match.  Now the
+		 * VP index is changing, adjust num_mismatched_vp_indexes if
+		 * it now matches or no longer matches vcpu_idx.
+		 */
+		if (hv_vcpu->vp_index == vcpu_idx)
+			atomic_inc(&hv->num_mismatched_vp_indexes);
+		else if (new_vp_index == vcpu_idx)
+			atomic_dec(&hv->num_mismatched_vp_indexes);
+
+		hv_vcpu->vp_index = new_vp_index;
 		break;
+	}
 	case HV_X64_MSR_VP_ASSIST_PAGE: {
 		u64 gfn;
 		unsigned long addr;
 
 		if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) {
-			hv->hv_vapic = data;
-			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+			hv_vcpu->hv_vapic = data;
+			if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0))
 				return 1;
 			break;
 		}
@@ -1062,12 +1119,19 @@
 		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
 		if (kvm_is_error_hva(addr))
 			return 1;
-		if (__clear_user((void __user *)addr, PAGE_SIZE))
+
+		/*
+		 * Clear apic_assist portion of f(struct hv_vp_assist_page
+		 * only, there can be valuable data in the rest which needs
+		 * to be preserved e.g. on migration.
+		 */
+		if (__clear_user((void __user *)addr, sizeof(u32)))
 			return 1;
-		hv->hv_vapic = data;
+		hv_vcpu->hv_vapic = data;
 		kvm_vcpu_mark_page_dirty(vcpu, gfn);
 		if (kvm_lapic_enable_pv_eoi(vcpu,
-					    gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+					    gfn_to_gpa(gfn) | KVM_MSR_ENABLED,
+					    sizeof(struct hv_vp_assist_page)))
 			return 1;
 		break;
 	}
@@ -1080,7 +1144,7 @@
 	case HV_X64_MSR_VP_RUNTIME:
 		if (!host)
 			return 1;
-		hv->runtime_offset = data - current_task_runtime_100ns();
+		hv_vcpu->runtime_offset = data - current_task_runtime_100ns();
 		break;
 	case HV_X64_MSR_SCONTROL:
 	case HV_X64_MSR_SVERSION:
@@ -1172,11 +1236,11 @@
 			  bool host)
 {
 	u64 data = 0;
-	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+	struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
 
 	switch (msr) {
 	case HV_X64_MSR_VP_INDEX:
-		data = hv->vp_index;
+		data = hv_vcpu->vp_index;
 		break;
 	case HV_X64_MSR_EOI:
 		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
@@ -1185,10 +1249,10 @@
 	case HV_X64_MSR_TPR:
 		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
 	case HV_X64_MSR_VP_ASSIST_PAGE:
-		data = hv->hv_vapic;
+		data = hv_vcpu->hv_vapic;
 		break;
 	case HV_X64_MSR_VP_RUNTIME:
-		data = current_task_runtime_100ns() + hv->runtime_offset;
+		data = current_task_runtime_100ns() + hv_vcpu->runtime_offset;
 		break;
 	case HV_X64_MSR_SCONTROL:
 	case HV_X64_MSR_SVERSION:
@@ -1255,32 +1319,47 @@
 		return kvm_hv_get_msr(vcpu, msr, pdata, host);
 }
 
-static __always_inline int get_sparse_bank_no(u64 valid_bank_mask, int bank_no)
+static __always_inline unsigned long *sparse_set_to_vcpu_mask(
+	struct kvm *kvm, u64 *sparse_banks, u64 valid_bank_mask,
+	u64 *vp_bitmap, unsigned long *vcpu_bitmap)
 {
-	int i = 0, j;
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+	struct kvm_vcpu *vcpu;
+	int i, bank, sbank = 0;
 
-	if (!(valid_bank_mask & BIT_ULL(bank_no)))
-		return -1;
+	memset(vp_bitmap, 0,
+	       KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap));
+	for_each_set_bit(bank, (unsigned long *)&valid_bank_mask,
+			 KVM_HV_MAX_SPARSE_VCPU_SET_BITS)
+		vp_bitmap[bank] = sparse_banks[sbank++];
 
-	for (j = 0; j < bank_no; j++)
-		if (valid_bank_mask & BIT_ULL(j))
-			i++;
+	if (likely(!atomic_read(&hv->num_mismatched_vp_indexes))) {
+		/* for all vcpus vp_index == vcpu_idx */
+		return (unsigned long *)vp_bitmap;
+	}
 
-	return i;
+	bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (test_bit(vcpu_to_hv_vcpu(vcpu)->vp_index,
+			     (unsigned long *)vp_bitmap))
+			__set_bit(i, vcpu_bitmap);
+	}
+	return vcpu_bitmap;
 }
 
 static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
 			    u16 rep_cnt, bool ex)
 {
 	struct kvm *kvm = current_vcpu->kvm;
-	struct kvm_vcpu_hv *hv_current = &current_vcpu->arch.hyperv;
+	struct kvm_vcpu_hv *hv_vcpu = &current_vcpu->arch.hyperv;
 	struct hv_tlb_flush_ex flush_ex;
 	struct hv_tlb_flush flush;
-	struct kvm_vcpu *vcpu;
-	unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)] = {0};
-	unsigned long valid_bank_mask = 0;
+	u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
+	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
+	unsigned long *vcpu_mask;
+	u64 valid_bank_mask;
 	u64 sparse_banks[64];
-	int sparse_banks_len, i;
+	int sparse_banks_len;
 	bool all_cpus;
 
 	if (!ex) {
@@ -1290,8 +1369,18 @@
 		trace_kvm_hv_flush_tlb(flush.processor_mask,
 				       flush.address_space, flush.flags);
 
+		valid_bank_mask = BIT_ULL(0);
 		sparse_banks[0] = flush.processor_mask;
-		all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
+
+		/*
+		 * Work around possible WS2012 bug: it sends hypercalls
+		 * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear,
+		 * while also expecting us to flush something and crashing if
+		 * we don't. Let's treat processor_mask == 0 same as
+		 * HV_FLUSH_ALL_PROCESSORS.
+		 */
+		all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) ||
+			flush.processor_mask == 0;
 	} else {
 		if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex,
 					    sizeof(flush_ex))))
@@ -1306,7 +1395,8 @@
 		all_cpus = flush_ex.hv_vp_set.format !=
 			HV_GENERIC_SET_SPARSE_4K;
 
-		sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
+		sparse_banks_len =
+			bitmap_weight((unsigned long *)&valid_bank_mask, 64) *
 			sizeof(sparse_banks[0]);
 
 		if (!sparse_banks_len && !all_cpus)
@@ -1321,48 +1411,19 @@
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 	}
 
-	cpumask_clear(&hv_current->tlb_lush);
+	cpumask_clear(&hv_vcpu->tlb_flush);
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
-		int bank = hv->vp_index / 64, sbank = 0;
+	vcpu_mask = all_cpus ? NULL :
+		sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
+					vp_bitmap, vcpu_bitmap);
 
-		if (!all_cpus) {
-			/* Banks >64 can't be represented */
-			if (bank >= 64)
-				continue;
-
-			/* Non-ex hypercalls can only address first 64 vCPUs */
-			if (!ex && bank)
-				continue;
-
-			if (ex) {
-				/*
-				 * Check is the bank of this vCPU is in sparse
-				 * set and get the sparse bank number.
-				 */
-				sbank = get_sparse_bank_no(valid_bank_mask,
-							   bank);
-
-				if (sbank < 0)
-					continue;
-			}
-
-			if (!(sparse_banks[sbank] & BIT_ULL(hv->vp_index % 64)))
-				continue;
-		}
-
-		/*
-		 * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we
-		 * can't analyze it here, flush TLB regardless of the specified
-		 * address space.
-		 */
-		__set_bit(i, vcpu_bitmap);
-	}
-
+	/*
+	 * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
+	 * analyze it here, flush TLB regardless of the specified address space.
+	 */
 	kvm_make_vcpus_request_mask(kvm,
 				    KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP,
-				    vcpu_bitmap, &hv_current->tlb_lush);
+				    vcpu_mask, &hv_vcpu->tlb_flush);
 
 ret_success:
 	/* We always do full TLB flush, set rep_done = rep_cnt. */
@@ -1370,6 +1431,99 @@
 		((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET);
 }
 
+static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
+				 unsigned long *vcpu_bitmap)
+{
+	struct kvm_lapic_irq irq = {
+		.delivery_mode = APIC_DM_FIXED,
+		.vector = vector
+	};
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
+			continue;
+
+		/* We fail only when APIC is disabled */
+		kvm_apic_set_irq(vcpu, &irq, NULL);
+	}
+}
+
+static u64 kvm_hv_send_ipi(struct kvm_vcpu *current_vcpu, u64 ingpa, u64 outgpa,
+			   bool ex, bool fast)
+{
+	struct kvm *kvm = current_vcpu->kvm;
+	struct hv_send_ipi_ex send_ipi_ex;
+	struct hv_send_ipi send_ipi;
+	u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
+	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
+	unsigned long *vcpu_mask;
+	unsigned long valid_bank_mask;
+	u64 sparse_banks[64];
+	int sparse_banks_len;
+	u32 vector;
+	bool all_cpus;
+
+	if (!ex) {
+		if (!fast) {
+			if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi,
+						    sizeof(send_ipi))))
+				return HV_STATUS_INVALID_HYPERCALL_INPUT;
+			sparse_banks[0] = send_ipi.cpu_mask;
+			vector = send_ipi.vector;
+		} else {
+			/* 'reserved' part of hv_send_ipi should be 0 */
+			if (unlikely(ingpa >> 32 != 0))
+				return HV_STATUS_INVALID_HYPERCALL_INPUT;
+			sparse_banks[0] = outgpa;
+			vector = (u32)ingpa;
+		}
+		all_cpus = false;
+		valid_bank_mask = BIT_ULL(0);
+
+		trace_kvm_hv_send_ipi(vector, sparse_banks[0]);
+	} else {
+		if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi_ex,
+					    sizeof(send_ipi_ex))))
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+		trace_kvm_hv_send_ipi_ex(send_ipi_ex.vector,
+					 send_ipi_ex.vp_set.format,
+					 send_ipi_ex.vp_set.valid_bank_mask);
+
+		vector = send_ipi_ex.vector;
+		valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask;
+		sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
+			sizeof(sparse_banks[0]);
+
+		all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
+
+		if (!sparse_banks_len)
+			goto ret_success;
+
+		if (!all_cpus &&
+		    kvm_read_guest(kvm,
+				   ingpa + offsetof(struct hv_send_ipi_ex,
+						    vp_set.bank_contents),
+				   sparse_banks,
+				   sparse_banks_len))
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+	}
+
+	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+		return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+	vcpu_mask = all_cpus ? NULL :
+		sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
+					vp_bitmap, vcpu_bitmap);
+
+	kvm_send_ipi_to_many(kvm, vector, vcpu_mask);
+
+ret_success:
+	return HV_STATUS_SUCCESS;
+}
+
 bool kvm_hv_hypercall_enabled(struct kvm *kvm)
 {
 	return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE;
@@ -1381,10 +1535,10 @@
 
 	longmode = is_64_bit_mode(vcpu);
 	if (longmode)
-		kvm_register_write(vcpu, VCPU_REGS_RAX, result);
+		kvm_rax_write(vcpu, result);
 	else {
-		kvm_register_write(vcpu, VCPU_REGS_RDX, result >> 32);
-		kvm_register_write(vcpu, VCPU_REGS_RAX, result & 0xffffffff);
+		kvm_rdx_write(vcpu, result >> 32);
+		kvm_rax_write(vcpu, result & 0xffffffff);
 	}
 }
 
@@ -1443,7 +1597,7 @@
 {
 	u64 param, ingpa, outgpa, ret = HV_STATUS_SUCCESS;
 	uint16_t code, rep_idx, rep_cnt;
-	bool fast, longmode, rep;
+	bool fast, rep;
 
 	/*
 	 * hypercall generates UD from non zero cpl and real mode
@@ -1454,23 +1608,21 @@
 		return 1;
 	}
 
-	longmode = is_64_bit_mode(vcpu);
-
-	if (!longmode) {
-		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
-		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
-		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
-	}
 #ifdef CONFIG_X86_64
-	else {
-		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
-		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
-		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
-	}
+	if (is_64_bit_mode(vcpu)) {
+		param = kvm_rcx_read(vcpu);
+		ingpa = kvm_rdx_read(vcpu);
+		outgpa = kvm_r8_read(vcpu);
+	} else
 #endif
+	{
+		param = ((u64)kvm_rdx_read(vcpu) << 32) |
+			(kvm_rax_read(vcpu) & 0xffffffff);
+		ingpa = ((u64)kvm_rbx_read(vcpu) << 32) |
+			(kvm_rcx_read(vcpu) & 0xffffffff);
+		outgpa = ((u64)kvm_rdi_read(vcpu) << 32) |
+			(kvm_rsi_read(vcpu) & 0xffffffff);
+	}
 
 	code = param & 0xffff;
 	fast = !!(param & HV_HYPERCALL_FAST_BIT);
@@ -1496,7 +1648,7 @@
 		ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
 		if (ret != HV_STATUS_INVALID_PORT_ID)
 			break;
-		/* maybe userspace knows this conn_id: fall through */
+		/* fall through - maybe userspace knows this conn_id. */
 	case HVCALL_POST_MESSAGE:
 		/* don't bother userspace if it has no way to handle it */
 		if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) {
@@ -1539,6 +1691,20 @@
 		}
 		ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true);
 		break;
+	case HVCALL_SEND_IPI:
+		if (unlikely(rep)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+			break;
+		}
+		ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, false, fast);
+		break;
+	case HVCALL_SEND_IPI_EX:
+		if (unlikely(fast || rep)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+			break;
+		}
+		ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false);
+		break;
 	default:
 		ret = HV_STATUS_INVALID_HYPERCALL_CODE;
 		break;
@@ -1575,7 +1741,7 @@
 
 	mutex_lock(&hv->hv_lock);
 	ret = idr_alloc(&hv->conn_to_evt, eventfd, conn_id, conn_id + 1,
-			GFP_KERNEL);
+			GFP_KERNEL_ACCOUNT);
 	mutex_unlock(&hv->hv_lock);
 
 	if (ret >= 0)
@@ -1614,3 +1780,133 @@
 		return kvm_hv_eventfd_deassign(kvm, args->conn_id);
 	return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd);
 }
+
+int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
+				struct kvm_cpuid_entry2 __user *entries)
+{
+	uint16_t evmcs_ver = 0;
+	struct kvm_cpuid_entry2 cpuid_entries[] = {
+		{ .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS },
+		{ .function = HYPERV_CPUID_INTERFACE },
+		{ .function = HYPERV_CPUID_VERSION },
+		{ .function = HYPERV_CPUID_FEATURES },
+		{ .function = HYPERV_CPUID_ENLIGHTMENT_INFO },
+		{ .function = HYPERV_CPUID_IMPLEMENT_LIMITS },
+		{ .function = HYPERV_CPUID_NESTED_FEATURES },
+	};
+	int i, nent = ARRAY_SIZE(cpuid_entries);
+
+	if (kvm_x86_ops->nested_get_evmcs_version)
+		evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
+
+	/* Skip NESTED_FEATURES if eVMCS is not supported */
+	if (!evmcs_ver)
+		--nent;
+
+	if (cpuid->nent < nent)
+		return -E2BIG;
+
+	if (cpuid->nent > nent)
+		cpuid->nent = nent;
+
+	for (i = 0; i < nent; i++) {
+		struct kvm_cpuid_entry2 *ent = &cpuid_entries[i];
+		u32 signature[3];
+
+		switch (ent->function) {
+		case HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS:
+			memcpy(signature, "Linux KVM Hv", 12);
+
+			ent->eax = HYPERV_CPUID_NESTED_FEATURES;
+			ent->ebx = signature[0];
+			ent->ecx = signature[1];
+			ent->edx = signature[2];
+			break;
+
+		case HYPERV_CPUID_INTERFACE:
+			memcpy(signature, "Hv#1\0\0\0\0\0\0\0\0", 12);
+			ent->eax = signature[0];
+			break;
+
+		case HYPERV_CPUID_VERSION:
+			/*
+			 * We implement some Hyper-V 2016 functions so let's use
+			 * this version.
+			 */
+			ent->eax = 0x00003839;
+			ent->ebx = 0x000A0000;
+			break;
+
+		case HYPERV_CPUID_FEATURES:
+			ent->eax |= HV_X64_MSR_VP_RUNTIME_AVAILABLE;
+			ent->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE;
+			ent->eax |= HV_X64_MSR_SYNIC_AVAILABLE;
+			ent->eax |= HV_MSR_SYNTIMER_AVAILABLE;
+			ent->eax |= HV_X64_MSR_APIC_ACCESS_AVAILABLE;
+			ent->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE;
+			ent->eax |= HV_X64_MSR_VP_INDEX_AVAILABLE;
+			ent->eax |= HV_X64_MSR_RESET_AVAILABLE;
+			ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE;
+			ent->eax |= HV_X64_ACCESS_FREQUENCY_MSRS;
+			ent->eax |= HV_X64_ACCESS_REENLIGHTENMENT;
+
+			ent->ebx |= HV_X64_POST_MESSAGES;
+			ent->ebx |= HV_X64_SIGNAL_EVENTS;
+
+			ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE;
+			ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
+
+			/*
+			 * Direct Synthetic timers only make sense with in-kernel
+			 * LAPIC
+			 */
+			if (lapic_in_kernel(vcpu))
+				ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE;
+
+			break;
+
+		case HYPERV_CPUID_ENLIGHTMENT_INFO:
+			ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
+			ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
+			ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
+			ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
+			ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED;
+			if (evmcs_ver)
+				ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
+			if (!cpu_smt_possible())
+				ent->eax |= HV_X64_NO_NONARCH_CORESHARING;
+			/*
+			 * Default number of spinlock retry attempts, matches
+			 * HyperV 2016.
+			 */
+			ent->ebx = 0x00000FFF;
+
+			break;
+
+		case HYPERV_CPUID_IMPLEMENT_LIMITS:
+			/* Maximum number of virtual processors */
+			ent->eax = KVM_MAX_VCPUS;
+			/*
+			 * Maximum number of logical processors, matches
+			 * HyperV 2016.
+			 */
+			ent->ebx = 64;
+
+			break;
+
+		case HYPERV_CPUID_NESTED_FEATURES:
+			ent->eax = evmcs_ver;
+
+			break;
+
+		default:
+			break;
+		}
+	}
+
+	if (copy_to_user(entries, cpuid_entries,
+			 nent * sizeof(struct kvm_cpuid_entry2)))
+		return -EFAULT;
+
+	return 0;
+}
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index d6aa969..757cb57 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * KVM Microsoft Hyper-V emulation
  *
@@ -15,15 +16,13 @@
  *   Amit Shah    <amit.shah@qumranet.com>
  *   Ben-Ami Yassour <benami@il.ibm.com>
  *   Andrey Smetanin <asmetanin@virtuozzo.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #ifndef __ARCH_X86_KVM_HYPERV_H__
 #define __ARCH_X86_KVM_HYPERV_H__
 
+#include <linux/kvm_host.h>
+
 static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu)
 {
 	return &vcpu->arch.hyperv;
@@ -62,6 +61,10 @@
 void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
 
+bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu);
+bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
+			    struct hv_vp_assist_page *assist_page);
+
 static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu,
 							int timer_index)
 {
@@ -91,5 +94,7 @@
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
 int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args);
+int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
+				struct kvm_cpuid_entry2 __user *entries);
 
 #endif
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index af19289..4a6dc54 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -653,7 +653,7 @@
 	pid_t pid_nr;
 	int ret;
 
-	pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL);
+	pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL_ACCOUNT);
 	if (!pit)
 		return NULL;
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index bdcd413..8b38bb4 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -583,7 +583,7 @@
 	struct kvm_pic *s;
 	int ret;
 
-	s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL);
+	s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL_ACCOUNT);
 	if (!s)
 		return -ENOMEM;
 	spin_lock_init(&s->lock);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 4e822ad..d859ae8 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -45,11 +45,6 @@
 #include "lapic.h"
 #include "irq.h"
 
-#if 0
-#define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg)
-#else
-#define ioapic_debug(fmt, arg...)
-#endif
 static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
 		bool line_status);
 
@@ -294,7 +289,6 @@
 	default:
 		index = (ioapic->ioregsel - 0x10) >> 1;
 
-		ioapic_debug("change redir index %x val %x\n", index, val);
 		if (index >= IOAPIC_NUM_PINS)
 			return;
 		e = &ioapic->redirtbl[index];
@@ -343,12 +337,6 @@
 	    entry->fields.remote_irr))
 		return -1;
 
-	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
-		     "vector=%x trig_mode=%x\n",
-		     entry->fields.dest_id, entry->fields.dest_mode,
-		     entry->fields.delivery_mode, entry->fields.vector,
-		     entry->fields.trig_mode);
-
 	irqe.dest_id = entry->fields.dest_id;
 	irqe.vector = entry->fields.vector;
 	irqe.dest_mode = entry->fields.dest_mode;
@@ -515,7 +503,6 @@
 	if (!ioapic_in_range(ioapic, addr))
 		return -EOPNOTSUPP;
 
-	ioapic_debug("addr %lx\n", (unsigned long)addr);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
 	addr &= 0xff;
@@ -558,8 +545,6 @@
 	if (!ioapic_in_range(ioapic, addr))
 		return -EOPNOTSUPP;
 
-	ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
-		     (void*)addr, len, val);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
 	switch (len) {
@@ -622,7 +607,7 @@
 	struct kvm_ioapic *ioapic;
 	int ret;
 
-	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
+	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL_ACCOUNT);
 	if (!ioapic)
 		return -ENOMEM;
 	spin_lock_init(&ioapic->lock);
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index faa2648..e330e7d 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -1,23 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * irq.c: API for in kernel interrupt controller
  * Copyright (c) 2007, Intel Corporation.
  * Copyright 2009 Red Hat, Inc. and/or its affiliates.
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
  * Authors:
  *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
- *
  */
 
 #include <linux/export.h>
@@ -172,3 +160,10 @@
 	__kvm_migrate_apic_timer(vcpu);
 	__kvm_migrate_pit_timer(vcpu);
 }
+
+bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
+{
+	bool resample = args->flags & KVM_IRQFD_FLAG_RESAMPLE;
+
+	return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm);
+}
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index d5005cc..7c6233d 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * irq.h: in kernel interrupt controller related definitions
  * Copyright (c) 2007, Intel Corporation.
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
  * Authors:
  *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
- *
  */
 
 #ifndef __IRQ_H
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 3cc3b2d..8ecd48d 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * irq_comm.c: Common API for in kernel interrupt controller
  * Copyright (c) 2007, Intel Corporation.
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
  * Authors:
  *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
  *
@@ -86,7 +75,7 @@
 			if (r < 0)
 				r = 0;
 			r += kvm_apic_set_irq(vcpu, irq, dest_map);
-		} else if (kvm_lapic_enabled(vcpu)) {
+		} else if (kvm_apic_sw_enabled(vcpu->arch.apic)) {
 			if (!kvm_vector_hashing_enabled()) {
 				if (!lowest)
 					lowest = vcpu;
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 9619dcc..1cc6c47 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -2,11 +2,41 @@
 #ifndef ASM_KVM_CACHE_REGS_H
 #define ASM_KVM_CACHE_REGS_H
 
+#include <linux/kvm_host.h>
+
 #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
 #define KVM_POSSIBLE_CR4_GUEST_BITS				  \
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
 	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
 
+#define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
+static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
+{									      \
+	return vcpu->arch.regs[VCPU_REGS_##uname];			      \
+}									      \
+static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu,	      \
+						unsigned long val)	      \
+{									      \
+	vcpu->arch.regs[VCPU_REGS_##uname] = val;			      \
+}
+BUILD_KVM_GPR_ACCESSORS(rax, RAX)
+BUILD_KVM_GPR_ACCESSORS(rbx, RBX)
+BUILD_KVM_GPR_ACCESSORS(rcx, RCX)
+BUILD_KVM_GPR_ACCESSORS(rdx, RDX)
+BUILD_KVM_GPR_ACCESSORS(rbp, RBP)
+BUILD_KVM_GPR_ACCESSORS(rsi, RSI)
+BUILD_KVM_GPR_ACCESSORS(rdi, RDI)
+#ifdef CONFIG_X86_64
+BUILD_KVM_GPR_ACCESSORS(r8,  R8)
+BUILD_KVM_GPR_ACCESSORS(r9,  R9)
+BUILD_KVM_GPR_ACCESSORS(r10, R10)
+BUILD_KVM_GPR_ACCESSORS(r11, R11)
+BUILD_KVM_GPR_ACCESSORS(r12, R12)
+BUILD_KVM_GPR_ACCESSORS(r13, R13)
+BUILD_KVM_GPR_ACCESSORS(r14, R14)
+BUILD_KVM_GPR_ACCESSORS(r15, R15)
+#endif
+
 static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
 					      enum kvm_reg reg)
 {
@@ -35,6 +65,16 @@
 	kvm_register_write(vcpu, VCPU_REGS_RIP, val);
 }
 
+static inline unsigned long kvm_rsp_read(struct kvm_vcpu *vcpu)
+{
+	return kvm_register_read(vcpu, VCPU_REGS_RSP);
+}
+
+static inline void kvm_rsp_write(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	kvm_register_write(vcpu, VCPU_REGS_RSP, val);
+}
+
 static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
 {
 	might_sleep();  /* on svm */
@@ -81,8 +121,8 @@
 
 static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
 {
-	return (kvm_register_read(vcpu, VCPU_REGS_RAX) & -1u)
-		| ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32);
+	return (kvm_rax_read(vcpu) & -1u)
+		| ((u64)(kvm_rdx_read(vcpu) & -1u) << 32);
 }
 
 static inline void enter_guest_mode(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3692de8..b29d00b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 
 /*
  * Local APIC virtualization
@@ -13,9 +14,6 @@
  *   Yaozu (Eddie) Dong <eddie.dong@intel.com>
  *
  * Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
  */
 
 #include <linux/kvm_host.h>
@@ -54,9 +52,6 @@
 #define PRIu64 "u"
 #define PRIo64 "o"
 
-/* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
-#define apic_debug(fmt, arg...) do {} while (0)
-
 /* 14 is the version for Xeon and Pentium 8.4.8*/
 #define APIC_VERSION			(0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16))
 #define LAPIC_MMIO_LENGTH		(1 << 12)
@@ -70,6 +65,14 @@
 #define APIC_BROADCAST			0xFF
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
+static bool lapic_timer_advance_dynamic __read_mostly;
+#define LAPIC_TIMER_ADVANCE_ADJUST_MIN	100	/* clock cycles */
+#define LAPIC_TIMER_ADVANCE_ADJUST_MAX	10000	/* clock cycles */
+#define LAPIC_TIMER_ADVANCE_NS_INIT	1000
+#define LAPIC_TIMER_ADVANCE_NS_MAX     5000
+/* step-by-step approximation to mitigate fluctuation */
+#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
+
 static inline int apic_test_vector(int vec, void *bitmap)
 {
 	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -83,11 +86,6 @@
 		apic_test_vector(vector, apic->regs + APIC_IRR);
 }
 
-static inline void apic_clear_vector(int vec, void *bitmap)
-{
-	clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
 static inline int __apic_test_and_set_vector(int vec, void *bitmap)
 {
 	return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -113,16 +111,22 @@
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
-static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
-{
-	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
-}
-
 static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
 {
 	return apic->vcpu->vcpu_id;
 }
 
+bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu)
+{
+	return pi_inject_timer && kvm_vcpu_apicv_active(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_can_post_timer_interrupt);
+
+static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu)
+{
+	return kvm_can_post_timer_interrupt(vcpu) && vcpu->mode == IN_GUEST_MODE;
+}
+
 static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 		u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) {
 	switch (map->mode) {
@@ -133,6 +137,7 @@
 		if (offset <= max_apic_id) {
 			u8 cluster_size = min(max_apic_id - offset + 1, 16U);
 
+			offset = array_index_nospec(offset, map->max_apic_id + 1);
 			*cluster = &map->phys_map[offset];
 			*mask = dest_id & (0xffff >> (16 - cluster_size));
 		} else {
@@ -176,7 +181,8 @@
 			max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic));
 
 	new = kvzalloc(sizeof(struct kvm_apic_map) +
-	                   sizeof(struct kvm_lapic *) * ((u64)max_id + 1), GFP_KERNEL);
+	                   sizeof(struct kvm_lapic *) * ((u64)max_id + 1),
+			   GFP_KERNEL_ACCOUNT);
 
 	if (!new)
 		goto out;
@@ -208,6 +214,9 @@
 		if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id])
 			new->phys_map[xapic_id] = apic;
 
+		if (!kvm_apic_sw_enabled(apic))
+			continue;
+
 		ldr = kvm_lapic_get_reg(apic, APIC_LDR);
 
 		if (apic_x2apic_mode(apic)) {
@@ -246,11 +255,12 @@
 
 	if (enabled != apic->sw_enabled) {
 		apic->sw_enabled = enabled;
-		if (enabled) {
+		if (enabled)
 			static_key_slow_dec_deferred(&apic_sw_disabled);
-			recalculate_apic_map(apic->vcpu->kvm);
-		} else
+		else
 			static_key_slow_inc(&apic_sw_disabled.key);
+
+		recalculate_apic_map(apic->vcpu->kvm);
 	}
 }
 
@@ -440,12 +450,12 @@
 
 	if (unlikely(vcpu->arch.apicv_active)) {
 		/* need to update RVI */
-		apic_clear_vector(vec, apic->regs + APIC_IRR);
+		kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
 		kvm_x86_ops->hwapic_irr_update(vcpu,
 				apic_find_highest_irr(apic));
 	} else {
 		apic->irr_pending = false;
-		apic_clear_vector(vec, apic->regs + APIC_IRR);
+		kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
 		if (apic_search_irr(apic) != -1)
 			apic->irr_pending = true;
 	}
@@ -628,7 +638,7 @@
 {
 	u8 val;
 	if (pv_eoi_get_user(vcpu, &val) < 0)
-		apic_debug("Can't read EOI MSR value: 0x%llx\n",
+		printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n",
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
 	return val & 0x1;
 }
@@ -636,7 +646,7 @@
 static void pv_eoi_set_pending(struct kvm_vcpu *vcpu)
 {
 	if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) {
-		apic_debug("Can't set EOI MSR value: 0x%llx\n",
+		printk(KERN_WARNING "Can't set EOI MSR value: 0x%llx\n",
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
 		return;
 	}
@@ -646,7 +656,7 @@
 static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 {
 	if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) {
-		apic_debug("Can't clear EOI MSR value: 0x%llx\n",
+		printk(KERN_WARNING "Can't clear EOI MSR value: 0x%llx\n",
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
 		return;
 	}
@@ -680,9 +690,6 @@
 	else
 		ppr = isrv & 0xf0;
 
-	apic_debug("vlapic %p, ppr 0x%x, isr 0x%x, isrv 0x%x",
-		   apic, ppr, isr, isrv);
-
 	*new_ppr = ppr;
 	if (old_ppr != ppr)
 		kvm_lapic_set_reg(apic, APIC_PROCPRI, ppr);
@@ -759,8 +766,6 @@
 		return ((logical_id >> 4) == (mda >> 4))
 		       && (logical_id & mda & 0xf) != 0;
 	default:
-		apic_debug("Bad DFR vcpu %d: %08x\n",
-			   apic->vcpu->vcpu_id, kvm_lapic_get_reg(apic, APIC_DFR));
 		return false;
 	}
 }
@@ -799,10 +804,6 @@
 	struct kvm_lapic *target = vcpu->arch.apic;
 	u32 mda = kvm_apic_mda(vcpu, dest, source, target);
 
-	apic_debug("target %p, source %p, dest 0x%x, "
-		   "dest_mode 0x%x, short_hand 0x%x\n",
-		   target, source, dest, dest_mode, short_hand);
-
 	ASSERT(target);
 	switch (short_hand) {
 	case APIC_DEST_NOSHORT:
@@ -817,8 +818,6 @@
 	case APIC_DEST_ALLBUT:
 		return target != source;
 	default:
-		apic_debug("kvm: apic: Bad dest shorthand value %x\n",
-			   short_hand);
 		return false;
 	}
 }
@@ -896,7 +895,8 @@
 		if (irq->dest_id > map->max_apic_id) {
 			*bitmap = 0;
 		} else {
-			*dst = &map->phys_map[irq->dest_id];
+			u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1);
+			*dst = &map->phys_map[dest_id];
 			*bitmap = 1;
 		}
 		return true;
@@ -960,14 +960,14 @@
 	map = rcu_dereference(kvm->arch.apic_map);
 
 	ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dst, &bitmap);
-	if (ret)
+	if (ret) {
+		*r = 0;
 		for_each_set_bit(i, &bitmap, 16) {
 			if (!dst[i])
 				continue;
-			if (*r < 0)
-				*r = 0;
 			*r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
 		}
+	}
 
 	rcu_read_unlock();
 	return ret;
@@ -1031,6 +1031,7 @@
 	switch (delivery_mode) {
 	case APIC_DM_LOWEST:
 		vcpu->arch.apic_arb_prio++;
+		/* fall through */
 	case APIC_DM_FIXED:
 		if (unlikely(trig_mode && !level))
 			break;
@@ -1048,9 +1049,11 @@
 
 		if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) {
 			if (trig_mode)
-				kvm_lapic_set_vector(vector, apic->regs + APIC_TMR);
+				kvm_lapic_set_vector(vector,
+						     apic->regs + APIC_TMR);
 			else
-				apic_clear_vector(vector, apic->regs + APIC_TMR);
+				kvm_lapic_clear_vector(vector,
+						       apic->regs + APIC_TMR);
 		}
 
 		if (vcpu->arch.apicv_active)
@@ -1092,15 +1095,10 @@
 			smp_wmb();
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
-		} else {
-			apic_debug("Ignoring de-assert INIT to vcpu %d\n",
-				   vcpu->vcpu_id);
 		}
 		break;
 
 	case APIC_DM_STARTUP:
-		apic_debug("SIPI to vcpu %d vector 0x%02x\n",
-			   vcpu->vcpu_id, vector);
 		result = 1;
 		apic->sipi_vector = vector;
 		/* make sure sipi_vector is visible for the receiver */
@@ -1198,10 +1196,8 @@
 }
 EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated);
 
-static void apic_send_ipi(struct kvm_lapic *apic)
+static void apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high)
 {
-	u32 icr_low = kvm_lapic_get_reg(apic, APIC_ICR);
-	u32 icr_high = kvm_lapic_get_reg(apic, APIC_ICR2);
 	struct kvm_lapic_irq irq;
 
 	irq.vector = icr_low & APIC_VECTOR_MASK;
@@ -1218,14 +1214,6 @@
 
 	trace_kvm_apic_ipi(icr_low, irq.dest_id);
 
-	apic_debug("icr_high 0x%x, icr_low 0x%x, "
-		   "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, "
-		   "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x, "
-		   "msi_redir_hint 0x%x\n",
-		   icr_high, icr_low, irq.shorthand, irq.dest_id,
-		   irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
-		   irq.vector, irq.msi_redir_hint);
-
 	kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL);
 }
 
@@ -1279,7 +1267,6 @@
 
 	switch (offset) {
 	case APIC_ARBPRI:
-		apic_debug("Access APIC ARBPRI register which is for P6\n");
 		break;
 
 	case APIC_TMCCT:	/* Timer CCR */
@@ -1308,25 +1295,46 @@
 	return container_of(dev, struct kvm_lapic, dev);
 }
 
+#define APIC_REG_MASK(reg)	(1ull << ((reg) >> 4))
+#define APIC_REGS_MASK(first, count) \
+	(APIC_REG_MASK(first) * ((1ull << (count)) - 1))
+
 int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 		void *data)
 {
 	unsigned char alignment = offset & 0xf;
 	u32 result;
 	/* this bitmask has a bit cleared for each reserved register */
-	static const u64 rmask = 0x43ff01ffffffe70cULL;
+	u64 valid_reg_mask =
+		APIC_REG_MASK(APIC_ID) |
+		APIC_REG_MASK(APIC_LVR) |
+		APIC_REG_MASK(APIC_TASKPRI) |
+		APIC_REG_MASK(APIC_PROCPRI) |
+		APIC_REG_MASK(APIC_LDR) |
+		APIC_REG_MASK(APIC_DFR) |
+		APIC_REG_MASK(APIC_SPIV) |
+		APIC_REGS_MASK(APIC_ISR, APIC_ISR_NR) |
+		APIC_REGS_MASK(APIC_TMR, APIC_ISR_NR) |
+		APIC_REGS_MASK(APIC_IRR, APIC_ISR_NR) |
+		APIC_REG_MASK(APIC_ESR) |
+		APIC_REG_MASK(APIC_ICR) |
+		APIC_REG_MASK(APIC_ICR2) |
+		APIC_REG_MASK(APIC_LVTT) |
+		APIC_REG_MASK(APIC_LVTTHMR) |
+		APIC_REG_MASK(APIC_LVTPC) |
+		APIC_REG_MASK(APIC_LVT0) |
+		APIC_REG_MASK(APIC_LVT1) |
+		APIC_REG_MASK(APIC_LVTERR) |
+		APIC_REG_MASK(APIC_TMICT) |
+		APIC_REG_MASK(APIC_TMCCT) |
+		APIC_REG_MASK(APIC_TDCR);
 
-	if ((alignment + len) > 4) {
-		apic_debug("KVM_APIC_READ: alignment error %x %d\n",
-			   offset, len);
-		return 1;
-	}
+	/* ARBPRI is not valid on x2APIC */
+	if (!apic_x2apic_mode(apic))
+		valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI);
 
-	if (offset > 0x3f0 || !(rmask & (1ULL << (offset >> 4)))) {
-		apic_debug("KVM_APIC_READ: read reserved register %x\n",
-			   offset);
+	if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset)))
 		return 1;
-	}
 
 	result = __apic_read(apic, offset & ~0xf);
 
@@ -1384,9 +1392,6 @@
 	tmp1 = tdcr & 0xf;
 	tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1;
 	apic->divide_count = 0x1 << (tmp2 & 0x7);
-
-	apic_debug("timer divide count is 0x%x\n",
-				   apic->divide_count);
 }
 
 static void limit_periodic_timer_frequency(struct kvm_lapic *apic)
@@ -1428,29 +1433,6 @@
 	}
 }
 
-static void apic_timer_expired(struct kvm_lapic *apic)
-{
-	struct kvm_vcpu *vcpu = apic->vcpu;
-	struct swait_queue_head *q = &vcpu->wq;
-	struct kvm_timer *ktimer = &apic->lapic_timer;
-
-	if (atomic_read(&apic->lapic_timer.pending))
-		return;
-
-	atomic_inc(&apic->lapic_timer.pending);
-	kvm_set_pending_timer(vcpu);
-
-	/*
-	 * For x86, the atomic_inc() is serialized, thus
-	 * using swait_active() is safe.
-	 */
-	if (swait_active(q))
-		swake_up_one(q);
-
-	if (apic_lvtt_tscdeadline(apic))
-		ktimer->expired_tscdeadline = ktimer->tscdeadline;
-}
-
 /*
  * On APICv, this test will cause a busy wait
  * during a higher-priority task.
@@ -1474,34 +1456,121 @@
 	return false;
 }
 
-void wait_lapic_expire(struct kvm_vcpu *vcpu)
+static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles)
+{
+	u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+
+	/*
+	 * If the guest TSC is running at a different ratio than the host, then
+	 * convert the delay to nanoseconds to achieve an accurate delay.  Note
+	 * that __delay() uses delay_tsc whenever the hardware has TSC, thus
+	 * always for VMX enabled hardware.
+	 */
+	if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) {
+		__delay(min(guest_cycles,
+			nsec_to_cycles(vcpu, timer_advance_ns)));
+	} else {
+		u64 delay_ns = guest_cycles * 1000000ULL;
+		do_div(delay_ns, vcpu->arch.virtual_tsc_khz);
+		ndelay(min_t(u32, delay_ns, timer_advance_ns));
+	}
+}
+
+static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu,
+					      s64 advance_expire_delta)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns;
+	u64 ns;
+
+	/* Do not adjust for tiny fluctuations or large random spikes. */
+	if (abs(advance_expire_delta) > LAPIC_TIMER_ADVANCE_ADJUST_MAX ||
+	    abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_MIN)
+		return;
+
+	/* too early */
+	if (advance_expire_delta < 0) {
+		ns = -advance_expire_delta * 1000000ULL;
+		do_div(ns, vcpu->arch.virtual_tsc_khz);
+		timer_advance_ns -= ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP;
+	} else {
+	/* too late */
+		ns = advance_expire_delta * 1000000ULL;
+		do_div(ns, vcpu->arch.virtual_tsc_khz);
+		timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP;
+	}
+
+	if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX))
+		timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
+	apic->lapic_timer.timer_advance_ns = timer_advance_ns;
+}
+
+static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u64 guest_tsc, tsc_deadline;
 
-	if (!lapic_in_kernel(vcpu))
-		return;
-
 	if (apic->lapic_timer.expired_tscdeadline == 0)
 		return;
 
-	if (!lapic_timer_int_injected(vcpu))
-		return;
-
 	tsc_deadline = apic->lapic_timer.expired_tscdeadline;
 	apic->lapic_timer.expired_tscdeadline = 0;
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
+	apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline;
 
-	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
 	if (guest_tsc < tsc_deadline)
-		__delay(min(tsc_deadline - guest_tsc,
-			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
+
+	if (lapic_timer_advance_dynamic)
+		adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
+}
+
+void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
+{
+	if (lapic_timer_int_injected(vcpu))
+		__kvm_wait_lapic_expire(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_wait_lapic_expire);
+
+static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic)
+{
+	struct kvm_timer *ktimer = &apic->lapic_timer;
+
+	kvm_apic_local_deliver(apic, APIC_LVTT);
+	if (apic_lvtt_tscdeadline(apic))
+		ktimer->tscdeadline = 0;
+	if (apic_lvtt_oneshot(apic)) {
+		ktimer->tscdeadline = 0;
+		ktimer->target_expiration = 0;
+	}
+}
+
+static void apic_timer_expired(struct kvm_lapic *apic)
+{
+	struct kvm_vcpu *vcpu = apic->vcpu;
+	struct kvm_timer *ktimer = &apic->lapic_timer;
+
+	if (atomic_read(&apic->lapic_timer.pending))
+		return;
+
+	if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use)
+		ktimer->expired_tscdeadline = ktimer->tscdeadline;
+
+	if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
+		if (apic->lapic_timer.timer_advance_ns)
+			__kvm_wait_lapic_expire(vcpu);
+		kvm_apic_inject_pending_timer_irqs(apic);
+		return;
+	}
+
+	atomic_inc(&apic->lapic_timer.pending);
+	kvm_set_pending_timer(vcpu);
 }
 
 static void start_sw_tscdeadline(struct kvm_lapic *apic)
 {
-	u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
+	struct kvm_timer *ktimer = &apic->lapic_timer;
+	u64 guest_tsc, tscdeadline = ktimer->tscdeadline;
 	u64 ns = 0;
 	ktime_t expire;
 	struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1516,13 +1585,15 @@
 
 	now = ktime_get();
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-	if (likely(tscdeadline > guest_tsc)) {
-		ns = (tscdeadline - guest_tsc) * 1000000ULL;
-		do_div(ns, this_tsc_khz);
+
+	ns = (tscdeadline - guest_tsc) * 1000000ULL;
+	do_div(ns, this_tsc_khz);
+
+	if (likely(tscdeadline > guest_tsc) &&
+	    likely(ns > apic->lapic_timer.timer_advance_ns)) {
 		expire = ktime_add_ns(now, ns);
-		expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
-		hrtimer_start(&apic->lapic_timer.timer,
-				expire, HRTIMER_MODE_ABS_PINNED);
+		expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
+		hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD);
 	} else
 		apic_timer_expired(apic);
 
@@ -1569,16 +1640,6 @@
 
 	limit_periodic_timer_frequency(apic);
 
-	apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
-		   PRIx64 ", "
-		   "timer initial count 0x%x, period %lldns, "
-		   "expire @ 0x%016" PRIx64 ".\n", __func__,
-		   APIC_BUS_CYCLE_NS, ktime_to_ns(now),
-		   kvm_lapic_get_reg(apic, APIC_TMICT),
-		   apic->lapic_timer.period,
-		   ktime_to_ns(ktime_add_ns(now,
-				apic->lapic_timer.period)));
-
 	apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
 		nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
 	apic->lapic_timer.target_expiration = ktime_add_ns(now, apic->lapic_timer.period);
@@ -1624,7 +1685,7 @@
 
 	hrtimer_start(&apic->lapic_timer.timer,
 		apic->lapic_timer.target_expiration,
-		HRTIMER_MODE_ABS_PINNED);
+		HRTIMER_MODE_ABS);
 }
 
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
@@ -1647,37 +1708,42 @@
 static bool start_hv_timer(struct kvm_lapic *apic)
 {
 	struct kvm_timer *ktimer = &apic->lapic_timer;
-	int r;
+	struct kvm_vcpu *vcpu = apic->vcpu;
+	bool expired;
 
 	WARN_ON(preemptible());
 	if (!kvm_x86_ops->set_hv_timer)
 		return false;
 
-	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
-		return false;
-
 	if (!ktimer->tscdeadline)
 		return false;
 
-	r = kvm_x86_ops->set_hv_timer(apic->vcpu, ktimer->tscdeadline);
-	if (r < 0)
+	if (kvm_x86_ops->set_hv_timer(vcpu, ktimer->tscdeadline, &expired))
 		return false;
 
 	ktimer->hv_timer_in_use = true;
 	hrtimer_cancel(&ktimer->timer);
 
 	/*
-	 * Also recheck ktimer->pending, in case the sw timer triggered in
-	 * the window.  For periodic timer, leave the hv timer running for
-	 * simplicity, and the deadline will be recomputed on the next vmexit.
+	 * To simplify handling the periodic timer, leave the hv timer running
+	 * even if the deadline timer has expired, i.e. rely on the resulting
+	 * VM-Exit to recompute the periodic timer's target expiration.
 	 */
-	if (!apic_lvtt_period(apic) && (r || atomic_read(&ktimer->pending))) {
-		if (r)
+	if (!apic_lvtt_period(apic)) {
+		/*
+		 * Cancel the hv timer if the sw timer fired while the hv timer
+		 * was being programmed, or if the hv timer itself expired.
+		 */
+		if (atomic_read(&ktimer->pending)) {
+			cancel_hv_timer(apic);
+		} else if (expired) {
 			apic_timer_expired(apic);
-		return false;
+			cancel_hv_timer(apic);
+		}
 	}
 
-	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, true);
+	trace_kvm_hv_timer_state(vcpu->vcpu_id, ktimer->hv_timer_in_use);
+
 	return true;
 }
 
@@ -1701,8 +1767,13 @@
 static void restart_apic_timer(struct kvm_lapic *apic)
 {
 	preempt_disable();
+
+	if (!apic_lvtt_period(apic) && atomic_read(&apic->lapic_timer.pending))
+		goto out;
+
 	if (!start_hv_timer(apic))
 		start_sw_timer(apic);
+out:
 	preempt_enable();
 }
 
@@ -1771,8 +1842,6 @@
 	if (apic->lvt0_in_nmi_mode != lvt0_in_nmi_mode) {
 		apic->lvt0_in_nmi_mode = lvt0_in_nmi_mode;
 		if (lvt0_in_nmi_mode) {
-			apic_debug("Receive NMI setting on APIC_LVT0 "
-				   "for cpu %d\n", apic->vcpu->vcpu_id);
 			atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
 		} else
 			atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
@@ -1840,8 +1909,9 @@
 	}
 	case APIC_ICR:
 		/* No delay here, so we always clear the pending bit */
-		kvm_lapic_set_reg(apic, APIC_ICR, val & ~(1 << 12));
-		apic_send_ipi(apic);
+		val &= ~(1 << 12);
+		apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2));
+		kvm_lapic_set_reg(apic, APIC_ICR, val);
 		break;
 
 	case APIC_ICR2:
@@ -1852,6 +1922,7 @@
 
 	case APIC_LVT0:
 		apic_manage_nmi_watchdog(apic, val);
+		/* fall through */
 	case APIC_LVTTHMR:
 	case APIC_LVTPC:
 	case APIC_LVT1:
@@ -1885,8 +1956,6 @@
 	case APIC_TDCR: {
 		uint32_t old_divisor = apic->divide_count;
 
-		if (val & 4)
-			apic_debug("KVM_WRITE:TDCR %x\n", val);
 		kvm_lapic_set_reg(apic, APIC_TDCR, val);
 		update_divide_count(apic);
 		if (apic->divide_count != old_divisor &&
@@ -1898,10 +1967,8 @@
 		break;
 	}
 	case APIC_ESR:
-		if (apic_x2apic_mode(apic) && val != 0) {
-			apic_debug("KVM_WRITE:ESR not zero %x\n", val);
+		if (apic_x2apic_mode(apic) && val != 0)
 			ret = 1;
-		}
 		break;
 
 	case APIC_SELF_IPI:
@@ -1914,8 +1981,7 @@
 		ret = 1;
 		break;
 	}
-	if (ret)
-		apic_debug("Local APIC Write to read-only register %x\n", reg);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_reg_write);
@@ -1943,19 +2009,11 @@
 	 * 32/64/128 bits registers must be accessed thru 32 bits.
 	 * Refer SDM 8.4.1
 	 */
-	if (len != 4 || (offset & 0xf)) {
-		/* Don't shout loud, $infamous_os would cause only noise. */
-		apic_debug("apic write: bad size=%d %lx\n", len, (long)address);
+	if (len != 4 || (offset & 0xf))
 		return 0;
-	}
 
 	val = *(u32*)data;
 
-	/* too common printing */
-	if (offset != APIC_EOI)
-		apic_debug("%s: offset 0x%x with length 0x%x, and value is "
-			   "0x%x\n", __func__, offset, len, val);
-
 	kvm_lapic_reg_write(apic, offset & 0xff0, val);
 
 	return 0;
@@ -2088,11 +2146,6 @@
 	if ((value & MSR_IA32_APICBASE_ENABLE) &&
 	     apic->base_address != APIC_DEFAULT_PHYS_BASE)
 		pr_warn_once("APIC base relocation is unsupported by KVM");
-
-	/* with FSB delivery interrupt, we can restart APIC functionality */
-	apic_debug("apic base msr is 0x%016" PRIx64 ", and base address is "
-		   "0x%lx.\n", apic->vcpu->arch.apic_base, apic->base_address);
-
 }
 
 void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -2103,8 +2156,6 @@
 	if (!apic)
 		return;
 
-	apic_debug("%s\n", __func__);
-
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
@@ -2157,11 +2208,6 @@
 
 	vcpu->arch.apic_arb_prio = 0;
 	vcpu->arch.apic_attention = 0;
-
-	apic_debug("%s: vcpu=%p, id=0x%x, base_msr="
-		   "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
-		   vcpu, kvm_lapic_get_reg(apic, APIC_ID),
-		   vcpu->arch.apic_base, apic->base_address);
 }
 
 /*
@@ -2228,20 +2274,19 @@
 		return HRTIMER_NORESTART;
 }
 
-int kvm_create_lapic(struct kvm_vcpu *vcpu)
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 {
 	struct kvm_lapic *apic;
 
 	ASSERT(vcpu != NULL);
-	apic_debug("apic_init %d\n", vcpu->vcpu_id);
 
-	apic = kzalloc(sizeof(*apic), GFP_KERNEL);
+	apic = kzalloc(sizeof(*apic), GFP_KERNEL_ACCOUNT);
 	if (!apic)
 		goto nomem;
 
 	vcpu->arch.apic = apic;
 
-	apic->regs = (void *)get_zeroed_page(GFP_KERNEL);
+	apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
 	if (!apic->regs) {
 		printk(KERN_ERR "malloc apic regs error for vcpu %x\n",
 		       vcpu->vcpu_id);
@@ -2250,12 +2295,19 @@
 	apic->vcpu = vcpu;
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_PINNED);
+		     HRTIMER_MODE_ABS_HARD);
 	apic->lapic_timer.timer.function = apic_timer_fn;
+	if (timer_advance_ns == -1) {
+		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
+		lapic_timer_advance_dynamic = true;
+	} else {
+		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
+		lapic_timer_advance_dynamic = false;
+	}
 
 	/*
 	 * APIC is created enabled. This will prevent kvm_lapic_set_base from
-	 * thinking that APIC satet has changed.
+	 * thinking that APIC state has changed.
 	 */
 	vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
 	static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
@@ -2264,6 +2316,7 @@
 	return 0;
 nomem_free_apic:
 	kfree(apic);
+	vcpu->arch.apic = NULL;
 nomem:
 	return -ENOMEM;
 }
@@ -2273,7 +2326,7 @@
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (!apic_enabled(apic))
+	if (!kvm_apic_hw_enabled(apic))
 		return -1;
 
 	__apic_update_ppr(apic, &ppr);
@@ -2298,13 +2351,7 @@
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	if (atomic_read(&apic->lapic_timer.pending) > 0) {
-		kvm_apic_local_deliver(apic, APIC_LVTT);
-		if (apic_lvtt_tscdeadline(apic))
-			apic->lapic_timer.tscdeadline = 0;
-		if (apic_lvtt_oneshot(apic)) {
-			apic->lapic_timer.tscdeadline = 0;
-			apic->lapic_timer.target_expiration = 0;
-		}
+		kvm_apic_inject_pending_timer_irqs(apic);
 		atomic_set(&apic->lapic_timer.pending, 0);
 	}
 }
@@ -2391,7 +2438,7 @@
 	r = kvm_apic_state_fixup(vcpu, s, true);
 	if (r)
 		return r;
-	memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
+	memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s));
 
 	recalculate_apic_map(vcpu->kvm);
 	kvm_apic_set_version(vcpu);
@@ -2426,12 +2473,13 @@
 {
 	struct hrtimer *timer;
 
-	if (!lapic_in_kernel(vcpu))
+	if (!lapic_in_kernel(vcpu) ||
+		kvm_can_post_timer_interrupt(vcpu))
 		return;
 
 	timer = &vcpu->arch.apic->lapic_timer.timer;
 	if (hrtimer_cancel(timer))
-		hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS_HARD);
 }
 
 /*
@@ -2579,11 +2627,8 @@
 	if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic))
 		return 1;
 
-	if (reg == APIC_DFR || reg == APIC_ICR2) {
-		apic_debug("KVM_APIC_READ: read x2apic reserved register %x\n",
-			   reg);
+	if (reg == APIC_DFR || reg == APIC_ICR2)
 		return 1;
-	}
 
 	if (kvm_lapic_reg_read(apic, reg, 4, &low))
 		return 1;
@@ -2626,17 +2671,25 @@
 	return 0;
 }
 
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
+int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len)
 {
 	u64 addr = data & ~KVM_MSR_ENABLED;
+	struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data;
+	unsigned long new_len;
+
 	if (!IS_ALIGNED(addr, 4))
 		return 1;
 
 	vcpu->arch.pv_eoi.msr_val = data;
 	if (!pv_eoi_enabled(vcpu))
 		return 0;
-	return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
-					 addr, sizeof(u8));
+
+	if (addr == ghc->gpa && len <= ghc->len)
+		new_len = ghc->len;
+	else
+		new_len = len;
+
+	return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len);
 }
 
 void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
@@ -2649,11 +2702,14 @@
 		return;
 
 	/*
-	 * INITs are latched while in SMM.  Because an SMM CPU cannot
-	 * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs
-	 * and delay processing of INIT until the next RSM.
+	 * INITs are latched while CPU is in specific states
+	 * (SMM, VMX non-root mode, SVM with GIF=0).
+	 * Because a CPU cannot be in these states immediately
+	 * after it has processed an INIT signal (and thus in
+	 * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs
+	 * and leave the INIT pending.
 	 */
-	if (is_smm(vcpu)) {
+	if (is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu)) {
 		WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
 		if (test_bit(KVM_APIC_SIPI, &apic->pending_events))
 			clear_bit(KVM_APIC_SIPI, &apic->pending_events);
@@ -2673,8 +2729,6 @@
 		/* evaluate pending_events before reading the vector */
 		smp_rmb();
 		sipi_vector = apic->sipi_vector;
-		apic_debug("vcpu %d received sipi with vector # %x\n",
-			 vcpu->vcpu_id, sipi_vector);
 		kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector);
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 	}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index ed0ed39..1f50148 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -31,6 +31,8 @@
 	u32 timer_mode_mask;
 	u64 tscdeadline;
 	u64 expired_tscdeadline;
+	u32 timer_advance_ns;
+	s64 advance_expire_delta;
 	atomic_t pending;			/* accumulated triggered timers */
 	bool hv_timer_in_use;
 };
@@ -62,7 +64,7 @@
 
 struct dest_map;
 
-int kvm_create_lapic(struct kvm_vcpu *vcpu);
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
 void kvm_free_lapic(struct kvm_vcpu *vcpu);
 
 int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
@@ -120,13 +122,18 @@
 	return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
 }
 
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
+int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
 void kvm_lapic_init(void);
 void kvm_lapic_exit(void);
 
 #define VEC_POS(v) ((v) & (32 - 1))
 #define REG_POS(v) (((v) >> 5) << 4)
 
+static inline void kvm_lapic_clear_vector(int vec, void *bitmap)
+{
+	clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
 static inline void kvm_lapic_set_vector(int vec, void *bitmap)
 {
 	set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -217,7 +224,7 @@
 
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
-void wait_lapic_expire(struct kvm_vcpu *vcpu);
+void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu);
 
 bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu);
@@ -228,10 +235,16 @@
 void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu);
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu);
 void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu);
+bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu);
 
 static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
 {
 	return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
 }
 
+static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
+{
+	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
+}
+
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1b82bc7..2ce9da5 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Kernel-based Virtual Machine driver for Linux
  *
@@ -12,10 +13,6 @@
  * Authors:
  *   Yaniv Kamay  <yaniv@qumranet.com>
  *   Avi Kivity   <avi@qumranet.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #include "irq.h"
@@ -40,15 +37,46 @@
 #include <linux/uaccess.h>
 #include <linux/hash.h>
 #include <linux/kern_levels.h>
+#include <linux/kthread.h>
 
 #include <asm/page.h>
 #include <asm/pat.h>
 #include <asm/cmpxchg.h>
+#include <asm/e820/api.h>
 #include <asm/io.h>
 #include <asm/vmx.h>
 #include <asm/kvm_page_track.h>
 #include "trace.h"
 
+extern bool itlb_multihit_kvm_mitigation;
+
+static int __read_mostly nx_huge_pages = -1;
+#ifdef CONFIG_PREEMPT_RT
+/* Recovery can cause latency spikes, disable it for PREEMPT_RT.  */
+static uint __read_mostly nx_huge_pages_recovery_ratio = 0;
+#else
+static uint __read_mostly nx_huge_pages_recovery_ratio = 60;
+#endif
+
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp);
+static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp);
+
+static struct kernel_param_ops nx_huge_pages_ops = {
+	.set = set_nx_huge_pages,
+	.get = param_get_bool,
+};
+
+static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = {
+	.set = set_nx_huge_pages_recovery_ratio,
+	.get = param_get_uint,
+};
+
+module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages, "bool");
+module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops,
+		&nx_huge_pages_recovery_ratio, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint");
+
 /*
  * When setting this variable to true it enables Two-Dimensional-Paging
  * where the hardware walks 2 page tables:
@@ -85,7 +113,17 @@
 #define PTE_PREFETCH_NUM		8
 
 #define PT_FIRST_AVAIL_BITS_SHIFT 10
-#define PT64_SECOND_AVAIL_BITS_SHIFT 52
+#define PT64_SECOND_AVAIL_BITS_SHIFT 54
+
+/*
+ * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
+ * Access Tracking SPTEs.
+ */
+#define SPTE_SPECIAL_MASK (3ULL << 52)
+#define SPTE_AD_ENABLED_MASK (0ULL << 52)
+#define SPTE_AD_DISABLED_MASK (1ULL << 52)
+#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52)
+#define SPTE_MMIO_MASK (3ULL << 52)
 
 #define PT64_LEVEL_BITS 9
 
@@ -109,9 +147,11 @@
 	(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
 
 
-#define PT64_BASE_ADDR_MASK __sme_clr((((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)))
-#define PT64_DIR_BASE_ADDR_MASK \
-	(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
+#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
+#define PT64_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1))
+#else
+#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#endif
 #define PT64_LVL_ADDR_MASK(level) \
 	(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
 						* PT64_LEVEL_BITS))) - 1))
@@ -140,9 +180,6 @@
 
 #include <trace/events/kvm.h>
 
-#define CREATE_TRACE_POINTS
-#include "mmutrace.h"
-
 #define SPTE_HOST_WRITEABLE	(1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
 #define SPTE_MMU_WRITEABLE	(1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
 
@@ -180,7 +217,7 @@
 
 static const union kvm_mmu_page_role mmu_base_role_mask = {
 	.cr0_wp = 1,
-	.cr4_pae = 1,
+	.gpte_is_8_bytes = 1,
 	.nxe = 1,
 	.smep_andnot_wp = 1,
 	.smap_andnot_wp = 1,
@@ -217,16 +254,16 @@
 static u64 __read_mostly shadow_dirty_mask;
 static u64 __read_mostly shadow_mmio_mask;
 static u64 __read_mostly shadow_mmio_value;
+static u64 __read_mostly shadow_mmio_access_mask;
 static u64 __read_mostly shadow_present_mask;
 static u64 __read_mostly shadow_me_mask;
 
 /*
- * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value.
- * Non-present SPTEs with shadow_acc_track_value set are in place for access
- * tracking.
+ * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK;
+ * shadow_acc_track_mask is the set of bits to be cleared in non-accessed
+ * pages.
  */
 static u64 __read_mostly shadow_acc_track_mask;
-static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK;
 
 /*
  * The mask/shift to use for saving the original R/X bits when marking the PTE
@@ -259,39 +296,106 @@
  */
 static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
 
+/*
+ * The number of non-reserved physical address bits irrespective of features
+ * that repurpose legal bits, e.g. MKTME.
+ */
+static u8 __read_mostly shadow_phys_bits;
 
 static void mmu_spte_set(u64 *sptep, u64 spte);
+static bool is_executable_pte(u64 spte);
 static union kvm_mmu_page_role
 kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu);
 
-void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value)
+#define CREATE_TRACE_POINTS
+#include "mmutrace.h"
+
+
+static inline bool kvm_available_flush_tlb_with_range(void)
 {
+	return kvm_x86_ops->tlb_remote_flush_with_range;
+}
+
+static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm,
+		struct kvm_tlb_range *range)
+{
+	int ret = -ENOTSUPP;
+
+	if (range && kvm_x86_ops->tlb_remote_flush_with_range)
+		ret = kvm_x86_ops->tlb_remote_flush_with_range(kvm, range);
+
+	if (ret)
+		kvm_flush_remote_tlbs(kvm);
+}
+
+static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
+		u64 start_gfn, u64 pages)
+{
+	struct kvm_tlb_range range;
+
+	range.start_gfn = start_gfn;
+	range.pages = pages;
+
+	kvm_flush_remote_tlbs_with_range(kvm, &range);
+}
+
+void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask)
+{
+	BUG_ON((u64)(unsigned)access_mask != access_mask);
 	BUG_ON((mmio_mask & mmio_value) != mmio_value);
-	shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK;
+	shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
 	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
+	shadow_mmio_access_mask = access_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
+static bool is_mmio_spte(u64 spte)
+{
+	return (spte & shadow_mmio_mask) == shadow_mmio_value;
+}
+
 static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
 {
 	return sp->role.ad_disabled;
 }
 
+static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * When using the EPT page-modification log, the GPAs in the log
+	 * would come from L2 rather than L1.  Therefore, we need to rely
+	 * on write protection to record dirty pages.  This also bypasses
+	 * PML, since writes now result in a vmexit.
+	 */
+	return vcpu->arch.mmu == &vcpu->arch.guest_mmu;
+}
+
 static inline bool spte_ad_enabled(u64 spte)
 {
-	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
-	return !(spte & shadow_acc_track_value);
+	MMU_WARN_ON(is_mmio_spte(spte));
+	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK;
+}
+
+static inline bool spte_ad_need_write_protect(u64 spte)
+{
+	MMU_WARN_ON(is_mmio_spte(spte));
+	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK;
+}
+
+static bool is_nx_huge_page_enabled(void)
+{
+	return READ_ONCE(nx_huge_pages);
 }
 
 static inline u64 spte_shadow_accessed_mask(u64 spte)
 {
-	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
+	MMU_WARN_ON(is_mmio_spte(spte));
 	return spte_ad_enabled(spte) ? shadow_accessed_mask : 0;
 }
 
 static inline u64 spte_shadow_dirty_mask(u64 spte)
 {
-	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
+	MMU_WARN_ON(is_mmio_spte(spte));
 	return spte_ad_enabled(spte) ? shadow_dirty_mask : 0;
 }
 
@@ -301,57 +405,60 @@
 }
 
 /*
- * the low bit of the generation number is always presumed to be zero.
- * This disables mmio caching during memslot updates.  The concept is
- * similar to a seqcount but instead of retrying the access we just punt
- * and ignore the cache.
+ * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of
+ * the memslots generation and is derived as follows:
  *
- * spte bits 3-11 are used as bits 1-9 of the generation number,
- * the bits 52-61 are used as bits 10-19 of the generation number.
+ * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11
+ * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61
+ *
+ * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
+ * the MMIO generation number, as doing so would require stealing a bit from
+ * the "real" generation number and thus effectively halve the maximum number
+ * of MMIO generations that can be handled before encountering a wrap (which
+ * requires a full MMU zap).  The flag is instead explicitly queried when
+ * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_LOW_SHIFT		2
-#define MMIO_SPTE_GEN_HIGH_SHIFT	52
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(18, 0)
 
-#define MMIO_GEN_SHIFT			20
-#define MMIO_GEN_LOW_SHIFT		10
-#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 2)
-#define MMIO_GEN_MASK			((1 << MMIO_GEN_SHIFT) - 1)
+#define MMIO_SPTE_GEN_LOW_START		3
+#define MMIO_SPTE_GEN_LOW_END		11
+#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
+						    MMIO_SPTE_GEN_LOW_START)
 
-static u64 generation_mmio_spte_mask(unsigned int gen)
+#define MMIO_SPTE_GEN_HIGH_START	52
+#define MMIO_SPTE_GEN_HIGH_END		61
+#define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
+						    MMIO_SPTE_GEN_HIGH_START)
+static u64 generation_mmio_spte_mask(u64 gen)
 {
 	u64 mask;
 
-	WARN_ON(gen & ~MMIO_GEN_MASK);
+	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
 
-	mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT;
-	mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT;
+	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
+	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;
 	return mask;
 }
 
-static unsigned int get_mmio_spte_generation(u64 spte)
+static u64 get_mmio_spte_generation(u64 spte)
 {
-	unsigned int gen;
+	u64 gen;
 
 	spte &= ~shadow_mmio_mask;
 
-	gen = (spte >> MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_GEN_LOW_MASK;
-	gen |= (spte >> MMIO_SPTE_GEN_HIGH_SHIFT) << MMIO_GEN_LOW_SHIFT;
+	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
+	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
 	return gen;
 }
 
-static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu)
-{
-	return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK;
-}
-
 static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
 			   unsigned access)
 {
-	unsigned int gen = kvm_current_mmio_generation(vcpu);
+	u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK;
 	u64 mask = generation_mmio_spte_mask(gen);
 	u64 gpa = gfn << PAGE_SHIFT;
 
-	access &= ACC_WRITE_MASK | ACC_USER_MASK;
+	access &= shadow_mmio_access_mask;
 	mask |= shadow_mmio_value | access;
 	mask |= gpa | shadow_nonpresent_or_rsvd_mask;
 	mask |= (gpa & shadow_nonpresent_or_rsvd_mask)
@@ -361,11 +468,6 @@
 	mmu_spte_set(sptep, mask);
 }
 
-static bool is_mmio_spte(u64 spte)
-{
-	return (spte & shadow_mmio_mask) == shadow_mmio_value;
-}
-
 static gfn_t get_mmio_spte_gfn(u64 spte)
 {
 	u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
@@ -378,8 +480,7 @@
 
 static unsigned get_mmio_spte_access(u64 spte)
 {
-	u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask;
-	return (spte & ~mask) & ~PAGE_MASK;
+	return spte & shadow_mmio_access_mask;
 }
 
 static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
@@ -395,9 +496,13 @@
 
 static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 {
-	unsigned int kvm_gen, spte_gen;
+	u64 kvm_gen, spte_gen, gen;
 
-	kvm_gen = kvm_current_mmio_generation(vcpu);
+	gen = kvm_vcpu_memslots(vcpu)->generation;
+	if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS))
+		return false;
+
+	kvm_gen = gen & MMIO_SPTE_GEN_MASK;
 	spte_gen = get_mmio_spte_generation(spte);
 
 	trace_check_mmio_spte(spte, kvm_gen, spte_gen);
@@ -417,7 +522,7 @@
 {
 	BUG_ON(!dirty_mask != !accessed_mask);
 	BUG_ON(!accessed_mask && !acc_track_mask);
-	BUG_ON(acc_track_mask & shadow_acc_track_value);
+	BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK);
 
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
@@ -430,6 +535,21 @@
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
+static u8 kvm_get_shadow_phys_bits(void)
+{
+	/*
+	 * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected
+	 * in CPU detection code, but MKTME treats those reduced bits as
+	 * 'keyID' thus they are not reserved bits. Therefore for MKTME
+	 * we should still return physical address bits reported by CPUID.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_TME) ||
+	    WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008))
+		return boot_cpu_data.x86_phys_bits;
+
+	return cpuid_eax(0x80000008) & 0xff;
+}
+
 static void kvm_mmu_reset_all_pte_masks(void)
 {
 	u8 low_phys_bits;
@@ -443,20 +563,30 @@
 	shadow_present_mask = 0;
 	shadow_acc_track_mask = 0;
 
+	shadow_phys_bits = kvm_get_shadow_phys_bits();
+
 	/*
 	 * If the CPU has 46 or less physical address bits, then set an
 	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
 	 * assumed that the CPU is not vulnerable to L1TF.
+	 *
+	 * Some Intel CPUs address the L1 cache using more PA bits than are
+	 * reported by CPUID. Use the PA width of the L1 cache when possible
+	 * to achieve more effective mitigation, e.g. if system RAM overlaps
+	 * the most significant bits of legal physical address space.
 	 */
-	low_phys_bits = boot_cpu_data.x86_phys_bits;
-	if (boot_cpu_data.x86_phys_bits <
+	shadow_nonpresent_or_rsvd_mask = 0;
+	low_phys_bits = boot_cpu_data.x86_cache_bits;
+	if (boot_cpu_data.x86_cache_bits <
 	    52 - shadow_nonpresent_or_rsvd_mask_len) {
 		shadow_nonpresent_or_rsvd_mask =
-			rsvd_bits(boot_cpu_data.x86_phys_bits -
+			rsvd_bits(boot_cpu_data.x86_cache_bits -
 				  shadow_nonpresent_or_rsvd_mask_len,
-				  boot_cpu_data.x86_phys_bits - 1);
+				  boot_cpu_data.x86_cache_bits - 1);
 		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
-	}
+	} else
+		WARN_ON_ONCE(boot_cpu_has_bug(X86_BUG_L1TF));
+
 	shadow_nonpresent_or_rsvd_lower_gfn_mask =
 		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
 }
@@ -604,7 +734,7 @@
 
 /*
  * The idea using the light way get the spte on x86_32 guest is from
- * gup_get_pte(arch/x86/mm/gup.c).
+ * gup_get_pte (mm/gup.c).
  *
  * An spte tlb flush may be pending, because kvm_set_pte_rmapp
  * coalesces them and we are running out of the MMU lock.  Therefore
@@ -930,9 +1060,9 @@
 	if (cache->nobjs >= min)
 		return 0;
 	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
-		obj = kmem_cache_zalloc(base_cache, GFP_KERNEL);
+		obj = kmem_cache_zalloc(base_cache, GFP_KERNEL_ACCOUNT);
 		if (!obj)
-			return -ENOMEM;
+			return cache->nobjs >= min ? 0 : -ENOMEM;
 		cache->objects[cache->nobjs++] = obj;
 	}
 	return 0;
@@ -960,7 +1090,7 @@
 	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
 		page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
 		if (!page)
-			return -ENOMEM;
+			return cache->nobjs >= min ? 0 : -ENOMEM;
 		cache->objects[cache->nobjs++] = page;
 	}
 	return 0;
@@ -1027,10 +1157,16 @@
 
 static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn)
 {
-	if (sp->role.direct)
-		BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index));
-	else
+	if (!sp->role.direct) {
 		sp->gfns[index] = gfn;
+		return;
+	}
+
+	if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index)))
+		pr_err_ratelimited("gfn mismatch under direct page %llx "
+				   "(expected %llx, got %llx)\n",
+				   sp->gfn,
+				   kvm_mmu_page_get_gfn(sp, index), gfn);
 }
 
 /*
@@ -1089,6 +1225,17 @@
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 }
 
+static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	if (sp->lpage_disallowed)
+		return;
+
+	++kvm->stat.nx_lpage_splits;
+	list_add_tail(&sp->lpage_disallowed_link,
+		      &kvm->arch.lpage_disallowed_mmu_pages);
+	sp->lpage_disallowed = true;
+}
+
 static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	struct kvm_memslots *slots;
@@ -1106,6 +1253,13 @@
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
 
+static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	--kvm->stat.nx_lpage_splits;
+	sp->lpage_disallowed = false;
+	list_del(&sp->lpage_disallowed_link);
+}
+
 static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
 					  struct kvm_memory_slot *slot)
 {
@@ -1265,24 +1419,24 @@
 	mmu_free_pte_list_desc(desc);
 }
 
-static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
+static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
 {
 	struct pte_list_desc *desc;
 	struct pte_list_desc *prev_desc;
 	int i;
 
 	if (!rmap_head->val) {
-		printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte);
+		pr_err("%s: %p 0->BUG\n", __func__, spte);
 		BUG();
 	} else if (!(rmap_head->val & 1)) {
-		rmap_printk("pte_list_remove:  %p 1->0\n", spte);
+		rmap_printk("%s:  %p 1->0\n", __func__, spte);
 		if ((u64 *)rmap_head->val != spte) {
-			printk(KERN_ERR "pte_list_remove:  %p 1->BUG\n", spte);
+			pr_err("%s:  %p 1->BUG\n", __func__, spte);
 			BUG();
 		}
 		rmap_head->val = 0;
 	} else {
-		rmap_printk("pte_list_remove:  %p many->many\n", spte);
+		rmap_printk("%s:  %p many->many\n", __func__, spte);
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
 		prev_desc = NULL;
 		while (desc) {
@@ -1296,11 +1450,17 @@
 			prev_desc = desc;
 			desc = desc->more;
 		}
-		pr_err("pte_list_remove: %p many->many\n", spte);
+		pr_err("%s: %p many->many\n", __func__, spte);
 		BUG();
 	}
 }
 
+static void pte_list_remove(struct kvm_rmap_head *rmap_head, u64 *sptep)
+{
+	mmu_spte_clear_track_bits(sptep);
+	__pte_list_remove(sptep, rmap_head);
+}
+
 static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level,
 					   struct kvm_memory_slot *slot)
 {
@@ -1349,7 +1509,7 @@
 	sp = page_header(__pa(spte));
 	gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
 	rmap_head = gfn_to_rmap(kvm, gfn, sp);
-	pte_list_remove(spte, rmap_head);
+	__pte_list_remove(spte, rmap_head);
 }
 
 /*
@@ -1450,8 +1610,12 @@
 
 static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
 {
-	if (__drop_large_spte(vcpu->kvm, sptep))
-		kvm_flush_remote_tlbs(vcpu->kvm);
+	if (__drop_large_spte(vcpu->kvm, sptep)) {
+		struct kvm_mmu_page *sp = page_header(__pa(sptep));
+
+		kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
+			KVM_PAGES_PER_HPAGE(sp->role.level));
+	}
 }
 
 /*
@@ -1504,16 +1668,16 @@
 
 	rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep);
 
+	MMU_WARN_ON(!spte_ad_enabled(spte));
 	spte &= ~shadow_dirty_mask;
-
 	return mmu_spte_update(sptep, spte);
 }
 
-static bool wrprot_ad_disabled_spte(u64 *sptep)
+static bool spte_wrprot_for_clear_dirty(u64 *sptep)
 {
 	bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT,
 					       (unsigned long *)sptep);
-	if (was_writable)
+	if (was_writable && !spte_ad_enabled(*sptep))
 		kvm_set_pfn_dirty(spte_to_pfn(*sptep));
 
 	return was_writable;
@@ -1532,10 +1696,10 @@
 	bool flush = false;
 
 	for_each_rmap_spte(rmap_head, &iter, sptep)
-		if (spte_ad_enabled(*sptep))
-			flush |= spte_clear_dirty(sptep);
+		if (spte_ad_need_write_protect(*sptep))
+			flush |= spte_wrprot_for_clear_dirty(sptep);
 		else
-			flush |= wrprot_ad_disabled_spte(sptep);
+			flush |= spte_clear_dirty(sptep);
 
 	return flush;
 }
@@ -1546,6 +1710,11 @@
 
 	rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep);
 
+	/*
+	 * Similar to the !kvm_x86_ops->slot_disable_log_dirty case,
+	 * do not bother adding back write access to pages marked
+	 * SPTE_AD_WRPROT_ONLY_MASK.
+	 */
 	spte |= shadow_dirty_mask;
 
 	return mmu_spte_update(sptep, spte);
@@ -1685,7 +1854,7 @@
 	while ((sptep = rmap_get_first(rmap_head, &iter))) {
 		rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);
 
-		drop_spte(kvm, sptep);
+		pte_list_remove(rmap_head, sptep);
 		flush = true;
 	}
 
@@ -1721,7 +1890,7 @@
 		need_flush = 1;
 
 		if (pte_write(*ptep)) {
-			drop_spte(kvm, sptep);
+			pte_list_remove(rmap_head, sptep);
 			goto restart;
 		} else {
 			new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
@@ -1737,10 +1906,12 @@
 		}
 	}
 
-	if (need_flush)
-		kvm_flush_remote_tlbs(kvm);
+	if (need_flush && kvm_available_flush_tlb_with_range()) {
+		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+		return 0;
+	}
 
-	return 0;
+	return need_flush;
 }
 
 struct slot_rmap_walk_iterator {
@@ -1874,9 +2045,9 @@
 	return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
 }
 
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
-	kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+	return kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
 }
 
 static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
@@ -1919,7 +2090,8 @@
 	rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);
 
 	kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, 0);
-	kvm_flush_remote_tlbs(vcpu->kvm);
+	kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
+			KVM_PAGES_PER_HPAGE(sp->role.level));
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
@@ -1954,7 +2126,7 @@
  * aggregate version in order to make the slab shrinker
  * faster
  */
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
 {
 	kvm->arch.n_used_mmu_pages += nr;
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -1988,7 +2160,7 @@
 static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
 				       u64 *parent_pte)
 {
-	pte_list_remove(parent_pte, &sp->parent_ptes);
+	__pte_list_remove(parent_pte, &sp->parent_ptes);
 }
 
 static void drop_parent_pte(struct kvm_mmu_page *sp,
@@ -2009,10 +2181,11 @@
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 
 	/*
-	 * The active_mmu_pages list is the FIFO list, do not move the
-	 * page until it is zapped. kvm_zap_obsolete_pages depends on
-	 * this feature. See the comments in kvm_zap_obsolete_pages().
+	 * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
+	 * depends on valid pages being added to the head of the list.  See
+	 * comments in kvm_zap_obsolete_pages().
 	 */
+	sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
 	kvm_mod_used_mmu_pages(vcpu->kvm, +1);
 	return sp;
@@ -2153,35 +2326,33 @@
 	--kvm->stat.mmu_unsync;
 }
 
-static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
-				    struct list_head *invalid_list);
+static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+				     struct list_head *invalid_list);
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 				    struct list_head *invalid_list);
 
-/*
- * NOTE: we should pay more attention on the zapped-obsolete page
- * (is_obsolete_sp(sp) && sp->role.invalid) when you do hash list walk
- * since it has been deleted from active_mmu_pages but still can be found
- * at hast list.
- *
- * for_each_valid_sp() has skipped that kind of pages.
- */
+
 #define for_each_valid_sp(_kvm, _sp, _gfn)				\
 	hlist_for_each_entry(_sp,					\
 	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
-		if (is_obsolete_sp((_kvm), (_sp)) || (_sp)->role.invalid) {    \
+		if (is_obsolete_sp((_kvm), (_sp))) {			\
 		} else
 
 #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn)			\
 	for_each_valid_sp(_kvm, _sp, _gfn)				\
 		if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
 
+static inline bool is_ept_sp(struct kvm_mmu_page *sp)
+{
+	return sp->role.cr0_wp && sp->role.smap_andnot_wp;
+}
+
 /* @sp->gfn should be write-protected at the call site */
 static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			    struct list_head *invalid_list)
 {
-	if (sp->role.cr4_pae != !!is_pae(vcpu)
-	    || vcpu->arch.mmu.sync_page(vcpu, sp) == 0) {
+	if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) ||
+	    vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
 		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
 		return false;
 	}
@@ -2189,18 +2360,28 @@
 	return true;
 }
 
+static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
+					struct list_head *invalid_list,
+					bool remote_flush)
+{
+	if (!remote_flush && list_empty(invalid_list))
+		return false;
+
+	if (!list_empty(invalid_list))
+		kvm_mmu_commit_zap_page(kvm, invalid_list);
+	else
+		kvm_flush_remote_tlbs(kvm);
+	return true;
+}
+
 static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu,
 				 struct list_head *invalid_list,
 				 bool remote_flush, bool local_flush)
 {
-	if (!list_empty(invalid_list)) {
-		kvm_mmu_commit_zap_page(vcpu->kvm, invalid_list);
+	if (kvm_mmu_remote_flush_or_zap(vcpu->kvm, invalid_list, remote_flush))
 		return;
-	}
 
-	if (remote_flush)
-		kvm_flush_remote_tlbs(vcpu->kvm);
-	else if (local_flush)
+	if (local_flush)
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
 
@@ -2213,7 +2394,8 @@
 
 static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
+	return sp->role.invalid ||
+	       unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
 }
 
 static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
@@ -2375,14 +2557,14 @@
 	int collisions = 0;
 	LIST_HEAD(invalid_list);
 
-	role = vcpu->arch.mmu.base_role;
+	role = vcpu->arch.mmu->mmu_role.base;
 	role.level = level;
 	role.direct = direct;
 	if (role.direct)
-		role.cr4_pae = 0;
+		role.gpte_is_8_bytes = true;
 	role.access = access;
-	if (!vcpu->arch.mmu.direct_map
-	    && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
+	if (!vcpu->arch.mmu->direct_map
+	    && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
 		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
 		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
 		role.quadrant = quadrant;
@@ -2435,12 +2617,11 @@
 		account_shadowed(vcpu->kvm, sp);
 		if (level == PT_PAGE_TABLE_LEVEL &&
 		      rmap_write_protect(vcpu, gfn))
-			kvm_flush_remote_tlbs(vcpu->kvm);
+			kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, 1);
 
 		if (level > PT_PAGE_TABLE_LEVEL && need_sync)
 			flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
 	}
-	sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
 	clear_page(sp->spt);
 	trace_kvm_mmu_get_page(sp, true);
 
@@ -2457,11 +2638,11 @@
 {
 	iterator->addr = addr;
 	iterator->shadow_addr = root;
-	iterator->level = vcpu->arch.mmu.shadow_root_level;
+	iterator->level = vcpu->arch.mmu->shadow_root_level;
 
 	if (iterator->level == PT64_ROOT_4LEVEL &&
-	    vcpu->arch.mmu.root_level < PT64_ROOT_4LEVEL &&
-	    !vcpu->arch.mmu.direct_map)
+	    vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
+	    !vcpu->arch.mmu->direct_map)
 		--iterator->level;
 
 	if (iterator->level == PT32E_ROOT_LEVEL) {
@@ -2469,10 +2650,10 @@
 		 * prev_root is currently only used for 64-bit hosts. So only
 		 * the active root_hpa is valid here.
 		 */
-		BUG_ON(root != vcpu->arch.mmu.root_hpa);
+		BUG_ON(root != vcpu->arch.mmu->root_hpa);
 
 		iterator->shadow_addr
-			= vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
+			= vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
 		iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
 		--iterator->level;
 		if (!iterator->shadow_addr)
@@ -2483,7 +2664,7 @@
 static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
 			     struct kvm_vcpu *vcpu, u64 addr)
 {
-	shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu.root_hpa,
+	shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root_hpa,
 				    addr);
 }
 
@@ -2525,7 +2706,7 @@
 	       shadow_user_mask | shadow_x_mask | shadow_me_mask;
 
 	if (sp_ad_disabled(sp))
-		spte |= shadow_acc_track_value;
+		spte |= SPTE_AD_DISABLED_MASK;
 	else
 		spte |= shadow_accessed_mask;
 
@@ -2555,7 +2736,7 @@
 			return;
 
 		drop_parent_pte(child, sptep);
-		kvm_flush_remote_tlbs(vcpu->kvm);
+		kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1);
 	}
 }
 
@@ -2626,17 +2807,22 @@
 	return zapped;
 }
 
-static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
-				    struct list_head *invalid_list)
+static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
+				       struct kvm_mmu_page *sp,
+				       struct list_head *invalid_list,
+				       int *nr_zapped)
 {
-	int ret;
+	bool list_unstable;
 
 	trace_kvm_mmu_prepare_zap_page(sp);
 	++kvm->stat.mmu_shadow_zapped;
-	ret = mmu_zap_unsync_children(kvm, sp, invalid_list);
+	*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
 	kvm_mmu_page_unlink_children(kvm, sp);
 	kvm_mmu_unlink_parents(kvm, sp);
 
+	/* Zapping children means active_mmu_pages has become unstable. */
+	list_unstable = *nr_zapped;
+
 	if (!sp->role.invalid && !sp->role.direct)
 		unaccount_shadowed(kvm, sp);
 
@@ -2644,22 +2830,35 @@
 		kvm_unlink_unsync_page(kvm, sp);
 	if (!sp->root_count) {
 		/* Count self */
-		ret++;
+		(*nr_zapped)++;
 		list_move(&sp->link, invalid_list);
 		kvm_mod_used_mmu_pages(kvm, -1);
 	} else {
 		list_move(&sp->link, &kvm->arch.active_mmu_pages);
 
 		/*
-		 * The obsolete pages can not be used on any vcpus.
-		 * See the comments in kvm_mmu_invalidate_zap_all_pages().
+		 * Obsolete pages cannot be used on any vCPUs, see the comment
+		 * in kvm_mmu_zap_all_fast().  Note, is_obsolete_sp() also
+		 * treats invalid shadow pages as being obsolete.
 		 */
-		if (!sp->role.invalid && !is_obsolete_sp(kvm, sp))
+		if (!is_obsolete_sp(kvm, sp))
 			kvm_reload_remote_mmus(kvm);
 	}
 
+	if (sp->lpage_disallowed)
+		unaccount_huge_nx_page(kvm, sp);
+
 	sp->role.invalid = 1;
-	return ret;
+	return list_unstable;
+}
+
+static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+				     struct list_head *invalid_list)
+{
+	int nr_zapped;
+
+	__kvm_mmu_prepare_zap_page(kvm, sp, invalid_list, &nr_zapped);
+	return nr_zapped;
 }
 
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
@@ -2704,7 +2903,7 @@
  * Changing the number of mmu pages allocated to the vm
  * Note: if goal_nr_mmu_pages is too small, you will get dead lock
  */
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
 {
 	LIST_HEAD(invalid_list);
 
@@ -2833,7 +3032,9 @@
 			 */
 			(!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn));
 
-	return true;
+	return !e820__mapped_raw_any(pfn_to_hpa(pfn),
+				     pfn_to_hpa(pfn + 1) - 1,
+				     E820_TYPE_RAM);
 }
 
 /* Bits which may be returned by set_spte() */
@@ -2854,7 +3055,9 @@
 
 	sp = page_header(__pa(sptep));
 	if (sp_ad_disabled(sp))
-		spte |= shadow_acc_track_value;
+		spte |= SPTE_AD_DISABLED_MASK;
+	else if (kvm_vcpu_ad_need_write_protect(vcpu))
+		spte |= SPTE_AD_WRPROT_ONLY_MASK;
 
 	/*
 	 * For the EPT case, shadow_present_mask is 0 if hardware
@@ -2866,6 +3069,11 @@
 	if (!speculative)
 		spte |= spte_shadow_accessed_mask(spte);
 
+	if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) &&
+	    is_nx_huge_page_enabled()) {
+		pte_access &= ~ACC_EXEC_MASK;
+	}
+
 	if (pte_access & ACC_EXEC_MASK)
 		spte |= shadow_x_mask;
 	else
@@ -2979,17 +3187,16 @@
 			ret = RET_PF_EMULATE;
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	}
+
 	if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH || flush)
-		kvm_flush_remote_tlbs(vcpu->kvm);
+		kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn,
+				KVM_PAGES_PER_HPAGE(level));
 
 	if (unlikely(is_mmio_spte(*sptep)))
 		ret = RET_PF_EMULATE;
 
 	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
-	pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n",
-		 is_large_pte(*sptep)? "2MB" : "4kB",
-		 *sptep & PT_WRITABLE_MASK ? "RW" : "R", gfn,
-		 *sptep, sptep);
+	trace_kvm_mmu_set_spte(level, gfn, sptep);
 	if (!was_rmapped && is_large_pte(*sptep))
 		++vcpu->kvm->stat.lpages;
 
@@ -3001,8 +3208,6 @@
 		}
 	}
 
-	kvm_release_pfn_clean(pfn);
-
 	return ret;
 }
 
@@ -3037,9 +3242,11 @@
 	if (ret <= 0)
 		return -1;
 
-	for (i = 0; i < ret; i++, gfn++, start++)
+	for (i = 0; i < ret; i++, gfn++, start++) {
 		mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn,
 			     page_to_pfn(pages[i]), true, true);
+		put_page(pages[i]);
+	}
 
 	return 0;
 }
@@ -3087,54 +3294,76 @@
 	__direct_pte_prefetch(vcpu, sp, sptep);
 }
 
-static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
-			int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault)
+static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
+				       gfn_t gfn, kvm_pfn_t *pfnp, int *levelp)
 {
-	struct kvm_shadow_walk_iterator iterator;
+	int level = *levelp;
+	u64 spte = *it.sptep;
+
+	if (it.level == level && level > PT_PAGE_TABLE_LEVEL &&
+	    is_nx_huge_page_enabled() &&
+	    is_shadow_present_pte(spte) &&
+	    !is_large_pte(spte)) {
+		/*
+		 * A small SPTE exists for this pfn, but FNAME(fetch)
+		 * and __direct_map would like to create a large PTE
+		 * instead: just force them to go down another level,
+		 * patching back for them into pfn the next 9 bits of
+		 * the address.
+		 */
+		u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1);
+		*pfnp |= gfn & page_mask;
+		(*levelp)--;
+	}
+}
+
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
+			int map_writable, int level, kvm_pfn_t pfn,
+			bool prefault, bool lpage_disallowed)
+{
+	struct kvm_shadow_walk_iterator it;
 	struct kvm_mmu_page *sp;
-	int emulate = 0;
-	gfn_t pseudo_gfn;
+	int ret;
+	gfn_t gfn = gpa >> PAGE_SHIFT;
+	gfn_t base_gfn = gfn;
 
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
-		return 0;
+	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
+		return RET_PF_RETRY;
 
-	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
-		if (iterator.level == level) {
-			emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
-					       write, level, gfn, pfn, prefault,
-					       map_writable);
-			direct_pte_prefetch(vcpu, iterator.sptep);
-			++vcpu->stat.pf_fixed;
+	trace_kvm_mmu_spte_requested(gpa, level, pfn);
+	for_each_shadow_entry(vcpu, gpa, it) {
+		/*
+		 * We cannot overwrite existing page tables with an NX
+		 * large page, as the leaf could be executable.
+		 */
+		disallowed_hugepage_adjust(it, gfn, &pfn, &level);
+
+		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		if (it.level == level)
 			break;
-		}
 
-		drop_large_spte(vcpu, iterator.sptep);
-		if (!is_shadow_present_pte(*iterator.sptep)) {
-			u64 base_addr = iterator.addr;
+		drop_large_spte(vcpu, it.sptep);
+		if (!is_shadow_present_pte(*it.sptep)) {
+			sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr,
+					      it.level - 1, true, ACC_ALL);
 
-			base_addr &= PT64_LVL_ADDR_MASK(iterator.level);
-			pseudo_gfn = base_addr >> PAGE_SHIFT;
-			sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
-					      iterator.level - 1, 1, ACC_ALL);
-
-			link_shadow_page(vcpu, iterator.sptep, sp);
+			link_shadow_page(vcpu, it.sptep, sp);
+			if (lpage_disallowed)
+				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
-	return emulate;
+
+	ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL,
+			   write, level, base_gfn, pfn, prefault,
+			   map_writable);
+	direct_pte_prefetch(vcpu, it.sptep);
+	++vcpu->stat.pf_fixed;
+	return ret;
 }
 
 static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
 {
-	siginfo_t info;
-
-	clear_siginfo(&info);
-	info.si_signo	= SIGBUS;
-	info.si_errno	= 0;
-	info.si_code	= BUS_MCEERR_AR;
-	info.si_addr	= (void __user *)address;
-	info.si_addr_lsb = PAGE_SHIFT;
-
-	send_sig_info(SIGBUS, &info, tsk);
+	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
 }
 
 static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
@@ -3156,11 +3385,10 @@
 }
 
 static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
-					gfn_t *gfnp, kvm_pfn_t *pfnp,
+					gfn_t gfn, kvm_pfn_t *pfnp,
 					int *levelp)
 {
 	kvm_pfn_t pfn = *pfnp;
-	gfn_t gfn = *gfnp;
 	int level = *levelp;
 
 	/*
@@ -3170,7 +3398,7 @@
 	 * here.
 	 */
 	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
-	    level == PT_PAGE_TABLE_LEVEL &&
+	    !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
 	    PageTransCompoundMap(pfn_to_page(pfn)) &&
 	    !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
 		unsigned long mask;
@@ -3187,8 +3415,6 @@
 		mask = KVM_PAGES_PER_HPAGE(level) - 1;
 		VM_BUG_ON((gfn & mask) != (pfn & mask));
 		if (pfn & mask) {
-			gfn &= ~mask;
-			*gfnp = gfn;
 			kvm_release_pfn_clean(pfn);
 			pfn &= ~mask;
 			kvm_get_pfn(pfn);
@@ -3207,7 +3433,8 @@
 	}
 
 	if (unlikely(is_noslot_pfn(pfn)))
-		vcpu_cache_mmio_info(vcpu, gva, gfn, access);
+		vcpu_cache_mmio_info(vcpu, gva, gfn,
+				     access & shadow_mmio_access_mask);
 
 	return false;
 }
@@ -3310,7 +3537,7 @@
 	u64 spte = 0ull;
 	uint retry_count = 0;
 
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
 		return false;
 
 	if (!page_fault_can_be_fast(error_code))
@@ -3383,7 +3610,7 @@
 		/*
 		 * Currently, fast page fault only works for direct mapping
 		 * since the gfn is not stable for indirect shadow page. See
-		 * Documentation/virtual/kvm/locking.txt to get more detail.
+		 * Documentation/virt/kvm/locking.txt to get more detail.
 		 */
 		fault_handled = fast_pf_fix_direct_spte(vcpu, sp,
 							iterator.sptep, spte,
@@ -3415,11 +3642,14 @@
 {
 	int r;
 	int level;
-	bool force_pt_level = false;
+	bool force_pt_level;
 	kvm_pfn_t pfn;
 	unsigned long mmu_seq;
 	bool map_writable, write = error_code & PFERR_WRITE_MASK;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
 
+	force_pt_level = lpage_disallowed;
 	level = mapping_level(vcpu, gfn, &force_pt_level);
 	if (likely(!force_pt_level)) {
 		/*
@@ -3445,22 +3675,20 @@
 	if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r))
 		return r;
 
+	r = RET_PF_RETRY;
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
 	if (make_mmu_pages_available(vcpu) < 0)
 		goto out_unlock;
 	if (likely(!force_pt_level))
-		transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
-	r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
-	spin_unlock(&vcpu->kvm->mmu_lock);
-
-	return r;
-
+		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
+	r = __direct_map(vcpu, v, write, map_writable, level, pfn,
+			 prefault, false);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
-	return RET_PF_RETRY;
+	return r;
 }
 
 static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
@@ -3480,11 +3708,11 @@
 }
 
 /* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free)
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+			ulong roots_to_free)
 {
 	int i;
 	LIST_HEAD(invalid_list);
-	struct kvm_mmu *mmu = &vcpu->arch.mmu;
 	bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT;
 
 	BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG);
@@ -3520,6 +3748,7 @@
 							   &invalid_list);
 			mmu->root_hpa = INVALID_PAGE;
 		}
+		mmu->root_cr3 = 0;
 	}
 
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
@@ -3544,20 +3773,20 @@
 	struct kvm_mmu_page *sp;
 	unsigned i;
 
-	if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL) {
+	if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) {
 		spin_lock(&vcpu->kvm->mmu_lock);
 		if(make_mmu_pages_available(vcpu) < 0) {
 			spin_unlock(&vcpu->kvm->mmu_lock);
 			return -ENOSPC;
 		}
 		sp = kvm_mmu_get_page(vcpu, 0, 0,
-				vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
+				vcpu->arch.mmu->shadow_root_level, 1, ACC_ALL);
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
-		vcpu->arch.mmu.root_hpa = __pa(sp->spt);
-	} else if (vcpu->arch.mmu.shadow_root_level == PT32E_ROOT_LEVEL) {
+		vcpu->arch.mmu->root_hpa = __pa(sp->spt);
+	} else if (vcpu->arch.mmu->shadow_root_level == PT32E_ROOT_LEVEL) {
 		for (i = 0; i < 4; ++i) {
-			hpa_t root = vcpu->arch.mmu.pae_root[i];
+			hpa_t root = vcpu->arch.mmu->pae_root[i];
 
 			MMU_WARN_ON(VALID_PAGE(root));
 			spin_lock(&vcpu->kvm->mmu_lock);
@@ -3570,11 +3799,12 @@
 			root = __pa(sp->spt);
 			++sp->root_count;
 			spin_unlock(&vcpu->kvm->mmu_lock);
-			vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
+			vcpu->arch.mmu->pae_root[i] = root | PT_PRESENT_MASK;
 		}
-		vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+		vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
 	} else
 		BUG();
+	vcpu->arch.mmu->root_cr3 = vcpu->arch.mmu->get_cr3(vcpu);
 
 	return 0;
 }
@@ -3583,10 +3813,11 @@
 {
 	struct kvm_mmu_page *sp;
 	u64 pdptr, pm_mask;
-	gfn_t root_gfn;
+	gfn_t root_gfn, root_cr3;
 	int i;
 
-	root_gfn = vcpu->arch.mmu.get_cr3(vcpu) >> PAGE_SHIFT;
+	root_cr3 = vcpu->arch.mmu->get_cr3(vcpu);
+	root_gfn = root_cr3 >> PAGE_SHIFT;
 
 	if (mmu_check_root(vcpu, root_gfn))
 		return 1;
@@ -3595,8 +3826,8 @@
 	 * Do we shadow a long mode page table? If so we need to
 	 * write-protect the guests page table root.
 	 */
-	if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
-		hpa_t root = vcpu->arch.mmu.root_hpa;
+	if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+		hpa_t root = vcpu->arch.mmu->root_hpa;
 
 		MMU_WARN_ON(VALID_PAGE(root));
 
@@ -3606,12 +3837,12 @@
 			return -ENOSPC;
 		}
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
-				vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
+				vcpu->arch.mmu->shadow_root_level, 0, ACC_ALL);
 		root = __pa(sp->spt);
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
-		vcpu->arch.mmu.root_hpa = root;
-		return 0;
+		vcpu->arch.mmu->root_hpa = root;
+		goto set_root_cr3;
 	}
 
 	/*
@@ -3620,17 +3851,17 @@
 	 * the shadow page table may be a PAE or a long mode page table.
 	 */
 	pm_mask = PT_PRESENT_MASK;
-	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL)
+	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL)
 		pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
 
 	for (i = 0; i < 4; ++i) {
-		hpa_t root = vcpu->arch.mmu.pae_root[i];
+		hpa_t root = vcpu->arch.mmu->pae_root[i];
 
 		MMU_WARN_ON(VALID_PAGE(root));
-		if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
-			pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
+		if (vcpu->arch.mmu->root_level == PT32E_ROOT_LEVEL) {
+			pdptr = vcpu->arch.mmu->get_pdptr(vcpu, i);
 			if (!(pdptr & PT_PRESENT_MASK)) {
-				vcpu->arch.mmu.pae_root[i] = 0;
+				vcpu->arch.mmu->pae_root[i] = 0;
 				continue;
 			}
 			root_gfn = pdptr >> PAGE_SHIFT;
@@ -3648,16 +3879,16 @@
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
 
-		vcpu->arch.mmu.pae_root[i] = root | pm_mask;
+		vcpu->arch.mmu->pae_root[i] = root | pm_mask;
 	}
-	vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+	vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
 
 	/*
 	 * If we shadow a 32 bit page table with a long mode page
 	 * table we enter this path.
 	 */
-	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL) {
-		if (vcpu->arch.mmu.lm_root == NULL) {
+	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
+		if (vcpu->arch.mmu->lm_root == NULL) {
 			/*
 			 * The additional page necessary for this is only
 			 * allocated on demand.
@@ -3665,24 +3896,27 @@
 
 			u64 *lm_root;
 
-			lm_root = (void*)get_zeroed_page(GFP_KERNEL);
+			lm_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT);
 			if (lm_root == NULL)
 				return 1;
 
-			lm_root[0] = __pa(vcpu->arch.mmu.pae_root) | pm_mask;
+			lm_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask;
 
-			vcpu->arch.mmu.lm_root = lm_root;
+			vcpu->arch.mmu->lm_root = lm_root;
 		}
 
-		vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.lm_root);
+		vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root);
 	}
 
+set_root_cr3:
+	vcpu->arch.mmu->root_cr3 = root_cr3;
+
 	return 0;
 }
 
 static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.mmu.direct_map)
+	if (vcpu->arch.mmu->direct_map)
 		return mmu_alloc_direct_roots(vcpu);
 	else
 		return mmu_alloc_shadow_roots(vcpu);
@@ -3693,17 +3927,16 @@
 	int i;
 	struct kvm_mmu_page *sp;
 
-	if (vcpu->arch.mmu.direct_map)
+	if (vcpu->arch.mmu->direct_map)
 		return;
 
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
 		return;
 
 	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 
-	if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
-		hpa_t root = vcpu->arch.mmu.root_hpa;
-
+	if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+		hpa_t root = vcpu->arch.mmu->root_hpa;
 		sp = page_header(root);
 
 		/*
@@ -3734,7 +3967,7 @@
 	kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 
 	for (i = 0; i < 4; ++i) {
-		hpa_t root = vcpu->arch.mmu.pae_root[i];
+		hpa_t root = vcpu->arch.mmu->pae_root[i];
 
 		if (root && VALID_PAGE(root)) {
 			root &= PT64_BASE_ADDR_MASK;
@@ -3808,7 +4041,7 @@
 	int root, leaf;
 	bool reserved = false;
 
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
 		goto exit;
 
 	walk_shadow_page_lockless_begin(vcpu);
@@ -3825,7 +4058,7 @@
 		if (!is_shadow_present_pte(spte))
 			break;
 
-		reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
+		reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte,
 						    iterator.level);
 	}
 
@@ -3904,7 +4137,7 @@
 	struct kvm_shadow_walk_iterator iterator;
 	u64 spte;
 
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
 		return;
 
 	walk_shadow_page_lockless_begin(vcpu);
@@ -3931,7 +4164,7 @@
 	if (r)
 		return r;
 
-	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
 
 
 	return nonpaging_map(vcpu, gva & PAGE_MASK,
@@ -3944,25 +4177,12 @@
 
 	arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
 	arch.gfn = gfn;
-	arch.direct_map = vcpu->arch.mmu.direct_map;
-	arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
+	arch.direct_map = vcpu->arch.mmu->direct_map;
+	arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
 
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
-{
-	if (unlikely(!lapic_in_kernel(vcpu) ||
-		     kvm_event_needs_reinjection(vcpu) ||
-		     vcpu->arch.exception.pending))
-		return false;
-
-	if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
-		return false;
-
-	return kvm_x86_ops->interrupt_allowed(vcpu);
-}
-
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable)
 {
@@ -4050,8 +4270,10 @@
 	unsigned long mmu_seq;
 	int write = error_code & PFERR_WRITE_MASK;
 	bool map_writable;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
 
-	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
 
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
 		return RET_PF_EMULATE;
@@ -4060,8 +4282,9 @@
 	if (r)
 		return r;
 
-	force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn,
-							   PT_DIRECTORY_LEVEL);
+	force_pt_level =
+		lpage_disallowed ||
+		!check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL);
 	level = mapping_level(vcpu, gfn, &force_pt_level);
 	if (likely(!force_pt_level)) {
 		if (level > PT_DIRECTORY_LEVEL &&
@@ -4082,22 +4305,20 @@
 	if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r))
 		return r;
 
+	r = RET_PF_RETRY;
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
 	if (make_mmu_pages_available(vcpu) < 0)
 		goto out_unlock;
 	if (likely(!force_pt_level))
-		transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
-	r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
-	spin_unlock(&vcpu->kvm->mmu_lock);
-
-	return r;
-
+		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
+	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
+			 prefault, lpage_disallowed);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
-	return RET_PF_RETRY;
+	return r;
 }
 
 static void nonpaging_init_context(struct kvm_vcpu *vcpu,
@@ -4127,9 +4348,9 @@
 {
 	uint i;
 	struct kvm_mmu_root_info root;
-	struct kvm_mmu *mmu = &vcpu->arch.mmu;
+	struct kvm_mmu *mmu = vcpu->arch.mmu;
 
-	root.cr3 = mmu->get_cr3(vcpu);
+	root.cr3 = mmu->root_cr3;
 	root.hpa = mmu->root_hpa;
 
 	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
@@ -4142,6 +4363,7 @@
 	}
 
 	mmu->root_hpa = root.hpa;
+	mmu->root_cr3 = root.cr3;
 
 	return i < KVM_MMU_NUM_PREV_ROOTS;
 }
@@ -4150,7 +4372,7 @@
 			    union kvm_mmu_page_role new_role,
 			    bool skip_tlb_flush)
 {
-	struct kvm_mmu *mmu = &vcpu->arch.mmu;
+	struct kvm_mmu *mmu = vcpu->arch.mmu;
 
 	/*
 	 * For now, limit the fast switch to 64-bit hosts+VMs in order to avoid
@@ -4165,12 +4387,11 @@
 		if (cached_root_available(vcpu, new_cr3, new_role)) {
 			/*
 			 * It is possible that the cached previous root page is
-			 * obsolete because of a change in the MMU
-			 * generation number. However, that is accompanied by
-			 * KVM_REQ_MMU_RELOAD, which will free the root that we
-			 * have set here and allocate a new one.
+			 * obsolete because of a change in the MMU generation
+			 * number. However, changing the generation number is
+			 * accompanied by KVM_REQ_MMU_RELOAD, which will free
+			 * the root set here and allocate a new one.
 			 */
-
 			kvm_make_request(KVM_REQ_LOAD_CR3, vcpu);
 			if (!skip_tlb_flush) {
 				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
@@ -4201,7 +4422,8 @@
 			      bool skip_tlb_flush)
 {
 	if (!fast_cr3_switch(vcpu, new_cr3, new_role, skip_tlb_flush))
-		kvm_mmu_free_roots(vcpu, KVM_MMU_ROOT_CURRENT);
+		kvm_mmu_free_roots(vcpu, vcpu->arch.mmu,
+				   KVM_MMU_ROOT_CURRENT);
 }
 
 void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush)
@@ -4219,7 +4441,7 @@
 static void inject_page_fault(struct kvm_vcpu *vcpu,
 			      struct x86_exception *fault)
 {
-	vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+	vcpu->arch.mmu->inject_page_fault(vcpu, fault);
 }
 
 static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
@@ -4336,6 +4558,7 @@
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[1][4] =
 			rsvd_check->rsvd_bits_mask[0][4];
+		/* fall through */
 	case PT64_ROOT_4LEVEL:
 		rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
@@ -4423,7 +4646,8 @@
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
-	bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+	bool uses_nx = context->nx ||
+		context->mmu_role.base.smep_andnot_wp;
 	struct rsvd_bits_validate *shadow_zero_check;
 	int i;
 
@@ -4433,7 +4657,7 @@
 	 */
 	shadow_zero_check = &context->shadow_zero_check;
 	__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
-				boot_cpu_data.x86_phys_bits,
+				shadow_phys_bits,
 				context->shadow_root_level, uses_nx,
 				guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
 				is_pse(vcpu), true);
@@ -4470,13 +4694,13 @@
 
 	if (boot_cpu_is_amd())
 		__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
-					boot_cpu_data.x86_phys_bits,
+					shadow_phys_bits,
 					context->shadow_root_level, false,
 					boot_cpu_has(X86_FEATURE_GBPAGES),
 					true, true);
 	else
 		__reset_rsvds_bits_mask_ept(shadow_zero_check,
-					    boot_cpu_data.x86_phys_bits,
+					    shadow_phys_bits,
 					    false);
 
 	if (!shadow_me_mask)
@@ -4497,7 +4721,7 @@
 				struct kvm_mmu *context, bool execonly)
 {
 	__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
-				    boot_cpu_data.x86_phys_bits, execonly);
+				    shadow_phys_bits, execonly);
 }
 
 #define BYTE_MASK(access) \
@@ -4532,11 +4756,11 @@
 		 */
 
 		/* Faults from writes to non-writable pages */
-		u8 wf = (pfec & PFERR_WRITE_MASK) ? ~w : 0;
+		u8 wf = (pfec & PFERR_WRITE_MASK) ? (u8)~w : 0;
 		/* Faults from user mode accesses to supervisor pages */
-		u8 uf = (pfec & PFERR_USER_MASK) ? ~u : 0;
+		u8 uf = (pfec & PFERR_USER_MASK) ? (u8)~u : 0;
 		/* Faults from fetches of non-executable pages*/
-		u8 ff = (pfec & PFERR_FETCH_MASK) ? ~x : 0;
+		u8 ff = (pfec & PFERR_FETCH_MASK) ? (u8)~x : 0;
 		/* Faults from kernel mode fetches of user pages */
 		u8 smepf = 0;
 		/* Faults from kernel mode accesses of user pages */
@@ -4562,7 +4786,7 @@
 			 * SMAP:kernel-mode data accesses from user-mode
 			 * mappings should fault. A fault is considered
 			 * as a SMAP violation if all of the following
-			 * conditions are ture:
+			 * conditions are true:
 			 *   - X86_CR4_SMAP is set in CR4
 			 *   - A user page is accessed
 			 *   - The access is not a fetch
@@ -4723,27 +4947,67 @@
 	paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL);
 }
 
-static union kvm_mmu_page_role
-kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu)
+static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
 {
-	union kvm_mmu_page_role role = {0};
+	union kvm_mmu_extended_role ext = {0};
 
-	role.guest_mode = is_guest_mode(vcpu);
-	role.smm = is_smm(vcpu);
-	role.ad_disabled = (shadow_accessed_mask == 0);
-	role.level = kvm_x86_ops->get_tdp_level(vcpu);
-	role.direct = true;
-	role.access = ACC_ALL;
+	ext.cr0_pg = !!is_paging(vcpu);
+	ext.cr4_pae = !!is_pae(vcpu);
+	ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
+	ext.cr4_pse = !!is_pse(vcpu);
+	ext.cr4_pke = !!kvm_read_cr4_bits(vcpu, X86_CR4_PKE);
+	ext.cr4_la57 = !!kvm_read_cr4_bits(vcpu, X86_CR4_LA57);
+	ext.maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+	ext.valid = 1;
+
+	return ext;
+}
+
+static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu,
+						   bool base_only)
+{
+	union kvm_mmu_role role = {0};
+
+	role.base.access = ACC_ALL;
+	role.base.nxe = !!is_nx(vcpu);
+	role.base.cr0_wp = is_write_protection(vcpu);
+	role.base.smm = is_smm(vcpu);
+	role.base.guest_mode = is_guest_mode(vcpu);
+
+	if (base_only)
+		return role;
+
+	role.ext = kvm_calc_mmu_role_ext(vcpu);
+
+	return role;
+}
+
+static union kvm_mmu_role
+kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
+{
+	union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);
+
+	role.base.ad_disabled = (shadow_accessed_mask == 0);
+	role.base.level = kvm_x86_ops->get_tdp_level(vcpu);
+	role.base.direct = true;
+	role.base.gpte_is_8_bytes = true;
 
 	return role;
 }
 
 static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 {
-	struct kvm_mmu *context = &vcpu->arch.mmu;
+	struct kvm_mmu *context = vcpu->arch.mmu;
+	union kvm_mmu_role new_role =
+		kvm_calc_tdp_mmu_root_page_role(vcpu, false);
 
-	context->base_role.word = mmu_base_role_mask.word &
-				  kvm_calc_tdp_mmu_root_page_role(vcpu).word;
+	new_role.base.word &= mmu_base_role_mask.word;
+	if (new_role.as_u64 == context->mmu_role.as_u64)
+		return;
+
+	context->mmu_role.as_u64 = new_role.as_u64;
 	context->page_fault = tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
@@ -4783,36 +5047,37 @@
 	reset_tdp_shadow_zero_bits_mask(vcpu, context);
 }
 
-static union kvm_mmu_page_role
-kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu)
+static union kvm_mmu_role
+kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 {
-	union kvm_mmu_page_role role = {0};
-	bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
-	bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
+	union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);
 
-	role.nxe = is_nx(vcpu);
-	role.cr4_pae = !!is_pae(vcpu);
-	role.cr0_wp  = is_write_protection(vcpu);
-	role.smep_andnot_wp = smep && !is_write_protection(vcpu);
-	role.smap_andnot_wp = smap && !is_write_protection(vcpu);
-	role.guest_mode = is_guest_mode(vcpu);
-	role.smm = is_smm(vcpu);
-	role.direct = !is_paging(vcpu);
-	role.access = ACC_ALL;
+	role.base.smep_andnot_wp = role.ext.cr4_smep &&
+		!is_write_protection(vcpu);
+	role.base.smap_andnot_wp = role.ext.cr4_smap &&
+		!is_write_protection(vcpu);
+	role.base.direct = !is_paging(vcpu);
+	role.base.gpte_is_8_bytes = !!is_pae(vcpu);
 
 	if (!is_long_mode(vcpu))
-		role.level = PT32E_ROOT_LEVEL;
+		role.base.level = PT32E_ROOT_LEVEL;
 	else if (is_la57_mode(vcpu))
-		role.level = PT64_ROOT_5LEVEL;
+		role.base.level = PT64_ROOT_5LEVEL;
 	else
-		role.level = PT64_ROOT_4LEVEL;
+		role.base.level = PT64_ROOT_4LEVEL;
 
 	return role;
 }
 
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 {
-	struct kvm_mmu *context = &vcpu->arch.mmu;
+	struct kvm_mmu *context = vcpu->arch.mmu;
+	union kvm_mmu_role new_role =
+		kvm_calc_shadow_mmu_root_page_role(vcpu, false);
+
+	new_role.base.word &= mmu_base_role_mask.word;
+	if (new_role.as_u64 == context->mmu_role.as_u64)
+		return;
 
 	if (!is_paging(vcpu))
 		nonpaging_init_context(vcpu, context);
@@ -4823,22 +5088,36 @@
 	else
 		paging32_init_context(vcpu, context);
 
-	context->base_role.word = mmu_base_role_mask.word &
-				  kvm_calc_shadow_mmu_root_page_role(vcpu).word;
+	context->mmu_role.as_u64 = new_role.as_u64;
 	reset_shadow_zero_bits_mask(vcpu, context);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
-static union kvm_mmu_page_role
-kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty)
+static union kvm_mmu_role
+kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
+				   bool execonly)
 {
-	union kvm_mmu_page_role role = vcpu->arch.mmu.base_role;
+	union kvm_mmu_role role = {0};
 
-	role.level = PT64_ROOT_4LEVEL;
-	role.direct = false;
-	role.ad_disabled = !accessed_dirty;
-	role.guest_mode = true;
-	role.access = ACC_ALL;
+	/* SMM flag is inherited from root_mmu */
+	role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm;
+
+	role.base.level = PT64_ROOT_4LEVEL;
+	role.base.gpte_is_8_bytes = true;
+	role.base.direct = false;
+	role.base.ad_disabled = !accessed_dirty;
+	role.base.guest_mode = true;
+	role.base.access = ACC_ALL;
+
+	/*
+	 * WP=1 and NOT_WP=1 is an impossible combination, use WP and the
+	 * SMAP variation to denote shadow EPT entries.
+	 */
+	role.base.cr0_wp = true;
+	role.base.smap_andnot_wp = true;
+
+	role.ext = kvm_calc_mmu_role_ext(vcpu);
+	role.ext.execonly = execonly;
 
 	return role;
 }
@@ -4846,11 +5125,17 @@
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty, gpa_t new_eptp)
 {
-	struct kvm_mmu *context = &vcpu->arch.mmu;
-	union kvm_mmu_page_role root_page_role =
-		kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty);
+	struct kvm_mmu *context = vcpu->arch.mmu;
+	union kvm_mmu_role new_role =
+		kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
+						   execonly);
 
-	__kvm_mmu_new_cr3(vcpu, new_eptp, root_page_role, false);
+	__kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false);
+
+	new_role.base.word &= mmu_base_role_mask.word;
+	if (new_role.as_u64 == context->mmu_role.as_u64)
+		return;
+
 	context->shadow_root_level = PT64_ROOT_4LEVEL;
 
 	context->nx = true;
@@ -4862,7 +5147,8 @@
 	context->update_pte = ept_update_pte;
 	context->root_level = PT64_ROOT_4LEVEL;
 	context->direct_map = false;
-	context->base_role.word = root_page_role.word & mmu_base_role_mask.word;
+	context->mmu_role.as_u64 = new_role.as_u64;
+
 	update_permission_bitmask(vcpu, context, true);
 	update_pkru_bitmask(vcpu, context, true);
 	update_last_nonleaf_level(vcpu, context);
@@ -4873,7 +5159,7 @@
 
 static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
 {
-	struct kvm_mmu *context = &vcpu->arch.mmu;
+	struct kvm_mmu *context = vcpu->arch.mmu;
 
 	kvm_init_shadow_mmu(vcpu);
 	context->set_cr3           = kvm_x86_ops->set_cr3;
@@ -4884,14 +5170,20 @@
 
 static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 {
+	union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false);
 	struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
 
+	new_role.base.word &= mmu_base_role_mask.word;
+	if (new_role.as_u64 == g_context->mmu_role.as_u64)
+		return;
+
+	g_context->mmu_role.as_u64 = new_role.as_u64;
 	g_context->get_cr3           = get_cr3;
 	g_context->get_pdptr         = kvm_pdptr_read;
 	g_context->inject_page_fault = kvm_inject_page_fault;
 
 	/*
-	 * Note that arch.mmu.gva_to_gpa translates l2_gpa to l1_gpa using
+	 * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using
 	 * L1's nested page tables (e.g. EPT12). The nested translation
 	 * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using
 	 * L2's page tables as the first level of translation and L1's
@@ -4930,10 +5222,10 @@
 	if (reset_roots) {
 		uint i;
 
-		vcpu->arch.mmu.root_hpa = INVALID_PAGE;
+		vcpu->arch.mmu->root_hpa = INVALID_PAGE;
 
 		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
-			vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+			vcpu->arch.mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
 	}
 
 	if (mmu_is_nested(vcpu))
@@ -4948,10 +5240,14 @@
 static union kvm_mmu_page_role
 kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu)
 {
+	union kvm_mmu_role role;
+
 	if (tdp_enabled)
-		return kvm_calc_tdp_mmu_root_page_role(vcpu);
+		role = kvm_calc_tdp_mmu_root_page_role(vcpu, true);
 	else
-		return kvm_calc_shadow_mmu_root_page_role(vcpu);
+		role = kvm_calc_shadow_mmu_root_page_role(vcpu, true);
+
+	return role.base;
 }
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
@@ -4981,8 +5277,10 @@
 
 void kvm_mmu_unload(struct kvm_vcpu *vcpu)
 {
-	kvm_mmu_free_roots(vcpu, KVM_MMU_ROOTS_ALL);
-	WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+	kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
+	WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root_hpa));
+	kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+	WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root_hpa));
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unload);
 
@@ -4996,7 +5294,7 @@
         }
 
 	++vcpu->kvm->stat.mmu_pte_updated;
-	vcpu->arch.mmu.update_pte(vcpu, sp, spte, new);
+	vcpu->arch.mmu->update_pte(vcpu, sp, spte, new);
 }
 
 static bool need_remote_flush(u64 old, u64 new)
@@ -5068,7 +5366,7 @@
 		 gpa, bytes, sp->role.word);
 
 	offset = offset_in_page(gpa);
-	pte_size = sp->role.cr4_pae ? 8 : 4;
+	pte_size = sp->role.gpte_is_8_bytes ? 8 : 4;
 
 	/*
 	 * Sometimes, the OS only writes the last one bytes to update status
@@ -5092,7 +5390,7 @@
 	page_offset = offset_in_page(gpa);
 	level = sp->role.level;
 	*nspte = 1;
-	if (!sp->role.cr4_pae) {
+	if (!sp->role.gpte_is_8_bytes) {
 		page_offset <<= 1;	/* 32->64 */
 		/*
 		 * A 32-bit pde maps 4MB while the shadow pdes map
@@ -5164,10 +5462,12 @@
 
 		local_flush = true;
 		while (npte--) {
+			u32 base_role = vcpu->arch.mmu->mmu_role.base.word;
+
 			entry = *spte;
 			mmu_page_zap_pte(vcpu->kvm, sp, spte);
 			if (gentry &&
-			      !((sp->role.word ^ vcpu->arch.mmu.base_role.word)
+			      !((sp->role.word ^ base_role)
 			      & mmu_base_role_mask.word) && rmap_can_add(vcpu))
 				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
 			if (need_remote_flush(entry, *spte))
@@ -5185,7 +5485,7 @@
 	gpa_t gpa;
 	int r;
 
-	if (vcpu->arch.mmu.direct_map)
+	if (vcpu->arch.mmu->direct_map)
 		return 0;
 
 	gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
@@ -5220,11 +5520,10 @@
 		       void *insn, int insn_len)
 {
 	int r, emulation_type = 0;
-	enum emulation_result er;
-	bool direct = vcpu->arch.mmu.direct_map;
+	bool direct = vcpu->arch.mmu->direct_map;
 
 	/* With shadow page tables, fault_address contains a GVA or nGPA.  */
-	if (vcpu->arch.mmu.direct_map) {
+	if (vcpu->arch.mmu->direct_map) {
 		vcpu->arch.gpa_available = true;
 		vcpu->arch.gpa_val = cr2;
 	}
@@ -5237,8 +5536,9 @@
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
-					      false);
+		r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+					       lower_32_bits(error_code),
+					       false);
 		WARN_ON(r == RET_PF_INVALID);
 	}
 
@@ -5254,7 +5554,7 @@
 	 * paging in both guests. If true, we simply unprotect the page
 	 * and resume the guest.
 	 */
-	if (vcpu->arch.mmu.direct_map &&
+	if (vcpu->arch.mmu->direct_map &&
 	    (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
 		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
 		return 1;
@@ -5279,30 +5579,21 @@
 	 * This can happen if a guest gets a page-fault on data access but the HW
 	 * table walker is not able to read the instruction page (e.g instruction
 	 * page is not present in memory). In those cases we simply restart the
-	 * guest.
+	 * guest, with the exception of AMD Erratum 1096 which is unrecoverable.
 	 */
-	if (unlikely(insn && !insn_len))
-		return 1;
-
-	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
-
-	switch (er) {
-	case EMULATE_DONE:
-		return 1;
-	case EMULATE_USER_EXIT:
-		++vcpu->stat.mmio_exits;
-		/* fall through */
-	case EMULATE_FAIL:
-		return 0;
-	default:
-		BUG();
+	if (unlikely(insn && !insn_len)) {
+		if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu))
+			return 1;
 	}
+
+	return x86_emulate_instruction(vcpu, cr2, emulation_type, insn,
+				       insn_len);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
 
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	struct kvm_mmu *mmu = &vcpu->arch.mmu;
+	struct kvm_mmu *mmu = vcpu->arch.mmu;
 	int i;
 
 	/* INVLPG on a * non-canonical address is a NOP according to the SDM.  */
@@ -5333,7 +5624,7 @@
 
 void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
 {
-	struct kvm_mmu *mmu = &vcpu->arch.mmu;
+	struct kvm_mmu *mmu = vcpu->arch.mmu;
 	bool tlb_flush = false;
 	uint i;
 
@@ -5375,85 +5666,6 @@
 }
 EXPORT_SYMBOL_GPL(kvm_disable_tdp);
 
-static void free_mmu_pages(struct kvm_vcpu *vcpu)
-{
-	free_page((unsigned long)vcpu->arch.mmu.pae_root);
-	free_page((unsigned long)vcpu->arch.mmu.lm_root);
-}
-
-static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
-{
-	struct page *page;
-	int i;
-
-	if (tdp_enabled)
-		return 0;
-
-	/*
-	 * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
-	 * Therefore we need to allocate shadow page tables in the first
-	 * 4GB of memory, which happens to fit the DMA32 zone.
-	 */
-	page = alloc_page(GFP_KERNEL | __GFP_DMA32);
-	if (!page)
-		return -ENOMEM;
-
-	vcpu->arch.mmu.pae_root = page_address(page);
-	for (i = 0; i < 4; ++i)
-		vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
-
-	return 0;
-}
-
-int kvm_mmu_create(struct kvm_vcpu *vcpu)
-{
-	uint i;
-
-	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
-	vcpu->arch.mmu.root_hpa = INVALID_PAGE;
-	vcpu->arch.mmu.translate_gpa = translate_gpa;
-	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
-
-	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
-		vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
-
-	return alloc_mmu_pages(vcpu);
-}
-
-void kvm_mmu_setup(struct kvm_vcpu *vcpu)
-{
-	MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
-
-	/*
-	 * kvm_mmu_setup() is called only on vCPU initialization.  
-	 * Therefore, no need to reset mmu roots as they are not yet
-	 * initialized.
-	 */
-	kvm_init_mmu(vcpu, false);
-}
-
-static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
-			struct kvm_memory_slot *slot,
-			struct kvm_page_track_notifier_node *node)
-{
-	kvm_mmu_invalidate_zap_all_pages(kvm);
-}
-
-void kvm_mmu_init_vm(struct kvm *kvm)
-{
-	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
-
-	node->track_write = kvm_mmu_pte_write;
-	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
-	kvm_page_track_register_notifier(kvm, node);
-}
-
-void kvm_mmu_uninit_vm(struct kvm *kvm)
-{
-	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
-
-	kvm_page_track_unregister_notifier(kvm, node);
-}
 
 /* The return value indicates if tlb flush on all vcpus is needed. */
 typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
@@ -5474,7 +5686,9 @@
 
 		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
 			if (flush && lock_flush_tlb) {
-				kvm_flush_remote_tlbs(kvm);
+				kvm_flush_remote_tlbs_with_address(kvm,
+						start_gfn,
+						iterator.gfn - start_gfn + 1);
 				flush = false;
 			}
 			cond_resched_lock(&kvm->mmu_lock);
@@ -5482,7 +5696,8 @@
 	}
 
 	if (flush && lock_flush_tlb) {
-		kvm_flush_remote_tlbs(kvm);
+		kvm_flush_remote_tlbs_with_address(kvm, start_gfn,
+						   end_gfn - start_gfn + 1);
 		flush = false;
 	}
 
@@ -5524,6 +5739,195 @@
 				 PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
 }
 
+static void free_mmu_pages(struct kvm_mmu *mmu)
+{
+	free_page((unsigned long)mmu->pae_root);
+	free_page((unsigned long)mmu->lm_root);
+}
+
+static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+	struct page *page;
+	int i;
+
+	/*
+	 * When using PAE paging, the four PDPTEs are treated as 'root' pages,
+	 * while the PDP table is a per-vCPU construct that's allocated at MMU
+	 * creation.  When emulating 32-bit mode, cr3 is only 32 bits even on
+	 * x86_64.  Therefore we need to allocate the PDP table in the first
+	 * 4GB of memory, which happens to fit the DMA32 zone.  Except for
+	 * SVM's 32-bit NPT support, TDP paging doesn't use PAE paging and can
+	 * skip allocating the PDP table.
+	 */
+	if (tdp_enabled && kvm_x86_ops->get_tdp_level(vcpu) > PT32E_ROOT_LEVEL)
+		return 0;
+
+	page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32);
+	if (!page)
+		return -ENOMEM;
+
+	mmu->pae_root = page_address(page);
+	for (i = 0; i < 4; ++i)
+		mmu->pae_root[i] = INVALID_PAGE;
+
+	return 0;
+}
+
+int kvm_mmu_create(struct kvm_vcpu *vcpu)
+{
+	uint i;
+	int ret;
+
+	vcpu->arch.mmu = &vcpu->arch.root_mmu;
+	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
+
+	vcpu->arch.root_mmu.root_hpa = INVALID_PAGE;
+	vcpu->arch.root_mmu.root_cr3 = 0;
+	vcpu->arch.root_mmu.translate_gpa = translate_gpa;
+	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+		vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+
+	vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE;
+	vcpu->arch.guest_mmu.root_cr3 = 0;
+	vcpu->arch.guest_mmu.translate_gpa = translate_gpa;
+	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+		vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+
+	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
+
+	ret = alloc_mmu_pages(vcpu, &vcpu->arch.guest_mmu);
+	if (ret)
+		return ret;
+
+	ret = alloc_mmu_pages(vcpu, &vcpu->arch.root_mmu);
+	if (ret)
+		goto fail_allocate_root;
+
+	return ret;
+ fail_allocate_root:
+	free_mmu_pages(&vcpu->arch.guest_mmu);
+	return ret;
+}
+
+#define BATCH_ZAP_PAGES	10
+static void kvm_zap_obsolete_pages(struct kvm *kvm)
+{
+	struct kvm_mmu_page *sp, *node;
+	int nr_zapped, batch = 0;
+
+restart:
+	list_for_each_entry_safe_reverse(sp, node,
+	      &kvm->arch.active_mmu_pages, link) {
+		/*
+		 * No obsolete valid page exists before a newly created page
+		 * since active_mmu_pages is a FIFO list.
+		 */
+		if (!is_obsolete_sp(kvm, sp))
+			break;
+
+		/*
+		 * Skip invalid pages with a non-zero root count, zapping pages
+		 * with a non-zero root count will never succeed, i.e. the page
+		 * will get thrown back on active_mmu_pages and we'll get stuck
+		 * in an infinite loop.
+		 */
+		if (sp->role.invalid && sp->root_count)
+			continue;
+
+		/*
+		 * No need to flush the TLB since we're only zapping shadow
+		 * pages with an obsolete generation number and all vCPUS have
+		 * loaded a new root, i.e. the shadow pages being zapped cannot
+		 * be in active use by the guest.
+		 */
+		if (batch >= BATCH_ZAP_PAGES &&
+		    cond_resched_lock(&kvm->mmu_lock)) {
+			batch = 0;
+			goto restart;
+		}
+
+		if (__kvm_mmu_prepare_zap_page(kvm, sp,
+				&kvm->arch.zapped_obsolete_pages, &nr_zapped)) {
+			batch += nr_zapped;
+			goto restart;
+		}
+	}
+
+	/*
+	 * Trigger a remote TLB flush before freeing the page tables to ensure
+	 * KVM is not in the middle of a lockless shadow page table walk, which
+	 * may reference the pages.
+	 */
+	kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages);
+}
+
+/*
+ * Fast invalidate all shadow pages and use lock-break technique
+ * to zap obsolete pages.
+ *
+ * It's required when memslot is being deleted or VM is being
+ * destroyed, in these cases, we should ensure that KVM MMU does
+ * not use any resource of the being-deleted slot or all slots
+ * after calling the function.
+ */
+static void kvm_mmu_zap_all_fast(struct kvm *kvm)
+{
+	lockdep_assert_held(&kvm->slots_lock);
+
+	spin_lock(&kvm->mmu_lock);
+	trace_kvm_mmu_zap_all_fast(kvm);
+
+	/*
+	 * Toggle mmu_valid_gen between '0' and '1'.  Because slots_lock is
+	 * held for the entire duration of zapping obsolete pages, it's
+	 * impossible for there to be multiple invalid generations associated
+	 * with *valid* shadow pages at any given time, i.e. there is exactly
+	 * one valid generation and (at most) one invalid generation.
+	 */
+	kvm->arch.mmu_valid_gen = kvm->arch.mmu_valid_gen ? 0 : 1;
+
+	/*
+	 * Notify all vcpus to reload its shadow page table and flush TLB.
+	 * Then all vcpus will switch to new shadow page table with the new
+	 * mmu_valid_gen.
+	 *
+	 * Note: we need to do this under the protection of mmu_lock,
+	 * otherwise, vcpu would purge shadow page but miss tlb flush.
+	 */
+	kvm_reload_remote_mmus(kvm);
+
+	kvm_zap_obsolete_pages(kvm);
+	spin_unlock(&kvm->mmu_lock);
+}
+
+static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
+{
+	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
+}
+
+static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
+			struct kvm_memory_slot *slot,
+			struct kvm_page_track_notifier_node *node)
+{
+	kvm_mmu_zap_all_fast(kvm);
+}
+
+void kvm_mmu_init_vm(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+	node->track_write = kvm_mmu_pte_write;
+	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
+	kvm_page_track_register_notifier(kvm, node);
+}
+
+void kvm_mmu_uninit_vm(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+	kvm_page_track_unregister_notifier(kvm, node);
+}
+
 void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 {
 	struct kvm_memslots *slots;
@@ -5580,12 +5984,13 @@
 	 * spte from present to present (changing the spte from present
 	 * to nonpresent will flush all the TLBs immediately), in other
 	 * words, the only case we care is mmu_spte_update() where we
-	 * haved checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE
+	 * have checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE
 	 * instead of PT_WRITABLE_MASK, that means it does not depend
 	 * on PT_WRITABLE_MASK anymore.
 	 */
 	if (flush)
-		kvm_flush_remote_tlbs(kvm);
+		kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
+			memslot->npages);
 }
 
 static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
@@ -5609,11 +6014,17 @@
 		 * the guest, and the guest page table is using 4K page size
 		 * mapping if the indirect sp has level = 1.
 		 */
-		if (sp->role.direct &&
-			!kvm_is_reserved_pfn(pfn) &&
-			PageTransCompoundMap(pfn_to_page(pfn))) {
-			drop_spte(kvm, sptep);
-			need_tlb_flush = 1;
+		if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
+		    !kvm_is_zone_device_pfn(pfn) &&
+		    PageTransCompoundMap(pfn_to_page(pfn))) {
+			pte_list_remove(rmap_head, sptep);
+
+			if (kvm_available_flush_tlb_with_range())
+				kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
+					KVM_PAGES_PER_HPAGE(sp->role.level));
+			else
+				need_tlb_flush = 1;
+
 			goto restart;
 		}
 	}
@@ -5649,7 +6060,8 @@
 	 * dirty_bitmap.
 	 */
 	if (flush)
-		kvm_flush_remote_tlbs(kvm);
+		kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
+				memslot->npages);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty);
 
@@ -5667,7 +6079,8 @@
 	lockdep_assert_held(&kvm->slots_lock);
 
 	if (flush)
-		kvm_flush_remote_tlbs(kvm);
+		kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
+				memslot->npages);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access);
 
@@ -5684,105 +6097,54 @@
 
 	/* see kvm_mmu_slot_leaf_clear_dirty */
 	if (flush)
-		kvm_flush_remote_tlbs(kvm);
+		kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
+				memslot->npages);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty);
 
-#define BATCH_ZAP_PAGES	10
-static void kvm_zap_obsolete_pages(struct kvm *kvm)
+void kvm_mmu_zap_all(struct kvm *kvm)
 {
 	struct kvm_mmu_page *sp, *node;
-	int batch = 0;
+	LIST_HEAD(invalid_list);
+	int ign;
 
+	spin_lock(&kvm->mmu_lock);
 restart:
-	list_for_each_entry_safe_reverse(sp, node,
-	      &kvm->arch.active_mmu_pages, link) {
-		int ret;
-
-		/*
-		 * No obsolete page exists before new created page since
-		 * active_mmu_pages is the FIFO list.
-		 */
-		if (!is_obsolete_sp(kvm, sp))
-			break;
-
-		/*
-		 * Since we are reversely walking the list and the invalid
-		 * list will be moved to the head, skip the invalid page
-		 * can help us to avoid the infinity list walking.
-		 */
-		if (sp->role.invalid)
+	list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) {
+		if (sp->role.invalid && sp->root_count)
 			continue;
-
-		/*
-		 * Need not flush tlb since we only zap the sp with invalid
-		 * generation number.
-		 */
-		if (batch >= BATCH_ZAP_PAGES &&
-		      cond_resched_lock(&kvm->mmu_lock)) {
-			batch = 0;
+		if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
 			goto restart;
-		}
-
-		ret = kvm_mmu_prepare_zap_page(kvm, sp,
-				&kvm->arch.zapped_obsolete_pages);
-		batch += ret;
-
-		if (ret)
+		if (cond_resched_lock(&kvm->mmu_lock))
 			goto restart;
 	}
 
-	/*
-	 * Should flush tlb before free page tables since lockless-walking
-	 * may use the pages.
-	 */
-	kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages);
-}
-
-/*
- * Fast invalidate all shadow pages and use lock-break technique
- * to zap obsolete pages.
- *
- * It's required when memslot is being deleted or VM is being
- * destroyed, in these cases, we should ensure that KVM MMU does
- * not use any resource of the being-deleted slot or all slots
- * after calling the function.
- */
-void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm)
-{
-	spin_lock(&kvm->mmu_lock);
-	trace_kvm_mmu_invalidate_zap_all_pages(kvm);
-	kvm->arch.mmu_valid_gen++;
-
-	/*
-	 * Notify all vcpus to reload its shadow page table
-	 * and flush TLB. Then all vcpus will switch to new
-	 * shadow page table with the new mmu_valid_gen.
-	 *
-	 * Note: we should do this under the protection of
-	 * mmu-lock, otherwise, vcpu would purge shadow page
-	 * but miss tlb flush.
-	 */
-	kvm_reload_remote_mmus(kvm);
-
-	kvm_zap_obsolete_pages(kvm);
+	kvm_mmu_commit_zap_page(kvm, &invalid_list);
 	spin_unlock(&kvm->mmu_lock);
 }
 
-static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
+void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 {
-	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
-}
+	WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
 
-void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots)
-{
+	gen &= MMIO_SPTE_GEN_MASK;
+
 	/*
-	 * The very rare case: if the generation-number is round,
+	 * Generation numbers are incremented in multiples of the number of
+	 * address spaces in order to provide unique generations across all
+	 * address spaces.  Strip what is effectively the address space
+	 * modifier prior to checking for a wrap of the MMIO generation so
+	 * that a wrap in any address space is detected.
+	 */
+	gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1);
+
+	/*
+	 * The very rare case: if the MMIO generation number has wrapped,
 	 * zap all shadow pages.
 	 */
-	if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) {
+	if (unlikely(gen == 0)) {
 		kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n");
-		kvm_mmu_invalidate_zap_all_pages(kvm);
+		kvm_mmu_zap_all_fast(kvm);
 	}
 }
 
@@ -5793,7 +6155,7 @@
 	int nr_to_scan = sc->nr_to_scan;
 	unsigned long freed = 0;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		int idx;
@@ -5814,7 +6176,7 @@
 		 * anyway.
 		 */
 		if (!kvm->arch.n_used_mmu_pages &&
-		      !kvm_has_zapped_obsolete_pages(kvm))
+		    !kvm_has_zapped_obsolete_pages(kvm))
 			continue;
 
 		idx = srcu_read_lock(&kvm->srcu);
@@ -5843,7 +6205,7 @@
 		break;
 	}
 
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	return freed;
 }
 
@@ -5865,12 +6227,101 @@
 	kmem_cache_destroy(mmu_page_header_cache);
 }
 
+static void kvm_set_mmio_spte_mask(void)
+{
+	u64 mask;
+
+	/*
+	 * Set the reserved bits and the present bit of an paging-structure
+	 * entry to generate page fault with PFER.RSV = 1.
+	 */
+
+	/*
+	 * Mask the uppermost physical address bit, which would be reserved as
+	 * long as the supported physical address width is less than 52.
+	 */
+	mask = 1ull << 51;
+
+	/* Set the present bit. */
+	mask |= 1ull;
+
+	/*
+	 * If reserved bit is not supported, clear the present bit to disable
+	 * mmio page fault.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52)
+		mask &= ~1ull;
+
+	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
+}
+
+static bool get_nx_auto_mode(void)
+{
+	/* Return true when CPU has the bug, and mitigations are ON */
+	return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off();
+}
+
+static void __set_nx_huge_pages(bool val)
+{
+	nx_huge_pages = itlb_multihit_kvm_mitigation = val;
+}
+
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
+{
+	bool old_val = nx_huge_pages;
+	bool new_val;
+
+	/* In "auto" mode deploy workaround only if CPU has the bug. */
+	if (sysfs_streq(val, "off"))
+		new_val = 0;
+	else if (sysfs_streq(val, "force"))
+		new_val = 1;
+	else if (sysfs_streq(val, "auto"))
+		new_val = get_nx_auto_mode();
+	else if (strtobool(val, &new_val) < 0)
+		return -EINVAL;
+
+	__set_nx_huge_pages(new_val);
+
+	if (new_val != old_val) {
+		struct kvm *kvm;
+
+		mutex_lock(&kvm_lock);
+
+		list_for_each_entry(kvm, &vm_list, vm_list) {
+			mutex_lock(&kvm->slots_lock);
+			kvm_mmu_zap_all_fast(kvm);
+			mutex_unlock(&kvm->slots_lock);
+
+			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+		}
+		mutex_unlock(&kvm_lock);
+	}
+
+	return 0;
+}
+
 int kvm_mmu_module_init(void)
 {
 	int ret = -ENOMEM;
 
+	if (nx_huge_pages == -1)
+		__set_nx_huge_pages(get_nx_auto_mode());
+
+	/*
+	 * MMU roles use union aliasing which is, generally speaking, an
+	 * undefined behavior. However, we supposedly know how compilers behave
+	 * and the current status quo is unlikely to change. Guardians below are
+	 * supposed to let us know if the assumption becomes false.
+	 */
+	BUILD_BUG_ON(sizeof(union kvm_mmu_page_role) != sizeof(u32));
+	BUILD_BUG_ON(sizeof(union kvm_mmu_extended_role) != sizeof(u32));
+	BUILD_BUG_ON(sizeof(union kvm_mmu_role) != sizeof(u64));
+
 	kvm_mmu_reset_all_pte_masks();
 
+	kvm_set_mmio_spte_mask();
+
 	pte_list_desc_cache = kmem_cache_create("pte_list_desc",
 					    sizeof(struct pte_list_desc),
 					    0, SLAB_ACCOUNT, NULL);
@@ -5898,12 +6349,12 @@
 }
 
 /*
- * Caculate mmu pages needed for kvm.
+ * Calculate mmu pages needed for kvm.
  */
-unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
 {
-	unsigned int nr_mmu_pages;
-	unsigned int  nr_pages = 0;
+	unsigned long nr_mmu_pages;
+	unsigned long nr_pages = 0;
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int i;
@@ -5916,8 +6367,7 @@
 	}
 
 	nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
-	nr_mmu_pages = max(nr_mmu_pages,
-			   (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+	nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
 
 	return nr_mmu_pages;
 }
@@ -5925,7 +6375,8 @@
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_unload(vcpu);
-	free_mmu_pages(vcpu);
+	free_mmu_pages(&vcpu->arch.root_mmu);
+	free_mmu_pages(&vcpu->arch.guest_mmu);
 	mmu_free_memory_caches(vcpu);
 }
 
@@ -5936,3 +6387,116 @@
 	unregister_shrinker(&mmu_shrinker);
 	mmu_audit_disable();
 }
+
+static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp)
+{
+	unsigned int old_val;
+	int err;
+
+	old_val = nx_huge_pages_recovery_ratio;
+	err = param_set_uint(val, kp);
+	if (err)
+		return err;
+
+	if (READ_ONCE(nx_huge_pages) &&
+	    !old_val && nx_huge_pages_recovery_ratio) {
+		struct kvm *kvm;
+
+		mutex_lock(&kvm_lock);
+
+		list_for_each_entry(kvm, &vm_list, vm_list)
+			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+
+		mutex_unlock(&kvm_lock);
+	}
+
+	return err;
+}
+
+static void kvm_recover_nx_lpages(struct kvm *kvm)
+{
+	int rcu_idx;
+	struct kvm_mmu_page *sp;
+	unsigned int ratio;
+	LIST_HEAD(invalid_list);
+	ulong to_zap;
+
+	rcu_idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+	to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0;
+	while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) {
+		/*
+		 * We use a separate list instead of just using active_mmu_pages
+		 * because the number of lpage_disallowed pages is expected to
+		 * be relatively small compared to the total.
+		 */
+		sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+				      struct kvm_mmu_page,
+				      lpage_disallowed_link);
+		WARN_ON_ONCE(!sp->lpage_disallowed);
+		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+		WARN_ON_ONCE(sp->lpage_disallowed);
+
+		if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+			kvm_mmu_commit_zap_page(kvm, &invalid_list);
+			if (to_zap)
+				cond_resched_lock(&kvm->mmu_lock);
+		}
+	}
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, rcu_idx);
+}
+
+static long get_nx_lpage_recovery_timeout(u64 start_time)
+{
+	return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio)
+		? start_time + 60 * HZ - get_jiffies_64()
+		: MAX_SCHEDULE_TIMEOUT;
+}
+
+static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
+{
+	u64 start_time;
+	long remaining_time;
+
+	while (true) {
+		start_time = get_jiffies_64();
+		remaining_time = get_nx_lpage_recovery_timeout(start_time);
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		while (!kthread_should_stop() && remaining_time > 0) {
+			schedule_timeout(remaining_time);
+			remaining_time = get_nx_lpage_recovery_timeout(start_time);
+			set_current_state(TASK_INTERRUPTIBLE);
+		}
+
+		set_current_state(TASK_RUNNING);
+
+		if (kthread_should_stop())
+			return 0;
+
+		kvm_recover_nx_lpages(kvm);
+	}
+}
+
+int kvm_mmu_post_init_vm(struct kvm *kvm)
+{
+	int err;
+
+	err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
+					  "kvm-nx-lpage-recovery",
+					  &kvm->arch.nx_lpage_recovery_thread);
+	if (!err)
+		kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
+
+	return err;
+}
+
+void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
+{
+	if (kvm->arch.nx_lpage_recovery_thread)
+		kthread_stop(kvm->arch.nx_lpage_recovery_thread);
+}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 1fab69c..d55674f 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -43,11 +43,6 @@
 #define PT32_ROOT_LEVEL 2
 #define PT32E_ROOT_LEVEL 3
 
-#define PT_PDPE_LEVEL 3
-#define PT_DIRECTORY_LEVEL 2
-#define PT_PAGE_TABLE_LEVEL 1
-#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1)
-
 static inline u64 rsvd_bits(int s, int e)
 {
 	if (e < s)
@@ -56,7 +51,7 @@
 	return ((1ULL << (e - s + 1)) - 1) << s;
 }
 
-void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value);
+void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask);
 
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
@@ -69,7 +64,7 @@
 int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 				u64 fault_address, char *insn, int insn_len);
 
-static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
 {
 	if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
 		return kvm->arch.n_max_mmu_pages -
@@ -80,7 +75,7 @@
 
 static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
 {
-	if (likely(vcpu->arch.mmu.root_hpa != INVALID_PAGE))
+	if (likely(vcpu->arch.mmu->root_hpa != INVALID_PAGE))
 		return 0;
 
 	return kvm_mmu_load(vcpu);
@@ -102,9 +97,9 @@
 
 static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu)
 {
-	if (VALID_PAGE(vcpu->arch.mmu.root_hpa))
-		vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa |
-					     kvm_get_active_pcid(vcpu));
+	if (VALID_PAGE(vcpu->arch.mmu->root_hpa))
+		vcpu->arch.mmu->set_cr3(vcpu, vcpu->arch.mmu->root_hpa |
+					      kvm_get_active_pcid(vcpu));
 }
 
 /*
@@ -208,7 +203,6 @@
 	return -(u32)fault & errcode;
 }
 
-void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
 void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
 
 void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
@@ -216,4 +210,8 @@
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
 int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+
+int kvm_mmu_post_init_vm(struct kvm *kvm);
+void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
+
 #endif
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 1272861..ca39f62 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * mmu_audit.c:
  *
@@ -11,10 +12,6 @@
  *   Avi Kivity   <avi@qumranet.com>
  *   Marcelo Tosatti <mtosatti@redhat.com>
  *   Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #include <linux/ratelimit.h>
@@ -59,19 +56,19 @@
 	int i;
 	struct kvm_mmu_page *sp;
 
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
 		return;
 
-	if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
-		hpa_t root = vcpu->arch.mmu.root_hpa;
+	if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+		hpa_t root = vcpu->arch.mmu->root_hpa;
 
 		sp = page_header(root);
-		__mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu.root_level);
+		__mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu->root_level);
 		return;
 	}
 
 	for (i = 0; i < 4; ++i) {
-		hpa_t root = vcpu->arch.mmu.pae_root[i];
+		hpa_t root = vcpu->arch.mmu->pae_root[i];
 
 		if (root && VALID_PAGE(root)) {
 			root &= PT64_BASE_ADDR_MASK;
@@ -122,7 +119,7 @@
 	hpa =  pfn << PAGE_SHIFT;
 	if ((*sptep & PT64_BASE_ADDR_MASK) != hpa)
 		audit_printk(vcpu->kvm, "levels %d pfn %llx hpa %llx "
-			     "ent %llxn", vcpu->arch.mmu.root_level, pfn,
+			     "ent %llxn", vcpu->arch.mmu->root_level, pfn,
 			     hpa, *sptep);
 }
 
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index c73bf4e..7ca8831 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -8,11 +8,11 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvmmmu
 
-#define KVM_MMU_PAGE_FIELDS			\
-	__field(unsigned long, mmu_valid_gen)	\
-	__field(__u64, gfn)			\
-	__field(__u32, role)			\
-	__field(__u32, root_count)		\
+#define KVM_MMU_PAGE_FIELDS		\
+	__field(__u8, mmu_valid_gen)	\
+	__field(__u64, gfn)		\
+	__field(__u32, role)		\
+	__field(__u32, root_count)	\
 	__field(bool, unsync)
 
 #define KVM_MMU_PAGE_ASSIGN(sp)				\
@@ -31,11 +31,11 @@
 								        \
 	role.word = __entry->role;					\
 									\
-	trace_seq_printf(p, "sp gen %lx gfn %llx l%u%s q%u%s %s%s"	\
+	trace_seq_printf(p, "sp gen %u gfn %llx l%u %u-byte q%u%s %s%s"	\
 			 " %snxe %sad root %u %s%c",			\
 			 __entry->mmu_valid_gen,			\
 			 __entry->gfn, role.level,			\
-			 role.cr4_pae ? " pae" : "",			\
+			 role.gpte_is_8_bytes ? 8 : 4,			\
 			 role.quadrant,					\
 			 role.direct ? " direct" : "",			\
 			 access_str[role.access],			\
@@ -283,12 +283,12 @@
 );
 
 TRACE_EVENT(
-	kvm_mmu_invalidate_zap_all_pages,
+	kvm_mmu_zap_all_fast,
 	TP_PROTO(struct kvm *kvm),
 	TP_ARGS(kvm),
 
 	TP_STRUCT__entry(
-		__field(unsigned long, mmu_valid_gen)
+		__field(__u8, mmu_valid_gen)
 		__field(unsigned int, mmu_used_pages)
 	),
 
@@ -297,7 +297,7 @@
 		__entry->mmu_used_pages = kvm->arch.n_used_mmu_pages;
 	),
 
-	TP_printk("kvm-mmu-valid-gen %lx used_pages %x",
+	TP_printk("kvm-mmu-valid-gen %u used_pages %x",
 		  __entry->mmu_valid_gen, __entry->mmu_used_pages
 	)
 );
@@ -325,6 +325,65 @@
 		  __entry->kvm_gen == __entry->spte_gen
 	)
 );
+
+TRACE_EVENT(
+	kvm_mmu_set_spte,
+	TP_PROTO(int level, gfn_t gfn, u64 *sptep),
+	TP_ARGS(level, gfn, sptep),
+
+	TP_STRUCT__entry(
+		__field(u64, gfn)
+		__field(u64, spte)
+		__field(u64, sptep)
+		__field(u8, level)
+		/* These depend on page entry type, so compute them now.  */
+		__field(bool, r)
+		__field(bool, x)
+		__field(u8, u)
+	),
+
+	TP_fast_assign(
+		__entry->gfn = gfn;
+		__entry->spte = *sptep;
+		__entry->sptep = virt_to_phys(sptep);
+		__entry->level = level;
+		__entry->r = shadow_present_mask || (__entry->spte & PT_PRESENT_MASK);
+		__entry->x = is_executable_pte(__entry->spte);
+		__entry->u = shadow_user_mask ? !!(__entry->spte & shadow_user_mask) : -1;
+	),
+
+	TP_printk("gfn %llx spte %llx (%s%s%s%s) level %d at %llx",
+		  __entry->gfn, __entry->spte,
+		  __entry->r ? "r" : "-",
+		  __entry->spte & PT_WRITABLE_MASK ? "w" : "-",
+		  __entry->x ? "x" : "-",
+		  __entry->u == -1 ? "" : (__entry->u ? "u" : "-"),
+		  __entry->level, __entry->sptep
+	)
+);
+
+TRACE_EVENT(
+	kvm_mmu_spte_requested,
+	TP_PROTO(gpa_t addr, int level, kvm_pfn_t pfn),
+	TP_ARGS(addr, level, pfn),
+
+	TP_STRUCT__entry(
+		__field(u64, gfn)
+		__field(u64, pfn)
+		__field(u8, level)
+	),
+
+	TP_fast_assign(
+		__entry->gfn = addr >> PAGE_SHIFT;
+		__entry->pfn = pfn | (__entry->gfn & (KVM_PAGES_PER_HPAGE(level) - 1));
+		__entry->level = level;
+	),
+
+	TP_printk("gfn %llx pfn %llx level %d",
+		  __entry->gfn, __entry->pfn, __entry->level
+	)
+);
+
 #endif /* _TRACE_KVMMMU_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index e9ea2d4..25ce3ed 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * vMTRR implementation
  *
@@ -11,9 +12,6 @@
  *   Marcelo Tosatti <mtosatti@redhat.com>
  *   Paolo Bonzini <pbonzini@redhat.com>
  *   Xiao Guangrong <guangrong.xiao@linux.intel.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
  */
 
 #include <linux/kvm_host.h>
@@ -48,11 +46,6 @@
 	return false;
 }
 
-static bool valid_pat_type(unsigned t)
-{
-	return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
-}
-
 static bool valid_mtrr_type(unsigned t)
 {
 	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
@@ -67,10 +60,7 @@
 		return false;
 
 	if (msr == MSR_IA32_CR_PAT) {
-		for (i = 0; i < 8; i++)
-			if (!valid_pat_type((data >> (i * 8)) & 0xff))
-				return false;
-		return true;
+		return kvm_pat_valid(data);
 	} else if (msr == MSR_MTRRdefType) {
 		if (data & ~0xcff)
 			return false;
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 3052a59..3521e2d 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Support KVM gust page tracking
  *
@@ -8,9 +9,6 @@
  *
  * Author:
  *   Xiao Guangrong <guangrong.xiao@linux.intel.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
  */
 
 #include <linux/kvm_host.h>
@@ -42,7 +40,7 @@
 	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
 		slot->arch.gfn_track[i] =
 			kvcalloc(npages, sizeof(*slot->arch.gfn_track[i]),
-				 GFP_KERNEL);
+				 GFP_KERNEL_ACCOUNT);
 		if (!slot->arch.gfn_track[i])
 			goto track_free;
 	}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 14ffd97..97b21e7 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Kernel-based Virtual Machine driver for Linux
  *
@@ -12,10 +13,6 @@
  * Authors:
  *   Yaniv Kamay  <yaniv@qumranet.com>
  *   Avi Kivity   <avi@qumranet.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 /*
@@ -140,16 +137,36 @@
 	pt_element_t *table;
 	struct page *page;
 
-	npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page);
-	/* Check if the user is doing something meaningless. */
-	if (unlikely(npages != 1))
-		return -EFAULT;
+	npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
+	if (likely(npages == 1)) {
+		table = kmap_atomic(page);
+		ret = CMPXCHG(&table[index], orig_pte, new_pte);
+		kunmap_atomic(table);
 
-	table = kmap_atomic(page);
-	ret = CMPXCHG(&table[index], orig_pte, new_pte);
-	kunmap_atomic(table);
+		kvm_release_page_dirty(page);
+	} else {
+		struct vm_area_struct *vma;
+		unsigned long vaddr = (unsigned long)ptep_user & PAGE_MASK;
+		unsigned long pfn;
+		unsigned long paddr;
 
-	kvm_release_page_dirty(page);
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma_intersection(current->mm, vaddr, vaddr + PAGE_SIZE);
+		if (!vma || !(vma->vm_flags & VM_PFNMAP)) {
+			up_read(&current->mm->mmap_sem);
+			return -EFAULT;
+		}
+		pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+		paddr = pfn << PAGE_SHIFT;
+		table = memremap(paddr, PAGE_SIZE, MEMREMAP_WB);
+		if (!table) {
+			up_read(&current->mm->mmap_sem);
+			return -EFAULT;
+		}
+		ret = CMPXCHG(&table[index], orig_pte, new_pte);
+		memunmap(table);
+		up_read(&current->mm->mmap_sem);
+	}
 
 	return (ret != orig_pte);
 }
@@ -158,14 +175,15 @@
 				  struct kvm_mmu_page *sp, u64 *spte,
 				  u64 gpte)
 {
-	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+	if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
 		goto no_present;
 
 	if (!FNAME(is_present_gpte)(gpte))
 		goto no_present;
 
 	/* if accessed bit is not supported prefetch non accessed gpte */
-	if (PT_HAVE_ACCESSED_DIRTY(&vcpu->arch.mmu) && !(gpte & PT_GUEST_ACCESSED_MASK))
+	if (PT_HAVE_ACCESSED_DIRTY(vcpu->arch.mmu) &&
+	    !(gpte & PT_GUEST_ACCESSED_MASK))
 		goto no_present;
 
 	return false;
@@ -480,7 +498,7 @@
 static int FNAME(walk_addr)(struct guest_walker *walker,
 			    struct kvm_vcpu *vcpu, gva_t addr, u32 access)
 {
-	return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.mmu, addr,
+	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
 					access);
 }
 
@@ -509,7 +527,7 @@
 
 	gfn = gpte_to_gfn(gpte);
 	pte_access = sp->role.access & FNAME(gpte_access)(gpte);
-	FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte);
+	FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
 	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
 			no_dirty_log && (pte_access & ACC_WRITE_MASK));
 	if (is_error_pfn(pfn))
@@ -522,6 +540,7 @@
 	mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn,
 		     true, true);
 
+	kvm_release_pfn_clean(pfn);
 	return true;
 }
 
@@ -595,16 +614,18 @@
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
-			 kvm_pfn_t pfn, bool map_writable, bool prefault)
+			 kvm_pfn_t pfn, bool map_writable, bool prefault,
+			 bool lpage_disallowed)
 {
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
 	unsigned direct_access, access = gw->pt_access;
 	int top_level, ret;
+	gfn_t gfn, base_gfn;
 
 	direct_access = gw->pte_access;
 
-	top_level = vcpu->arch.mmu.root_level;
+	top_level = vcpu->arch.mmu->root_level;
 	if (top_level == PT32E_ROOT_LEVEL)
 		top_level = PT32_ROOT_LEVEL;
 	/*
@@ -616,7 +637,7 @@
 	if (FNAME(gpte_changed)(vcpu, gw, top_level))
 		goto out_gpte_changed;
 
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
 		goto out_gpte_changed;
 
 	for (shadow_walk_init(&it, vcpu, addr);
@@ -645,35 +666,48 @@
 			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
-	for (;
-	     shadow_walk_okay(&it) && it.level > hlevel;
-	     shadow_walk_next(&it)) {
-		gfn_t direct_gfn;
+	/*
+	 * FNAME(page_fault) might have clobbered the bottom bits of
+	 * gw->gfn, restore them from the virtual address.
+	 */
+	gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT);
+	base_gfn = gfn;
 
+	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
+
+	for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
 		clear_sp_write_flooding_count(it.sptep);
+
+		/*
+		 * We cannot overwrite existing page tables with an NX
+		 * large page, as the leaf could be executable.
+		 */
+		disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel);
+
+		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		if (it.level == hlevel)
+			break;
+
 		validate_direct_spte(vcpu, it.sptep, direct_access);
 
 		drop_large_spte(vcpu, it.sptep);
 
-		if (is_shadow_present_pte(*it.sptep))
-			continue;
-
-		direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
-
-		sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
-				      true, direct_access);
-		link_shadow_page(vcpu, it.sptep, sp);
+		if (!is_shadow_present_pte(*it.sptep)) {
+			sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
+					      it.level - 1, true, direct_access);
+			link_shadow_page(vcpu, it.sptep, sp);
+			if (lpage_disallowed)
+				account_huge_nx_page(vcpu->kvm, sp);
+		}
 	}
 
-	clear_sp_write_flooding_count(it.sptep);
 	ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
-			   it.level, gw->gfn, pfn, prefault, map_writable);
+			   it.level, base_gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
-
+	++vcpu->stat.pf_fixed;
 	return ret;
 
 out_gpte_changed:
-	kvm_release_pfn_clean(pfn);
 	return RET_PF_RETRY;
 }
 
@@ -740,9 +774,11 @@
 	int r;
 	kvm_pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
-	bool force_pt_level = false;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
+	bool force_pt_level = lpage_disallowed;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -821,6 +857,7 @@
 			walker.pte_access &= ~ACC_EXEC_MASK;
 	}
 
+	r = RET_PF_RETRY;
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
@@ -829,19 +866,15 @@
 	if (make_mmu_pages_available(vcpu) < 0)
 		goto out_unlock;
 	if (!force_pt_level)
-		transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
+		transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level);
 	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
-			 level, pfn, map_writable, prefault);
-	++vcpu->stat.pf_fixed;
+			 level, pfn, map_writable, prefault, lpage_disallowed);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
-	spin_unlock(&vcpu->kvm->mmu_lock);
-
-	return r;
 
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
-	return RET_PF_RETRY;
+	return r;
 }
 
 static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
@@ -893,7 +926,8 @@
 			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
 
 			if (mmu_page_zap_pte(vcpu->kvm, sp, sptep))
-				kvm_flush_remote_tlbs(vcpu->kvm);
+				kvm_flush_remote_tlbs_with_address(vcpu->kvm,
+					sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));
 
 			if (!rmap_can_add(vcpu))
 				break;
@@ -1004,7 +1038,7 @@
 		gfn = gpte_to_gfn(gpte);
 		pte_access = sp->role.access;
 		pte_access &= FNAME(gpte_access)(gpte);
-		FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte);
+		FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
 
 		if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access,
 		      &nr_present))
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 58ead7d..46875bb 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Kernel-based Virtual Machine -- Performance Monitoring Unit support
  *
@@ -7,10 +8,6 @@
  *   Avi Kivity   <avi@redhat.com>
  *   Gleb Natapov <gleb@redhat.com>
  *   Wei Huang    <wei@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #include <linux/types.h>
@@ -22,6 +19,9 @@
 #include "lapic.h"
 #include "pmu.h"
 
+/* This is enough to filter the vast majority of currently defined events. */
+#define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300
+
 /* NOTE:
  * - Each perf counter is defined as "struct kvm_pmc";
  * - There are two types of perf counters: general purpose (gp) and fixed.
@@ -131,8 +131,8 @@
 						 intr ? kvm_perf_overflow_intr :
 						 kvm_perf_overflow, pmc);
 	if (IS_ERR(event)) {
-		printk_once("kvm_pmu: event creation failed %ld\n",
-			    PTR_ERR(event));
+		pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n",
+			    PTR_ERR(event), pmc->idx);
 		return;
 	}
 
@@ -144,6 +144,10 @@
 {
 	unsigned config, type = PERF_TYPE_RAW;
 	u8 event_select, unit_mask;
+	struct kvm *kvm = pmc->vcpu->kvm;
+	struct kvm_pmu_event_filter *filter;
+	int i;
+	bool allow_event = true;
 
 	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
 		printk_once("kvm pmu: pin control bit is ignored\n");
@@ -155,6 +159,22 @@
 	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
 		return;
 
+	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
+	if (filter) {
+		for (i = 0; i < filter->nevents; i++)
+			if (filter->events[i] ==
+			    (eventsel & AMD64_RAW_EVENT_MASK_NB))
+				break;
+		if (filter->action == KVM_PMU_EVENT_ALLOW &&
+		    i == filter->nevents)
+			allow_event = false;
+		if (filter->action == KVM_PMU_EVENT_DENY &&
+		    i < filter->nevents)
+			allow_event = false;
+	}
+	if (!allow_event)
+		return;
+
 	event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
 	unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 
@@ -186,12 +206,24 @@
 {
 	unsigned en_field = ctrl & 0x3;
 	bool pmi = ctrl & 0x8;
+	struct kvm_pmu_event_filter *filter;
+	struct kvm *kvm = pmc->vcpu->kvm;
 
 	pmc_stop_counter(pmc);
 
 	if (!en_field || !pmc_is_enabled(pmc))
 		return;
 
+	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
+	if (filter) {
+		if (filter->action == KVM_PMU_EVENT_DENY &&
+		    test_bit(idx, (ulong *)&filter->fixed_counter_bitmap))
+			return;
+		if (filter->action == KVM_PMU_EVENT_ALLOW &&
+		    !test_bit(idx, (ulong *)&filter->fixed_counter_bitmap))
+			return;
+	}
+
 	pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
 			      kvm_x86_ops->pmu_ops->find_fixed_event(idx),
 			      !(en_field & 0x2), /* exclude user */
@@ -264,10 +296,10 @@
 		ctr_val = rdtsc();
 		break;
 	case VMWARE_BACKDOOR_PMC_REAL_TIME:
-		ctr_val = ktime_get_boot_ns();
+		ctr_val = ktime_get_boottime_ns();
 		break;
 	case VMWARE_BACKDOOR_PMC_APPARENT_TIME:
-		ctr_val = ktime_get_boot_ns() +
+		ctr_val = ktime_get_boottime_ns() +
 			vcpu->kvm->arch.kvmclock_offset;
 		break;
 	default:
@@ -281,21 +313,21 @@
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 {
 	bool fast_mode = idx & (1u << 31);
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
-	u64 ctr_val;
+	u64 mask = fast_mode ? ~0u : ~0ull;
+
+	if (!pmu->version)
+		return 1;
 
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 
-	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx);
+	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask);
 	if (!pmc)
 		return 1;
 
-	ctr_val = pmc_read_counter(pmc);
-	if (fast_mode)
-		ctr_val = (u32)ctr_val;
-
-	*data = ctr_val;
+	*data = pmc_read_counter(pmc) & mask;
 	return 0;
 }
 
@@ -351,3 +383,46 @@
 {
 	kvm_pmu_reset(vcpu);
 }
+
+int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_pmu_event_filter tmp, *filter;
+	size_t size;
+	int r;
+
+	if (copy_from_user(&tmp, argp, sizeof(tmp)))
+		return -EFAULT;
+
+	if (tmp.action != KVM_PMU_EVENT_ALLOW &&
+	    tmp.action != KVM_PMU_EVENT_DENY)
+		return -EINVAL;
+
+	if (tmp.flags != 0)
+		return -EINVAL;
+
+	if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS)
+		return -E2BIG;
+
+	size = struct_size(filter, events, tmp.nevents);
+	filter = kmalloc(size, GFP_KERNEL_ACCOUNT);
+	if (!filter)
+		return -ENOMEM;
+
+	r = -EFAULT;
+	if (copy_from_user(filter, argp, size))
+		goto cleanup;
+
+	/* Ensure nevents can't be changed between the user copies. */
+	*filter = tmp;
+
+	mutex_lock(&kvm->lock);
+	rcu_swap_protected(kvm->arch.pmu_event_filter, filter,
+			   mutex_is_locked(&kvm->lock));
+	mutex_unlock(&kvm->lock);
+
+	synchronize_srcu_expedited(&kvm->srcu);
+	r = 0;
+cleanup:
+	kfree(filter);
+	return r;
+}
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index ba8898e..58265f7 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -25,7 +25,8 @@
 	unsigned (*find_fixed_event)(int idx);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
-	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx);
+	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx,
+					  u64 *mask);
 	int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
@@ -117,6 +118,7 @@
 void kvm_pmu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_init(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
+int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp);
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx);
 
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 1495a73..c838838 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * KVM PMU support for AMD
  *
@@ -6,9 +7,6 @@
  * Author:
  *   Wei Huang <wei@redhat.com>
  *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  * Implementation is based on pmu_intel.c file
  */
 #include <linux/types.h>
@@ -186,7 +184,7 @@
 }
 
 /* idx is the ECX register of RDPMC instruction */
-static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx)
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *counters;
@@ -269,10 +267,10 @@
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
 	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->nr_arch_fixed_counters = 0;
-	pmu->version = 0;
 	pmu->global_status = 0;
 }
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f1d3fe5..c5673bd 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Kernel-based Virtual Machine driver for Linux
  *
@@ -9,10 +10,6 @@
  * Authors:
  *   Yaniv Kamay  <yaniv@qumranet.com>
  *   Avi Kivity   <avi@qumranet.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #define pr_fmt(fmt) "SVM: " fmt
@@ -71,10 +68,8 @@
 #define SEG_TYPE_LDT 2
 #define SEG_TYPE_BUSY_TSS16 3
 
-#define SVM_FEATURE_NPT            (1 <<  0)
 #define SVM_FEATURE_LBRV           (1 <<  1)
 #define SVM_FEATURE_SVML           (1 <<  2)
-#define SVM_FEATURE_NRIP           (1 <<  3)
 #define SVM_FEATURE_TSC_RATE       (1 <<  4)
 #define SVM_FEATURE_VMCB_CLEAN     (1 <<  5)
 #define SVM_FEATURE_FLUSH_ASID     (1 <<  6)
@@ -145,7 +140,6 @@
 
 	/* Struct members for AVIC */
 	u32 avic_vm_id;
-	u32 ldr_mode;
 	struct page *avic_logical_id_table_page;
 	struct page *avic_physical_id_table_page;
 	struct hlist_node hnode;
@@ -236,6 +230,7 @@
 	bool nrips_enabled	: 1;
 
 	u32 ldr_reg;
+	u32 dfr_reg;
 	struct page *avic_backing_page;
 	u64 *avic_physical_id_cache;
 	bool avic_is_running;
@@ -262,6 +257,7 @@
 };
 
 #define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK	(0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT			31
 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK		(1 << 31)
 
 #define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK	(0xFFULL)
@@ -366,6 +362,10 @@
 module_param(avic, int, S_IRUGO);
 #endif
 
+/* enable/disable Next RIP Save */
+static int nrips = true;
+module_param(nrips, int, 0444);
+
 /* enable/disable Virtual VMLOAD VMSAVE */
 static int vls = true;
 module_param(vls, int, 0444);
@@ -378,6 +378,9 @@
 static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
 module_param(sev, int, 0444);
 
+static bool __read_mostly dump_invalid_vmcb = 0;
+module_param(dump_invalid_vmcb, bool, 0644);
+
 static u8 rsm_ins_bytes[] = "\x0f\xaa";
 
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
@@ -675,11 +678,6 @@
 
 static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
 
-struct svm_init_data {
-	int cpu;
-	int r;
-};
-
 static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
 
 #define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
@@ -711,17 +709,17 @@
 
 static inline void clgi(void)
 {
-	asm volatile (__ex(SVM_CLGI));
+	asm volatile (__ex("clgi"));
 }
 
 static inline void stgi(void)
 {
-	asm volatile (__ex(SVM_STGI));
+	asm volatile (__ex("stgi"));
 }
 
 static inline void invlpga(unsigned long addr, u32 asid)
 {
-	asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid));
+	asm volatile (__ex("invlpga %1, %0") : : "c"(asid), "a"(addr));
 }
 
 static int get_npt_level(struct kvm_vcpu *vcpu)
@@ -736,8 +734,14 @@
 static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	vcpu->arch.efer = efer;
-	if (!npt_enabled && !(efer & EFER_LMA))
-		efer &= ~EFER_LME;
+
+	if (!npt_enabled) {
+		/* Shadow paging assumes NX to be available.  */
+		efer |= EFER_NX;
+
+		if (!(efer & EFER_LMA))
+			efer &= ~EFER_LME;
+	}
 
 	to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME;
 	mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
@@ -770,27 +774,27 @@
 
 }
 
-static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
+static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm->vmcb->control.next_rip != 0) {
+	if (nrips && svm->vmcb->control.next_rip != 0) {
 		WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
 	}
 
 	if (!svm->next_rip) {
-		if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) !=
-				EMULATE_DONE)
-			printk(KERN_DEBUG "%s: NOP\n", __func__);
-		return;
+		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
+			return 0;
+	} else {
+		if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE)
+			pr_err("%s: ip 0x%lx next 0x%llx\n",
+			       __func__, kvm_rip_read(vcpu), svm->next_rip);
+		kvm_rip_write(vcpu, svm->next_rip);
 	}
-	if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE)
-		printk(KERN_ERR "%s: ip 0x%lx next 0x%llx\n",
-		       __func__, kvm_rip_read(vcpu), svm->next_rip);
-
-	kvm_rip_write(vcpu, svm->next_rip);
 	svm_set_interrupt_shadow(vcpu, 0);
+
+	return 1;
 }
 
 static void svm_queue_exception(struct kvm_vcpu *vcpu)
@@ -809,7 +813,9 @@
 	    nested_svm_check_exception(svm, nr, has_error_code, error_code))
 		return;
 
-	if (nr == BP_VECTOR && !static_cpu_has(X86_FEATURE_NRIPS)) {
+	kvm_deliver_exception_payload(&svm->vcpu);
+
+	if (nr == BP_VECTOR && !nrips) {
 		unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
 
 		/*
@@ -819,7 +825,7 @@
 		 * raises a fault that is not intercepted. Still better than
 		 * failing in all cases.
 		 */
-		skip_emulated_instruction(&svm->vcpu);
+		(void)skip_emulated_instruction(&svm->vcpu);
 		rip = kvm_rip_read(&svm->vcpu);
 		svm->int3_rip = rip + svm->vmcb->save.cs.base;
 		svm->int3_injected = rip - old_rip;
@@ -1267,11 +1273,11 @@
 							pause_filter_count_grow,
 							pause_filter_count_max);
 
-	if (control->pause_filter_count != old)
+	if (control->pause_filter_count != old) {
 		mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
-
-	trace_kvm_ple_window_grow(vcpu->vcpu_id,
-				  control->pause_filter_count, old);
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    control->pause_filter_count, old);
+	}
 }
 
 static void shrink_ple_window(struct kvm_vcpu *vcpu)
@@ -1285,11 +1291,11 @@
 						    pause_filter_count,
 						    pause_filter_count_shrink,
 						    pause_filter_count);
-	if (control->pause_filter_count != old)
+	if (control->pause_filter_count != old) {
 		mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
-
-	trace_kvm_ple_window_shrink(vcpu->vcpu_id,
-				    control->pause_filter_count, old);
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    control->pause_filter_count, old);
+	}
 }
 
 static __init int svm_hardware_setup(void)
@@ -1366,6 +1372,11 @@
 	} else
 		kvm_disable_tdp();
 
+	if (nrips) {
+		if (!boot_cpu_has(X86_FEATURE_NRIPS))
+			nrips = false;
+	}
+
 	if (avic) {
 		if (!npt_enabled ||
 		    !boot_cpu_has(X86_FEATURE_AVIC) ||
@@ -1454,10 +1465,11 @@
 		g_tsc_offset = svm->vmcb->control.tsc_offset -
 			       svm->nested.hsave->control.tsc_offset;
 		svm->nested.hsave->control.tsc_offset = offset;
-	} else
-		trace_kvm_write_tsc_offset(vcpu->vcpu_id,
-					   svm->vmcb->control.tsc_offset,
-					   offset);
+	}
+
+	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
+				   svm->vmcb->control.tsc_offset - g_tsc_offset,
+				   offset);
 
 	svm->vmcb->control.tsc_offset = offset + g_tsc_offset;
 
@@ -1534,6 +1546,7 @@
 	set_intercept(svm, INTERCEPT_SKINIT);
 	set_intercept(svm, INTERCEPT_WBINVD);
 	set_intercept(svm, INTERCEPT_XSETBV);
+	set_intercept(svm, INTERCEPT_RDPRU);
 	set_intercept(svm, INTERCEPT_RSM);
 
 	if (!kvm_mwait_in_guest(svm->vcpu.kvm)) {
@@ -1706,7 +1719,6 @@
 	if (!entry)
 		return -EINVAL;
 
-	new_entry = READ_ONCE(*entry);
 	new_entry = __sme_set((page_to_phys(svm->avic_backing_page) &
 			      AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
 			      AVIC_PHYSICAL_ID_ENTRY_VALID_MASK);
@@ -1797,15 +1809,16 @@
 	/* Avoid using vmalloc for smaller buffers. */
 	size = npages * sizeof(struct page *);
 	if (size > PAGE_SIZE)
-		pages = vmalloc(size);
+		pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO,
+				  PAGE_KERNEL);
 	else
-		pages = kmalloc(size, GFP_KERNEL);
+		pages = kmalloc(size, GFP_KERNEL_ACCOUNT);
 
 	if (!pages)
 		return NULL;
 
 	/* Pin the user virtual address. */
-	npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
+	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
 	if (npinned != npages) {
 		pr_err("SEV: Failure locking %lu pages.\n", npages);
 		goto err;
@@ -1867,7 +1880,9 @@
 
 static struct kvm *svm_vm_alloc(void)
 {
-	struct kvm_svm *kvm_svm = vzalloc(sizeof(struct kvm_svm));
+	struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm),
+					    GFP_KERNEL_ACCOUNT | __GFP_ZERO,
+					    PAGE_KERNEL);
 	return &kvm_svm->kvm;
 }
 
@@ -1942,7 +1957,7 @@
 		return 0;
 
 	/* Allocating physical APIC ID table (4KB) */
-	p_page = alloc_page(GFP_KERNEL);
+	p_page = alloc_page(GFP_KERNEL_ACCOUNT);
 	if (!p_page)
 		goto free_avic;
 
@@ -1950,7 +1965,7 @@
 	clear_page(page_address(p_page));
 
 	/* Allocating logical APIC ID table (4KB) */
-	l_page = alloc_page(GFP_KERNEL);
+	l_page = alloc_page(GFP_KERNEL_ACCOUNT);
 	if (!l_page)
 		goto free_avic;
 
@@ -2022,7 +2037,11 @@
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
-	if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
+	/*
+	 * Since the host physical APIC id is 8 bits,
+	 * we can support host APIC ID upto 255.
+	 */
+	if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
 		return;
 
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
@@ -2089,7 +2108,7 @@
 	init_vmcb(svm);
 
 	kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, true);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
+	kvm_rdx_write(vcpu, eax);
 
 	if (kvm_vcpu_apicv_active(vcpu) && !init_event)
 		avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE);
@@ -2108,6 +2127,7 @@
 
 	INIT_LIST_HEAD(&svm->ir_list);
 	spin_lock_init(&svm->ir_list_lock);
+	svm->dfr_reg = APIC_DFR_FLAT;
 
 	return ret;
 }
@@ -2121,30 +2141,49 @@
 	struct page *nested_msrpm_pages;
 	int err;
 
-	svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	BUILD_BUG_ON_MSG(offsetof(struct vcpu_svm, vcpu) != 0,
+		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
+
+	svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
 	if (!svm) {
 		err = -ENOMEM;
 		goto out;
 	}
 
+	svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+						     GFP_KERNEL_ACCOUNT);
+	if (!svm->vcpu.arch.user_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+		err = -ENOMEM;
+		goto free_partial_svm;
+	}
+
+	svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
+						     GFP_KERNEL_ACCOUNT);
+	if (!svm->vcpu.arch.guest_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
+		err = -ENOMEM;
+		goto free_user_fpu;
+	}
+
 	err = kvm_vcpu_init(&svm->vcpu, kvm, id);
 	if (err)
 		goto free_svm;
 
 	err = -ENOMEM;
-	page = alloc_page(GFP_KERNEL);
+	page = alloc_page(GFP_KERNEL_ACCOUNT);
 	if (!page)
 		goto uninit;
 
-	msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
+	msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
 	if (!msrpm_pages)
 		goto free_page1;
 
-	nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
+	nested_msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
 	if (!nested_msrpm_pages)
 		goto free_page2;
 
-	hsave_page = alloc_page(GFP_KERNEL);
+	hsave_page = alloc_page(GFP_KERNEL_ACCOUNT);
 	if (!hsave_page)
 		goto free_page3;
 
@@ -2186,6 +2225,10 @@
 uninit:
 	kvm_vcpu_uninit(&svm->vcpu);
 free_svm:
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
+free_partial_svm:
 	kmem_cache_free(kvm_vcpu_cache, svm);
 out:
 	return ERR_PTR(err);
@@ -2215,6 +2258,8 @@
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
 }
 
@@ -2679,6 +2724,7 @@
 static int db_interception(struct vcpu_svm *svm)
 {
 	struct kvm_run *kvm_run = svm->vcpu.run;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	if (!(svm->vcpu.guest_debug &
 	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
@@ -2689,6 +2735,8 @@
 
 	if (svm->nmi_singlestep) {
 		disable_nmi_singlestep(svm);
+		/* Make sure we check for pending NMIs upon entry */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
 	}
 
 	if (svm->vcpu.guest_debug &
@@ -2728,17 +2776,18 @@
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	u32 error_code = svm->vmcb->control.exit_info_1;
-	int er;
 
 	WARN_ON_ONCE(!enable_vmware_backdoor);
 
-	er = kvm_emulate_instruction(vcpu,
-		EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL);
-	if (er == EMULATE_USER_EXIT)
-		return 0;
-	else if (er != EMULATE_DONE)
+	/*
+	 * VMware backdoor emulation on #GP interception only handles IN{S},
+	 * OUT{S}, and RDPMC, none of which generate a non-zero error code.
+	 */
+	if (error_code) {
 		kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
-	return 1;
+		return 1;
+	}
+	return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP);
 }
 
 static bool is_erratum_383(void)
@@ -2836,7 +2885,7 @@
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
 	if (string)
-		return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
+		return kvm_emulate_instruction(vcpu, 0);
 
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
@@ -2863,13 +2912,11 @@
 
 static int halt_interception(struct vcpu_svm *svm)
 {
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 1;
 	return kvm_emulate_halt(&svm->vcpu);
 }
 
 static int vmmcall_interception(struct vcpu_svm *svm)
 {
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	return kvm_emulate_hypercall(&svm->vcpu);
 }
 
@@ -2935,19 +2982,22 @@
 static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 {
 	WARN_ON(mmu_is_nested(vcpu));
+
+	vcpu->arch.mmu = &vcpu->arch.guest_mmu;
 	kvm_init_shadow_mmu(vcpu);
-	vcpu->arch.mmu.set_cr3           = nested_svm_set_tdp_cr3;
-	vcpu->arch.mmu.get_cr3           = nested_svm_get_tdp_cr3;
-	vcpu->arch.mmu.get_pdptr         = nested_svm_get_tdp_pdptr;
-	vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
-	vcpu->arch.mmu.shadow_root_level = get_npt_level(vcpu);
-	reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
+	vcpu->arch.mmu->set_cr3           = nested_svm_set_tdp_cr3;
+	vcpu->arch.mmu->get_cr3           = nested_svm_get_tdp_cr3;
+	vcpu->arch.mmu->get_pdptr         = nested_svm_get_tdp_pdptr;
+	vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit;
+	vcpu->arch.mmu->shadow_root_level = get_npt_level(vcpu);
+	reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu);
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
 }
 
 static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+	vcpu->arch.mmu = &vcpu->arch.root_mmu;
+	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
 }
 
 static int nested_svm_check_permissions(struct vcpu_svm *svm)
@@ -2983,16 +3033,13 @@
 	svm->vmcb->control.exit_info_1 = error_code;
 
 	/*
-	 * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception.
-	 * The fix is to add the ancillary datum (CR2 or DR6) to structs
-	 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be
-	 * written only when inject_pending_event runs (DR6 would written here
-	 * too).  This should be conditional on a new capability---if the
-	 * capability is disabled, kvm_multiple_exception would write the
-	 * ancillary information to CR2 or DR6, for backwards ABI-compatibility.
+	 * EXITINFO2 is undefined for all exception intercepts other
+	 * than #PF.
 	 */
 	if (svm->vcpu.arch.exception.nested_apf)
 		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
+	else if (svm->vcpu.arch.exception.has_payload)
+		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload;
 	else
 		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
 
@@ -3054,32 +3101,6 @@
 	return false;
 }
 
-static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
-{
-	struct page *page;
-
-	might_sleep();
-
-	page = kvm_vcpu_gfn_to_page(&svm->vcpu, gpa >> PAGE_SHIFT);
-	if (is_error_page(page))
-		goto error;
-
-	*_page = page;
-
-	return kmap(page);
-
-error:
-	kvm_inject_gp(&svm->vcpu, 0);
-
-	return NULL;
-}
-
-static void nested_svm_unmap(struct page *page)
-{
-	kunmap(page);
-	kvm_release_page_dirty(page);
-}
-
 static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 {
 	unsigned port, size, iopm_len;
@@ -3276,14 +3297,17 @@
 	dst->event_inj_err        = from->event_inj_err;
 	dst->nested_cr3           = from->nested_cr3;
 	dst->virt_ext              = from->virt_ext;
+	dst->pause_filter_count   = from->pause_filter_count;
+	dst->pause_filter_thresh  = from->pause_filter_thresh;
 }
 
 static int nested_svm_vmexit(struct vcpu_svm *svm)
 {
+	int rc;
 	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 
 	trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
 				       vmcb->control.exit_info_1,
@@ -3292,9 +3316,14 @@
 				       vmcb->control.exit_int_info_err,
 				       KVM_ISA_SVM);
 
-	nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page);
-	if (!nested_vmcb)
+	rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb), &map);
+	if (rc) {
+		if (rc == -EINVAL)
+			kvm_inject_gp(&svm->vcpu, 0);
 		return 1;
+	}
+
+	nested_vmcb = map.hva;
 
 	/* Exit Guest-Mode */
 	leave_guest_mode(&svm->vcpu);
@@ -3354,6 +3383,11 @@
 	nested_vmcb->control.event_inj         = 0;
 	nested_vmcb->control.event_inj_err     = 0;
 
+	nested_vmcb->control.pause_filter_count =
+		svm->vmcb->control.pause_filter_count;
+	nested_vmcb->control.pause_filter_thresh =
+		svm->vmcb->control.pause_filter_thresh;
+
 	/* We always set V_INTR_MASKING and remember the old value in hflags */
 	if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
 		nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
@@ -3384,21 +3418,29 @@
 	} else {
 		(void)kvm_set_cr3(&svm->vcpu, hsave->save.cr3);
 	}
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, hsave->save.rax);
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, hsave->save.rsp);
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, hsave->save.rip);
+	kvm_rax_write(&svm->vcpu, hsave->save.rax);
+	kvm_rsp_write(&svm->vcpu, hsave->save.rsp);
+	kvm_rip_write(&svm->vcpu, hsave->save.rip);
 	svm->vmcb->save.dr7 = 0;
 	svm->vmcb->save.cpl = 0;
 	svm->vmcb->control.exit_int_info = 0;
 
 	mark_all_dirty(svm->vmcb);
 
-	nested_svm_unmap(page);
+	kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
 	nested_svm_uninit_mmu_context(&svm->vcpu);
 	kvm_mmu_reset_context(&svm->vcpu);
 	kvm_mmu_load(&svm->vcpu);
 
+	/*
+	 * Drop what we picked up for L2 via svm_complete_interrupts() so it
+	 * doesn't end up in L1.
+	 */
+	svm->vcpu.arch.nmi_injected = false;
+	kvm_clear_exception_queue(&svm->vcpu);
+	kvm_clear_interrupt_queue(&svm->vcpu);
+
 	return 0;
 }
 
@@ -3451,7 +3493,7 @@
 }
 
 static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
-				 struct vmcb *nested_vmcb, struct page *page)
+				 struct vmcb *nested_vmcb, struct kvm_host_map *map)
 {
 	if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF)
 		svm->vcpu.arch.hflags |= HF_HIF_MASK;
@@ -3459,7 +3501,6 @@
 		svm->vcpu.arch.hflags &= ~HF_HIF_MASK;
 
 	if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) {
-		kvm_mmu_unload(&svm->vcpu);
 		svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3;
 		nested_svm_init_mmu_context(&svm->vcpu);
 	}
@@ -3485,9 +3526,9 @@
 	kvm_mmu_reset_context(&svm->vcpu);
 
 	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
+	kvm_rax_write(&svm->vcpu, nested_vmcb->save.rax);
+	kvm_rsp_write(&svm->vcpu, nested_vmcb->save.rsp);
+	kvm_rip_write(&svm->vcpu, nested_vmcb->save.rip);
 
 	/* In case we don't even reach vcpu_run, the fields are not updated */
 	svm->vmcb->save.rax = nested_vmcb->save.rax;
@@ -3531,7 +3572,12 @@
 	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
 	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
 
-	nested_svm_unmap(page);
+	svm->vmcb->control.pause_filter_count =
+		nested_vmcb->control.pause_filter_count;
+	svm->vmcb->control.pause_filter_thresh =
+		nested_vmcb->control.pause_filter_thresh;
+
+	kvm_vcpu_unmap(&svm->vcpu, map, true);
 
 	/* Enter Guest-Mode */
 	enter_guest_mode(&svm->vcpu);
@@ -3549,19 +3595,28 @@
 	mark_all_dirty(svm->vmcb);
 }
 
-static bool nested_svm_vmrun(struct vcpu_svm *svm)
+static int nested_svm_vmrun(struct vcpu_svm *svm)
 {
+	int ret;
 	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 	u64 vmcb_gpa;
 
 	vmcb_gpa = svm->vmcb->save.rax;
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
-	if (!nested_vmcb)
-		return false;
+	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map);
+	if (ret == -EINVAL) {
+		kvm_inject_gp(&svm->vcpu, 0);
+		return 1;
+	} else if (ret) {
+		return kvm_skip_emulated_instruction(&svm->vcpu);
+	}
+
+	ret = kvm_skip_emulated_instruction(&svm->vcpu);
+
+	nested_vmcb = map.hva;
 
 	if (!nested_vmcb_checks(nested_vmcb)) {
 		nested_vmcb->control.exit_code    = SVM_EXIT_ERR;
@@ -3569,9 +3624,9 @@
 		nested_vmcb->control.exit_info_1  = 0;
 		nested_vmcb->control.exit_info_2  = 0;
 
-		nested_svm_unmap(page);
+		kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
-		return false;
+		return ret;
 	}
 
 	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa,
@@ -3613,9 +3668,18 @@
 
 	copy_vmcb_control_area(hsave, vmcb);
 
-	enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, page);
+	enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map);
 
-	return true;
+	if (!nested_svm_vmrun_msrpm(svm)) {
+		svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
+		svm->vmcb->control.exit_code_hi = 0;
+		svm->vmcb->control.exit_info_1  = 0;
+		svm->vmcb->control.exit_info_2  = 0;
+
+		nested_svm_vmexit(svm);
+	}
+
+	return ret;
 }
 
 static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
@@ -3637,21 +3701,25 @@
 static int vmload_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 	int ret;
 
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
-	if (!nested_vmcb)
+	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map);
+	if (ret) {
+		if (ret == -EINVAL)
+			kvm_inject_gp(&svm->vcpu, 0);
 		return 1;
+	}
 
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	nested_vmcb = map.hva;
+
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
 	nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
-	nested_svm_unmap(page);
+	kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
 	return ret;
 }
@@ -3659,21 +3727,25 @@
 static int vmsave_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 	int ret;
 
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
-	if (!nested_vmcb)
+	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map);
+	if (ret) {
+		if (ret == -EINVAL)
+			kvm_inject_gp(&svm->vcpu, 0);
 		return 1;
+	}
 
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	nested_vmcb = map.hva;
+
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
 	nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
-	nested_svm_unmap(page);
+	kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
 	return ret;
 }
@@ -3683,27 +3755,7 @@
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
-	/* Save rip after vmrun instruction */
-	kvm_rip_write(&svm->vcpu, kvm_rip_read(&svm->vcpu) + 3);
-
-	if (!nested_svm_vmrun(svm))
-		return 1;
-
-	if (!nested_svm_vmrun_msrpm(svm))
-		goto failed;
-
-	return 1;
-
-failed:
-
-	svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
-	svm->vmcb->control.exit_code_hi = 0;
-	svm->vmcb->control.exit_info_1  = 0;
-	svm->vmcb->control.exit_info_2  = 0;
-
-	nested_svm_vmexit(svm);
-
-	return 1;
+	return nested_svm_vmrun(svm);
 }
 
 static int stgi_interception(struct vcpu_svm *svm)
@@ -3720,7 +3772,6 @@
 	if (vgif_enabled(svm))
 		clr_intercept(svm, INTERCEPT_STGI);
 
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 
@@ -3736,7 +3787,6 @@
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
 	disable_gif(svm);
@@ -3755,19 +3805,18 @@
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
-	trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX),
-			  kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
+	trace_kvm_invlpga(svm->vmcb->save.rip, kvm_rcx_read(&svm->vcpu),
+			  kvm_rax_read(&svm->vcpu));
 
 	/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
-	kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
+	kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu));
 
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	return kvm_skip_emulated_instruction(&svm->vcpu);
 }
 
 static int skinit_interception(struct vcpu_svm *svm)
 {
-	trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
+	trace_kvm_skinit(svm->vmcb->save.rip, kvm_rax_read(&svm->vcpu));
 
 	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
@@ -3781,16 +3830,21 @@
 static int xsetbv_interception(struct vcpu_svm *svm)
 {
 	u64 new_bv = kvm_read_edx_eax(&svm->vcpu);
-	u32 index = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
+	u32 index = kvm_rcx_read(&svm->vcpu);
 
 	if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) {
-		svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 		return kvm_skip_emulated_instruction(&svm->vcpu);
 	}
 
 	return 1;
 }
 
+static int rdpru_interception(struct vcpu_svm *svm)
+{
+	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
+	return 1;
+}
+
 static int task_switch_interception(struct vcpu_svm *svm)
 {
 	u16 tss_selector;
@@ -3843,25 +3897,20 @@
 	if (reason != TASK_SWITCH_GATE ||
 	    int_type == SVM_EXITINTINFO_TYPE_SOFT ||
 	    (int_type == SVM_EXITINTINFO_TYPE_EXEPT &&
-	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR)))
-		skip_emulated_instruction(&svm->vcpu);
+	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) {
+		if (!skip_emulated_instruction(&svm->vcpu))
+			return 0;
+	}
 
 	if (int_type != SVM_EXITINTINFO_TYPE_SOFT)
 		int_vec = -1;
 
-	if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason,
-				has_error_code, error_code) == EMULATE_FAIL) {
-		svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-		svm->vcpu.run->internal.ndata = 0;
-		return 0;
-	}
-	return 1;
+	return kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason,
+			       has_error_code, error_code);
 }
 
 static int cpuid_interception(struct vcpu_svm *svm)
 {
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
 	return kvm_emulate_cpuid(&svm->vcpu);
 }
 
@@ -3878,7 +3927,7 @@
 static int invlpg_interception(struct vcpu_svm *svm)
 {
 	if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
-		return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
+		return kvm_emulate_instruction(&svm->vcpu, 0);
 
 	kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1);
 	return kvm_skip_emulated_instruction(&svm->vcpu);
@@ -3886,20 +3935,19 @@
 
 static int emulate_on_interception(struct vcpu_svm *svm)
 {
-	return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
+	return kvm_emulate_instruction(&svm->vcpu, 0);
 }
 
 static int rsm_interception(struct vcpu_svm *svm)
 {
-	return kvm_emulate_instruction_from_buffer(&svm->vcpu,
-					rsm_ins_bytes, 2) == EMULATE_DONE;
+	return kvm_emulate_instruction_from_buffer(&svm->vcpu, rsm_ins_bytes, 2);
 }
 
 static int rdpmc_interception(struct vcpu_svm *svm)
 {
 	int err;
 
-	if (!static_cpu_has(X86_FEATURE_NRIPS))
+	if (!nrips)
 		return emulate_on_interception(svm);
 
 	err = kvm_rdpmc(&svm->vcpu);
@@ -4177,25 +4225,7 @@
 
 static int rdmsr_interception(struct vcpu_svm *svm)
 {
-	u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
-	struct msr_data msr_info;
-
-	msr_info.index = ecx;
-	msr_info.host_initiated = false;
-	if (svm_get_msr(&svm->vcpu, &msr_info)) {
-		trace_kvm_msr_read_ex(ecx);
-		kvm_inject_gp(&svm->vcpu, 0);
-		return 1;
-	} else {
-		trace_kvm_msr_read(ecx, msr_info.data);
-
-		kvm_register_write(&svm->vcpu, VCPU_REGS_RAX,
-				   msr_info.data & 0xffffffff);
-		kvm_register_write(&svm->vcpu, VCPU_REGS_RDX,
-				   msr_info.data >> 32);
-		svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-		return kvm_skip_emulated_instruction(&svm->vcpu);
-	}
+	return kvm_emulate_rdmsr(&svm->vcpu);
 }
 
 static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
@@ -4376,7 +4406,7 @@
 	case MSR_IA32_APICBASE:
 		if (kvm_vcpu_apicv_active(vcpu))
 			avic_update_vapic_bar(to_svm(vcpu), data);
-		/* Follow through */
+		/* Fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4385,23 +4415,7 @@
 
 static int wrmsr_interception(struct vcpu_svm *svm)
 {
-	struct msr_data msr;
-	u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
-	u64 data = kvm_read_edx_eax(&svm->vcpu);
-
-	msr.data = data;
-	msr.index = ecx;
-	msr.host_initiated = false;
-
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-	if (kvm_set_msr(&svm->vcpu, &msr)) {
-		trace_kvm_msr_write_ex(ecx, data);
-		kvm_inject_gp(&svm->vcpu, 0);
-		return 1;
-	} else {
-		trace_kvm_msr_write(ecx, data);
-		return kvm_skip_emulated_instruction(&svm->vcpu);
-	}
+	return kvm_emulate_wrmsr(&svm->vcpu);
 }
 
 static int msr_interception(struct vcpu_svm *svm)
@@ -4507,6 +4521,8 @@
 		break;
 	}
 	case AVIC_IPI_FAILURE_INVALID_TARGET:
+		WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n",
+			  index, svm->vcpu.vcpu_id, icrh, icrl);
 		break;
 	case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
 		WARN_ONCE(1, "Invalid backing page\n");
@@ -4547,8 +4563,7 @@
 	return &logical_apic_id_table[index];
 }
 
-static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr,
-			  bool valid)
+static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr)
 {
 	bool flat;
 	u32 *entry, new_entry;
@@ -4561,31 +4576,40 @@
 	new_entry = READ_ONCE(*entry);
 	new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
 	new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK);
-	if (valid)
-		new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK;
-	else
-		new_entry &= ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK;
+	new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK;
 	WRITE_ONCE(*entry, new_entry);
 
 	return 0;
 }
 
+static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	bool flat = svm->dfr_reg == APIC_DFR_FLAT;
+	u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
+
+	if (entry)
+		clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
+}
+
 static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 {
-	int ret;
+	int ret = 0;
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR);
+	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
-	if (!ldr)
-		return 1;
+	if (ldr == svm->ldr_reg)
+		return 0;
 
-	ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr, true);
-	if (ret && svm->ldr_reg) {
-		avic_ldr_write(vcpu, 0, svm->ldr_reg, false);
-		svm->ldr_reg = 0;
-	} else {
+	avic_invalidate_logical_id_entry(vcpu);
+
+	if (ldr)
+		ret = avic_ldr_write(vcpu, id, ldr);
+
+	if (!ret)
 		svm->ldr_reg = ldr;
-	}
+
 	return ret;
 }
 
@@ -4593,8 +4617,7 @@
 {
 	u64 *old, *new;
 	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID);
-	u32 id = (apic_id_reg >> 24) & 0xff;
+	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
 	if (vcpu->vcpu_id == id)
 		return 0;
@@ -4619,27 +4642,16 @@
 	return 0;
 }
 
-static int avic_handle_dfr_update(struct kvm_vcpu *vcpu)
+static void avic_handle_dfr_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
 	u32 dfr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR);
-	u32 mod = (dfr >> 28) & 0xf;
 
-	/*
-	 * We assume that all local APICs are using the same type.
-	 * If this changes, we need to flush the AVIC logical
-	 * APID id table.
-	 */
-	if (kvm_svm->ldr_mode == mod)
-		return 0;
+	if (svm->dfr_reg == dfr)
+		return;
 
-	clear_page(page_address(kvm_svm->avic_logical_id_table_page));
-	kvm_svm->ldr_mode = mod;
-
-	if (svm->ldr_reg)
-		avic_handle_ldr_update(vcpu);
-	return 0;
+	avic_invalidate_logical_id_entry(vcpu);
+	svm->dfr_reg = dfr;
 }
 
 static int avic_unaccel_trap_write(struct vcpu_svm *svm)
@@ -4717,7 +4729,7 @@
 		ret = avic_unaccel_trap_write(svm);
 	} else {
 		/* Handling Fault */
-		ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE);
+		ret = kvm_emulate_instruction(&svm->vcpu, 0);
 	}
 
 	return ret;
@@ -4784,6 +4796,7 @@
 	[SVM_EXIT_MONITOR]			= monitor_interception,
 	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
+	[SVM_EXIT_RDPRU]			= rdpru_interception,
 	[SVM_EXIT_NPF]				= npf_interception,
 	[SVM_EXIT_RSM]                          = rsm_interception,
 	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
@@ -4796,6 +4809,11 @@
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct vmcb_save_area *save = &svm->vmcb->save;
 
+	if (!dump_invalid_vmcb) {
+		pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
+		return;
+	}
+
 	pr_err("VMCB Control Area:\n");
 	pr_err("%-20s%04x\n", "cr_read:", control->intercept_cr & 0xffff);
 	pr_err("%-20s%04x\n", "cr_write:", control->intercept_cr >> 16);
@@ -4954,7 +4972,6 @@
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		kvm_run->fail_entry.hardware_entry_failure_reason
 			= svm->vmcb->control.exit_code;
-		pr_err("KVM: FAILED VMRUN WITH VMCB:\n");
 		dump_vmcb(vcpu);
 		return 0;
 	}
@@ -4970,9 +4987,14 @@
 
 	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
 	    || !svm_exit_handlers[exit_code]) {
-		WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code);
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
+		vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code);
+		dump_vmcb(vcpu);
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror =
+			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+		vcpu->run->internal.ndata = 1;
+		vcpu->run->internal.data[0] = exit_code;
+		return 0;
 	}
 
 	return svm_exit_handlers[exit_code](svm);
@@ -5107,11 +5129,11 @@
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb;
 
-	if (!kvm_vcpu_apicv_active(&svm->vcpu))
-		return;
-
-	vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
-	mark_dirty(vmcb, VMCB_INTR);
+	if (kvm_vcpu_apicv_active(vcpu))
+		vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
+	else
+		vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
+	mark_dirty(vmcb, VMCB_AVIC);
 }
 
 static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
@@ -5124,13 +5146,21 @@
 	kvm_lapic_set_irr(vec, vcpu->arch.apic);
 	smp_mb__after_atomic();
 
-	if (avic_vcpu_is_running(vcpu))
-		wrmsrl(SVM_AVIC_DOORBELL,
-		       kvm_cpu_get_apicid(vcpu->cpu));
-	else
+	if (avic_vcpu_is_running(vcpu)) {
+		int cpuid = vcpu->cpu;
+
+		if (cpuid != get_cpu())
+			wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid));
+		put_cpu();
+	} else
 		kvm_vcpu_wake_up(vcpu);
 }
 
+static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 {
 	unsigned long flags;
@@ -5177,7 +5207,7 @@
 	 * Allocating new amd_iommu_pi_data, which will get
 	 * add to the per-vcpu ir_list.
 	 */
-	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL);
+	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
 	if (!ir) {
 		ret = -ENOMEM;
 		goto out;
@@ -5211,7 +5241,8 @@
 
 	kvm_set_msi_irq(kvm, e, &irq);
 
-	if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+	if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
+	    !kvm_irq_is_postable(&irq)) {
 		pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n",
 			 __func__, irq.vector);
 		return -1;
@@ -5265,6 +5296,7 @@
 		 * 1. When cannot target interrupt to a specific vcpu.
 		 * 2. Unsetting posted interrupt.
 		 * 3. APIC virtialization is disabled for the vcpu.
+		 * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
 		 */
 		if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
 		    kvm_vcpu_apicv_active(&svm->vcpu)) {
@@ -5602,6 +5634,11 @@
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
 	clgi();
+	kvm_load_guest_xcr0(vcpu);
+
+	if (lapic_in_kernel(vcpu) &&
+		vcpu->arch.apic->lapic_timer.timer_advance_ns)
+		kvm_wait_lapic_expire(vcpu);
 
 	/*
 	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -5635,9 +5672,9 @@
 		/* Enter guest mode */
 		"push %%" _ASM_AX " \n\t"
 		"mov %c[vmcb](%[svm]), %%" _ASM_AX " \n\t"
-		__ex(SVM_VMLOAD) "\n\t"
-		__ex(SVM_VMRUN) "\n\t"
-		__ex(SVM_VMSAVE) "\n\t"
+		__ex("vmload %%" _ASM_AX) "\n\t"
+		__ex("vmrun %%" _ASM_AX) "\n\t"
+		__ex("vmsave %%" _ASM_AX) "\n\t"
 		"pop %%" _ASM_AX " \n\t"
 
 		/* Save guest registers, load host registers */
@@ -5656,26 +5693,24 @@
 		"mov %%r13, %c[r13](%[svm]) \n\t"
 		"mov %%r14, %c[r14](%[svm]) \n\t"
 		"mov %%r15, %c[r15](%[svm]) \n\t"
-#endif
 		/*
 		* Clear host registers marked as clobbered to prevent
 		* speculative use.
 		*/
-		"xor %%" _ASM_BX ", %%" _ASM_BX " \n\t"
-		"xor %%" _ASM_CX ", %%" _ASM_CX " \n\t"
-		"xor %%" _ASM_DX ", %%" _ASM_DX " \n\t"
-		"xor %%" _ASM_SI ", %%" _ASM_SI " \n\t"
-		"xor %%" _ASM_DI ", %%" _ASM_DI " \n\t"
-#ifdef CONFIG_X86_64
-		"xor %%r8, %%r8 \n\t"
-		"xor %%r9, %%r9 \n\t"
-		"xor %%r10, %%r10 \n\t"
-		"xor %%r11, %%r11 \n\t"
-		"xor %%r12, %%r12 \n\t"
-		"xor %%r13, %%r13 \n\t"
-		"xor %%r14, %%r14 \n\t"
-		"xor %%r15, %%r15 \n\t"
+		"xor %%r8d, %%r8d \n\t"
+		"xor %%r9d, %%r9d \n\t"
+		"xor %%r10d, %%r10d \n\t"
+		"xor %%r11d, %%r11d \n\t"
+		"xor %%r12d, %%r12d \n\t"
+		"xor %%r13d, %%r13d \n\t"
+		"xor %%r14d, %%r14d \n\t"
+		"xor %%r15d, %%r15d \n\t"
 #endif
+		"xor %%ebx, %%ebx \n\t"
+		"xor %%ecx, %%ecx \n\t"
+		"xor %%edx, %%edx \n\t"
+		"xor %%esi, %%esi \n\t"
+		"xor %%edi, %%edi \n\t"
 		"pop %%" _ASM_BP
 		:
 		: [svm]"a"(svm),
@@ -5749,6 +5784,7 @@
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(&svm->vcpu);
 
+	kvm_put_guest_xcr0(vcpu);
 	stgi();
 
 	/* Any pending NMI will happen here */
@@ -5825,9 +5861,9 @@
 	hypercall[2] = 0xd9;
 }
 
-static void svm_check_processor_compat(void *rtn)
+static int __init svm_check_processor_compat(void)
 {
-	*(int *)rtn = 0;
+	return 0;
 }
 
 static bool svm_cpu_has_accelerated_tpr(void)
@@ -5837,6 +5873,14 @@
 
 static bool svm_has_emulated_msr(int index)
 {
+	switch (index) {
+	case MSR_IA32_MCG_EXT_CTL:
+	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
+		return false;
+	default:
+		break;
+	}
+
 	return true;
 }
 
@@ -5858,6 +5902,8 @@
 	guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC);
 }
 
+#define F(x) bit(X86_FEATURE_##x)
+
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	switch (func) {
@@ -5869,6 +5915,11 @@
 		if (nested)
 			entry->ecx |= (1 << 2); /* Set SVM bit */
 		break;
+	case 0x80000008:
+		if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
+		     boot_cpu_has(X86_FEATURE_AMD_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
+		break;
 	case 0x8000000A:
 		entry->eax = 1; /* SVM revision 1 */
 		entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper
@@ -5879,11 +5930,11 @@
 
 		/* Support next_rip if host supports it */
 		if (boot_cpu_has(X86_FEATURE_NRIPS))
-			entry->edx |= SVM_FEATURE_NRIP;
+			entry->edx |= F(NRIPS);
 
 		/* Support NPT for the guest if enabled */
 		if (npt_enabled)
-			entry->edx |= SVM_FEATURE_NPT;
+			entry->edx |= F(NPT);
 
 		break;
 	case 0x8000001F:
@@ -5925,6 +5976,11 @@
 	return false;
 }
 
+static bool svm_pt_supported(void)
+{
+	return false;
+}
+
 static bool svm_has_wbinvd_exit(void)
 {
 	return true;
@@ -5987,6 +6043,7 @@
 	[x86_intercept_ins]		= POST_EX(SVM_EXIT_IOIO),
 	[x86_intercept_out]		= POST_EX(SVM_EXIT_IOIO),
 	[x86_intercept_outs]		= POST_EX(SVM_EXIT_IOIO),
+	[x86_intercept_xsetbv]		= PRE_EX(SVM_EXIT_XSETBV),
 };
 
 #undef PRE_EX
@@ -6114,15 +6171,9 @@
 	return ret;
 }
 
-static void svm_handle_external_intr(struct kvm_vcpu *vcpu)
+static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 {
-	local_irq_enable();
-	/*
-	 * We must have an instruction with interrupts enabled, so
-	 * the timer interrupt isn't delayed by the interrupt shadow.
-	 */
-	asm("nop");
-	local_irq_disable();
+
 }
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
@@ -6135,8 +6186,7 @@
 {
 	if (avic_handle_apic_id_update(vcpu) != 0)
 		return;
-	if (avic_handle_dfr_update(vcpu) != 0)
-		return;
+	avic_handle_dfr_update(vcpu);
 	avic_handle_ldr_update(vcpu);
 }
 
@@ -6187,32 +6237,24 @@
 	return 0;
 }
 
-static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *nested_vmcb;
-	struct page *page;
-	struct {
-		u64 guest;
-		u64 vmcb;
-	} svm_state_save;
-	int ret;
+	struct kvm_host_map map;
+	u64 guest;
+	u64 vmcb;
 
-	ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save,
-				  sizeof(svm_state_save));
-	if (ret)
-		return ret;
+	guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+	vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
 
-	if (svm_state_save.guest) {
-		vcpu->arch.hflags &= ~HF_SMM_MASK;
-		nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page);
-		if (nested_vmcb)
-			enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page);
-		else
-			ret = 1;
-		vcpu->arch.hflags |= HF_SMM_MASK;
+	if (guest) {
+		if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL)
+			return 1;
+		nested_vmcb = map.hva;
+		enter_svm_guest_mode(svm, vmcb, nested_vmcb, &map);
 	}
-	return ret;
+	return 0;
 }
 
 static int enable_smi_window(struct kvm_vcpu *vcpu)
@@ -6249,6 +6291,9 @@
 	int asid, ret;
 
 	ret = -EBUSY;
+	if (unlikely(sev->active))
+		return ret;
+
 	asid = sev_asid_new();
 	if (asid < 0)
 		return ret;
@@ -6280,7 +6325,7 @@
 	if (ret)
 		return ret;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
 
@@ -6330,7 +6375,7 @@
 	if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
 		return -EFAULT;
 
-	start = kzalloc(sizeof(*start), GFP_KERNEL);
+	start = kzalloc(sizeof(*start), GFP_KERNEL_ACCOUNT);
 	if (!start)
 		return -ENOMEM;
 
@@ -6391,11 +6436,11 @@
 	return ret;
 }
 
-static int get_num_contig_pages(int idx, struct page **inpages,
-				unsigned long npages)
+static unsigned long get_num_contig_pages(unsigned long idx,
+				struct page **inpages, unsigned long npages)
 {
 	unsigned long paddr, next_paddr;
-	int i = idx + 1, pages = 1;
+	unsigned long i = idx + 1, pages = 1;
 
 	/* find the number of contiguous pages starting from idx */
 	paddr = __sme_page_pa(inpages[idx]);
@@ -6414,12 +6459,12 @@
 
 static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	unsigned long vaddr, vaddr_end, next_vaddr, npages, size;
+	unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i;
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct kvm_sev_launch_update_data params;
 	struct sev_data_launch_update_data *data;
 	struct page **inpages;
-	int i, ret, pages;
+	int ret;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
@@ -6427,7 +6472,7 @@
 	if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
 		return -EFAULT;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
 
@@ -6504,7 +6549,7 @@
 	if (copy_from_user(&params, measure, sizeof(params)))
 		return -EFAULT;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
 
@@ -6566,7 +6611,7 @@
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
 
@@ -6587,7 +6632,7 @@
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
 
@@ -6615,7 +6660,7 @@
 	struct sev_data_dbg *data;
 	int ret;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
 
@@ -6768,7 +6813,8 @@
 	struct page **src_p, **dst_p;
 	struct kvm_sev_dbg debug;
 	unsigned long n;
-	int ret, size;
+	unsigned int size;
+	int ret;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
@@ -6776,6 +6822,11 @@
 	if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug)))
 		return -EFAULT;
 
+	if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr)
+		return -EINVAL;
+	if (!debug.dst_uaddr)
+		return -EINVAL;
+
 	vaddr = debug.src_uaddr;
 	size = debug.len;
 	vaddr_end = vaddr + size;
@@ -6826,8 +6877,8 @@
 						     dst_vaddr,
 						     len, &argp->error);
 
-		sev_unpin_memory(kvm, src_p, 1);
-		sev_unpin_memory(kvm, dst_p, 1);
+		sev_unpin_memory(kvm, src_p, n);
+		sev_unpin_memory(kvm, dst_p, n);
 
 		if (ret)
 			goto err;
@@ -6870,7 +6921,7 @@
 	}
 
 	ret = -ENOMEM;
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		goto e_unpin_memory;
 
@@ -6976,7 +7027,7 @@
 	if (range->addr > ULONG_MAX || range->size > ULONG_MAX)
 		return -EINVAL;
 
-	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT);
 	if (!region)
 		return -ENOMEM;
 
@@ -7054,6 +7105,79 @@
 	return ret;
 }
 
+static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
+{
+	unsigned long cr4 = kvm_read_cr4(vcpu);
+	bool smep = cr4 & X86_CR4_SMEP;
+	bool smap = cr4 & X86_CR4_SMAP;
+	bool is_user = svm_get_cpl(vcpu) == 3;
+
+	/*
+	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
+	 *
+	 * Errata:
+	 * When CPU raise #NPF on guest data access and vCPU CR4.SMAP=1, it is
+	 * possible that CPU microcode implementing DecodeAssist will fail
+	 * to read bytes of instruction which caused #NPF. In this case,
+	 * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly
+	 * return 0 instead of the correct guest instruction bytes.
+	 *
+	 * This happens because CPU microcode reading instruction bytes
+	 * uses a special opcode which attempts to read data using CPL=0
+	 * priviledges. The microcode reads CS:RIP and if it hits a SMAP
+	 * fault, it gives up and returns no instruction bytes.
+	 *
+	 * Detection:
+	 * We reach here in case CPU supports DecodeAssist, raised #NPF and
+	 * returned 0 in GuestIntrBytes field of the VMCB.
+	 * First, errata can only be triggered in case vCPU CR4.SMAP=1.
+	 * Second, if vCPU CR4.SMEP=1, errata could only be triggered
+	 * in case vCPU CPL==3 (Because otherwise guest would have triggered
+	 * a SMEP fault instead of #NPF).
+	 * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL.
+	 * As most guests enable SMAP if they have also enabled SMEP, use above
+	 * logic in order to attempt minimize false-positive of detecting errata
+	 * while still preserving all cases semantic correctness.
+	 *
+	 * Workaround:
+	 * To determine what instruction the guest was executing, the hypervisor
+	 * will have to decode the instruction at the instruction pointer.
+	 *
+	 * In non SEV guest, hypervisor will be able to read the guest
+	 * memory to decode the instruction pointer when insn_len is zero
+	 * so we return true to indicate that decoding is possible.
+	 *
+	 * But in the SEV guest, the guest memory is encrypted with the
+	 * guest specific key and hypervisor will not be able to decode the
+	 * instruction pointer so we will not able to workaround it. Lets
+	 * print the error and request to kill the guest.
+	 */
+	if (smap && (!smep || is_user)) {
+		if (!sev_guest(vcpu->kvm))
+			return true;
+
+		pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n");
+		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+	}
+
+	return false;
+}
+
+static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/*
+	 * TODO: Last condition latch INIT signals on vCPU when
+	 * vCPU is in guest-mode and vmcb12 defines intercept on INIT.
+	 * To properly emulate the INIT intercept, SVM should implement
+	 * kvm_x86_ops->check_nested_events() and call nested_svm_vmexit()
+	 * there if an INIT signal is pending.
+	 */
+	return !gif_set(svm) ||
+		   (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT));
+}
+
 static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -7153,6 +7277,7 @@
 	.mpx_supported = svm_mpx_supported,
 	.xsaves_supported = svm_xsaves_supported,
 	.umip_emulated = svm_umip_emulated,
+	.pt_supported = svm_pt_supported,
 
 	.set_supported_cpuid = svm_set_supported_cpuid,
 
@@ -7164,7 +7289,7 @@
 	.set_tdp_cr3 = set_tdp_cr3,
 
 	.check_intercept = svm_check_intercept,
-	.handle_external_intr = svm_handle_external_intr,
+	.handle_exit_irqoff = svm_handle_exit_irqoff,
 
 	.request_immediate_exit = __kvm_request_immediate_exit,
 
@@ -7172,6 +7297,7 @@
 
 	.pmu_ops = &amd_pmu_ops,
 	.deliver_posted_interrupt = svm_deliver_avic_intr,
+	.dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt,
 	.update_pi_irte = svm_update_pi_irte,
 	.setup_mce = svm_setup_mce,
 
@@ -7183,6 +7309,13 @@
 	.mem_enc_op = svm_mem_enc_op,
 	.mem_enc_reg_region = svm_register_enc_region,
 	.mem_enc_unreg_region = svm_unregister_enc_region,
+
+	.nested_enable_evmcs = NULL,
+	.nested_get_evmcs_version = NULL,
+
+	.need_emulation_on_page_fault = svm_need_emulation_on_page_fault,
+
+	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 0f99768..7c741a0 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -232,17 +232,20 @@
 		__field(	u32,	        isa             )
 		__field(	u64,	        info1           )
 		__field(	u64,	        info2           )
+		__field(	unsigned int,	vcpu_id         )
 	),
 
 	TP_fast_assign(
 		__entry->exit_reason	= exit_reason;
 		__entry->guest_rip	= kvm_rip_read(vcpu);
 		__entry->isa            = isa;
+		__entry->vcpu_id        = vcpu->vcpu_id;
 		kvm_x86_ops->get_exit_info(vcpu, &__entry->info1,
 					   &__entry->info2);
 	),
 
-	TP_printk("reason %s rip 0x%lx info %llx %llx",
+	TP_printk("vcpu %u reason %s rip 0x%lx info %llx %llx",
+		  __entry->vcpu_id,
 		 (__entry->isa == KVM_ISA_VMX) ?
 		 __print_symbolic(__entry->exit_reason, VMX_EXIT_REASONS) :
 		 __print_symbolic(__entry->exit_reason, SVM_EXIT_REASONS),
@@ -438,13 +441,13 @@
 );
 
 TRACE_EVENT(kvm_apic_accept_irq,
-	    TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+	    TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec),
 	    TP_ARGS(apicid, dm, tm, vec),
 
 	TP_STRUCT__entry(
 		__field(	__u32,		apicid		)
 		__field(	__u16,		dm		)
-		__field(	__u8,		tm		)
+		__field(	__u16,		tm		)
 		__field(	__u8,		vec		)
 	),
 
@@ -887,36 +890,27 @@
 	TP_printk("vcpu %d: PML full", __entry->vcpu_id)
 );
 
-TRACE_EVENT(kvm_ple_window,
-	TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old),
-	TP_ARGS(grow, vcpu_id, new, old),
+TRACE_EVENT(kvm_ple_window_update,
+	TP_PROTO(unsigned int vcpu_id, unsigned int new, unsigned int old),
+	TP_ARGS(vcpu_id, new, old),
 
 	TP_STRUCT__entry(
-		__field(                bool,      grow         )
 		__field(        unsigned int,   vcpu_id         )
-		__field(                 int,       new         )
-		__field(                 int,       old         )
+		__field(        unsigned int,       new         )
+		__field(        unsigned int,       old         )
 	),
 
 	TP_fast_assign(
-		__entry->grow           = grow;
 		__entry->vcpu_id        = vcpu_id;
 		__entry->new            = new;
 		__entry->old            = old;
 	),
 
-	TP_printk("vcpu %u: ple_window %d (%s %d)",
-	          __entry->vcpu_id,
-	          __entry->new,
-	          __entry->grow ? "grow" : "shrink",
-	          __entry->old)
+	TP_printk("vcpu %u old %u new %u (%s)",
+	          __entry->vcpu_id, __entry->old, __entry->new,
+		  __entry->old < __entry->new ? "growed" : "shrinked")
 );
 
-#define trace_kvm_ple_window_grow(vcpu_id, new, old) \
-	trace_kvm_ple_window(true, vcpu_id, new, old)
-#define trace_kvm_ple_window_shrink(vcpu_id, new, old) \
-	trace_kvm_ple_window(false, vcpu_id, new, old)
-
 TRACE_EVENT(kvm_pvclock_update,
 	TP_PROTO(unsigned int vcpu_id, struct pvclock_vcpu_time_info *pvclock),
 	TP_ARGS(vcpu_id, pvclock),
@@ -1254,24 +1248,26 @@
  * Tracepoint for stimer_expiration.
  */
 TRACE_EVENT(kvm_hv_stimer_expiration,
-	TP_PROTO(int vcpu_id, int timer_index, int msg_send_result),
-	TP_ARGS(vcpu_id, timer_index, msg_send_result),
+	TP_PROTO(int vcpu_id, int timer_index, int direct, int msg_send_result),
+	TP_ARGS(vcpu_id, timer_index, direct, msg_send_result),
 
 	TP_STRUCT__entry(
 		__field(int, vcpu_id)
 		__field(int, timer_index)
+		__field(int, direct)
 		__field(int, msg_send_result)
 	),
 
 	TP_fast_assign(
 		__entry->vcpu_id = vcpu_id;
 		__entry->timer_index = timer_index;
+		__entry->direct = direct;
 		__entry->msg_send_result = msg_send_result;
 	),
 
-	TP_printk("vcpu_id %d timer %d msg send result %d",
+	TP_printk("vcpu_id %d timer %d direct %d send result %d",
 		  __entry->vcpu_id, __entry->timer_index,
-		  __entry->msg_send_result)
+		  __entry->direct, __entry->msg_send_result)
 );
 
 /*
@@ -1318,7 +1314,7 @@
 		__entry->index = index;
 	),
 
-	TP_printk("vcpu=%u, icrh:icrl=%#010x:%08x, id=%u, index=%u\n",
+	TP_printk("vcpu=%u, icrh:icrl=%#010x:%08x, id=%u, index=%u",
 		  __entry->vcpu, __entry->icrh, __entry->icrl,
 		  __entry->id, __entry->index)
 );
@@ -1343,7 +1339,7 @@
 		__entry->vec = vec;
 	),
 
-	TP_printk("vcpu=%u, offset=%#x(%s), %s, %s, vec=%#x\n",
+	TP_printk("vcpu=%u, offset=%#x(%s), %s, %s, vec=%#x",
 		  __entry->vcpu,
 		  __entry->offset,
 		  __print_symbolic(__entry->offset, kvm_trace_symbol_apic),
@@ -1363,7 +1359,7 @@
 			__entry->vcpu_id = vcpu_id;
 			__entry->hv_timer_in_use = hv_timer_in_use;
 			),
-		TP_printk("vcpu_id %x hv_timer %x\n",
+		TP_printk("vcpu_id %x hv_timer %x",
 			__entry->vcpu_id,
 			__entry->hv_timer_in_use)
 );
@@ -1418,10 +1414,92 @@
 		  __entry->valid_bank_mask, __entry->format,
 		  __entry->address_space, __entry->flags)
 );
+
+/*
+ * Tracepoints for kvm_hv_send_ipi.
+ */
+TRACE_EVENT(kvm_hv_send_ipi,
+	TP_PROTO(u32 vector, u64 processor_mask),
+	TP_ARGS(vector, processor_mask),
+
+	TP_STRUCT__entry(
+		__field(u32, vector)
+		__field(u64, processor_mask)
+	),
+
+	TP_fast_assign(
+		__entry->vector = vector;
+		__entry->processor_mask = processor_mask;
+	),
+
+	TP_printk("vector %x processor_mask 0x%llx",
+		  __entry->vector, __entry->processor_mask)
+);
+
+TRACE_EVENT(kvm_hv_send_ipi_ex,
+	TP_PROTO(u32 vector, u64 format, u64 valid_bank_mask),
+	TP_ARGS(vector, format, valid_bank_mask),
+
+	TP_STRUCT__entry(
+		__field(u32, vector)
+		__field(u64, format)
+		__field(u64, valid_bank_mask)
+	),
+
+	TP_fast_assign(
+		__entry->vector = vector;
+		__entry->format = format;
+		__entry->valid_bank_mask = valid_bank_mask;
+	),
+
+	TP_printk("vector %x format %llx valid_bank_mask 0x%llx",
+		  __entry->vector, __entry->format,
+		  __entry->valid_bank_mask)
+);
+
+TRACE_EVENT(kvm_pv_tlb_flush,
+	TP_PROTO(unsigned int vcpu_id, bool need_flush_tlb),
+	TP_ARGS(vcpu_id, need_flush_tlb),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	vcpu_id		)
+		__field(	bool,	need_flush_tlb		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id	= vcpu_id;
+		__entry->need_flush_tlb = need_flush_tlb;
+	),
+
+	TP_printk("vcpu %u need_flush_tlb %s", __entry->vcpu_id,
+		__entry->need_flush_tlb ? "true" : "false")
+);
+
+/*
+ * Tracepoint for failed nested VMX VM-Enter.
+ */
+TRACE_EVENT(kvm_nested_vmenter_failed,
+	TP_PROTO(const char *msg, u32 err),
+	TP_ARGS(msg, err),
+
+	TP_STRUCT__entry(
+		__field(const char *, msg)
+		__field(u32, err)
+	),
+
+	TP_fast_assign(
+		__entry->msg = msg;
+		__entry->err = err;
+	),
+
+	TP_printk("%s%s", __entry->msg, !__entry->err ? "" :
+		__print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS))
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH arch/x86/kvm
+#define TRACE_INCLUDE_PATH ../../arch/x86/kvm
 #undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE trace
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
deleted file mode 100644
index 33ffb6d..0000000
--- a/arch/x86/kvm/vmx.c
+++ /dev/null
@@ -1,14368 +0,0 @@
-/*
- * Kernel-based Virtual Machine driver for Linux
- *
- * This module enables machines with Intel VT-x extensions to run virtual
- * machines without emulation or binary translation.
- *
- * Copyright (C) 2006 Qumranet, Inc.
- * Copyright 2010 Red Hat, Inc. and/or its affiliates.
- *
- * Authors:
- *   Avi Kivity   <avi@qumranet.com>
- *   Yaniv Kamay  <yaniv@qumranet.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- */
-
-#include "irq.h"
-#include "mmu.h"
-#include "cpuid.h"
-#include "lapic.h"
-
-#include <linux/kvm_host.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/sched.h>
-#include <linux/moduleparam.h>
-#include <linux/mod_devicetable.h>
-#include <linux/trace_events.h>
-#include <linux/slab.h>
-#include <linux/tboot.h>
-#include <linux/hrtimer.h>
-#include <linux/frame.h>
-#include <linux/nospec.h>
-#include "kvm_cache_regs.h"
-#include "x86.h"
-
-#include <asm/asm.h>
-#include <asm/cpu.h>
-#include <asm/io.h>
-#include <asm/desc.h>
-#include <asm/vmx.h>
-#include <asm/virtext.h>
-#include <asm/mce.h>
-#include <asm/fpu/internal.h>
-#include <asm/perf_event.h>
-#include <asm/debugreg.h>
-#include <asm/kexec.h>
-#include <asm/apic.h>
-#include <asm/irq_remapping.h>
-#include <asm/mmu_context.h>
-#include <asm/spec-ctrl.h>
-#include <asm/mshyperv.h>
-
-#include "trace.h"
-#include "pmu.h"
-#include "vmx_evmcs.h"
-
-#define __ex(x) __kvm_handle_fault_on_reboot(x)
-#define __ex_clear(x, reg) \
-	____kvm_handle_fault_on_reboot(x, "xor " reg " , " reg)
-
-MODULE_AUTHOR("Qumranet");
-MODULE_LICENSE("GPL");
-
-static const struct x86_cpu_id vmx_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_VMX),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
-
-static bool __read_mostly enable_vpid = 1;
-module_param_named(vpid, enable_vpid, bool, 0444);
-
-static bool __read_mostly enable_vnmi = 1;
-module_param_named(vnmi, enable_vnmi, bool, S_IRUGO);
-
-static bool __read_mostly flexpriority_enabled = 1;
-module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);
-
-static bool __read_mostly enable_ept = 1;
-module_param_named(ept, enable_ept, bool, S_IRUGO);
-
-static bool __read_mostly enable_unrestricted_guest = 1;
-module_param_named(unrestricted_guest,
-			enable_unrestricted_guest, bool, S_IRUGO);
-
-static bool __read_mostly enable_ept_ad_bits = 1;
-module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO);
-
-static bool __read_mostly emulate_invalid_guest_state = true;
-module_param(emulate_invalid_guest_state, bool, S_IRUGO);
-
-static bool __read_mostly fasteoi = 1;
-module_param(fasteoi, bool, S_IRUGO);
-
-static bool __read_mostly enable_apicv = 1;
-module_param(enable_apicv, bool, S_IRUGO);
-
-static bool __read_mostly enable_shadow_vmcs = 1;
-module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
-/*
- * If nested=1, nested virtualization is supported, i.e., guests may use
- * VMX and be a hypervisor for its own guests. If nested=0, guests may not
- * use VMX instructions.
- */
-static bool __read_mostly nested = 0;
-module_param(nested, bool, S_IRUGO);
-
-static u64 __read_mostly host_xss;
-
-static bool __read_mostly enable_pml = 1;
-module_param_named(pml, enable_pml, bool, S_IRUGO);
-
-#define MSR_TYPE_R	1
-#define MSR_TYPE_W	2
-#define MSR_TYPE_RW	3
-
-#define MSR_BITMAP_MODE_X2APIC		1
-#define MSR_BITMAP_MODE_X2APIC_APICV	2
-
-#define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL
-
-/* Guest_tsc -> host_tsc conversion requires 64-bit division.  */
-static int __read_mostly cpu_preemption_timer_multi;
-static bool __read_mostly enable_preemption_timer = 1;
-#ifdef CONFIG_X86_64
-module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
-#endif
-
-#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
-#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
-#define KVM_VM_CR0_ALWAYS_ON				\
-	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | 	\
-	 X86_CR0_WP | X86_CR0_PG | X86_CR0_PE)
-#define KVM_CR4_GUEST_OWNED_BITS				      \
-	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD)
-
-#define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE
-#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
-#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
-
-#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
-
-#define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5
-
-/*
- * Hyper-V requires all of these, so mark them as supported even though
- * they are just treated the same as all-context.
- */
-#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
-	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
-	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
-	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
-	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)
-
-/*
- * These 2 parameters are used to config the controls for Pause-Loop Exiting:
- * ple_gap:    upper bound on the amount of time between two successive
- *             executions of PAUSE in a loop. Also indicate if ple enabled.
- *             According to test, this time is usually smaller than 128 cycles.
- * ple_window: upper bound on the amount of time a guest is allowed to execute
- *             in a PAUSE loop. Tests indicate that most spinlocks are held for
- *             less than 2^12 cycles
- * Time is measured based on a counter that runs at the same rate as the TSC,
- * refer SDM volume 3b section 21.6.13 & 22.1.3.
- */
-static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP;
-module_param(ple_gap, uint, 0444);
-
-static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
-module_param(ple_window, uint, 0444);
-
-/* Default doubles per-vcpu window every exit. */
-static unsigned int ple_window_grow = KVM_DEFAULT_PLE_WINDOW_GROW;
-module_param(ple_window_grow, uint, 0444);
-
-/* Default resets per-vcpu window every exit to ple_window. */
-static unsigned int ple_window_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK;
-module_param(ple_window_shrink, uint, 0444);
-
-/* Default is to compute the maximum so we can never overflow. */
-static unsigned int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
-module_param(ple_window_max, uint, 0444);
-
-extern const ulong vmx_return;
-
-static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
-static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
-static DEFINE_MUTEX(vmx_l1d_flush_mutex);
-
-/* Storage for pre module init parameter parsing */
-static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;
-
-static const struct {
-	const char *option;
-	bool for_parse;
-} vmentry_l1d_param[] = {
-	[VMENTER_L1D_FLUSH_AUTO]	 = {"auto", true},
-	[VMENTER_L1D_FLUSH_NEVER]	 = {"never", true},
-	[VMENTER_L1D_FLUSH_COND]	 = {"cond", true},
-	[VMENTER_L1D_FLUSH_ALWAYS]	 = {"always", true},
-	[VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false},
-	[VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false},
-};
-
-#define L1D_CACHE_ORDER 4
-static void *vmx_l1d_flush_pages;
-
-static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
-{
-	struct page *page;
-	unsigned int i;
-
-	if (!enable_ept) {
-		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
-		return 0;
-	}
-
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
-		u64 msr;
-
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
-		if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
-			l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
-			return 0;
-		}
-	}
-
-	/* If set to auto use the default l1tf mitigation method */
-	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
-		switch (l1tf_mitigation) {
-		case L1TF_MITIGATION_OFF:
-			l1tf = VMENTER_L1D_FLUSH_NEVER;
-			break;
-		case L1TF_MITIGATION_FLUSH_NOWARN:
-		case L1TF_MITIGATION_FLUSH:
-		case L1TF_MITIGATION_FLUSH_NOSMT:
-			l1tf = VMENTER_L1D_FLUSH_COND;
-			break;
-		case L1TF_MITIGATION_FULL:
-		case L1TF_MITIGATION_FULL_FORCE:
-			l1tf = VMENTER_L1D_FLUSH_ALWAYS;
-			break;
-		}
-	} else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) {
-		l1tf = VMENTER_L1D_FLUSH_ALWAYS;
-	}
-
-	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
-	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
-		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
-		if (!page)
-			return -ENOMEM;
-		vmx_l1d_flush_pages = page_address(page);
-
-		/*
-		 * Initialize each page with a different pattern in
-		 * order to protect against KSM in the nested
-		 * virtualization case.
-		 */
-		for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) {
-			memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1,
-			       PAGE_SIZE);
-		}
-	}
-
-	l1tf_vmx_mitigation = l1tf;
-
-	if (l1tf != VMENTER_L1D_FLUSH_NEVER)
-		static_branch_enable(&vmx_l1d_should_flush);
-	else
-		static_branch_disable(&vmx_l1d_should_flush);
-
-	if (l1tf == VMENTER_L1D_FLUSH_COND)
-		static_branch_enable(&vmx_l1d_flush_cond);
-	else
-		static_branch_disable(&vmx_l1d_flush_cond);
-	return 0;
-}
-
-static int vmentry_l1d_flush_parse(const char *s)
-{
-	unsigned int i;
-
-	if (s) {
-		for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
-			if (vmentry_l1d_param[i].for_parse &&
-			    sysfs_streq(s, vmentry_l1d_param[i].option))
-				return i;
-		}
-	}
-	return -EINVAL;
-}
-
-static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
-{
-	int l1tf, ret;
-
-	l1tf = vmentry_l1d_flush_parse(s);
-	if (l1tf < 0)
-		return l1tf;
-
-	if (!boot_cpu_has(X86_BUG_L1TF))
-		return 0;
-
-	/*
-	 * Has vmx_init() run already? If not then this is the pre init
-	 * parameter parsing. In that case just store the value and let
-	 * vmx_init() do the proper setup after enable_ept has been
-	 * established.
-	 */
-	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) {
-		vmentry_l1d_flush_param = l1tf;
-		return 0;
-	}
-
-	mutex_lock(&vmx_l1d_flush_mutex);
-	ret = vmx_setup_l1d_flush(l1tf);
-	mutex_unlock(&vmx_l1d_flush_mutex);
-	return ret;
-}
-
-static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
-{
-	if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param)))
-		return sprintf(s, "???\n");
-
-	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
-}
-
-static const struct kernel_param_ops vmentry_l1d_flush_ops = {
-	.set = vmentry_l1d_flush_set,
-	.get = vmentry_l1d_flush_get,
-};
-module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);
-
-enum ept_pointers_status {
-	EPT_POINTERS_CHECK = 0,
-	EPT_POINTERS_MATCH = 1,
-	EPT_POINTERS_MISMATCH = 2
-};
-
-struct kvm_vmx {
-	struct kvm kvm;
-
-	unsigned int tss_addr;
-	bool ept_identity_pagetable_done;
-	gpa_t ept_identity_map_addr;
-
-	enum ept_pointers_status ept_pointers_match;
-	spinlock_t ept_pointer_lock;
-};
-
-#define NR_AUTOLOAD_MSRS 8
-
-struct vmcs_hdr {
-	u32 revision_id:31;
-	u32 shadow_vmcs:1;
-};
-
-struct vmcs {
-	struct vmcs_hdr hdr;
-	u32 abort;
-	char data[0];
-};
-
-/*
- * vmcs_host_state tracks registers that are loaded from the VMCS on VMEXIT
- * and whose values change infrequently, but are not constant.  I.e. this is
- * used as a write-through cache of the corresponding VMCS fields.
- */
-struct vmcs_host_state {
-	unsigned long cr3;	/* May not match real cr3 */
-	unsigned long cr4;	/* May not match real cr4 */
-	unsigned long gs_base;
-	unsigned long fs_base;
-
-	u16           fs_sel, gs_sel, ldt_sel;
-#ifdef CONFIG_X86_64
-	u16           ds_sel, es_sel;
-#endif
-};
-
-/*
- * Track a VMCS that may be loaded on a certain CPU. If it is (cpu!=-1), also
- * remember whether it was VMLAUNCHed, and maintain a linked list of all VMCSs
- * loaded on this CPU (so we can clear them if the CPU goes down).
- */
-struct loaded_vmcs {
-	struct vmcs *vmcs;
-	struct vmcs *shadow_vmcs;
-	int cpu;
-	bool launched;
-	bool nmi_known_unmasked;
-	bool hv_timer_armed;
-	/* Support for vnmi-less CPUs */
-	int soft_vnmi_blocked;
-	ktime_t entry_time;
-	s64 vnmi_blocked_time;
-	unsigned long *msr_bitmap;
-	struct list_head loaded_vmcss_on_cpu_link;
-	struct vmcs_host_state host_state;
-};
-
-struct shared_msr_entry {
-	unsigned index;
-	u64 data;
-	u64 mask;
-};
-
-/*
- * struct vmcs12 describes the state that our guest hypervisor (L1) keeps for a
- * single nested guest (L2), hence the name vmcs12. Any VMX implementation has
- * a VMCS structure, and vmcs12 is our emulated VMX's VMCS. This structure is
- * stored in guest memory specified by VMPTRLD, but is opaque to the guest,
- * which must access it using VMREAD/VMWRITE/VMCLEAR instructions.
- * More than one of these structures may exist, if L1 runs multiple L2 guests.
- * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the
- * underlying hardware which will be used to run L2.
- * This structure is packed to ensure that its layout is identical across
- * machines (necessary for live migration).
- *
- * IMPORTANT: Changing the layout of existing fields in this structure
- * will break save/restore compatibility with older kvm releases. When
- * adding new fields, either use space in the reserved padding* arrays
- * or add the new fields to the end of the structure.
- */
-typedef u64 natural_width;
-struct __packed vmcs12 {
-	/* According to the Intel spec, a VMCS region must start with the
-	 * following two fields. Then follow implementation-specific data.
-	 */
-	struct vmcs_hdr hdr;
-	u32 abort;
-
-	u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */
-	u32 padding[7]; /* room for future expansion */
-
-	u64 io_bitmap_a;
-	u64 io_bitmap_b;
-	u64 msr_bitmap;
-	u64 vm_exit_msr_store_addr;
-	u64 vm_exit_msr_load_addr;
-	u64 vm_entry_msr_load_addr;
-	u64 tsc_offset;
-	u64 virtual_apic_page_addr;
-	u64 apic_access_addr;
-	u64 posted_intr_desc_addr;
-	u64 ept_pointer;
-	u64 eoi_exit_bitmap0;
-	u64 eoi_exit_bitmap1;
-	u64 eoi_exit_bitmap2;
-	u64 eoi_exit_bitmap3;
-	u64 xss_exit_bitmap;
-	u64 guest_physical_address;
-	u64 vmcs_link_pointer;
-	u64 guest_ia32_debugctl;
-	u64 guest_ia32_pat;
-	u64 guest_ia32_efer;
-	u64 guest_ia32_perf_global_ctrl;
-	u64 guest_pdptr0;
-	u64 guest_pdptr1;
-	u64 guest_pdptr2;
-	u64 guest_pdptr3;
-	u64 guest_bndcfgs;
-	u64 host_ia32_pat;
-	u64 host_ia32_efer;
-	u64 host_ia32_perf_global_ctrl;
-	u64 vmread_bitmap;
-	u64 vmwrite_bitmap;
-	u64 vm_function_control;
-	u64 eptp_list_address;
-	u64 pml_address;
-	u64 padding64[3]; /* room for future expansion */
-	/*
-	 * To allow migration of L1 (complete with its L2 guests) between
-	 * machines of different natural widths (32 or 64 bit), we cannot have
-	 * unsigned long fields with no explict size. We use u64 (aliased
-	 * natural_width) instead. Luckily, x86 is little-endian.
-	 */
-	natural_width cr0_guest_host_mask;
-	natural_width cr4_guest_host_mask;
-	natural_width cr0_read_shadow;
-	natural_width cr4_read_shadow;
-	natural_width cr3_target_value0;
-	natural_width cr3_target_value1;
-	natural_width cr3_target_value2;
-	natural_width cr3_target_value3;
-	natural_width exit_qualification;
-	natural_width guest_linear_address;
-	natural_width guest_cr0;
-	natural_width guest_cr3;
-	natural_width guest_cr4;
-	natural_width guest_es_base;
-	natural_width guest_cs_base;
-	natural_width guest_ss_base;
-	natural_width guest_ds_base;
-	natural_width guest_fs_base;
-	natural_width guest_gs_base;
-	natural_width guest_ldtr_base;
-	natural_width guest_tr_base;
-	natural_width guest_gdtr_base;
-	natural_width guest_idtr_base;
-	natural_width guest_dr7;
-	natural_width guest_rsp;
-	natural_width guest_rip;
-	natural_width guest_rflags;
-	natural_width guest_pending_dbg_exceptions;
-	natural_width guest_sysenter_esp;
-	natural_width guest_sysenter_eip;
-	natural_width host_cr0;
-	natural_width host_cr3;
-	natural_width host_cr4;
-	natural_width host_fs_base;
-	natural_width host_gs_base;
-	natural_width host_tr_base;
-	natural_width host_gdtr_base;
-	natural_width host_idtr_base;
-	natural_width host_ia32_sysenter_esp;
-	natural_width host_ia32_sysenter_eip;
-	natural_width host_rsp;
-	natural_width host_rip;
-	natural_width paddingl[8]; /* room for future expansion */
-	u32 pin_based_vm_exec_control;
-	u32 cpu_based_vm_exec_control;
-	u32 exception_bitmap;
-	u32 page_fault_error_code_mask;
-	u32 page_fault_error_code_match;
-	u32 cr3_target_count;
-	u32 vm_exit_controls;
-	u32 vm_exit_msr_store_count;
-	u32 vm_exit_msr_load_count;
-	u32 vm_entry_controls;
-	u32 vm_entry_msr_load_count;
-	u32 vm_entry_intr_info_field;
-	u32 vm_entry_exception_error_code;
-	u32 vm_entry_instruction_len;
-	u32 tpr_threshold;
-	u32 secondary_vm_exec_control;
-	u32 vm_instruction_error;
-	u32 vm_exit_reason;
-	u32 vm_exit_intr_info;
-	u32 vm_exit_intr_error_code;
-	u32 idt_vectoring_info_field;
-	u32 idt_vectoring_error_code;
-	u32 vm_exit_instruction_len;
-	u32 vmx_instruction_info;
-	u32 guest_es_limit;
-	u32 guest_cs_limit;
-	u32 guest_ss_limit;
-	u32 guest_ds_limit;
-	u32 guest_fs_limit;
-	u32 guest_gs_limit;
-	u32 guest_ldtr_limit;
-	u32 guest_tr_limit;
-	u32 guest_gdtr_limit;
-	u32 guest_idtr_limit;
-	u32 guest_es_ar_bytes;
-	u32 guest_cs_ar_bytes;
-	u32 guest_ss_ar_bytes;
-	u32 guest_ds_ar_bytes;
-	u32 guest_fs_ar_bytes;
-	u32 guest_gs_ar_bytes;
-	u32 guest_ldtr_ar_bytes;
-	u32 guest_tr_ar_bytes;
-	u32 guest_interruptibility_info;
-	u32 guest_activity_state;
-	u32 guest_sysenter_cs;
-	u32 host_ia32_sysenter_cs;
-	u32 vmx_preemption_timer_value;
-	u32 padding32[7]; /* room for future expansion */
-	u16 virtual_processor_id;
-	u16 posted_intr_nv;
-	u16 guest_es_selector;
-	u16 guest_cs_selector;
-	u16 guest_ss_selector;
-	u16 guest_ds_selector;
-	u16 guest_fs_selector;
-	u16 guest_gs_selector;
-	u16 guest_ldtr_selector;
-	u16 guest_tr_selector;
-	u16 guest_intr_status;
-	u16 host_es_selector;
-	u16 host_cs_selector;
-	u16 host_ss_selector;
-	u16 host_ds_selector;
-	u16 host_fs_selector;
-	u16 host_gs_selector;
-	u16 host_tr_selector;
-	u16 guest_pml_index;
-};
-
-/*
- * For save/restore compatibility, the vmcs12 field offsets must not change.
- */
-#define CHECK_OFFSET(field, loc)				\
-	BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc),	\
-		"Offset of " #field " in struct vmcs12 has changed.")
-
-static inline void vmx_check_vmcs12_offsets(void) {
-	CHECK_OFFSET(hdr, 0);
-	CHECK_OFFSET(abort, 4);
-	CHECK_OFFSET(launch_state, 8);
-	CHECK_OFFSET(io_bitmap_a, 40);
-	CHECK_OFFSET(io_bitmap_b, 48);
-	CHECK_OFFSET(msr_bitmap, 56);
-	CHECK_OFFSET(vm_exit_msr_store_addr, 64);
-	CHECK_OFFSET(vm_exit_msr_load_addr, 72);
-	CHECK_OFFSET(vm_entry_msr_load_addr, 80);
-	CHECK_OFFSET(tsc_offset, 88);
-	CHECK_OFFSET(virtual_apic_page_addr, 96);
-	CHECK_OFFSET(apic_access_addr, 104);
-	CHECK_OFFSET(posted_intr_desc_addr, 112);
-	CHECK_OFFSET(ept_pointer, 120);
-	CHECK_OFFSET(eoi_exit_bitmap0, 128);
-	CHECK_OFFSET(eoi_exit_bitmap1, 136);
-	CHECK_OFFSET(eoi_exit_bitmap2, 144);
-	CHECK_OFFSET(eoi_exit_bitmap3, 152);
-	CHECK_OFFSET(xss_exit_bitmap, 160);
-	CHECK_OFFSET(guest_physical_address, 168);
-	CHECK_OFFSET(vmcs_link_pointer, 176);
-	CHECK_OFFSET(guest_ia32_debugctl, 184);
-	CHECK_OFFSET(guest_ia32_pat, 192);
-	CHECK_OFFSET(guest_ia32_efer, 200);
-	CHECK_OFFSET(guest_ia32_perf_global_ctrl, 208);
-	CHECK_OFFSET(guest_pdptr0, 216);
-	CHECK_OFFSET(guest_pdptr1, 224);
-	CHECK_OFFSET(guest_pdptr2, 232);
-	CHECK_OFFSET(guest_pdptr3, 240);
-	CHECK_OFFSET(guest_bndcfgs, 248);
-	CHECK_OFFSET(host_ia32_pat, 256);
-	CHECK_OFFSET(host_ia32_efer, 264);
-	CHECK_OFFSET(host_ia32_perf_global_ctrl, 272);
-	CHECK_OFFSET(vmread_bitmap, 280);
-	CHECK_OFFSET(vmwrite_bitmap, 288);
-	CHECK_OFFSET(vm_function_control, 296);
-	CHECK_OFFSET(eptp_list_address, 304);
-	CHECK_OFFSET(pml_address, 312);
-	CHECK_OFFSET(cr0_guest_host_mask, 344);
-	CHECK_OFFSET(cr4_guest_host_mask, 352);
-	CHECK_OFFSET(cr0_read_shadow, 360);
-	CHECK_OFFSET(cr4_read_shadow, 368);
-	CHECK_OFFSET(cr3_target_value0, 376);
-	CHECK_OFFSET(cr3_target_value1, 384);
-	CHECK_OFFSET(cr3_target_value2, 392);
-	CHECK_OFFSET(cr3_target_value3, 400);
-	CHECK_OFFSET(exit_qualification, 408);
-	CHECK_OFFSET(guest_linear_address, 416);
-	CHECK_OFFSET(guest_cr0, 424);
-	CHECK_OFFSET(guest_cr3, 432);
-	CHECK_OFFSET(guest_cr4, 440);
-	CHECK_OFFSET(guest_es_base, 448);
-	CHECK_OFFSET(guest_cs_base, 456);
-	CHECK_OFFSET(guest_ss_base, 464);
-	CHECK_OFFSET(guest_ds_base, 472);
-	CHECK_OFFSET(guest_fs_base, 480);
-	CHECK_OFFSET(guest_gs_base, 488);
-	CHECK_OFFSET(guest_ldtr_base, 496);
-	CHECK_OFFSET(guest_tr_base, 504);
-	CHECK_OFFSET(guest_gdtr_base, 512);
-	CHECK_OFFSET(guest_idtr_base, 520);
-	CHECK_OFFSET(guest_dr7, 528);
-	CHECK_OFFSET(guest_rsp, 536);
-	CHECK_OFFSET(guest_rip, 544);
-	CHECK_OFFSET(guest_rflags, 552);
-	CHECK_OFFSET(guest_pending_dbg_exceptions, 560);
-	CHECK_OFFSET(guest_sysenter_esp, 568);
-	CHECK_OFFSET(guest_sysenter_eip, 576);
-	CHECK_OFFSET(host_cr0, 584);
-	CHECK_OFFSET(host_cr3, 592);
-	CHECK_OFFSET(host_cr4, 600);
-	CHECK_OFFSET(host_fs_base, 608);
-	CHECK_OFFSET(host_gs_base, 616);
-	CHECK_OFFSET(host_tr_base, 624);
-	CHECK_OFFSET(host_gdtr_base, 632);
-	CHECK_OFFSET(host_idtr_base, 640);
-	CHECK_OFFSET(host_ia32_sysenter_esp, 648);
-	CHECK_OFFSET(host_ia32_sysenter_eip, 656);
-	CHECK_OFFSET(host_rsp, 664);
-	CHECK_OFFSET(host_rip, 672);
-	CHECK_OFFSET(pin_based_vm_exec_control, 744);
-	CHECK_OFFSET(cpu_based_vm_exec_control, 748);
-	CHECK_OFFSET(exception_bitmap, 752);
-	CHECK_OFFSET(page_fault_error_code_mask, 756);
-	CHECK_OFFSET(page_fault_error_code_match, 760);
-	CHECK_OFFSET(cr3_target_count, 764);
-	CHECK_OFFSET(vm_exit_controls, 768);
-	CHECK_OFFSET(vm_exit_msr_store_count, 772);
-	CHECK_OFFSET(vm_exit_msr_load_count, 776);
-	CHECK_OFFSET(vm_entry_controls, 780);
-	CHECK_OFFSET(vm_entry_msr_load_count, 784);
-	CHECK_OFFSET(vm_entry_intr_info_field, 788);
-	CHECK_OFFSET(vm_entry_exception_error_code, 792);
-	CHECK_OFFSET(vm_entry_instruction_len, 796);
-	CHECK_OFFSET(tpr_threshold, 800);
-	CHECK_OFFSET(secondary_vm_exec_control, 804);
-	CHECK_OFFSET(vm_instruction_error, 808);
-	CHECK_OFFSET(vm_exit_reason, 812);
-	CHECK_OFFSET(vm_exit_intr_info, 816);
-	CHECK_OFFSET(vm_exit_intr_error_code, 820);
-	CHECK_OFFSET(idt_vectoring_info_field, 824);
-	CHECK_OFFSET(idt_vectoring_error_code, 828);
-	CHECK_OFFSET(vm_exit_instruction_len, 832);
-	CHECK_OFFSET(vmx_instruction_info, 836);
-	CHECK_OFFSET(guest_es_limit, 840);
-	CHECK_OFFSET(guest_cs_limit, 844);
-	CHECK_OFFSET(guest_ss_limit, 848);
-	CHECK_OFFSET(guest_ds_limit, 852);
-	CHECK_OFFSET(guest_fs_limit, 856);
-	CHECK_OFFSET(guest_gs_limit, 860);
-	CHECK_OFFSET(guest_ldtr_limit, 864);
-	CHECK_OFFSET(guest_tr_limit, 868);
-	CHECK_OFFSET(guest_gdtr_limit, 872);
-	CHECK_OFFSET(guest_idtr_limit, 876);
-	CHECK_OFFSET(guest_es_ar_bytes, 880);
-	CHECK_OFFSET(guest_cs_ar_bytes, 884);
-	CHECK_OFFSET(guest_ss_ar_bytes, 888);
-	CHECK_OFFSET(guest_ds_ar_bytes, 892);
-	CHECK_OFFSET(guest_fs_ar_bytes, 896);
-	CHECK_OFFSET(guest_gs_ar_bytes, 900);
-	CHECK_OFFSET(guest_ldtr_ar_bytes, 904);
-	CHECK_OFFSET(guest_tr_ar_bytes, 908);
-	CHECK_OFFSET(guest_interruptibility_info, 912);
-	CHECK_OFFSET(guest_activity_state, 916);
-	CHECK_OFFSET(guest_sysenter_cs, 920);
-	CHECK_OFFSET(host_ia32_sysenter_cs, 924);
-	CHECK_OFFSET(vmx_preemption_timer_value, 928);
-	CHECK_OFFSET(virtual_processor_id, 960);
-	CHECK_OFFSET(posted_intr_nv, 962);
-	CHECK_OFFSET(guest_es_selector, 964);
-	CHECK_OFFSET(guest_cs_selector, 966);
-	CHECK_OFFSET(guest_ss_selector, 968);
-	CHECK_OFFSET(guest_ds_selector, 970);
-	CHECK_OFFSET(guest_fs_selector, 972);
-	CHECK_OFFSET(guest_gs_selector, 974);
-	CHECK_OFFSET(guest_ldtr_selector, 976);
-	CHECK_OFFSET(guest_tr_selector, 978);
-	CHECK_OFFSET(guest_intr_status, 980);
-	CHECK_OFFSET(host_es_selector, 982);
-	CHECK_OFFSET(host_cs_selector, 984);
-	CHECK_OFFSET(host_ss_selector, 986);
-	CHECK_OFFSET(host_ds_selector, 988);
-	CHECK_OFFSET(host_fs_selector, 990);
-	CHECK_OFFSET(host_gs_selector, 992);
-	CHECK_OFFSET(host_tr_selector, 994);
-	CHECK_OFFSET(guest_pml_index, 996);
-}
-
-/*
- * VMCS12_REVISION is an arbitrary id that should be changed if the content or
- * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and
- * VMPTRLD verifies that the VMCS region that L1 is loading contains this id.
- *
- * IMPORTANT: Changing this value will break save/restore compatibility with
- * older kvm releases.
- */
-#define VMCS12_REVISION 0x11e57ed0
-
-/*
- * VMCS12_SIZE is the number of bytes L1 should allocate for the VMXON region
- * and any VMCS region. Although only sizeof(struct vmcs12) are used by the
- * current implementation, 4K are reserved to avoid future complications.
- */
-#define VMCS12_SIZE 0x1000
-
-/*
- * VMCS12_MAX_FIELD_INDEX is the highest index value used in any
- * supported VMCS12 field encoding.
- */
-#define VMCS12_MAX_FIELD_INDEX 0x17
-
-struct nested_vmx_msrs {
-	/*
-	 * We only store the "true" versions of the VMX capability MSRs. We
-	 * generate the "non-true" versions by setting the must-be-1 bits
-	 * according to the SDM.
-	 */
-	u32 procbased_ctls_low;
-	u32 procbased_ctls_high;
-	u32 secondary_ctls_low;
-	u32 secondary_ctls_high;
-	u32 pinbased_ctls_low;
-	u32 pinbased_ctls_high;
-	u32 exit_ctls_low;
-	u32 exit_ctls_high;
-	u32 entry_ctls_low;
-	u32 entry_ctls_high;
-	u32 misc_low;
-	u32 misc_high;
-	u32 ept_caps;
-	u32 vpid_caps;
-	u64 basic;
-	u64 cr0_fixed0;
-	u64 cr0_fixed1;
-	u64 cr4_fixed0;
-	u64 cr4_fixed1;
-	u64 vmcs_enum;
-	u64 vmfunc_controls;
-};
-
-/*
- * The nested_vmx structure is part of vcpu_vmx, and holds information we need
- * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
- */
-struct nested_vmx {
-	/* Has the level1 guest done vmxon? */
-	bool vmxon;
-	gpa_t vmxon_ptr;
-	bool pml_full;
-
-	/* The guest-physical address of the current VMCS L1 keeps for L2 */
-	gpa_t current_vmptr;
-	/*
-	 * Cache of the guest's VMCS, existing outside of guest memory.
-	 * Loaded from guest memory during VMPTRLD. Flushed to guest
-	 * memory during VMCLEAR and VMPTRLD.
-	 */
-	struct vmcs12 *cached_vmcs12;
-	/*
-	 * Cache of the guest's shadow VMCS, existing outside of guest
-	 * memory. Loaded from guest memory during VM entry. Flushed
-	 * to guest memory during VM exit.
-	 */
-	struct vmcs12 *cached_shadow_vmcs12;
-	/*
-	 * Indicates if the shadow vmcs must be updated with the
-	 * data hold by vmcs12
-	 */
-	bool sync_shadow_vmcs;
-	bool dirty_vmcs12;
-
-	bool change_vmcs01_virtual_apic_mode;
-
-	/* L2 must run next, and mustn't decide to exit to L1. */
-	bool nested_run_pending;
-
-	struct loaded_vmcs vmcs02;
-
-	/*
-	 * Guest pages referred to in the vmcs02 with host-physical
-	 * pointers, so we must keep them pinned while L2 runs.
-	 */
-	struct page *apic_access_page;
-	struct page *virtual_apic_page;
-	struct page *pi_desc_page;
-	struct pi_desc *pi_desc;
-	bool pi_pending;
-	u16 posted_intr_nv;
-
-	struct hrtimer preemption_timer;
-	bool preemption_timer_expired;
-
-	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
-	u64 vmcs01_debugctl;
-	u64 vmcs01_guest_bndcfgs;
-
-	u16 vpid02;
-	u16 last_vpid;
-
-	struct nested_vmx_msrs msrs;
-
-	/* SMM related state */
-	struct {
-		/* in VMX operation on SMM entry? */
-		bool vmxon;
-		/* in guest mode on SMM entry? */
-		bool guest_mode;
-	} smm;
-};
-
-#define POSTED_INTR_ON  0
-#define POSTED_INTR_SN  1
-
-/* Posted-Interrupt Descriptor */
-struct pi_desc {
-	u32 pir[8];     /* Posted interrupt requested */
-	union {
-		struct {
-				/* bit 256 - Outstanding Notification */
-			u16	on	: 1,
-				/* bit 257 - Suppress Notification */
-				sn	: 1,
-				/* bit 271:258 - Reserved */
-				rsvd_1	: 14;
-				/* bit 279:272 - Notification Vector */
-			u8	nv;
-				/* bit 287:280 - Reserved */
-			u8	rsvd_2;
-				/* bit 319:288 - Notification Destination */
-			u32	ndst;
-		};
-		u64 control;
-	};
-	u32 rsvd[6];
-} __aligned(64);
-
-static bool pi_test_and_set_on(struct pi_desc *pi_desc)
-{
-	return test_and_set_bit(POSTED_INTR_ON,
-			(unsigned long *)&pi_desc->control);
-}
-
-static bool pi_test_and_clear_on(struct pi_desc *pi_desc)
-{
-	return test_and_clear_bit(POSTED_INTR_ON,
-			(unsigned long *)&pi_desc->control);
-}
-
-static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
-{
-	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
-}
-
-static inline void pi_clear_sn(struct pi_desc *pi_desc)
-{
-	return clear_bit(POSTED_INTR_SN,
-			(unsigned long *)&pi_desc->control);
-}
-
-static inline void pi_set_sn(struct pi_desc *pi_desc)
-{
-	return set_bit(POSTED_INTR_SN,
-			(unsigned long *)&pi_desc->control);
-}
-
-static inline void pi_clear_on(struct pi_desc *pi_desc)
-{
-	clear_bit(POSTED_INTR_ON,
-  		  (unsigned long *)&pi_desc->control);
-}
-
-static inline int pi_test_on(struct pi_desc *pi_desc)
-{
-	return test_bit(POSTED_INTR_ON,
-			(unsigned long *)&pi_desc->control);
-}
-
-static inline int pi_test_sn(struct pi_desc *pi_desc)
-{
-	return test_bit(POSTED_INTR_SN,
-			(unsigned long *)&pi_desc->control);
-}
-
-struct vmx_msrs {
-	unsigned int		nr;
-	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
-};
-
-struct vcpu_vmx {
-	struct kvm_vcpu       vcpu;
-	unsigned long         host_rsp;
-	u8                    fail;
-	u8		      msr_bitmap_mode;
-	u32                   exit_intr_info;
-	u32                   idt_vectoring_info;
-	ulong                 rflags;
-	struct shared_msr_entry *guest_msrs;
-	int                   nmsrs;
-	int                   save_nmsrs;
-	bool                  guest_msrs_dirty;
-	unsigned long	      host_idt_base;
-#ifdef CONFIG_X86_64
-	u64 		      msr_host_kernel_gs_base;
-	u64 		      msr_guest_kernel_gs_base;
-#endif
-
-	u64 		      arch_capabilities;
-	u64 		      spec_ctrl;
-
-	u32 vm_entry_controls_shadow;
-	u32 vm_exit_controls_shadow;
-	u32 secondary_exec_control;
-
-	/*
-	 * loaded_vmcs points to the VMCS currently used in this vcpu. For a
-	 * non-nested (L1) guest, it always points to vmcs01. For a nested
-	 * guest (L2), it points to a different VMCS.  loaded_cpu_state points
-	 * to the VMCS whose state is loaded into the CPU registers that only
-	 * need to be switched when transitioning to/from the kernel; a NULL
-	 * value indicates that host state is loaded.
-	 */
-	struct loaded_vmcs    vmcs01;
-	struct loaded_vmcs   *loaded_vmcs;
-	struct loaded_vmcs   *loaded_cpu_state;
-	bool                  __launched; /* temporary, used in vmx_vcpu_run */
-	struct msr_autoload {
-		struct vmx_msrs guest;
-		struct vmx_msrs host;
-	} msr_autoload;
-
-	struct {
-		int vm86_active;
-		ulong save_rflags;
-		struct kvm_segment segs[8];
-	} rmode;
-	struct {
-		u32 bitmask; /* 4 bits per segment (1 bit per field) */
-		struct kvm_save_segment {
-			u16 selector;
-			unsigned long base;
-			u32 limit;
-			u32 ar;
-		} seg[8];
-	} segment_cache;
-	int vpid;
-	bool emulation_required;
-
-	u32 exit_reason;
-
-	/* Posted interrupt descriptor */
-	struct pi_desc pi_desc;
-
-	/* Support for a guest hypervisor (nested VMX) */
-	struct nested_vmx nested;
-
-	/* Dynamic PLE window. */
-	int ple_window;
-	bool ple_window_dirty;
-
-	bool req_immediate_exit;
-
-	/* Support for PML */
-#define PML_ENTITY_NUM		512
-	struct page *pml_pg;
-
-	/* apic deadline value in host tsc */
-	u64 hv_deadline_tsc;
-
-	u64 current_tsc_ratio;
-
-	u32 host_pkru;
-
-	unsigned long host_debugctlmsr;
-
-	/*
-	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
-	 * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
-	 * in msr_ia32_feature_control_valid_bits.
-	 */
-	u64 msr_ia32_feature_control;
-	u64 msr_ia32_feature_control_valid_bits;
-	u64 ept_pointer;
-};
-
-enum segment_cache_field {
-	SEG_FIELD_SEL = 0,
-	SEG_FIELD_BASE = 1,
-	SEG_FIELD_LIMIT = 2,
-	SEG_FIELD_AR = 3,
-
-	SEG_FIELD_NR = 4
-};
-
-static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm)
-{
-	return container_of(kvm, struct kvm_vmx, kvm);
-}
-
-static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
-{
-	return container_of(vcpu, struct vcpu_vmx, vcpu);
-}
-
-static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
-{
-	return &(to_vmx(vcpu)->pi_desc);
-}
-
-#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n)))))
-#define VMCS12_OFFSET(x) offsetof(struct vmcs12, x)
-#define FIELD(number, name)	[ROL16(number, 6)] = VMCS12_OFFSET(name)
-#define FIELD64(number, name)						\
-	FIELD(number, name),						\
-	[ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32)
-
-
-static u16 shadow_read_only_fields[] = {
-#define SHADOW_FIELD_RO(x) x,
-#include "vmx_shadow_fields.h"
-};
-static int max_shadow_read_only_fields =
-	ARRAY_SIZE(shadow_read_only_fields);
-
-static u16 shadow_read_write_fields[] = {
-#define SHADOW_FIELD_RW(x) x,
-#include "vmx_shadow_fields.h"
-};
-static int max_shadow_read_write_fields =
-	ARRAY_SIZE(shadow_read_write_fields);
-
-static const unsigned short vmcs_field_to_offset_table[] = {
-	FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id),
-	FIELD(POSTED_INTR_NV, posted_intr_nv),
-	FIELD(GUEST_ES_SELECTOR, guest_es_selector),
-	FIELD(GUEST_CS_SELECTOR, guest_cs_selector),
-	FIELD(GUEST_SS_SELECTOR, guest_ss_selector),
-	FIELD(GUEST_DS_SELECTOR, guest_ds_selector),
-	FIELD(GUEST_FS_SELECTOR, guest_fs_selector),
-	FIELD(GUEST_GS_SELECTOR, guest_gs_selector),
-	FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector),
-	FIELD(GUEST_TR_SELECTOR, guest_tr_selector),
-	FIELD(GUEST_INTR_STATUS, guest_intr_status),
-	FIELD(GUEST_PML_INDEX, guest_pml_index),
-	FIELD(HOST_ES_SELECTOR, host_es_selector),
-	FIELD(HOST_CS_SELECTOR, host_cs_selector),
-	FIELD(HOST_SS_SELECTOR, host_ss_selector),
-	FIELD(HOST_DS_SELECTOR, host_ds_selector),
-	FIELD(HOST_FS_SELECTOR, host_fs_selector),
-	FIELD(HOST_GS_SELECTOR, host_gs_selector),
-	FIELD(HOST_TR_SELECTOR, host_tr_selector),
-	FIELD64(IO_BITMAP_A, io_bitmap_a),
-	FIELD64(IO_BITMAP_B, io_bitmap_b),
-	FIELD64(MSR_BITMAP, msr_bitmap),
-	FIELD64(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr),
-	FIELD64(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr),
-	FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr),
-	FIELD64(PML_ADDRESS, pml_address),
-	FIELD64(TSC_OFFSET, tsc_offset),
-	FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr),
-	FIELD64(APIC_ACCESS_ADDR, apic_access_addr),
-	FIELD64(POSTED_INTR_DESC_ADDR, posted_intr_desc_addr),
-	FIELD64(VM_FUNCTION_CONTROL, vm_function_control),
-	FIELD64(EPT_POINTER, ept_pointer),
-	FIELD64(EOI_EXIT_BITMAP0, eoi_exit_bitmap0),
-	FIELD64(EOI_EXIT_BITMAP1, eoi_exit_bitmap1),
-	FIELD64(EOI_EXIT_BITMAP2, eoi_exit_bitmap2),
-	FIELD64(EOI_EXIT_BITMAP3, eoi_exit_bitmap3),
-	FIELD64(EPTP_LIST_ADDRESS, eptp_list_address),
-	FIELD64(VMREAD_BITMAP, vmread_bitmap),
-	FIELD64(VMWRITE_BITMAP, vmwrite_bitmap),
-	FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
-	FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
-	FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
-	FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
-	FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
-	FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
-	FIELD64(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl),
-	FIELD64(GUEST_PDPTR0, guest_pdptr0),
-	FIELD64(GUEST_PDPTR1, guest_pdptr1),
-	FIELD64(GUEST_PDPTR2, guest_pdptr2),
-	FIELD64(GUEST_PDPTR3, guest_pdptr3),
-	FIELD64(GUEST_BNDCFGS, guest_bndcfgs),
-	FIELD64(HOST_IA32_PAT, host_ia32_pat),
-	FIELD64(HOST_IA32_EFER, host_ia32_efer),
-	FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl),
-	FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control),
-	FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control),
-	FIELD(EXCEPTION_BITMAP, exception_bitmap),
-	FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask),
-	FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match),
-	FIELD(CR3_TARGET_COUNT, cr3_target_count),
-	FIELD(VM_EXIT_CONTROLS, vm_exit_controls),
-	FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count),
-	FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count),
-	FIELD(VM_ENTRY_CONTROLS, vm_entry_controls),
-	FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count),
-	FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field),
-	FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, vm_entry_exception_error_code),
-	FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len),
-	FIELD(TPR_THRESHOLD, tpr_threshold),
-	FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control),
-	FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error),
-	FIELD(VM_EXIT_REASON, vm_exit_reason),
-	FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info),
-	FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code),
-	FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field),
-	FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code),
-	FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len),
-	FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info),
-	FIELD(GUEST_ES_LIMIT, guest_es_limit),
-	FIELD(GUEST_CS_LIMIT, guest_cs_limit),
-	FIELD(GUEST_SS_LIMIT, guest_ss_limit),
-	FIELD(GUEST_DS_LIMIT, guest_ds_limit),
-	FIELD(GUEST_FS_LIMIT, guest_fs_limit),
-	FIELD(GUEST_GS_LIMIT, guest_gs_limit),
-	FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit),
-	FIELD(GUEST_TR_LIMIT, guest_tr_limit),
-	FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit),
-	FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit),
-	FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes),
-	FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes),
-	FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes),
-	FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes),
-	FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes),
-	FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes),
-	FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes),
-	FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes),
-	FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info),
-	FIELD(GUEST_ACTIVITY_STATE, guest_activity_state),
-	FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs),
-	FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs),
-	FIELD(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value),
-	FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask),
-	FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask),
-	FIELD(CR0_READ_SHADOW, cr0_read_shadow),
-	FIELD(CR4_READ_SHADOW, cr4_read_shadow),
-	FIELD(CR3_TARGET_VALUE0, cr3_target_value0),
-	FIELD(CR3_TARGET_VALUE1, cr3_target_value1),
-	FIELD(CR3_TARGET_VALUE2, cr3_target_value2),
-	FIELD(CR3_TARGET_VALUE3, cr3_target_value3),
-	FIELD(EXIT_QUALIFICATION, exit_qualification),
-	FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address),
-	FIELD(GUEST_CR0, guest_cr0),
-	FIELD(GUEST_CR3, guest_cr3),
-	FIELD(GUEST_CR4, guest_cr4),
-	FIELD(GUEST_ES_BASE, guest_es_base),
-	FIELD(GUEST_CS_BASE, guest_cs_base),
-	FIELD(GUEST_SS_BASE, guest_ss_base),
-	FIELD(GUEST_DS_BASE, guest_ds_base),
-	FIELD(GUEST_FS_BASE, guest_fs_base),
-	FIELD(GUEST_GS_BASE, guest_gs_base),
-	FIELD(GUEST_LDTR_BASE, guest_ldtr_base),
-	FIELD(GUEST_TR_BASE, guest_tr_base),
-	FIELD(GUEST_GDTR_BASE, guest_gdtr_base),
-	FIELD(GUEST_IDTR_BASE, guest_idtr_base),
-	FIELD(GUEST_DR7, guest_dr7),
-	FIELD(GUEST_RSP, guest_rsp),
-	FIELD(GUEST_RIP, guest_rip),
-	FIELD(GUEST_RFLAGS, guest_rflags),
-	FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions),
-	FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp),
-	FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip),
-	FIELD(HOST_CR0, host_cr0),
-	FIELD(HOST_CR3, host_cr3),
-	FIELD(HOST_CR4, host_cr4),
-	FIELD(HOST_FS_BASE, host_fs_base),
-	FIELD(HOST_GS_BASE, host_gs_base),
-	FIELD(HOST_TR_BASE, host_tr_base),
-	FIELD(HOST_GDTR_BASE, host_gdtr_base),
-	FIELD(HOST_IDTR_BASE, host_idtr_base),
-	FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp),
-	FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip),
-	FIELD(HOST_RSP, host_rsp),
-	FIELD(HOST_RIP, host_rip),
-};
-
-static inline short vmcs_field_to_offset(unsigned long field)
-{
-	const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table);
-	unsigned short offset;
-	unsigned index;
-
-	if (field >> 15)
-		return -ENOENT;
-
-	index = ROL16(field, 6);
-	if (index >= size)
-		return -ENOENT;
-
-	index = array_index_nospec(index, size);
-	offset = vmcs_field_to_offset_table[index];
-	if (offset == 0)
-		return -ENOENT;
-	return offset;
-}
-
-static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->nested.cached_vmcs12;
-}
-
-static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->nested.cached_shadow_vmcs12;
-}
-
-static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu);
-static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
-static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa);
-static bool vmx_xsaves_supported(void);
-static void vmx_set_segment(struct kvm_vcpu *vcpu,
-			    struct kvm_segment *var, int seg);
-static void vmx_get_segment(struct kvm_vcpu *vcpu,
-			    struct kvm_segment *var, int seg);
-static bool guest_state_valid(struct kvm_vcpu *vcpu);
-static u32 vmx_segment_access_rights(struct kvm_segment *var);
-static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
-static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
-static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
-static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
-					    u16 error_code);
-static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
-static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
-							  u32 msr, int type);
-
-static DEFINE_PER_CPU(struct vmcs *, vmxarea);
-static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
-/*
- * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed
- * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it.
- */
-static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
-
-/*
- * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we
- * can find which vCPU should be waken up.
- */
-static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
-static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
-
-enum {
-	VMX_VMREAD_BITMAP,
-	VMX_VMWRITE_BITMAP,
-	VMX_BITMAP_NR
-};
-
-static unsigned long *vmx_bitmap[VMX_BITMAP_NR];
-
-#define vmx_vmread_bitmap                    (vmx_bitmap[VMX_VMREAD_BITMAP])
-#define vmx_vmwrite_bitmap                   (vmx_bitmap[VMX_VMWRITE_BITMAP])
-
-static bool cpu_has_load_ia32_efer;
-static bool cpu_has_load_perf_global_ctrl;
-
-static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
-static DEFINE_SPINLOCK(vmx_vpid_lock);
-
-static struct vmcs_config {
-	int size;
-	int order;
-	u32 basic_cap;
-	u32 revision_id;
-	u32 pin_based_exec_ctrl;
-	u32 cpu_based_exec_ctrl;
-	u32 cpu_based_2nd_exec_ctrl;
-	u32 vmexit_ctrl;
-	u32 vmentry_ctrl;
-	struct nested_vmx_msrs nested;
-} vmcs_config;
-
-static struct vmx_capability {
-	u32 ept;
-	u32 vpid;
-} vmx_capability;
-
-#define VMX_SEGMENT_FIELD(seg)					\
-	[VCPU_SREG_##seg] = {                                   \
-		.selector = GUEST_##seg##_SELECTOR,		\
-		.base = GUEST_##seg##_BASE,		   	\
-		.limit = GUEST_##seg##_LIMIT,		   	\
-		.ar_bytes = GUEST_##seg##_AR_BYTES,	   	\
-	}
-
-static const struct kvm_vmx_segment_field {
-	unsigned selector;
-	unsigned base;
-	unsigned limit;
-	unsigned ar_bytes;
-} kvm_vmx_segment_fields[] = {
-	VMX_SEGMENT_FIELD(CS),
-	VMX_SEGMENT_FIELD(DS),
-	VMX_SEGMENT_FIELD(ES),
-	VMX_SEGMENT_FIELD(FS),
-	VMX_SEGMENT_FIELD(GS),
-	VMX_SEGMENT_FIELD(SS),
-	VMX_SEGMENT_FIELD(TR),
-	VMX_SEGMENT_FIELD(LDTR),
-};
-
-static u64 host_efer;
-
-static void ept_save_pdptrs(struct kvm_vcpu *vcpu);
-
-/*
- * Keep MSR_STAR at the end, as setup_msrs() will try to optimize it
- * away by decrementing the array size.
- */
-static const u32 vmx_msr_index[] = {
-#ifdef CONFIG_X86_64
-	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
-#endif
-	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
-};
-
-DEFINE_STATIC_KEY_FALSE(enable_evmcs);
-
-#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs))
-
-#define KVM_EVMCS_VERSION 1
-
-#if IS_ENABLED(CONFIG_HYPERV)
-static bool __read_mostly enlightened_vmcs = true;
-module_param(enlightened_vmcs, bool, 0444);
-
-static inline void evmcs_write64(unsigned long field, u64 value)
-{
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u64 *)((char *)current_evmcs + offset) = value;
-
-	current_evmcs->hv_clean_fields &= ~clean_field;
-}
-
-static inline void evmcs_write32(unsigned long field, u32 value)
-{
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u32 *)((char *)current_evmcs + offset) = value;
-	current_evmcs->hv_clean_fields &= ~clean_field;
-}
-
-static inline void evmcs_write16(unsigned long field, u16 value)
-{
-	u16 clean_field;
-	int offset = get_evmcs_offset(field, &clean_field);
-
-	if (offset < 0)
-		return;
-
-	*(u16 *)((char *)current_evmcs + offset) = value;
-	current_evmcs->hv_clean_fields &= ~clean_field;
-}
-
-static inline u64 evmcs_read64(unsigned long field)
-{
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u64 *)((char *)current_evmcs + offset);
-}
-
-static inline u32 evmcs_read32(unsigned long field)
-{
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u32 *)((char *)current_evmcs + offset);
-}
-
-static inline u16 evmcs_read16(unsigned long field)
-{
-	int offset = get_evmcs_offset(field, NULL);
-
-	if (offset < 0)
-		return 0;
-
-	return *(u16 *)((char *)current_evmcs + offset);
-}
-
-static inline void evmcs_touch_msr_bitmap(void)
-{
-	if (unlikely(!current_evmcs))
-		return;
-
-	if (current_evmcs->hv_enlightenments_control.msr_bitmap)
-		current_evmcs->hv_clean_fields &=
-			~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
-}
-
-static void evmcs_load(u64 phys_addr)
-{
-	struct hv_vp_assist_page *vp_ap =
-		hv_get_vp_assist_page(smp_processor_id());
-
-	vp_ap->current_nested_vmcs = phys_addr;
-	vp_ap->enlighten_vmentry = 1;
-}
-
-static void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
-{
-	/*
-	 * Enlightened VMCSv1 doesn't support these:
-	 *
-	 *	POSTED_INTR_NV                  = 0x00000002,
-	 *	GUEST_INTR_STATUS               = 0x00000810,
-	 *	APIC_ACCESS_ADDR		= 0x00002014,
-	 *	POSTED_INTR_DESC_ADDR           = 0x00002016,
-	 *	EOI_EXIT_BITMAP0                = 0x0000201c,
-	 *	EOI_EXIT_BITMAP1                = 0x0000201e,
-	 *	EOI_EXIT_BITMAP2                = 0x00002020,
-	 *	EOI_EXIT_BITMAP3                = 0x00002022,
-	 */
-	vmcs_conf->pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
-	vmcs_conf->cpu_based_2nd_exec_ctrl &=
-		~SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
-	vmcs_conf->cpu_based_2nd_exec_ctrl &=
-		~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-	vmcs_conf->cpu_based_2nd_exec_ctrl &=
-		~SECONDARY_EXEC_APIC_REGISTER_VIRT;
-
-	/*
-	 *	GUEST_PML_INDEX			= 0x00000812,
-	 *	PML_ADDRESS			= 0x0000200e,
-	 */
-	vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_ENABLE_PML;
-
-	/*	VM_FUNCTION_CONTROL             = 0x00002018, */
-	vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_ENABLE_VMFUNC;
-
-	/*
-	 *	EPTP_LIST_ADDRESS               = 0x00002024,
-	 *	VMREAD_BITMAP                   = 0x00002026,
-	 *	VMWRITE_BITMAP                  = 0x00002028,
-	 */
-	vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_SHADOW_VMCS;
-
-	/*
-	 *	TSC_MULTIPLIER                  = 0x00002032,
-	 */
-	vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_TSC_SCALING;
-
-	/*
-	 *	PLE_GAP                         = 0x00004020,
-	 *	PLE_WINDOW                      = 0x00004022,
-	 */
-	vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
-
-	/*
-	 *	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
-	 */
-	vmcs_conf->pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
-
-	/*
-	 *      GUEST_IA32_PERF_GLOBAL_CTRL     = 0x00002808,
-	 *      HOST_IA32_PERF_GLOBAL_CTRL      = 0x00002c04,
-	 */
-	vmcs_conf->vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
-	vmcs_conf->vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
-
-	/*
-	 * Currently unsupported in KVM:
-	 *	GUEST_IA32_RTIT_CTL		= 0x00002814,
-	 */
-}
-
-/* check_ept_pointer() should be under protection of ept_pointer_lock. */
-static void check_ept_pointer_match(struct kvm *kvm)
-{
-	struct kvm_vcpu *vcpu;
-	u64 tmp_eptp = INVALID_PAGE;
-	int i;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (!VALID_PAGE(tmp_eptp)) {
-			tmp_eptp = to_vmx(vcpu)->ept_pointer;
-		} else if (tmp_eptp != to_vmx(vcpu)->ept_pointer) {
-			to_kvm_vmx(kvm)->ept_pointers_match
-				= EPT_POINTERS_MISMATCH;
-			return;
-		}
-	}
-
-	to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH;
-}
-
-static int vmx_hv_remote_flush_tlb(struct kvm *kvm)
-{
-	int ret;
-
-	spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock);
-
-	if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK)
-		check_ept_pointer_match(kvm);
-
-	if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) {
-		ret = -ENOTSUPP;
-		goto out;
-	}
-
-	/*
-	 * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs the address of the
-	 * base of EPT PML4 table, strip off EPT configuration information.
-	 */
-	ret = hyperv_flush_guest_mapping(
-			to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer & PAGE_MASK);
-
-out:
-	spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
-	return ret;
-}
-#else /* !IS_ENABLED(CONFIG_HYPERV) */
-static inline void evmcs_write64(unsigned long field, u64 value) {}
-static inline void evmcs_write32(unsigned long field, u32 value) {}
-static inline void evmcs_write16(unsigned long field, u16 value) {}
-static inline u64 evmcs_read64(unsigned long field) { return 0; }
-static inline u32 evmcs_read32(unsigned long field) { return 0; }
-static inline u16 evmcs_read16(unsigned long field) { return 0; }
-static inline void evmcs_load(u64 phys_addr) {}
-static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
-static inline void evmcs_touch_msr_bitmap(void) {}
-#endif /* IS_ENABLED(CONFIG_HYPERV) */
-
-static inline bool is_exception_n(u32 intr_info, u8 vector)
-{
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
-}
-
-static inline bool is_debug(u32 intr_info)
-{
-	return is_exception_n(intr_info, DB_VECTOR);
-}
-
-static inline bool is_breakpoint(u32 intr_info)
-{
-	return is_exception_n(intr_info, BP_VECTOR);
-}
-
-static inline bool is_page_fault(u32 intr_info)
-{
-	return is_exception_n(intr_info, PF_VECTOR);
-}
-
-static inline bool is_no_device(u32 intr_info)
-{
-	return is_exception_n(intr_info, NM_VECTOR);
-}
-
-static inline bool is_invalid_opcode(u32 intr_info)
-{
-	return is_exception_n(intr_info, UD_VECTOR);
-}
-
-static inline bool is_gp_fault(u32 intr_info)
-{
-	return is_exception_n(intr_info, GP_VECTOR);
-}
-
-static inline bool is_external_interrupt(u32 intr_info)
-{
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
-}
-
-static inline bool is_machine_check(u32 intr_info)
-{
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
-}
-
-/* Undocumented: icebp/int1 */
-static inline bool is_icebp(u32 intr_info)
-{
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
-}
-
-static inline bool cpu_has_vmx_msr_bitmap(void)
-{
-	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
-}
-
-static inline bool cpu_has_vmx_tpr_shadow(void)
-{
-	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
-}
-
-static inline bool cpu_need_tpr_shadow(struct kvm_vcpu *vcpu)
-{
-	return cpu_has_vmx_tpr_shadow() && lapic_in_kernel(vcpu);
-}
-
-static inline bool cpu_has_secondary_exec_ctrls(void)
-{
-	return vmcs_config.cpu_based_exec_ctrl &
-		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
-}
-
-static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-}
-
-static inline bool cpu_has_vmx_virtualize_x2apic_mode(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
-}
-
-static inline bool cpu_has_vmx_apic_register_virt(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_APIC_REGISTER_VIRT;
-}
-
-static inline bool cpu_has_vmx_virtual_intr_delivery(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
-}
-
-static inline bool cpu_has_vmx_encls_vmexit(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_ENCLS_EXITING;
-}
-
-/*
- * Comment's format: document - errata name - stepping - processor name.
- * Refer from
- * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp
- */
-static u32 vmx_preemption_cpu_tfms[] = {
-/* 323344.pdf - BA86   - D0 - Xeon 7500 Series */
-0x000206E6,
-/* 323056.pdf - AAX65  - C2 - Xeon L3406 */
-/* 322814.pdf - AAT59  - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */
-/* 322911.pdf - AAU65  - C2 - i5-600, i3-500 Desktop and Pentium G6950 */
-0x00020652,
-/* 322911.pdf - AAU65  - K0 - i5-600, i3-500 Desktop and Pentium G6950 */
-0x00020655,
-/* 322373.pdf - AAO95  - B1 - Xeon 3400 Series */
-/* 322166.pdf - AAN92  - B1 - i7-800 and i5-700 Desktop */
-/*
- * 320767.pdf - AAP86  - B1 -
- * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile
- */
-0x000106E5,
-/* 321333.pdf - AAM126 - C0 - Xeon 3500 */
-0x000106A0,
-/* 321333.pdf - AAM126 - C1 - Xeon 3500 */
-0x000106A1,
-/* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */
-0x000106A4,
- /* 321333.pdf - AAM126 - D0 - Xeon 3500 */
- /* 321324.pdf - AAK139 - D0 - Xeon 5500 */
- /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */
-0x000106A5,
-};
-
-static inline bool cpu_has_broken_vmx_preemption_timer(void)
-{
-	u32 eax = cpuid_eax(0x00000001), i;
-
-	/* Clear the reserved bits */
-	eax &= ~(0x3U << 14 | 0xfU << 28);
-	for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++)
-		if (eax == vmx_preemption_cpu_tfms[i])
-			return true;
-
-	return false;
-}
-
-static inline bool cpu_has_vmx_preemption_timer(void)
-{
-	return vmcs_config.pin_based_exec_ctrl &
-		PIN_BASED_VMX_PREEMPTION_TIMER;
-}
-
-static inline bool cpu_has_vmx_posted_intr(void)
-{
-	return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
-		vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
-}
-
-static inline bool cpu_has_vmx_apicv(void)
-{
-	return cpu_has_vmx_apic_register_virt() &&
-		cpu_has_vmx_virtual_intr_delivery() &&
-		cpu_has_vmx_posted_intr();
-}
-
-static inline bool cpu_has_vmx_flexpriority(void)
-{
-	return cpu_has_vmx_tpr_shadow() &&
-		cpu_has_vmx_virtualize_apic_accesses();
-}
-
-static inline bool cpu_has_vmx_ept_execute_only(void)
-{
-	return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
-}
-
-static inline bool cpu_has_vmx_ept_2m_page(void)
-{
-	return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
-}
-
-static inline bool cpu_has_vmx_ept_1g_page(void)
-{
-	return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
-}
-
-static inline bool cpu_has_vmx_ept_4levels(void)
-{
-	return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT;
-}
-
-static inline bool cpu_has_vmx_ept_mt_wb(void)
-{
-	return vmx_capability.ept & VMX_EPTP_WB_BIT;
-}
-
-static inline bool cpu_has_vmx_ept_5levels(void)
-{
-	return vmx_capability.ept & VMX_EPT_PAGE_WALK_5_BIT;
-}
-
-static inline bool cpu_has_vmx_ept_ad_bits(void)
-{
-	return vmx_capability.ept & VMX_EPT_AD_BIT;
-}
-
-static inline bool cpu_has_vmx_invept_context(void)
-{
-	return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
-}
-
-static inline bool cpu_has_vmx_invept_global(void)
-{
-	return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
-}
-
-static inline bool cpu_has_vmx_invvpid_individual_addr(void)
-{
-	return vmx_capability.vpid & VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT;
-}
-
-static inline bool cpu_has_vmx_invvpid_single(void)
-{
-	return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
-}
-
-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 &
-		SECONDARY_EXEC_ENABLE_EPT;
-}
-
-static inline bool cpu_has_vmx_unrestricted_guest(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_UNRESTRICTED_GUEST;
-}
-
-static inline bool cpu_has_vmx_ple(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
-}
-
-static inline bool cpu_has_vmx_basic_inout(void)
-{
-	return	(((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT);
-}
-
-static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
-{
-	return flexpriority_enabled && lapic_in_kernel(vcpu);
-}
-
-static inline bool cpu_has_vmx_vpid(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_ENABLE_VPID;
-}
-
-static inline bool cpu_has_vmx_rdtscp(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_RDTSCP;
-}
-
-static inline bool cpu_has_vmx_invpcid(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_ENABLE_INVPCID;
-}
-
-static inline bool cpu_has_virtual_nmis(void)
-{
-	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
-}
-
-static inline bool cpu_has_vmx_wbinvd_exit(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_WBINVD_EXITING;
-}
-
-static inline bool cpu_has_vmx_shadow_vmcs(void)
-{
-	u64 vmx_msr;
-	rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
-	/* check if the cpu supports writing r/o exit information fields */
-	if (!(vmx_msr & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS))
-		return false;
-
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_SHADOW_VMCS;
-}
-
-static inline bool cpu_has_vmx_pml(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML;
-}
-
-static inline bool cpu_has_vmx_tsc_scaling(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_TSC_SCALING;
-}
-
-static inline bool cpu_has_vmx_vmfunc(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_ENABLE_VMFUNC;
-}
-
-static bool vmx_umip_emulated(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_DESC;
-}
-
-static inline bool report_flexpriority(void)
-{
-	return flexpriority_enabled;
-}
-
-static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
-{
-	return vmx_misc_cr3_count(to_vmx(vcpu)->nested.msrs.misc_low);
-}
-
-/*
- * Do the virtual VMX capability MSRs specify that L1 can use VMWRITE
- * to modify any valid field of the VMCS, or are the VM-exit
- * information fields read-only?
- */
-static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->nested.msrs.misc_low &
-		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
-}
-
-static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS;
-}
-
-static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->nested.msrs.procbased_ctls_high &
-			CPU_BASED_MONITOR_TRAP_FLAG;
-}
-
-static inline bool nested_cpu_has_vmx_shadow_vmcs(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->nested.msrs.secondary_ctls_high &
-		SECONDARY_EXEC_SHADOW_VMCS;
-}
-
-static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
-{
-	return vmcs12->cpu_based_vm_exec_control & bit;
-}
-
-static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
-{
-	return (vmcs12->cpu_based_vm_exec_control &
-			CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
-		(vmcs12->secondary_vm_exec_control & bit);
-}
-
-static inline bool nested_cpu_has_preemption_timer(struct vmcs12 *vmcs12)
-{
-	return vmcs12->pin_based_vm_exec_control &
-		PIN_BASED_VMX_PREEMPTION_TIMER;
-}
-
-static inline bool nested_cpu_has_nmi_exiting(struct vmcs12 *vmcs12)
-{
-	return vmcs12->pin_based_vm_exec_control & PIN_BASED_NMI_EXITING;
-}
-
-static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
-{
-	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
-}
-
-static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
-}
-
-static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
-}
-
-static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML);
-}
-
-static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
-}
-
-static inline bool nested_cpu_has_vpid(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VPID);
-}
-
-static inline bool nested_cpu_has_apic_reg_virt(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_APIC_REGISTER_VIRT);
-}
-
-static inline bool nested_cpu_has_vid(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
-}
-
-static inline bool nested_cpu_has_posted_intr(struct vmcs12 *vmcs12)
-{
-	return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR;
-}
-
-static inline bool nested_cpu_has_vmfunc(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VMFUNC);
-}
-
-static inline bool nested_cpu_has_eptp_switching(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has_vmfunc(vmcs12) &&
-		(vmcs12->vm_function_control &
-		 VMX_VMFUNC_EPTP_SWITCHING);
-}
-
-static inline bool nested_cpu_has_shadow_vmcs(struct vmcs12 *vmcs12)
-{
-	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS);
-}
-
-static inline bool is_nmi(u32 intr_info)
-{
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
-}
-
-static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
-			      u32 exit_intr_info,
-			      unsigned long exit_qualification);
-static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
-			struct vmcs12 *vmcs12,
-			u32 reason, unsigned long qualification);
-
-static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
-{
-	int i;
-
-	for (i = 0; i < vmx->nmsrs; ++i)
-		if (vmx_msr_index[vmx->guest_msrs[i].index] == msr)
-			return i;
-	return -1;
-}
-
-static inline void __invvpid(int ext, u16 vpid, gva_t gva)
-{
-    struct {
-	u64 vpid : 16;
-	u64 rsvd : 48;
-	u64 gva;
-    } operand = { vpid, 0, gva };
-    bool error;
-
-    asm volatile (__ex(ASM_VMX_INVVPID) CC_SET(na)
-		  : CC_OUT(na) (error) : "a"(&operand), "c"(ext)
-		  : "memory");
-    BUG_ON(error);
-}
-
-static inline void __invept(int ext, u64 eptp, gpa_t gpa)
-{
-	struct {
-		u64 eptp, gpa;
-	} operand = {eptp, gpa};
-	bool error;
-
-	asm volatile (__ex(ASM_VMX_INVEPT) CC_SET(na)
-		      : CC_OUT(na) (error) : "a" (&operand), "c" (ext)
-		      : "memory");
-	BUG_ON(error);
-}
-
-static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
-{
-	int i;
-
-	i = __find_msr_index(vmx, msr);
-	if (i >= 0)
-		return &vmx->guest_msrs[i];
-	return NULL;
-}
-
-static void vmcs_clear(struct vmcs *vmcs)
-{
-	u64 phys_addr = __pa(vmcs);
-	bool error;
-
-	asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) CC_SET(na)
-		      : CC_OUT(na) (error) : "a"(&phys_addr), "m"(phys_addr)
-		      : "memory");
-	if (unlikely(error))
-		printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n",
-		       vmcs, phys_addr);
-}
-
-static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
-{
-	vmcs_clear(loaded_vmcs->vmcs);
-	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
-		vmcs_clear(loaded_vmcs->shadow_vmcs);
-	loaded_vmcs->cpu = -1;
-	loaded_vmcs->launched = 0;
-}
-
-static void vmcs_load(struct vmcs *vmcs)
-{
-	u64 phys_addr = __pa(vmcs);
-	bool error;
-
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_load(phys_addr);
-
-	asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) CC_SET(na)
-		      : CC_OUT(na) (error) : "a"(&phys_addr), "m"(phys_addr)
-		      : "memory");
-	if (unlikely(error))
-		printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n",
-		       vmcs, phys_addr);
-}
-
-#ifdef CONFIG_KEXEC_CORE
-/*
- * This bitmap is used to indicate whether the vmclear
- * operation is enabled on all cpus. All disabled by
- * default.
- */
-static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
-
-static inline void crash_enable_local_vmclear(int cpu)
-{
-	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline void crash_disable_local_vmclear(int cpu)
-{
-	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline int crash_local_vmclear_enabled(int cpu)
-{
-	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static void crash_vmclear_local_loaded_vmcss(void)
-{
-	int cpu = raw_smp_processor_id();
-	struct loaded_vmcs *v;
-
-	if (!crash_local_vmclear_enabled(cpu))
-		return;
-
-	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
-			    loaded_vmcss_on_cpu_link)
-		vmcs_clear(v->vmcs);
-}
-#else
-static inline void crash_enable_local_vmclear(int cpu) { }
-static inline void crash_disable_local_vmclear(int cpu) { }
-#endif /* CONFIG_KEXEC_CORE */
-
-static void __loaded_vmcs_clear(void *arg)
-{
-	struct loaded_vmcs *loaded_vmcs = arg;
-	int cpu = raw_smp_processor_id();
-
-	if (loaded_vmcs->cpu != cpu)
-		return; /* vcpu migration can race with cpu offline */
-	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
-		per_cpu(current_vmcs, cpu) = NULL;
-	crash_disable_local_vmclear(cpu);
-	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
-
-	/*
-	 * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link
-	 * is before setting loaded_vmcs->vcpu to -1 which is done in
-	 * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist
-	 * then adds the vmcs into percpu list before it is deleted.
-	 */
-	smp_wmb();
-
-	loaded_vmcs_init(loaded_vmcs);
-	crash_enable_local_vmclear(cpu);
-}
-
-static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
-{
-	int cpu = loaded_vmcs->cpu;
-
-	if (cpu != -1)
-		smp_call_function_single(cpu,
-			 __loaded_vmcs_clear, loaded_vmcs, 1);
-}
-
-static inline bool vpid_sync_vcpu_addr(int vpid, gva_t addr)
-{
-	if (vpid == 0)
-		return true;
-
-	if (cpu_has_vmx_invvpid_individual_addr()) {
-		__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR, vpid, addr);
-		return true;
-	}
-
-	return false;
-}
-
-static inline void vpid_sync_vcpu_single(int vpid)
-{
-	if (vpid == 0)
-		return;
-
-	if (cpu_has_vmx_invvpid_single())
-		__invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0);
-}
-
-static inline void vpid_sync_vcpu_global(void)
-{
-	if (cpu_has_vmx_invvpid_global())
-		__invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0);
-}
-
-static inline void vpid_sync_context(int vpid)
-{
-	if (cpu_has_vmx_invvpid_single())
-		vpid_sync_vcpu_single(vpid);
-	else
-		vpid_sync_vcpu_global();
-}
-
-static inline void ept_sync_global(void)
-{
-	__invept(VMX_EPT_EXTENT_GLOBAL, 0, 0);
-}
-
-static inline void ept_sync_context(u64 eptp)
-{
-	if (cpu_has_vmx_invept_context())
-		__invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0);
-	else
-		ept_sync_global();
-}
-
-static __always_inline void vmcs_check16(unsigned long field)
-{
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000,
-			 "16-bit accessor invalid for 64-bit field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
-			 "16-bit accessor invalid for 64-bit high field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
-			 "16-bit accessor invalid for 32-bit high field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
-			 "16-bit accessor invalid for natural width field");
-}
-
-static __always_inline void vmcs_check32(unsigned long field)
-{
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
-			 "32-bit accessor invalid for 16-bit field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
-			 "32-bit accessor invalid for natural width field");
-}
-
-static __always_inline void vmcs_check64(unsigned long field)
-{
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
-			 "64-bit accessor invalid for 16-bit field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
-			 "64-bit accessor invalid for 64-bit high field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
-			 "64-bit accessor invalid for 32-bit field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
-			 "64-bit accessor invalid for natural width field");
-}
-
-static __always_inline void vmcs_checkl(unsigned long field)
-{
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
-			 "Natural width accessor invalid for 16-bit field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000,
-			 "Natural width accessor invalid for 64-bit field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
-			 "Natural width accessor invalid for 64-bit high field");
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
-			 "Natural width accessor invalid for 32-bit field");
-}
-
-static __always_inline unsigned long __vmcs_readl(unsigned long field)
-{
-	unsigned long value;
-
-	asm volatile (__ex_clear(ASM_VMX_VMREAD_RDX_RAX, "%0")
-		      : "=a"(value) : "d"(field) : "cc");
-	return value;
-}
-
-static __always_inline u16 vmcs_read16(unsigned long field)
-{
-	vmcs_check16(field);
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_read16(field);
-	return __vmcs_readl(field);
-}
-
-static __always_inline u32 vmcs_read32(unsigned long field)
-{
-	vmcs_check32(field);
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_read32(field);
-	return __vmcs_readl(field);
-}
-
-static __always_inline u64 vmcs_read64(unsigned long field)
-{
-	vmcs_check64(field);
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_read64(field);
-#ifdef CONFIG_X86_64
-	return __vmcs_readl(field);
-#else
-	return __vmcs_readl(field) | ((u64)__vmcs_readl(field+1) << 32);
-#endif
-}
-
-static __always_inline unsigned long vmcs_readl(unsigned long field)
-{
-	vmcs_checkl(field);
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_read64(field);
-	return __vmcs_readl(field);
-}
-
-static noinline void vmwrite_error(unsigned long field, unsigned long value)
-{
-	printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
-	       field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
-	dump_stack();
-}
-
-static __always_inline void __vmcs_writel(unsigned long field, unsigned long value)
-{
-	bool error;
-
-	asm volatile (__ex(ASM_VMX_VMWRITE_RAX_RDX) CC_SET(na)
-		      : CC_OUT(na) (error) : "a"(value), "d"(field));
-	if (unlikely(error))
-		vmwrite_error(field, value);
-}
-
-static __always_inline void vmcs_write16(unsigned long field, u16 value)
-{
-	vmcs_check16(field);
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_write16(field, value);
-
-	__vmcs_writel(field, value);
-}
-
-static __always_inline void vmcs_write32(unsigned long field, u32 value)
-{
-	vmcs_check32(field);
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_write32(field, value);
-
-	__vmcs_writel(field, value);
-}
-
-static __always_inline void vmcs_write64(unsigned long field, u64 value)
-{
-	vmcs_check64(field);
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_write64(field, value);
-
-	__vmcs_writel(field, value);
-#ifndef CONFIG_X86_64
-	asm volatile ("");
-	__vmcs_writel(field+1, value >> 32);
-#endif
-}
-
-static __always_inline void vmcs_writel(unsigned long field, unsigned long value)
-{
-	vmcs_checkl(field);
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_write64(field, value);
-
-	__vmcs_writel(field, value);
-}
-
-static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask)
-{
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000,
-			 "vmcs_clear_bits does not support 64-bit fields");
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_write32(field, evmcs_read32(field) & ~mask);
-
-	__vmcs_writel(field, __vmcs_readl(field) & ~mask);
-}
-
-static __always_inline void vmcs_set_bits(unsigned long field, u32 mask)
-{
-        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000,
-			 "vmcs_set_bits does not support 64-bit fields");
-	if (static_branch_unlikely(&enable_evmcs))
-		return evmcs_write32(field, evmcs_read32(field) | mask);
-
-	__vmcs_writel(field, __vmcs_readl(field) | mask);
-}
-
-static inline void vm_entry_controls_reset_shadow(struct vcpu_vmx *vmx)
-{
-	vmx->vm_entry_controls_shadow = vmcs_read32(VM_ENTRY_CONTROLS);
-}
-
-static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val)
-{
-	vmcs_write32(VM_ENTRY_CONTROLS, val);
-	vmx->vm_entry_controls_shadow = val;
-}
-
-static inline void vm_entry_controls_set(struct vcpu_vmx *vmx, u32 val)
-{
-	if (vmx->vm_entry_controls_shadow != val)
-		vm_entry_controls_init(vmx, val);
-}
-
-static inline u32 vm_entry_controls_get(struct vcpu_vmx *vmx)
-{
-	return vmx->vm_entry_controls_shadow;
-}
-
-
-static inline void vm_entry_controls_setbit(struct vcpu_vmx *vmx, u32 val)
-{
-	vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) | val);
-}
-
-static inline void vm_entry_controls_clearbit(struct vcpu_vmx *vmx, u32 val)
-{
-	vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) & ~val);
-}
-
-static inline void vm_exit_controls_reset_shadow(struct vcpu_vmx *vmx)
-{
-	vmx->vm_exit_controls_shadow = vmcs_read32(VM_EXIT_CONTROLS);
-}
-
-static inline void vm_exit_controls_init(struct vcpu_vmx *vmx, u32 val)
-{
-	vmcs_write32(VM_EXIT_CONTROLS, val);
-	vmx->vm_exit_controls_shadow = val;
-}
-
-static inline void vm_exit_controls_set(struct vcpu_vmx *vmx, u32 val)
-{
-	if (vmx->vm_exit_controls_shadow != val)
-		vm_exit_controls_init(vmx, val);
-}
-
-static inline u32 vm_exit_controls_get(struct vcpu_vmx *vmx)
-{
-	return vmx->vm_exit_controls_shadow;
-}
-
-
-static inline void vm_exit_controls_setbit(struct vcpu_vmx *vmx, u32 val)
-{
-	vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) | val);
-}
-
-static inline void vm_exit_controls_clearbit(struct vcpu_vmx *vmx, u32 val)
-{
-	vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) & ~val);
-}
-
-static void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
-{
-	vmx->segment_cache.bitmask = 0;
-}
-
-static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg,
-				       unsigned field)
-{
-	bool ret;
-	u32 mask = 1 << (seg * SEG_FIELD_NR + field);
-
-	if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) {
-		vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS);
-		vmx->segment_cache.bitmask = 0;
-	}
-	ret = vmx->segment_cache.bitmask & mask;
-	vmx->segment_cache.bitmask |= mask;
-	return ret;
-}
-
-static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg)
-{
-	u16 *p = &vmx->segment_cache.seg[seg].selector;
-
-	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL))
-		*p = vmcs_read16(kvm_vmx_segment_fields[seg].selector);
-	return *p;
-}
-
-static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg)
-{
-	ulong *p = &vmx->segment_cache.seg[seg].base;
-
-	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE))
-		*p = vmcs_readl(kvm_vmx_segment_fields[seg].base);
-	return *p;
-}
-
-static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg)
-{
-	u32 *p = &vmx->segment_cache.seg[seg].limit;
-
-	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT))
-		*p = vmcs_read32(kvm_vmx_segment_fields[seg].limit);
-	return *p;
-}
-
-static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg)
-{
-	u32 *p = &vmx->segment_cache.seg[seg].ar;
-
-	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR))
-		*p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes);
-	return *p;
-}
-
-static void update_exception_bitmap(struct kvm_vcpu *vcpu)
-{
-	u32 eb;
-
-	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
-	     (1u << DB_VECTOR) | (1u << AC_VECTOR);
-	/*
-	 * Guest access to VMware backdoor ports could legitimately
-	 * trigger #GP because of TSS I/O permission bitmap.
-	 * We intercept those #GP and allow access to them anyway
-	 * as VMware does.
-	 */
-	if (enable_vmware_backdoor)
-		eb |= (1u << GP_VECTOR);
-	if ((vcpu->guest_debug &
-	     (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
-	    (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP))
-		eb |= 1u << BP_VECTOR;
-	if (to_vmx(vcpu)->rmode.vm86_active)
-		eb = ~0;
-	if (enable_ept)
-		eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
-
-	/* When we are running a nested L2 guest and L1 specified for it a
-	 * certain exception bitmap, we must trap the same exceptions and pass
-	 * them to L1. When running L2, we will only handle the exceptions
-	 * specified above if L1 did not want them.
-	 */
-	if (is_guest_mode(vcpu))
-		eb |= get_vmcs12(vcpu)->exception_bitmap;
-
-	vmcs_write32(EXCEPTION_BITMAP, eb);
-}
-
-/*
- * Check if MSR is intercepted for currently loaded MSR bitmap.
- */
-static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
-{
-	unsigned long *msr_bitmap;
-	int f = sizeof(unsigned long);
-
-	if (!cpu_has_vmx_msr_bitmap())
-		return true;
-
-	msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap;
-
-	if (msr <= 0x1fff) {
-		return !!test_bit(msr, msr_bitmap + 0x800 / f);
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
-	}
-
-	return true;
-}
-
-/*
- * Check if MSR is intercepted for L01 MSR bitmap.
- */
-static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
-{
-	unsigned long *msr_bitmap;
-	int f = sizeof(unsigned long);
-
-	if (!cpu_has_vmx_msr_bitmap())
-		return true;
-
-	msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
-
-	if (msr <= 0x1fff) {
-		return !!test_bit(msr, msr_bitmap + 0x800 / f);
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
-	}
-
-	return true;
-}
-
-static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
-		unsigned long entry, unsigned long exit)
-{
-	vm_entry_controls_clearbit(vmx, entry);
-	vm_exit_controls_clearbit(vmx, exit);
-}
-
-static int find_msr(struct vmx_msrs *m, unsigned int msr)
-{
-	unsigned int i;
-
-	for (i = 0; i < m->nr; ++i) {
-		if (m->val[i].index == msr)
-			return i;
-	}
-	return -ENOENT;
-}
-
-static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
-{
-	int i;
-	struct msr_autoload *m = &vmx->msr_autoload;
-
-	switch (msr) {
-	case MSR_EFER:
-		if (cpu_has_load_ia32_efer) {
-			clear_atomic_switch_msr_special(vmx,
-					VM_ENTRY_LOAD_IA32_EFER,
-					VM_EXIT_LOAD_IA32_EFER);
-			return;
-		}
-		break;
-	case MSR_CORE_PERF_GLOBAL_CTRL:
-		if (cpu_has_load_perf_global_ctrl) {
-			clear_atomic_switch_msr_special(vmx,
-					VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
-					VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
-			return;
-		}
-		break;
-	}
-	i = find_msr(&m->guest, msr);
-	if (i < 0)
-		goto skip_guest;
-	--m->guest.nr;
-	m->guest.val[i] = m->guest.val[m->guest.nr];
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
-
-skip_guest:
-	i = find_msr(&m->host, msr);
-	if (i < 0)
-		return;
-
-	--m->host.nr;
-	m->host.val[i] = m->host.val[m->host.nr];
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
-}
-
-static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
-		unsigned long entry, unsigned long exit,
-		unsigned long guest_val_vmcs, unsigned long host_val_vmcs,
-		u64 guest_val, u64 host_val)
-{
-	vmcs_write64(guest_val_vmcs, guest_val);
-	vmcs_write64(host_val_vmcs, host_val);
-	vm_entry_controls_setbit(vmx, entry);
-	vm_exit_controls_setbit(vmx, exit);
-}
-
-static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
-				  u64 guest_val, u64 host_val, bool entry_only)
-{
-	int i, j = 0;
-	struct msr_autoload *m = &vmx->msr_autoload;
-
-	switch (msr) {
-	case MSR_EFER:
-		if (cpu_has_load_ia32_efer) {
-			add_atomic_switch_msr_special(vmx,
-					VM_ENTRY_LOAD_IA32_EFER,
-					VM_EXIT_LOAD_IA32_EFER,
-					GUEST_IA32_EFER,
-					HOST_IA32_EFER,
-					guest_val, host_val);
-			return;
-		}
-		break;
-	case MSR_CORE_PERF_GLOBAL_CTRL:
-		if (cpu_has_load_perf_global_ctrl) {
-			add_atomic_switch_msr_special(vmx,
-					VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
-					VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL,
-					GUEST_IA32_PERF_GLOBAL_CTRL,
-					HOST_IA32_PERF_GLOBAL_CTRL,
-					guest_val, host_val);
-			return;
-		}
-		break;
-	case MSR_IA32_PEBS_ENABLE:
-		/* PEBS needs a quiescent period after being disabled (to write
-		 * a record).  Disabling PEBS through VMX MSR swapping doesn't
-		 * provide that period, so a CPU could write host's record into
-		 * guest's memory.
-		 */
-		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
-	}
-
-	i = find_msr(&m->guest, msr);
-	if (!entry_only)
-		j = find_msr(&m->host, msr);
-
-	if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
-		printk_once(KERN_WARNING "Not enough msr switch entries. "
-				"Can't add msr %x\n", msr);
-		return;
-	}
-	if (i < 0) {
-		i = m->guest.nr++;
-		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
-	}
-	m->guest.val[i].index = msr;
-	m->guest.val[i].value = guest_val;
-
-	if (entry_only)
-		return;
-
-	if (j < 0) {
-		j = m->host.nr++;
-		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
-	}
-	m->host.val[j].index = msr;
-	m->host.val[j].value = host_val;
-}
-
-static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
-{
-	u64 guest_efer = vmx->vcpu.arch.efer;
-	u64 ignore_bits = 0;
-
-	if (!enable_ept) {
-		/*
-		 * NX is needed to handle CR0.WP=1, CR4.SMEP=1.  Testing
-		 * host CPUID is more efficient than testing guest CPUID
-		 * or CR4.  Host SMEP is anyway a requirement for guest SMEP.
-		 */
-		if (boot_cpu_has(X86_FEATURE_SMEP))
-			guest_efer |= EFER_NX;
-		else if (!(guest_efer & EFER_NX))
-			ignore_bits |= EFER_NX;
-	}
-
-	/*
-	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
-	 */
-	ignore_bits |= EFER_SCE;
-#ifdef CONFIG_X86_64
-	ignore_bits |= EFER_LMA | EFER_LME;
-	/* SCE is meaningful only in long mode on Intel */
-	if (guest_efer & EFER_LMA)
-		ignore_bits &= ~(u64)EFER_SCE;
-#endif
-
-	clear_atomic_switch_msr(vmx, MSR_EFER);
-
-	/*
-	 * On EPT, we can't emulate NX, so we must switch EFER atomically.
-	 * On CPUs that support "load IA32_EFER", always switch EFER
-	 * atomically, since it's faster than switching it manually.
-	 */
-	if (cpu_has_load_ia32_efer ||
-	    (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
-		if (!(guest_efer & EFER_LMA))
-			guest_efer &= ~EFER_LME;
-		if (guest_efer != host_efer)
-			add_atomic_switch_msr(vmx, MSR_EFER,
-					      guest_efer, host_efer, false);
-		return false;
-	} else {
-		guest_efer &= ~ignore_bits;
-		guest_efer |= host_efer & ignore_bits;
-
-		vmx->guest_msrs[efer_offset].data = guest_efer;
-		vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
-
-		return true;
-	}
-}
-
-#ifdef CONFIG_X86_32
-/*
- * On 32-bit kernels, VM exits still load the FS and GS bases from the
- * VMCS rather than the segment table.  KVM uses this helper to figure
- * out the current bases to poke them into the VMCS before entry.
- */
-static unsigned long segment_base(u16 selector)
-{
-	struct desc_struct *table;
-	unsigned long v;
-
-	if (!(selector & ~SEGMENT_RPL_MASK))
-		return 0;
-
-	table = get_current_gdt_ro();
-
-	if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) {
-		u16 ldt_selector = kvm_read_ldt();
-
-		if (!(ldt_selector & ~SEGMENT_RPL_MASK))
-			return 0;
-
-		table = (struct desc_struct *)segment_base(ldt_selector);
-	}
-	v = get_desc_base(&table[selector >> 3]);
-	return v;
-}
-#endif
-
-static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct vmcs_host_state *host_state;
-#ifdef CONFIG_X86_64
-	int cpu = raw_smp_processor_id();
-#endif
-	unsigned long fs_base, gs_base;
-	u16 fs_sel, gs_sel;
-	int i;
-
-	vmx->req_immediate_exit = false;
-
-	/*
-	 * Note that guest MSRs to be saved/restored can also be changed
-	 * when guest state is loaded. This happens when guest transitions
-	 * to/from long-mode by setting MSR_EFER.LMA.
-	 */
-	if (!vmx->loaded_cpu_state || vmx->guest_msrs_dirty) {
-		vmx->guest_msrs_dirty = false;
-		for (i = 0; i < vmx->save_nmsrs; ++i)
-			kvm_set_shared_msr(vmx->guest_msrs[i].index,
-					   vmx->guest_msrs[i].data,
-					   vmx->guest_msrs[i].mask);
-
-	}
-
-	if (vmx->loaded_cpu_state)
-		return;
-
-	vmx->loaded_cpu_state = vmx->loaded_vmcs;
-	host_state = &vmx->loaded_cpu_state->host_state;
-
-	/*
-	 * Set host fs and gs selectors.  Unfortunately, 22.2.3 does not
-	 * allow segment selectors with cpl > 0 or ti == 1.
-	 */
-	host_state->ldt_sel = kvm_read_ldt();
-
-#ifdef CONFIG_X86_64
-	savesegment(ds, host_state->ds_sel);
-	savesegment(es, host_state->es_sel);
-
-	gs_base = cpu_kernelmode_gs_base(cpu);
-	if (likely(is_64bit_mm(current->mm))) {
-		save_fsgs_for_kvm();
-		fs_sel = current->thread.fsindex;
-		gs_sel = current->thread.gsindex;
-		fs_base = current->thread.fsbase;
-		vmx->msr_host_kernel_gs_base = current->thread.gsbase;
-	} else {
-		savesegment(fs, fs_sel);
-		savesegment(gs, gs_sel);
-		fs_base = read_msr(MSR_FS_BASE);
-		vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
-	}
-
-	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-#else
-	savesegment(fs, fs_sel);
-	savesegment(gs, gs_sel);
-	fs_base = segment_base(fs_sel);
-	gs_base = segment_base(gs_sel);
-#endif
-
-	if (unlikely(fs_sel != host_state->fs_sel)) {
-		if (!(fs_sel & 7))
-			vmcs_write16(HOST_FS_SELECTOR, fs_sel);
-		else
-			vmcs_write16(HOST_FS_SELECTOR, 0);
-		host_state->fs_sel = fs_sel;
-	}
-	if (unlikely(gs_sel != host_state->gs_sel)) {
-		if (!(gs_sel & 7))
-			vmcs_write16(HOST_GS_SELECTOR, gs_sel);
-		else
-			vmcs_write16(HOST_GS_SELECTOR, 0);
-		host_state->gs_sel = gs_sel;
-	}
-	if (unlikely(fs_base != host_state->fs_base)) {
-		vmcs_writel(HOST_FS_BASE, fs_base);
-		host_state->fs_base = fs_base;
-	}
-	if (unlikely(gs_base != host_state->gs_base)) {
-		vmcs_writel(HOST_GS_BASE, gs_base);
-		host_state->gs_base = gs_base;
-	}
-}
-
-static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
-{
-	struct vmcs_host_state *host_state;
-
-	if (!vmx->loaded_cpu_state)
-		return;
-
-	WARN_ON_ONCE(vmx->loaded_cpu_state != vmx->loaded_vmcs);
-	host_state = &vmx->loaded_cpu_state->host_state;
-
-	++vmx->vcpu.stat.host_state_reload;
-	vmx->loaded_cpu_state = NULL;
-
-#ifdef CONFIG_X86_64
-	rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-#endif
-	if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
-		kvm_load_ldt(host_state->ldt_sel);
-#ifdef CONFIG_X86_64
-		load_gs_index(host_state->gs_sel);
-#else
-		loadsegment(gs, host_state->gs_sel);
-#endif
-	}
-	if (host_state->fs_sel & 7)
-		loadsegment(fs, host_state->fs_sel);
-#ifdef CONFIG_X86_64
-	if (unlikely(host_state->ds_sel | host_state->es_sel)) {
-		loadsegment(ds, host_state->ds_sel);
-		loadsegment(es, host_state->es_sel);
-	}
-#endif
-	invalidate_tss_limit();
-#ifdef CONFIG_X86_64
-	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
-#endif
-	load_fixmap_gdt(raw_smp_processor_id());
-}
-
-#ifdef CONFIG_X86_64
-static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
-{
-	preempt_disable();
-	if (vmx->loaded_cpu_state)
-		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-	preempt_enable();
-	return vmx->msr_guest_kernel_gs_base;
-}
-
-static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
-{
-	preempt_disable();
-	if (vmx->loaded_cpu_state)
-		wrmsrl(MSR_KERNEL_GS_BASE, data);
-	preempt_enable();
-	vmx->msr_guest_kernel_gs_base = data;
-}
-#endif
-
-static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-
-	/*
-	 * In case of hot-plug or hot-unplug, we may have to undo
-	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
-	 * always keep PI.NDST up to date for simplicity: it makes the
-	 * code easier, and CPU migration is not a fast path.
-	 */
-	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
-		return;
-
-	/*
-	 * First handle the simple case where no cmpxchg is necessary; just
-	 * allow posting non-urgent interrupts.
-	 *
-	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
-	 * PI.NDST: pi_post_block will do it for us and the wakeup_handler
-	 * expects the VCPU to be on the blocked_vcpu_list that matches
-	 * PI.NDST.
-	 */
-	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
-	    vcpu->cpu == cpu) {
-		pi_clear_sn(pi_desc);
-		return;
-	}
-
-	/* The full case.  */
-	do {
-		old.control = new.control = pi_desc->control;
-
-		dest = cpu_physical_id(cpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		new.sn = 0;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
-}
-
-static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
-{
-	vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
-	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
-}
-
-/*
- * Switches to specified vcpu, until a matching vcpu_put(), but assumes
- * vcpu mutex is already taken.
- */
-static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
-
-	if (!already_loaded) {
-		loaded_vmcs_clear(vmx->loaded_vmcs);
-		local_irq_disable();
-		crash_disable_local_vmclear(cpu);
-
-		/*
-		 * Read loaded_vmcs->cpu should be before fetching
-		 * loaded_vmcs->loaded_vmcss_on_cpu_link.
-		 * See the comments in __loaded_vmcs_clear().
-		 */
-		smp_rmb();
-
-		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
-			 &per_cpu(loaded_vmcss_on_cpu, cpu));
-		crash_enable_local_vmclear(cpu);
-		local_irq_enable();
-	}
-
-	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
-		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
-		vmcs_load(vmx->loaded_vmcs->vmcs);
-		indirect_branch_prediction_barrier();
-	}
-
-	if (!already_loaded) {
-		void *gdt = get_current_gdt_ro();
-		unsigned long sysenter_esp;
-
-		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-
-		/*
-		 * Linux uses per-cpu TSS and GDT, so set these when switching
-		 * processors.  See 22.2.4.
-		 */
-		vmcs_writel(HOST_TR_BASE,
-			    (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
-		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */
-
-		/*
-		 * VM exits change the host TR limit to 0x67 after a VM
-		 * exit.  This is okay, since 0x67 covers everything except
-		 * the IO bitmap and have have code to handle the IO bitmap
-		 * being lost after a VM exit.
-		 */
-		BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67);
-
-		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
-		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
-
-		vmx->loaded_vmcs->cpu = cpu;
-	}
-
-	/* Setup TSC multiplier */
-	if (kvm_has_tsc_control &&
-	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio)
-		decache_tsc_multiplier(vmx);
-
-	vmx_vcpu_pi_load(vcpu, cpu);
-	vmx->host_pkru = read_pkru();
-	vmx->host_debugctlmsr = get_debugctlmsr();
-}
-
-static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
-		return;
-
-	/* Set SN when the vCPU is preempted */
-	if (vcpu->preempted)
-		pi_set_sn(pi_desc);
-}
-
-static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
-{
-	vmx_vcpu_pi_put(vcpu);
-
-	vmx_prepare_switch_to_host(to_vmx(vcpu));
-}
-
-static bool emulation_required(struct kvm_vcpu *vcpu)
-{
-	return emulate_invalid_guest_state && !guest_state_valid(vcpu);
-}
-
-static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
-
-/*
- * Return the cr0 value that a nested guest would read. This is a combination
- * of the real cr0 used to run the guest (guest_cr0), and the bits shadowed by
- * its hypervisor (cr0_read_shadow).
- */
-static inline unsigned long nested_read_cr0(struct vmcs12 *fields)
-{
-	return (fields->guest_cr0 & ~fields->cr0_guest_host_mask) |
-		(fields->cr0_read_shadow & fields->cr0_guest_host_mask);
-}
-static inline unsigned long nested_read_cr4(struct vmcs12 *fields)
-{
-	return (fields->guest_cr4 & ~fields->cr4_guest_host_mask) |
-		(fields->cr4_read_shadow & fields->cr4_guest_host_mask);
-}
-
-static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
-{
-	unsigned long rflags, save_rflags;
-
-	if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) {
-		__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
-		rflags = vmcs_readl(GUEST_RFLAGS);
-		if (to_vmx(vcpu)->rmode.vm86_active) {
-			rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
-			save_rflags = to_vmx(vcpu)->rmode.save_rflags;
-			rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
-		}
-		to_vmx(vcpu)->rflags = rflags;
-	}
-	return to_vmx(vcpu)->rflags;
-}
-
-static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
-{
-	unsigned long old_rflags = vmx_get_rflags(vcpu);
-
-	__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
-	to_vmx(vcpu)->rflags = rflags;
-	if (to_vmx(vcpu)->rmode.vm86_active) {
-		to_vmx(vcpu)->rmode.save_rflags = rflags;
-		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
-	}
-	vmcs_writel(GUEST_RFLAGS, rflags);
-
-	if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM)
-		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
-}
-
-static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
-{
-	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
-	int ret = 0;
-
-	if (interruptibility & GUEST_INTR_STATE_STI)
-		ret |= KVM_X86_SHADOW_INT_STI;
-	if (interruptibility & GUEST_INTR_STATE_MOV_SS)
-		ret |= KVM_X86_SHADOW_INT_MOV_SS;
-
-	return ret;
-}
-
-static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
-{
-	u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
-	u32 interruptibility = interruptibility_old;
-
-	interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
-
-	if (mask & KVM_X86_SHADOW_INT_MOV_SS)
-		interruptibility |= GUEST_INTR_STATE_MOV_SS;
-	else if (mask & KVM_X86_SHADOW_INT_STI)
-		interruptibility |= GUEST_INTR_STATE_STI;
-
-	if ((interruptibility != interruptibility_old))
-		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility);
-}
-
-static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
-{
-	unsigned long rip;
-
-	rip = kvm_rip_read(vcpu);
-	rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
-	kvm_rip_write(vcpu, rip);
-
-	/* skipping an emulated instruction also counts */
-	vmx_set_interrupt_shadow(vcpu, 0);
-}
-
-static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
-					       unsigned long exit_qual)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	unsigned int nr = vcpu->arch.exception.nr;
-	u32 intr_info = nr | INTR_INFO_VALID_MASK;
-
-	if (vcpu->arch.exception.has_error_code) {
-		vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
-		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
-	}
-
-	if (kvm_exception_is_soft(nr))
-		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
-	else
-		intr_info |= INTR_TYPE_HARD_EXCEPTION;
-
-	if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) &&
-	    vmx_get_nmi_mask(vcpu))
-		intr_info |= INTR_INFO_UNBLOCK_NMI;
-
-	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
-}
-
-/*
- * KVM wants to inject page-faults which it got to the guest. This function
- * checks whether in a nested guest, we need to inject them to L1 or L2.
- */
-static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	unsigned int nr = vcpu->arch.exception.nr;
-
-	if (nr == PF_VECTOR) {
-		if (vcpu->arch.exception.nested_apf) {
-			*exit_qual = vcpu->arch.apf.nested_apf_token;
-			return 1;
-		}
-		/*
-		 * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
-		 * The fix is to add the ancillary datum (CR2 or DR6) to structs
-		 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
-		 * can be written only when inject_pending_event runs.  This should be
-		 * conditional on a new capability---if the capability is disabled,
-		 * kvm_multiple_exception would write the ancillary information to
-		 * CR2 or DR6, for backwards ABI-compatibility.
-		 */
-		if (nested_vmx_is_page_fault_vmexit(vmcs12,
-						    vcpu->arch.exception.error_code)) {
-			*exit_qual = vcpu->arch.cr2;
-			return 1;
-		}
-	} else {
-		if (vmcs12->exception_bitmap & (1u << nr)) {
-			if (nr == DB_VECTOR) {
-				*exit_qual = vcpu->arch.dr6;
-				*exit_qual &= ~(DR6_FIXED_1 | DR6_BT);
-				*exit_qual ^= DR6_RTM;
-			} else {
-				*exit_qual = 0;
-			}
-			return 1;
-		}
-	}
-
-	return 0;
-}
-
-static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * Ensure that we clear the HLT state in the VMCS.  We don't need to
-	 * explicitly skip the instruction because if the HLT state is set,
-	 * then the instruction is already executing and RIP has already been
-	 * advanced.
-	 */
-	if (kvm_hlt_in_guest(vcpu->kvm) &&
-			vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT)
-		vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
-}
-
-static void vmx_queue_exception(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned nr = vcpu->arch.exception.nr;
-	bool has_error_code = vcpu->arch.exception.has_error_code;
-	u32 error_code = vcpu->arch.exception.error_code;
-	u32 intr_info = nr | INTR_INFO_VALID_MASK;
-
-	if (has_error_code) {
-		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
-		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
-	}
-
-	if (vmx->rmode.vm86_active) {
-		int inc_eip = 0;
-		if (kvm_exception_is_soft(nr))
-			inc_eip = vcpu->arch.event_exit_inst_len;
-		if (kvm_inject_realmode_interrupt(vcpu, nr, inc_eip) != EMULATE_DONE)
-			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		return;
-	}
-
-	WARN_ON_ONCE(vmx->emulation_required);
-
-	if (kvm_exception_is_soft(nr)) {
-		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
-			     vmx->vcpu.arch.event_exit_inst_len);
-		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
-	} else
-		intr_info |= INTR_TYPE_HARD_EXCEPTION;
-
-	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
-
-	vmx_clear_hlt(vcpu);
-}
-
-static bool vmx_rdtscp_supported(void)
-{
-	return cpu_has_vmx_rdtscp();
-}
-
-static bool vmx_invpcid_supported(void)
-{
-	return cpu_has_vmx_invpcid();
-}
-
-/*
- * Swap MSR entry in host/guest MSR entry array.
- */
-static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
-{
-	struct shared_msr_entry tmp;
-
-	tmp = vmx->guest_msrs[to];
-	vmx->guest_msrs[to] = vmx->guest_msrs[from];
-	vmx->guest_msrs[from] = tmp;
-}
-
-/*
- * Set up the vmcs to automatically save and restore system
- * msrs.  Don't touch the 64-bit msrs if the guest is in legacy
- * mode, as fiddling with msrs is very expensive.
- */
-static void setup_msrs(struct vcpu_vmx *vmx)
-{
-	int save_nmsrs, index;
-
-	save_nmsrs = 0;
-#ifdef CONFIG_X86_64
-	if (is_long_mode(&vmx->vcpu)) {
-		index = __find_msr_index(vmx, MSR_SYSCALL_MASK);
-		if (index >= 0)
-			move_msr_up(vmx, index, save_nmsrs++);
-		index = __find_msr_index(vmx, MSR_LSTAR);
-		if (index >= 0)
-			move_msr_up(vmx, index, save_nmsrs++);
-		index = __find_msr_index(vmx, MSR_CSTAR);
-		if (index >= 0)
-			move_msr_up(vmx, index, save_nmsrs++);
-		index = __find_msr_index(vmx, MSR_TSC_AUX);
-		if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
-			move_msr_up(vmx, index, save_nmsrs++);
-		/*
-		 * MSR_STAR is only needed on long mode guests, and only
-		 * if efer.sce is enabled.
-		 */
-		index = __find_msr_index(vmx, MSR_STAR);
-		if ((index >= 0) && (vmx->vcpu.arch.efer & EFER_SCE))
-			move_msr_up(vmx, index, save_nmsrs++);
-	}
-#endif
-	index = __find_msr_index(vmx, MSR_EFER);
-	if (index >= 0 && update_transition_efer(vmx, index))
-		move_msr_up(vmx, index, save_nmsrs++);
-
-	vmx->save_nmsrs = save_nmsrs;
-	vmx->guest_msrs_dirty = true;
-
-	if (cpu_has_vmx_msr_bitmap())
-		vmx_update_msr_bitmap(&vmx->vcpu);
-}
-
-static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-
-	if (is_guest_mode(vcpu) &&
-	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
-		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
-
-	return vcpu->arch.tsc_offset;
-}
-
-static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
-{
-	u64 active_offset = offset;
-	if (is_guest_mode(vcpu)) {
-		/*
-		 * We're here if L1 chose not to trap WRMSR to TSC. According
-		 * to the spec, this should set L1's TSC; The offset that L1
-		 * set for L2 remains unchanged, and still needs to be added
-		 * to the newly set TSC to get L2's TSC.
-		 */
-		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-		if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING))
-			active_offset += vmcs12->tsc_offset;
-	} else {
-		trace_kvm_write_tsc_offset(vcpu->vcpu_id,
-					   vmcs_read64(TSC_OFFSET), offset);
-	}
-
-	vmcs_write64(TSC_OFFSET, active_offset);
-	return active_offset;
-}
-
-/*
- * nested_vmx_allowed() checks whether a guest should be allowed to use VMX
- * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for
- * all guests if the "nested" module option is off, and can also be disabled
- * for a single guest by disabling its VMX cpuid bit.
- */
-static inline bool nested_vmx_allowed(struct kvm_vcpu *vcpu)
-{
-	return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX);
-}
-
-/*
- * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be
- * returned for the various VMX controls MSRs when nested VMX is enabled.
- * The same values should also be used to verify that vmcs12 control fields are
- * valid during nested entry from L1 to L2.
- * Each of these control msrs has a low and high 32-bit half: A low bit is on
- * if the corresponding bit in the (32-bit) control field *must* be on, and a
- * bit in the high half is on if the corresponding bit in the control field
- * may be on. See also vmx_control_verify().
- */
-static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
-{
-	if (!nested) {
-		memset(msrs, 0, sizeof(*msrs));
-		return;
-	}
-
-	/*
-	 * Note that as a general rule, the high half of the MSRs (bits in
-	 * the control fields which may be 1) should be initialized by the
-	 * intersection of the underlying hardware's MSR (i.e., features which
-	 * can be supported) and the list of features we want to expose -
-	 * because they are known to be properly supported in our code.
-	 * Also, usually, the low half of the MSRs (bits which must be 1) can
-	 * be set to 0, meaning that L1 may turn off any of these bits. The
-	 * reason is that if one of these bits is necessary, it will appear
-	 * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
-	 * fields of vmcs01 and vmcs02, will turn these bits off - and
-	 * nested_vmx_exit_reflected() will not pass related exits to L1.
-	 * These rules have exceptions below.
-	 */
-
-	/* pin-based controls */
-	rdmsr(MSR_IA32_VMX_PINBASED_CTLS,
-		msrs->pinbased_ctls_low,
-		msrs->pinbased_ctls_high);
-	msrs->pinbased_ctls_low |=
-		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
-	msrs->pinbased_ctls_high &=
-		PIN_BASED_EXT_INTR_MASK |
-		PIN_BASED_NMI_EXITING |
-		PIN_BASED_VIRTUAL_NMIS |
-		(apicv ? PIN_BASED_POSTED_INTR : 0);
-	msrs->pinbased_ctls_high |=
-		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
-		PIN_BASED_VMX_PREEMPTION_TIMER;
-
-	/* exit controls */
-	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
-		msrs->exit_ctls_low,
-		msrs->exit_ctls_high);
-	msrs->exit_ctls_low =
-		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
-
-	msrs->exit_ctls_high &=
-#ifdef CONFIG_X86_64
-		VM_EXIT_HOST_ADDR_SPACE_SIZE |
-#endif
-		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
-	msrs->exit_ctls_high |=
-		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
-		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
-		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
-
-	/* We support free control of debug control saving. */
-	msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
-
-	/* entry controls */
-	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
-		msrs->entry_ctls_low,
-		msrs->entry_ctls_high);
-	msrs->entry_ctls_low =
-		VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
-	msrs->entry_ctls_high &=
-#ifdef CONFIG_X86_64
-		VM_ENTRY_IA32E_MODE |
-#endif
-		VM_ENTRY_LOAD_IA32_PAT;
-	msrs->entry_ctls_high |=
-		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
-
-	/* We support free control of debug control loading. */
-	msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
-
-	/* cpu-based controls */
-	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
-		msrs->procbased_ctls_low,
-		msrs->procbased_ctls_high);
-	msrs->procbased_ctls_low =
-		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
-	msrs->procbased_ctls_high &=
-		CPU_BASED_VIRTUAL_INTR_PENDING |
-		CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING |
-		CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING |
-		CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING |
-		CPU_BASED_CR3_STORE_EXITING |
-#ifdef CONFIG_X86_64
-		CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING |
-#endif
-		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
-		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG |
-		CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING |
-		CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING |
-		CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
-	/*
-	 * We can allow some features even when not supported by the
-	 * hardware. For example, L1 can specify an MSR bitmap - and we
-	 * can use it to avoid exits to L1 - even when L0 runs L2
-	 * without MSR bitmaps.
-	 */
-	msrs->procbased_ctls_high |=
-		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
-		CPU_BASED_USE_MSR_BITMAPS;
-
-	/* We support free control of CR3 access interception. */
-	msrs->procbased_ctls_low &=
-		~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING);
-
-	/*
-	 * secondary cpu-based controls.  Do not include those that
-	 * depend on CPUID bits, they are added later by vmx_cpuid_update.
-	 */
-	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
-		msrs->secondary_ctls_low,
-		msrs->secondary_ctls_high);
-	msrs->secondary_ctls_low = 0;
-	msrs->secondary_ctls_high &=
-		SECONDARY_EXEC_DESC |
-		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
-		SECONDARY_EXEC_APIC_REGISTER_VIRT |
-		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
-		SECONDARY_EXEC_WBINVD_EXITING;
-
-	/*
-	 * We can emulate "VMCS shadowing," even if the hardware
-	 * doesn't support it.
-	 */
-	msrs->secondary_ctls_high |=
-		SECONDARY_EXEC_SHADOW_VMCS;
-
-	if (enable_ept) {
-		/* nested EPT: emulate EPT also to L1 */
-		msrs->secondary_ctls_high |=
-			SECONDARY_EXEC_ENABLE_EPT;
-		msrs->ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
-			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
-		if (cpu_has_vmx_ept_execute_only())
-			msrs->ept_caps |=
-				VMX_EPT_EXECUTE_ONLY_BIT;
-		msrs->ept_caps &= vmx_capability.ept;
-		msrs->ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
-			VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT |
-			VMX_EPT_1GB_PAGE_BIT;
-		if (enable_ept_ad_bits) {
-			msrs->secondary_ctls_high |=
-				SECONDARY_EXEC_ENABLE_PML;
-			msrs->ept_caps |= VMX_EPT_AD_BIT;
-		}
-	}
-
-	if (cpu_has_vmx_vmfunc()) {
-		msrs->secondary_ctls_high |=
-			SECONDARY_EXEC_ENABLE_VMFUNC;
-		/*
-		 * Advertise EPTP switching unconditionally
-		 * since we emulate it
-		 */
-		if (enable_ept)
-			msrs->vmfunc_controls =
-				VMX_VMFUNC_EPTP_SWITCHING;
-	}
-
-	/*
-	 * Old versions of KVM use the single-context version without
-	 * checking for support, so declare that it is supported even
-	 * though it is treated as global context.  The alternative is
-	 * not failing the single-context invvpid, and it is worse.
-	 */
-	if (enable_vpid) {
-		msrs->secondary_ctls_high |=
-			SECONDARY_EXEC_ENABLE_VPID;
-		msrs->vpid_caps = VMX_VPID_INVVPID_BIT |
-			VMX_VPID_EXTENT_SUPPORTED_MASK;
-	}
-
-	if (enable_unrestricted_guest)
-		msrs->secondary_ctls_high |=
-			SECONDARY_EXEC_UNRESTRICTED_GUEST;
-
-	if (flexpriority_enabled)
-		msrs->secondary_ctls_high |=
-			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-
-	/* miscellaneous data */
-	rdmsr(MSR_IA32_VMX_MISC,
-		msrs->misc_low,
-		msrs->misc_high);
-	msrs->misc_low &= VMX_MISC_SAVE_EFER_LMA;
-	msrs->misc_low |=
-		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
-		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
-		VMX_MISC_ACTIVITY_HLT;
-	msrs->misc_high = 0;
-
-	/*
-	 * This MSR reports some information about VMX support. We
-	 * should return information about the VMX we emulate for the
-	 * guest, and the VMCS structure we give it - not about the
-	 * VMX support of the underlying hardware.
-	 */
-	msrs->basic =
-		VMCS12_REVISION |
-		VMX_BASIC_TRUE_CTLS |
-		((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
-		(VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
-
-	if (cpu_has_vmx_basic_inout())
-		msrs->basic |= VMX_BASIC_INOUT;
-
-	/*
-	 * These MSRs specify bits which the guest must keep fixed on
-	 * while L1 is in VMXON mode (in L1's root mode, or running an L2).
-	 * We picked the standard core2 setting.
-	 */
-#define VMXON_CR0_ALWAYSON     (X86_CR0_PE | X86_CR0_PG | X86_CR0_NE)
-#define VMXON_CR4_ALWAYSON     X86_CR4_VMXE
-	msrs->cr0_fixed0 = VMXON_CR0_ALWAYSON;
-	msrs->cr4_fixed0 = VMXON_CR4_ALWAYSON;
-
-	/* These MSRs specify bits which the guest must keep fixed off. */
-	rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1);
-	rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1);
-
-	/* highest index: VMX_PREEMPTION_TIMER_VALUE */
-	msrs->vmcs_enum = VMCS12_MAX_FIELD_INDEX << 1;
-}
-
-/*
- * if fixed0[i] == 1: val[i] must be 1
- * if fixed1[i] == 0: val[i] must be 0
- */
-static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1)
-{
-	return ((val & fixed1) | fixed0) == val;
-}
-
-static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
-{
-	return fixed_bits_valid(control, low, high);
-}
-
-static inline u64 vmx_control_msr(u32 low, u32 high)
-{
-	return low | ((u64)high << 32);
-}
-
-static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
-{
-	superset &= mask;
-	subset &= mask;
-
-	return (superset | subset) == superset;
-}
-
-static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
-{
-	const u64 feature_and_reserved =
-		/* feature (except bit 48; see below) */
-		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
-		/* reserved */
-		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
-	u64 vmx_basic = vmx->nested.msrs.basic;
-
-	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
-		return -EINVAL;
-
-	/*
-	 * KVM does not emulate a version of VMX that constrains physical
-	 * addresses of VMX structures (e.g. VMCS) to 32-bits.
-	 */
-	if (data & BIT_ULL(48))
-		return -EINVAL;
-
-	if (vmx_basic_vmcs_revision_id(vmx_basic) !=
-	    vmx_basic_vmcs_revision_id(data))
-		return -EINVAL;
-
-	if (vmx_basic_vmcs_size(vmx_basic) > vmx_basic_vmcs_size(data))
-		return -EINVAL;
-
-	vmx->nested.msrs.basic = data;
-	return 0;
-}
-
-static int
-vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
-{
-	u64 supported;
-	u32 *lowp, *highp;
-
-	switch (msr_index) {
-	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
-		lowp = &vmx->nested.msrs.pinbased_ctls_low;
-		highp = &vmx->nested.msrs.pinbased_ctls_high;
-		break;
-	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
-		lowp = &vmx->nested.msrs.procbased_ctls_low;
-		highp = &vmx->nested.msrs.procbased_ctls_high;
-		break;
-	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
-		lowp = &vmx->nested.msrs.exit_ctls_low;
-		highp = &vmx->nested.msrs.exit_ctls_high;
-		break;
-	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
-		lowp = &vmx->nested.msrs.entry_ctls_low;
-		highp = &vmx->nested.msrs.entry_ctls_high;
-		break;
-	case MSR_IA32_VMX_PROCBASED_CTLS2:
-		lowp = &vmx->nested.msrs.secondary_ctls_low;
-		highp = &vmx->nested.msrs.secondary_ctls_high;
-		break;
-	default:
-		BUG();
-	}
-
-	supported = vmx_control_msr(*lowp, *highp);
-
-	/* Check must-be-1 bits are still 1. */
-	if (!is_bitwise_subset(data, supported, GENMASK_ULL(31, 0)))
-		return -EINVAL;
-
-	/* Check must-be-0 bits are still 0. */
-	if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32)))
-		return -EINVAL;
-
-	*lowp = data;
-	*highp = data >> 32;
-	return 0;
-}
-
-static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
-{
-	const u64 feature_and_reserved_bits =
-		/* feature */
-		BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) |
-		BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
-		/* reserved */
-		GENMASK_ULL(13, 9) | BIT_ULL(31);
-	u64 vmx_misc;
-
-	vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
-				   vmx->nested.msrs.misc_high);
-
-	if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
-		return -EINVAL;
-
-	if ((vmx->nested.msrs.pinbased_ctls_high &
-	     PIN_BASED_VMX_PREEMPTION_TIMER) &&
-	    vmx_misc_preemption_timer_rate(data) !=
-	    vmx_misc_preemption_timer_rate(vmx_misc))
-		return -EINVAL;
-
-	if (vmx_misc_cr3_count(data) > vmx_misc_cr3_count(vmx_misc))
-		return -EINVAL;
-
-	if (vmx_misc_max_msr(data) > vmx_misc_max_msr(vmx_misc))
-		return -EINVAL;
-
-	if (vmx_misc_mseg_revid(data) != vmx_misc_mseg_revid(vmx_misc))
-		return -EINVAL;
-
-	vmx->nested.msrs.misc_low = data;
-	vmx->nested.msrs.misc_high = data >> 32;
-
-	/*
-	 * If L1 has read-only VM-exit information fields, use the
-	 * less permissive vmx_vmwrite_bitmap to specify write
-	 * permissions for the shadow VMCS.
-	 */
-	if (enable_shadow_vmcs && !nested_cpu_has_vmwrite_any_field(&vmx->vcpu))
-		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
-
-	return 0;
-}
-
-static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data)
-{
-	u64 vmx_ept_vpid_cap;
-
-	vmx_ept_vpid_cap = vmx_control_msr(vmx->nested.msrs.ept_caps,
-					   vmx->nested.msrs.vpid_caps);
-
-	/* Every bit is either reserved or a feature bit. */
-	if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL))
-		return -EINVAL;
-
-	vmx->nested.msrs.ept_caps = data;
-	vmx->nested.msrs.vpid_caps = data >> 32;
-	return 0;
-}
-
-static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
-{
-	u64 *msr;
-
-	switch (msr_index) {
-	case MSR_IA32_VMX_CR0_FIXED0:
-		msr = &vmx->nested.msrs.cr0_fixed0;
-		break;
-	case MSR_IA32_VMX_CR4_FIXED0:
-		msr = &vmx->nested.msrs.cr4_fixed0;
-		break;
-	default:
-		BUG();
-	}
-
-	/*
-	 * 1 bits (which indicates bits which "must-be-1" during VMX operation)
-	 * must be 1 in the restored value.
-	 */
-	if (!is_bitwise_subset(data, *msr, -1ULL))
-		return -EINVAL;
-
-	*msr = data;
-	return 0;
-}
-
-/*
- * Called when userspace is restoring VMX MSRs.
- *
- * Returns 0 on success, non-0 otherwise.
- */
-static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	/*
-	 * Don't allow changes to the VMX capability MSRs while the vCPU
-	 * is in VMX operation.
-	 */
-	if (vmx->nested.vmxon)
-		return -EBUSY;
-
-	switch (msr_index) {
-	case MSR_IA32_VMX_BASIC:
-		return vmx_restore_vmx_basic(vmx, data);
-	case MSR_IA32_VMX_PINBASED_CTLS:
-	case MSR_IA32_VMX_PROCBASED_CTLS:
-	case MSR_IA32_VMX_EXIT_CTLS:
-	case MSR_IA32_VMX_ENTRY_CTLS:
-		/*
-		 * The "non-true" VMX capability MSRs are generated from the
-		 * "true" MSRs, so we do not support restoring them directly.
-		 *
-		 * If userspace wants to emulate VMX_BASIC[55]=0, userspace
-		 * should restore the "true" MSRs with the must-be-1 bits
-		 * set according to the SDM Vol 3. A.2 "RESERVED CONTROLS AND
-		 * DEFAULT SETTINGS".
-		 */
-		return -EINVAL;
-	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
-	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
-	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
-	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
-	case MSR_IA32_VMX_PROCBASED_CTLS2:
-		return vmx_restore_control_msr(vmx, msr_index, data);
-	case MSR_IA32_VMX_MISC:
-		return vmx_restore_vmx_misc(vmx, data);
-	case MSR_IA32_VMX_CR0_FIXED0:
-	case MSR_IA32_VMX_CR4_FIXED0:
-		return vmx_restore_fixed0_msr(vmx, msr_index, data);
-	case MSR_IA32_VMX_CR0_FIXED1:
-	case MSR_IA32_VMX_CR4_FIXED1:
-		/*
-		 * These MSRs are generated based on the vCPU's CPUID, so we
-		 * do not support restoring them directly.
-		 */
-		return -EINVAL;
-	case MSR_IA32_VMX_EPT_VPID_CAP:
-		return vmx_restore_vmx_ept_vpid_cap(vmx, data);
-	case MSR_IA32_VMX_VMCS_ENUM:
-		vmx->nested.msrs.vmcs_enum = data;
-		return 0;
-	default:
-		/*
-		 * The rest of the VMX capability MSRs do not support restore.
-		 */
-		return -EINVAL;
-	}
-}
-
-/* Returns 0 on success, non-0 otherwise. */
-static int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata)
-{
-	switch (msr_index) {
-	case MSR_IA32_VMX_BASIC:
-		*pdata = msrs->basic;
-		break;
-	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
-	case MSR_IA32_VMX_PINBASED_CTLS:
-		*pdata = vmx_control_msr(
-			msrs->pinbased_ctls_low,
-			msrs->pinbased_ctls_high);
-		if (msr_index == MSR_IA32_VMX_PINBASED_CTLS)
-			*pdata |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
-		break;
-	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
-	case MSR_IA32_VMX_PROCBASED_CTLS:
-		*pdata = vmx_control_msr(
-			msrs->procbased_ctls_low,
-			msrs->procbased_ctls_high);
-		if (msr_index == MSR_IA32_VMX_PROCBASED_CTLS)
-			*pdata |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
-		break;
-	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
-	case MSR_IA32_VMX_EXIT_CTLS:
-		*pdata = vmx_control_msr(
-			msrs->exit_ctls_low,
-			msrs->exit_ctls_high);
-		if (msr_index == MSR_IA32_VMX_EXIT_CTLS)
-			*pdata |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
-		break;
-	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
-	case MSR_IA32_VMX_ENTRY_CTLS:
-		*pdata = vmx_control_msr(
-			msrs->entry_ctls_low,
-			msrs->entry_ctls_high);
-		if (msr_index == MSR_IA32_VMX_ENTRY_CTLS)
-			*pdata |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
-		break;
-	case MSR_IA32_VMX_MISC:
-		*pdata = vmx_control_msr(
-			msrs->misc_low,
-			msrs->misc_high);
-		break;
-	case MSR_IA32_VMX_CR0_FIXED0:
-		*pdata = msrs->cr0_fixed0;
-		break;
-	case MSR_IA32_VMX_CR0_FIXED1:
-		*pdata = msrs->cr0_fixed1;
-		break;
-	case MSR_IA32_VMX_CR4_FIXED0:
-		*pdata = msrs->cr4_fixed0;
-		break;
-	case MSR_IA32_VMX_CR4_FIXED1:
-		*pdata = msrs->cr4_fixed1;
-		break;
-	case MSR_IA32_VMX_VMCS_ENUM:
-		*pdata = msrs->vmcs_enum;
-		break;
-	case MSR_IA32_VMX_PROCBASED_CTLS2:
-		*pdata = vmx_control_msr(
-			msrs->secondary_ctls_low,
-			msrs->secondary_ctls_high);
-		break;
-	case MSR_IA32_VMX_EPT_VPID_CAP:
-		*pdata = msrs->ept_caps |
-			((u64)msrs->vpid_caps << 32);
-		break;
-	case MSR_IA32_VMX_VMFUNC:
-		*pdata = msrs->vmfunc_controls;
-		break;
-	default:
-		return 1;
-	}
-
-	return 0;
-}
-
-static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu,
-						 uint64_t val)
-{
-	uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits;
-
-	return !(val & ~valid_bits);
-}
-
-static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
-{
-	switch (msr->index) {
-	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
-		if (!nested)
-			return 1;
-		return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data);
-	default:
-		return 1;
-	}
-
-	return 0;
-}
-
-/*
- * Reads an msr value (of 'msr_index') into 'pdata'.
- * Returns 0 on success, non-0 otherwise.
- * Assumes vcpu_load() was already called.
- */
-static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct shared_msr_entry *msr;
-
-	switch (msr_info->index) {
-#ifdef CONFIG_X86_64
-	case MSR_FS_BASE:
-		msr_info->data = vmcs_readl(GUEST_FS_BASE);
-		break;
-	case MSR_GS_BASE:
-		msr_info->data = vmcs_readl(GUEST_GS_BASE);
-		break;
-	case MSR_KERNEL_GS_BASE:
-		msr_info->data = vmx_read_guest_kernel_gs_base(vmx);
-		break;
-#endif
-	case MSR_EFER:
-		return kvm_get_msr_common(vcpu, msr_info);
-	case MSR_IA32_SPEC_CTRL:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
-			return 1;
-
-		msr_info->data = to_vmx(vcpu)->spec_ctrl;
-		break;
-	case MSR_IA32_ARCH_CAPABILITIES:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
-			return 1;
-		msr_info->data = to_vmx(vcpu)->arch_capabilities;
-		break;
-	case MSR_IA32_SYSENTER_CS:
-		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
-		break;
-	case MSR_IA32_SYSENTER_EIP:
-		msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP);
-		break;
-	case MSR_IA32_SYSENTER_ESP:
-		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
-		break;
-	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported() ||
-		    (!msr_info->host_initiated &&
-		     !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
-			return 1;
-		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
-		break;
-	case MSR_IA32_MCG_EXT_CTL:
-		if (!msr_info->host_initiated &&
-		    !(vmx->msr_ia32_feature_control &
-		      FEATURE_CONTROL_LMCE))
-			return 1;
-		msr_info->data = vcpu->arch.mcg_ext_ctl;
-		break;
-	case MSR_IA32_FEATURE_CONTROL:
-		msr_info->data = vmx->msr_ia32_feature_control;
-		break;
-	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
-		if (!nested_vmx_allowed(vcpu))
-			return 1;
-		return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
-				       &msr_info->data);
-	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported())
-			return 1;
-		msr_info->data = vcpu->arch.ia32_xss;
-		break;
-	case MSR_TSC_AUX:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
-			return 1;
-		/* Otherwise falls through */
-	default:
-		msr = find_msr_entry(vmx, msr_info->index);
-		if (msr) {
-			msr_info->data = msr->data;
-			break;
-		}
-		return kvm_get_msr_common(vcpu, msr_info);
-	}
-
-	return 0;
-}
-
-static void vmx_leave_nested(struct kvm_vcpu *vcpu);
-
-/*
- * Writes msr value into into the appropriate "register".
- * Returns 0 on success, non-0 otherwise.
- * Assumes vcpu_load() was already called.
- */
-static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct shared_msr_entry *msr;
-	int ret = 0;
-	u32 msr_index = msr_info->index;
-	u64 data = msr_info->data;
-
-	switch (msr_index) {
-	case MSR_EFER:
-		ret = kvm_set_msr_common(vcpu, msr_info);
-		break;
-#ifdef CONFIG_X86_64
-	case MSR_FS_BASE:
-		vmx_segment_cache_clear(vmx);
-		vmcs_writel(GUEST_FS_BASE, data);
-		break;
-	case MSR_GS_BASE:
-		vmx_segment_cache_clear(vmx);
-		vmcs_writel(GUEST_GS_BASE, data);
-		break;
-	case MSR_KERNEL_GS_BASE:
-		vmx_write_guest_kernel_gs_base(vmx, data);
-		break;
-#endif
-	case MSR_IA32_SYSENTER_CS:
-		vmcs_write32(GUEST_SYSENTER_CS, data);
-		break;
-	case MSR_IA32_SYSENTER_EIP:
-		vmcs_writel(GUEST_SYSENTER_EIP, data);
-		break;
-	case MSR_IA32_SYSENTER_ESP:
-		vmcs_writel(GUEST_SYSENTER_ESP, data);
-		break;
-	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported() ||
-		    (!msr_info->host_initiated &&
-		     !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
-			return 1;
-		if (is_noncanonical_address(data & PAGE_MASK, vcpu) ||
-		    (data & MSR_IA32_BNDCFGS_RSVD))
-			return 1;
-		vmcs_write64(GUEST_BNDCFGS, data);
-		break;
-	case MSR_IA32_SPEC_CTRL:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
-			return 1;
-
-		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
-			return 1;
-
-		vmx->spec_ctrl = data;
-
-		if (!data)
-			break;
-
-		/*
-		 * For non-nested:
-		 * When it's written (to non-zero) for the first time, pass
-		 * it through.
-		 *
-		 * For nested:
-		 * The handling of the MSR bitmap for L2 guests is done in
-		 * nested_vmx_merge_msr_bitmap. We should not touch the
-		 * vmcs02.msr_bitmap here since it gets completely overwritten
-		 * in the merging. We update the vmcs01 here for L1 as well
-		 * since it will end up touching the MSR anyway now.
-		 */
-		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
-					      MSR_IA32_SPEC_CTRL,
-					      MSR_TYPE_RW);
-		break;
-	case MSR_IA32_PRED_CMD:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
-			return 1;
-
-		if (data & ~PRED_CMD_IBPB)
-			return 1;
-
-		if (!data)
-			break;
-
-		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
-
-		/*
-		 * For non-nested:
-		 * When it's written (to non-zero) for the first time, pass
-		 * it through.
-		 *
-		 * For nested:
-		 * The handling of the MSR bitmap for L2 guests is done in
-		 * nested_vmx_merge_msr_bitmap. We should not touch the
-		 * vmcs02.msr_bitmap here since it gets completely overwritten
-		 * in the merging.
-		 */
-		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
-					      MSR_TYPE_W);
-		break;
-	case MSR_IA32_ARCH_CAPABILITIES:
-		if (!msr_info->host_initiated)
-			return 1;
-		vmx->arch_capabilities = data;
-		break;
-	case MSR_IA32_CR_PAT:
-		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
-			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
-				return 1;
-			vmcs_write64(GUEST_IA32_PAT, data);
-			vcpu->arch.pat = data;
-			break;
-		}
-		ret = kvm_set_msr_common(vcpu, msr_info);
-		break;
-	case MSR_IA32_TSC_ADJUST:
-		ret = kvm_set_msr_common(vcpu, msr_info);
-		break;
-	case MSR_IA32_MCG_EXT_CTL:
-		if ((!msr_info->host_initiated &&
-		     !(to_vmx(vcpu)->msr_ia32_feature_control &
-		       FEATURE_CONTROL_LMCE)) ||
-		    (data & ~MCG_EXT_CTL_LMCE_EN))
-			return 1;
-		vcpu->arch.mcg_ext_ctl = data;
-		break;
-	case MSR_IA32_FEATURE_CONTROL:
-		if (!vmx_feature_control_msr_valid(vcpu, data) ||
-		    (to_vmx(vcpu)->msr_ia32_feature_control &
-		     FEATURE_CONTROL_LOCKED && !msr_info->host_initiated))
-			return 1;
-		vmx->msr_ia32_feature_control = data;
-		if (msr_info->host_initiated && data == 0)
-			vmx_leave_nested(vcpu);
-		break;
-	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
-		if (!msr_info->host_initiated)
-			return 1; /* they are read-only */
-		if (!nested_vmx_allowed(vcpu))
-			return 1;
-		return vmx_set_vmx_msr(vcpu, msr_index, data);
-	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported())
-			return 1;
-		/*
-		 * The only supported bit as of Skylake is bit 8, but
-		 * it is not supported on KVM.
-		 */
-		if (data != 0)
-			return 1;
-		vcpu->arch.ia32_xss = data;
-		if (vcpu->arch.ia32_xss != host_xss)
-			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
-				vcpu->arch.ia32_xss, host_xss, false);
-		else
-			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
-		break;
-	case MSR_TSC_AUX:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
-			return 1;
-		/* Check reserved bit, higher 32 bits should be zero */
-		if ((data >> 32) != 0)
-			return 1;
-		/* Otherwise falls through */
-	default:
-		msr = find_msr_entry(vmx, msr_index);
-		if (msr) {
-			u64 old_msr_data = msr->data;
-			msr->data = data;
-			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
-				preempt_disable();
-				ret = kvm_set_shared_msr(msr->index, msr->data,
-							 msr->mask);
-				preempt_enable();
-				if (ret)
-					msr->data = old_msr_data;
-			}
-			break;
-		}
-		ret = kvm_set_msr_common(vcpu, msr_info);
-	}
-
-	return ret;
-}
-
-static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
-{
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-	switch (reg) {
-	case VCPU_REGS_RSP:
-		vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP);
-		break;
-	case VCPU_REGS_RIP:
-		vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP);
-		break;
-	case VCPU_EXREG_PDPTR:
-		if (enable_ept)
-			ept_save_pdptrs(vcpu);
-		break;
-	default:
-		break;
-	}
-}
-
-static __init int cpu_has_kvm_support(void)
-{
-	return cpu_has_vmx();
-}
-
-static __init int vmx_disabled_by_bios(void)
-{
-	u64 msr;
-
-	rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
-	if (msr & FEATURE_CONTROL_LOCKED) {
-		/* launched w/ TXT and VMX disabled */
-		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
-			&& tboot_enabled())
-			return 1;
-		/* launched w/o TXT and VMX only enabled w/ TXT */
-		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
-			&& (msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
-			&& !tboot_enabled()) {
-			printk(KERN_WARNING "kvm: disable TXT in the BIOS or "
-				"activate TXT before enabling KVM\n");
-			return 1;
-		}
-		/* launched w/o TXT and VMX disabled */
-		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
-			&& !tboot_enabled())
-			return 1;
-	}
-
-	return 0;
-}
-
-static void kvm_cpu_vmxon(u64 addr)
-{
-	cr4_set_bits(X86_CR4_VMXE);
-	intel_pt_handle_vmx(1);
-
-	asm volatile (ASM_VMX_VMXON_RAX
-			: : "a"(&addr), "m"(addr)
-			: "memory", "cc");
-}
-
-static int hardware_enable(void)
-{
-	int cpu = raw_smp_processor_id();
-	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
-	u64 old, test_bits;
-
-	if (cr4_read_shadow() & X86_CR4_VMXE)
-		return -EBUSY;
-
-	/*
-	 * This can happen if we hot-added a CPU but failed to allocate
-	 * VP assist page for it.
-	 */
-	if (static_branch_unlikely(&enable_evmcs) &&
-	    !hv_get_vp_assist_page(cpu))
-		return -EFAULT;
-
-	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
-	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-
-	/*
-	 * Now we can enable the vmclear operation in kdump
-	 * since the loaded_vmcss_on_cpu list on this cpu
-	 * has been initialized.
-	 *
-	 * Though the cpu is not in VMX operation now, there
-	 * is no problem to enable the vmclear operation
-	 * for the loaded_vmcss_on_cpu list is empty!
-	 */
-	crash_enable_local_vmclear(cpu);
-
-	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
-
-	test_bits = FEATURE_CONTROL_LOCKED;
-	test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
-	if (tboot_enabled())
-		test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX;
-
-	if ((old & test_bits) != test_bits) {
-		/* enable and lock */
-		wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
-	}
-	kvm_cpu_vmxon(phys_addr);
-	if (enable_ept)
-		ept_sync_global();
-
-	return 0;
-}
-
-static void vmclear_local_loaded_vmcss(void)
-{
-	int cpu = raw_smp_processor_id();
-	struct loaded_vmcs *v, *n;
-
-	list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu),
-				 loaded_vmcss_on_cpu_link)
-		__loaded_vmcs_clear(v);
-}
-
-
-/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot()
- * tricks.
- */
-static void kvm_cpu_vmxoff(void)
-{
-	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
-
-	intel_pt_handle_vmx(0);
-	cr4_clear_bits(X86_CR4_VMXE);
-}
-
-static void hardware_disable(void)
-{
-	vmclear_local_loaded_vmcss();
-	kvm_cpu_vmxoff();
-}
-
-static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
-				      u32 msr, u32 *result)
-{
-	u32 vmx_msr_low, vmx_msr_high;
-	u32 ctl = ctl_min | ctl_opt;
-
-	rdmsr(msr, vmx_msr_low, vmx_msr_high);
-
-	ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */
-	ctl |= vmx_msr_low;  /* bit == 1 in low word  ==> must be one  */
-
-	/* Ensure minimum (required) set of control bits are supported. */
-	if (ctl_min & ~ctl)
-		return -EIO;
-
-	*result = ctl;
-	return 0;
-}
-
-static __init bool allow_1_setting(u32 msr, u32 ctl)
-{
-	u32 vmx_msr_low, vmx_msr_high;
-
-	rdmsr(msr, vmx_msr_low, vmx_msr_high);
-	return vmx_msr_high & ctl;
-}
-
-static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
-{
-	u32 vmx_msr_low, vmx_msr_high;
-	u32 min, opt, min2, opt2;
-	u32 _pin_based_exec_control = 0;
-	u32 _cpu_based_exec_control = 0;
-	u32 _cpu_based_2nd_exec_control = 0;
-	u32 _vmexit_control = 0;
-	u32 _vmentry_control = 0;
-
-	memset(vmcs_conf, 0, sizeof(*vmcs_conf));
-	min = CPU_BASED_HLT_EXITING |
-#ifdef CONFIG_X86_64
-	      CPU_BASED_CR8_LOAD_EXITING |
-	      CPU_BASED_CR8_STORE_EXITING |
-#endif
-	      CPU_BASED_CR3_LOAD_EXITING |
-	      CPU_BASED_CR3_STORE_EXITING |
-	      CPU_BASED_UNCOND_IO_EXITING |
-	      CPU_BASED_MOV_DR_EXITING |
-	      CPU_BASED_USE_TSC_OFFSETING |
-	      CPU_BASED_MWAIT_EXITING |
-	      CPU_BASED_MONITOR_EXITING |
-	      CPU_BASED_INVLPG_EXITING |
-	      CPU_BASED_RDPMC_EXITING;
-
-	opt = CPU_BASED_TPR_SHADOW |
-	      CPU_BASED_USE_MSR_BITMAPS |
-	      CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
-	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
-				&_cpu_based_exec_control) < 0)
-		return -EIO;
-#ifdef CONFIG_X86_64
-	if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
-		_cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING &
-					   ~CPU_BASED_CR8_STORE_EXITING;
-#endif
-	if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
-		min2 = 0;
-		opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
-			SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
-			SECONDARY_EXEC_WBINVD_EXITING |
-			SECONDARY_EXEC_ENABLE_VPID |
-			SECONDARY_EXEC_ENABLE_EPT |
-			SECONDARY_EXEC_UNRESTRICTED_GUEST |
-			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
-			SECONDARY_EXEC_DESC |
-			SECONDARY_EXEC_RDTSCP |
-			SECONDARY_EXEC_ENABLE_INVPCID |
-			SECONDARY_EXEC_APIC_REGISTER_VIRT |
-			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
-			SECONDARY_EXEC_SHADOW_VMCS |
-			SECONDARY_EXEC_XSAVES |
-			SECONDARY_EXEC_RDSEED_EXITING |
-			SECONDARY_EXEC_RDRAND_EXITING |
-			SECONDARY_EXEC_ENABLE_PML |
-			SECONDARY_EXEC_TSC_SCALING |
-			SECONDARY_EXEC_ENABLE_VMFUNC |
-			SECONDARY_EXEC_ENCLS_EXITING;
-		if (adjust_vmx_controls(min2, opt2,
-					MSR_IA32_VMX_PROCBASED_CTLS2,
-					&_cpu_based_2nd_exec_control) < 0)
-			return -EIO;
-	}
-#ifndef CONFIG_X86_64
-	if (!(_cpu_based_2nd_exec_control &
-				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
-		_cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW;
-#endif
-
-	if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
-		_cpu_based_2nd_exec_control &= ~(
-				SECONDARY_EXEC_APIC_REGISTER_VIRT |
-				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
-				SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
-
-	rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP,
-		&vmx_capability.ept, &vmx_capability.vpid);
-
-	if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
-		/* CR3 accesses and invlpg don't need to cause VM Exits when EPT
-		   enabled */
-		_cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING |
-					     CPU_BASED_CR3_STORE_EXITING |
-					     CPU_BASED_INVLPG_EXITING);
-	} else if (vmx_capability.ept) {
-		vmx_capability.ept = 0;
-		pr_warn_once("EPT CAP should not exist if not support "
-				"1-setting enable EPT VM-execution control\n");
-	}
-	if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) &&
-		vmx_capability.vpid) {
-		vmx_capability.vpid = 0;
-		pr_warn_once("VPID CAP should not exist if not support "
-				"1-setting enable VPID VM-execution control\n");
-	}
-
-	min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT;
-#ifdef CONFIG_X86_64
-	min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
-#endif
-	opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT |
-		VM_EXIT_CLEAR_BNDCFGS;
-	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
-				&_vmexit_control) < 0)
-		return -EIO;
-
-	min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
-	opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
-		 PIN_BASED_VMX_PREEMPTION_TIMER;
-	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
-				&_pin_based_exec_control) < 0)
-		return -EIO;
-
-	if (cpu_has_broken_vmx_preemption_timer())
-		_pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
-	if (!(_cpu_based_2nd_exec_control &
-		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY))
-		_pin_based_exec_control &= ~PIN_BASED_POSTED_INTR;
-
-	min = VM_ENTRY_LOAD_DEBUG_CONTROLS;
-	opt = VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS;
-	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
-				&_vmentry_control) < 0)
-		return -EIO;
-
-	rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high);
-
-	/* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */
-	if ((vmx_msr_high & 0x1fff) > PAGE_SIZE)
-		return -EIO;
-
-#ifdef CONFIG_X86_64
-	/* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */
-	if (vmx_msr_high & (1u<<16))
-		return -EIO;
-#endif
-
-	/* Require Write-Back (WB) memory type for VMCS accesses. */
-	if (((vmx_msr_high >> 18) & 15) != 6)
-		return -EIO;
-
-	vmcs_conf->size = vmx_msr_high & 0x1fff;
-	vmcs_conf->order = get_order(vmcs_conf->size);
-	vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
-
-	vmcs_conf->revision_id = vmx_msr_low;
-
-	vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
-	vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
-	vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control;
-	vmcs_conf->vmexit_ctrl         = _vmexit_control;
-	vmcs_conf->vmentry_ctrl        = _vmentry_control;
-
-	if (static_branch_unlikely(&enable_evmcs))
-		evmcs_sanitize_exec_ctrls(vmcs_conf);
-
-	cpu_has_load_ia32_efer =
-		allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS,
-				VM_ENTRY_LOAD_IA32_EFER)
-		&& allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
-				   VM_EXIT_LOAD_IA32_EFER);
-
-	cpu_has_load_perf_global_ctrl =
-		allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS,
-				VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
-		&& allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
-				   VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
-
-	/*
-	 * Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL
-	 * but due to errata below it can't be used. Workaround is to use
-	 * msr load mechanism to switch IA32_PERF_GLOBAL_CTRL.
-	 *
-	 * VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32]
-	 *
-	 * AAK155             (model 26)
-	 * AAP115             (model 30)
-	 * AAT100             (model 37)
-	 * BC86,AAY89,BD102   (model 44)
-	 * BA97               (model 46)
-	 *
-	 */
-	if (cpu_has_load_perf_global_ctrl && boot_cpu_data.x86 == 0x6) {
-		switch (boot_cpu_data.x86_model) {
-		case 26:
-		case 30:
-		case 37:
-		case 44:
-		case 46:
-			cpu_has_load_perf_global_ctrl = false;
-			printk_once(KERN_WARNING"kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
-					"does not work properly. Using workaround\n");
-			break;
-		default:
-			break;
-		}
-	}
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		rdmsrl(MSR_IA32_XSS, host_xss);
-
-	return 0;
-}
-
-static struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu)
-{
-	int node = cpu_to_node(cpu);
-	struct page *pages;
-	struct vmcs *vmcs;
-
-	pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order);
-	if (!pages)
-		return NULL;
-	vmcs = page_address(pages);
-	memset(vmcs, 0, vmcs_config.size);
-
-	/* KVM supports Enlightened VMCS v1 only */
-	if (static_branch_unlikely(&enable_evmcs))
-		vmcs->hdr.revision_id = KVM_EVMCS_VERSION;
-	else
-		vmcs->hdr.revision_id = vmcs_config.revision_id;
-
-	if (shadow)
-		vmcs->hdr.shadow_vmcs = 1;
-	return vmcs;
-}
-
-static void free_vmcs(struct vmcs *vmcs)
-{
-	free_pages((unsigned long)vmcs, vmcs_config.order);
-}
-
-/*
- * Free a VMCS, but before that VMCLEAR it on the CPU where it was last loaded
- */
-static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
-{
-	if (!loaded_vmcs->vmcs)
-		return;
-	loaded_vmcs_clear(loaded_vmcs);
-	free_vmcs(loaded_vmcs->vmcs);
-	loaded_vmcs->vmcs = NULL;
-	if (loaded_vmcs->msr_bitmap)
-		free_page((unsigned long)loaded_vmcs->msr_bitmap);
-	WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
-}
-
-static struct vmcs *alloc_vmcs(bool shadow)
-{
-	return alloc_vmcs_cpu(shadow, raw_smp_processor_id());
-}
-
-static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
-{
-	loaded_vmcs->vmcs = alloc_vmcs(false);
-	if (!loaded_vmcs->vmcs)
-		return -ENOMEM;
-
-	loaded_vmcs->shadow_vmcs = NULL;
-	loaded_vmcs_init(loaded_vmcs);
-
-	if (cpu_has_vmx_msr_bitmap()) {
-		loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
-		if (!loaded_vmcs->msr_bitmap)
-			goto out_vmcs;
-		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
-
-		if (IS_ENABLED(CONFIG_HYPERV) &&
-		    static_branch_unlikely(&enable_evmcs) &&
-		    (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
-			struct hv_enlightened_vmcs *evmcs =
-				(struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;
-
-			evmcs->hv_enlightenments_control.msr_bitmap = 1;
-		}
-	}
-
-	memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state));
-
-	return 0;
-
-out_vmcs:
-	free_loaded_vmcs(loaded_vmcs);
-	return -ENOMEM;
-}
-
-static void free_kvm_area(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		free_vmcs(per_cpu(vmxarea, cpu));
-		per_cpu(vmxarea, cpu) = NULL;
-	}
-}
-
-enum vmcs_field_width {
-	VMCS_FIELD_WIDTH_U16 = 0,
-	VMCS_FIELD_WIDTH_U64 = 1,
-	VMCS_FIELD_WIDTH_U32 = 2,
-	VMCS_FIELD_WIDTH_NATURAL_WIDTH = 3
-};
-
-static inline int vmcs_field_width(unsigned long field)
-{
-	if (0x1 & field)	/* the *_HIGH fields are all 32 bit */
-		return VMCS_FIELD_WIDTH_U32;
-	return (field >> 13) & 0x3 ;
-}
-
-static inline int vmcs_field_readonly(unsigned long field)
-{
-	return (((field >> 10) & 0x3) == 1);
-}
-
-static void init_vmcs_shadow_fields(void)
-{
-	int i, j;
-
-	for (i = j = 0; i < max_shadow_read_only_fields; i++) {
-		u16 field = shadow_read_only_fields[i];
-		if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
-		    (i + 1 == max_shadow_read_only_fields ||
-		     shadow_read_only_fields[i + 1] != field + 1))
-			pr_err("Missing field from shadow_read_only_field %x\n",
-			       field + 1);
-
-		clear_bit(field, vmx_vmread_bitmap);
-#ifdef CONFIG_X86_64
-		if (field & 1)
-			continue;
-#endif
-		if (j < i)
-			shadow_read_only_fields[j] = field;
-		j++;
-	}
-	max_shadow_read_only_fields = j;
-
-	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
-		u16 field = shadow_read_write_fields[i];
-		if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
-		    (i + 1 == max_shadow_read_write_fields ||
-		     shadow_read_write_fields[i + 1] != field + 1))
-			pr_err("Missing field from shadow_read_write_field %x\n",
-			       field + 1);
-
-		/*
-		 * PML and the preemption timer can be emulated, but the
-		 * processor cannot vmwrite to fields that don't exist
-		 * on bare metal.
-		 */
-		switch (field) {
-		case GUEST_PML_INDEX:
-			if (!cpu_has_vmx_pml())
-				continue;
-			break;
-		case VMX_PREEMPTION_TIMER_VALUE:
-			if (!cpu_has_vmx_preemption_timer())
-				continue;
-			break;
-		case GUEST_INTR_STATUS:
-			if (!cpu_has_vmx_apicv())
-				continue;
-			break;
-		default:
-			break;
-		}
-
-		clear_bit(field, vmx_vmwrite_bitmap);
-		clear_bit(field, vmx_vmread_bitmap);
-#ifdef CONFIG_X86_64
-		if (field & 1)
-			continue;
-#endif
-		if (j < i)
-			shadow_read_write_fields[j] = field;
-		j++;
-	}
-	max_shadow_read_write_fields = j;
-}
-
-static __init int alloc_kvm_area(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct vmcs *vmcs;
-
-		vmcs = alloc_vmcs_cpu(false, cpu);
-		if (!vmcs) {
-			free_kvm_area();
-			return -ENOMEM;
-		}
-
-		/*
-		 * When eVMCS is enabled, alloc_vmcs_cpu() sets
-		 * vmcs->revision_id to KVM_EVMCS_VERSION instead of
-		 * revision_id reported by MSR_IA32_VMX_BASIC.
-		 *
-		 * However, even though not explictly documented by
-		 * TLFS, VMXArea passed as VMXON argument should
-		 * still be marked with revision_id reported by
-		 * physical CPU.
-		 */
-		if (static_branch_unlikely(&enable_evmcs))
-			vmcs->hdr.revision_id = vmcs_config.revision_id;
-
-		per_cpu(vmxarea, cpu) = vmcs;
-	}
-	return 0;
-}
-
-static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg,
-		struct kvm_segment *save)
-{
-	if (!emulate_invalid_guest_state) {
-		/*
-		 * CS and SS RPL should be equal during guest entry according
-		 * to VMX spec, but in reality it is not always so. Since vcpu
-		 * is in the middle of the transition from real mode to
-		 * protected mode it is safe to assume that RPL 0 is a good
-		 * default value.
-		 */
-		if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS)
-			save->selector &= ~SEGMENT_RPL_MASK;
-		save->dpl = save->selector & SEGMENT_RPL_MASK;
-		save->s = 1;
-	}
-	vmx_set_segment(vcpu, save, seg);
-}
-
-static void enter_pmode(struct kvm_vcpu *vcpu)
-{
-	unsigned long flags;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	/*
-	 * Update real mode segment cache. It may be not up-to-date if sement
-	 * register was written while vcpu was in a guest mode.
-	 */
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS);
-
-	vmx->rmode.vm86_active = 0;
-
-	vmx_segment_cache_clear(vmx);
-
-	vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
-
-	flags = vmcs_readl(GUEST_RFLAGS);
-	flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
-	flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
-	vmcs_writel(GUEST_RFLAGS, flags);
-
-	vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
-			(vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME));
-
-	update_exception_bitmap(vcpu);
-
-	fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]);
-	fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]);
-	fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
-	fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
-	fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
-	fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
-}
-
-static void fix_rmode_seg(int seg, struct kvm_segment *save)
-{
-	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
-	struct kvm_segment var = *save;
-
-	var.dpl = 0x3;
-	if (seg == VCPU_SREG_CS)
-		var.type = 0x3;
-
-	if (!emulate_invalid_guest_state) {
-		var.selector = var.base >> 4;
-		var.base = var.base & 0xffff0;
-		var.limit = 0xffff;
-		var.g = 0;
-		var.db = 0;
-		var.present = 1;
-		var.s = 1;
-		var.l = 0;
-		var.unusable = 0;
-		var.type = 0x3;
-		var.avl = 0;
-		if (save->base & 0xf)
-			printk_once(KERN_WARNING "kvm: segment base is not "
-					"paragraph aligned when entering "
-					"protected mode (seg=%d)", seg);
-	}
-
-	vmcs_write16(sf->selector, var.selector);
-	vmcs_writel(sf->base, var.base);
-	vmcs_write32(sf->limit, var.limit);
-	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var));
-}
-
-static void enter_rmode(struct kvm_vcpu *vcpu)
-{
-	unsigned long flags;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm);
-
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS);
-	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS);
-
-	vmx->rmode.vm86_active = 1;
-
-	/*
-	 * Very old userspace does not call KVM_SET_TSS_ADDR before entering
-	 * vcpu. Warn the user that an update is overdue.
-	 */
-	if (!kvm_vmx->tss_addr)
-		printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be "
-			     "called before entering vcpu\n");
-
-	vmx_segment_cache_clear(vmx);
-
-	vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr);
-	vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);
-	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
-
-	flags = vmcs_readl(GUEST_RFLAGS);
-	vmx->rmode.save_rflags = flags;
-
-	flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
-
-	vmcs_writel(GUEST_RFLAGS, flags);
-	vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
-	update_exception_bitmap(vcpu);
-
-	fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]);
-	fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]);
-	fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
-	fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
-	fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
-	fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
-
-	kvm_mmu_reset_context(vcpu);
-}
-
-static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
-
-	if (!msr)
-		return;
-
-	vcpu->arch.efer = efer;
-	if (efer & EFER_LMA) {
-		vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
-		msr->data = efer;
-	} else {
-		vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
-
-		msr->data = efer & ~EFER_LME;
-	}
-	setup_msrs(vmx);
-}
-
-#ifdef CONFIG_X86_64
-
-static void enter_lmode(struct kvm_vcpu *vcpu)
-{
-	u32 guest_tr_ar;
-
-	vmx_segment_cache_clear(to_vmx(vcpu));
-
-	guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
-	if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) {
-		pr_debug_ratelimited("%s: tss fixup for long mode. \n",
-				     __func__);
-		vmcs_write32(GUEST_TR_AR_BYTES,
-			     (guest_tr_ar & ~VMX_AR_TYPE_MASK)
-			     | VMX_AR_TYPE_BUSY_64_TSS);
-	}
-	vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
-}
-
-static void exit_lmode(struct kvm_vcpu *vcpu)
-{
-	vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
-	vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA);
-}
-
-#endif
-
-static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid,
-				bool invalidate_gpa)
-{
-	if (enable_ept && (invalidate_gpa || !enable_vpid)) {
-		if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
-			return;
-		ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
-	} else {
-		vpid_sync_context(vpid);
-	}
-}
-
-static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
-{
-	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
-}
-
-static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
-{
-	int vpid = to_vmx(vcpu)->vpid;
-
-	if (!vpid_sync_vcpu_addr(vpid, addr))
-		vpid_sync_context(vpid);
-
-	/*
-	 * If VPIDs are not supported or enabled, then the above is a no-op.
-	 * But we don't really need a TLB flush in that case anyway, because
-	 * each VM entry/exit includes an implicit flush when VPID is 0.
-	 */
-}
-
-static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
-{
-	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
-
-	vcpu->arch.cr0 &= ~cr0_guest_owned_bits;
-	vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
-}
-
-static void vmx_decache_cr3(struct kvm_vcpu *vcpu)
-{
-	if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
-		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
-}
-
-static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
-{
-	ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
-
-	vcpu->arch.cr4 &= ~cr4_guest_owned_bits;
-	vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits;
-}
-
-static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
-{
-	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
-
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_dirty))
-		return;
-
-	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
-		vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
-		vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
-		vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
-	}
-}
-
-static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
-{
-	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
-
-	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
-		mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
-		mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
-		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
-	}
-
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_dirty);
-}
-
-static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
-	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-
-	if (to_vmx(vcpu)->nested.msrs.secondary_ctls_high &
-		SECONDARY_EXEC_UNRESTRICTED_GUEST &&
-	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
-		fixed0 &= ~(X86_CR0_PE | X86_CR0_PG);
-
-	return fixed_bits_valid(val, fixed0, fixed1);
-}
-
-static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
-	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
-
-	return fixed_bits_valid(val, fixed0, fixed1);
-}
-
-static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0;
-	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1;
-
-	return fixed_bits_valid(val, fixed0, fixed1);
-}
-
-/* No difference in the restrictions on guest and host CR4 in VMX operation. */
-#define nested_guest_cr4_valid	nested_cr4_valid
-#define nested_host_cr4_valid	nested_cr4_valid
-
-static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
-
-static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
-					unsigned long cr0,
-					struct kvm_vcpu *vcpu)
-{
-	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
-		vmx_decache_cr3(vcpu);
-	if (!(cr0 & X86_CR0_PG)) {
-		/* From paging/starting to nonpaging */
-		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
-			     vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) |
-			     (CPU_BASED_CR3_LOAD_EXITING |
-			      CPU_BASED_CR3_STORE_EXITING));
-		vcpu->arch.cr0 = cr0;
-		vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
-	} else if (!is_paging(vcpu)) {
-		/* From nonpaging to paging */
-		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
-			     vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
-			     ~(CPU_BASED_CR3_LOAD_EXITING |
-			       CPU_BASED_CR3_STORE_EXITING));
-		vcpu->arch.cr0 = cr0;
-		vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
-	}
-
-	if (!(cr0 & X86_CR0_WP))
-		*hw_cr0 &= ~X86_CR0_WP;
-}
-
-static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long hw_cr0;
-
-	hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK);
-	if (enable_unrestricted_guest)
-		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
-	else {
-		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON;
-
-		if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
-			enter_pmode(vcpu);
-
-		if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE))
-			enter_rmode(vcpu);
-	}
-
-#ifdef CONFIG_X86_64
-	if (vcpu->arch.efer & EFER_LME) {
-		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG))
-			enter_lmode(vcpu);
-		if (is_paging(vcpu) && !(cr0 & X86_CR0_PG))
-			exit_lmode(vcpu);
-	}
-#endif
-
-	if (enable_ept && !enable_unrestricted_guest)
-		ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
-
-	vmcs_writel(CR0_READ_SHADOW, cr0);
-	vmcs_writel(GUEST_CR0, hw_cr0);
-	vcpu->arch.cr0 = cr0;
-
-	/* depends on vcpu->arch.cr0 to be set to a new value */
-	vmx->emulation_required = emulation_required(vcpu);
-}
-
-static int get_ept_level(struct kvm_vcpu *vcpu)
-{
-	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
-		return 5;
-	return 4;
-}
-
-static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
-{
-	u64 eptp = VMX_EPTP_MT_WB;
-
-	eptp |= (get_ept_level(vcpu) == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;
-
-	if (enable_ept_ad_bits &&
-	    (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu)))
-		eptp |= VMX_EPTP_AD_ENABLE_BIT;
-	eptp |= (root_hpa & PAGE_MASK);
-
-	return eptp;
-}
-
-static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
-{
-	struct kvm *kvm = vcpu->kvm;
-	unsigned long guest_cr3;
-	u64 eptp;
-
-	guest_cr3 = cr3;
-	if (enable_ept) {
-		eptp = construct_eptp(vcpu, cr3);
-		vmcs_write64(EPT_POINTER, eptp);
-
-		if (kvm_x86_ops->tlb_remote_flush) {
-			spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock);
-			to_vmx(vcpu)->ept_pointer = eptp;
-			to_kvm_vmx(kvm)->ept_pointers_match
-				= EPT_POINTERS_CHECK;
-			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
-		}
-
-		if (enable_unrestricted_guest || is_paging(vcpu) ||
-		    is_guest_mode(vcpu))
-			guest_cr3 = kvm_read_cr3(vcpu);
-		else
-			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
-		ept_load_pdptrs(vcpu);
-	}
-
-	vmcs_writel(GUEST_CR3, guest_cr3);
-}
-
-static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
-{
-	/*
-	 * Pass through host's Machine Check Enable value to hw_cr4, which
-	 * is in force while we are in guest mode.  Do not let guests control
-	 * this bit, even if host CR4.MCE == 0.
-	 */
-	unsigned long hw_cr4;
-
-	hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE);
-	if (enable_unrestricted_guest)
-		hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST;
-	else if (to_vmx(vcpu)->rmode.vm86_active)
-		hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON;
-	else
-		hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
-
-	if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
-		if (cr4 & X86_CR4_UMIP) {
-			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
-				SECONDARY_EXEC_DESC);
-			hw_cr4 &= ~X86_CR4_UMIP;
-		} else if (!is_guest_mode(vcpu) ||
-			!nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
-			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
-					SECONDARY_EXEC_DESC);
-	}
-
-	if (cr4 & X86_CR4_VMXE) {
-		/*
-		 * To use VMXON (and later other VMX instructions), a guest
-		 * must first be able to turn on cr4.VMXE (see handle_vmon()).
-		 * So basically the check on whether to allow nested VMX
-		 * is here.  We operate under the default treatment of SMM,
-		 * so VMX cannot be enabled under SMM.
-		 */
-		if (!nested_vmx_allowed(vcpu) || is_smm(vcpu))
-			return 1;
-	}
-
-	if (to_vmx(vcpu)->nested.vmxon && !nested_cr4_valid(vcpu, cr4))
-		return 1;
-
-	vcpu->arch.cr4 = cr4;
-
-	if (!enable_unrestricted_guest) {
-		if (enable_ept) {
-			if (!is_paging(vcpu)) {
-				hw_cr4 &= ~X86_CR4_PAE;
-				hw_cr4 |= X86_CR4_PSE;
-			} else if (!(cr4 & X86_CR4_PAE)) {
-				hw_cr4 &= ~X86_CR4_PAE;
-			}
-		}
-
-		/*
-		 * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in
-		 * hardware.  To emulate this behavior, SMEP/SMAP/PKU needs
-		 * to be manually disabled when guest switches to non-paging
-		 * mode.
-		 *
-		 * If !enable_unrestricted_guest, the CPU is always running
-		 * with CR0.PG=1 and CR4 needs to be modified.
-		 * If enable_unrestricted_guest, the CPU automatically
-		 * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0.
-		 */
-		if (!is_paging(vcpu))
-			hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE);
-	}
-
-	vmcs_writel(CR4_READ_SHADOW, cr4);
-	vmcs_writel(GUEST_CR4, hw_cr4);
-	return 0;
-}
-
-static void vmx_get_segment(struct kvm_vcpu *vcpu,
-			    struct kvm_segment *var, int seg)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 ar;
-
-	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
-		*var = vmx->rmode.segs[seg];
-		if (seg == VCPU_SREG_TR
-		    || var->selector == vmx_read_guest_seg_selector(vmx, seg))
-			return;
-		var->base = vmx_read_guest_seg_base(vmx, seg);
-		var->selector = vmx_read_guest_seg_selector(vmx, seg);
-		return;
-	}
-	var->base = vmx_read_guest_seg_base(vmx, seg);
-	var->limit = vmx_read_guest_seg_limit(vmx, seg);
-	var->selector = vmx_read_guest_seg_selector(vmx, seg);
-	ar = vmx_read_guest_seg_ar(vmx, seg);
-	var->unusable = (ar >> 16) & 1;
-	var->type = ar & 15;
-	var->s = (ar >> 4) & 1;
-	var->dpl = (ar >> 5) & 3;
-	/*
-	 * Some userspaces do not preserve unusable property. Since usable
-	 * segment has to be present according to VMX spec we can use present
-	 * property to amend userspace bug by making unusable segment always
-	 * nonpresent. vmx_segment_access_rights() already marks nonpresent
-	 * segment as unusable.
-	 */
-	var->present = !var->unusable;
-	var->avl = (ar >> 12) & 1;
-	var->l = (ar >> 13) & 1;
-	var->db = (ar >> 14) & 1;
-	var->g = (ar >> 15) & 1;
-}
-
-static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
-{
-	struct kvm_segment s;
-
-	if (to_vmx(vcpu)->rmode.vm86_active) {
-		vmx_get_segment(vcpu, &s, seg);
-		return s.base;
-	}
-	return vmx_read_guest_seg_base(to_vmx(vcpu), seg);
-}
-
-static int vmx_get_cpl(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (unlikely(vmx->rmode.vm86_active))
-		return 0;
-	else {
-		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
-		return VMX_AR_DPL(ar);
-	}
-}
-
-static u32 vmx_segment_access_rights(struct kvm_segment *var)
-{
-	u32 ar;
-
-	if (var->unusable || !var->present)
-		ar = 1 << 16;
-	else {
-		ar = var->type & 15;
-		ar |= (var->s & 1) << 4;
-		ar |= (var->dpl & 3) << 5;
-		ar |= (var->present & 1) << 7;
-		ar |= (var->avl & 1) << 12;
-		ar |= (var->l & 1) << 13;
-		ar |= (var->db & 1) << 14;
-		ar |= (var->g & 1) << 15;
-	}
-
-	return ar;
-}
-
-static void vmx_set_segment(struct kvm_vcpu *vcpu,
-			    struct kvm_segment *var, int seg)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
-
-	vmx_segment_cache_clear(vmx);
-
-	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
-		vmx->rmode.segs[seg] = *var;
-		if (seg == VCPU_SREG_TR)
-			vmcs_write16(sf->selector, var->selector);
-		else if (var->s)
-			fix_rmode_seg(seg, &vmx->rmode.segs[seg]);
-		goto out;
-	}
-
-	vmcs_writel(sf->base, var->base);
-	vmcs_write32(sf->limit, var->limit);
-	vmcs_write16(sf->selector, var->selector);
-
-	/*
-	 *   Fix the "Accessed" bit in AR field of segment registers for older
-	 * qemu binaries.
-	 *   IA32 arch specifies that at the time of processor reset the
-	 * "Accessed" bit in the AR field of segment registers is 1. And qemu
-	 * is setting it to 0 in the userland code. This causes invalid guest
-	 * state vmexit when "unrestricted guest" mode is turned on.
-	 *    Fix for this setup issue in cpu_reset is being pushed in the qemu
-	 * tree. Newer qemu binaries with that qemu fix would not need this
-	 * kvm hack.
-	 */
-	if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR))
-		var->type |= 0x1; /* Accessed */
-
-	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var));
-
-out:
-	vmx->emulation_required = emulation_required(vcpu);
-}
-
-static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
-{
-	u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS);
-
-	*db = (ar >> 14) & 1;
-	*l = (ar >> 13) & 1;
-}
-
-static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
-{
-	dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
-	dt->address = vmcs_readl(GUEST_IDTR_BASE);
-}
-
-static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
-{
-	vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
-	vmcs_writel(GUEST_IDTR_BASE, dt->address);
-}
-
-static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
-{
-	dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
-	dt->address = vmcs_readl(GUEST_GDTR_BASE);
-}
-
-static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
-{
-	vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
-	vmcs_writel(GUEST_GDTR_BASE, dt->address);
-}
-
-static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
-{
-	struct kvm_segment var;
-	u32 ar;
-
-	vmx_get_segment(vcpu, &var, seg);
-	var.dpl = 0x3;
-	if (seg == VCPU_SREG_CS)
-		var.type = 0x3;
-	ar = vmx_segment_access_rights(&var);
-
-	if (var.base != (var.selector << 4))
-		return false;
-	if (var.limit != 0xffff)
-		return false;
-	if (ar != 0xf3)
-		return false;
-
-	return true;
-}
-
-static bool code_segment_valid(struct kvm_vcpu *vcpu)
-{
-	struct kvm_segment cs;
-	unsigned int cs_rpl;
-
-	vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
-	cs_rpl = cs.selector & SEGMENT_RPL_MASK;
-
-	if (cs.unusable)
-		return false;
-	if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK))
-		return false;
-	if (!cs.s)
-		return false;
-	if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) {
-		if (cs.dpl > cs_rpl)
-			return false;
-	} else {
-		if (cs.dpl != cs_rpl)
-			return false;
-	}
-	if (!cs.present)
-		return false;
-
-	/* TODO: Add Reserved field check, this'll require a new member in the kvm_segment_field structure */
-	return true;
-}
-
-static bool stack_segment_valid(struct kvm_vcpu *vcpu)
-{
-	struct kvm_segment ss;
-	unsigned int ss_rpl;
-
-	vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
-	ss_rpl = ss.selector & SEGMENT_RPL_MASK;
-
-	if (ss.unusable)
-		return true;
-	if (ss.type != 3 && ss.type != 7)
-		return false;
-	if (!ss.s)
-		return false;
-	if (ss.dpl != ss_rpl) /* DPL != RPL */
-		return false;
-	if (!ss.present)
-		return false;
-
-	return true;
-}
-
-static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
-{
-	struct kvm_segment var;
-	unsigned int rpl;
-
-	vmx_get_segment(vcpu, &var, seg);
-	rpl = var.selector & SEGMENT_RPL_MASK;
-
-	if (var.unusable)
-		return true;
-	if (!var.s)
-		return false;
-	if (!var.present)
-		return false;
-	if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) {
-		if (var.dpl < rpl) /* DPL < RPL */
-			return false;
-	}
-
-	/* TODO: Add other members to kvm_segment_field to allow checking for other access
-	 * rights flags
-	 */
-	return true;
-}
-
-static bool tr_valid(struct kvm_vcpu *vcpu)
-{
-	struct kvm_segment tr;
-
-	vmx_get_segment(vcpu, &tr, VCPU_SREG_TR);
-
-	if (tr.unusable)
-		return false;
-	if (tr.selector & SEGMENT_TI_MASK)	/* TI = 1 */
-		return false;
-	if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */
-		return false;
-	if (!tr.present)
-		return false;
-
-	return true;
-}
-
-static bool ldtr_valid(struct kvm_vcpu *vcpu)
-{
-	struct kvm_segment ldtr;
-
-	vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR);
-
-	if (ldtr.unusable)
-		return true;
-	if (ldtr.selector & SEGMENT_TI_MASK)	/* TI = 1 */
-		return false;
-	if (ldtr.type != 2)
-		return false;
-	if (!ldtr.present)
-		return false;
-
-	return true;
-}
-
-static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
-{
-	struct kvm_segment cs, ss;
-
-	vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
-	vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
-
-	return ((cs.selector & SEGMENT_RPL_MASK) ==
-		 (ss.selector & SEGMENT_RPL_MASK));
-}
-
-/*
- * Check if guest state is valid. Returns true if valid, false if
- * not.
- * We assume that registers are always usable
- */
-static bool guest_state_valid(struct kvm_vcpu *vcpu)
-{
-	if (enable_unrestricted_guest)
-		return true;
-
-	/* real mode guest state checks */
-	if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) {
-		if (!rmode_segment_valid(vcpu, VCPU_SREG_CS))
-			return false;
-		if (!rmode_segment_valid(vcpu, VCPU_SREG_SS))
-			return false;
-		if (!rmode_segment_valid(vcpu, VCPU_SREG_DS))
-			return false;
-		if (!rmode_segment_valid(vcpu, VCPU_SREG_ES))
-			return false;
-		if (!rmode_segment_valid(vcpu, VCPU_SREG_FS))
-			return false;
-		if (!rmode_segment_valid(vcpu, VCPU_SREG_GS))
-			return false;
-	} else {
-	/* protected mode guest state checks */
-		if (!cs_ss_rpl_check(vcpu))
-			return false;
-		if (!code_segment_valid(vcpu))
-			return false;
-		if (!stack_segment_valid(vcpu))
-			return false;
-		if (!data_segment_valid(vcpu, VCPU_SREG_DS))
-			return false;
-		if (!data_segment_valid(vcpu, VCPU_SREG_ES))
-			return false;
-		if (!data_segment_valid(vcpu, VCPU_SREG_FS))
-			return false;
-		if (!data_segment_valid(vcpu, VCPU_SREG_GS))
-			return false;
-		if (!tr_valid(vcpu))
-			return false;
-		if (!ldtr_valid(vcpu))
-			return false;
-	}
-	/* TODO:
-	 * - Add checks on RIP
-	 * - Add checks on RFLAGS
-	 */
-
-	return true;
-}
-
-static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
-{
-	return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
-}
-
-static int init_rmode_tss(struct kvm *kvm)
-{
-	gfn_t fn;
-	u16 data = 0;
-	int idx, r;
-
-	idx = srcu_read_lock(&kvm->srcu);
-	fn = to_kvm_vmx(kvm)->tss_addr >> PAGE_SHIFT;
-	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
-	if (r < 0)
-		goto out;
-	data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
-	r = kvm_write_guest_page(kvm, fn++, &data,
-			TSS_IOPB_BASE_OFFSET, sizeof(u16));
-	if (r < 0)
-		goto out;
-	r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE);
-	if (r < 0)
-		goto out;
-	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
-	if (r < 0)
-		goto out;
-	data = ~0;
-	r = kvm_write_guest_page(kvm, fn, &data,
-				 RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
-				 sizeof(u8));
-out:
-	srcu_read_unlock(&kvm->srcu, idx);
-	return r;
-}
-
-static int init_rmode_identity_map(struct kvm *kvm)
-{
-	struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
-	int i, idx, r = 0;
-	kvm_pfn_t identity_map_pfn;
-	u32 tmp;
-
-	/* Protect kvm_vmx->ept_identity_pagetable_done. */
-	mutex_lock(&kvm->slots_lock);
-
-	if (likely(kvm_vmx->ept_identity_pagetable_done))
-		goto out2;
-
-	if (!kvm_vmx->ept_identity_map_addr)
-		kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR;
-	identity_map_pfn = kvm_vmx->ept_identity_map_addr >> PAGE_SHIFT;
-
-	r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
-				    kvm_vmx->ept_identity_map_addr, PAGE_SIZE);
-	if (r < 0)
-		goto out2;
-
-	idx = srcu_read_lock(&kvm->srcu);
-	r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
-	if (r < 0)
-		goto out;
-	/* Set up identity-mapping pagetable for EPT in real mode */
-	for (i = 0; i < PT32_ENT_PER_PAGE; i++) {
-		tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
-			_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
-		r = kvm_write_guest_page(kvm, identity_map_pfn,
-				&tmp, i * sizeof(tmp), sizeof(tmp));
-		if (r < 0)
-			goto out;
-	}
-	kvm_vmx->ept_identity_pagetable_done = true;
-
-out:
-	srcu_read_unlock(&kvm->srcu, idx);
-
-out2:
-	mutex_unlock(&kvm->slots_lock);
-	return r;
-}
-
-static void seg_setup(int seg)
-{
-	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
-	unsigned int ar;
-
-	vmcs_write16(sf->selector, 0);
-	vmcs_writel(sf->base, 0);
-	vmcs_write32(sf->limit, 0xffff);
-	ar = 0x93;
-	if (seg == VCPU_SREG_CS)
-		ar |= 0x08; /* code segment */
-
-	vmcs_write32(sf->ar_bytes, ar);
-}
-
-static int alloc_apic_access_page(struct kvm *kvm)
-{
-	struct page *page;
-	int r = 0;
-
-	mutex_lock(&kvm->slots_lock);
-	if (kvm->arch.apic_access_page_done)
-		goto out;
-	r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
-				    APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
-	if (r)
-		goto out;
-
-	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
-	if (is_error_page(page)) {
-		r = -EFAULT;
-		goto out;
-	}
-
-	/*
-	 * Do not pin the page in memory, so that memory hot-unplug
-	 * is able to migrate it.
-	 */
-	put_page(page);
-	kvm->arch.apic_access_page_done = true;
-out:
-	mutex_unlock(&kvm->slots_lock);
-	return r;
-}
-
-static int allocate_vpid(void)
-{
-	int vpid;
-
-	if (!enable_vpid)
-		return 0;
-	spin_lock(&vmx_vpid_lock);
-	vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
-	if (vpid < VMX_NR_VPIDS)
-		__set_bit(vpid, vmx_vpid_bitmap);
-	else
-		vpid = 0;
-	spin_unlock(&vmx_vpid_lock);
-	return vpid;
-}
-
-static void free_vpid(int vpid)
-{
-	if (!enable_vpid || vpid == 0)
-		return;
-	spin_lock(&vmx_vpid_lock);
-	__clear_bit(vpid, vmx_vpid_bitmap);
-	spin_unlock(&vmx_vpid_lock);
-}
-
-static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
-							  u32 msr, int type)
-{
-	int f = sizeof(unsigned long);
-
-	if (!cpu_has_vmx_msr_bitmap())
-		return;
-
-	if (static_branch_unlikely(&enable_evmcs))
-		evmcs_touch_msr_bitmap();
-
-	/*
-	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
-	 * have the write-low and read-high bitmap offsets the wrong way round.
-	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
-	 */
-	if (msr <= 0x1fff) {
-		if (type & MSR_TYPE_R)
-			/* read-low */
-			__clear_bit(msr, msr_bitmap + 0x000 / f);
-
-		if (type & MSR_TYPE_W)
-			/* write-low */
-			__clear_bit(msr, msr_bitmap + 0x800 / f);
-
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		if (type & MSR_TYPE_R)
-			/* read-high */
-			__clear_bit(msr, msr_bitmap + 0x400 / f);
-
-		if (type & MSR_TYPE_W)
-			/* write-high */
-			__clear_bit(msr, msr_bitmap + 0xc00 / f);
-
-	}
-}
-
-static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
-							 u32 msr, int type)
-{
-	int f = sizeof(unsigned long);
-
-	if (!cpu_has_vmx_msr_bitmap())
-		return;
-
-	if (static_branch_unlikely(&enable_evmcs))
-		evmcs_touch_msr_bitmap();
-
-	/*
-	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
-	 * have the write-low and read-high bitmap offsets the wrong way round.
-	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
-	 */
-	if (msr <= 0x1fff) {
-		if (type & MSR_TYPE_R)
-			/* read-low */
-			__set_bit(msr, msr_bitmap + 0x000 / f);
-
-		if (type & MSR_TYPE_W)
-			/* write-low */
-			__set_bit(msr, msr_bitmap + 0x800 / f);
-
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		if (type & MSR_TYPE_R)
-			/* read-high */
-			__set_bit(msr, msr_bitmap + 0x400 / f);
-
-		if (type & MSR_TYPE_W)
-			/* write-high */
-			__set_bit(msr, msr_bitmap + 0xc00 / f);
-
-	}
-}
-
-static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
-			     			      u32 msr, int type, bool value)
-{
-	if (value)
-		vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
-	else
-		vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
-}
-
-/*
- * If a msr is allowed by L0, we should check whether it is allowed by L1.
- * The corresponding bit will be cleared unless both of L0 and L1 allow it.
- */
-static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
-					       unsigned long *msr_bitmap_nested,
-					       u32 msr, int type)
-{
-	int f = sizeof(unsigned long);
-
-	/*
-	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
-	 * have the write-low and read-high bitmap offsets the wrong way round.
-	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
-	 */
-	if (msr <= 0x1fff) {
-		if (type & MSR_TYPE_R &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x000 / f))
-			/* read-low */
-			__clear_bit(msr, msr_bitmap_nested + 0x000 / f);
-
-		if (type & MSR_TYPE_W &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x800 / f))
-			/* write-low */
-			__clear_bit(msr, msr_bitmap_nested + 0x800 / f);
-
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		if (type & MSR_TYPE_R &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x400 / f))
-			/* read-high */
-			__clear_bit(msr, msr_bitmap_nested + 0x400 / f);
-
-		if (type & MSR_TYPE_W &&
-		   !test_bit(msr, msr_bitmap_l1 + 0xc00 / f))
-			/* write-high */
-			__clear_bit(msr, msr_bitmap_nested + 0xc00 / f);
-
-	}
-}
-
-static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
-{
-	u8 mode = 0;
-
-	if (cpu_has_secondary_exec_ctrls() &&
-	    (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
-	     SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
-		mode |= MSR_BITMAP_MODE_X2APIC;
-		if (enable_apicv && kvm_vcpu_apicv_active(vcpu))
-			mode |= MSR_BITMAP_MODE_X2APIC_APICV;
-	}
-
-	return mode;
-}
-
-#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
-
-static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
-					 u8 mode)
-{
-	int msr;
-
-	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-		unsigned word = msr / BITS_PER_LONG;
-		msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
-		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
-	}
-
-	if (mode & MSR_BITMAP_MODE_X2APIC) {
-		/*
-		 * TPR reads and writes can be virtualized even if virtual interrupt
-		 * delivery is not in use.
-		 */
-		vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
-		if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
-			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
-			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
-			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
-		}
-	}
-}
-
-static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
-	u8 mode = vmx_msr_bitmap_mode(vcpu);
-	u8 changed = mode ^ vmx->msr_bitmap_mode;
-
-	if (!changed)
-		return;
-
-	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
-		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
-
-	vmx->msr_bitmap_mode = mode;
-}
-
-static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
-{
-	return enable_apicv;
-}
-
-static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	gfn_t gfn;
-
-	/*
-	 * Don't need to mark the APIC access page dirty; it is never
-	 * written to by the CPU during APIC virtualization.
-	 */
-
-	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
-		gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
-		kvm_vcpu_mark_page_dirty(vcpu, gfn);
-	}
-
-	if (nested_cpu_has_posted_intr(vmcs12)) {
-		gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
-		kvm_vcpu_mark_page_dirty(vcpu, gfn);
-	}
-}
-
-
-static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int max_irr;
-	void *vapic_page;
-	u16 status;
-
-	if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
-		return;
-
-	vmx->nested.pi_pending = false;
-	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-		return;
-
-	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
-	if (max_irr != 256) {
-		vapic_page = kmap(vmx->nested.virtual_apic_page);
-		__kvm_apic_update_irr(vmx->nested.pi_desc->pir,
-			vapic_page, &max_irr);
-		kunmap(vmx->nested.virtual_apic_page);
-
-		status = vmcs_read16(GUEST_INTR_STATUS);
-		if ((u8)max_irr > ((u8)status & 0xff)) {
-			status &= ~0xff;
-			status |= (u8)max_irr;
-			vmcs_write16(GUEST_INTR_STATUS, status);
-		}
-	}
-
-	nested_mark_vmcs12_pages_dirty(vcpu);
-}
-
-static u8 vmx_get_rvi(void)
-{
-	return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
-}
-
-static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	void *vapic_page;
-	u32 vppr;
-	int rvi;
-
-	if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
-		!nested_cpu_has_vid(get_vmcs12(vcpu)) ||
-		WARN_ON_ONCE(!vmx->nested.virtual_apic_page))
-		return false;
-
-	rvi = vmx_get_rvi();
-
-	vapic_page = kmap(vmx->nested.virtual_apic_page);
-	vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
-	kunmap(vmx->nested.virtual_apic_page);
-
-	return ((rvi & 0xf0) > (vppr & 0xf0));
-}
-
-static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
-						     bool nested)
-{
-#ifdef CONFIG_SMP
-	int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
-
-	if (vcpu->mode == IN_GUEST_MODE) {
-		/*
-		 * The vector of interrupt to be delivered to vcpu had
-		 * been set in PIR before this function.
-		 *
-		 * Following cases will be reached in this block, and
-		 * we always send a notification event in all cases as
-		 * explained below.
-		 *
-		 * Case 1: vcpu keeps in non-root mode. Sending a
-		 * notification event posts the interrupt to vcpu.
-		 *
-		 * Case 2: vcpu exits to root mode and is still
-		 * runnable. PIR will be synced to vIRR before the
-		 * next vcpu entry. Sending a notification event in
-		 * this case has no effect, as vcpu is not in root
-		 * mode.
-		 *
-		 * Case 3: vcpu exits to root mode and is blocked.
-		 * vcpu_block() has already synced PIR to vIRR and
-		 * never blocks vcpu if vIRR is not cleared. Therefore,
-		 * a blocked vcpu here does not wait for any requested
-		 * interrupts in PIR, and sending a notification event
-		 * which has no effect is safe here.
-		 */
-
-		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
-		return true;
-	}
-#endif
-	return false;
-}
-
-static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
-						int vector)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (is_guest_mode(vcpu) &&
-	    vector == vmx->nested.posted_intr_nv) {
-		/*
-		 * If a posted intr is not recognized by hardware,
-		 * we will accomplish it in the next vmentry.
-		 */
-		vmx->nested.pi_pending = true;
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
-		/* the PIR and ON have been set by L1. */
-		if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))
-			kvm_vcpu_kick(vcpu);
-		return 0;
-	}
-	return -1;
-}
-/*
- * Send interrupt to vcpu via posted interrupt way.
- * 1. If target vcpu is running(non-root mode), send posted interrupt
- * notification to vcpu and hardware will sync PIR to vIRR atomically.
- * 2. If target vcpu isn't running(root mode), kick it to pick up the
- * interrupt from PIR in next vmentry.
- */
-static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int r;
-
-	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
-	if (!r)
-		return;
-
-	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
-		return;
-
-	/* If a previous notification has sent the IPI, nothing to do.  */
-	if (pi_test_and_set_on(&vmx->pi_desc))
-		return;
-
-	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
-		kvm_vcpu_kick(vcpu);
-}
-
-/*
- * Set up the vmcs's constant host-state fields, i.e., host-state fields that
- * will not change in the lifetime of the guest.
- * Note that host-state that does change is set elsewhere. E.g., host-state
- * that is set differently for each CPU is set in vmx_vcpu_load(), not here.
- */
-static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
-{
-	u32 low32, high32;
-	unsigned long tmpl;
-	struct desc_ptr dt;
-	unsigned long cr0, cr3, cr4;
-
-	cr0 = read_cr0();
-	WARN_ON(cr0 & X86_CR0_TS);
-	vmcs_writel(HOST_CR0, cr0);  /* 22.2.3 */
-
-	/*
-	 * Save the most likely value for this task's CR3 in the VMCS.
-	 * We can't use __get_current_cr3_fast() because we're not atomic.
-	 */
-	cr3 = __read_cr3();
-	vmcs_writel(HOST_CR3, cr3);		/* 22.2.3  FIXME: shadow tables */
-	vmx->loaded_vmcs->host_state.cr3 = cr3;
-
-	/* Save the most likely value for this task's CR4 in the VMCS. */
-	cr4 = cr4_read_shadow();
-	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
-	vmx->loaded_vmcs->host_state.cr4 = cr4;
-
-	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
-#ifdef CONFIG_X86_64
-	/*
-	 * Load null selectors, so we can avoid reloading them in
-	 * vmx_prepare_switch_to_host(), in case userspace uses
-	 * the null selectors too (the expected case).
-	 */
-	vmcs_write16(HOST_DS_SELECTOR, 0);
-	vmcs_write16(HOST_ES_SELECTOR, 0);
-#else
-	vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
-	vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
-#endif
-	vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
-	vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8);  /* 22.2.4 */
-
-	store_idt(&dt);
-	vmcs_writel(HOST_IDTR_BASE, dt.address);   /* 22.2.4 */
-	vmx->host_idt_base = dt.address;
-
-	vmcs_writel(HOST_RIP, vmx_return); /* 22.2.5 */
-
-	rdmsr(MSR_IA32_SYSENTER_CS, low32, high32);
-	vmcs_write32(HOST_IA32_SYSENTER_CS, low32);
-	rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl);
-	vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl);   /* 22.2.3 */
-
-	if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
-		rdmsr(MSR_IA32_CR_PAT, low32, high32);
-		vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32));
-	}
-}
-
-static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
-{
-	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
-	if (enable_ept)
-		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
-	if (is_guest_mode(&vmx->vcpu))
-		vmx->vcpu.arch.cr4_guest_owned_bits &=
-			~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask;
-	vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits);
-}
-
-static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
-{
-	u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl;
-
-	if (!kvm_vcpu_apicv_active(&vmx->vcpu))
-		pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
-
-	if (!enable_vnmi)
-		pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS;
-
-	/* Enable the preemption timer dynamically */
-	pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
-	return pin_based_exec_ctrl;
-}
-
-static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
-	if (cpu_has_secondary_exec_ctrls()) {
-		if (kvm_vcpu_apicv_active(vcpu))
-			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
-				      SECONDARY_EXEC_APIC_REGISTER_VIRT |
-				      SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
-		else
-			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
-					SECONDARY_EXEC_APIC_REGISTER_VIRT |
-					SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
-	}
-
-	if (cpu_has_vmx_msr_bitmap())
-		vmx_update_msr_bitmap(vcpu);
-}
-
-static u32 vmx_exec_control(struct vcpu_vmx *vmx)
-{
-	u32 exec_control = vmcs_config.cpu_based_exec_ctrl;
-
-	if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)
-		exec_control &= ~CPU_BASED_MOV_DR_EXITING;
-
-	if (!cpu_need_tpr_shadow(&vmx->vcpu)) {
-		exec_control &= ~CPU_BASED_TPR_SHADOW;
-#ifdef CONFIG_X86_64
-		exec_control |= CPU_BASED_CR8_STORE_EXITING |
-				CPU_BASED_CR8_LOAD_EXITING;
-#endif
-	}
-	if (!enable_ept)
-		exec_control |= CPU_BASED_CR3_STORE_EXITING |
-				CPU_BASED_CR3_LOAD_EXITING  |
-				CPU_BASED_INVLPG_EXITING;
-	if (kvm_mwait_in_guest(vmx->vcpu.kvm))
-		exec_control &= ~(CPU_BASED_MWAIT_EXITING |
-				CPU_BASED_MONITOR_EXITING);
-	if (kvm_hlt_in_guest(vmx->vcpu.kvm))
-		exec_control &= ~CPU_BASED_HLT_EXITING;
-	return exec_control;
-}
-
-static bool vmx_rdrand_supported(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_RDRAND_EXITING;
-}
-
-static bool vmx_rdseed_supported(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_RDSEED_EXITING;
-}
-
-static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
-{
-	struct kvm_vcpu *vcpu = &vmx->vcpu;
-
-	u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
-
-	if (!cpu_need_virtualize_apic_accesses(vcpu))
-		exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-	if (vmx->vpid == 0)
-		exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
-	if (!enable_ept) {
-		exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
-		enable_unrestricted_guest = 0;
-	}
-	if (!enable_unrestricted_guest)
-		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
-	if (kvm_pause_in_guest(vmx->vcpu.kvm))
-		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
-	if (!kvm_vcpu_apicv_active(vcpu))
-		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
-				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
-	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
-
-	/* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP,
-	 * in vmx_set_cr4.  */
-	exec_control &= ~SECONDARY_EXEC_DESC;
-
-	/* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD
-	   (handle_vmptrld).
-	   We can NOT enable shadow_vmcs here because we don't have yet
-	   a current VMCS12
-	*/
-	exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
-
-	if (!enable_pml)
-		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
-
-	if (vmx_xsaves_supported()) {
-		/* Exposing XSAVES only when XSAVE is exposed */
-		bool xsaves_enabled =
-			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
-
-		if (!xsaves_enabled)
-			exec_control &= ~SECONDARY_EXEC_XSAVES;
-
-		if (nested) {
-			if (xsaves_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_XSAVES;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_XSAVES;
-		}
-	}
-
-	if (vmx_rdtscp_supported()) {
-		bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP);
-		if (!rdtscp_enabled)
-			exec_control &= ~SECONDARY_EXEC_RDTSCP;
-
-		if (nested) {
-			if (rdtscp_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_RDTSCP;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_RDTSCP;
-		}
-	}
-
-	if (vmx_invpcid_supported()) {
-		/* Exposing INVPCID only when PCID is exposed */
-		bool invpcid_enabled =
-			guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) &&
-			guest_cpuid_has(vcpu, X86_FEATURE_PCID);
-
-		if (!invpcid_enabled) {
-			exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
-			guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID);
-		}
-
-		if (nested) {
-			if (invpcid_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_ENABLE_INVPCID;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_ENABLE_INVPCID;
-		}
-	}
-
-	if (vmx_rdrand_supported()) {
-		bool rdrand_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDRAND);
-		if (rdrand_enabled)
-			exec_control &= ~SECONDARY_EXEC_RDRAND_EXITING;
-
-		if (nested) {
-			if (rdrand_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_RDRAND_EXITING;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_RDRAND_EXITING;
-		}
-	}
-
-	if (vmx_rdseed_supported()) {
-		bool rdseed_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDSEED);
-		if (rdseed_enabled)
-			exec_control &= ~SECONDARY_EXEC_RDSEED_EXITING;
-
-		if (nested) {
-			if (rdseed_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_RDSEED_EXITING;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_RDSEED_EXITING;
-		}
-	}
-
-	vmx->secondary_exec_control = exec_control;
-}
-
-static void ept_set_mmio_spte_mask(void)
-{
-	/*
-	 * EPT Misconfigurations can be generated if the value of bits 2:0
-	 * of an EPT paging-structure entry is 110b (write/execute).
-	 */
-	kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK,
-				   VMX_EPT_MISCONFIG_WX_VALUE);
-}
-
-#define VMX_XSS_EXIT_BITMAP 0
-/*
- * Sets up the vmcs for emulated real mode.
- */
-static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
-{
-	int i;
-
-	if (enable_shadow_vmcs) {
-		/*
-		 * At vCPU creation, "VMWRITE to any supported field
-		 * in the VMCS" is supported, so use the more
-		 * permissive vmx_vmread_bitmap to specify both read
-		 * and write permissions for the shadow VMCS.
-		 */
-		vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
-		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmread_bitmap));
-	}
-	if (cpu_has_vmx_msr_bitmap())
-		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
-
-	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
-
-	/* Control */
-	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
-	vmx->hv_deadline_tsc = -1;
-
-	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));
-
-	if (cpu_has_secondary_exec_ctrls()) {
-		vmx_compute_secondary_exec_control(vmx);
-		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
-			     vmx->secondary_exec_control);
-	}
-
-	if (kvm_vcpu_apicv_active(&vmx->vcpu)) {
-		vmcs_write64(EOI_EXIT_BITMAP0, 0);
-		vmcs_write64(EOI_EXIT_BITMAP1, 0);
-		vmcs_write64(EOI_EXIT_BITMAP2, 0);
-		vmcs_write64(EOI_EXIT_BITMAP3, 0);
-
-		vmcs_write16(GUEST_INTR_STATUS, 0);
-
-		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
-		vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
-	}
-
-	if (!kvm_pause_in_guest(vmx->vcpu.kvm)) {
-		vmcs_write32(PLE_GAP, ple_gap);
-		vmx->ple_window = ple_window;
-		vmx->ple_window_dirty = true;
-	}
-
-	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
-	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
-	vmcs_write32(CR3_TARGET_COUNT, 0);           /* 22.2.1 */
-
-	vmcs_write16(HOST_FS_SELECTOR, 0);            /* 22.2.4 */
-	vmcs_write16(HOST_GS_SELECTOR, 0);            /* 22.2.4 */
-	vmx_set_constant_host_state(vmx);
-	vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */
-	vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */
-
-	if (cpu_has_vmx_vmfunc())
-		vmcs_write64(VM_FUNCTION_CONTROL, 0);
-
-	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
-
-	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
-		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
-
-	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
-		u32 index = vmx_msr_index[i];
-		u32 data_low, data_high;
-		int j = vmx->nmsrs;
-
-		if (rdmsr_safe(index, &data_low, &data_high) < 0)
-			continue;
-		if (wrmsr_safe(index, data_low, data_high) < 0)
-			continue;
-		vmx->guest_msrs[j].index = i;
-		vmx->guest_msrs[j].data = 0;
-		vmx->guest_msrs[j].mask = -1ull;
-		++vmx->nmsrs;
-	}
-
-	vmx->arch_capabilities = kvm_get_arch_capabilities();
-
-	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
-
-	/* 22.2.1, 20.8.1 */
-	vm_entry_controls_init(vmx, vmcs_config.vmentry_ctrl);
-
-	vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS;
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS);
-
-	set_cr4_guest_host_mask(vmx);
-
-	if (vmx_xsaves_supported())
-		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
-
-	if (enable_pml) {
-		ASSERT(vmx->pml_pg);
-		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-	}
-
-	if (cpu_has_vmx_encls_vmexit())
-		vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);
-}
-
-static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct msr_data apic_base_msr;
-	u64 cr0;
-
-	vmx->rmode.vm86_active = 0;
-	vmx->spec_ctrl = 0;
-
-	vcpu->arch.microcode_version = 0x100000000ULL;
-	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
-	kvm_set_cr8(vcpu, 0);
-
-	if (!init_event) {
-		apic_base_msr.data = APIC_DEFAULT_PHYS_BASE |
-				     MSR_IA32_APICBASE_ENABLE;
-		if (kvm_vcpu_is_reset_bsp(vcpu))
-			apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
-		apic_base_msr.host_initiated = true;
-		kvm_set_apic_base(vcpu, &apic_base_msr);
-	}
-
-	vmx_segment_cache_clear(vmx);
-
-	seg_setup(VCPU_SREG_CS);
-	vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
-	vmcs_writel(GUEST_CS_BASE, 0xffff0000ul);
-
-	seg_setup(VCPU_SREG_DS);
-	seg_setup(VCPU_SREG_ES);
-	seg_setup(VCPU_SREG_FS);
-	seg_setup(VCPU_SREG_GS);
-	seg_setup(VCPU_SREG_SS);
-
-	vmcs_write16(GUEST_TR_SELECTOR, 0);
-	vmcs_writel(GUEST_TR_BASE, 0);
-	vmcs_write32(GUEST_TR_LIMIT, 0xffff);
-	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
-
-	vmcs_write16(GUEST_LDTR_SELECTOR, 0);
-	vmcs_writel(GUEST_LDTR_BASE, 0);
-	vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
-	vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);
-
-	if (!init_event) {
-		vmcs_write32(GUEST_SYSENTER_CS, 0);
-		vmcs_writel(GUEST_SYSENTER_ESP, 0);
-		vmcs_writel(GUEST_SYSENTER_EIP, 0);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
-	}
-
-	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
-	kvm_rip_write(vcpu, 0xfff0);
-
-	vmcs_writel(GUEST_GDTR_BASE, 0);
-	vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);
-
-	vmcs_writel(GUEST_IDTR_BASE, 0);
-	vmcs_write32(GUEST_IDTR_LIMIT, 0xffff);
-
-	vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
-	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
-	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0);
-	if (kvm_mpx_supported())
-		vmcs_write64(GUEST_BNDCFGS, 0);
-
-	setup_msrs(vmx);
-
-	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);  /* 22.2.1 */
-
-	if (cpu_has_vmx_tpr_shadow() && !init_event) {
-		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
-		if (cpu_need_tpr_shadow(vcpu))
-			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
-				     __pa(vcpu->arch.apic->regs));
-		vmcs_write32(TPR_THRESHOLD, 0);
-	}
-
-	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
-
-	if (vmx->vpid != 0)
-		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
-
-	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
-	vmx->vcpu.arch.cr0 = cr0;
-	vmx_set_cr0(vcpu, cr0); /* enter rmode */
-	vmx_set_cr4(vcpu, 0);
-	vmx_set_efer(vcpu, 0);
-
-	update_exception_bitmap(vcpu);
-
-	vpid_sync_context(vmx->vpid);
-	if (init_event)
-		vmx_clear_hlt(vcpu);
-}
-
-/*
- * In nested virtualization, check if L1 asked to exit on external interrupts.
- * For most existing hypervisors, this will always return true.
- */
-static bool nested_exit_on_intr(struct kvm_vcpu *vcpu)
-{
-	return get_vmcs12(vcpu)->pin_based_vm_exec_control &
-		PIN_BASED_EXT_INTR_MASK;
-}
-
-/*
- * In nested virtualization, check if L1 has set
- * VM_EXIT_ACK_INTR_ON_EXIT
- */
-static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu)
-{
-	return get_vmcs12(vcpu)->vm_exit_controls &
-		VM_EXIT_ACK_INTR_ON_EXIT;
-}
-
-static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
-{
-	return nested_cpu_has_nmi_exiting(get_vmcs12(vcpu));
-}
-
-static void enable_irq_window(struct kvm_vcpu *vcpu)
-{
-	vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL,
-		      CPU_BASED_VIRTUAL_INTR_PENDING);
-}
-
-static void enable_nmi_window(struct kvm_vcpu *vcpu)
-{
-	if (!enable_vnmi ||
-	    vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
-		enable_irq_window(vcpu);
-		return;
-	}
-
-	vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL,
-		      CPU_BASED_VIRTUAL_NMI_PENDING);
-}
-
-static void vmx_inject_irq(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	uint32_t intr;
-	int irq = vcpu->arch.interrupt.nr;
-
-	trace_kvm_inj_virq(irq);
-
-	++vcpu->stat.irq_injections;
-	if (vmx->rmode.vm86_active) {
-		int inc_eip = 0;
-		if (vcpu->arch.interrupt.soft)
-			inc_eip = vcpu->arch.event_exit_inst_len;
-		if (kvm_inject_realmode_interrupt(vcpu, irq, inc_eip) != EMULATE_DONE)
-			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		return;
-	}
-	intr = irq | INTR_INFO_VALID_MASK;
-	if (vcpu->arch.interrupt.soft) {
-		intr |= INTR_TYPE_SOFT_INTR;
-		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
-			     vmx->vcpu.arch.event_exit_inst_len);
-	} else
-		intr |= INTR_TYPE_EXT_INTR;
-	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr);
-
-	vmx_clear_hlt(vcpu);
-}
-
-static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (!enable_vnmi) {
-		/*
-		 * Tracking the NMI-blocked state in software is built upon
-		 * finding the next open IRQ window. This, in turn, depends on
-		 * well-behaving guests: They have to keep IRQs disabled at
-		 * least as long as the NMI handler runs. Otherwise we may
-		 * cause NMI nesting, maybe breaking the guest. But as this is
-		 * highly unlikely, we can live with the residual risk.
-		 */
-		vmx->loaded_vmcs->soft_vnmi_blocked = 1;
-		vmx->loaded_vmcs->vnmi_blocked_time = 0;
-	}
-
-	++vcpu->stat.nmi_injections;
-	vmx->loaded_vmcs->nmi_known_unmasked = false;
-
-	if (vmx->rmode.vm86_active) {
-		if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE)
-			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		return;
-	}
-
-	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
-			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
-
-	vmx_clear_hlt(vcpu);
-}
-
-static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	bool masked;
-
-	if (!enable_vnmi)
-		return vmx->loaded_vmcs->soft_vnmi_blocked;
-	if (vmx->loaded_vmcs->nmi_known_unmasked)
-		return false;
-	masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
-	vmx->loaded_vmcs->nmi_known_unmasked = !masked;
-	return masked;
-}
-
-static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (!enable_vnmi) {
-		if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) {
-			vmx->loaded_vmcs->soft_vnmi_blocked = masked;
-			vmx->loaded_vmcs->vnmi_blocked_time = 0;
-		}
-	} else {
-		vmx->loaded_vmcs->nmi_known_unmasked = !masked;
-		if (masked)
-			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
-				      GUEST_INTR_STATE_NMI);
-		else
-			vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
-					GUEST_INTR_STATE_NMI);
-	}
-}
-
-static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
-{
-	if (to_vmx(vcpu)->nested.nested_run_pending)
-		return 0;
-
-	if (!enable_vnmi &&
-	    to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked)
-		return 0;
-
-	return	!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
-		  (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI
-		   | GUEST_INTR_STATE_NMI));
-}
-
-static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
-{
-	return (!to_vmx(vcpu)->nested.nested_run_pending &&
-		vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
-		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
-			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
-}
-
-static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
-{
-	int ret;
-
-	if (enable_unrestricted_guest)
-		return 0;
-
-	ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr,
-				    PAGE_SIZE * 3);
-	if (ret)
-		return ret;
-	to_kvm_vmx(kvm)->tss_addr = addr;
-	return init_rmode_tss(kvm);
-}
-
-static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
-{
-	to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr;
-	return 0;
-}
-
-static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
-{
-	switch (vec) {
-	case BP_VECTOR:
-		/*
-		 * Update instruction length as we may reinject the exception
-		 * from user space while in guest debugging mode.
-		 */
-		to_vmx(vcpu)->vcpu.arch.event_exit_inst_len =
-			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
-			return false;
-		/* fall through */
-	case DB_VECTOR:
-		if (vcpu->guest_debug &
-			(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
-			return false;
-		/* fall through */
-	case DE_VECTOR:
-	case OF_VECTOR:
-	case BR_VECTOR:
-	case UD_VECTOR:
-	case DF_VECTOR:
-	case SS_VECTOR:
-	case GP_VECTOR:
-	case MF_VECTOR:
-		return true;
-	break;
-	}
-	return false;
-}
-
-static int handle_rmode_exception(struct kvm_vcpu *vcpu,
-				  int vec, u32 err_code)
-{
-	/*
-	 * Instruction with address size override prefix opcode 0x67
-	 * Cause the #SS fault with 0 error code in VM86 mode.
-	 */
-	if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) {
-		if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) {
-			if (vcpu->arch.halt_request) {
-				vcpu->arch.halt_request = 0;
-				return kvm_vcpu_halt(vcpu);
-			}
-			return 1;
-		}
-		return 0;
-	}
-
-	/*
-	 * Forward all other exceptions that are valid in real mode.
-	 * FIXME: Breaks guest debugging in real mode, needs to be fixed with
-	 *        the required debugging infrastructure rework.
-	 */
-	kvm_queue_exception(vcpu, vec);
-	return 1;
-}
-
-/*
- * Trigger machine check on the host. We assume all the MSRs are already set up
- * by the CPU and that we still run on the same CPU as the MCE occurred on.
- * We pass a fake environment to the machine check handler because we want
- * the guest to be always treated like user space, no matter what context
- * it used internally.
- */
-static void kvm_machine_check(void)
-{
-#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
-	struct pt_regs regs = {
-		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
-		.flags = X86_EFLAGS_IF,
-	};
-
-	do_machine_check(&regs, 0);
-#endif
-}
-
-static int handle_machine_check(struct kvm_vcpu *vcpu)
-{
-	/* already handled by vcpu_run */
-	return 1;
-}
-
-static int handle_exception(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_run *kvm_run = vcpu->run;
-	u32 intr_info, ex_no, error_code;
-	unsigned long cr2, rip, dr6;
-	u32 vect_info;
-	enum emulation_result er;
-
-	vect_info = vmx->idt_vectoring_info;
-	intr_info = vmx->exit_intr_info;
-
-	if (is_machine_check(intr_info))
-		return handle_machine_check(vcpu);
-
-	if (is_nmi(intr_info))
-		return 1;  /* already handled by vmx_vcpu_run() */
-
-	if (is_invalid_opcode(intr_info))
-		return handle_ud(vcpu);
-
-	error_code = 0;
-	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
-		error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
-
-	if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) {
-		WARN_ON_ONCE(!enable_vmware_backdoor);
-		er = kvm_emulate_instruction(vcpu,
-			EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL);
-		if (er == EMULATE_USER_EXIT)
-			return 0;
-		else if (er != EMULATE_DONE)
-			kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
-		return 1;
-	}
-
-	/*
-	 * The #PF with PFEC.RSVD = 1 indicates the guest is accessing
-	 * MMIO, it is better to report an internal error.
-	 * See the comments in vmx_handle_exit.
-	 */
-	if ((vect_info & VECTORING_INFO_VALID_MASK) &&
-	    !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) {
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX;
-		vcpu->run->internal.ndata = 3;
-		vcpu->run->internal.data[0] = vect_info;
-		vcpu->run->internal.data[1] = intr_info;
-		vcpu->run->internal.data[2] = error_code;
-		return 0;
-	}
-
-	if (is_page_fault(intr_info)) {
-		cr2 = vmcs_readl(EXIT_QUALIFICATION);
-		/* EPT won't cause page fault directly */
-		WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept);
-		return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0);
-	}
-
-	ex_no = intr_info & INTR_INFO_VECTOR_MASK;
-
-	if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no))
-		return handle_rmode_exception(vcpu, ex_no, error_code);
-
-	switch (ex_no) {
-	case AC_VECTOR:
-		kvm_queue_exception_e(vcpu, AC_VECTOR, error_code);
-		return 1;
-	case DB_VECTOR:
-		dr6 = vmcs_readl(EXIT_QUALIFICATION);
-		if (!(vcpu->guest_debug &
-		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
-			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= dr6 | DR6_RTM;
-			if (is_icebp(intr_info))
-				skip_emulated_instruction(vcpu);
-
-			kvm_queue_exception(vcpu, DB_VECTOR);
-			return 1;
-		}
-		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
-		kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
-		/* fall through */
-	case BP_VECTOR:
-		/*
-		 * Update instruction length as we may reinject #BP from
-		 * user space while in guest debugging mode. Reading it for
-		 * #DB as well causes no harm, it is not used in that case.
-		 */
-		vmx->vcpu.arch.event_exit_inst_len =
-			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
-		kvm_run->exit_reason = KVM_EXIT_DEBUG;
-		rip = kvm_rip_read(vcpu);
-		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
-		kvm_run->debug.arch.exception = ex_no;
-		break;
-	default:
-		kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
-		kvm_run->ex.exception = ex_no;
-		kvm_run->ex.error_code = error_code;
-		break;
-	}
-	return 0;
-}
-
-static int handle_external_interrupt(struct kvm_vcpu *vcpu)
-{
-	++vcpu->stat.irq_exits;
-	return 1;
-}
-
-static int handle_triple_fault(struct kvm_vcpu *vcpu)
-{
-	vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
-	vcpu->mmio_needed = 0;
-	return 0;
-}
-
-static int handle_io(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qualification;
-	int size, in, string;
-	unsigned port;
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	string = (exit_qualification & 16) != 0;
-
-	++vcpu->stat.io_exits;
-
-	if (string)
-		return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
-
-	port = exit_qualification >> 16;
-	size = (exit_qualification & 7) + 1;
-	in = (exit_qualification & 8) != 0;
-
-	return kvm_fast_pio(vcpu, size, port, in);
-}
-
-static void
-vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
-{
-	/*
-	 * Patch in the VMCALL instruction:
-	 */
-	hypercall[0] = 0x0f;
-	hypercall[1] = 0x01;
-	hypercall[2] = 0xc1;
-}
-
-/* called to set cr0 as appropriate for a mov-to-cr0 exit. */
-static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	if (is_guest_mode(vcpu)) {
-		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-		unsigned long orig_val = val;
-
-		/*
-		 * We get here when L2 changed cr0 in a way that did not change
-		 * any of L1's shadowed bits (see nested_vmx_exit_handled_cr),
-		 * but did change L0 shadowed bits. So we first calculate the
-		 * effective cr0 value that L1 would like to write into the
-		 * hardware. It consists of the L2-owned bits from the new
-		 * value combined with the L1-owned bits from L1's guest_cr0.
-		 */
-		val = (val & ~vmcs12->cr0_guest_host_mask) |
-			(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask);
-
-		if (!nested_guest_cr0_valid(vcpu, val))
-			return 1;
-
-		if (kvm_set_cr0(vcpu, val))
-			return 1;
-		vmcs_writel(CR0_READ_SHADOW, orig_val);
-		return 0;
-	} else {
-		if (to_vmx(vcpu)->nested.vmxon &&
-		    !nested_host_cr0_valid(vcpu, val))
-			return 1;
-
-		return kvm_set_cr0(vcpu, val);
-	}
-}
-
-static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	if (is_guest_mode(vcpu)) {
-		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-		unsigned long orig_val = val;
-
-		/* analogously to handle_set_cr0 */
-		val = (val & ~vmcs12->cr4_guest_host_mask) |
-			(vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask);
-		if (kvm_set_cr4(vcpu, val))
-			return 1;
-		vmcs_writel(CR4_READ_SHADOW, orig_val);
-		return 0;
-	} else
-		return kvm_set_cr4(vcpu, val);
-}
-
-static int handle_desc(struct kvm_vcpu *vcpu)
-{
-	WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
-	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
-}
-
-static int handle_cr(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qualification, val;
-	int cr;
-	int reg;
-	int err;
-	int ret;
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	cr = exit_qualification & 15;
-	reg = (exit_qualification >> 8) & 15;
-	switch ((exit_qualification >> 4) & 3) {
-	case 0: /* mov to cr */
-		val = kvm_register_readl(vcpu, reg);
-		trace_kvm_cr_write(cr, val);
-		switch (cr) {
-		case 0:
-			err = handle_set_cr0(vcpu, val);
-			return kvm_complete_insn_gp(vcpu, err);
-		case 3:
-			WARN_ON_ONCE(enable_unrestricted_guest);
-			err = kvm_set_cr3(vcpu, val);
-			return kvm_complete_insn_gp(vcpu, err);
-		case 4:
-			err = handle_set_cr4(vcpu, val);
-			return kvm_complete_insn_gp(vcpu, err);
-		case 8: {
-				u8 cr8_prev = kvm_get_cr8(vcpu);
-				u8 cr8 = (u8)val;
-				err = kvm_set_cr8(vcpu, cr8);
-				ret = kvm_complete_insn_gp(vcpu, err);
-				if (lapic_in_kernel(vcpu))
-					return ret;
-				if (cr8_prev <= cr8)
-					return ret;
-				/*
-				 * TODO: we might be squashing a
-				 * KVM_GUESTDBG_SINGLESTEP-triggered
-				 * KVM_EXIT_DEBUG here.
-				 */
-				vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
-				return 0;
-			}
-		}
-		break;
-	case 2: /* clts */
-		WARN_ONCE(1, "Guest should always own CR0.TS");
-		vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
-		trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
-		return kvm_skip_emulated_instruction(vcpu);
-	case 1: /*mov from cr*/
-		switch (cr) {
-		case 3:
-			WARN_ON_ONCE(enable_unrestricted_guest);
-			val = kvm_read_cr3(vcpu);
-			kvm_register_write(vcpu, reg, val);
-			trace_kvm_cr_read(cr, val);
-			return kvm_skip_emulated_instruction(vcpu);
-		case 8:
-			val = kvm_get_cr8(vcpu);
-			kvm_register_write(vcpu, reg, val);
-			trace_kvm_cr_read(cr, val);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		break;
-	case 3: /* lmsw */
-		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
-		trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val);
-		kvm_lmsw(vcpu, val);
-
-		return kvm_skip_emulated_instruction(vcpu);
-	default:
-		break;
-	}
-	vcpu->run->exit_reason = 0;
-	vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n",
-	       (int)(exit_qualification >> 4) & 3, cr);
-	return 0;
-}
-
-static int handle_dr(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qualification;
-	int dr, dr7, reg;
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
-
-	/* First, if DR does not exist, trigger UD */
-	if (!kvm_require_dr(vcpu, dr))
-		return 1;
-
-	/* Do not handle if the CPL > 0, will trigger GP on re-entry */
-	if (!kvm_require_cpl(vcpu, 0))
-		return 1;
-	dr7 = vmcs_readl(GUEST_DR7);
-	if (dr7 & DR7_GD) {
-		/*
-		 * As the vm-exit takes precedence over the debug trap, we
-		 * need to emulate the latter, either for the host or the
-		 * guest debugging itself.
-		 */
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
-			vcpu->run->debug.arch.dr6 = vcpu->arch.dr6;
-			vcpu->run->debug.arch.dr7 = dr7;
-			vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu);
-			vcpu->run->debug.arch.exception = DB_VECTOR;
-			vcpu->run->exit_reason = KVM_EXIT_DEBUG;
-			return 0;
-		} else {
-			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= DR6_BD | DR6_RTM;
-			kvm_queue_exception(vcpu, DB_VECTOR);
-			return 1;
-		}
-	}
-
-	if (vcpu->guest_debug == 0) {
-		vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
-				CPU_BASED_MOV_DR_EXITING);
-
-		/*
-		 * No more DR vmexits; force a reload of the debug registers
-		 * and reenter on this instruction.  The next vmexit will
-		 * retrieve the full state of the debug registers.
-		 */
-		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT;
-		return 1;
-	}
-
-	reg = DEBUG_REG_ACCESS_REG(exit_qualification);
-	if (exit_qualification & TYPE_MOV_FROM_DR) {
-		unsigned long val;
-
-		if (kvm_get_dr(vcpu, dr, &val))
-			return 1;
-		kvm_register_write(vcpu, reg, val);
-	} else
-		if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg)))
-			return 1;
-
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static u64 vmx_get_dr6(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.dr6;
-}
-
-static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
-{
-}
-
-static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
-{
-	get_debugreg(vcpu->arch.db[0], 0);
-	get_debugreg(vcpu->arch.db[1], 1);
-	get_debugreg(vcpu->arch.db[2], 2);
-	get_debugreg(vcpu->arch.db[3], 3);
-	get_debugreg(vcpu->arch.dr6, 6);
-	vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
-
-	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
-	vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING);
-}
-
-static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	vmcs_writel(GUEST_DR7, val);
-}
-
-static int handle_cpuid(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_cpuid(vcpu);
-}
-
-static int handle_rdmsr(struct kvm_vcpu *vcpu)
-{
-	u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
-	struct msr_data msr_info;
-
-	msr_info.index = ecx;
-	msr_info.host_initiated = false;
-	if (vmx_get_msr(vcpu, &msr_info)) {
-		trace_kvm_msr_read_ex(ecx);
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
-	trace_kvm_msr_read(ecx, msr_info.data);
-
-	/* FIXME: handling of bits 32:63 of rax, rdx */
-	vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u;
-	vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u;
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int handle_wrmsr(struct kvm_vcpu *vcpu)
-{
-	struct msr_data msr;
-	u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
-	u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
-		| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);
-
-	msr.data = data;
-	msr.index = ecx;
-	msr.host_initiated = false;
-	if (kvm_set_msr(vcpu, &msr) != 0) {
-		trace_kvm_msr_write_ex(ecx, data);
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
-	trace_kvm_msr_write(ecx, data);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
-{
-	kvm_apic_update_ppr(vcpu);
-	return 1;
-}
-
-static int handle_interrupt_window(struct kvm_vcpu *vcpu)
-{
-	vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
-			CPU_BASED_VIRTUAL_INTR_PENDING);
-
-	kvm_make_request(KVM_REQ_EVENT, vcpu);
-
-	++vcpu->stat.irq_window_exits;
-	return 1;
-}
-
-static int handle_halt(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_halt(vcpu);
-}
-
-static int handle_vmcall(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_hypercall(vcpu);
-}
-
-static int handle_invd(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
-}
-
-static int handle_invlpg(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	kvm_mmu_invlpg(vcpu, exit_qualification);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int handle_rdpmc(struct kvm_vcpu *vcpu)
-{
-	int err;
-
-	err = kvm_rdpmc(vcpu);
-	return kvm_complete_insn_gp(vcpu, err);
-}
-
-static int handle_wbinvd(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_wbinvd(vcpu);
-}
-
-static int handle_xsetbv(struct kvm_vcpu *vcpu)
-{
-	u64 new_bv = kvm_read_edx_eax(vcpu);
-	u32 index = kvm_register_read(vcpu, VCPU_REGS_RCX);
-
-	if (kvm_set_xcr(vcpu, index, new_bv) == 0)
-		return kvm_skip_emulated_instruction(vcpu);
-	return 1;
-}
-
-static int handle_xsaves(struct kvm_vcpu *vcpu)
-{
-	kvm_skip_emulated_instruction(vcpu);
-	WARN(1, "this should never happen\n");
-	return 1;
-}
-
-static int handle_xrstors(struct kvm_vcpu *vcpu)
-{
-	kvm_skip_emulated_instruction(vcpu);
-	WARN(1, "this should never happen\n");
-	return 1;
-}
-
-static int handle_apic_access(struct kvm_vcpu *vcpu)
-{
-	if (likely(fasteoi)) {
-		unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-		int access_type, offset;
-
-		access_type = exit_qualification & APIC_ACCESS_TYPE;
-		offset = exit_qualification & APIC_ACCESS_OFFSET;
-		/*
-		 * Sane guest uses MOV to write EOI, with written value
-		 * not cared. So make a short-circuit here by avoiding
-		 * heavy instruction emulation.
-		 */
-		if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) &&
-		    (offset == APIC_EOI)) {
-			kvm_lapic_set_eoi(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-	}
-	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
-}
-
-static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	int vector = exit_qualification & 0xff;
-
-	/* EOI-induced VM exit is trap-like and thus no need to adjust IP */
-	kvm_apic_set_eoi_accelerated(vcpu, vector);
-	return 1;
-}
-
-static int handle_apic_write(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 offset = exit_qualification & 0xfff;
-
-	/* APIC-write VM exit is trap-like and thus no need to adjust IP */
-	kvm_apic_write_nodecode(vcpu, offset);
-	return 1;
-}
-
-static int handle_task_switch(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long exit_qualification;
-	bool has_error_code = false;
-	u32 error_code = 0;
-	u16 tss_selector;
-	int reason, type, idt_v, idt_index;
-
-	idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK);
-	idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK);
-	type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK);
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	reason = (u32)exit_qualification >> 30;
-	if (reason == TASK_SWITCH_GATE && idt_v) {
-		switch (type) {
-		case INTR_TYPE_NMI_INTR:
-			vcpu->arch.nmi_injected = false;
-			vmx_set_nmi_mask(vcpu, true);
-			break;
-		case INTR_TYPE_EXT_INTR:
-		case INTR_TYPE_SOFT_INTR:
-			kvm_clear_interrupt_queue(vcpu);
-			break;
-		case INTR_TYPE_HARD_EXCEPTION:
-			if (vmx->idt_vectoring_info &
-			    VECTORING_INFO_DELIVER_CODE_MASK) {
-				has_error_code = true;
-				error_code =
-					vmcs_read32(IDT_VECTORING_ERROR_CODE);
-			}
-			/* fall through */
-		case INTR_TYPE_SOFT_EXCEPTION:
-			kvm_clear_exception_queue(vcpu);
-			break;
-		default:
-			break;
-		}
-	}
-	tss_selector = exit_qualification;
-
-	if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION &&
-		       type != INTR_TYPE_EXT_INTR &&
-		       type != INTR_TYPE_NMI_INTR))
-		skip_emulated_instruction(vcpu);
-
-	if (kvm_task_switch(vcpu, tss_selector,
-			    type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason,
-			    has_error_code, error_code) == EMULATE_FAIL) {
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
-		return 0;
-	}
-
-	/*
-	 * TODO: What about debug traps on tss switch?
-	 *       Are we supposed to inject them and update dr6?
-	 */
-
-	return 1;
-}
-
-static int handle_ept_violation(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qualification;
-	gpa_t gpa;
-	u64 error_code;
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	/*
-	 * EPT violation happened while executing iret from NMI,
-	 * "blocked by NMI" bit has to be set before next VM entry.
-	 * There are errata that may cause this bit to not be set:
-	 * AAK134, BY25.
-	 */
-	if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
-			enable_vnmi &&
-			(exit_qualification & INTR_INFO_UNBLOCK_NMI))
-		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
-
-	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
-	trace_kvm_page_fault(gpa, exit_qualification);
-
-	/* Is it a read fault? */
-	error_code = (exit_qualification & EPT_VIOLATION_ACC_READ)
-		     ? PFERR_USER_MASK : 0;
-	/* Is it a write fault? */
-	error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE)
-		      ? PFERR_WRITE_MASK : 0;
-	/* Is it a fetch fault? */
-	error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
-		      ? PFERR_FETCH_MASK : 0;
-	/* ept page table entry is present? */
-	error_code |= (exit_qualification &
-		       (EPT_VIOLATION_READABLE | EPT_VIOLATION_WRITABLE |
-			EPT_VIOLATION_EXECUTABLE))
-		      ? PFERR_PRESENT_MASK : 0;
-
-	error_code |= (exit_qualification & 0x100) != 0 ?
-	       PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
-
-	vcpu->arch.exit_qualification = exit_qualification;
-	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
-}
-
-static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
-{
-	gpa_t gpa;
-
-	/*
-	 * A nested guest cannot optimize MMIO vmexits, because we have an
-	 * nGPA here instead of the required GPA.
-	 */
-	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
-	if (!is_guest_mode(vcpu) &&
-	    !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
-		trace_kvm_fast_mmio(gpa);
-		/*
-		 * Doing kvm_skip_emulated_instruction() depends on undefined
-		 * behavior: Intel's manual doesn't mandate
-		 * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG
-		 * occurs and while on real hardware it was observed to be set,
-		 * other hypervisors (namely Hyper-V) don't set it, we end up
-		 * advancing IP with some random value. Disable fast mmio when
-		 * running nested and keep it for real hardware in hope that
-		 * VM_EXIT_INSTRUCTION_LEN will always be set correctly.
-		 */
-		if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
-			return kvm_skip_emulated_instruction(vcpu);
-		else
-			return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) ==
-								EMULATE_DONE;
-	}
-
-	return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
-}
-
-static int handle_nmi_window(struct kvm_vcpu *vcpu)
-{
-	WARN_ON_ONCE(!enable_vnmi);
-	vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
-			CPU_BASED_VIRTUAL_NMI_PENDING);
-	++vcpu->stat.nmi_window_exits;
-	kvm_make_request(KVM_REQ_EVENT, vcpu);
-
-	return 1;
-}
-
-static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	enum emulation_result err = EMULATE_DONE;
-	int ret = 1;
-	u32 cpu_exec_ctrl;
-	bool intr_window_requested;
-	unsigned count = 130;
-
-	/*
-	 * We should never reach the point where we are emulating L2
-	 * due to invalid guest state as that means we incorrectly
-	 * allowed a nested VMEntry with an invalid vmcs12.
-	 */
-	WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending);
-
-	cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
-	intr_window_requested = cpu_exec_ctrl & CPU_BASED_VIRTUAL_INTR_PENDING;
-
-	while (vmx->emulation_required && count-- != 0) {
-		if (intr_window_requested && vmx_interrupt_allowed(vcpu))
-			return handle_interrupt_window(&vmx->vcpu);
-
-		if (kvm_test_request(KVM_REQ_EVENT, vcpu))
-			return 1;
-
-		err = kvm_emulate_instruction(vcpu, 0);
-
-		if (err == EMULATE_USER_EXIT) {
-			++vcpu->stat.mmio_exits;
-			ret = 0;
-			goto out;
-		}
-
-		if (err != EMULATE_DONE)
-			goto emulation_error;
-
-		if (vmx->emulation_required && !vmx->rmode.vm86_active &&
-		    vcpu->arch.exception.pending)
-			goto emulation_error;
-
-		if (vcpu->arch.halt_request) {
-			vcpu->arch.halt_request = 0;
-			ret = kvm_vcpu_halt(vcpu);
-			goto out;
-		}
-
-		if (signal_pending(current))
-			goto out;
-		if (need_resched())
-			schedule();
-	}
-
-out:
-	return ret;
-
-emulation_error:
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-	vcpu->run->internal.ndata = 0;
-	return 0;
-}
-
-static void grow_ple_window(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int old = vmx->ple_window;
-
-	vmx->ple_window = __grow_ple_window(old, ple_window,
-					    ple_window_grow,
-					    ple_window_max);
-
-	if (vmx->ple_window != old)
-		vmx->ple_window_dirty = true;
-
-	trace_kvm_ple_window_grow(vcpu->vcpu_id, vmx->ple_window, old);
-}
-
-static void shrink_ple_window(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int old = vmx->ple_window;
-
-	vmx->ple_window = __shrink_ple_window(old, ple_window,
-					      ple_window_shrink,
-					      ple_window);
-
-	if (vmx->ple_window != old)
-		vmx->ple_window_dirty = true;
-
-	trace_kvm_ple_window_shrink(vcpu->vcpu_id, vmx->ple_window, old);
-}
-
-/*
- * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
- */
-static void wakeup_handler(void)
-{
-	struct kvm_vcpu *vcpu;
-	int cpu = smp_processor_id();
-
-	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-	list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
-			blocked_vcpu_list) {
-		struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-		if (pi_test_on(pi_desc) == 1)
-			kvm_vcpu_kick(vcpu);
-	}
-	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-}
-
-static void vmx_enable_tdp(void)
-{
-	kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK,
-		enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull,
-		enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull,
-		0ull, VMX_EPT_EXECUTABLE_MASK,
-		cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK,
-		VMX_EPT_RWX_MASK, 0ull);
-
-	ept_set_mmio_spte_mask();
-	kvm_enable_tdp();
-}
-
-static __init int hardware_setup(void)
-{
-	unsigned long host_bndcfgs;
-	int r = -ENOMEM, i;
-
-	rdmsrl_safe(MSR_EFER, &host_efer);
-
-	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)
-		kvm_define_shared_msr(i, vmx_msr_index[i]);
-
-	for (i = 0; i < VMX_BITMAP_NR; i++) {
-		vmx_bitmap[i] = (unsigned long *)__get_free_page(GFP_KERNEL);
-		if (!vmx_bitmap[i])
-			goto out;
-	}
-
-	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
-	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
-
-	if (setup_vmcs_config(&vmcs_config) < 0) {
-		r = -EIO;
-		goto out;
-	}
-
-	if (boot_cpu_has(X86_FEATURE_NX))
-		kvm_enable_efer_bits(EFER_NX);
-
-	if (boot_cpu_has(X86_FEATURE_MPX)) {
-		rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs);
-		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
-	}
-
-	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_ept() ||
-	    !cpu_has_vmx_ept_4levels() ||
-	    !cpu_has_vmx_ept_mt_wb() ||
-	    !cpu_has_vmx_invept_global())
-		enable_ept = 0;
-
-	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
-		enable_ept_ad_bits = 0;
-
-	if (!cpu_has_vmx_unrestricted_guest() || !enable_ept)
-		enable_unrestricted_guest = 0;
-
-	if (!cpu_has_vmx_flexpriority())
-		flexpriority_enabled = 0;
-
-	if (!cpu_has_virtual_nmis())
-		enable_vnmi = 0;
-
-	/*
-	 * set_apic_access_page_addr() is used to reload apic access
-	 * page upon invalidation.  No need to do anything if not
-	 * using the APIC_ACCESS_ADDR VMCS field.
-	 */
-	if (!flexpriority_enabled)
-		kvm_x86_ops->set_apic_access_page_addr = NULL;
-
-	if (!cpu_has_vmx_tpr_shadow())
-		kvm_x86_ops->update_cr8_intercept = NULL;
-
-	if (enable_ept && !cpu_has_vmx_ept_2m_page())
-		kvm_disable_largepages();
-
-#if IS_ENABLED(CONFIG_HYPERV)
-	if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH
-	    && enable_ept)
-		kvm_x86_ops->tlb_remote_flush = vmx_hv_remote_flush_tlb;
-#endif
-
-	if (!cpu_has_vmx_ple()) {
-		ple_gap = 0;
-		ple_window = 0;
-		ple_window_grow = 0;
-		ple_window_max = 0;
-		ple_window_shrink = 0;
-	}
-
-	if (!cpu_has_vmx_apicv()) {
-		enable_apicv = 0;
-		kvm_x86_ops->sync_pir_to_irr = NULL;
-	}
-
-	if (cpu_has_vmx_tsc_scaling()) {
-		kvm_has_tsc_control = true;
-		kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;
-		kvm_tsc_scaling_ratio_frac_bits = 48;
-	}
-
-	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
-
-	if (enable_ept)
-		vmx_enable_tdp();
-	else
-		kvm_disable_tdp();
-
-	if (!nested) {
-		kvm_x86_ops->get_nested_state = NULL;
-		kvm_x86_ops->set_nested_state = NULL;
-	}
-
-	/*
-	 * Only enable PML when hardware supports PML feature, and both EPT
-	 * and EPT A/D bit features are enabled -- PML depends on them to work.
-	 */
-	if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())
-		enable_pml = 0;
-
-	if (!enable_pml) {
-		kvm_x86_ops->slot_enable_log_dirty = NULL;
-		kvm_x86_ops->slot_disable_log_dirty = NULL;
-		kvm_x86_ops->flush_log_dirty = NULL;
-		kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
-	}
-
-	if (!cpu_has_vmx_preemption_timer())
-		kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit;
-
-	if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {
-		u64 vmx_msr;
-
-		rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
-		cpu_preemption_timer_multi =
-			 vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
-	} else {
-		kvm_x86_ops->set_hv_timer = NULL;
-		kvm_x86_ops->cancel_hv_timer = NULL;
-	}
-
-	if (!cpu_has_vmx_shadow_vmcs())
-		enable_shadow_vmcs = 0;
-	if (enable_shadow_vmcs)
-		init_vmcs_shadow_fields();
-
-	kvm_set_posted_intr_wakeup_handler(wakeup_handler);
-	nested_vmx_setup_ctls_msrs(&vmcs_config.nested, enable_apicv);
-
-	kvm_mce_cap_supported |= MCG_LMCE_P;
-
-	return alloc_kvm_area();
-
-out:
-	for (i = 0; i < VMX_BITMAP_NR; i++)
-		free_page((unsigned long)vmx_bitmap[i]);
-
-    return r;
-}
-
-static __exit void hardware_unsetup(void)
-{
-	int i;
-
-	for (i = 0; i < VMX_BITMAP_NR; i++)
-		free_page((unsigned long)vmx_bitmap[i]);
-
-	free_kvm_area();
-}
-
-/*
- * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
- * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
- */
-static int handle_pause(struct kvm_vcpu *vcpu)
-{
-	if (!kvm_pause_in_guest(vcpu->kvm))
-		grow_ple_window(vcpu);
-
-	/*
-	 * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting"
-	 * VM-execution control is ignored if CPL > 0. OTOH, KVM
-	 * never set PAUSE_EXITING and just set PLE if supported,
-	 * so the vcpu must be CPL=0 if it gets a PAUSE exit.
-	 */
-	kvm_vcpu_on_spin(vcpu, true);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int handle_nop(struct kvm_vcpu *vcpu)
-{
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int handle_mwait(struct kvm_vcpu *vcpu)
-{
-	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
-	return handle_nop(vcpu);
-}
-
-static int handle_invalid_op(struct kvm_vcpu *vcpu)
-{
-	kvm_queue_exception(vcpu, UD_VECTOR);
-	return 1;
-}
-
-static int handle_monitor_trap(struct kvm_vcpu *vcpu)
-{
-	return 1;
-}
-
-static int handle_monitor(struct kvm_vcpu *vcpu)
-{
-	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
-	return handle_nop(vcpu);
-}
-
-/*
- * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
- * set the success or error code of an emulated VMX instruction, as specified
- * by Vol 2B, VMX Instruction Reference, "Conventions".
- */
-static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
-{
-	vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
-			    X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
-}
-
-static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
-{
-	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
-			    X86_EFLAGS_SF | X86_EFLAGS_OF))
-			| X86_EFLAGS_CF);
-}
-
-static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
-					u32 vm_instruction_error)
-{
-	if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
-		/*
-		 * failValid writes the error number to the current VMCS, which
-		 * can't be done there isn't a current VMCS.
-		 */
-		nested_vmx_failInvalid(vcpu);
-		return;
-	}
-	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
-			    X86_EFLAGS_SF | X86_EFLAGS_OF))
-			| X86_EFLAGS_ZF);
-	get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
-	/*
-	 * We don't need to force a shadow sync because
-	 * VM_INSTRUCTION_ERROR is not shadowed
-	 */
-}
-
-static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
-{
-	/* TODO: not to reset guest simply here. */
-	kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-	pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator);
-}
-
-static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
-{
-	struct vcpu_vmx *vmx =
-		container_of(timer, struct vcpu_vmx, nested.preemption_timer);
-
-	vmx->nested.preemption_timer_expired = true;
-	kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu);
-	kvm_vcpu_kick(&vmx->vcpu);
-
-	return HRTIMER_NORESTART;
-}
-
-/*
- * Decode the memory-address operand of a vmx instruction, as recorded on an
- * exit caused by such an instruction (run by a guest hypervisor).
- * On success, returns 0. When the operand is invalid, returns 1 and throws
- * #UD or #GP.
- */
-static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
-				 unsigned long exit_qualification,
-				 u32 vmx_instruction_info, bool wr, gva_t *ret)
-{
-	gva_t off;
-	bool exn;
-	struct kvm_segment s;
-
-	/*
-	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
-	 * Execution", on an exit, vmx_instruction_info holds most of the
-	 * addressing components of the operand. Only the displacement part
-	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
-	 * For how an actual address is calculated from all these components,
-	 * refer to Vol. 1, "Operand Addressing".
-	 */
-	int  scaling = vmx_instruction_info & 3;
-	int  addr_size = (vmx_instruction_info >> 7) & 7;
-	bool is_reg = vmx_instruction_info & (1u << 10);
-	int  seg_reg = (vmx_instruction_info >> 15) & 7;
-	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
-	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
-	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
-	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));
-
-	if (is_reg) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	/* Addr = segment_base + offset */
-	/* offset = base + [index * scale] + displacement */
-	off = exit_qualification; /* holds the displacement */
-	if (base_is_valid)
-		off += kvm_register_read(vcpu, base_reg);
-	if (index_is_valid)
-		off += kvm_register_read(vcpu, index_reg)<<scaling;
-	vmx_get_segment(vcpu, &s, seg_reg);
-	*ret = s.base + off;
-
-	if (addr_size == 1) /* 32 bit */
-		*ret &= 0xffffffff;
-
-	/* Checks for #GP/#SS exceptions. */
-	exn = false;
-	if (is_long_mode(vcpu)) {
-		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
-		 * non-canonical form. This is the only check on the memory
-		 * destination for long mode!
-		 */
-		exn = is_noncanonical_address(*ret, vcpu);
-	} else if (is_protmode(vcpu)) {
-		/* Protected mode: apply checks for segment validity in the
-		 * following order:
-		 * - segment type check (#GP(0) may be thrown)
-		 * - usability check (#GP(0)/#SS(0))
-		 * - limit check (#GP(0)/#SS(0))
-		 */
-		if (wr)
-			/* #GP(0) if the destination operand is located in a
-			 * read-only data segment or any code segment.
-			 */
-			exn = ((s.type & 0xa) == 0 || (s.type & 8));
-		else
-			/* #GP(0) if the source operand is located in an
-			 * execute-only code segment
-			 */
-			exn = ((s.type & 0xa) == 8);
-		if (exn) {
-			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
-			return 1;
-		}
-		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
-		 */
-		exn = (s.unusable != 0);
-		/* Protected mode: #GP(0)/#SS(0) if the memory
-		 * operand is outside the segment limit.
-		 */
-		exn = exn || (off + sizeof(u64) > s.limit);
-	}
-	if (exn) {
-		kvm_queue_exception_e(vcpu,
-				      seg_reg == VCPU_SREG_SS ?
-						SS_VECTOR : GP_VECTOR,
-				      0);
-		return 1;
-	}
-
-	return 0;
-}
-
-static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
-{
-	gva_t gva;
-	struct x86_exception e;
-
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
-		return 1;
-
-	if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	return 0;
-}
-
-/*
- * Allocate a shadow VMCS and associate it with the currently loaded
- * VMCS, unless such a shadow VMCS already exists. The newly allocated
- * VMCS is also VMCLEARed, so that it is ready for use.
- */
-static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs;
-
-	/*
-	 * We should allocate a shadow vmcs for vmcs01 only when L1
-	 * executes VMXON and free it when L1 executes VMXOFF.
-	 * As it is invalid to execute VMXON twice, we shouldn't reach
-	 * here when vmcs01 already have an allocated shadow vmcs.
-	 */
-	WARN_ON(loaded_vmcs == &vmx->vmcs01 && loaded_vmcs->shadow_vmcs);
-
-	if (!loaded_vmcs->shadow_vmcs) {
-		loaded_vmcs->shadow_vmcs = alloc_vmcs(true);
-		if (loaded_vmcs->shadow_vmcs)
-			vmcs_clear(loaded_vmcs->shadow_vmcs);
-	}
-	return loaded_vmcs->shadow_vmcs;
-}
-
-static int enter_vmx_operation(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int r;
-
-	r = alloc_loaded_vmcs(&vmx->nested.vmcs02);
-	if (r < 0)
-		goto out_vmcs02;
-
-	vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
-	if (!vmx->nested.cached_vmcs12)
-		goto out_cached_vmcs12;
-
-	vmx->nested.cached_shadow_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
-	if (!vmx->nested.cached_shadow_vmcs12)
-		goto out_cached_shadow_vmcs12;
-
-	if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu))
-		goto out_shadow_vmcs;
-
-	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL_PINNED);
-	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
-
-	vmx->nested.vpid02 = allocate_vpid();
-
-	vmx->nested.vmxon = true;
-	return 0;
-
-out_shadow_vmcs:
-	kfree(vmx->nested.cached_shadow_vmcs12);
-
-out_cached_shadow_vmcs12:
-	kfree(vmx->nested.cached_vmcs12);
-
-out_cached_vmcs12:
-	free_loaded_vmcs(&vmx->nested.vmcs02);
-
-out_vmcs02:
-	return -ENOMEM;
-}
-
-/*
- * Emulate the VMXON instruction.
- * Currently, we just remember that VMX is active, and do not save or even
- * inspect the argument to VMXON (the so-called "VMXON pointer") because we
- * do not currently need to store anything in that guest-allocated memory
- * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their
- * argument is different from the VMXON pointer (which the spec says they do).
- */
-static int handle_vmon(struct kvm_vcpu *vcpu)
-{
-	int ret;
-	gpa_t vmptr;
-	struct page *page;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
-		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
-
-	/*
-	 * The Intel VMX Instruction Reference lists a bunch of bits that are
-	 * prerequisite to running VMXON, most notably cr4.VMXE must be set to
-	 * 1 (see vmx_set_cr4() for when we allow the guest to set this).
-	 * Otherwise, we should fail with #UD.  But most faulting conditions
-	 * have already been checked by hardware, prior to the VM-exit for
-	 * VMXON.  We do test guest cr4.VMXE because processor CR4 always has
-	 * that bit set to 1 in non-root mode.
-	 */
-	if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	/* CPL=0 must be checked manually. */
-	if (vmx_get_cpl(vcpu)) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
-	if (vmx->nested.vmxon) {
-		nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
-			!= VMXON_NEEDED_FEATURES) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
-	if (nested_vmx_get_vmptr(vcpu, &vmptr))
-		return 1;
-
-	/*
-	 * SDM 3: 24.11.5
-	 * The first 4 bytes of VMXON region contain the supported
-	 * VMCS revision identifier
-	 *
-	 * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
-	 * which replaces physical address width with 32
-	 */
-	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
-		nested_vmx_failInvalid(vcpu);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
-	if (is_error_page(page)) {
-		nested_vmx_failInvalid(vcpu);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-	if (*(u32 *)kmap(page) != VMCS12_REVISION) {
-		kunmap(page);
-		kvm_release_page_clean(page);
-		nested_vmx_failInvalid(vcpu);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-	kunmap(page);
-	kvm_release_page_clean(page);
-
-	vmx->nested.vmxon_ptr = vmptr;
-	ret = enter_vmx_operation(vcpu);
-	if (ret)
-		return ret;
-
-	nested_vmx_succeed(vcpu);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-/*
- * Intel's VMX Instruction Reference specifies a common set of prerequisites
- * for running VMX instructions (except VMXON, whose prerequisites are
- * slightly different). It also specifies what exception to inject otherwise.
- * Note that many of these exceptions have priority over VM exits, so they
- * don't have to be checked again here.
- */
-static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
-{
-	if (!to_vmx(vcpu)->nested.vmxon) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 0;
-	}
-
-	if (vmx_get_cpl(vcpu)) {
-		kvm_inject_gp(vcpu, 0);
-		return 0;
-	}
-
-	return 1;
-}
-
-static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
-{
-	vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
-	vmcs_write64(VMCS_LINK_POINTER, -1ull);
-}
-
-static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
-{
-	if (vmx->nested.current_vmptr == -1ull)
-		return;
-
-	if (enable_shadow_vmcs) {
-		/* copy to memory all shadowed fields in case
-		   they were modified */
-		copy_shadow_to_vmcs12(vmx);
-		vmx->nested.sync_shadow_vmcs = false;
-		vmx_disable_shadow_vmcs(vmx);
-	}
-	vmx->nested.posted_intr_nv = -1;
-
-	/* Flush VMCS12 to guest memory */
-	kvm_vcpu_write_guest_page(&vmx->vcpu,
-				  vmx->nested.current_vmptr >> PAGE_SHIFT,
-				  vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
-
-	vmx->nested.current_vmptr = -1ull;
-}
-
-/*
- * Free whatever needs to be freed from vmx->nested when L1 goes down, or
- * just stops using VMX.
- */
-static void free_nested(struct vcpu_vmx *vmx)
-{
-	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
-		return;
-
-	vmx->nested.vmxon = false;
-	vmx->nested.smm.vmxon = false;
-	free_vpid(vmx->nested.vpid02);
-	vmx->nested.posted_intr_nv = -1;
-	vmx->nested.current_vmptr = -1ull;
-	if (enable_shadow_vmcs) {
-		vmx_disable_shadow_vmcs(vmx);
-		vmcs_clear(vmx->vmcs01.shadow_vmcs);
-		free_vmcs(vmx->vmcs01.shadow_vmcs);
-		vmx->vmcs01.shadow_vmcs = NULL;
-	}
-	kfree(vmx->nested.cached_vmcs12);
-	kfree(vmx->nested.cached_shadow_vmcs12);
-	/* Unpin physical memory we referred to in the vmcs02 */
-	if (vmx->nested.apic_access_page) {
-		kvm_release_page_dirty(vmx->nested.apic_access_page);
-		vmx->nested.apic_access_page = NULL;
-	}
-	if (vmx->nested.virtual_apic_page) {
-		kvm_release_page_dirty(vmx->nested.virtual_apic_page);
-		vmx->nested.virtual_apic_page = NULL;
-	}
-	if (vmx->nested.pi_desc_page) {
-		kunmap(vmx->nested.pi_desc_page);
-		kvm_release_page_dirty(vmx->nested.pi_desc_page);
-		vmx->nested.pi_desc_page = NULL;
-		vmx->nested.pi_desc = NULL;
-	}
-
-	free_loaded_vmcs(&vmx->nested.vmcs02);
-}
-
-/* Emulate the VMXOFF instruction */
-static int handle_vmoff(struct kvm_vcpu *vcpu)
-{
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-	free_nested(to_vmx(vcpu));
-	nested_vmx_succeed(vcpu);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-/* Emulate the VMCLEAR instruction */
-static int handle_vmclear(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 zero = 0;
-	gpa_t vmptr;
-
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-
-	if (nested_vmx_get_vmptr(vcpu, &vmptr))
-		return 1;
-
-	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
-		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	if (vmptr == vmx->nested.vmxon_ptr) {
-		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	if (vmptr == vmx->nested.current_vmptr)
-		nested_release_vmcs12(vmx);
-
-	kvm_vcpu_write_guest(vcpu,
-			vmptr + offsetof(struct vmcs12, launch_state),
-			&zero, sizeof(zero));
-
-	nested_vmx_succeed(vcpu);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);
-
-/* Emulate the VMLAUNCH instruction */
-static int handle_vmlaunch(struct kvm_vcpu *vcpu)
-{
-	return nested_vmx_run(vcpu, true);
-}
-
-/* Emulate the VMRESUME instruction */
-static int handle_vmresume(struct kvm_vcpu *vcpu)
-{
-
-	return nested_vmx_run(vcpu, false);
-}
-
-/*
- * Read a vmcs12 field. Since these can have varying lengths and we return
- * one type, we chose the biggest type (u64) and zero-extend the return value
- * to that size. Note that the caller, handle_vmread, might need to use only
- * some of the bits we return here (e.g., on 32-bit guests, only 32 bits of
- * 64-bit fields are to be returned).
- */
-static inline int vmcs12_read_any(struct vmcs12 *vmcs12,
-				  unsigned long field, u64 *ret)
-{
-	short offset = vmcs_field_to_offset(field);
-	char *p;
-
-	if (offset < 0)
-		return offset;
-
-	p = (char *)vmcs12 + offset;
-
-	switch (vmcs_field_width(field)) {
-	case VMCS_FIELD_WIDTH_NATURAL_WIDTH:
-		*ret = *((natural_width *)p);
-		return 0;
-	case VMCS_FIELD_WIDTH_U16:
-		*ret = *((u16 *)p);
-		return 0;
-	case VMCS_FIELD_WIDTH_U32:
-		*ret = *((u32 *)p);
-		return 0;
-	case VMCS_FIELD_WIDTH_U64:
-		*ret = *((u64 *)p);
-		return 0;
-	default:
-		WARN_ON(1);
-		return -ENOENT;
-	}
-}
-
-
-static inline int vmcs12_write_any(struct vmcs12 *vmcs12,
-				   unsigned long field, u64 field_value){
-	short offset = vmcs_field_to_offset(field);
-	char *p = (char *)vmcs12 + offset;
-	if (offset < 0)
-		return offset;
-
-	switch (vmcs_field_width(field)) {
-	case VMCS_FIELD_WIDTH_U16:
-		*(u16 *)p = field_value;
-		return 0;
-	case VMCS_FIELD_WIDTH_U32:
-		*(u32 *)p = field_value;
-		return 0;
-	case VMCS_FIELD_WIDTH_U64:
-		*(u64 *)p = field_value;
-		return 0;
-	case VMCS_FIELD_WIDTH_NATURAL_WIDTH:
-		*(natural_width *)p = field_value;
-		return 0;
-	default:
-		WARN_ON(1);
-		return -ENOENT;
-	}
-
-}
-
-/*
- * Copy the writable VMCS shadow fields back to the VMCS12, in case
- * they have been modified by the L1 guest. Note that the "read-only"
- * VM-exit information fields are actually writable if the vCPU is
- * configured to support "VMWRITE to any supported field in the VMCS."
- */
-static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
-{
-	const u16 *fields[] = {
-		shadow_read_write_fields,
-		shadow_read_only_fields
-	};
-	const int max_fields[] = {
-		max_shadow_read_write_fields,
-		max_shadow_read_only_fields
-	};
-	int i, q;
-	unsigned long field;
-	u64 field_value;
-	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
-
-	preempt_disable();
-
-	vmcs_load(shadow_vmcs);
-
-	for (q = 0; q < ARRAY_SIZE(fields); q++) {
-		for (i = 0; i < max_fields[q]; i++) {
-			field = fields[q][i];
-			field_value = __vmcs_readl(field);
-			vmcs12_write_any(get_vmcs12(&vmx->vcpu), field, field_value);
-		}
-		/*
-		 * Skip the VM-exit information fields if they are read-only.
-		 */
-		if (!nested_cpu_has_vmwrite_any_field(&vmx->vcpu))
-			break;
-	}
-
-	vmcs_clear(shadow_vmcs);
-	vmcs_load(vmx->loaded_vmcs->vmcs);
-
-	preempt_enable();
-}
-
-static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
-{
-	const u16 *fields[] = {
-		shadow_read_write_fields,
-		shadow_read_only_fields
-	};
-	const int max_fields[] = {
-		max_shadow_read_write_fields,
-		max_shadow_read_only_fields
-	};
-	int i, q;
-	unsigned long field;
-	u64 field_value = 0;
-	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
-
-	vmcs_load(shadow_vmcs);
-
-	for (q = 0; q < ARRAY_SIZE(fields); q++) {
-		for (i = 0; i < max_fields[q]; i++) {
-			field = fields[q][i];
-			vmcs12_read_any(get_vmcs12(&vmx->vcpu), field, &field_value);
-			__vmcs_writel(field, field_value);
-		}
-	}
-
-	vmcs_clear(shadow_vmcs);
-	vmcs_load(vmx->loaded_vmcs->vmcs);
-}
-
-/*
- * VMX instructions which assume a current vmcs12 (i.e., that VMPTRLD was
- * used before) all generate the same failure when it is missing.
- */
-static int nested_vmx_check_vmcs12(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	if (vmx->nested.current_vmptr == -1ull) {
-		nested_vmx_failInvalid(vcpu);
-		return 0;
-	}
-	return 1;
-}
-
-static int handle_vmread(struct kvm_vcpu *vcpu)
-{
-	unsigned long field;
-	u64 field_value;
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	gva_t gva = 0;
-	struct vmcs12 *vmcs12;
-
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-
-	if (!nested_vmx_check_vmcs12(vcpu))
-		return kvm_skip_emulated_instruction(vcpu);
-
-	if (!is_guest_mode(vcpu))
-		vmcs12 = get_vmcs12(vcpu);
-	else {
-		/*
-		 * When vmcs->vmcs_link_pointer is -1ull, any VMREAD
-		 * to shadowed-field sets the ALU flags for VMfailInvalid.
-		 */
-		if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) {
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		vmcs12 = get_shadow_vmcs12(vcpu);
-	}
-
-	/* Decode instruction info and find the field to read */
-	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
-	/* Read the field, zero-extended to a u64 field_value */
-	if (vmcs12_read_any(vmcs12, field, &field_value) < 0) {
-		nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-	/*
-	 * Now copy part of this value to register or memory, as requested.
-	 * Note that the number of bits actually copied is 32 or 64 depending
-	 * on the guest's mode (32 or 64 bit), not on the given field's length.
-	 */
-	if (vmx_instruction_info & (1u << 10)) {
-		kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf),
-			field_value);
-	} else {
-		if (get_vmx_mem_address(vcpu, exit_qualification,
-				vmx_instruction_info, true, &gva))
-			return 1;
-		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
-		kvm_write_guest_virt_system(vcpu, gva, &field_value,
-					    (is_long_mode(vcpu) ? 8 : 4), NULL);
-	}
-
-	nested_vmx_succeed(vcpu);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-
-static int handle_vmwrite(struct kvm_vcpu *vcpu)
-{
-	unsigned long field;
-	gva_t gva;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-
-	/* The value to write might be 32 or 64 bits, depending on L1's long
-	 * mode, and eventually we need to write that into a field of several
-	 * possible lengths. The code below first zero-extends the value to 64
-	 * bit (field_value), and then copies only the appropriate number of
-	 * bits into the vmcs12 field.
-	 */
-	u64 field_value = 0;
-	struct x86_exception e;
-	struct vmcs12 *vmcs12;
-
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-
-	if (!nested_vmx_check_vmcs12(vcpu))
-		return kvm_skip_emulated_instruction(vcpu);
-
-	if (vmx_instruction_info & (1u << 10))
-		field_value = kvm_register_readl(vcpu,
-			(((vmx_instruction_info) >> 3) & 0xf));
-	else {
-		if (get_vmx_mem_address(vcpu, exit_qualification,
-				vmx_instruction_info, false, &gva))
-			return 1;
-		if (kvm_read_guest_virt(vcpu, gva, &field_value,
-					(is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
-			kvm_inject_page_fault(vcpu, &e);
-			return 1;
-		}
-	}
-
-
-	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
-	/*
-	 * If the vCPU supports "VMWRITE to any supported field in the
-	 * VMCS," then the "read-only" fields are actually read/write.
-	 */
-	if (vmcs_field_readonly(field) &&
-	    !nested_cpu_has_vmwrite_any_field(vcpu)) {
-		nested_vmx_failValid(vcpu,
-			VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	if (!is_guest_mode(vcpu))
-		vmcs12 = get_vmcs12(vcpu);
-	else {
-		/*
-		 * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE
-		 * to shadowed-field sets the ALU flags for VMfailInvalid.
-		 */
-		if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) {
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		vmcs12 = get_shadow_vmcs12(vcpu);
-
-	}
-
-	if (vmcs12_write_any(vmcs12, field, field_value) < 0) {
-		nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	/*
-	 * Do not track vmcs12 dirty-state if in guest-mode
-	 * as we actually dirty shadow vmcs12 instead of vmcs12.
-	 */
-	if (!is_guest_mode(vcpu)) {
-		switch (field) {
-#define SHADOW_FIELD_RW(x) case x:
-#include "vmx_shadow_fields.h"
-			/*
-			 * The fields that can be updated by L1 without a vmexit are
-			 * always updated in the vmcs02, the others go down the slow
-			 * path of prepare_vmcs02.
-			 */
-			break;
-		default:
-			vmx->nested.dirty_vmcs12 = true;
-			break;
-		}
-	}
-
-	nested_vmx_succeed(vcpu);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
-{
-	vmx->nested.current_vmptr = vmptr;
-	if (enable_shadow_vmcs) {
-		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
-			      SECONDARY_EXEC_SHADOW_VMCS);
-		vmcs_write64(VMCS_LINK_POINTER,
-			     __pa(vmx->vmcs01.shadow_vmcs));
-		vmx->nested.sync_shadow_vmcs = true;
-	}
-	vmx->nested.dirty_vmcs12 = true;
-}
-
-/* Emulate the VMPTRLD instruction */
-static int handle_vmptrld(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t vmptr;
-
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-
-	if (nested_vmx_get_vmptr(vcpu, &vmptr))
-		return 1;
-
-	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
-		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	if (vmptr == vmx->nested.vmxon_ptr) {
-		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	if (vmx->nested.current_vmptr != vmptr) {
-		struct vmcs12 *new_vmcs12;
-		struct page *page;
-		page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
-		if (is_error_page(page)) {
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		new_vmcs12 = kmap(page);
-		if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
-		    (new_vmcs12->hdr.shadow_vmcs &&
-		     !nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
-			kunmap(page);
-			kvm_release_page_clean(page);
-			nested_vmx_failValid(vcpu,
-				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-
-		nested_release_vmcs12(vmx);
-		/*
-		 * Load VMCS12 from guest memory since it is not already
-		 * cached.
-		 */
-		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
-		kunmap(page);
-		kvm_release_page_clean(page);
-
-		set_current_vmptr(vmx, vmptr);
-	}
-
-	nested_vmx_succeed(vcpu);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-/* Emulate the VMPTRST instruction */
-static int handle_vmptrst(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION);
-	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
-	struct x86_exception e;
-	gva_t gva;
-
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-
-	if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva))
-		return 1;
-	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
-	if (kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
-					sizeof(gpa_t), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-	nested_vmx_succeed(vcpu);
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-/* Emulate the INVEPT instruction */
-static int handle_invept(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 vmx_instruction_info, types;
-	unsigned long type;
-	gva_t gva;
-	struct x86_exception e;
-	struct {
-		u64 eptp, gpa;
-	} operand;
-
-	if (!(vmx->nested.msrs.secondary_ctls_high &
-	      SECONDARY_EXEC_ENABLE_EPT) ||
-	    !(vmx->nested.msrs.ept_caps & VMX_EPT_INVEPT_BIT)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-
-	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
-
-	types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
-
-	if (type >= 32 || !(types & (1 << type))) {
-		nested_vmx_failValid(vcpu,
-				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	/* According to the Intel VMX instruction reference, the memory
-	 * operand is read even if it isn't needed (e.g., for type==global)
-	 */
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmx_instruction_info, false, &gva))
-		return 1;
-	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	switch (type) {
-	case VMX_EPT_EXTENT_GLOBAL:
-	/*
-	 * TODO: track mappings and invalidate
-	 * single context requests appropriately
-	 */
-	case VMX_EPT_EXTENT_CONTEXT:
-		kvm_mmu_sync_roots(vcpu);
-		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-		nested_vmx_succeed(vcpu);
-		break;
-	default:
-		BUG_ON(1);
-		break;
-	}
-
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int handle_invvpid(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 vmx_instruction_info;
-	unsigned long type, types;
-	gva_t gva;
-	struct x86_exception e;
-	struct {
-		u64 vpid;
-		u64 gla;
-	} operand;
-
-	if (!(vmx->nested.msrs.secondary_ctls_high &
-	      SECONDARY_EXEC_ENABLE_VPID) ||
-			!(vmx->nested.msrs.vpid_caps & VMX_VPID_INVVPID_BIT)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-
-	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
-
-	types = (vmx->nested.msrs.vpid_caps &
-			VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
-
-	if (type >= 32 || !(types & (1 << type))) {
-		nested_vmx_failValid(vcpu,
-			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	/* according to the intel vmx instruction reference, the memory
-	 * operand is read even if it isn't needed (e.g., for type==global)
-	 */
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmx_instruction_info, false, &gva))
-		return 1;
-	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-	if (operand.vpid >> 16) {
-		nested_vmx_failValid(vcpu,
-			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	switch (type) {
-	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
-		if (!operand.vpid ||
-		    is_noncanonical_address(operand.gla, vcpu)) {
-			nested_vmx_failValid(vcpu,
-				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		if (cpu_has_vmx_invvpid_individual_addr() &&
-		    vmx->nested.vpid02) {
-			__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR,
-				vmx->nested.vpid02, operand.gla);
-		} else
-			__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
-		break;
-	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
-	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
-		if (!operand.vpid) {
-			nested_vmx_failValid(vcpu,
-				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
-		break;
-	case VMX_VPID_EXTENT_ALL_CONTEXT:
-		__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return kvm_skip_emulated_instruction(vcpu);
-	}
-
-	nested_vmx_succeed(vcpu);
-
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int handle_invpcid(struct kvm_vcpu *vcpu)
-{
-	u32 vmx_instruction_info;
-	unsigned long type;
-	bool pcid_enabled;
-	gva_t gva;
-	struct x86_exception e;
-	unsigned i;
-	unsigned long roots_to_free = 0;
-	struct {
-		u64 pcid;
-		u64 gla;
-	} operand;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
-
-	if (type > 3) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
-	/* According to the Intel instruction reference, the memory operand
-	 * is read even if it isn't needed (e.g., for type==all)
-	 */
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-				vmx_instruction_info, false, &gva))
-		return 1;
-
-	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	if (operand.pcid >> 12 != 0) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
-	pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
-
-	switch (type) {
-	case INVPCID_TYPE_INDIV_ADDR:
-		if ((!pcid_enabled && (operand.pcid != 0)) ||
-		    is_noncanonical_address(operand.gla, vcpu)) {
-			kvm_inject_gp(vcpu, 0);
-			return 1;
-		}
-		kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid);
-		return kvm_skip_emulated_instruction(vcpu);
-
-	case INVPCID_TYPE_SINGLE_CTXT:
-		if (!pcid_enabled && (operand.pcid != 0)) {
-			kvm_inject_gp(vcpu, 0);
-			return 1;
-		}
-
-		if (kvm_get_active_pcid(vcpu) == operand.pcid) {
-			kvm_mmu_sync_roots(vcpu);
-			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-		}
-
-		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
-			if (kvm_get_pcid(vcpu, vcpu->arch.mmu.prev_roots[i].cr3)
-			    == operand.pcid)
-				roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
-
-		kvm_mmu_free_roots(vcpu, roots_to_free);
-		/*
-		 * If neither the current cr3 nor any of the prev_roots use the
-		 * given PCID, then nothing needs to be done here because a
-		 * resync will happen anyway before switching to any other CR3.
-		 */
-
-		return kvm_skip_emulated_instruction(vcpu);
-
-	case INVPCID_TYPE_ALL_NON_GLOBAL:
-		/*
-		 * Currently, KVM doesn't mark global entries in the shadow
-		 * page tables, so a non-global flush just degenerates to a
-		 * global flush. If needed, we could optimize this later by
-		 * keeping track of global entries in shadow page tables.
-		 */
-
-		/* fall-through */
-	case INVPCID_TYPE_ALL_INCL_GLOBAL:
-		kvm_mmu_unload(vcpu);
-		return kvm_skip_emulated_instruction(vcpu);
-
-	default:
-		BUG(); /* We have already checked above that type <= 3 */
-	}
-}
-
-static int handle_pml_full(struct kvm_vcpu *vcpu)
-{
-	unsigned long exit_qualification;
-
-	trace_kvm_pml_full(vcpu->vcpu_id);
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	/*
-	 * PML buffer FULL happened while executing iret from NMI,
-	 * "blocked by NMI" bit has to be set before next VM entry.
-	 */
-	if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
-			enable_vnmi &&
-			(exit_qualification & INTR_INFO_UNBLOCK_NMI))
-		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
-				GUEST_INTR_STATE_NMI);
-
-	/*
-	 * PML buffer already flushed at beginning of VMEXIT. Nothing to do
-	 * here.., and there's no userspace involvement needed for PML.
-	 */
-	return 1;
-}
-
-static int handle_preemption_timer(struct kvm_vcpu *vcpu)
-{
-	if (!to_vmx(vcpu)->req_immediate_exit)
-		kvm_lapic_expired_hv_timer(vcpu);
-	return 1;
-}
-
-static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int maxphyaddr = cpuid_maxphyaddr(vcpu);
-
-	/* Check for memory type validity */
-	switch (address & VMX_EPTP_MT_MASK) {
-	case VMX_EPTP_MT_UC:
-		if (!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT))
-			return false;
-		break;
-	case VMX_EPTP_MT_WB:
-		if (!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT))
-			return false;
-		break;
-	default:
-		return false;
-	}
-
-	/* only 4 levels page-walk length are valid */
-	if ((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4)
-		return false;
-
-	/* Reserved bits should not be set */
-	if (address >> maxphyaddr || ((address >> 7) & 0x1f))
-		return false;
-
-	/* AD, if set, should be supported */
-	if (address & VMX_EPTP_AD_ENABLE_BIT) {
-		if (!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT))
-			return false;
-	}
-
-	return true;
-}
-
-static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
-				     struct vmcs12 *vmcs12)
-{
-	u32 index = vcpu->arch.regs[VCPU_REGS_RCX];
-	u64 address;
-	bool accessed_dirty;
-	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
-
-	if (!nested_cpu_has_eptp_switching(vmcs12) ||
-	    !nested_cpu_has_ept(vmcs12))
-		return 1;
-
-	if (index >= VMFUNC_EPTP_ENTRIES)
-		return 1;
-
-
-	if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT,
-				     &address, index * 8, 8))
-		return 1;
-
-	accessed_dirty = !!(address & VMX_EPTP_AD_ENABLE_BIT);
-
-	/*
-	 * If the (L2) guest does a vmfunc to the currently
-	 * active ept pointer, we don't have to do anything else
-	 */
-	if (vmcs12->ept_pointer != address) {
-		if (!valid_ept_address(vcpu, address))
-			return 1;
-
-		kvm_mmu_unload(vcpu);
-		mmu->ept_ad = accessed_dirty;
-		mmu->base_role.ad_disabled = !accessed_dirty;
-		vmcs12->ept_pointer = address;
-		/*
-		 * TODO: Check what's the correct approach in case
-		 * mmu reload fails. Currently, we just let the next
-		 * reload potentially fail
-		 */
-		kvm_mmu_reload(vcpu);
-	}
-
-	return 0;
-}
-
-static int handle_vmfunc(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct vmcs12 *vmcs12;
-	u32 function = vcpu->arch.regs[VCPU_REGS_RAX];
-
-	/*
-	 * VMFUNC is only supported for nested guests, but we always enable the
-	 * secondary control for simplicity; for non-nested mode, fake that we
-	 * didn't by injecting #UD.
-	 */
-	if (!is_guest_mode(vcpu)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	vmcs12 = get_vmcs12(vcpu);
-	if ((vmcs12->vm_function_control & (1 << function)) == 0)
-		goto fail;
-
-	switch (function) {
-	case 0:
-		if (nested_vmx_eptp_switching(vcpu, vmcs12))
-			goto fail;
-		break;
-	default:
-		goto fail;
-	}
-	return kvm_skip_emulated_instruction(vcpu);
-
-fail:
-	nested_vmx_vmexit(vcpu, vmx->exit_reason,
-			  vmcs_read32(VM_EXIT_INTR_INFO),
-			  vmcs_readl(EXIT_QUALIFICATION));
-	return 1;
-}
-
-static int handle_encls(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * SGX virtualization is not yet supported.  There is no software
-	 * enable bit for SGX, so we have to trap ENCLS and inject a #UD
-	 * to prevent the guest from executing ENCLS.
-	 */
-	kvm_queue_exception(vcpu, UD_VECTOR);
-	return 1;
-}
-
-/*
- * The exit handlers return 1 if the exit was handled fully and guest execution
- * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
- * to be done to userspace and return 0.
- */
-static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
-	[EXIT_REASON_EXCEPTION_NMI]           = handle_exception,
-	[EXIT_REASON_EXTERNAL_INTERRUPT]      = handle_external_interrupt,
-	[EXIT_REASON_TRIPLE_FAULT]            = handle_triple_fault,
-	[EXIT_REASON_NMI_WINDOW]	      = handle_nmi_window,
-	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
-	[EXIT_REASON_CR_ACCESS]               = handle_cr,
-	[EXIT_REASON_DR_ACCESS]               = handle_dr,
-	[EXIT_REASON_CPUID]                   = handle_cpuid,
-	[EXIT_REASON_MSR_READ]                = handle_rdmsr,
-	[EXIT_REASON_MSR_WRITE]               = handle_wrmsr,
-	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
-	[EXIT_REASON_HLT]                     = handle_halt,
-	[EXIT_REASON_INVD]		      = handle_invd,
-	[EXIT_REASON_INVLPG]		      = handle_invlpg,
-	[EXIT_REASON_RDPMC]                   = handle_rdpmc,
-	[EXIT_REASON_VMCALL]                  = handle_vmcall,
-	[EXIT_REASON_VMCLEAR]	              = handle_vmclear,
-	[EXIT_REASON_VMLAUNCH]                = handle_vmlaunch,
-	[EXIT_REASON_VMPTRLD]                 = handle_vmptrld,
-	[EXIT_REASON_VMPTRST]                 = handle_vmptrst,
-	[EXIT_REASON_VMREAD]                  = handle_vmread,
-	[EXIT_REASON_VMRESUME]                = handle_vmresume,
-	[EXIT_REASON_VMWRITE]                 = handle_vmwrite,
-	[EXIT_REASON_VMOFF]                   = handle_vmoff,
-	[EXIT_REASON_VMON]                    = handle_vmon,
-	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
-	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
-	[EXIT_REASON_APIC_WRITE]              = handle_apic_write,
-	[EXIT_REASON_EOI_INDUCED]             = handle_apic_eoi_induced,
-	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
-	[EXIT_REASON_XSETBV]                  = handle_xsetbv,
-	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
-	[EXIT_REASON_MCE_DURING_VMENTRY]      = handle_machine_check,
-	[EXIT_REASON_GDTR_IDTR]		      = handle_desc,
-	[EXIT_REASON_LDTR_TR]		      = handle_desc,
-	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
-	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
-	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
-	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
-	[EXIT_REASON_MONITOR_TRAP_FLAG]       = handle_monitor_trap,
-	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
-	[EXIT_REASON_INVEPT]                  = handle_invept,
-	[EXIT_REASON_INVVPID]                 = handle_invvpid,
-	[EXIT_REASON_RDRAND]                  = handle_invalid_op,
-	[EXIT_REASON_RDSEED]                  = handle_invalid_op,
-	[EXIT_REASON_XSAVES]                  = handle_xsaves,
-	[EXIT_REASON_XRSTORS]                 = handle_xrstors,
-	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
-	[EXIT_REASON_INVPCID]                 = handle_invpcid,
-	[EXIT_REASON_VMFUNC]                  = handle_vmfunc,
-	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
-	[EXIT_REASON_ENCLS]		      = handle_encls,
-};
-
-static const int kvm_vmx_max_exit_handlers =
-	ARRAY_SIZE(kvm_vmx_exit_handlers);
-
-static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
-				       struct vmcs12 *vmcs12)
-{
-	unsigned long exit_qualification;
-	gpa_t bitmap, last_bitmap;
-	unsigned int port;
-	int size;
-	u8 b;
-
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
-		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	port = exit_qualification >> 16;
-	size = (exit_qualification & 7) + 1;
-
-	last_bitmap = (gpa_t)-1;
-	b = -1;
-
-	while (size > 0) {
-		if (port < 0x8000)
-			bitmap = vmcs12->io_bitmap_a;
-		else if (port < 0x10000)
-			bitmap = vmcs12->io_bitmap_b;
-		else
-			return true;
-		bitmap += (port & 0x7fff) / 8;
-
-		if (last_bitmap != bitmap)
-			if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1))
-				return true;
-		if (b & (1 << (port & 7)))
-			return true;
-
-		port++;
-		size--;
-		last_bitmap = bitmap;
-	}
-
-	return false;
-}
-
-/*
- * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
- * rather than handle it ourselves in L0. I.e., check whether L1 expressed
- * disinterest in the current event (read or write a specific MSR) by using an
- * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps.
- */
-static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
-	struct vmcs12 *vmcs12, u32 exit_reason)
-{
-	u32 msr_index = vcpu->arch.regs[VCPU_REGS_RCX];
-	gpa_t bitmap;
-
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
-		return true;
-
-	/*
-	 * The MSR_BITMAP page is divided into four 1024-byte bitmaps,
-	 * for the four combinations of read/write and low/high MSR numbers.
-	 * First we need to figure out which of the four to use:
-	 */
-	bitmap = vmcs12->msr_bitmap;
-	if (exit_reason == EXIT_REASON_MSR_WRITE)
-		bitmap += 2048;
-	if (msr_index >= 0xc0000000) {
-		msr_index -= 0xc0000000;
-		bitmap += 1024;
-	}
-
-	/* Then read the msr_index'th bit from this bitmap: */
-	if (msr_index < 1024*8) {
-		unsigned char b;
-		if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1))
-			return true;
-		return 1 & (b >> (msr_index & 7));
-	} else
-		return true; /* let L1 handle the wrong parameter */
-}
-
-/*
- * Return 1 if we should exit from L2 to L1 to handle a CR access exit,
- * rather than handle it ourselves in L0. I.e., check if L1 wanted to
- * intercept (via guest_host_mask etc.) the current event.
- */
-static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
-	struct vmcs12 *vmcs12)
-{
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	int cr = exit_qualification & 15;
-	int reg;
-	unsigned long val;
-
-	switch ((exit_qualification >> 4) & 3) {
-	case 0: /* mov to cr */
-		reg = (exit_qualification >> 8) & 15;
-		val = kvm_register_readl(vcpu, reg);
-		switch (cr) {
-		case 0:
-			if (vmcs12->cr0_guest_host_mask &
-			    (val ^ vmcs12->cr0_read_shadow))
-				return true;
-			break;
-		case 3:
-			if ((vmcs12->cr3_target_count >= 1 &&
-					vmcs12->cr3_target_value0 == val) ||
-				(vmcs12->cr3_target_count >= 2 &&
-					vmcs12->cr3_target_value1 == val) ||
-				(vmcs12->cr3_target_count >= 3 &&
-					vmcs12->cr3_target_value2 == val) ||
-				(vmcs12->cr3_target_count >= 4 &&
-					vmcs12->cr3_target_value3 == val))
-				return false;
-			if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING))
-				return true;
-			break;
-		case 4:
-			if (vmcs12->cr4_guest_host_mask &
-			    (vmcs12->cr4_read_shadow ^ val))
-				return true;
-			break;
-		case 8:
-			if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING))
-				return true;
-			break;
-		}
-		break;
-	case 2: /* clts */
-		if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) &&
-		    (vmcs12->cr0_read_shadow & X86_CR0_TS))
-			return true;
-		break;
-	case 1: /* mov from cr */
-		switch (cr) {
-		case 3:
-			if (vmcs12->cpu_based_vm_exec_control &
-			    CPU_BASED_CR3_STORE_EXITING)
-				return true;
-			break;
-		case 8:
-			if (vmcs12->cpu_based_vm_exec_control &
-			    CPU_BASED_CR8_STORE_EXITING)
-				return true;
-			break;
-		}
-		break;
-	case 3: /* lmsw */
-		/*
-		 * lmsw can change bits 1..3 of cr0, and only set bit 0 of
-		 * cr0. Other attempted changes are ignored, with no exit.
-		 */
-		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
-		if (vmcs12->cr0_guest_host_mask & 0xe &
-		    (val ^ vmcs12->cr0_read_shadow))
-			return true;
-		if ((vmcs12->cr0_guest_host_mask & 0x1) &&
-		    !(vmcs12->cr0_read_shadow & 0x1) &&
-		    (val & 0x1))
-			return true;
-		break;
-	}
-	return false;
-}
-
-static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu,
-	struct vmcs12 *vmcs12, gpa_t bitmap)
-{
-	u32 vmx_instruction_info;
-	unsigned long field;
-	u8 b;
-
-	if (!nested_cpu_has_shadow_vmcs(vmcs12))
-		return true;
-
-	/* Decode instruction info and find the field to access */
-	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
-
-	/* Out-of-range fields always cause a VM exit from L2 to L1 */
-	if (field >> 15)
-		return true;
-
-	if (kvm_vcpu_read_guest(vcpu, bitmap + field/8, &b, 1))
-		return true;
-
-	return 1 & (b >> (field & 7));
-}
-
-/*
- * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we
- * should handle it ourselves in L0 (and then continue L2). Only call this
- * when in is_guest_mode (L2).
- */
-static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
-{
-	u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-
-	if (vmx->nested.nested_run_pending)
-		return false;
-
-	if (unlikely(vmx->fail)) {
-		pr_info_ratelimited("%s failed vm entry %x\n", __func__,
-				    vmcs_read32(VM_INSTRUCTION_ERROR));
-		return true;
-	}
-
-	/*
-	 * The host physical addresses of some pages of guest memory
-	 * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
-	 * Page). The CPU may write to these pages via their host
-	 * physical address while L2 is running, bypassing any
-	 * address-translation-based dirty tracking (e.g. EPT write
-	 * protection).
-	 *
-	 * Mark them dirty on every exit from L2 to prevent them from
-	 * getting out of sync with dirty tracking.
-	 */
-	nested_mark_vmcs12_pages_dirty(vcpu);
-
-	trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
-				vmcs_readl(EXIT_QUALIFICATION),
-				vmx->idt_vectoring_info,
-				intr_info,
-				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
-				KVM_ISA_VMX);
-
-	switch (exit_reason) {
-	case EXIT_REASON_EXCEPTION_NMI:
-		if (is_nmi(intr_info))
-			return false;
-		else if (is_page_fault(intr_info))
-			return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept;
-		else if (is_no_device(intr_info) &&
-			 !(vmcs12->guest_cr0 & X86_CR0_TS))
-			return false;
-		else if (is_debug(intr_info) &&
-			 vcpu->guest_debug &
-			 (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
-			return false;
-		else if (is_breakpoint(intr_info) &&
-			 vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
-			return false;
-		return vmcs12->exception_bitmap &
-				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
-	case EXIT_REASON_EXTERNAL_INTERRUPT:
-		return false;
-	case EXIT_REASON_TRIPLE_FAULT:
-		return true;
-	case EXIT_REASON_PENDING_INTERRUPT:
-		return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING);
-	case EXIT_REASON_NMI_WINDOW:
-		return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING);
-	case EXIT_REASON_TASK_SWITCH:
-		return true;
-	case EXIT_REASON_CPUID:
-		return true;
-	case EXIT_REASON_HLT:
-		return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
-	case EXIT_REASON_INVD:
-		return true;
-	case EXIT_REASON_INVLPG:
-		return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
-	case EXIT_REASON_RDPMC:
-		return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING);
-	case EXIT_REASON_RDRAND:
-		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDRAND_EXITING);
-	case EXIT_REASON_RDSEED:
-		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDSEED_EXITING);
-	case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP:
-		return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING);
-	case EXIT_REASON_VMREAD:
-		return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12,
-			vmcs12->vmread_bitmap);
-	case EXIT_REASON_VMWRITE:
-		return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12,
-			vmcs12->vmwrite_bitmap);
-	case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR:
-	case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD:
-	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMRESUME:
-	case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
-	case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID:
-		/*
-		 * VMX instructions trap unconditionally. This allows L1 to
-		 * emulate them for its L2 guest, i.e., allows 3-level nesting!
-		 */
-		return true;
-	case EXIT_REASON_CR_ACCESS:
-		return nested_vmx_exit_handled_cr(vcpu, vmcs12);
-	case EXIT_REASON_DR_ACCESS:
-		return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING);
-	case EXIT_REASON_IO_INSTRUCTION:
-		return nested_vmx_exit_handled_io(vcpu, vmcs12);
-	case EXIT_REASON_GDTR_IDTR: case EXIT_REASON_LDTR_TR:
-		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC);
-	case EXIT_REASON_MSR_READ:
-	case EXIT_REASON_MSR_WRITE:
-		return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason);
-	case EXIT_REASON_INVALID_STATE:
-		return true;
-	case EXIT_REASON_MWAIT_INSTRUCTION:
-		return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
-	case EXIT_REASON_MONITOR_TRAP_FLAG:
-		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
-	case EXIT_REASON_MONITOR_INSTRUCTION:
-		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
-	case EXIT_REASON_PAUSE_INSTRUCTION:
-		return nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING) ||
-			nested_cpu_has2(vmcs12,
-				SECONDARY_EXEC_PAUSE_LOOP_EXITING);
-	case EXIT_REASON_MCE_DURING_VMENTRY:
-		return false;
-	case EXIT_REASON_TPR_BELOW_THRESHOLD:
-		return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
-	case EXIT_REASON_APIC_ACCESS:
-	case EXIT_REASON_APIC_WRITE:
-	case EXIT_REASON_EOI_INDUCED:
-		/*
-		 * The controls for "virtualize APIC accesses," "APIC-
-		 * register virtualization," and "virtual-interrupt
-		 * delivery" only come from vmcs12.
-		 */
-		return true;
-	case EXIT_REASON_EPT_VIOLATION:
-		/*
-		 * L0 always deals with the EPT violation. If nested EPT is
-		 * used, and the nested mmu code discovers that the address is
-		 * missing in the guest EPT table (EPT12), the EPT violation
-		 * will be injected with nested_ept_inject_page_fault()
-		 */
-		return false;
-	case EXIT_REASON_EPT_MISCONFIG:
-		/*
-		 * L2 never uses directly L1's EPT, but rather L0's own EPT
-		 * table (shadow on EPT) or a merged EPT table that L0 built
-		 * (EPT on EPT). So any problems with the structure of the
-		 * table is L0's fault.
-		 */
-		return false;
-	case EXIT_REASON_INVPCID:
-		return
-			nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_INVPCID) &&
-			nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
-	case EXIT_REASON_WBINVD:
-		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING);
-	case EXIT_REASON_XSETBV:
-		return true;
-	case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS:
-		/*
-		 * This should never happen, since it is not possible to
-		 * set XSS to a non-zero value---neither in L1 nor in L2.
-		 * If if it were, XSS would have to be checked against
-		 * the XSS exit bitmap in vmcs12.
-		 */
-		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
-	case EXIT_REASON_PREEMPTION_TIMER:
-		return false;
-	case EXIT_REASON_PML_FULL:
-		/* We emulate PML support to L1. */
-		return false;
-	case EXIT_REASON_VMFUNC:
-		/* VM functions are emulated through L2->L0 vmexits. */
-		return false;
-	case EXIT_REASON_ENCLS:
-		/* SGX is never exposed to L1 */
-		return false;
-	default:
-		return true;
-	}
-}
-
-static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason)
-{
-	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-
-	/*
-	 * At this point, the exit interruption info in exit_intr_info
-	 * is only valid for EXCEPTION_NMI exits.  For EXTERNAL_INTERRUPT
-	 * we need to query the in-kernel LAPIC.
-	 */
-	WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT);
-	if ((exit_intr_info &
-	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
-	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
-		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-		vmcs12->vm_exit_intr_error_code =
-			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
-	}
-
-	nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info,
-			  vmcs_readl(EXIT_QUALIFICATION));
-	return 1;
-}
-
-static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
-{
-	*info1 = vmcs_readl(EXIT_QUALIFICATION);
-	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
-}
-
-static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
-{
-	if (vmx->pml_pg) {
-		__free_page(vmx->pml_pg);
-		vmx->pml_pg = NULL;
-	}
-}
-
-static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u64 *pml_buf;
-	u16 pml_idx;
-
-	pml_idx = vmcs_read16(GUEST_PML_INDEX);
-
-	/* Do nothing if PML buffer is empty */
-	if (pml_idx == (PML_ENTITY_NUM - 1))
-		return;
-
-	/* PML index always points to next available PML buffer entity */
-	if (pml_idx >= PML_ENTITY_NUM)
-		pml_idx = 0;
-	else
-		pml_idx++;
-
-	pml_buf = page_address(vmx->pml_pg);
-	for (; pml_idx < PML_ENTITY_NUM; pml_idx++) {
-		u64 gpa;
-
-		gpa = pml_buf[pml_idx];
-		WARN_ON(gpa & (PAGE_SIZE - 1));
-		kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
-	}
-
-	/* reset PML index */
-	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-}
-
-/*
- * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap.
- * Called before reporting dirty_bitmap to userspace.
- */
-static void kvm_flush_pml_buffers(struct kvm *kvm)
-{
-	int i;
-	struct kvm_vcpu *vcpu;
-	/*
-	 * We only need to kick vcpu out of guest mode here, as PML buffer
-	 * is flushed at beginning of all VMEXITs, and it's obvious that only
-	 * vcpus running in guest are possible to have unflushed GPAs in PML
-	 * buffer.
-	 */
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vcpu_kick(vcpu);
-}
-
-static void vmx_dump_sel(char *name, uint32_t sel)
-{
-	pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
-	       name, vmcs_read16(sel),
-	       vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR),
-	       vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR),
-	       vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR));
-}
-
-static void vmx_dump_dtsel(char *name, uint32_t limit)
-{
-	pr_err("%s                           limit=0x%08x, base=0x%016lx\n",
-	       name, vmcs_read32(limit),
-	       vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
-}
-
-static void dump_vmcs(void)
-{
-	u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
-	u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
-	u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
-	u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
-	u32 secondary_exec_control = 0;
-	unsigned long cr4 = vmcs_readl(GUEST_CR4);
-	u64 efer = vmcs_read64(GUEST_IA32_EFER);
-	int i, n;
-
-	if (cpu_has_secondary_exec_ctrls())
-		secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-
-	pr_err("*** Guest State ***\n");
-	pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
-	       vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW),
-	       vmcs_readl(CR0_GUEST_HOST_MASK));
-	pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
-	       cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK));
-	pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3));
-	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
-	    (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA))
-	{
-		pr_err("PDPTR0 = 0x%016llx  PDPTR1 = 0x%016llx\n",
-		       vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1));
-		pr_err("PDPTR2 = 0x%016llx  PDPTR3 = 0x%016llx\n",
-		       vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3));
-	}
-	pr_err("RSP = 0x%016lx  RIP = 0x%016lx\n",
-	       vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP));
-	pr_err("RFLAGS=0x%08lx         DR7 = 0x%016lx\n",
-	       vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7));
-	pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
-	       vmcs_readl(GUEST_SYSENTER_ESP),
-	       vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP));
-	vmx_dump_sel("CS:  ", GUEST_CS_SELECTOR);
-	vmx_dump_sel("DS:  ", GUEST_DS_SELECTOR);
-	vmx_dump_sel("SS:  ", GUEST_SS_SELECTOR);
-	vmx_dump_sel("ES:  ", GUEST_ES_SELECTOR);
-	vmx_dump_sel("FS:  ", GUEST_FS_SELECTOR);
-	vmx_dump_sel("GS:  ", GUEST_GS_SELECTOR);
-	vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT);
-	vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
-	vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
-	vmx_dump_sel("TR:  ", GUEST_TR_SELECTOR);
-	if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
-	    (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
-		pr_err("EFER =     0x%016llx  PAT = 0x%016llx\n",
-		       efer, vmcs_read64(GUEST_IA32_PAT));
-	pr_err("DebugCtl = 0x%016llx  DebugExceptions = 0x%016lx\n",
-	       vmcs_read64(GUEST_IA32_DEBUGCTL),
-	       vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
-	if (cpu_has_load_perf_global_ctrl &&
-	    vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
-		pr_err("PerfGlobCtl = 0x%016llx\n",
-		       vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL));
-	if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS)
-		pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS));
-	pr_err("Interruptibility = %08x  ActivityState = %08x\n",
-	       vmcs_read32(GUEST_INTERRUPTIBILITY_INFO),
-	       vmcs_read32(GUEST_ACTIVITY_STATE));
-	if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
-		pr_err("InterruptStatus = %04x\n",
-		       vmcs_read16(GUEST_INTR_STATUS));
-
-	pr_err("*** Host State ***\n");
-	pr_err("RIP = 0x%016lx  RSP = 0x%016lx\n",
-	       vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP));
-	pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n",
-	       vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR),
-	       vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR),
-	       vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR),
-	       vmcs_read16(HOST_TR_SELECTOR));
-	pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n",
-	       vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE),
-	       vmcs_readl(HOST_TR_BASE));
-	pr_err("GDTBase=%016lx IDTBase=%016lx\n",
-	       vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE));
-	pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n",
-	       vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3),
-	       vmcs_readl(HOST_CR4));
-	pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
-	       vmcs_readl(HOST_IA32_SYSENTER_ESP),
-	       vmcs_read32(HOST_IA32_SYSENTER_CS),
-	       vmcs_readl(HOST_IA32_SYSENTER_EIP));
-	if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER))
-		pr_err("EFER = 0x%016llx  PAT = 0x%016llx\n",
-		       vmcs_read64(HOST_IA32_EFER),
-		       vmcs_read64(HOST_IA32_PAT));
-	if (cpu_has_load_perf_global_ctrl &&
-	    vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		pr_err("PerfGlobCtl = 0x%016llx\n",
-		       vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL));
-
-	pr_err("*** Control State ***\n");
-	pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n",
-	       pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control);
-	pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl);
-	pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n",
-	       vmcs_read32(EXCEPTION_BITMAP),
-	       vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK),
-	       vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH));
-	pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n",
-	       vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
-	       vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE),
-	       vmcs_read32(VM_ENTRY_INSTRUCTION_LEN));
-	pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n",
-	       vmcs_read32(VM_EXIT_INTR_INFO),
-	       vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
-	       vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
-	pr_err("        reason=%08x qualification=%016lx\n",
-	       vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION));
-	pr_err("IDTVectoring: info=%08x errcode=%08x\n",
-	       vmcs_read32(IDT_VECTORING_INFO_FIELD),
-	       vmcs_read32(IDT_VECTORING_ERROR_CODE));
-	pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET));
-	if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING)
-		pr_err("TSC Multiplier = 0x%016llx\n",
-		       vmcs_read64(TSC_MULTIPLIER));
-	if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW)
-		pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD));
-	if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR)
-		pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV));
-	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT))
-		pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER));
-	n = vmcs_read32(CR3_TARGET_COUNT);
-	for (i = 0; i + 1 < n; i += 4)
-		pr_err("CR3 target%u=%016lx target%u=%016lx\n",
-		       i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2),
-		       i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2));
-	if (i < n)
-		pr_err("CR3 target%u=%016lx\n",
-		       i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2));
-	if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING)
-		pr_err("PLE Gap=%08x Window=%08x\n",
-		       vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW));
-	if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID)
-		pr_err("Virtual processor ID = 0x%04x\n",
-		       vmcs_read16(VIRTUAL_PROCESSOR_ID));
-}
-
-/*
- * The guest has exited.  See if we can fix it or if we need userspace
- * assistance.
- */
-static int vmx_handle_exit(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 exit_reason = vmx->exit_reason;
-	u32 vectoring_info = vmx->idt_vectoring_info;
-
-	trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX);
-
-	/*
-	 * Flush logged GPAs PML buffer, this will make dirty_bitmap more
-	 * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before
-	 * querying dirty_bitmap, we only need to kick all vcpus out of guest
-	 * mode as if vcpus is in root mode, the PML buffer must has been
-	 * flushed already.
-	 */
-	if (enable_pml)
-		vmx_flush_pml_buffer(vcpu);
-
-	/* If guest state is invalid, start emulating */
-	if (vmx->emulation_required)
-		return handle_invalid_guest_state(vcpu);
-
-	if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason))
-		return nested_vmx_reflect_vmexit(vcpu, exit_reason);
-
-	if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
-		dump_vmcs();
-		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
-		vcpu->run->fail_entry.hardware_entry_failure_reason
-			= exit_reason;
-		return 0;
-	}
-
-	if (unlikely(vmx->fail)) {
-		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
-		vcpu->run->fail_entry.hardware_entry_failure_reason
-			= vmcs_read32(VM_INSTRUCTION_ERROR);
-		return 0;
-	}
-
-	/*
-	 * Note:
-	 * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by
-	 * delivery event since it indicates guest is accessing MMIO.
-	 * The vm-exit can be triggered again after return to guest that
-	 * will cause infinite loop.
-	 */
-	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
-			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
-			exit_reason != EXIT_REASON_EPT_VIOLATION &&
-			exit_reason != EXIT_REASON_PML_FULL &&
-			exit_reason != EXIT_REASON_TASK_SWITCH)) {
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
-		vcpu->run->internal.ndata = 3;
-		vcpu->run->internal.data[0] = vectoring_info;
-		vcpu->run->internal.data[1] = exit_reason;
-		vcpu->run->internal.data[2] = vcpu->arch.exit_qualification;
-		if (exit_reason == EXIT_REASON_EPT_MISCONFIG) {
-			vcpu->run->internal.ndata++;
-			vcpu->run->internal.data[3] =
-				vmcs_read64(GUEST_PHYSICAL_ADDRESS);
-		}
-		return 0;
-	}
-
-	if (unlikely(!enable_vnmi &&
-		     vmx->loaded_vmcs->soft_vnmi_blocked)) {
-		if (vmx_interrupt_allowed(vcpu)) {
-			vmx->loaded_vmcs->soft_vnmi_blocked = 0;
-		} else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL &&
-			   vcpu->arch.nmi_pending) {
-			/*
-			 * This CPU don't support us in finding the end of an
-			 * NMI-blocked window if the guest runs with IRQs
-			 * disabled. So we pull the trigger after 1 s of
-			 * futile waiting, but inform the user about this.
-			 */
-			printk(KERN_WARNING "%s: Breaking out of NMI-blocked "
-			       "state on VCPU %d after 1 s timeout\n",
-			       __func__, vcpu->vcpu_id);
-			vmx->loaded_vmcs->soft_vnmi_blocked = 0;
-		}
-	}
-
-	if (exit_reason < kvm_vmx_max_exit_handlers
-	    && kvm_vmx_exit_handlers[exit_reason])
-		return kvm_vmx_exit_handlers[exit_reason](vcpu);
-	else {
-		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
-				exit_reason);
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-}
-
-/*
- * Software based L1D cache flush which is used when microcode providing
- * the cache control MSR is not loaded.
- *
- * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
- * flush it is required to read in 64 KiB because the replacement algorithm
- * is not exactly LRU. This could be sized at runtime via topology
- * information but as all relevant affected CPUs have 32KiB L1D cache size
- * there is no point in doing so.
- */
-static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
-{
-	int size = PAGE_SIZE << L1D_CACHE_ORDER;
-
-	/*
-	 * This code is only executed when the the flush mode is 'cond' or
-	 * 'always'
-	 */
-	if (static_branch_likely(&vmx_l1d_flush_cond)) {
-		bool flush_l1d;
-
-		/*
-		 * Clear the per-vcpu flush bit, it gets set again
-		 * either from vcpu_run() or from one of the unsafe
-		 * VMEXIT handlers.
-		 */
-		flush_l1d = vcpu->arch.l1tf_flush_l1d;
-		vcpu->arch.l1tf_flush_l1d = false;
-
-		/*
-		 * Clear the per-cpu flush bit, it gets set again from
-		 * the interrupt handlers.
-		 */
-		flush_l1d |= kvm_get_cpu_l1tf_flush_l1d();
-		kvm_clear_cpu_l1tf_flush_l1d();
-
-		if (!flush_l1d)
-			return;
-	}
-
-	vcpu->stat.l1d_flush++;
-
-	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
-		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
-		return;
-	}
-
-	asm volatile(
-		/* First ensure the pages are in the TLB */
-		"xorl	%%eax, %%eax\n"
-		".Lpopulate_tlb:\n\t"
-		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
-		"addl	$4096, %%eax\n\t"
-		"cmpl	%%eax, %[size]\n\t"
-		"jne	.Lpopulate_tlb\n\t"
-		"xorl	%%eax, %%eax\n\t"
-		"cpuid\n\t"
-		/* Now fill the cache */
-		"xorl	%%eax, %%eax\n"
-		".Lfill_cache:\n"
-		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
-		"addl	$64, %%eax\n\t"
-		"cmpl	%%eax, %[size]\n\t"
-		"jne	.Lfill_cache\n\t"
-		"lfence\n"
-		:: [flush_pages] "r" (vmx_l1d_flush_pages),
-		    [size] "r" (size)
-		: "eax", "ebx", "ecx", "edx");
-}
-
-static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-
-	if (is_guest_mode(vcpu) &&
-		nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
-		return;
-
-	if (irr == -1 || tpr < irr) {
-		vmcs_write32(TPR_THRESHOLD, 0);
-		return;
-	}
-
-	vmcs_write32(TPR_THRESHOLD, irr);
-}
-
-static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
-{
-	u32 sec_exec_control;
-
-	if (!lapic_in_kernel(vcpu))
-		return;
-
-	if (!flexpriority_enabled &&
-	    !cpu_has_vmx_virtualize_x2apic_mode())
-		return;
-
-	/* Postpone execution until vmcs01 is the current VMCS. */
-	if (is_guest_mode(vcpu)) {
-		to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
-		return;
-	}
-
-	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-	sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
-			      SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
-
-	switch (kvm_get_apic_mode(vcpu)) {
-	case LAPIC_MODE_INVALID:
-		WARN_ONCE(true, "Invalid local APIC state");
-	case LAPIC_MODE_DISABLED:
-		break;
-	case LAPIC_MODE_XAPIC:
-		if (flexpriority_enabled) {
-			sec_exec_control |=
-				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-			vmx_flush_tlb(vcpu, true);
-		}
-		break;
-	case LAPIC_MODE_X2APIC:
-		if (cpu_has_vmx_virtualize_x2apic_mode())
-			sec_exec_control |=
-				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
-		break;
-	}
-	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
-
-	vmx_update_msr_bitmap(vcpu);
-}
-
-static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
-{
-	if (!is_guest_mode(vcpu)) {
-		vmcs_write64(APIC_ACCESS_ADDR, hpa);
-		vmx_flush_tlb(vcpu, true);
-	}
-}
-
-static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
-{
-	u16 status;
-	u8 old;
-
-	if (max_isr == -1)
-		max_isr = 0;
-
-	status = vmcs_read16(GUEST_INTR_STATUS);
-	old = status >> 8;
-	if (max_isr != old) {
-		status &= 0xff;
-		status |= max_isr << 8;
-		vmcs_write16(GUEST_INTR_STATUS, status);
-	}
-}
-
-static void vmx_set_rvi(int vector)
-{
-	u16 status;
-	u8 old;
-
-	if (vector == -1)
-		vector = 0;
-
-	status = vmcs_read16(GUEST_INTR_STATUS);
-	old = (u8)status & 0xff;
-	if ((u8)vector != old) {
-		status &= ~0xff;
-		status |= (u8)vector;
-		vmcs_write16(GUEST_INTR_STATUS, status);
-	}
-}
-
-static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
-{
-	/*
-	 * When running L2, updating RVI is only relevant when
-	 * vmcs12 virtual-interrupt-delivery enabled.
-	 * However, it can be enabled only when L1 also
-	 * intercepts external-interrupts and in that case
-	 * we should not update vmcs02 RVI but instead intercept
-	 * interrupt. Therefore, do nothing when running L2.
-	 */
-	if (!is_guest_mode(vcpu))
-		vmx_set_rvi(max_irr);
-}
-
-static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int max_irr;
-	bool max_irr_updated;
-
-	WARN_ON(!vcpu->arch.apicv_active);
-	if (pi_test_on(&vmx->pi_desc)) {
-		pi_clear_on(&vmx->pi_desc);
-		/*
-		 * IOMMU can write to PIR.ON, so the barrier matters even on UP.
-		 * But on x86 this is just a compiler barrier anyway.
-		 */
-		smp_mb__after_atomic();
-		max_irr_updated =
-			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
-
-		/*
-		 * If we are running L2 and L1 has a new pending interrupt
-		 * which can be injected, we should re-evaluate
-		 * what should be done with this new L1 interrupt.
-		 * If L1 intercepts external-interrupts, we should
-		 * exit from L2 to L1. Otherwise, interrupt should be
-		 * delivered directly to L2.
-		 */
-		if (is_guest_mode(vcpu) && max_irr_updated) {
-			if (nested_exit_on_intr(vcpu))
-				kvm_vcpu_exiting_guest_mode(vcpu);
-			else
-				kvm_make_request(KVM_REQ_EVENT, vcpu);
-		}
-	} else {
-		max_irr = kvm_lapic_find_highest_irr(vcpu);
-	}
-	vmx_hwapic_irr_update(vcpu, max_irr);
-	return max_irr;
-}
-
-static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu)
-{
-	u8 rvi = vmx_get_rvi();
-	u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI);
-
-	return ((rvi & 0xf0) > (vppr & 0xf0));
-}
-
-static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
-{
-	if (!kvm_vcpu_apicv_active(vcpu))
-		return;
-
-	vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]);
-	vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]);
-	vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]);
-	vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]);
-}
-
-static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	pi_clear_on(&vmx->pi_desc);
-	memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
-}
-
-static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
-{
-	u32 exit_intr_info = 0;
-	u16 basic_exit_reason = (u16)vmx->exit_reason;
-
-	if (!(basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY
-	      || basic_exit_reason == EXIT_REASON_EXCEPTION_NMI))
-		return;
-
-	if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
-		exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-	vmx->exit_intr_info = exit_intr_info;
-
-	/* if exit due to PF check for async PF */
-	if (is_page_fault(exit_intr_info))
-		vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason();
-
-	/* Handle machine checks before interrupts are enabled */
-	if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY ||
-	    is_machine_check(exit_intr_info))
-		kvm_machine_check();
-
-	/* We need to handle NMIs before interrupts are enabled */
-	if (is_nmi(exit_intr_info)) {
-		kvm_before_interrupt(&vmx->vcpu);
-		asm("int $2");
-		kvm_after_interrupt(&vmx->vcpu);
-	}
-}
-
-static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
-{
-	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-
-	if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
-			== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
-		unsigned int vector;
-		unsigned long entry;
-		gate_desc *desc;
-		struct vcpu_vmx *vmx = to_vmx(vcpu);
-#ifdef CONFIG_X86_64
-		unsigned long tmp;
-#endif
-
-		vector =  exit_intr_info & INTR_INFO_VECTOR_MASK;
-		desc = (gate_desc *)vmx->host_idt_base + vector;
-		entry = gate_offset(desc);
-		asm volatile(
-#ifdef CONFIG_X86_64
-			"mov %%" _ASM_SP ", %[sp]\n\t"
-			"and $0xfffffffffffffff0, %%" _ASM_SP "\n\t"
-			"push $%c[ss]\n\t"
-			"push %[sp]\n\t"
-#endif
-			"pushf\n\t"
-			__ASM_SIZE(push) " $%c[cs]\n\t"
-			CALL_NOSPEC
-			:
-#ifdef CONFIG_X86_64
-			[sp]"=&r"(tmp),
-#endif
-			ASM_CALL_CONSTRAINT
-			:
-			THUNK_TARGET(entry),
-			[ss]"i"(__KERNEL_DS),
-			[cs]"i"(__KERNEL_CS)
-			);
-	}
-}
-STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
-
-static bool vmx_has_emulated_msr(int index)
-{
-	switch (index) {
-	case MSR_IA32_SMBASE:
-		/*
-		 * We cannot do SMM unless we can run the guest in big
-		 * real mode.
-		 */
-		return enable_unrestricted_guest || emulate_invalid_guest_state;
-	case MSR_AMD64_VIRT_SPEC_CTRL:
-		/* This is AMD only.  */
-		return false;
-	default:
-		return true;
-	}
-}
-
-static bool vmx_mpx_supported(void)
-{
-	return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) &&
-		(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS);
-}
-
-static bool vmx_xsaves_supported(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_XSAVES;
-}
-
-static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
-{
-	u32 exit_intr_info;
-	bool unblock_nmi;
-	u8 vector;
-	bool idtv_info_valid;
-
-	idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK;
-
-	if (enable_vnmi) {
-		if (vmx->loaded_vmcs->nmi_known_unmasked)
-			return;
-		/*
-		 * Can't use vmx->exit_intr_info since we're not sure what
-		 * the exit reason is.
-		 */
-		exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-		unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
-		vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
-		/*
-		 * SDM 3: 27.7.1.2 (September 2008)
-		 * Re-set bit "block by NMI" before VM entry if vmexit caused by
-		 * a guest IRET fault.
-		 * SDM 3: 23.2.2 (September 2008)
-		 * Bit 12 is undefined in any of the following cases:
-		 *  If the VM exit sets the valid bit in the IDT-vectoring
-		 *   information field.
-		 *  If the VM exit is due to a double fault.
-		 */
-		if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
-		    vector != DF_VECTOR && !idtv_info_valid)
-			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
-				      GUEST_INTR_STATE_NMI);
-		else
-			vmx->loaded_vmcs->nmi_known_unmasked =
-				!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
-				  & GUEST_INTR_STATE_NMI);
-	} else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked))
-		vmx->loaded_vmcs->vnmi_blocked_time +=
-			ktime_to_ns(ktime_sub(ktime_get(),
-					      vmx->loaded_vmcs->entry_time));
-}
-
-static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
-				      u32 idt_vectoring_info,
-				      int instr_len_field,
-				      int error_code_field)
-{
-	u8 vector;
-	int type;
-	bool idtv_info_valid;
-
-	idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
-
-	vcpu->arch.nmi_injected = false;
-	kvm_clear_exception_queue(vcpu);
-	kvm_clear_interrupt_queue(vcpu);
-
-	if (!idtv_info_valid)
-		return;
-
-	kvm_make_request(KVM_REQ_EVENT, vcpu);
-
-	vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK;
-	type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK;
-
-	switch (type) {
-	case INTR_TYPE_NMI_INTR:
-		vcpu->arch.nmi_injected = true;
-		/*
-		 * SDM 3: 27.7.1.2 (September 2008)
-		 * Clear bit "block by NMI" before VM entry if a NMI
-		 * delivery faulted.
-		 */
-		vmx_set_nmi_mask(vcpu, false);
-		break;
-	case INTR_TYPE_SOFT_EXCEPTION:
-		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
-		/* fall through */
-	case INTR_TYPE_HARD_EXCEPTION:
-		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
-			u32 err = vmcs_read32(error_code_field);
-			kvm_requeue_exception_e(vcpu, vector, err);
-		} else
-			kvm_requeue_exception(vcpu, vector);
-		break;
-	case INTR_TYPE_SOFT_INTR:
-		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
-		/* fall through */
-	case INTR_TYPE_EXT_INTR:
-		kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR);
-		break;
-	default:
-		break;
-	}
-}
-
-static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
-{
-	__vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info,
-				  VM_EXIT_INSTRUCTION_LEN,
-				  IDT_VECTORING_ERROR_CODE);
-}
-
-static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
-{
-	__vmx_complete_interrupts(vcpu,
-				  vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
-				  VM_ENTRY_INSTRUCTION_LEN,
-				  VM_ENTRY_EXCEPTION_ERROR_CODE);
-
-	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
-}
-
-static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
-{
-	int i, nr_msrs;
-	struct perf_guest_switch_msr *msrs;
-
-	msrs = perf_guest_get_msrs(&nr_msrs);
-
-	if (!msrs)
-		return;
-
-	for (i = 0; i < nr_msrs; i++)
-		if (msrs[i].host == msrs[i].guest)
-			clear_atomic_switch_msr(vmx, msrs[i].msr);
-		else
-			add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
-					msrs[i].host, false);
-}
-
-static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val)
-{
-	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val);
-	if (!vmx->loaded_vmcs->hv_timer_armed)
-		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
-			      PIN_BASED_VMX_PREEMPTION_TIMER);
-	vmx->loaded_vmcs->hv_timer_armed = true;
-}
-
-static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u64 tscl;
-	u32 delta_tsc;
-
-	if (vmx->req_immediate_exit) {
-		vmx_arm_hv_timer(vmx, 0);
-		return;
-	}
-
-	if (vmx->hv_deadline_tsc != -1) {
-		tscl = rdtsc();
-		if (vmx->hv_deadline_tsc > tscl)
-			/* set_hv_timer ensures the delta fits in 32-bits */
-			delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
-				cpu_preemption_timer_multi);
-		else
-			delta_tsc = 0;
-
-		vmx_arm_hv_timer(vmx, delta_tsc);
-		return;
-	}
-
-	if (vmx->loaded_vmcs->hv_timer_armed)
-		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
-				PIN_BASED_VMX_PREEMPTION_TIMER);
-	vmx->loaded_vmcs->hv_timer_armed = false;
-}
-
-static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr3, cr4, evmcs_rsp;
-
-	/* Record the guest's net vcpu time for enforced NMI injections. */
-	if (unlikely(!enable_vnmi &&
-		     vmx->loaded_vmcs->soft_vnmi_blocked))
-		vmx->loaded_vmcs->entry_time = ktime_get();
-
-	/* Don't enter VMX if guest state is invalid, let the exit handler
-	   start emulation until we arrive back to a valid state */
-	if (vmx->emulation_required)
-		return;
-
-	if (vmx->ple_window_dirty) {
-		vmx->ple_window_dirty = false;
-		vmcs_write32(PLE_WINDOW, vmx->ple_window);
-	}
-
-	if (vmx->nested.sync_shadow_vmcs) {
-		copy_vmcs12_to_shadow(vmx);
-		vmx->nested.sync_shadow_vmcs = false;
-	}
-
-	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
-		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
-	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
-		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
-
-	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
-		vmcs_writel(HOST_CR3, cr3);
-		vmx->loaded_vmcs->host_state.cr3 = cr3;
-	}
-
-	cr4 = cr4_read_shadow();
-	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
-		vmcs_writel(HOST_CR4, cr4);
-		vmx->loaded_vmcs->host_state.cr4 = cr4;
-	}
-
-	/* When single-stepping over STI and MOV SS, we must clear the
-	 * corresponding interruptibility bits in the guest state. Otherwise
-	 * vmentry fails as it then expects bit 14 (BS) in pending debug
-	 * exceptions being set, but that's not correct for the guest debugging
-	 * case. */
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		vmx_set_interrupt_shadow(vcpu, 0);
-
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
-	    vcpu->arch.pkru != vmx->host_pkru)
-		__write_pkru(vcpu->arch.pkru);
-
-	atomic_switch_perf_msrs(vmx);
-
-	vmx_update_hv_timer(vcpu);
-
-	/*
-	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
-	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
-	 * is no need to worry about the conditional branch over the wrmsr
-	 * being speculatively taken.
-	 */
-	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
-
-	vmx->__launched = vmx->loaded_vmcs->launched;
-
-	evmcs_rsp = static_branch_unlikely(&enable_evmcs) ?
-		(unsigned long)&current_evmcs->host_rsp : 0;
-
-	if (static_branch_unlikely(&vmx_l1d_should_flush))
-		vmx_l1d_flush(vcpu);
-
-	asm(
-		/* Store host registers */
-		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
-		"push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */
-		"push %%" _ASM_CX " \n\t"
-		"cmp %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
-		"je 1f \n\t"
-		"mov %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
-		/* Avoid VMWRITE when Enlightened VMCS is in use */
-		"test %%" _ASM_SI ", %%" _ASM_SI " \n\t"
-		"jz 2f \n\t"
-		"mov %%" _ASM_SP ", (%%" _ASM_SI ") \n\t"
-		"jmp 1f \n\t"
-		"2: \n\t"
-		__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
-		"1: \n\t"
-		/* Reload cr2 if changed */
-		"mov %c[cr2](%0), %%" _ASM_AX " \n\t"
-		"mov %%cr2, %%" _ASM_DX " \n\t"
-		"cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t"
-		"je 3f \n\t"
-		"mov %%" _ASM_AX", %%cr2 \n\t"
-		"3: \n\t"
-		/* Check if vmlaunch of vmresume is needed */
-		"cmpl $0, %c[launched](%0) \n\t"
-		/* Load guest registers.  Don't clobber flags. */
-		"mov %c[rax](%0), %%" _ASM_AX " \n\t"
-		"mov %c[rbx](%0), %%" _ASM_BX " \n\t"
-		"mov %c[rdx](%0), %%" _ASM_DX " \n\t"
-		"mov %c[rsi](%0), %%" _ASM_SI " \n\t"
-		"mov %c[rdi](%0), %%" _ASM_DI " \n\t"
-		"mov %c[rbp](%0), %%" _ASM_BP " \n\t"
-#ifdef CONFIG_X86_64
-		"mov %c[r8](%0),  %%r8  \n\t"
-		"mov %c[r9](%0),  %%r9  \n\t"
-		"mov %c[r10](%0), %%r10 \n\t"
-		"mov %c[r11](%0), %%r11 \n\t"
-		"mov %c[r12](%0), %%r12 \n\t"
-		"mov %c[r13](%0), %%r13 \n\t"
-		"mov %c[r14](%0), %%r14 \n\t"
-		"mov %c[r15](%0), %%r15 \n\t"
-#endif
-		"mov %c[rcx](%0), %%" _ASM_CX " \n\t" /* kills %0 (ecx) */
-
-		/* Enter guest mode */
-		"jne 1f \n\t"
-		__ex(ASM_VMX_VMLAUNCH) "\n\t"
-		"jmp 2f \n\t"
-		"1: " __ex(ASM_VMX_VMRESUME) "\n\t"
-		"2: "
-		/* Save guest registers, load host registers, keep flags */
-		"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
-		"pop %0 \n\t"
-		"setbe %c[fail](%0)\n\t"
-		"mov %%" _ASM_AX ", %c[rax](%0) \n\t"
-		"mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
-		__ASM_SIZE(pop) " %c[rcx](%0) \n\t"
-		"mov %%" _ASM_DX ", %c[rdx](%0) \n\t"
-		"mov %%" _ASM_SI ", %c[rsi](%0) \n\t"
-		"mov %%" _ASM_DI ", %c[rdi](%0) \n\t"
-		"mov %%" _ASM_BP ", %c[rbp](%0) \n\t"
-#ifdef CONFIG_X86_64
-		"mov %%r8,  %c[r8](%0) \n\t"
-		"mov %%r9,  %c[r9](%0) \n\t"
-		"mov %%r10, %c[r10](%0) \n\t"
-		"mov %%r11, %c[r11](%0) \n\t"
-		"mov %%r12, %c[r12](%0) \n\t"
-		"mov %%r13, %c[r13](%0) \n\t"
-		"mov %%r14, %c[r14](%0) \n\t"
-		"mov %%r15, %c[r15](%0) \n\t"
-		"xor %%r8d,  %%r8d \n\t"
-		"xor %%r9d,  %%r9d \n\t"
-		"xor %%r10d, %%r10d \n\t"
-		"xor %%r11d, %%r11d \n\t"
-		"xor %%r12d, %%r12d \n\t"
-		"xor %%r13d, %%r13d \n\t"
-		"xor %%r14d, %%r14d \n\t"
-		"xor %%r15d, %%r15d \n\t"
-#endif
-		"mov %%cr2, %%" _ASM_AX "   \n\t"
-		"mov %%" _ASM_AX ", %c[cr2](%0) \n\t"
-
-		"xor %%eax, %%eax \n\t"
-		"xor %%ebx, %%ebx \n\t"
-		"xor %%esi, %%esi \n\t"
-		"xor %%edi, %%edi \n\t"
-		"pop  %%" _ASM_BP "; pop  %%" _ASM_DX " \n\t"
-		".pushsection .rodata \n\t"
-		".global vmx_return \n\t"
-		"vmx_return: " _ASM_PTR " 2b \n\t"
-		".popsection"
-	      : : "c"(vmx), "d"((unsigned long)HOST_RSP), "S"(evmcs_rsp),
-		[launched]"i"(offsetof(struct vcpu_vmx, __launched)),
-		[fail]"i"(offsetof(struct vcpu_vmx, fail)),
-		[host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)),
-		[rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])),
-		[rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])),
-		[rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])),
-		[rdx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDX])),
-		[rsi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RSI])),
-		[rdi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDI])),
-		[rbp]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBP])),
-#ifdef CONFIG_X86_64
-		[r8]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R8])),
-		[r9]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R9])),
-		[r10]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R10])),
-		[r11]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R11])),
-		[r12]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R12])),
-		[r13]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R13])),
-		[r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])),
-		[r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])),
-#endif
-		[cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)),
-		[wordsize]"i"(sizeof(ulong))
-	      : "cc", "memory"
-#ifdef CONFIG_X86_64
-		, "rax", "rbx", "rdi"
-		, "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
-#else
-		, "eax", "ebx", "edi"
-#endif
-	      );
-
-	/*
-	 * We do not use IBRS in the kernel. If this vCPU has used the
-	 * SPEC_CTRL MSR it may have left it on; save the value and
-	 * turn it off. This is much more efficient than blindly adding
-	 * it to the atomic save/restore list. Especially as the former
-	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
-	 *
-	 * For non-nested case:
-	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
-	 * save it.
-	 *
-	 * For nested case:
-	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
-	 * save it.
-	 */
-	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
-		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
-
-	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
-
-	/* Eliminate branch target predictions from guest mode */
-	vmexit_fill_RSB();
-
-	/* All fields are clean at this point */
-	if (static_branch_unlikely(&enable_evmcs))
-		current_evmcs->hv_clean_fields |=
-			HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
-
-	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
-	if (vmx->host_debugctlmsr)
-		update_debugctlmsr(vmx->host_debugctlmsr);
-
-#ifndef CONFIG_X86_64
-	/*
-	 * The sysexit path does not restore ds/es, so we must set them to
-	 * a reasonable value ourselves.
-	 *
-	 * We can't defer this to vmx_prepare_switch_to_host() since that
-	 * function may be executed in interrupt context, which saves and
-	 * restore segments around it, nullifying its effect.
-	 */
-	loadsegment(ds, __USER_DS);
-	loadsegment(es, __USER_DS);
-#endif
-
-	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
-				  | (1 << VCPU_EXREG_RFLAGS)
-				  | (1 << VCPU_EXREG_PDPTR)
-				  | (1 << VCPU_EXREG_SEGMENTS)
-				  | (1 << VCPU_EXREG_CR3));
-	vcpu->arch.regs_dirty = 0;
-
-	/*
-	 * eager fpu is enabled if PKEY is supported and CR4 is switched
-	 * back on host, so it is safe to read guest PKRU from current
-	 * XSAVE.
-	 */
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
-		vcpu->arch.pkru = __read_pkru();
-		if (vcpu->arch.pkru != vmx->host_pkru)
-			__write_pkru(vmx->host_pkru);
-	}
-
-	vmx->nested.nested_run_pending = 0;
-	vmx->idt_vectoring_info = 0;
-
-	vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON);
-	if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
-		return;
-
-	vmx->loaded_vmcs->launched = 1;
-	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
-
-	vmx_complete_atomic_exit(vmx);
-	vmx_recover_nmi_blocking(vmx);
-	vmx_complete_interrupts(vmx);
-}
-STACK_FRAME_NON_STANDARD(vmx_vcpu_run);
-
-static struct kvm *vmx_vm_alloc(void)
-{
-	struct kvm_vmx *kvm_vmx = vzalloc(sizeof(struct kvm_vmx));
-	return &kvm_vmx->kvm;
-}
-
-static void vmx_vm_free(struct kvm *kvm)
-{
-	vfree(to_kvm_vmx(kvm));
-}
-
-static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int cpu;
-
-	if (vmx->loaded_vmcs == vmcs)
-		return;
-
-	cpu = get_cpu();
-	vmx_vcpu_put(vcpu);
-	vmx->loaded_vmcs = vmcs;
-	vmx_vcpu_load(vcpu, cpu);
-	put_cpu();
-}
-
-/*
- * Ensure that the current vmcs of the logical processor is the
- * vmcs01 of the vcpu before calling free_nested().
- */
-static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
-{
-       struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-       vcpu_load(vcpu);
-       vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-       free_nested(vmx);
-       vcpu_put(vcpu);
-}
-
-static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (enable_pml)
-		vmx_destroy_pml_buffer(vmx);
-	free_vpid(vmx->vpid);
-	leave_guest_mode(vcpu);
-	vmx_free_vcpu_nested(vcpu);
-	free_loaded_vmcs(vmx->loaded_vmcs);
-	kfree(vmx->guest_msrs);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vmx);
-}
-
-static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
-{
-	int err;
-	struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	unsigned long *msr_bitmap;
-	int cpu;
-
-	if (!vmx)
-		return ERR_PTR(-ENOMEM);
-
-	vmx->vpid = allocate_vpid();
-
-	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
-
-	err = -ENOMEM;
-
-	/*
-	 * If PML is turned on, failure on enabling PML just results in failure
-	 * of creating the vcpu, therefore we can simplify PML logic (by
-	 * avoiding dealing with cases, such as enabling PML partially on vcpus
-	 * for the guest, etc.
-	 */
-	if (enable_pml) {
-		vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!vmx->pml_pg)
-			goto uninit_vcpu;
-	}
-
-	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
-		     > PAGE_SIZE);
-
-	if (!vmx->guest_msrs)
-		goto free_pml;
-
-	err = alloc_loaded_vmcs(&vmx->vmcs01);
-	if (err < 0)
-		goto free_msrs;
-
-	msr_bitmap = vmx->vmcs01.msr_bitmap;
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
-	vmx->msr_bitmap_mode = 0;
-
-	vmx->loaded_vmcs = &vmx->vmcs01;
-	cpu = get_cpu();
-	vmx_vcpu_load(&vmx->vcpu, cpu);
-	vmx->vcpu.cpu = cpu;
-	vmx_vcpu_setup(vmx);
-	vmx_vcpu_put(&vmx->vcpu);
-	put_cpu();
-	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
-		err = alloc_apic_access_page(kvm);
-		if (err)
-			goto free_vmcs;
-	}
-
-	if (enable_ept && !enable_unrestricted_guest) {
-		err = init_rmode_identity_map(kvm);
-		if (err)
-			goto free_vmcs;
-	}
-
-	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
-					   kvm_vcpu_apicv_active(&vmx->vcpu));
-
-	vmx->nested.posted_intr_nv = -1;
-	vmx->nested.current_vmptr = -1ull;
-
-	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
-
-	/*
-	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
-	 * or POSTED_INTR_WAKEUP_VECTOR.
-	 */
-	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
-	vmx->pi_desc.sn = 1;
-
-	return &vmx->vcpu;
-
-free_vmcs:
-	free_loaded_vmcs(vmx->loaded_vmcs);
-free_msrs:
-	kfree(vmx->guest_msrs);
-free_pml:
-	vmx_destroy_pml_buffer(vmx);
-uninit_vcpu:
-	kvm_vcpu_uninit(&vmx->vcpu);
-free_vcpu:
-	free_vpid(vmx->vpid);
-	kmem_cache_free(kvm_vcpu_cache, vmx);
-	return ERR_PTR(err);
-}
-
-#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
-#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
-
-static int vmx_vm_init(struct kvm *kvm)
-{
-	spin_lock_init(&to_kvm_vmx(kvm)->ept_pointer_lock);
-
-	if (!ple_gap)
-		kvm->arch.pause_in_guest = true;
-
-	if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
-		switch (l1tf_mitigation) {
-		case L1TF_MITIGATION_OFF:
-		case L1TF_MITIGATION_FLUSH_NOWARN:
-			/* 'I explicitly don't care' is set */
-			break;
-		case L1TF_MITIGATION_FLUSH:
-		case L1TF_MITIGATION_FLUSH_NOSMT:
-		case L1TF_MITIGATION_FULL:
-			/*
-			 * Warn upon starting the first VM in a potentially
-			 * insecure environment.
-			 */
-			if (cpu_smt_control == CPU_SMT_ENABLED)
-				pr_warn_once(L1TF_MSG_SMT);
-			if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
-				pr_warn_once(L1TF_MSG_L1D);
-			break;
-		case L1TF_MITIGATION_FULL_FORCE:
-			/* Flush is enforced */
-			break;
-		}
-	}
-	return 0;
-}
-
-static void __init vmx_check_processor_compat(void *rtn)
-{
-	struct vmcs_config vmcs_conf;
-
-	*(int *)rtn = 0;
-	if (setup_vmcs_config(&vmcs_conf) < 0)
-		*(int *)rtn = -EIO;
-	nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, enable_apicv);
-	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
-		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
-				smp_processor_id());
-		*(int *)rtn = -EIO;
-	}
-}
-
-static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	u8 cache;
-	u64 ipat = 0;
-
-	/* For VT-d and EPT combination
-	 * 1. MMIO: always map as UC
-	 * 2. EPT with VT-d:
-	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.
-	 *   b. VT-d with snooping control feature: snooping control feature of
-	 *	VT-d engine can guarantee the cache correctness. Just set it
-	 *	to WB to keep consistent with host. So the same as item 3.
-	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
-	 *    consistent with host MTRR
-	 */
-	if (is_mmio) {
-		cache = MTRR_TYPE_UNCACHABLE;
-		goto exit;
-	}
-
-	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
-		ipat = VMX_EPT_IPAT_BIT;
-		cache = MTRR_TYPE_WRBACK;
-		goto exit;
-	}
-
-	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
-		ipat = VMX_EPT_IPAT_BIT;
-		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
-			cache = MTRR_TYPE_WRBACK;
-		else
-			cache = MTRR_TYPE_UNCACHABLE;
-		goto exit;
-	}
-
-	cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
-
-exit:
-	return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat;
-}
-
-static int vmx_get_lpage_level(void)
-{
-	if (enable_ept && !cpu_has_vmx_ept_1g_page())
-		return PT_DIRECTORY_LEVEL;
-	else
-		/* For shadow and EPT supported 1GB page */
-		return PT_PDPE_LEVEL;
-}
-
-static void vmcs_set_secondary_exec_control(u32 new_ctl)
-{
-	/*
-	 * These bits in the secondary execution controls field
-	 * are dynamic, the others are mostly based on the hypervisor
-	 * architecture and the guest's CPUID.  Do not touch the
-	 * dynamic bits.
-	 */
-	u32 mask =
-		SECONDARY_EXEC_SHADOW_VMCS |
-		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
-		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
-		SECONDARY_EXEC_DESC;
-
-	u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-
-	vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
-		     (new_ctl & ~mask) | (cur_ctl & mask));
-}
-
-/*
- * Generate MSR_IA32_VMX_CR{0,4}_FIXED1 according to CPUID. Only set bits
- * (indicating "allowed-1") if they are supported in the guest's CPUID.
- */
-static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_cpuid_entry2 *entry;
-
-	vmx->nested.msrs.cr0_fixed1 = 0xffffffff;
-	vmx->nested.msrs.cr4_fixed1 = X86_CR4_PCE;
-
-#define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do {		\
-	if (entry && (entry->_reg & (_cpuid_mask)))			\
-		vmx->nested.msrs.cr4_fixed1 |= (_cr4_mask);	\
-} while (0)
-
-	entry = kvm_find_cpuid_entry(vcpu, 0x1, 0);
-	cr4_fixed1_update(X86_CR4_VME,        edx, bit(X86_FEATURE_VME));
-	cr4_fixed1_update(X86_CR4_PVI,        edx, bit(X86_FEATURE_VME));
-	cr4_fixed1_update(X86_CR4_TSD,        edx, bit(X86_FEATURE_TSC));
-	cr4_fixed1_update(X86_CR4_DE,         edx, bit(X86_FEATURE_DE));
-	cr4_fixed1_update(X86_CR4_PSE,        edx, bit(X86_FEATURE_PSE));
-	cr4_fixed1_update(X86_CR4_PAE,        edx, bit(X86_FEATURE_PAE));
-	cr4_fixed1_update(X86_CR4_MCE,        edx, bit(X86_FEATURE_MCE));
-	cr4_fixed1_update(X86_CR4_PGE,        edx, bit(X86_FEATURE_PGE));
-	cr4_fixed1_update(X86_CR4_OSFXSR,     edx, bit(X86_FEATURE_FXSR));
-	cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM));
-	cr4_fixed1_update(X86_CR4_VMXE,       ecx, bit(X86_FEATURE_VMX));
-	cr4_fixed1_update(X86_CR4_SMXE,       ecx, bit(X86_FEATURE_SMX));
-	cr4_fixed1_update(X86_CR4_PCIDE,      ecx, bit(X86_FEATURE_PCID));
-	cr4_fixed1_update(X86_CR4_OSXSAVE,    ecx, bit(X86_FEATURE_XSAVE));
-
-	entry = kvm_find_cpuid_entry(vcpu, 0x7, 0);
-	cr4_fixed1_update(X86_CR4_FSGSBASE,   ebx, bit(X86_FEATURE_FSGSBASE));
-	cr4_fixed1_update(X86_CR4_SMEP,       ebx, bit(X86_FEATURE_SMEP));
-	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
-	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
-	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));
-
-#undef cr4_fixed1_update
-}
-
-static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (kvm_mpx_supported()) {
-		bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX);
-
-		if (mpx_enabled) {
-			vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
-			vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
-		} else {
-			vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS;
-			vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS;
-		}
-	}
-}
-
-static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (cpu_has_secondary_exec_ctrls()) {
-		vmx_compute_secondary_exec_control(vmx);
-		vmcs_set_secondary_exec_control(vmx->secondary_exec_control);
-	}
-
-	if (nested_vmx_allowed(vcpu))
-		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
-			FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
-	else
-		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
-			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
-
-	if (nested_vmx_allowed(vcpu)) {
-		nested_vmx_cr_fixed1_bits_update(vcpu);
-		nested_vmx_entry_exit_ctls_update(vcpu);
-	}
-}
-
-static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
-{
-	if (func == 1 && nested)
-		entry->ecx |= bit(X86_FEATURE_VMX);
-}
-
-static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
-		struct x86_exception *fault)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 exit_reason;
-	unsigned long exit_qualification = vcpu->arch.exit_qualification;
-
-	if (vmx->nested.pml_full) {
-		exit_reason = EXIT_REASON_PML_FULL;
-		vmx->nested.pml_full = false;
-		exit_qualification &= INTR_INFO_UNBLOCK_NMI;
-	} else if (fault->error_code & PFERR_RSVD_MASK)
-		exit_reason = EXIT_REASON_EPT_MISCONFIG;
-	else
-		exit_reason = EXIT_REASON_EPT_VIOLATION;
-
-	nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification);
-	vmcs12->guest_physical_address = fault->address;
-}
-
-static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu)
-{
-	return nested_ept_get_cr3(vcpu) & VMX_EPTP_AD_ENABLE_BIT;
-}
-
-/* Callbacks for nested_ept_init_mmu_context: */
-
-static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
-{
-	/* return the page table to be shadowed - in our case, EPT12 */
-	return get_vmcs12(vcpu)->ept_pointer;
-}
-
-static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
-{
-	WARN_ON(mmu_is_nested(vcpu));
-	if (!valid_ept_address(vcpu, nested_ept_get_cr3(vcpu)))
-		return 1;
-
-	kvm_init_shadow_ept_mmu(vcpu,
-			to_vmx(vcpu)->nested.msrs.ept_caps &
-			VMX_EPT_EXECUTE_ONLY_BIT,
-			nested_ept_ad_enabled(vcpu),
-			nested_ept_get_cr3(vcpu));
-	vcpu->arch.mmu.set_cr3           = vmx_set_cr3;
-	vcpu->arch.mmu.get_cr3           = nested_ept_get_cr3;
-	vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
-
-	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
-	return 0;
-}
-
-static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
-}
-
-static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
-					    u16 error_code)
-{
-	bool inequality, bit;
-
-	bit = (vmcs12->exception_bitmap & (1u << PF_VECTOR)) != 0;
-	inequality =
-		(error_code & vmcs12->page_fault_error_code_mask) !=
-		 vmcs12->page_fault_error_code_match;
-	return inequality ^ bit;
-}
-
-static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
-		struct x86_exception *fault)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-
-	WARN_ON(!is_guest_mode(vcpu));
-
-	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
-		!to_vmx(vcpu)->nested.nested_run_pending) {
-		vmcs12->vm_exit_intr_error_code = fault->error_code;
-		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
-				  INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
-				  fault->address);
-	} else {
-		kvm_inject_page_fault(vcpu, fault);
-	}
-}
-
-static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
-						 struct vmcs12 *vmcs12);
-
-static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct page *page;
-	u64 hpa;
-
-	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		/*
-		 * Translate L1 physical address to host physical
-		 * address for vmcs02. Keep the page pinned, so this
-		 * physical address remains valid. We keep a reference
-		 * to it so we can release it later.
-		 */
-		if (vmx->nested.apic_access_page) { /* shouldn't happen */
-			kvm_release_page_dirty(vmx->nested.apic_access_page);
-			vmx->nested.apic_access_page = NULL;
-		}
-		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
-		/*
-		 * If translation failed, no matter: This feature asks
-		 * to exit when accessing the given address, and if it
-		 * can never be accessed, this feature won't do
-		 * anything anyway.
-		 */
-		if (!is_error_page(page)) {
-			vmx->nested.apic_access_page = page;
-			hpa = page_to_phys(vmx->nested.apic_access_page);
-			vmcs_write64(APIC_ACCESS_ADDR, hpa);
-		} else {
-			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
-					SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
-		}
-	}
-
-	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
-		if (vmx->nested.virtual_apic_page) { /* shouldn't happen */
-			kvm_release_page_dirty(vmx->nested.virtual_apic_page);
-			vmx->nested.virtual_apic_page = NULL;
-		}
-		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->virtual_apic_page_addr);
-
-		/*
-		 * If translation failed, VM entry will fail because
-		 * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
-		 * Failing the vm entry is _not_ what the processor
-		 * does but it's basically the only possibility we
-		 * have.  We could still enter the guest if CR8 load
-		 * exits are enabled, CR8 store exits are enabled, and
-		 * virtualize APIC access is disabled; in this case
-		 * the processor would never use the TPR shadow and we
-		 * could simply clear the bit from the execution
-		 * control.  But such a configuration is useless, so
-		 * let's keep the code simple.
-		 */
-		if (!is_error_page(page)) {
-			vmx->nested.virtual_apic_page = page;
-			hpa = page_to_phys(vmx->nested.virtual_apic_page);
-			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
-		}
-	}
-
-	if (nested_cpu_has_posted_intr(vmcs12)) {
-		if (vmx->nested.pi_desc_page) { /* shouldn't happen */
-			kunmap(vmx->nested.pi_desc_page);
-			kvm_release_page_dirty(vmx->nested.pi_desc_page);
-			vmx->nested.pi_desc_page = NULL;
-			vmx->nested.pi_desc = NULL;
-			vmcs_write64(POSTED_INTR_DESC_ADDR, -1ull);
-		}
-		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->posted_intr_desc_addr);
-		if (is_error_page(page))
-			return;
-		vmx->nested.pi_desc_page = page;
-		vmx->nested.pi_desc = kmap(vmx->nested.pi_desc_page);
-		vmx->nested.pi_desc =
-			(struct pi_desc *)((void *)vmx->nested.pi_desc +
-			(unsigned long)(vmcs12->posted_intr_desc_addr &
-			(PAGE_SIZE - 1)));
-		vmcs_write64(POSTED_INTR_DESC_ADDR,
-			page_to_phys(vmx->nested.pi_desc_page) +
-			(unsigned long)(vmcs12->posted_intr_desc_addr &
-			(PAGE_SIZE - 1)));
-	}
-	if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12))
-		vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL,
-			      CPU_BASED_USE_MSR_BITMAPS);
-	else
-		vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
-				CPU_BASED_USE_MSR_BITMAPS);
-}
-
-static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
-{
-	u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	/*
-	 * A timer value of zero is architecturally guaranteed to cause
-	 * a VMExit prior to executing any instructions in the guest.
-	 */
-	if (preemption_timeout == 0) {
-		vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
-		return;
-	}
-
-	if (vcpu->arch.virtual_tsc_khz == 0)
-		return;
-
-	preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
-	preemption_timeout *= 1000000;
-	do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
-	hrtimer_start(&vmx->nested.preemption_timer,
-		      ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
-}
-
-static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
-					       struct vmcs12 *vmcs12)
-{
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
-		return 0;
-
-	if (!page_address_valid(vcpu, vmcs12->io_bitmap_a) ||
-	    !page_address_valid(vcpu, vmcs12->io_bitmap_b))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu,
-						struct vmcs12 *vmcs12)
-{
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
-		return 0;
-
-	if (!page_address_valid(vcpu, vmcs12->msr_bitmap))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
-						struct vmcs12 *vmcs12)
-{
-	if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
-		return 0;
-
-	if (!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))
-		return -EINVAL;
-
-	return 0;
-}
-
-/*
- * Merge L0's and L1's MSR bitmap, return false to indicate that
- * we do not use the hardware.
- */
-static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
-						 struct vmcs12 *vmcs12)
-{
-	int msr;
-	struct page *page;
-	unsigned long *msr_bitmap_l1;
-	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
-	/*
-	 * pred_cmd & spec_ctrl are trying to verify two things:
-	 *
-	 * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
-	 *    ensures that we do not accidentally generate an L02 MSR bitmap
-	 *    from the L12 MSR bitmap that is too permissive.
-	 * 2. That L1 or L2s have actually used the MSR. This avoids
-	 *    unnecessarily merging of the bitmap if the MSR is unused. This
-	 *    works properly because we only update the L01 MSR bitmap lazily.
-	 *    So even if L0 should pass L1 these MSRs, the L01 bitmap is only
-	 *    updated to reflect this when L1 (or its L2s) actually write to
-	 *    the MSR.
-	 */
-	bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
-	bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
-
-	/* Nothing to do if the MSR bitmap is not in use.  */
-	if (!cpu_has_vmx_msr_bitmap() ||
-	    !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
-		return false;
-
-	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
-	    !pred_cmd && !spec_ctrl)
-		return false;
-
-	page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap);
-	if (is_error_page(page))
-		return false;
-
-	msr_bitmap_l1 = (unsigned long *)kmap(page);
-	if (nested_cpu_has_apic_reg_virt(vmcs12)) {
-		/*
-		 * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
-		 * just lets the processor take the value from the virtual-APIC page;
-		 * take those 256 bits directly from the L1 bitmap.
-		 */
-		for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-			unsigned word = msr / BITS_PER_LONG;
-			msr_bitmap_l0[word] = msr_bitmap_l1[word];
-			msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
-		}
-	} else {
-		for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-			unsigned word = msr / BITS_PER_LONG;
-			msr_bitmap_l0[word] = ~0;
-			msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
-		}
-	}
-
-	nested_vmx_disable_intercept_for_msr(
-		msr_bitmap_l1, msr_bitmap_l0,
-		X2APIC_MSR(APIC_TASKPRI),
-		MSR_TYPE_W);
-
-	if (nested_cpu_has_vid(vmcs12)) {
-		nested_vmx_disable_intercept_for_msr(
-			msr_bitmap_l1, msr_bitmap_l0,
-			X2APIC_MSR(APIC_EOI),
-			MSR_TYPE_W);
-		nested_vmx_disable_intercept_for_msr(
-			msr_bitmap_l1, msr_bitmap_l0,
-			X2APIC_MSR(APIC_SELF_IPI),
-			MSR_TYPE_W);
-	}
-
-	if (spec_ctrl)
-		nested_vmx_disable_intercept_for_msr(
-					msr_bitmap_l1, msr_bitmap_l0,
-					MSR_IA32_SPEC_CTRL,
-					MSR_TYPE_R | MSR_TYPE_W);
-
-	if (pred_cmd)
-		nested_vmx_disable_intercept_for_msr(
-					msr_bitmap_l1, msr_bitmap_l0,
-					MSR_IA32_PRED_CMD,
-					MSR_TYPE_W);
-
-	kunmap(page);
-	kvm_release_page_clean(page);
-
-	return true;
-}
-
-static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
-				       struct vmcs12 *vmcs12)
-{
-	struct vmcs12 *shadow;
-	struct page *page;
-
-	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
-	    vmcs12->vmcs_link_pointer == -1ull)
-		return;
-
-	shadow = get_shadow_vmcs12(vcpu);
-	page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->vmcs_link_pointer);
-
-	memcpy(shadow, kmap(page), VMCS12_SIZE);
-
-	kunmap(page);
-	kvm_release_page_clean(page);
-}
-
-static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
-					      struct vmcs12 *vmcs12)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
-	    vmcs12->vmcs_link_pointer == -1ull)
-		return;
-
-	kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer,
-			get_shadow_vmcs12(vcpu), VMCS12_SIZE);
-}
-
-static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
-					  struct vmcs12 *vmcs12)
-{
-	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
-	    !page_address_valid(vcpu, vmcs12->apic_access_addr))
-		return -EINVAL;
-	else
-		return 0;
-}
-
-static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
-					   struct vmcs12 *vmcs12)
-{
-	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
-	    !nested_cpu_has_apic_reg_virt(vmcs12) &&
-	    !nested_cpu_has_vid(vmcs12) &&
-	    !nested_cpu_has_posted_intr(vmcs12))
-		return 0;
-
-	/*
-	 * If virtualize x2apic mode is enabled,
-	 * virtualize apic access must be disabled.
-	 */
-	if (nested_cpu_has_virt_x2apic_mode(vmcs12) &&
-	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
-		return -EINVAL;
-
-	/*
-	 * If virtual interrupt delivery is enabled,
-	 * we must exit on external interrupts.
-	 */
-	if (nested_cpu_has_vid(vmcs12) &&
-	   !nested_exit_on_intr(vcpu))
-		return -EINVAL;
-
-	/*
-	 * bits 15:8 should be zero in posted_intr_nv,
-	 * the descriptor address has been already checked
-	 * in nested_get_vmcs12_pages.
-	 *
-	 * bits 5:0 of posted_intr_desc_addr should be zero.
-	 */
-	if (nested_cpu_has_posted_intr(vmcs12) &&
-	   (!nested_cpu_has_vid(vmcs12) ||
-	    !nested_exit_intr_ack_set(vcpu) ||
-	    (vmcs12->posted_intr_nv & 0xff00) ||
-	    (vmcs12->posted_intr_desc_addr & 0x3f) ||
-	    (!page_address_valid(vcpu, vmcs12->posted_intr_desc_addr))))
-		return -EINVAL;
-
-	/* tpr shadow is needed by all apicv features. */
-	if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
-				       unsigned long count_field,
-				       unsigned long addr_field)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	int maxphyaddr;
-	u64 count, addr;
-
-	if (vmcs12_read_any(vmcs12, count_field, &count) ||
-	    vmcs12_read_any(vmcs12, addr_field, &addr)) {
-		WARN_ON(1);
-		return -EINVAL;
-	}
-	if (count == 0)
-		return 0;
-	maxphyaddr = cpuid_maxphyaddr(vcpu);
-	if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr ||
-	    (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) {
-		pr_debug_ratelimited(
-			"nVMX: invalid MSR switch (0x%lx, %d, %llu, 0x%08llx)",
-			addr_field, maxphyaddr, count, addr);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu,
-						struct vmcs12 *vmcs12)
-{
-	if (vmcs12->vm_exit_msr_load_count == 0 &&
-	    vmcs12->vm_exit_msr_store_count == 0 &&
-	    vmcs12->vm_entry_msr_load_count == 0)
-		return 0; /* Fast path */
-	if (nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_LOAD_COUNT,
-					VM_EXIT_MSR_LOAD_ADDR) ||
-	    nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_STORE_COUNT,
-					VM_EXIT_MSR_STORE_ADDR) ||
-	    nested_vmx_check_msr_switch(vcpu, VM_ENTRY_MSR_LOAD_COUNT,
-					VM_ENTRY_MSR_LOAD_ADDR))
-		return -EINVAL;
-	return 0;
-}
-
-static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
-					 struct vmcs12 *vmcs12)
-{
-	u64 address = vmcs12->pml_address;
-	int maxphyaddr = cpuid_maxphyaddr(vcpu);
-
-	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML)) {
-		if (!nested_cpu_has_ept(vmcs12) ||
-		    !IS_ALIGNED(address, 4096)  ||
-		    address >> maxphyaddr)
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu,
-						 struct vmcs12 *vmcs12)
-{
-	if (!nested_cpu_has_shadow_vmcs(vmcs12))
-		return 0;
-
-	if (!page_address_valid(vcpu, vmcs12->vmread_bitmap) ||
-	    !page_address_valid(vcpu, vmcs12->vmwrite_bitmap))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
-				       struct vmx_msr_entry *e)
-{
-	/* x2APIC MSR accesses are not allowed */
-	if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)
-		return -EINVAL;
-	if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */
-	    e->index == MSR_IA32_UCODE_REV)
-		return -EINVAL;
-	if (e->reserved != 0)
-		return -EINVAL;
-	return 0;
-}
-
-static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu,
-				     struct vmx_msr_entry *e)
-{
-	if (e->index == MSR_FS_BASE ||
-	    e->index == MSR_GS_BASE ||
-	    e->index == MSR_IA32_SMM_MONITOR_CTL || /* SMM is not supported */
-	    nested_vmx_msr_check_common(vcpu, e))
-		return -EINVAL;
-	return 0;
-}
-
-static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
-				      struct vmx_msr_entry *e)
-{
-	if (e->index == MSR_IA32_SMBASE || /* SMM is not supported */
-	    nested_vmx_msr_check_common(vcpu, e))
-		return -EINVAL;
-	return 0;
-}
-
-/*
- * Load guest's/host's msr at nested entry/exit.
- * return 0 for success, entry index for failure.
- */
-static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
-{
-	u32 i;
-	struct vmx_msr_entry e;
-	struct msr_data msr;
-
-	msr.host_initiated = false;
-	for (i = 0; i < count; i++) {
-		if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
-					&e, sizeof(e))) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR entry (%u, 0x%08llx)\n",
-				__func__, i, gpa + i * sizeof(e));
-			goto fail;
-		}
-		if (nested_vmx_load_msr_check(vcpu, &e)) {
-			pr_debug_ratelimited(
-				"%s check failed (%u, 0x%x, 0x%x)\n",
-				__func__, i, e.index, e.reserved);
-			goto fail;
-		}
-		msr.index = e.index;
-		msr.data = e.value;
-		if (kvm_set_msr(vcpu, &msr)) {
-			pr_debug_ratelimited(
-				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
-				__func__, i, e.index, e.value);
-			goto fail;
-		}
-	}
-	return 0;
-fail:
-	return i + 1;
-}
-
-static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
-{
-	u32 i;
-	struct vmx_msr_entry e;
-
-	for (i = 0; i < count; i++) {
-		struct msr_data msr_info;
-		if (kvm_vcpu_read_guest(vcpu,
-					gpa + i * sizeof(e),
-					&e, 2 * sizeof(u32))) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR entry (%u, 0x%08llx)\n",
-				__func__, i, gpa + i * sizeof(e));
-			return -EINVAL;
-		}
-		if (nested_vmx_store_msr_check(vcpu, &e)) {
-			pr_debug_ratelimited(
-				"%s check failed (%u, 0x%x, 0x%x)\n",
-				__func__, i, e.index, e.reserved);
-			return -EINVAL;
-		}
-		msr_info.host_initiated = false;
-		msr_info.index = e.index;
-		if (kvm_get_msr(vcpu, &msr_info)) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR (%u, 0x%x)\n",
-				__func__, i, e.index);
-			return -EINVAL;
-		}
-		if (kvm_vcpu_write_guest(vcpu,
-					 gpa + i * sizeof(e) +
-					     offsetof(struct vmx_msr_entry, value),
-					 &msr_info.data, sizeof(msr_info.data))) {
-			pr_debug_ratelimited(
-				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
-				__func__, i, e.index, msr_info.data);
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-
-static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	unsigned long invalid_mask;
-
-	invalid_mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
-	return (val & invalid_mask) == 0;
-}
-
-/*
- * Load guest's/host's cr3 at nested entry/exit. nested_ept is true if we are
- * emulating VM entry into a guest with EPT enabled.
- * Returns 0 on success, 1 on failure. Invalid state exit qualification code
- * is assigned to entry_failure_code on failure.
- */
-static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
-			       u32 *entry_failure_code)
-{
-	if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) {
-		if (!nested_cr3_valid(vcpu, cr3)) {
-			*entry_failure_code = ENTRY_FAIL_DEFAULT;
-			return 1;
-		}
-
-		/*
-		 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
-		 * must not be dereferenced.
-		 */
-		if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu) &&
-		    !nested_ept) {
-			if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) {
-				*entry_failure_code = ENTRY_FAIL_PDPTE;
-				return 1;
-			}
-		}
-	}
-
-	if (!nested_ept)
-		kvm_mmu_new_cr3(vcpu, cr3, false);
-
-	vcpu->arch.cr3 = cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
-
-	kvm_init_mmu(vcpu, false);
-
-	return 0;
-}
-
-static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
-	vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
-	vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
-	vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
-	vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
-	vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
-	vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
-	vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
-	vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
-	vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
-	vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
-	vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
-	vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
-	vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
-	vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
-	vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
-	vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
-	vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
-	vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
-	vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
-	vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
-	vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
-	vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
-	vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
-	vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
-	vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
-	vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
-	vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
-	vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
-	vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
-	vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
-
-	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
-	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
-		vmcs12->guest_pending_dbg_exceptions);
-	vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
-	vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
-
-	if (nested_cpu_has_xsaves(vmcs12))
-		vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
-	vmcs_write64(VMCS_LINK_POINTER, -1ull);
-
-	if (cpu_has_vmx_posted_intr())
-		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
-
-	/*
-	 * Whether page-faults are trapped is determined by a combination of
-	 * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
-	 * If enable_ept, L0 doesn't care about page faults and we should
-	 * set all of these to L1's desires. However, if !enable_ept, L0 does
-	 * care about (at least some) page faults, and because it is not easy
-	 * (if at all possible?) to merge L0 and L1's desires, we simply ask
-	 * to exit on each and every L2 page fault. This is done by setting
-	 * MASK=MATCH=0 and (see below) EB.PF=1.
-	 * Note that below we don't need special code to set EB.PF beyond the
-	 * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
-	 * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
-	 * !enable_ept, EB.PF is 1, so the "or" will always be 1.
-	 */
-	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
-		enable_ept ? vmcs12->page_fault_error_code_mask : 0);
-	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
-		enable_ept ? vmcs12->page_fault_error_code_match : 0);
-
-	/* All VMFUNCs are currently emulated through L0 vmexits.  */
-	if (cpu_has_vmx_vmfunc())
-		vmcs_write64(VM_FUNCTION_CONTROL, 0);
-
-	if (cpu_has_vmx_apicv()) {
-		vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
-		vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
-		vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
-		vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
-	}
-
-	/*
-	 * Set host-state according to L0's settings (vmcs12 is irrelevant here)
-	 * Some constant fields are set here by vmx_set_constant_host_state().
-	 * Other fields are different per CPU, and will be set later when
-	 * vmx_vcpu_load() is called, and when vmx_prepare_switch_to_guest()
-	 * is called.
-	 */
-	vmx_set_constant_host_state(vmx);
-
-	/*
-	 * Set the MSR load/store lists to match L0's settings.
-	 */
-	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
-
-	set_cr4_guest_host_mask(vmx);
-
-	if (kvm_mpx_supported()) {
-		if (vmx->nested.nested_run_pending &&
-			(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
-			vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
-		else
-			vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
-	}
-
-	if (enable_vpid) {
-		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
-			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
-		else
-			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
-	}
-
-	/*
-	 * L1 may access the L2's PDPTR, so save them to construct vmcs12
-	 */
-	if (enable_ept) {
-		vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
-		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
-		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
-		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
-	}
-
-	if (cpu_has_vmx_msr_bitmap())
-		vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
-}
-
-/*
- * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
- * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
- * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
- * guest in a way that will both be appropriate to L1's requests, and our
- * needs. In addition to modifying the active vmcs (which is vmcs02), this
- * function also has additional necessary side-effects, like setting various
- * vcpu->arch fields.
- * Returns 0 on success, 1 on failure. Invalid state exit qualification code
- * is assigned to entry_failure_code on failure.
- */
-static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
-			  u32 *entry_failure_code)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 exec_control, vmcs12_exec_ctrl;
-
-	if (vmx->nested.dirty_vmcs12) {
-		prepare_vmcs02_full(vcpu, vmcs12);
-		vmx->nested.dirty_vmcs12 = false;
-	}
-
-	/*
-	 * First, the fields that are shadowed.  This must be kept in sync
-	 * with vmx_shadow_fields.h.
-	 */
-
-	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
-	vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
-	vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
-	vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
-	vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
-
-	if (vmx->nested.nested_run_pending &&
-	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
-		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
-	} else {
-		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
-	}
-	if (vmx->nested.nested_run_pending) {
-		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
-			     vmcs12->vm_entry_intr_info_field);
-		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
-			     vmcs12->vm_entry_exception_error_code);
-		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
-			     vmcs12->vm_entry_instruction_len);
-		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
-			     vmcs12->guest_interruptibility_info);
-		vmx->loaded_vmcs->nmi_known_unmasked =
-			!(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
-	} else {
-		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
-	}
-	vmx_set_rflags(vcpu, vmcs12->guest_rflags);
-
-	exec_control = vmcs12->pin_based_vm_exec_control;
-
-	/* Preemption timer setting is computed directly in vmx_vcpu_run.  */
-	exec_control |= vmcs_config.pin_based_exec_ctrl;
-	exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
-	vmx->loaded_vmcs->hv_timer_armed = false;
-
-	/* Posted interrupts setting is only taken from vmcs12.  */
-	if (nested_cpu_has_posted_intr(vmcs12)) {
-		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
-		vmx->nested.pi_pending = false;
-	} else {
-		exec_control &= ~PIN_BASED_POSTED_INTR;
-	}
-
-	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control);
-
-	vmx->nested.preemption_timer_expired = false;
-	if (nested_cpu_has_preemption_timer(vmcs12))
-		vmx_start_preemption_timer(vcpu);
-
-	if (cpu_has_secondary_exec_ctrls()) {
-		exec_control = vmx->secondary_exec_control;
-
-		/* Take the following fields only from vmcs12 */
-		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
-				  SECONDARY_EXEC_ENABLE_INVPCID |
-				  SECONDARY_EXEC_RDTSCP |
-				  SECONDARY_EXEC_XSAVES |
-				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
-				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
-				  SECONDARY_EXEC_ENABLE_VMFUNC);
-		if (nested_cpu_has(vmcs12,
-				   CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
-			vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
-				~SECONDARY_EXEC_ENABLE_PML;
-			exec_control |= vmcs12_exec_ctrl;
-		}
-
-		/* VMCS shadowing for L2 is emulated for now */
-		exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
-
-		if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
-			vmcs_write16(GUEST_INTR_STATUS,
-				vmcs12->guest_intr_status);
-
-		/*
-		 * Write an illegal value to APIC_ACCESS_ADDR. Later,
-		 * nested_get_vmcs12_pages will either fix it up or
-		 * remove the VM execution control.
-		 */
-		if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)
-			vmcs_write64(APIC_ACCESS_ADDR, -1ull);
-
-		if (exec_control & SECONDARY_EXEC_ENCLS_EXITING)
-			vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);
-
-		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
-	}
-
-	/*
-	 * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
-	 * entry, but only if the current (host) sp changed from the value
-	 * we wrote last (vmx->host_rsp). This cache is no longer relevant
-	 * if we switch vmcs, and rather than hold a separate cache per vmcs,
-	 * here we just force the write to happen on entry.
-	 */
-	vmx->host_rsp = 0;
-
-	exec_control = vmx_exec_control(vmx); /* L0's desires */
-	exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
-	exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
-	exec_control &= ~CPU_BASED_TPR_SHADOW;
-	exec_control |= vmcs12->cpu_based_vm_exec_control;
-
-	/*
-	 * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if
-	 * nested_get_vmcs12_pages can't fix it up, the illegal value
-	 * will result in a VM entry failure.
-	 */
-	if (exec_control & CPU_BASED_TPR_SHADOW) {
-		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
-		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
-	} else {
-#ifdef CONFIG_X86_64
-		exec_control |= CPU_BASED_CR8_LOAD_EXITING |
-				CPU_BASED_CR8_STORE_EXITING;
-#endif
-	}
-
-	/*
-	 * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
-	 * for I/O port accesses.
-	 */
-	exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
-	exec_control |= CPU_BASED_UNCOND_IO_EXITING;
-
-	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
-
-	/* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
-	 * bitwise-or of what L1 wants to trap for L2, and what we want to
-	 * trap. Note that CR0.TS also needs updating - we do this later.
-	 */
-	update_exception_bitmap(vcpu);
-	vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
-
-	/* L2->L1 exit controls are emulated - the hardware exit is to L0 so
-	 * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
-	 * bits are further modified by vmx_set_efer() below.
-	 */
-	vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
-
-	/* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
-	 * emulated by vmx_set_efer(), below.
-	 */
-	vm_entry_controls_init(vmx, 
-		(vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER &
-			~VM_ENTRY_IA32E_MODE) |
-		(vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
-
-	if (vmx->nested.nested_run_pending &&
-	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) {
-		vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
-		vcpu->arch.pat = vmcs12->guest_ia32_pat;
-	} else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
-		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
-	}
-
-	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
-
-	if (kvm_has_tsc_control)
-		decache_tsc_multiplier(vmx);
-
-	if (enable_vpid) {
-		/*
-		 * There is no direct mapping between vpid02 and vpid12, the
-		 * vpid02 is per-vCPU for L0 and reused while the value of
-		 * vpid12 is changed w/ one invvpid during nested vmentry.
-		 * The vpid12 is allocated by L1 for L2, so it will not
-		 * influence global bitmap(for vpid01 and vpid02 allocation)
-		 * even if spawn a lot of nested vCPUs.
-		 */
-		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
-			if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
-				vmx->nested.last_vpid = vmcs12->virtual_processor_id;
-				__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
-			}
-		} else {
-			vmx_flush_tlb(vcpu, true);
-		}
-	}
-
-	if (enable_pml) {
-		/*
-		 * Conceptually we want to copy the PML address and index from
-		 * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
-		 * since we always flush the log on each vmexit, this happens
-		 * to be equivalent to simply resetting the fields in vmcs02.
-		 */
-		ASSERT(vmx->pml_pg);
-		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-	}
-
-	if (nested_cpu_has_ept(vmcs12)) {
-		if (nested_ept_init_mmu_context(vcpu)) {
-			*entry_failure_code = ENTRY_FAIL_DEFAULT;
-			return 1;
-		}
-	} else if (nested_cpu_has2(vmcs12,
-				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb(vcpu, true);
-	}
-
-	/*
-	 * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
-	 * bits which we consider mandatory enabled.
-	 * The CR0_READ_SHADOW is what L2 should have expected to read given
-	 * the specifications by L1; It's not enough to take
-	 * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we
-	 * have more bits than L1 expected.
-	 */
-	vmx_set_cr0(vcpu, vmcs12->guest_cr0);
-	vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12));
-
-	vmx_set_cr4(vcpu, vmcs12->guest_cr4);
-	vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));
-
-	if (vmx->nested.nested_run_pending &&
-	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
-		vcpu->arch.efer = vmcs12->guest_ia32_efer;
-	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
-		vcpu->arch.efer |= (EFER_LMA | EFER_LME);
-	else
-		vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
-	/* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
-	vmx_set_efer(vcpu, vcpu->arch.efer);
-
-	/*
-	 * Guest state is invalid and unrestricted guest is disabled,
-	 * which means L1 attempted VMEntry to L2 with invalid state.
-	 * Fail the VMEntry.
-	 */
-	if (vmx->emulation_required) {
-		*entry_failure_code = ENTRY_FAIL_DEFAULT;
-		return 1;
-	}
-
-	/* Shadow page tables on either EPT or shadow page tables. */
-	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
-				entry_failure_code))
-		return 1;
-
-	if (!enable_ept)
-		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
-
-	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
-	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
-	return 0;
-}
-
-static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12)
-{
-	if (!nested_cpu_has_nmi_exiting(vmcs12) &&
-	    nested_cpu_has_virtual_nmis(vmcs12))
-		return -EINVAL;
-
-	if (!nested_cpu_has_virtual_nmis(vmcs12) &&
-	    nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
-	    vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_apic_access_controls(vcpu, vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_apicv_controls(vcpu, vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_pml_controls(vcpu, vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_shadow_vmcs_controls(vcpu, vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
-				vmx->nested.msrs.procbased_ctls_low,
-				vmx->nested.msrs.procbased_ctls_high) ||
-	    (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
-	     !vmx_control_verify(vmcs12->secondary_vm_exec_control,
-				 vmx->nested.msrs.secondary_ctls_low,
-				 vmx->nested.msrs.secondary_ctls_high)) ||
-	    !vmx_control_verify(vmcs12->pin_based_vm_exec_control,
-				vmx->nested.msrs.pinbased_ctls_low,
-				vmx->nested.msrs.pinbased_ctls_high) ||
-	    !vmx_control_verify(vmcs12->vm_exit_controls,
-				vmx->nested.msrs.exit_ctls_low,
-				vmx->nested.msrs.exit_ctls_high) ||
-	    !vmx_control_verify(vmcs12->vm_entry_controls,
-				vmx->nested.msrs.entry_ctls_low,
-				vmx->nested.msrs.entry_ctls_high))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_vmx_check_nmi_controls(vmcs12))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (nested_cpu_has_vmfunc(vmcs12)) {
-		if (vmcs12->vm_function_control &
-		    ~vmx->nested.msrs.vmfunc_controls)
-			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-		if (nested_cpu_has_eptp_switching(vmcs12)) {
-			if (!nested_cpu_has_ept(vmcs12) ||
-			    !page_address_valid(vcpu, vmcs12->eptp_list_address))
-				return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-		}
-	}
-
-	if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu))
-		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-	if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) ||
-	    !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
-	    !nested_cr3_valid(vcpu, vmcs12->host_cr3))
-		return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
-
-	/*
-	 * From the Intel SDM, volume 3:
-	 * Fields relevant to VM-entry event injection must be set properly.
-	 * These fields are the VM-entry interruption-information field, the
-	 * VM-entry exception error code, and the VM-entry instruction length.
-	 */
-	if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
-		u32 intr_info = vmcs12->vm_entry_intr_info_field;
-		u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
-		u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
-		bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
-		bool should_have_error_code;
-		bool urg = nested_cpu_has2(vmcs12,
-					   SECONDARY_EXEC_UNRESTRICTED_GUEST);
-		bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;
-
-		/* VM-entry interruption-info field: interruption type */
-		if (intr_type == INTR_TYPE_RESERVED ||
-		    (intr_type == INTR_TYPE_OTHER_EVENT &&
-		     !nested_cpu_supports_monitor_trap_flag(vcpu)))
-			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-		/* VM-entry interruption-info field: vector */
-		if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) ||
-		    (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) ||
-		    (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
-			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-		/* VM-entry interruption-info field: deliver error code */
-		should_have_error_code =
-			intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
-			x86_exception_has_error_code(vector);
-		if (has_error_code != should_have_error_code)
-			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-		/* VM-entry exception error code */
-		if (has_error_code &&
-		    vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))
-			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-		/* VM-entry interruption-info field: reserved bits */
-		if (intr_info & INTR_INFO_RESVD_BITS_MASK)
-			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-
-		/* VM-entry instruction length */
-		switch (intr_type) {
-		case INTR_TYPE_SOFT_EXCEPTION:
-		case INTR_TYPE_SOFT_INTR:
-		case INTR_TYPE_PRIV_SW_EXCEPTION:
-			if ((vmcs12->vm_entry_instruction_len > 15) ||
-			    (vmcs12->vm_entry_instruction_len == 0 &&
-			     !nested_cpu_has_zero_length_injection(vcpu)))
-				return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
-		}
-	}
-
-	return 0;
-}
-
-static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
-					  struct vmcs12 *vmcs12)
-{
-	int r;
-	struct page *page;
-	struct vmcs12 *shadow;
-
-	if (vmcs12->vmcs_link_pointer == -1ull)
-		return 0;
-
-	if (!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))
-		return -EINVAL;
-
-	page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->vmcs_link_pointer);
-	if (is_error_page(page))
-		return -EINVAL;
-
-	r = 0;
-	shadow = kmap(page);
-	if (shadow->hdr.revision_id != VMCS12_REVISION ||
-	    shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))
-		r = -EINVAL;
-	kunmap(page);
-	kvm_release_page_clean(page);
-	return r;
-}
-
-static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
-				  u32 *exit_qual)
-{
-	bool ia32e;
-
-	*exit_qual = ENTRY_FAIL_DEFAULT;
-
-	if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) ||
-	    !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))
-		return 1;
-
-	if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) {
-		*exit_qual = ENTRY_FAIL_VMCS_LINK_PTR;
-		return 1;
-	}
-
-	/*
-	 * If the load IA32_EFER VM-entry control is 1, the following checks
-	 * are performed on the field for the IA32_EFER MSR:
-	 * - Bits reserved in the IA32_EFER MSR must be 0.
-	 * - Bit 10 (corresponding to IA32_EFER.LMA) must equal the value of
-	 *   the IA-32e mode guest VM-exit control. It must also be identical
-	 *   to bit 8 (LME) if bit 31 in the CR0 field (corresponding to
-	 *   CR0.PG) is 1.
-	 */
-	if (to_vmx(vcpu)->nested.nested_run_pending &&
-	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
-		ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
-		if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) ||
-		    ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) ||
-		    ((vmcs12->guest_cr0 & X86_CR0_PG) &&
-		     ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME)))
-			return 1;
-	}
-
-	/*
-	 * If the load IA32_EFER VM-exit control is 1, bits reserved in the
-	 * IA32_EFER MSR must be 0 in the field for that register. In addition,
-	 * the values of the LMA and LME bits in the field must each be that of
-	 * the host address-space size VM-exit control.
-	 */
-	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) {
-		ia32e = (vmcs12->vm_exit_controls &
-			 VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0;
-		if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) ||
-		    ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) ||
-		    ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))
-			return 1;
-	}
-
-	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
-		(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) ||
-		(vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))
-			return 1;
-
-	return 0;
-}
-
-/*
- * If exit_qual is NULL, this is being called from state restore (either RSM
- * or KVM_SET_NESTED_STATE).  Otherwise it's called from vmlaunch/vmresume.
- */
-static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	bool from_vmentry = !!exit_qual;
-	u32 dummy_exit_qual;
-	bool evaluate_pending_interrupts;
-	int r = 0;
-
-	evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
-		(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
-	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
-		evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
-
-	enter_guest_mode(vcpu);
-
-	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
-		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
-	if (kvm_mpx_supported() &&
-		!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
-		vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
-
-	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
-	vmx_segment_cache_clear(vmx);
-
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
-		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
-
-	r = EXIT_REASON_INVALID_STATE;
-	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry ? exit_qual : &dummy_exit_qual))
-		goto fail;
-
-	if (from_vmentry) {
-		nested_get_vmcs12_pages(vcpu);
-
-		r = EXIT_REASON_MSR_LOAD_FAIL;
-		*exit_qual = nested_vmx_load_msr(vcpu,
-	     					 vmcs12->vm_entry_msr_load_addr,
-					      	 vmcs12->vm_entry_msr_load_count);
-		if (*exit_qual)
-			goto fail;
-	} else {
-		/*
-		 * The MMU is not initialized to point at the right entities yet and
-		 * "get pages" would need to read data from the guest (i.e. we will
-		 * need to perform gpa to hpa translation). Request a call
-		 * to nested_get_vmcs12_pages before the next VM-entry.  The MSRs
-		 * have already been set at vmentry time and should not be reset.
-		 */
-		kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
-	}
-
-	/*
-	 * If L1 had a pending IRQ/NMI until it executed
-	 * VMLAUNCH/VMRESUME which wasn't delivered because it was
-	 * disallowed (e.g. interrupts disabled), L0 needs to
-	 * evaluate if this pending event should cause an exit from L2
-	 * to L1 or delivered directly to L2 (e.g. In case L1 don't
-	 * intercept EXTERNAL_INTERRUPT).
-	 *
-	 * Usually this would be handled by the processor noticing an
-	 * IRQ/NMI window request, or checking RVI during evaluation of
-	 * pending virtual interrupts.  However, this setting was done
-	 * on VMCS01 and now VMCS02 is active instead. Thus, we force L0
-	 * to perform pending event evaluation by requesting a KVM_REQ_EVENT.
-	 */
-	if (unlikely(evaluate_pending_interrupts))
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
-
-	/*
-	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
-	 * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet
-	 * returned as far as L1 is concerned. It will only return (and set
-	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
-	 */
-	return 0;
-
-fail:
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
-		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
-	leave_guest_mode(vcpu);
-	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-	return r;
-}
-
-/*
- * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1
- * for running an L2 nested guest.
- */
-static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
-{
-	struct vmcs12 *vmcs12;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
-	u32 exit_qual;
-	int ret;
-
-	if (!nested_vmx_check_permission(vcpu))
-		return 1;
-
-	if (!nested_vmx_check_vmcs12(vcpu))
-		goto out;
-
-	vmcs12 = get_vmcs12(vcpu);
-
-	/*
-	 * Can't VMLAUNCH or VMRESUME a shadow VMCS. Despite the fact
-	 * that there *is* a valid VMCS pointer, RFLAGS.CF is set
-	 * rather than RFLAGS.ZF, and no error number is stored to the
-	 * VM-instruction error field.
-	 */
-	if (vmcs12->hdr.shadow_vmcs) {
-		nested_vmx_failInvalid(vcpu);
-		goto out;
-	}
-
-	if (enable_shadow_vmcs)
-		copy_shadow_to_vmcs12(vmx);
-
-	/*
-	 * The nested entry process starts with enforcing various prerequisites
-	 * on vmcs12 as required by the Intel SDM, and act appropriately when
-	 * they fail: As the SDM explains, some conditions should cause the
-	 * instruction to fail, while others will cause the instruction to seem
-	 * to succeed, but return an EXIT_REASON_INVALID_STATE.
-	 * To speed up the normal (success) code path, we should avoid checking
-	 * for misconfigurations which will anyway be caught by the processor
-	 * when using the merged vmcs02.
-	 */
-	if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS) {
-		nested_vmx_failValid(vcpu,
-				     VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
-		goto out;
-	}
-
-	if (vmcs12->launch_state == launch) {
-		nested_vmx_failValid(vcpu,
-			launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
-			       : VMXERR_VMRESUME_NONLAUNCHED_VMCS);
-		goto out;
-	}
-
-	ret = check_vmentry_prereqs(vcpu, vmcs12);
-	if (ret) {
-		nested_vmx_failValid(vcpu, ret);
-		goto out;
-	}
-
-	/*
-	 * After this point, the trap flag no longer triggers a singlestep trap
-	 * on the vm entry instructions; don't call kvm_skip_emulated_instruction.
-	 * This is not 100% correct; for performance reasons, we delegate most
-	 * of the checks on host state to the processor.  If those fail,
-	 * the singlestep trap is missed.
-	 */
-	skip_emulated_instruction(vcpu);
-
-	ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual);
-	if (ret) {
-		nested_vmx_entry_failure(vcpu, vmcs12,
-					 EXIT_REASON_INVALID_STATE, exit_qual);
-		return 1;
-	}
-
-	/*
-	 * We're finally done with prerequisite checking, and can start with
-	 * the nested entry.
-	 */
-
-	vmx->nested.nested_run_pending = 1;
-	ret = enter_vmx_non_root_mode(vcpu, &exit_qual);
-	if (ret) {
-		nested_vmx_entry_failure(vcpu, vmcs12, ret, exit_qual);
-		vmx->nested.nested_run_pending = 0;
-		return 1;
-	}
-
-	/* Hide L1D cache contents from the nested guest.  */
-	vmx->vcpu.arch.l1tf_flush_l1d = true;
-
-	/*
-	 * Must happen outside of enter_vmx_non_root_mode() as it will
-	 * also be used as part of restoring nVMX state for
-	 * snapshot restore (migration).
-	 *
-	 * In this flow, it is assumed that vmcs12 cache was
-	 * trasferred as part of captured nVMX state and should
-	 * therefore not be read from guest memory (which may not
-	 * exist on destination host yet).
-	 */
-	nested_cache_shadow_vmcs12(vcpu, vmcs12);
-
-	/*
-	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
-	 * by event injection, halt vcpu.
-	 */
-	if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
-	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) {
-		vmx->nested.nested_run_pending = 0;
-		return kvm_vcpu_halt(vcpu);
-	}
-	return 1;
-
-out:
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-/*
- * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date
- * because L2 may have changed some cr0 bits directly (CRO_GUEST_HOST_MASK).
- * This function returns the new value we should put in vmcs12.guest_cr0.
- * It's not enough to just return the vmcs02 GUEST_CR0. Rather,
- *  1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now
- *     available in vmcs02 GUEST_CR0. (Note: It's enough to check that L0
- *     didn't trap the bit, because if L1 did, so would L0).
- *  2. Bits that L1 asked to trap (and therefore L0 also did) could not have
- *     been modified by L2, and L1 knows it. So just leave the old value of
- *     the bit from vmcs12.guest_cr0. Note that the bit from vmcs02 GUEST_CR0
- *     isn't relevant, because if L0 traps this bit it can set it to anything.
- *  3. Bits that L1 didn't trap, but L0 did. L1 believes the guest could have
- *     changed these bits, and therefore they need to be updated, but L0
- *     didn't necessarily allow them to be changed in GUEST_CR0 - and rather
- *     put them in vmcs02 CR0_READ_SHADOW. So take these bits from there.
- */
-static inline unsigned long
-vmcs12_guest_cr0(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
-{
-	return
-	/*1*/	(vmcs_readl(GUEST_CR0) & vcpu->arch.cr0_guest_owned_bits) |
-	/*2*/	(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask) |
-	/*3*/	(vmcs_readl(CR0_READ_SHADOW) & ~(vmcs12->cr0_guest_host_mask |
-			vcpu->arch.cr0_guest_owned_bits));
-}
-
-static inline unsigned long
-vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
-{
-	return
-	/*1*/	(vmcs_readl(GUEST_CR4) & vcpu->arch.cr4_guest_owned_bits) |
-	/*2*/	(vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask) |
-	/*3*/	(vmcs_readl(CR4_READ_SHADOW) & ~(vmcs12->cr4_guest_host_mask |
-			vcpu->arch.cr4_guest_owned_bits));
-}
-
-static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
-				       struct vmcs12 *vmcs12)
-{
-	u32 idt_vectoring;
-	unsigned int nr;
-
-	if (vcpu->arch.exception.injected) {
-		nr = vcpu->arch.exception.nr;
-		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
-
-		if (kvm_exception_is_soft(nr)) {
-			vmcs12->vm_exit_instruction_len =
-				vcpu->arch.event_exit_inst_len;
-			idt_vectoring |= INTR_TYPE_SOFT_EXCEPTION;
-		} else
-			idt_vectoring |= INTR_TYPE_HARD_EXCEPTION;
-
-		if (vcpu->arch.exception.has_error_code) {
-			idt_vectoring |= VECTORING_INFO_DELIVER_CODE_MASK;
-			vmcs12->idt_vectoring_error_code =
-				vcpu->arch.exception.error_code;
-		}
-
-		vmcs12->idt_vectoring_info_field = idt_vectoring;
-	} else if (vcpu->arch.nmi_injected) {
-		vmcs12->idt_vectoring_info_field =
-			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR;
-	} else if (vcpu->arch.interrupt.injected) {
-		nr = vcpu->arch.interrupt.nr;
-		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
-
-		if (vcpu->arch.interrupt.soft) {
-			idt_vectoring |= INTR_TYPE_SOFT_INTR;
-			vmcs12->vm_entry_instruction_len =
-				vcpu->arch.event_exit_inst_len;
-		} else
-			idt_vectoring |= INTR_TYPE_EXT_INTR;
-
-		vmcs12->idt_vectoring_info_field = idt_vectoring;
-	}
-}
-
-static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long exit_qual;
-	bool block_nested_events =
-	    vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
-
-	if (vcpu->arch.exception.pending &&
-		nested_vmx_check_exception(vcpu, &exit_qual)) {
-		if (block_nested_events)
-			return -EBUSY;
-		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
-		return 0;
-	}
-
-	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
-	    vmx->nested.preemption_timer_expired) {
-		if (block_nested_events)
-			return -EBUSY;
-		nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
-		return 0;
-	}
-
-	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
-		if (block_nested_events)
-			return -EBUSY;
-		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-				  NMI_VECTOR | INTR_TYPE_NMI_INTR |
-				  INTR_INFO_VALID_MASK, 0);
-		/*
-		 * The NMI-triggered VM exit counts as injection:
-		 * clear this one and block further NMIs.
-		 */
-		vcpu->arch.nmi_pending = 0;
-		vmx_set_nmi_mask(vcpu, true);
-		return 0;
-	}
-
-	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
-	    nested_exit_on_intr(vcpu)) {
-		if (block_nested_events)
-			return -EBUSY;
-		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
-		return 0;
-	}
-
-	vmx_complete_nested_posted_interrupt(vcpu);
-	return 0;
-}
-
-static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
-{
-	to_vmx(vcpu)->req_immediate_exit = true;
-}
-
-static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)
-{
-	ktime_t remaining =
-		hrtimer_get_remaining(&to_vmx(vcpu)->nested.preemption_timer);
-	u64 value;
-
-	if (ktime_to_ns(remaining) <= 0)
-		return 0;
-
-	value = ktime_to_ns(remaining) * vcpu->arch.virtual_tsc_khz;
-	do_div(value, 1000000);
-	return value >> VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
-}
-
-/*
- * Update the guest state fields of vmcs12 to reflect changes that
- * occurred while L2 was running. (The "IA-32e mode guest" bit of the
- * VM-entry controls is also updated, since this is really a guest
- * state bit.)
- */
-static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
-{
-	vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
-	vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);
-
-	vmcs12->guest_rsp = kvm_register_read(vcpu, VCPU_REGS_RSP);
-	vmcs12->guest_rip = kvm_register_read(vcpu, VCPU_REGS_RIP);
-	vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS);
-
-	vmcs12->guest_es_selector = vmcs_read16(GUEST_ES_SELECTOR);
-	vmcs12->guest_cs_selector = vmcs_read16(GUEST_CS_SELECTOR);
-	vmcs12->guest_ss_selector = vmcs_read16(GUEST_SS_SELECTOR);
-	vmcs12->guest_ds_selector = vmcs_read16(GUEST_DS_SELECTOR);
-	vmcs12->guest_fs_selector = vmcs_read16(GUEST_FS_SELECTOR);
-	vmcs12->guest_gs_selector = vmcs_read16(GUEST_GS_SELECTOR);
-	vmcs12->guest_ldtr_selector = vmcs_read16(GUEST_LDTR_SELECTOR);
-	vmcs12->guest_tr_selector = vmcs_read16(GUEST_TR_SELECTOR);
-	vmcs12->guest_es_limit = vmcs_read32(GUEST_ES_LIMIT);
-	vmcs12->guest_cs_limit = vmcs_read32(GUEST_CS_LIMIT);
-	vmcs12->guest_ss_limit = vmcs_read32(GUEST_SS_LIMIT);
-	vmcs12->guest_ds_limit = vmcs_read32(GUEST_DS_LIMIT);
-	vmcs12->guest_fs_limit = vmcs_read32(GUEST_FS_LIMIT);
-	vmcs12->guest_gs_limit = vmcs_read32(GUEST_GS_LIMIT);
-	vmcs12->guest_ldtr_limit = vmcs_read32(GUEST_LDTR_LIMIT);
-	vmcs12->guest_tr_limit = vmcs_read32(GUEST_TR_LIMIT);
-	vmcs12->guest_gdtr_limit = vmcs_read32(GUEST_GDTR_LIMIT);
-	vmcs12->guest_idtr_limit = vmcs_read32(GUEST_IDTR_LIMIT);
-	vmcs12->guest_es_ar_bytes = vmcs_read32(GUEST_ES_AR_BYTES);
-	vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES);
-	vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES);
-	vmcs12->guest_ds_ar_bytes = vmcs_read32(GUEST_DS_AR_BYTES);
-	vmcs12->guest_fs_ar_bytes = vmcs_read32(GUEST_FS_AR_BYTES);
-	vmcs12->guest_gs_ar_bytes = vmcs_read32(GUEST_GS_AR_BYTES);
-	vmcs12->guest_ldtr_ar_bytes = vmcs_read32(GUEST_LDTR_AR_BYTES);
-	vmcs12->guest_tr_ar_bytes = vmcs_read32(GUEST_TR_AR_BYTES);
-	vmcs12->guest_es_base = vmcs_readl(GUEST_ES_BASE);
-	vmcs12->guest_cs_base = vmcs_readl(GUEST_CS_BASE);
-	vmcs12->guest_ss_base = vmcs_readl(GUEST_SS_BASE);
-	vmcs12->guest_ds_base = vmcs_readl(GUEST_DS_BASE);
-	vmcs12->guest_fs_base = vmcs_readl(GUEST_FS_BASE);
-	vmcs12->guest_gs_base = vmcs_readl(GUEST_GS_BASE);
-	vmcs12->guest_ldtr_base = vmcs_readl(GUEST_LDTR_BASE);
-	vmcs12->guest_tr_base = vmcs_readl(GUEST_TR_BASE);
-	vmcs12->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE);
-	vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE);
-
-	vmcs12->guest_interruptibility_info =
-		vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
-	vmcs12->guest_pending_dbg_exceptions =
-		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
-	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
-		vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT;
-	else
-		vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE;
-
-	if (nested_cpu_has_preemption_timer(vmcs12)) {
-		if (vmcs12->vm_exit_controls &
-		    VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
-			vmcs12->vmx_preemption_timer_value =
-				vmx_get_preemption_timer_value(vcpu);
-		hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer);
-	}
-
-	/*
-	 * In some cases (usually, nested EPT), L2 is allowed to change its
-	 * own CR3 without exiting. If it has changed it, we must keep it.
-	 * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined
-	 * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12.
-	 *
-	 * Additionally, restore L2's PDPTR to vmcs12.
-	 */
-	if (enable_ept) {
-		vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3);
-		vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0);
-		vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1);
-		vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2);
-		vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
-	}
-
-	vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS);
-
-	if (nested_cpu_has_vid(vmcs12))
-		vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS);
-
-	vmcs12->vm_entry_controls =
-		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
-		(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
-
-	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) {
-		kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7);
-		vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
-	}
-
-	/* TODO: These cannot have changed unless we have MSR bitmaps and
-	 * the relevant bit asks not to trap the change */
-	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT)
-		vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT);
-	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER)
-		vmcs12->guest_ia32_efer = vcpu->arch.efer;
-	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
-	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
-	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
-	if (kvm_mpx_supported())
-		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
-}
-
-/*
- * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits
- * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12),
- * and this function updates it to reflect the changes to the guest state while
- * L2 was running (and perhaps made some exits which were handled directly by L0
- * without going back to L1), and to reflect the exit reason.
- * Note that we do not have to copy here all VMCS fields, just those that
- * could have changed by the L2 guest or the exit - i.e., the guest-state and
- * exit-information fields only. Other fields are modified by L1 with VMWRITE,
- * which already writes to vmcs12 directly.
- */
-static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
-			   u32 exit_reason, u32 exit_intr_info,
-			   unsigned long exit_qualification)
-{
-	/* update guest state fields: */
-	sync_vmcs12(vcpu, vmcs12);
-
-	/* update exit information fields: */
-
-	vmcs12->vm_exit_reason = exit_reason;
-	vmcs12->exit_qualification = exit_qualification;
-	vmcs12->vm_exit_intr_info = exit_intr_info;
-
-	vmcs12->idt_vectoring_info_field = 0;
-	vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
-	vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-
-	if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) {
-		vmcs12->launch_state = 1;
-
-		/* vm_entry_intr_info_field is cleared on exit. Emulate this
-		 * instead of reading the real value. */
-		vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK;
-
-		/*
-		 * Transfer the event that L0 or L1 may wanted to inject into
-		 * L2 to IDT_VECTORING_INFO_FIELD.
-		 */
-		vmcs12_save_pending_event(vcpu, vmcs12);
-	}
-
-	/*
-	 * Drop what we picked up for L2 via vmx_complete_interrupts. It is
-	 * preserved above and would only end up incorrectly in L1.
-	 */
-	vcpu->arch.nmi_injected = false;
-	kvm_clear_exception_queue(vcpu);
-	kvm_clear_interrupt_queue(vcpu);
-}
-
-static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu,
-			struct vmcs12 *vmcs12)
-{
-	u32 entry_failure_code;
-
-	nested_ept_uninit_mmu_context(vcpu);
-
-	/*
-	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
-	 * couldn't have changed.
-	 */
-	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
-		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
-
-	if (!enable_ept)
-		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
-}
-
-/*
- * A part of what we need to when the nested L2 guest exits and we want to
- * run its L1 parent, is to reset L1's guest state to the host state specified
- * in vmcs12.
- * This function is to be called not only on normal nested exit, but also on
- * a nested entry failure, as explained in Intel's spec, 3B.23.7 ("VM-Entry
- * Failures During or After Loading Guest State").
- * This function should be called when the active VMCS is L1's (vmcs01).
- */
-static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
-				   struct vmcs12 *vmcs12)
-{
-	struct kvm_segment seg;
-
-	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
-		vcpu->arch.efer = vmcs12->host_ia32_efer;
-	else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
-		vcpu->arch.efer |= (EFER_LMA | EFER_LME);
-	else
-		vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
-	vmx_set_efer(vcpu, vcpu->arch.efer);
-
-	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp);
-	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip);
-	vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
-	/*
-	 * Note that calling vmx_set_cr0 is important, even if cr0 hasn't
-	 * actually changed, because vmx_set_cr0 refers to efer set above.
-	 *
-	 * CR0_GUEST_HOST_MASK is already set in the original vmcs01
-	 * (KVM doesn't change it);
-	 */
-	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
-	vmx_set_cr0(vcpu, vmcs12->host_cr0);
-
-	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
-	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
-	vmx_set_cr4(vcpu, vmcs12->host_cr4);
-
-	load_vmcs12_mmu_host_state(vcpu, vmcs12);
-
-	/*
-	 * If vmcs01 don't use VPID, CPU flushes TLB on every
-	 * VMEntry/VMExit. Thus, no need to flush TLB.
-	 *
-	 * If vmcs12 uses VPID, TLB entries populated by L2 are
-	 * tagged with vmx->nested.vpid02 while L1 entries are tagged
-	 * with vmx->vpid. Thus, no need to flush TLB.
-	 *
-	 * Therefore, flush TLB only in case vmcs01 uses VPID and
-	 * vmcs12 don't use VPID as in this case L1 & L2 TLB entries
-	 * are both tagged with vmx->vpid.
-	 */
-	if (enable_vpid &&
-	    !(nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02)) {
-		vmx_flush_tlb(vcpu, true);
-	}
-
-	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
-	vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
-	vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
-	vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
-	vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
-	vmcs_write32(GUEST_IDTR_LIMIT, 0xFFFF);
-	vmcs_write32(GUEST_GDTR_LIMIT, 0xFFFF);
-
-	/* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1.  */
-	if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS)
-		vmcs_write64(GUEST_BNDCFGS, 0);
-
-	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) {
-		vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
-		vcpu->arch.pat = vmcs12->host_ia32_pat;
-	}
-	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
-			vmcs12->host_ia32_perf_global_ctrl);
-
-	/* Set L1 segment info according to Intel SDM
-	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
-	seg = (struct kvm_segment) {
-		.base = 0,
-		.limit = 0xFFFFFFFF,
-		.selector = vmcs12->host_cs_selector,
-		.type = 11,
-		.present = 1,
-		.s = 1,
-		.g = 1
-	};
-	if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
-		seg.l = 1;
-	else
-		seg.db = 1;
-	vmx_set_segment(vcpu, &seg, VCPU_SREG_CS);
-	seg = (struct kvm_segment) {
-		.base = 0,
-		.limit = 0xFFFFFFFF,
-		.type = 3,
-		.present = 1,
-		.s = 1,
-		.db = 1,
-		.g = 1
-	};
-	seg.selector = vmcs12->host_ds_selector;
-	vmx_set_segment(vcpu, &seg, VCPU_SREG_DS);
-	seg.selector = vmcs12->host_es_selector;
-	vmx_set_segment(vcpu, &seg, VCPU_SREG_ES);
-	seg.selector = vmcs12->host_ss_selector;
-	vmx_set_segment(vcpu, &seg, VCPU_SREG_SS);
-	seg.selector = vmcs12->host_fs_selector;
-	seg.base = vmcs12->host_fs_base;
-	vmx_set_segment(vcpu, &seg, VCPU_SREG_FS);
-	seg.selector = vmcs12->host_gs_selector;
-	seg.base = vmcs12->host_gs_base;
-	vmx_set_segment(vcpu, &seg, VCPU_SREG_GS);
-	seg = (struct kvm_segment) {
-		.base = vmcs12->host_tr_base,
-		.limit = 0x67,
-		.selector = vmcs12->host_tr_selector,
-		.type = 11,
-		.present = 1
-	};
-	vmx_set_segment(vcpu, &seg, VCPU_SREG_TR);
-
-	kvm_set_dr(vcpu, 7, 0x400);
-	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
-
-	if (cpu_has_vmx_msr_bitmap())
-		vmx_update_msr_bitmap(vcpu);
-
-	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
-				vmcs12->vm_exit_msr_load_count))
-		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
-}
-
-/*
- * Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1
- * and modify vmcs12 to make it see what it would expect to see there if
- * L2 was its real guest. Must only be called when in L2 (is_guest_mode())
- */
-static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
-			      u32 exit_intr_info,
-			      unsigned long exit_qualification)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-
-	/* trying to cancel vmlaunch/vmresume is a bug */
-	WARN_ON_ONCE(vmx->nested.nested_run_pending);
-
-	/*
-	 * The only expected VM-instruction error is "VM entry with
-	 * invalid control field(s)." Anything else indicates a
-	 * problem with L0.
-	 */
-	WARN_ON_ONCE(vmx->fail && (vmcs_read32(VM_INSTRUCTION_ERROR) !=
-				   VMXERR_ENTRY_INVALID_CONTROL_FIELD));
-
-	leave_guest_mode(vcpu);
-
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
-		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
-
-	if (likely(!vmx->fail)) {
-		if (exit_reason == -1)
-			sync_vmcs12(vcpu, vmcs12);
-		else
-			prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
-				       exit_qualification);
-
-		/*
-		 * Must happen outside of sync_vmcs12() as it will
-		 * also be used to capture vmcs12 cache as part of
-		 * capturing nVMX state for snapshot (migration).
-		 *
-		 * Otherwise, this flush will dirty guest memory at a
-		 * point it is already assumed by user-space to be
-		 * immutable.
-		 */
-		nested_flush_cached_shadow_vmcs12(vcpu, vmcs12);
-
-		if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr,
-					 vmcs12->vm_exit_msr_store_count))
-			nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL);
-	}
-
-	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-	vm_entry_controls_reset_shadow(vmx);
-	vm_exit_controls_reset_shadow(vmx);
-	vmx_segment_cache_clear(vmx);
-
-	/* Update any VMCS fields that might have changed while L2 ran */
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
-	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
-
-	if (kvm_has_tsc_control)
-		decache_tsc_multiplier(vmx);
-
-	if (vmx->nested.change_vmcs01_virtual_apic_mode) {
-		vmx->nested.change_vmcs01_virtual_apic_mode = false;
-		vmx_set_virtual_apic_mode(vcpu);
-	} else if (!nested_cpu_has_ept(vmcs12) &&
-		   nested_cpu_has2(vmcs12,
-				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb(vcpu, true);
-	}
-
-	/* This is needed for same reason as it was needed in prepare_vmcs02 */
-	vmx->host_rsp = 0;
-
-	/* Unpin physical memory we referred to in vmcs02 */
-	if (vmx->nested.apic_access_page) {
-		kvm_release_page_dirty(vmx->nested.apic_access_page);
-		vmx->nested.apic_access_page = NULL;
-	}
-	if (vmx->nested.virtual_apic_page) {
-		kvm_release_page_dirty(vmx->nested.virtual_apic_page);
-		vmx->nested.virtual_apic_page = NULL;
-	}
-	if (vmx->nested.pi_desc_page) {
-		kunmap(vmx->nested.pi_desc_page);
-		kvm_release_page_dirty(vmx->nested.pi_desc_page);
-		vmx->nested.pi_desc_page = NULL;
-		vmx->nested.pi_desc = NULL;
-	}
-
-	/*
-	 * We are now running in L2, mmu_notifier will force to reload the
-	 * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1.
-	 */
-	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
-
-	if (enable_shadow_vmcs && exit_reason != -1)
-		vmx->nested.sync_shadow_vmcs = true;
-
-	/* in case we halted in L2 */
-	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-
-	if (likely(!vmx->fail)) {
-		/*
-		 * TODO: SDM says that with acknowledge interrupt on
-		 * exit, bit 31 of the VM-exit interrupt information
-		 * (valid interrupt) is always set to 1 on
-		 * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't
-		 * need kvm_cpu_has_interrupt().  See the commit
-		 * message for details.
-		 */
-		if (nested_exit_intr_ack_set(vcpu) &&
-		    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
-		    kvm_cpu_has_interrupt(vcpu)) {
-			int irq = kvm_cpu_get_interrupt(vcpu);
-			WARN_ON(irq < 0);
-			vmcs12->vm_exit_intr_info = irq |
-				INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
-		}
-
-		if (exit_reason != -1)
-			trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
-						       vmcs12->exit_qualification,
-						       vmcs12->idt_vectoring_info_field,
-						       vmcs12->vm_exit_intr_info,
-						       vmcs12->vm_exit_intr_error_code,
-						       KVM_ISA_VMX);
-
-		load_vmcs12_host_state(vcpu, vmcs12);
-
-		return;
-	}
-	
-	/*
-	 * After an early L2 VM-entry failure, we're now back
-	 * in L1 which thinks it just finished a VMLAUNCH or
-	 * VMRESUME instruction, so we need to set the failure
-	 * flag and the VM-instruction error field of the VMCS
-	 * accordingly.
-	 */
-	nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-
-	load_vmcs12_mmu_host_state(vcpu, vmcs12);
-
-	/*
-	 * The emulated instruction was already skipped in
-	 * nested_vmx_run, but the updated RIP was never
-	 * written back to the vmcs01.
-	 */
-	skip_emulated_instruction(vcpu);
-	vmx->fail = 0;
-}
-
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
-static void vmx_leave_nested(struct kvm_vcpu *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));
-}
-
-/*
- * L1's failure to enter L2 is a subset of a normal exit, as explained in
- * 23.7 "VM-entry failures during or after loading guest state" (this also
- * lists the acceptable exit-reason and exit-qualification parameters).
- * It should only be called before L2 actually succeeded to run, and when
- * vmcs01 is current (it doesn't leave_guest_mode() or switch vmcss).
- */
-static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
-			struct vmcs12 *vmcs12,
-			u32 reason, unsigned long qualification)
-{
-	load_vmcs12_host_state(vcpu, vmcs12);
-	vmcs12->vm_exit_reason = reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
-	vmcs12->exit_qualification = qualification;
-	nested_vmx_succeed(vcpu);
-	if (enable_shadow_vmcs)
-		to_vmx(vcpu)->nested.sync_shadow_vmcs = true;
-}
-
-static int vmx_check_intercept(struct kvm_vcpu *vcpu,
-			       struct x86_instruction_info *info,
-			       enum x86_intercept_stage stage)
-{
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
-
-	/*
-	 * RDPID causes #UD if disabled through secondary execution controls.
-	 * Because it is marked as EmulateOnUD, we need to intercept it here.
-	 */
-	if (info->intercept == x86_intercept_rdtscp &&
-	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
-		ctxt->exception.vector = UD_VECTOR;
-		ctxt->exception.error_code_valid = false;
-		return X86EMUL_PROPAGATE_FAULT;
-	}
-
-	/* TODO: check more intercepts... */
-	return X86EMUL_CONTINUE;
-}
-
-#ifdef CONFIG_X86_64
-/* (a << shift) / divisor, return 1 if overflow otherwise 0 */
-static inline int u64_shl_div_u64(u64 a, unsigned int shift,
-				  u64 divisor, u64 *result)
-{
-	u64 low = a << shift, high = a >> (64 - shift);
-
-	/* To avoid the overflow on divq */
-	if (high >= divisor)
-		return 1;
-
-	/* Low hold the result, high hold rem which is discarded */
-	asm("divq %2\n\t" : "=a" (low), "=d" (high) :
-	    "rm" (divisor), "0" (low), "1" (high));
-	*result = low;
-
-	return 0;
-}
-
-static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
-{
-	struct vcpu_vmx *vmx;
-	u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
-
-	if (kvm_mwait_in_guest(vcpu->kvm))
-		return -EOPNOTSUPP;
-
-	vmx = to_vmx(vcpu);
-	tscl = rdtsc();
-	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
-	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
-	lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
-
-	if (delta_tsc > lapic_timer_advance_cycles)
-		delta_tsc -= lapic_timer_advance_cycles;
-	else
-		delta_tsc = 0;
-
-	/* Convert to host delta tsc if tsc scaling is enabled */
-	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
-			u64_shl_div_u64(delta_tsc,
-				kvm_tsc_scaling_ratio_frac_bits,
-				vcpu->arch.tsc_scaling_ratio,
-				&delta_tsc))
-		return -ERANGE;
-
-	/*
-	 * If the delta tsc can't fit in the 32 bit after the multi shift,
-	 * we can't use the preemption timer.
-	 * It's possible that it fits on later vmentries, but checking
-	 * on every vmentry is costly so we just use an hrtimer.
-	 */
-	if (delta_tsc >> (cpu_preemption_timer_multi + 32))
-		return -ERANGE;
-
-	vmx->hv_deadline_tsc = tscl + delta_tsc;
-	return delta_tsc == 0;
-}
-
-static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
-{
-	to_vmx(vcpu)->hv_deadline_tsc = -1;
-}
-#endif
-
-static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
-	if (!kvm_pause_in_guest(vcpu->kvm))
-		shrink_ple_window(vcpu);
-}
-
-static void vmx_slot_enable_log_dirty(struct kvm *kvm,
-				     struct kvm_memory_slot *slot)
-{
-	kvm_mmu_slot_leaf_clear_dirty(kvm, slot);
-	kvm_mmu_slot_largepage_remove_write_access(kvm, slot);
-}
-
-static void vmx_slot_disable_log_dirty(struct kvm *kvm,
-				       struct kvm_memory_slot *slot)
-{
-	kvm_mmu_slot_set_dirty(kvm, slot);
-}
-
-static void vmx_flush_log_dirty(struct kvm *kvm)
-{
-	kvm_flush_pml_buffers(kvm);
-}
-
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
-{
-	struct vmcs12 *vmcs12;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa;
-	struct page *page = NULL;
-	u64 *pml_address;
-
-	if (is_guest_mode(vcpu)) {
-		WARN_ON_ONCE(vmx->nested.pml_full);
-
-		/*
-		 * Check if PML is enabled for the nested guest.
-		 * Whether eptp bit 6 is set is already checked
-		 * as part of A/D emulation.
-		 */
-		vmcs12 = get_vmcs12(vcpu);
-		if (!nested_cpu_has_pml(vmcs12))
-			return 0;
-
-		if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
-			vmx->nested.pml_full = true;
-			return 1;
-		}
-
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
-
-		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->pml_address);
-		if (is_error_page(page))
-			return 0;
-
-		pml_address = kmap(page);
-		pml_address[vmcs12->guest_pml_index--] = gpa;
-		kunmap(page);
-		kvm_release_page_clean(page);
-	}
-
-	return 0;
-}
-
-static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
-					   struct kvm_memory_slot *memslot,
-					   gfn_t offset, unsigned long mask)
-{
-	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
-}
-
-static void __pi_post_block(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-
-	do {
-		old.control = new.control = pi_desc->control;
-		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
-		     "Wakeup handler not enabled while the VCPU is blocked\n");
-
-		dest = cpu_physical_id(vcpu->cpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* set 'NV' to 'notification vector' */
-		new.nv = POSTED_INTR_VECTOR;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
-
-	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
-		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		list_del(&vcpu->blocked_vcpu_list);
-		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		vcpu->pre_pcpu = -1;
-	}
-}
-
-/*
- * This routine does the following things for vCPU which is going
- * to be blocked if VT-d PI is enabled.
- * - Store the vCPU to the wakeup list, so when interrupts happen
- *   we can find the right vCPU to wake up.
- * - Change the Posted-interrupt descriptor as below:
- *      'NDST' <-- vcpu->pre_pcpu
- *      'NV' <-- POSTED_INTR_WAKEUP_VECTOR
- * - If 'ON' is set during this process, which means at least one
- *   interrupt is posted for this vCPU, we cannot block it, in
- *   this case, return 1, otherwise, return 0.
- *
- */
-static int pi_pre_block(struct kvm_vcpu *vcpu)
-{
-	unsigned int dest;
-	struct pi_desc old, new;
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
-		return 0;
-
-	WARN_ON(irqs_disabled());
-	local_irq_disable();
-	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
-		vcpu->pre_pcpu = vcpu->cpu;
-		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		list_add_tail(&vcpu->blocked_vcpu_list,
-			      &per_cpu(blocked_vcpu_on_cpu,
-				       vcpu->pre_pcpu));
-		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-	}
-
-	do {
-		old.control = new.control = pi_desc->control;
-
-		WARN((pi_desc->sn == 1),
-		     "Warning: SN field of posted-interrupts "
-		     "is set before blocking\n");
-
-		/*
-		 * Since vCPU can be preempted during this process,
-		 * vcpu->cpu could be different with pre_pcpu, we
-		 * need to set pre_pcpu as the destination of wakeup
-		 * notification event, then we can find the right vCPU
-		 * to wakeup in wakeup handler if interrupts happen
-		 * when the vCPU is in blocked state.
-		 */
-		dest = cpu_physical_id(vcpu->pre_pcpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* set 'NV' to 'wakeup vector' */
-		new.nv = POSTED_INTR_WAKEUP_VECTOR;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
-
-	/* We should not block the vCPU if an interrupt is posted for it.  */
-	if (pi_test_on(pi_desc) == 1)
-		__pi_post_block(vcpu);
-
-	local_irq_enable();
-	return (vcpu->pre_pcpu == -1);
-}
-
-static int vmx_pre_block(struct kvm_vcpu *vcpu)
-{
-	if (pi_pre_block(vcpu))
-		return 1;
-
-	if (kvm_lapic_hv_timer_in_use(vcpu))
-		kvm_lapic_switch_to_sw_timer(vcpu);
-
-	return 0;
-}
-
-static void pi_post_block(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->pre_pcpu == -1)
-		return;
-
-	WARN_ON(irqs_disabled());
-	local_irq_disable();
-	__pi_post_block(vcpu);
-	local_irq_enable();
-}
-
-static void vmx_post_block(struct kvm_vcpu *vcpu)
-{
-	if (kvm_x86_ops->set_hv_timer)
-		kvm_lapic_switch_to_hv_timer(vcpu);
-
-	pi_post_block(vcpu);
-}
-
-/*
- * vmx_update_pi_irte - set IRTE for Posted-Interrupts
- *
- * @kvm: kvm
- * @host_irq: host irq of the interrupt
- * @guest_irq: gsi of the interrupt
- * @set: set or unset PI
- * returns 0 on success, < 0 on failure
- */
-static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
-			      uint32_t guest_irq, bool set)
-{
-	struct kvm_kernel_irq_routing_entry *e;
-	struct kvm_irq_routing_table *irq_rt;
-	struct kvm_lapic_irq irq;
-	struct kvm_vcpu *vcpu;
-	struct vcpu_data vcpu_info;
-	int idx, ret = 0;
-
-	if (!kvm_arch_has_assigned_device(kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP) ||
-		!kvm_vcpu_apicv_active(kvm->vcpus[0]))
-		return 0;
-
-	idx = srcu_read_lock(&kvm->irq_srcu);
-	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	if (guest_irq >= irq_rt->nr_rt_entries ||
-	    hlist_empty(&irq_rt->map[guest_irq])) {
-		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
-			     guest_irq, irq_rt->nr_rt_entries);
-		goto out;
-	}
-
-	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
-		if (e->type != KVM_IRQ_ROUTING_MSI)
-			continue;
-		/*
-		 * VT-d PI cannot support posting multicast/broadcast
-		 * interrupts to a vCPU, we still use interrupt remapping
-		 * for these kind of interrupts.
-		 *
-		 * For lowest-priority interrupts, we only support
-		 * those with single CPU as the destination, e.g. user
-		 * configures the interrupts via /proc/irq or uses
-		 * irqbalance to make the interrupts single-CPU.
-		 *
-		 * We will support full lowest-priority interrupt later.
-		 */
-
-		kvm_set_msi_irq(kvm, e, &irq);
-		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
-			/*
-			 * Make sure the IRTE is in remapped mode if
-			 * we don't handle it in posted mode.
-			 */
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			if (ret < 0) {
-				printk(KERN_INFO
-				   "failed to back to remapped mode, irq: %u\n",
-				   host_irq);
-				goto out;
-			}
-
-			continue;
-		}
-
-		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
-		vcpu_info.vector = irq.vector;
-
-		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
-				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
-
-		if (set)
-			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
-
-		if (ret < 0) {
-			printk(KERN_INFO "%s: failed to update PI IRTE\n",
-					__func__);
-			goto out;
-		}
-	}
-
-	ret = 0;
-out:
-	srcu_read_unlock(&kvm->irq_srcu, idx);
-	return ret;
-}
-
-static void vmx_setup_mce(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.mcg_cap & MCG_LMCE_P)
-		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
-			FEATURE_CONTROL_LMCE;
-	else
-		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
-			~FEATURE_CONTROL_LMCE;
-}
-
-static int vmx_smi_allowed(struct kvm_vcpu *vcpu)
-{
-	/* we need a nested vmexit to enter SMM, postpone if run is pending */
-	if (to_vmx(vcpu)->nested.nested_run_pending)
-		return 0;
-	return 1;
-}
-
-static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	vmx->nested.smm.guest_mode = is_guest_mode(vcpu);
-	if (vmx->nested.smm.guest_mode)
-		nested_vmx_vmexit(vcpu, -1, 0, 0);
-
-	vmx->nested.smm.vmxon = vmx->nested.vmxon;
-	vmx->nested.vmxon = false;
-	vmx_clear_hlt(vcpu);
-	return 0;
-}
-
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int ret;
-
-	if (vmx->nested.smm.vmxon) {
-		vmx->nested.vmxon = true;
-		vmx->nested.smm.vmxon = false;
-	}
-
-	if (vmx->nested.smm.guest_mode) {
-		vcpu->arch.hflags &= ~HF_SMM_MASK;
-		ret = enter_vmx_non_root_mode(vcpu, NULL);
-		vcpu->arch.hflags |= HF_SMM_MASK;
-		if (ret)
-			return ret;
-
-		vmx->nested.smm.guest_mode = false;
-	}
-	return 0;
-}
-
-static int enable_smi_window(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
-static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
-				struct kvm_nested_state __user *user_kvm_nested_state,
-				u32 user_data_size)
-{
-	struct vcpu_vmx *vmx;
-	struct vmcs12 *vmcs12;
-	struct kvm_nested_state kvm_state = {
-		.flags = 0,
-		.format = 0,
-		.size = sizeof(kvm_state),
-		.vmx.vmxon_pa = -1ull,
-		.vmx.vmcs_pa = -1ull,
-	};
-
-	if (!vcpu)
-		return kvm_state.size + 2 * VMCS12_SIZE;
-
-	vmx = to_vmx(vcpu);
-	vmcs12 = get_vmcs12(vcpu);
-	if (nested_vmx_allowed(vcpu) &&
-	    (vmx->nested.vmxon || vmx->nested.smm.vmxon)) {
-		kvm_state.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
-		kvm_state.vmx.vmcs_pa = vmx->nested.current_vmptr;
-
-		if (vmx->nested.current_vmptr != -1ull) {
-			kvm_state.size += VMCS12_SIZE;
-
-			if (is_guest_mode(vcpu) &&
-			    nested_cpu_has_shadow_vmcs(vmcs12) &&
-			    vmcs12->vmcs_link_pointer != -1ull)
-				kvm_state.size += VMCS12_SIZE;
-		}
-
-		if (vmx->nested.smm.vmxon)
-			kvm_state.vmx.smm.flags |= KVM_STATE_NESTED_SMM_VMXON;
-
-		if (vmx->nested.smm.guest_mode)
-			kvm_state.vmx.smm.flags |= KVM_STATE_NESTED_SMM_GUEST_MODE;
-
-		if (is_guest_mode(vcpu)) {
-			kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
-
-			if (vmx->nested.nested_run_pending)
-				kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
-		}
-	}
-
-	if (user_data_size < kvm_state.size)
-		goto out;
-
-	if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state)))
-		return -EFAULT;
-
-	if (vmx->nested.current_vmptr == -1ull)
-		goto out;
-
-	/*
-	 * When running L2, the authoritative vmcs12 state is in the
-	 * vmcs02. When running L1, the authoritative vmcs12 state is
-	 * in the shadow vmcs linked to vmcs01, unless
-	 * sync_shadow_vmcs is set, in which case, the authoritative
-	 * vmcs12 state is in the vmcs12 already.
-	 */
-	if (is_guest_mode(vcpu))
-		sync_vmcs12(vcpu, vmcs12);
-	else if (enable_shadow_vmcs && !vmx->nested.sync_shadow_vmcs)
-		copy_shadow_to_vmcs12(vmx);
-
-	if (copy_to_user(user_kvm_nested_state->data, vmcs12, sizeof(*vmcs12)))
-		return -EFAULT;
-
-	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
-	    vmcs12->vmcs_link_pointer != -1ull) {
-		if (copy_to_user(user_kvm_nested_state->data + VMCS12_SIZE,
-				 get_shadow_vmcs12(vcpu), sizeof(*vmcs12)))
-			return -EFAULT;
-	}
-
-out:
-	return kvm_state.size;
-}
-
-static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
-				struct kvm_nested_state __user *user_kvm_nested_state,
-				struct kvm_nested_state *kvm_state)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct vmcs12 *vmcs12;
-	u32 exit_qual;
-	int ret;
-
-	if (kvm_state->format != 0)
-		return -EINVAL;
-
-	if (!nested_vmx_allowed(vcpu))
-		return kvm_state->vmx.vmxon_pa == -1ull ? 0 : -EINVAL;
-
-	if (kvm_state->vmx.vmxon_pa == -1ull) {
-		if (kvm_state->vmx.smm.flags)
-			return -EINVAL;
-
-		if (kvm_state->vmx.vmcs_pa != -1ull)
-			return -EINVAL;
-
-		vmx_leave_nested(vcpu);
-		return 0;
-	}
-
-	if (!page_address_valid(vcpu, kvm_state->vmx.vmxon_pa))
-		return -EINVAL;
-
-	if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
-	    (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
-		return -EINVAL;
-
-	if (kvm_state->vmx.smm.flags &
-	    ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
-		return -EINVAL;
-
-	/*
-	 * SMM temporarily disables VMX, so we cannot be in guest mode,
-	 * nor can VMLAUNCH/VMRESUME be pending.  Outside SMM, SMM flags
-	 * must be zero.
-	 */
-	if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags)
-		return -EINVAL;
-
-	if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
-	    !(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
-		return -EINVAL;
-
-	vmx_leave_nested(vcpu);
-	if (kvm_state->vmx.vmxon_pa == -1ull)
-		return 0;
-
-	vmx->nested.vmxon_ptr = kvm_state->vmx.vmxon_pa;
-	ret = enter_vmx_operation(vcpu);
-	if (ret)
-		return ret;
-
-	/* Empty 'VMXON' state is permitted */
-	if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
-		return 0;
-
-	if (kvm_state->vmx.vmcs_pa == kvm_state->vmx.vmxon_pa ||
-	    !page_address_valid(vcpu, kvm_state->vmx.vmcs_pa))
-		return -EINVAL;
-
-	set_current_vmptr(vmx, kvm_state->vmx.vmcs_pa);
-
-	if (kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) {
-		vmx->nested.smm.vmxon = true;
-		vmx->nested.vmxon = false;
-
-		if (kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE)
-			vmx->nested.smm.guest_mode = true;
-	}
-
-	vmcs12 = get_vmcs12(vcpu);
-	if (copy_from_user(vmcs12, user_kvm_nested_state->data, sizeof(*vmcs12)))
-		return -EFAULT;
-
-	if (vmcs12->hdr.revision_id != VMCS12_REVISION)
-		return -EINVAL;
-
-	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
-		return 0;
-
-	vmx->nested.nested_run_pending =
-		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
-
-	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
-	    vmcs12->vmcs_link_pointer != -1ull) {
-		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
-		if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12))
-			return -EINVAL;
-
-		if (copy_from_user(shadow_vmcs12,
-				   user_kvm_nested_state->data + VMCS12_SIZE,
-				   sizeof(*vmcs12)))
-			return -EFAULT;
-
-		if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
-		    !shadow_vmcs12->hdr.shadow_vmcs)
-			return -EINVAL;
-	}
-
-	if (check_vmentry_prereqs(vcpu, vmcs12) ||
-	    check_vmentry_postreqs(vcpu, vmcs12, &exit_qual))
-		return -EINVAL;
-
-	vmx->nested.dirty_vmcs12 = true;
-	ret = enter_vmx_non_root_mode(vcpu, NULL);
-	if (ret)
-		return -EINVAL;
-
-	return 0;
-}
-
-static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
-	.cpu_has_kvm_support = cpu_has_kvm_support,
-	.disabled_by_bios = vmx_disabled_by_bios,
-	.hardware_setup = hardware_setup,
-	.hardware_unsetup = hardware_unsetup,
-	.check_processor_compatibility = vmx_check_processor_compat,
-	.hardware_enable = hardware_enable,
-	.hardware_disable = hardware_disable,
-	.cpu_has_accelerated_tpr = report_flexpriority,
-	.has_emulated_msr = vmx_has_emulated_msr,
-
-	.vm_init = vmx_vm_init,
-	.vm_alloc = vmx_vm_alloc,
-	.vm_free = vmx_vm_free,
-
-	.vcpu_create = vmx_create_vcpu,
-	.vcpu_free = vmx_free_vcpu,
-	.vcpu_reset = vmx_vcpu_reset,
-
-	.prepare_guest_switch = vmx_prepare_switch_to_guest,
-	.vcpu_load = vmx_vcpu_load,
-	.vcpu_put = vmx_vcpu_put,
-
-	.update_bp_intercept = update_exception_bitmap,
-	.get_msr_feature = vmx_get_msr_feature,
-	.get_msr = vmx_get_msr,
-	.set_msr = vmx_set_msr,
-	.get_segment_base = vmx_get_segment_base,
-	.get_segment = vmx_get_segment,
-	.set_segment = vmx_set_segment,
-	.get_cpl = vmx_get_cpl,
-	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
-	.decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
-	.decache_cr3 = vmx_decache_cr3,
-	.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
-	.set_cr0 = vmx_set_cr0,
-	.set_cr3 = vmx_set_cr3,
-	.set_cr4 = vmx_set_cr4,
-	.set_efer = vmx_set_efer,
-	.get_idt = vmx_get_idt,
-	.set_idt = vmx_set_idt,
-	.get_gdt = vmx_get_gdt,
-	.set_gdt = vmx_set_gdt,
-	.get_dr6 = vmx_get_dr6,
-	.set_dr6 = vmx_set_dr6,
-	.set_dr7 = vmx_set_dr7,
-	.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
-	.cache_reg = vmx_cache_reg,
-	.get_rflags = vmx_get_rflags,
-	.set_rflags = vmx_set_rflags,
-
-	.tlb_flush = vmx_flush_tlb,
-	.tlb_flush_gva = vmx_flush_tlb_gva,
-
-	.run = vmx_vcpu_run,
-	.handle_exit = vmx_handle_exit,
-	.skip_emulated_instruction = skip_emulated_instruction,
-	.set_interrupt_shadow = vmx_set_interrupt_shadow,
-	.get_interrupt_shadow = vmx_get_interrupt_shadow,
-	.patch_hypercall = vmx_patch_hypercall,
-	.set_irq = vmx_inject_irq,
-	.set_nmi = vmx_inject_nmi,
-	.queue_exception = vmx_queue_exception,
-	.cancel_injection = vmx_cancel_injection,
-	.interrupt_allowed = vmx_interrupt_allowed,
-	.nmi_allowed = vmx_nmi_allowed,
-	.get_nmi_mask = vmx_get_nmi_mask,
-	.set_nmi_mask = vmx_set_nmi_mask,
-	.enable_nmi_window = enable_nmi_window,
-	.enable_irq_window = enable_irq_window,
-	.update_cr8_intercept = update_cr8_intercept,
-	.set_virtual_apic_mode = vmx_set_virtual_apic_mode,
-	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
-	.get_enable_apicv = vmx_get_enable_apicv,
-	.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
-	.load_eoi_exitmap = vmx_load_eoi_exitmap,
-	.apicv_post_state_restore = vmx_apicv_post_state_restore,
-	.hwapic_irr_update = vmx_hwapic_irr_update,
-	.hwapic_isr_update = vmx_hwapic_isr_update,
-	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
-	.sync_pir_to_irr = vmx_sync_pir_to_irr,
-	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
-
-	.set_tss_addr = vmx_set_tss_addr,
-	.set_identity_map_addr = vmx_set_identity_map_addr,
-	.get_tdp_level = get_ept_level,
-	.get_mt_mask = vmx_get_mt_mask,
-
-	.get_exit_info = vmx_get_exit_info,
-
-	.get_lpage_level = vmx_get_lpage_level,
-
-	.cpuid_update = vmx_cpuid_update,
-
-	.rdtscp_supported = vmx_rdtscp_supported,
-	.invpcid_supported = vmx_invpcid_supported,
-
-	.set_supported_cpuid = vmx_set_supported_cpuid,
-
-	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
-
-	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
-	.write_l1_tsc_offset = vmx_write_l1_tsc_offset,
-
-	.set_tdp_cr3 = vmx_set_cr3,
-
-	.check_intercept = vmx_check_intercept,
-	.handle_external_intr = vmx_handle_external_intr,
-	.mpx_supported = vmx_mpx_supported,
-	.xsaves_supported = vmx_xsaves_supported,
-	.umip_emulated = vmx_umip_emulated,
-
-	.check_nested_events = vmx_check_nested_events,
-	.request_immediate_exit = vmx_request_immediate_exit,
-
-	.sched_in = vmx_sched_in,
-
-	.slot_enable_log_dirty = vmx_slot_enable_log_dirty,
-	.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
-	.flush_log_dirty = vmx_flush_log_dirty,
-	.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
-	.write_log_dirty = vmx_write_pml_buffer,
-
-	.pre_block = vmx_pre_block,
-	.post_block = vmx_post_block,
-
-	.pmu_ops = &intel_pmu_ops,
-
-	.update_pi_irte = vmx_update_pi_irte,
-
-#ifdef CONFIG_X86_64
-	.set_hv_timer = vmx_set_hv_timer,
-	.cancel_hv_timer = vmx_cancel_hv_timer,
-#endif
-
-	.setup_mce = vmx_setup_mce,
-
-	.get_nested_state = vmx_get_nested_state,
-	.set_nested_state = vmx_set_nested_state,
-	.get_vmcs12_pages = nested_get_vmcs12_pages,
-
-	.smi_allowed = vmx_smi_allowed,
-	.pre_enter_smm = vmx_pre_enter_smm,
-	.pre_leave_smm = vmx_pre_leave_smm,
-	.enable_smi_window = enable_smi_window,
-};
-
-static void vmx_cleanup_l1d_flush(void)
-{
-	if (vmx_l1d_flush_pages) {
-		free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
-		vmx_l1d_flush_pages = NULL;
-	}
-	/* Restore state so sysfs ignores VMX */
-	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
-}
-
-static void vmx_exit(void)
-{
-#ifdef CONFIG_KEXEC_CORE
-	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
-	synchronize_rcu();
-#endif
-
-	kvm_exit();
-
-#if IS_ENABLED(CONFIG_HYPERV)
-	if (static_branch_unlikely(&enable_evmcs)) {
-		int cpu;
-		struct hv_vp_assist_page *vp_ap;
-		/*
-		 * Reset everything to support using non-enlightened VMCS
-		 * access later (e.g. when we reload the module with
-		 * enlightened_vmcs=0)
-		 */
-		for_each_online_cpu(cpu) {
-			vp_ap =	hv_get_vp_assist_page(cpu);
-
-			if (!vp_ap)
-				continue;
-
-			vp_ap->current_nested_vmcs = 0;
-			vp_ap->enlighten_vmentry = 0;
-		}
-
-		static_branch_disable(&enable_evmcs);
-	}
-#endif
-	vmx_cleanup_l1d_flush();
-}
-module_exit(vmx_exit);
-
-static int __init vmx_init(void)
-{
-	int r;
-
-#if IS_ENABLED(CONFIG_HYPERV)
-	/*
-	 * Enlightened VMCS usage should be recommended and the host needs
-	 * to support eVMCS v1 or above. We can also disable eVMCS support
-	 * with module parameter.
-	 */
-	if (enlightened_vmcs &&
-	    ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED &&
-	    (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >=
-	    KVM_EVMCS_VERSION) {
-		int cpu;
-
-		/* Check that we have assist pages on all online CPUs */
-		for_each_online_cpu(cpu) {
-			if (!hv_get_vp_assist_page(cpu)) {
-				enlightened_vmcs = false;
-				break;
-			}
-		}
-
-		if (enlightened_vmcs) {
-			pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n");
-			static_branch_enable(&enable_evmcs);
-		}
-	} else {
-		enlightened_vmcs = false;
-	}
-#endif
-
-	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
-		     __alignof__(struct vcpu_vmx), THIS_MODULE);
-	if (r)
-		return r;
-
-	/*
-	 * Must be called after kvm_init() so enable_ept is properly set
-	 * up. Hand the parameter mitigation value in which was stored in
-	 * the pre module init parser. If no parameter was given, it will
-	 * contain 'auto' which will be turned into the default 'cond'
-	 * mitigation mode.
-	 */
-	if (boot_cpu_has(X86_BUG_L1TF)) {
-		r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
-		if (r) {
-			vmx_exit();
-			return r;
-		}
-	}
-
-#ifdef CONFIG_KEXEC_CORE
-	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
-			   crash_vmclear_local_loaded_vmcss);
-#endif
-	vmx_check_vmcs12_offsets();
-
-	return 0;
-}
-module_init(vmx_init);
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
new file mode 100644
index 0000000..7aa6971
--- /dev/null
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -0,0 +1,351 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_CAPS_H
+#define __KVM_X86_VMX_CAPS_H
+
+#include <asm/vmx.h>
+
+#include "lapic.h"
+
+extern bool __read_mostly enable_vpid;
+extern bool __read_mostly flexpriority_enabled;
+extern bool __read_mostly enable_ept;
+extern bool __read_mostly enable_unrestricted_guest;
+extern bool __read_mostly enable_ept_ad_bits;
+extern bool __read_mostly enable_pml;
+extern int __read_mostly pt_mode;
+
+#define PT_MODE_SYSTEM		0
+#define PT_MODE_HOST_GUEST	1
+
+struct nested_vmx_msrs {
+	/*
+	 * We only store the "true" versions of the VMX capability MSRs. We
+	 * generate the "non-true" versions by setting the must-be-1 bits
+	 * according to the SDM.
+	 */
+	u32 procbased_ctls_low;
+	u32 procbased_ctls_high;
+	u32 secondary_ctls_low;
+	u32 secondary_ctls_high;
+	u32 pinbased_ctls_low;
+	u32 pinbased_ctls_high;
+	u32 exit_ctls_low;
+	u32 exit_ctls_high;
+	u32 entry_ctls_low;
+	u32 entry_ctls_high;
+	u32 misc_low;
+	u32 misc_high;
+	u32 ept_caps;
+	u32 vpid_caps;
+	u64 basic;
+	u64 cr0_fixed0;
+	u64 cr0_fixed1;
+	u64 cr4_fixed0;
+	u64 cr4_fixed1;
+	u64 vmcs_enum;
+	u64 vmfunc_controls;
+};
+
+struct vmcs_config {
+	int size;
+	int order;
+	u32 basic_cap;
+	u32 revision_id;
+	u32 pin_based_exec_ctrl;
+	u32 cpu_based_exec_ctrl;
+	u32 cpu_based_2nd_exec_ctrl;
+	u32 vmexit_ctrl;
+	u32 vmentry_ctrl;
+	struct nested_vmx_msrs nested;
+};
+extern struct vmcs_config vmcs_config;
+
+struct vmx_capability {
+	u32 ept;
+	u32 vpid;
+};
+extern struct vmx_capability vmx_capability;
+
+static inline bool cpu_has_vmx_basic_inout(void)
+{
+	return	(((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT);
+}
+
+static inline bool cpu_has_virtual_nmis(void)
+{
+	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
+}
+
+static inline bool cpu_has_vmx_preemption_timer(void)
+{
+	return vmcs_config.pin_based_exec_ctrl &
+		PIN_BASED_VMX_PREEMPTION_TIMER;
+}
+
+static inline bool cpu_has_vmx_posted_intr(void)
+{
+	return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
+		vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
+}
+
+static inline bool cpu_has_load_ia32_efer(void)
+{
+	return (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_EFER) &&
+	       (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_EFER);
+}
+
+static inline bool cpu_has_load_perf_global_ctrl(void)
+{
+	return (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	       (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
+}
+
+static inline bool vmx_mpx_supported(void)
+{
+	return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) &&
+		(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS);
+}
+
+static inline bool cpu_has_vmx_tpr_shadow(void)
+{
+	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
+}
+
+static inline bool cpu_need_tpr_shadow(struct kvm_vcpu *vcpu)
+{
+	return cpu_has_vmx_tpr_shadow() && lapic_in_kernel(vcpu);
+}
+
+static inline bool cpu_has_vmx_msr_bitmap(void)
+{
+	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
+}
+
+static inline bool cpu_has_secondary_exec_ctrls(void)
+{
+	return vmcs_config.cpu_based_exec_ctrl &
+		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+}
+
+static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+}
+
+static inline bool cpu_has_vmx_ept(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_EPT;
+}
+
+static inline bool vmx_umip_emulated(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_DESC;
+}
+
+static inline bool cpu_has_vmx_rdtscp(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_RDTSCP;
+}
+
+static inline bool cpu_has_vmx_virtualize_x2apic_mode(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+}
+
+static inline bool cpu_has_vmx_vpid(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_VPID;
+}
+
+static inline bool cpu_has_vmx_wbinvd_exit(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_WBINVD_EXITING;
+}
+
+static inline bool cpu_has_vmx_unrestricted_guest(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_UNRESTRICTED_GUEST;
+}
+
+static inline bool cpu_has_vmx_apic_register_virt(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_APIC_REGISTER_VIRT;
+}
+
+static inline bool cpu_has_vmx_virtual_intr_delivery(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
+}
+
+static inline bool cpu_has_vmx_ple(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
+}
+
+static inline bool vmx_rdrand_supported(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_RDRAND_EXITING;
+}
+
+static inline bool cpu_has_vmx_invpcid(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_INVPCID;
+}
+
+static inline bool cpu_has_vmx_vmfunc(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_VMFUNC;
+}
+
+static inline bool cpu_has_vmx_shadow_vmcs(void)
+{
+	u64 vmx_msr;
+
+	/* check if the cpu supports writing r/o exit information fields */
+	rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
+	if (!(vmx_msr & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS))
+		return false;
+
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_SHADOW_VMCS;
+}
+
+static inline bool cpu_has_vmx_encls_vmexit(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENCLS_EXITING;
+}
+
+static inline bool vmx_rdseed_supported(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_RDSEED_EXITING;
+}
+
+static inline bool cpu_has_vmx_pml(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML;
+}
+
+static inline bool vmx_xsaves_supported(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_XSAVES;
+}
+
+static inline bool vmx_waitpkg_supported(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+}
+
+static inline bool cpu_has_vmx_tsc_scaling(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_TSC_SCALING;
+}
+
+static inline bool cpu_has_vmx_apicv(void)
+{
+	return cpu_has_vmx_apic_register_virt() &&
+		cpu_has_vmx_virtual_intr_delivery() &&
+		cpu_has_vmx_posted_intr();
+}
+
+static inline bool cpu_has_vmx_flexpriority(void)
+{
+	return cpu_has_vmx_tpr_shadow() &&
+		cpu_has_vmx_virtualize_apic_accesses();
+}
+
+static inline bool cpu_has_vmx_ept_execute_only(void)
+{
+	return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
+}
+
+static inline bool cpu_has_vmx_ept_4levels(void)
+{
+	return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT;
+}
+
+static inline bool cpu_has_vmx_ept_5levels(void)
+{
+	return vmx_capability.ept & VMX_EPT_PAGE_WALK_5_BIT;
+}
+
+static inline bool cpu_has_vmx_ept_mt_wb(void)
+{
+	return vmx_capability.ept & VMX_EPTP_WB_BIT;
+}
+
+static inline bool cpu_has_vmx_ept_2m_page(void)
+{
+	return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
+}
+
+static inline bool cpu_has_vmx_ept_1g_page(void)
+{
+	return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
+}
+
+static inline bool cpu_has_vmx_ept_ad_bits(void)
+{
+	return vmx_capability.ept & VMX_EPT_AD_BIT;
+}
+
+static inline bool cpu_has_vmx_invept_context(void)
+{
+	return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
+}
+
+static inline bool cpu_has_vmx_invept_global(void)
+{
+	return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
+}
+
+static inline bool cpu_has_vmx_invvpid(void)
+{
+	return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
+}
+
+static inline bool cpu_has_vmx_invvpid_individual_addr(void)
+{
+	return vmx_capability.vpid & VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT;
+}
+
+static inline bool cpu_has_vmx_invvpid_single(void)
+{
+	return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
+}
+
+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_intel_pt(void)
+{
+	u64 vmx_msr;
+
+	rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
+	return (vmx_msr & MSR_IA32_VMX_MISC_INTEL_PT) &&
+		(vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) &&
+		(vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_IA32_RTIT_CTL) &&
+		(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL);
+}
+
+#endif /* __KVM_X86_VMX_CAPS_H */
diff --git a/arch/x86/kvm/vmx_evmcs.h b/arch/x86/kvm/vmx/evmcs.c
similarity index 85%
rename from arch/x86/kvm/vmx_evmcs.h
rename to arch/x86/kvm/vmx/evmcs.c
index 210a884..7235970 100644
--- a/arch/x86/kvm/vmx_evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -1,20 +1,23 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __KVM_X86_VMX_EVMCS_H
-#define __KVM_X86_VMX_EVMCS_H
+// SPDX-License-Identifier: GPL-2.0
 
-#include <asm/hyperv-tlfs.h>
+#include <linux/errno.h>
+#include <linux/smp.h>
+
+#include "../hyperv.h"
+#include "evmcs.h"
+#include "vmcs.h"
+#include "vmx.h"
+
+DEFINE_STATIC_KEY_FALSE(enable_evmcs);
+
+#if IS_ENABLED(CONFIG_HYPERV)
 
 #define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n)))))
 #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x)
 #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \
 		{EVMCS1_OFFSET(name), clean_field}
 
-struct evmcs_field {
-	u16 offset;
-	u16 clean_field;
-};
-
-static const struct evmcs_field vmcs_field_to_evmcs_1[] = {
+const struct evmcs_field vmcs_field_to_evmcs_1[] = {
 	/* 64 bit rw */
 	EVMCS1_FIELD(GUEST_RIP, guest_rip,
 		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE),
@@ -298,27 +301,71 @@
 	EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id,
 		     HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT),
 };
+const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
 
-static __always_inline int get_evmcs_offset(unsigned long field,
-					    u16 *clean_field)
+void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
 {
-	unsigned int index = ROL16(field, 6);
-	const struct evmcs_field *evmcs_field;
+	vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+	vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
 
-	if (unlikely(index >= ARRAY_SIZE(vmcs_field_to_evmcs_1))) {
-		WARN_ONCE(1, "KVM: accessing unsupported EVMCS field %lx\n",
-			  field);
-		return -ENOENT;
-	}
+	vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+	vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
 
-	evmcs_field = &vmcs_field_to_evmcs_1[index];
+}
+#endif
 
-	if (clean_field)
-		*clean_field = evmcs_field->clean_field;
+bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa)
+{
+	struct hv_vp_assist_page assist_page;
 
-	return evmcs_field->offset;
+	*evmcs_gpa = -1ull;
+
+	if (unlikely(!kvm_hv_get_assist_page(vcpu, &assist_page)))
+		return false;
+
+	if (unlikely(!assist_page.enlighten_vmentry))
+		return false;
+
+	*evmcs_gpa = assist_page.current_nested_vmcs;
+
+	return true;
 }
 
-#undef ROL16
+uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+       /*
+        * vmcs_version represents the range of supported Enlightened VMCS
+        * versions: lower 8 bits is the minimal version, higher 8 bits is the
+        * maximum supported version. KVM supports versions from 1 to
+        * KVM_EVMCS_VERSION.
+        */
+       if (vmx->nested.enlightened_vmcs_enabled)
+               return (KVM_EVMCS_VERSION << 8) | 1;
 
-#endif /* __KVM_X86_VMX_EVMCS_H */
+       return 0;
+}
+
+int nested_enable_evmcs(struct kvm_vcpu *vcpu,
+			uint16_t *vmcs_version)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool evmcs_already_enabled = vmx->nested.enlightened_vmcs_enabled;
+
+	vmx->nested.enlightened_vmcs_enabled = true;
+
+	if (vmcs_version)
+		*vmcs_version = nested_get_evmcs_version(vcpu);
+
+	/* We don't support disabling the feature for simplicity. */
+	if (evmcs_already_enabled)
+		return 0;
+
+	vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+	vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
+	vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+	vmx->nested.msrs.secondary_ctls_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+	vmx->nested.msrs.vmfunc_controls &= ~EVMCS1_UNSUPPORTED_VMFUNC;
+
+	return 0;
+}
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
new file mode 100644
index 0000000..07ebf68
--- /dev/null
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_EVMCS_H
+#define __KVM_X86_VMX_EVMCS_H
+
+#include <linux/jump_label.h>
+
+#include <asm/hyperv-tlfs.h>
+#include <asm/mshyperv.h>
+#include <asm/vmx.h>
+
+#include "capabilities.h"
+#include "vmcs.h"
+
+struct vmcs_config;
+
+DECLARE_STATIC_KEY_FALSE(enable_evmcs);
+
+#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs))
+
+#define KVM_EVMCS_VERSION 1
+
+/*
+ * Enlightened VMCSv1 doesn't support these:
+ *
+ *	POSTED_INTR_NV                  = 0x00000002,
+ *	GUEST_INTR_STATUS               = 0x00000810,
+ *	APIC_ACCESS_ADDR		= 0x00002014,
+ *	POSTED_INTR_DESC_ADDR           = 0x00002016,
+ *	EOI_EXIT_BITMAP0                = 0x0000201c,
+ *	EOI_EXIT_BITMAP1                = 0x0000201e,
+ *	EOI_EXIT_BITMAP2                = 0x00002020,
+ *	EOI_EXIT_BITMAP3                = 0x00002022,
+ *	GUEST_PML_INDEX			= 0x00000812,
+ *	PML_ADDRESS			= 0x0000200e,
+ *	VM_FUNCTION_CONTROL             = 0x00002018,
+ *	EPTP_LIST_ADDRESS               = 0x00002024,
+ *	VMREAD_BITMAP                   = 0x00002026,
+ *	VMWRITE_BITMAP                  = 0x00002028,
+ *
+ *	TSC_MULTIPLIER                  = 0x00002032,
+ *	PLE_GAP                         = 0x00004020,
+ *	PLE_WINDOW                      = 0x00004022,
+ *	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
+ *      GUEST_IA32_PERF_GLOBAL_CTRL     = 0x00002808,
+ *      HOST_IA32_PERF_GLOBAL_CTRL      = 0x00002c04,
+ *
+ * Currently unsupported in KVM:
+ *	GUEST_IA32_RTIT_CTL		= 0x00002814,
+ */
+#define EVMCS1_UNSUPPORTED_PINCTRL (PIN_BASED_POSTED_INTR | \
+				    PIN_BASED_VMX_PREEMPTION_TIMER)
+#define EVMCS1_UNSUPPORTED_2NDEXEC					\
+	(SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |				\
+	 SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |			\
+	 SECONDARY_EXEC_APIC_REGISTER_VIRT |				\
+	 SECONDARY_EXEC_ENABLE_PML |					\
+	 SECONDARY_EXEC_ENABLE_VMFUNC |					\
+	 SECONDARY_EXEC_SHADOW_VMCS |					\
+	 SECONDARY_EXEC_TSC_SCALING |					\
+	 SECONDARY_EXEC_PAUSE_LOOP_EXITING)
+#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING)
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+struct evmcs_field {
+	u16 offset;
+	u16 clean_field;
+};
+
+extern const struct evmcs_field vmcs_field_to_evmcs_1[];
+extern const unsigned int nr_evmcs_1_fields;
+
+#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n)))))
+
+static __always_inline int get_evmcs_offset(unsigned long field,
+					    u16 *clean_field)
+{
+	unsigned int index = ROL16(field, 6);
+	const struct evmcs_field *evmcs_field;
+
+	if (unlikely(index >= nr_evmcs_1_fields)) {
+		WARN_ONCE(1, "KVM: accessing unsupported EVMCS field %lx\n",
+			  field);
+		return -ENOENT;
+	}
+
+	evmcs_field = &vmcs_field_to_evmcs_1[index];
+
+	if (clean_field)
+		*clean_field = evmcs_field->clean_field;
+
+	return evmcs_field->offset;
+}
+
+#undef ROL16
+
+static inline void evmcs_write64(unsigned long field, u64 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u64 *)((char *)current_evmcs + offset) = value;
+
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static inline void evmcs_write32(unsigned long field, u32 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u32 *)((char *)current_evmcs + offset) = value;
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static inline void evmcs_write16(unsigned long field, u16 value)
+{
+	u16 clean_field;
+	int offset = get_evmcs_offset(field, &clean_field);
+
+	if (offset < 0)
+		return;
+
+	*(u16 *)((char *)current_evmcs + offset) = value;
+	current_evmcs->hv_clean_fields &= ~clean_field;
+}
+
+static inline u64 evmcs_read64(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u64 *)((char *)current_evmcs + offset);
+}
+
+static inline u32 evmcs_read32(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u32 *)((char *)current_evmcs + offset);
+}
+
+static inline u16 evmcs_read16(unsigned long field)
+{
+	int offset = get_evmcs_offset(field, NULL);
+
+	if (offset < 0)
+		return 0;
+
+	return *(u16 *)((char *)current_evmcs + offset);
+}
+
+static inline void evmcs_touch_msr_bitmap(void)
+{
+	if (unlikely(!current_evmcs))
+		return;
+
+	if (current_evmcs->hv_enlightenments_control.msr_bitmap)
+		current_evmcs->hv_clean_fields &=
+			~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
+}
+
+static inline void evmcs_load(u64 phys_addr)
+{
+	struct hv_vp_assist_page *vp_ap =
+		hv_get_vp_assist_page(smp_processor_id());
+
+	if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall)
+		vp_ap->nested_control.features.directhypercall = 1;
+	vp_ap->current_nested_vmcs = phys_addr;
+	vp_ap->enlighten_vmentry = 1;
+}
+
+void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
+#else /* !IS_ENABLED(CONFIG_HYPERV) */
+static inline void evmcs_write64(unsigned long field, u64 value) {}
+static inline void evmcs_write32(unsigned long field, u32 value) {}
+static inline void evmcs_write16(unsigned long field, u16 value) {}
+static inline u64 evmcs_read64(unsigned long field) { return 0; }
+static inline u32 evmcs_read32(unsigned long field) { return 0; }
+static inline u16 evmcs_read16(unsigned long field) { return 0; }
+static inline void evmcs_load(u64 phys_addr) {}
+static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
+static inline void evmcs_touch_msr_bitmap(void) {}
+#endif /* IS_ENABLED(CONFIG_HYPERV) */
+
+bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa);
+uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu);
+int nested_enable_evmcs(struct kvm_vcpu *vcpu,
+			uint16_t *vmcs_version);
+
+#endif /* __KVM_X86_VMX_EVMCS_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
new file mode 100644
index 0000000..0e7c930
--- /dev/null
+++ b/arch/x86/kvm/vmx/nested.c
@@ -0,0 +1,6071 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/frame.h>
+#include <linux/percpu.h>
+
+#include <asm/debugreg.h>
+#include <asm/mmu_context.h>
+
+#include "cpuid.h"
+#include "hyperv.h"
+#include "mmu.h"
+#include "nested.h"
+#include "trace.h"
+#include "x86.h"
+
+static bool __read_mostly enable_shadow_vmcs = 1;
+module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
+
+static bool __read_mostly nested_early_check = 0;
+module_param(nested_early_check, bool, S_IRUGO);
+
+#define CC(consistency_check)						\
+({									\
+	bool failed = (consistency_check);				\
+	if (failed)							\
+		trace_kvm_nested_vmenter_failed(#consistency_check, 0);	\
+	failed;								\
+})
+
+/*
+ * Hyper-V requires all of these, so mark them as supported even though
+ * they are just treated the same as all-context.
+ */
+#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
+	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)
+
+#define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5
+
+enum {
+	VMX_VMREAD_BITMAP,
+	VMX_VMWRITE_BITMAP,
+	VMX_BITMAP_NR
+};
+static unsigned long *vmx_bitmap[VMX_BITMAP_NR];
+
+#define vmx_vmread_bitmap                    (vmx_bitmap[VMX_VMREAD_BITMAP])
+#define vmx_vmwrite_bitmap                   (vmx_bitmap[VMX_VMWRITE_BITMAP])
+
+struct shadow_vmcs_field {
+	u16	encoding;
+	u16	offset;
+};
+static struct shadow_vmcs_field shadow_read_only_fields[] = {
+#define SHADOW_FIELD_RO(x, y) { x, offsetof(struct vmcs12, y) },
+#include "vmcs_shadow_fields.h"
+};
+static int max_shadow_read_only_fields =
+	ARRAY_SIZE(shadow_read_only_fields);
+
+static struct shadow_vmcs_field shadow_read_write_fields[] = {
+#define SHADOW_FIELD_RW(x, y) { x, offsetof(struct vmcs12, y) },
+#include "vmcs_shadow_fields.h"
+};
+static int max_shadow_read_write_fields =
+	ARRAY_SIZE(shadow_read_write_fields);
+
+static void init_vmcs_shadow_fields(void)
+{
+	int i, j;
+
+	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
+	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
+
+	for (i = j = 0; i < max_shadow_read_only_fields; i++) {
+		struct shadow_vmcs_field entry = shadow_read_only_fields[i];
+		u16 field = entry.encoding;
+
+		if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
+		    (i + 1 == max_shadow_read_only_fields ||
+		     shadow_read_only_fields[i + 1].encoding != field + 1))
+			pr_err("Missing field from shadow_read_only_field %x\n",
+			       field + 1);
+
+		clear_bit(field, vmx_vmread_bitmap);
+		if (field & 1)
+#ifdef CONFIG_X86_64
+			continue;
+#else
+			entry.offset += sizeof(u32);
+#endif
+		shadow_read_only_fields[j++] = entry;
+	}
+	max_shadow_read_only_fields = j;
+
+	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
+		struct shadow_vmcs_field entry = shadow_read_write_fields[i];
+		u16 field = entry.encoding;
+
+		if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
+		    (i + 1 == max_shadow_read_write_fields ||
+		     shadow_read_write_fields[i + 1].encoding != field + 1))
+			pr_err("Missing field from shadow_read_write_field %x\n",
+			       field + 1);
+
+		WARN_ONCE(field >= GUEST_ES_AR_BYTES &&
+			  field <= GUEST_TR_AR_BYTES,
+			  "Update vmcs12_write_any() to drop reserved bits from AR_BYTES");
+
+		/*
+		 * PML and the preemption timer can be emulated, but the
+		 * processor cannot vmwrite to fields that don't exist
+		 * on bare metal.
+		 */
+		switch (field) {
+		case GUEST_PML_INDEX:
+			if (!cpu_has_vmx_pml())
+				continue;
+			break;
+		case VMX_PREEMPTION_TIMER_VALUE:
+			if (!cpu_has_vmx_preemption_timer())
+				continue;
+			break;
+		case GUEST_INTR_STATUS:
+			if (!cpu_has_vmx_apicv())
+				continue;
+			break;
+		default:
+			break;
+		}
+
+		clear_bit(field, vmx_vmwrite_bitmap);
+		clear_bit(field, vmx_vmread_bitmap);
+		if (field & 1)
+#ifdef CONFIG_X86_64
+			continue;
+#else
+			entry.offset += sizeof(u32);
+#endif
+		shadow_read_write_fields[j++] = entry;
+	}
+	max_shadow_read_write_fields = j;
+}
+
+/*
+ * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
+ * set the success or error code of an emulated VMX instruction (as specified
+ * by Vol 2B, VMX Instruction Reference, "Conventions"), and skip the emulated
+ * instruction.
+ */
+static int nested_vmx_succeed(struct kvm_vcpu *vcpu)
+{
+	vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+			    X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
+{
+	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
+			    X86_EFLAGS_SF | X86_EFLAGS_OF))
+			| X86_EFLAGS_CF);
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
+				u32 vm_instruction_error)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * failValid writes the error number to the current VMCS, which
+	 * can't be done if there isn't a current VMCS.
+	 */
+	if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs)
+		return nested_vmx_failInvalid(vcpu);
+
+	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+			    X86_EFLAGS_SF | X86_EFLAGS_OF))
+			| X86_EFLAGS_ZF);
+	get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
+	/*
+	 * We don't need to force a shadow sync because
+	 * VM_INSTRUCTION_ERROR is not shadowed
+	 */
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
+{
+	/* TODO: not to reset guest simply here. */
+	kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+	pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator);
+}
+
+static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
+{
+	return fixed_bits_valid(control, low, high);
+}
+
+static inline u64 vmx_control_msr(u32 low, u32 high)
+{
+	return low | ((u64)high << 32);
+}
+
+static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
+{
+	secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
+	vmcs_write64(VMCS_LINK_POINTER, -1ull);
+	vmx->nested.need_vmcs12_to_shadow_sync = false;
+}
+
+static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!vmx->nested.hv_evmcs)
+		return;
+
+	kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
+	vmx->nested.hv_evmcs_vmptr = -1ull;
+	vmx->nested.hv_evmcs = NULL;
+}
+
+/*
+ * Free whatever needs to be freed from vmx->nested when L1 goes down, or
+ * just stops using VMX.
+ */
+static void free_nested(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
+		return;
+
+	kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+
+	vmx->nested.vmxon = false;
+	vmx->nested.smm.vmxon = false;
+	free_vpid(vmx->nested.vpid02);
+	vmx->nested.posted_intr_nv = -1;
+	vmx->nested.current_vmptr = -1ull;
+	if (enable_shadow_vmcs) {
+		vmx_disable_shadow_vmcs(vmx);
+		vmcs_clear(vmx->vmcs01.shadow_vmcs);
+		free_vmcs(vmx->vmcs01.shadow_vmcs);
+		vmx->vmcs01.shadow_vmcs = NULL;
+	}
+	kfree(vmx->nested.cached_vmcs12);
+	vmx->nested.cached_vmcs12 = NULL;
+	kfree(vmx->nested.cached_shadow_vmcs12);
+	vmx->nested.cached_shadow_vmcs12 = NULL;
+	/* Unpin physical memory we referred to in the vmcs02 */
+	if (vmx->nested.apic_access_page) {
+		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		vmx->nested.apic_access_page = NULL;
+	}
+	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
+	vmx->nested.pi_desc = NULL;
+
+	kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
+	nested_release_evmcs(vcpu);
+
+	free_loaded_vmcs(&vmx->nested.vmcs02);
+}
+
+static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
+				     struct loaded_vmcs *prev)
+{
+	struct vmcs_host_state *dest, *src;
+
+	if (unlikely(!vmx->guest_state_loaded))
+		return;
+
+	src = &prev->host_state;
+	dest = &vmx->loaded_vmcs->host_state;
+
+	vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
+	dest->ldt_sel = src->ldt_sel;
+#ifdef CONFIG_X86_64
+	dest->ds_sel = src->ds_sel;
+	dest->es_sel = src->es_sel;
+#endif
+}
+
+static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct loaded_vmcs *prev;
+	int cpu;
+
+	if (vmx->loaded_vmcs == vmcs)
+		return;
+
+	cpu = get_cpu();
+	prev = vmx->loaded_vmcs;
+	vmx->loaded_vmcs = vmcs;
+	vmx_vcpu_load_vmcs(vcpu, cpu);
+	vmx_sync_vmcs_host_state(vmx, prev);
+	put_cpu();
+
+	vmx_segment_cache_clear(vmx);
+}
+
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu)
+{
+	vcpu_load(vcpu);
+	vmx_leave_nested(vcpu);
+	vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01);
+	free_nested(vcpu);
+	vcpu_put(vcpu);
+}
+
+static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
+		struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 exit_reason;
+	unsigned long exit_qualification = vcpu->arch.exit_qualification;
+
+	if (vmx->nested.pml_full) {
+		exit_reason = EXIT_REASON_PML_FULL;
+		vmx->nested.pml_full = false;
+		exit_qualification &= INTR_INFO_UNBLOCK_NMI;
+	} else if (fault->error_code & PFERR_RSVD_MASK)
+		exit_reason = EXIT_REASON_EPT_MISCONFIG;
+	else
+		exit_reason = EXIT_REASON_EPT_VIOLATION;
+
+	nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification);
+	vmcs12->guest_physical_address = fault->address;
+}
+
+static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(mmu_is_nested(vcpu));
+
+	vcpu->arch.mmu = &vcpu->arch.guest_mmu;
+	kvm_init_shadow_ept_mmu(vcpu,
+			to_vmx(vcpu)->nested.msrs.ept_caps &
+			VMX_EPT_EXECUTE_ONLY_BIT,
+			nested_ept_ad_enabled(vcpu),
+			nested_ept_get_cr3(vcpu));
+	vcpu->arch.mmu->set_cr3           = vmx_set_cr3;
+	vcpu->arch.mmu->get_cr3           = nested_ept_get_cr3;
+	vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
+	vcpu->arch.mmu->get_pdptr         = kvm_pdptr_read;
+
+	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
+}
+
+static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.mmu = &vcpu->arch.root_mmu;
+	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
+}
+
+static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
+					    u16 error_code)
+{
+	bool inequality, bit;
+
+	bit = (vmcs12->exception_bitmap & (1u << PF_VECTOR)) != 0;
+	inequality =
+		(error_code & vmcs12->page_fault_error_code_mask) !=
+		 vmcs12->page_fault_error_code_match;
+	return inequality ^ bit;
+}
+
+
+/*
+ * KVM wants to inject page-faults which it got to the guest. This function
+ * checks whether in a nested guest, we need to inject them to L1 or L2.
+ */
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned int nr = vcpu->arch.exception.nr;
+	bool has_payload = vcpu->arch.exception.has_payload;
+	unsigned long payload = vcpu->arch.exception.payload;
+
+	if (nr == PF_VECTOR) {
+		if (vcpu->arch.exception.nested_apf) {
+			*exit_qual = vcpu->arch.apf.nested_apf_token;
+			return 1;
+		}
+		if (nested_vmx_is_page_fault_vmexit(vmcs12,
+						    vcpu->arch.exception.error_code)) {
+			*exit_qual = has_payload ? payload : vcpu->arch.cr2;
+			return 1;
+		}
+	} else if (vmcs12->exception_bitmap & (1u << nr)) {
+		if (nr == DB_VECTOR) {
+			if (!has_payload) {
+				payload = vcpu->arch.dr6;
+				payload &= ~(DR6_FIXED_1 | DR6_BT);
+				payload ^= DR6_RTM;
+			}
+			*exit_qual = payload;
+		} else
+			*exit_qual = 0;
+		return 1;
+	}
+
+	return 0;
+}
+
+
+static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
+		struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	WARN_ON(!is_guest_mode(vcpu));
+
+	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
+		!to_vmx(vcpu)->nested.nested_run_pending) {
+		vmcs12->vm_exit_intr_error_code = fault->error_code;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+				  INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+				  fault->address);
+	} else {
+		kvm_inject_page_fault(vcpu, fault);
+	}
+}
+
+static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
+{
+	return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
+}
+
+static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
+					       struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return 0;
+
+	if (CC(!page_address_valid(vcpu, vmcs12->io_bitmap_a)) ||
+	    CC(!page_address_valid(vcpu, vmcs12->io_bitmap_b)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu,
+						struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
+		return 0;
+
+	if (CC(!page_address_valid(vcpu, vmcs12->msr_bitmap)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
+						struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+		return 0;
+
+	if (CC(!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr)))
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Check if MSR is intercepted for L01 MSR bitmap.
+ */
+static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
+{
+	unsigned long *msr_bitmap;
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return true;
+
+	msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
+
+	if (msr <= 0x1fff) {
+		return !!test_bit(msr, msr_bitmap + 0x800 / f);
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+	}
+
+	return true;
+}
+
+/*
+ * If a msr is allowed by L0, we should check whether it is allowed by L1.
+ * The corresponding bit will be cleared unless both of L0 and L1 allow it.
+ */
+static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
+					       unsigned long *msr_bitmap_nested,
+					       u32 msr, int type)
+{
+	int f = sizeof(unsigned long);
+
+	/*
+	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+	 * have the write-low and read-high bitmap offsets the wrong way round.
+	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+	 */
+	if (msr <= 0x1fff) {
+		if (type & MSR_TYPE_R &&
+		   !test_bit(msr, msr_bitmap_l1 + 0x000 / f))
+			/* read-low */
+			__clear_bit(msr, msr_bitmap_nested + 0x000 / f);
+
+		if (type & MSR_TYPE_W &&
+		   !test_bit(msr, msr_bitmap_l1 + 0x800 / f))
+			/* write-low */
+			__clear_bit(msr, msr_bitmap_nested + 0x800 / f);
+
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		if (type & MSR_TYPE_R &&
+		   !test_bit(msr, msr_bitmap_l1 + 0x400 / f))
+			/* read-high */
+			__clear_bit(msr, msr_bitmap_nested + 0x400 / f);
+
+		if (type & MSR_TYPE_W &&
+		   !test_bit(msr, msr_bitmap_l1 + 0xc00 / f))
+			/* write-high */
+			__clear_bit(msr, msr_bitmap_nested + 0xc00 / f);
+
+	}
+}
+
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+	int msr;
+
+	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+		unsigned word = msr / BITS_PER_LONG;
+
+		msr_bitmap[word] = ~0;
+		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+	}
+}
+
+/*
+ * Merge L0's and L1's MSR bitmap, return false to indicate that
+ * we do not use the hardware.
+ */
+static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
+						 struct vmcs12 *vmcs12)
+{
+	int msr;
+	unsigned long *msr_bitmap_l1;
+	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
+	struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map;
+
+	/* Nothing to do if the MSR bitmap is not in use.  */
+	if (!cpu_has_vmx_msr_bitmap() ||
+	    !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
+		return false;
+
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
+		return false;
+
+	msr_bitmap_l1 = (unsigned long *)map->hva;
+
+	/*
+	 * To keep the control flow simple, pay eight 8-byte writes (sixteen
+	 * 4-byte writes on 32-bit systems) up front to enable intercepts for
+	 * the x2APIC MSR range and selectively disable them below.
+	 */
+	enable_x2apic_msr_intercepts(msr_bitmap_l0);
+
+	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
+		if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+			/*
+			 * L0 need not intercept reads for MSRs between 0x800
+			 * and 0x8ff, it just lets the processor take the value
+			 * from the virtual-APIC page; take those 256 bits
+			 * directly from the L1 bitmap.
+			 */
+			for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+				unsigned word = msr / BITS_PER_LONG;
+
+				msr_bitmap_l0[word] = msr_bitmap_l1[word];
+			}
+		}
+
+		nested_vmx_disable_intercept_for_msr(
+			msr_bitmap_l1, msr_bitmap_l0,
+			X2APIC_MSR(APIC_TASKPRI),
+			MSR_TYPE_R | MSR_TYPE_W);
+
+		if (nested_cpu_has_vid(vmcs12)) {
+			nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
+				X2APIC_MSR(APIC_EOI),
+				MSR_TYPE_W);
+			nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
+				X2APIC_MSR(APIC_SELF_IPI),
+				MSR_TYPE_W);
+		}
+	}
+
+	/* KVM unconditionally exposes the FS/GS base MSRs to L1. */
+	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
+					     MSR_FS_BASE, MSR_TYPE_RW);
+
+	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
+					     MSR_GS_BASE, MSR_TYPE_RW);
+
+	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
+					     MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+
+	/*
+	 * Checking the L0->L1 bitmap is trying to verify two things:
+	 *
+	 * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
+	 *    ensures that we do not accidentally generate an L02 MSR bitmap
+	 *    from the L12 MSR bitmap that is too permissive.
+	 * 2. That L1 or L2s have actually used the MSR. This avoids
+	 *    unnecessarily merging of the bitmap if the MSR is unused. This
+	 *    works properly because we only update the L01 MSR bitmap lazily.
+	 *    So even if L0 should pass L1 these MSRs, the L01 bitmap is only
+	 *    updated to reflect this when L1 (or its L2s) actually write to
+	 *    the MSR.
+	 */
+	if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL))
+		nested_vmx_disable_intercept_for_msr(
+					msr_bitmap_l1, msr_bitmap_l0,
+					MSR_IA32_SPEC_CTRL,
+					MSR_TYPE_R | MSR_TYPE_W);
+
+	if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD))
+		nested_vmx_disable_intercept_for_msr(
+					msr_bitmap_l1, msr_bitmap_l0,
+					MSR_IA32_PRED_CMD,
+					MSR_TYPE_W);
+
+	kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false);
+
+	return true;
+}
+
+static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	struct kvm_host_map map;
+	struct vmcs12 *shadow;
+
+	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
+	    vmcs12->vmcs_link_pointer == -1ull)
+		return;
+
+	shadow = get_shadow_vmcs12(vcpu);
+
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))
+		return;
+
+	memcpy(shadow, map.hva, VMCS12_SIZE);
+	kvm_vcpu_unmap(vcpu, &map, false);
+}
+
+static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
+					      struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
+	    vmcs12->vmcs_link_pointer == -1ull)
+		return;
+
+	kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer,
+			get_shadow_vmcs12(vcpu), VMCS12_SIZE);
+}
+
+/*
+ * In nested virtualization, check if L1 has set
+ * VM_EXIT_ACK_INTR_ON_EXIT
+ */
+static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu)
+{
+	return get_vmcs12(vcpu)->vm_exit_controls &
+		VM_EXIT_ACK_INTR_ON_EXIT;
+}
+
+static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
+{
+	return nested_cpu_has_nmi_exiting(get_vmcs12(vcpu));
+}
+
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+	    CC(!page_address_valid(vcpu, vmcs12->apic_access_addr)))
+		return -EINVAL;
+	else
+		return 0;
+}
+
+static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
+					   struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+	    !nested_cpu_has_apic_reg_virt(vmcs12) &&
+	    !nested_cpu_has_vid(vmcs12) &&
+	    !nested_cpu_has_posted_intr(vmcs12))
+		return 0;
+
+	/*
+	 * If virtualize x2apic mode is enabled,
+	 * virtualize apic access must be disabled.
+	 */
+	if (CC(nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+	       nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)))
+		return -EINVAL;
+
+	/*
+	 * If virtual interrupt delivery is enabled,
+	 * we must exit on external interrupts.
+	 */
+	if (CC(nested_cpu_has_vid(vmcs12) && !nested_exit_on_intr(vcpu)))
+		return -EINVAL;
+
+	/*
+	 * bits 15:8 should be zero in posted_intr_nv,
+	 * the descriptor address has been already checked
+	 * in nested_get_vmcs12_pages.
+	 *
+	 * bits 5:0 of posted_intr_desc_addr should be zero.
+	 */
+	if (nested_cpu_has_posted_intr(vmcs12) &&
+	   (CC(!nested_cpu_has_vid(vmcs12)) ||
+	    CC(!nested_exit_intr_ack_set(vcpu)) ||
+	    CC((vmcs12->posted_intr_nv & 0xff00)) ||
+	    CC((vmcs12->posted_intr_desc_addr & 0x3f)) ||
+	    CC((vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu)))))
+		return -EINVAL;
+
+	/* tpr shadow is needed by all apicv features. */
+	if (CC(!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
+				       u32 count, u64 addr)
+{
+	int maxphyaddr;
+
+	if (count == 0)
+		return 0;
+	maxphyaddr = cpuid_maxphyaddr(vcpu);
+	if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr ||
+	    (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_exit_msr_switch_controls(struct kvm_vcpu *vcpu,
+						     struct vmcs12 *vmcs12)
+{
+	if (CC(nested_vmx_check_msr_switch(vcpu,
+					   vmcs12->vm_exit_msr_load_count,
+					   vmcs12->vm_exit_msr_load_addr)) ||
+	    CC(nested_vmx_check_msr_switch(vcpu,
+					   vmcs12->vm_exit_msr_store_count,
+					   vmcs12->vm_exit_msr_store_addr)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_entry_msr_switch_controls(struct kvm_vcpu *vcpu,
+                                                      struct vmcs12 *vmcs12)
+{
+	if (CC(nested_vmx_check_msr_switch(vcpu,
+					   vmcs12->vm_entry_msr_load_count,
+					   vmcs12->vm_entry_msr_load_addr)))
+                return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
+					 struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has_pml(vmcs12))
+		return 0;
+
+	if (CC(!nested_cpu_has_ept(vmcs12)) ||
+	    CC(!page_address_valid(vcpu, vmcs12->pml_address)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu,
+							struct vmcs12 *vmcs12)
+{
+	if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) &&
+	       !nested_cpu_has_ept(vmcs12)))
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_check_mode_based_ept_exec_controls(struct kvm_vcpu *vcpu,
+							 struct vmcs12 *vmcs12)
+{
+	if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) &&
+	       !nested_cpu_has_ept(vmcs12)))
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu,
+						 struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has_shadow_vmcs(vmcs12))
+		return 0;
+
+	if (CC(!page_address_valid(vcpu, vmcs12->vmread_bitmap)) ||
+	    CC(!page_address_valid(vcpu, vmcs12->vmwrite_bitmap)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
+				       struct vmx_msr_entry *e)
+{
+	/* x2APIC MSR accesses are not allowed */
+	if (CC(vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8))
+		return -EINVAL;
+	if (CC(e->index == MSR_IA32_UCODE_WRITE) || /* SDM Table 35-2 */
+	    CC(e->index == MSR_IA32_UCODE_REV))
+		return -EINVAL;
+	if (CC(e->reserved != 0))
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu,
+				     struct vmx_msr_entry *e)
+{
+	if (CC(e->index == MSR_FS_BASE) ||
+	    CC(e->index == MSR_GS_BASE) ||
+	    CC(e->index == MSR_IA32_SMM_MONITOR_CTL) || /* SMM is not supported */
+	    nested_vmx_msr_check_common(vcpu, e))
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
+				      struct vmx_msr_entry *e)
+{
+	if (CC(e->index == MSR_IA32_SMBASE) || /* SMM is not supported */
+	    nested_vmx_msr_check_common(vcpu, e))
+		return -EINVAL;
+	return 0;
+}
+
+static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
+				       vmx->nested.msrs.misc_high);
+
+	return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
+}
+
+/*
+ * Load guest's/host's msr at nested entry/exit.
+ * return 0 for success, entry index for failure.
+ *
+ * One of the failure modes for MSR load/store is when a list exceeds the
+ * virtual hardware's capacity. To maintain compatibility with hardware inasmuch
+ * as possible, process all valid entries before failing rather than precheck
+ * for a capacity violation.
+ */
+static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
+{
+	u32 i;
+	struct vmx_msr_entry e;
+	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
+
+	for (i = 0; i < count; i++) {
+		if (unlikely(i >= max_msr_list_size))
+			goto fail;
+
+		if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
+					&e, sizeof(e))) {
+			pr_debug_ratelimited(
+				"%s cannot read MSR entry (%u, 0x%08llx)\n",
+				__func__, i, gpa + i * sizeof(e));
+			goto fail;
+		}
+		if (nested_vmx_load_msr_check(vcpu, &e)) {
+			pr_debug_ratelimited(
+				"%s check failed (%u, 0x%x, 0x%x)\n",
+				__func__, i, e.index, e.reserved);
+			goto fail;
+		}
+		if (kvm_set_msr(vcpu, e.index, e.value)) {
+			pr_debug_ratelimited(
+				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
+				__func__, i, e.index, e.value);
+			goto fail;
+		}
+	}
+	return 0;
+fail:
+	return i + 1;
+}
+
+static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
+{
+	u64 data;
+	u32 i;
+	struct vmx_msr_entry e;
+	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
+
+	for (i = 0; i < count; i++) {
+		if (unlikely(i >= max_msr_list_size))
+			return -EINVAL;
+
+		if (kvm_vcpu_read_guest(vcpu,
+					gpa + i * sizeof(e),
+					&e, 2 * sizeof(u32))) {
+			pr_debug_ratelimited(
+				"%s cannot read MSR entry (%u, 0x%08llx)\n",
+				__func__, i, gpa + i * sizeof(e));
+			return -EINVAL;
+		}
+		if (nested_vmx_store_msr_check(vcpu, &e)) {
+			pr_debug_ratelimited(
+				"%s check failed (%u, 0x%x, 0x%x)\n",
+				__func__, i, e.index, e.reserved);
+			return -EINVAL;
+		}
+		if (kvm_get_msr(vcpu, e.index, &data)) {
+			pr_debug_ratelimited(
+				"%s cannot read MSR (%u, 0x%x)\n",
+				__func__, i, e.index);
+			return -EINVAL;
+		}
+		if (kvm_vcpu_write_guest(vcpu,
+					 gpa + i * sizeof(e) +
+					     offsetof(struct vmx_msr_entry, value),
+					 &data, sizeof(data))) {
+			pr_debug_ratelimited(
+				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
+				__func__, i, e.index, data);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	unsigned long invalid_mask;
+
+	invalid_mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
+	return (val & invalid_mask) == 0;
+}
+
+/*
+ * Load guest's/host's cr3 at nested entry/exit. nested_ept is true if we are
+ * emulating VM entry into a guest with EPT enabled.
+ * Returns 0 on success, 1 on failure. Invalid state exit qualification code
+ * is assigned to entry_failure_code on failure.
+ */
+static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
+			       u32 *entry_failure_code)
+{
+	if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) {
+		if (CC(!nested_cr3_valid(vcpu, cr3))) {
+			*entry_failure_code = ENTRY_FAIL_DEFAULT;
+			return -EINVAL;
+		}
+
+		/*
+		 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
+		 * must not be dereferenced.
+		 */
+		if (is_pae_paging(vcpu) && !nested_ept) {
+			if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) {
+				*entry_failure_code = ENTRY_FAIL_PDPTE;
+				return -EINVAL;
+			}
+		}
+	}
+
+	if (!nested_ept)
+		kvm_mmu_new_cr3(vcpu, cr3, false);
+
+	vcpu->arch.cr3 = cr3;
+	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+	kvm_init_mmu(vcpu, false);
+
+	return 0;
+}
+
+/*
+ * Returns if KVM is able to config CPU to tag TLB entries
+ * populated by L2 differently than TLB entries populated
+ * by L1.
+ *
+ * If L1 uses EPT, then TLB entries are tagged with different EPTP.
+ *
+ * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
+ * with different VPID (L1 entries are tagged with vmx->vpid
+ * while L2 entries are tagged with vmx->nested.vpid02).
+ */
+static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	return nested_cpu_has_ept(vmcs12) ||
+	       (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
+}
+
+static u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid;
+}
+
+static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
+{
+	superset &= mask;
+	subset &= mask;
+
+	return (superset | subset) == superset;
+}
+
+static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
+{
+	const u64 feature_and_reserved =
+		/* feature (except bit 48; see below) */
+		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
+		/* reserved */
+		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
+	u64 vmx_basic = vmx->nested.msrs.basic;
+
+	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
+		return -EINVAL;
+
+	/*
+	 * KVM does not emulate a version of VMX that constrains physical
+	 * addresses of VMX structures (e.g. VMCS) to 32-bits.
+	 */
+	if (data & BIT_ULL(48))
+		return -EINVAL;
+
+	if (vmx_basic_vmcs_revision_id(vmx_basic) !=
+	    vmx_basic_vmcs_revision_id(data))
+		return -EINVAL;
+
+	if (vmx_basic_vmcs_size(vmx_basic) > vmx_basic_vmcs_size(data))
+		return -EINVAL;
+
+	vmx->nested.msrs.basic = data;
+	return 0;
+}
+
+static int
+vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	u64 supported;
+	u32 *lowp, *highp;
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
+		lowp = &vmx->nested.msrs.pinbased_ctls_low;
+		highp = &vmx->nested.msrs.pinbased_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+		lowp = &vmx->nested.msrs.procbased_ctls_low;
+		highp = &vmx->nested.msrs.procbased_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+		lowp = &vmx->nested.msrs.exit_ctls_low;
+		highp = &vmx->nested.msrs.exit_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+		lowp = &vmx->nested.msrs.entry_ctls_low;
+		highp = &vmx->nested.msrs.entry_ctls_high;
+		break;
+	case MSR_IA32_VMX_PROCBASED_CTLS2:
+		lowp = &vmx->nested.msrs.secondary_ctls_low;
+		highp = &vmx->nested.msrs.secondary_ctls_high;
+		break;
+	default:
+		BUG();
+	}
+
+	supported = vmx_control_msr(*lowp, *highp);
+
+	/* Check must-be-1 bits are still 1. */
+	if (!is_bitwise_subset(data, supported, GENMASK_ULL(31, 0)))
+		return -EINVAL;
+
+	/* Check must-be-0 bits are still 0. */
+	if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32)))
+		return -EINVAL;
+
+	*lowp = data;
+	*highp = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
+{
+	const u64 feature_and_reserved_bits =
+		/* feature */
+		BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) |
+		BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
+		/* reserved */
+		GENMASK_ULL(13, 9) | BIT_ULL(31);
+	u64 vmx_misc;
+
+	vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
+				   vmx->nested.msrs.misc_high);
+
+	if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
+		return -EINVAL;
+
+	if ((vmx->nested.msrs.pinbased_ctls_high &
+	     PIN_BASED_VMX_PREEMPTION_TIMER) &&
+	    vmx_misc_preemption_timer_rate(data) !=
+	    vmx_misc_preemption_timer_rate(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_cr3_count(data) > vmx_misc_cr3_count(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_max_msr(data) > vmx_misc_max_msr(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_mseg_revid(data) != vmx_misc_mseg_revid(vmx_misc))
+		return -EINVAL;
+
+	vmx->nested.msrs.misc_low = data;
+	vmx->nested.msrs.misc_high = data >> 32;
+
+	return 0;
+}
+
+static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data)
+{
+	u64 vmx_ept_vpid_cap;
+
+	vmx_ept_vpid_cap = vmx_control_msr(vmx->nested.msrs.ept_caps,
+					   vmx->nested.msrs.vpid_caps);
+
+	/* Every bit is either reserved or a feature bit. */
+	if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL))
+		return -EINVAL;
+
+	vmx->nested.msrs.ept_caps = data;
+	vmx->nested.msrs.vpid_caps = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	u64 *msr;
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_CR0_FIXED0:
+		msr = &vmx->nested.msrs.cr0_fixed0;
+		break;
+	case MSR_IA32_VMX_CR4_FIXED0:
+		msr = &vmx->nested.msrs.cr4_fixed0;
+		break;
+	default:
+		BUG();
+	}
+
+	/*
+	 * 1 bits (which indicates bits which "must-be-1" during VMX operation)
+	 * must be 1 in the restored value.
+	 */
+	if (!is_bitwise_subset(data, *msr, -1ULL))
+		return -EINVAL;
+
+	*msr = data;
+	return 0;
+}
+
+/*
+ * Called when userspace is restoring VMX MSRs.
+ *
+ * Returns 0 on success, non-0 otherwise.
+ */
+int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * Don't allow changes to the VMX capability MSRs while the vCPU
+	 * is in VMX operation.
+	 */
+	if (vmx->nested.vmxon)
+		return -EBUSY;
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_BASIC:
+		return vmx_restore_vmx_basic(vmx, data);
+	case MSR_IA32_VMX_PINBASED_CTLS:
+	case MSR_IA32_VMX_PROCBASED_CTLS:
+	case MSR_IA32_VMX_EXIT_CTLS:
+	case MSR_IA32_VMX_ENTRY_CTLS:
+		/*
+		 * The "non-true" VMX capability MSRs are generated from the
+		 * "true" MSRs, so we do not support restoring them directly.
+		 *
+		 * If userspace wants to emulate VMX_BASIC[55]=0, userspace
+		 * should restore the "true" MSRs with the must-be-1 bits
+		 * set according to the SDM Vol 3. A.2 "RESERVED CONTROLS AND
+		 * DEFAULT SETTINGS".
+		 */
+		return -EINVAL;
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
+	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+	case MSR_IA32_VMX_PROCBASED_CTLS2:
+		return vmx_restore_control_msr(vmx, msr_index, data);
+	case MSR_IA32_VMX_MISC:
+		return vmx_restore_vmx_misc(vmx, data);
+	case MSR_IA32_VMX_CR0_FIXED0:
+	case MSR_IA32_VMX_CR4_FIXED0:
+		return vmx_restore_fixed0_msr(vmx, msr_index, data);
+	case MSR_IA32_VMX_CR0_FIXED1:
+	case MSR_IA32_VMX_CR4_FIXED1:
+		/*
+		 * These MSRs are generated based on the vCPU's CPUID, so we
+		 * do not support restoring them directly.
+		 */
+		return -EINVAL;
+	case MSR_IA32_VMX_EPT_VPID_CAP:
+		return vmx_restore_vmx_ept_vpid_cap(vmx, data);
+	case MSR_IA32_VMX_VMCS_ENUM:
+		vmx->nested.msrs.vmcs_enum = data;
+		return 0;
+	case MSR_IA32_VMX_VMFUNC:
+		if (data & ~vmx->nested.msrs.vmfunc_controls)
+			return -EINVAL;
+		vmx->nested.msrs.vmfunc_controls = data;
+		return 0;
+	default:
+		/*
+		 * The rest of the VMX capability MSRs do not support restore.
+		 */
+		return -EINVAL;
+	}
+}
+
+/* Returns 0 on success, non-0 otherwise. */
+int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata)
+{
+	switch (msr_index) {
+	case MSR_IA32_VMX_BASIC:
+		*pdata = msrs->basic;
+		break;
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
+	case MSR_IA32_VMX_PINBASED_CTLS:
+		*pdata = vmx_control_msr(
+			msrs->pinbased_ctls_low,
+			msrs->pinbased_ctls_high);
+		if (msr_index == MSR_IA32_VMX_PINBASED_CTLS)
+			*pdata |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
+		break;
+	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+	case MSR_IA32_VMX_PROCBASED_CTLS:
+		*pdata = vmx_control_msr(
+			msrs->procbased_ctls_low,
+			msrs->procbased_ctls_high);
+		if (msr_index == MSR_IA32_VMX_PROCBASED_CTLS)
+			*pdata |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
+		break;
+	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+	case MSR_IA32_VMX_EXIT_CTLS:
+		*pdata = vmx_control_msr(
+			msrs->exit_ctls_low,
+			msrs->exit_ctls_high);
+		if (msr_index == MSR_IA32_VMX_EXIT_CTLS)
+			*pdata |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
+		break;
+	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+	case MSR_IA32_VMX_ENTRY_CTLS:
+		*pdata = vmx_control_msr(
+			msrs->entry_ctls_low,
+			msrs->entry_ctls_high);
+		if (msr_index == MSR_IA32_VMX_ENTRY_CTLS)
+			*pdata |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
+		break;
+	case MSR_IA32_VMX_MISC:
+		*pdata = vmx_control_msr(
+			msrs->misc_low,
+			msrs->misc_high);
+		break;
+	case MSR_IA32_VMX_CR0_FIXED0:
+		*pdata = msrs->cr0_fixed0;
+		break;
+	case MSR_IA32_VMX_CR0_FIXED1:
+		*pdata = msrs->cr0_fixed1;
+		break;
+	case MSR_IA32_VMX_CR4_FIXED0:
+		*pdata = msrs->cr4_fixed0;
+		break;
+	case MSR_IA32_VMX_CR4_FIXED1:
+		*pdata = msrs->cr4_fixed1;
+		break;
+	case MSR_IA32_VMX_VMCS_ENUM:
+		*pdata = msrs->vmcs_enum;
+		break;
+	case MSR_IA32_VMX_PROCBASED_CTLS2:
+		*pdata = vmx_control_msr(
+			msrs->secondary_ctls_low,
+			msrs->secondary_ctls_high);
+		break;
+	case MSR_IA32_VMX_EPT_VPID_CAP:
+		*pdata = msrs->ept_caps |
+			((u64)msrs->vpid_caps << 32);
+		break;
+	case MSR_IA32_VMX_VMFUNC:
+		*pdata = msrs->vmfunc_controls;
+		break;
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Copy the writable VMCS shadow fields back to the VMCS12, in case they have
+ * been modified by the L1 guest.  Note, "writable" in this context means
+ * "writable by the guest", i.e. tagged SHADOW_FIELD_RW; the set of
+ * fields tagged SHADOW_FIELD_RO may or may not align with the "read-only"
+ * VM-exit information fields (which are actually writable if the vCPU is
+ * configured to support "VMWRITE to any supported field in the VMCS").
+ */
+static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
+{
+	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
+	struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu);
+	struct shadow_vmcs_field field;
+	unsigned long val;
+	int i;
+
+	if (WARN_ON(!shadow_vmcs))
+		return;
+
+	preempt_disable();
+
+	vmcs_load(shadow_vmcs);
+
+	for (i = 0; i < max_shadow_read_write_fields; i++) {
+		field = shadow_read_write_fields[i];
+		val = __vmcs_readl(field.encoding);
+		vmcs12_write_any(vmcs12, field.encoding, field.offset, val);
+	}
+
+	vmcs_clear(shadow_vmcs);
+	vmcs_load(vmx->loaded_vmcs->vmcs);
+
+	preempt_enable();
+}
+
+static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
+{
+	const struct shadow_vmcs_field *fields[] = {
+		shadow_read_write_fields,
+		shadow_read_only_fields
+	};
+	const int max_fields[] = {
+		max_shadow_read_write_fields,
+		max_shadow_read_only_fields
+	};
+	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
+	struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu);
+	struct shadow_vmcs_field field;
+	unsigned long val;
+	int i, q;
+
+	if (WARN_ON(!shadow_vmcs))
+		return;
+
+	vmcs_load(shadow_vmcs);
+
+	for (q = 0; q < ARRAY_SIZE(fields); q++) {
+		for (i = 0; i < max_fields[q]; i++) {
+			field = fields[q][i];
+			val = vmcs12_read_any(vmcs12, field.encoding,
+					      field.offset);
+			__vmcs_writel(field.encoding, val);
+		}
+	}
+
+	vmcs_clear(shadow_vmcs);
+	vmcs_load(vmx->loaded_vmcs->vmcs);
+}
+
+static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
+{
+	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
+	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+
+	/* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */
+	vmcs12->tpr_threshold = evmcs->tpr_threshold;
+	vmcs12->guest_rip = evmcs->guest_rip;
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) {
+		vmcs12->guest_rsp = evmcs->guest_rsp;
+		vmcs12->guest_rflags = evmcs->guest_rflags;
+		vmcs12->guest_interruptibility_info =
+			evmcs->guest_interruptibility_info;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
+		vmcs12->cpu_based_vm_exec_control =
+			evmcs->cpu_based_vm_exec_control;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN))) {
+		vmcs12->exception_bitmap = evmcs->exception_bitmap;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) {
+		vmcs12->vm_entry_controls = evmcs->vm_entry_controls;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) {
+		vmcs12->vm_entry_intr_info_field =
+			evmcs->vm_entry_intr_info_field;
+		vmcs12->vm_entry_exception_error_code =
+			evmcs->vm_entry_exception_error_code;
+		vmcs12->vm_entry_instruction_len =
+			evmcs->vm_entry_instruction_len;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
+		vmcs12->host_ia32_pat = evmcs->host_ia32_pat;
+		vmcs12->host_ia32_efer = evmcs->host_ia32_efer;
+		vmcs12->host_cr0 = evmcs->host_cr0;
+		vmcs12->host_cr3 = evmcs->host_cr3;
+		vmcs12->host_cr4 = evmcs->host_cr4;
+		vmcs12->host_ia32_sysenter_esp = evmcs->host_ia32_sysenter_esp;
+		vmcs12->host_ia32_sysenter_eip = evmcs->host_ia32_sysenter_eip;
+		vmcs12->host_rip = evmcs->host_rip;
+		vmcs12->host_ia32_sysenter_cs = evmcs->host_ia32_sysenter_cs;
+		vmcs12->host_es_selector = evmcs->host_es_selector;
+		vmcs12->host_cs_selector = evmcs->host_cs_selector;
+		vmcs12->host_ss_selector = evmcs->host_ss_selector;
+		vmcs12->host_ds_selector = evmcs->host_ds_selector;
+		vmcs12->host_fs_selector = evmcs->host_fs_selector;
+		vmcs12->host_gs_selector = evmcs->host_gs_selector;
+		vmcs12->host_tr_selector = evmcs->host_tr_selector;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1))) {
+		vmcs12->pin_based_vm_exec_control =
+			evmcs->pin_based_vm_exec_control;
+		vmcs12->vm_exit_controls = evmcs->vm_exit_controls;
+		vmcs12->secondary_vm_exec_control =
+			evmcs->secondary_vm_exec_control;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) {
+		vmcs12->io_bitmap_a = evmcs->io_bitmap_a;
+		vmcs12->io_bitmap_b = evmcs->io_bitmap_b;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) {
+		vmcs12->msr_bitmap = evmcs->msr_bitmap;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) {
+		vmcs12->guest_es_base = evmcs->guest_es_base;
+		vmcs12->guest_cs_base = evmcs->guest_cs_base;
+		vmcs12->guest_ss_base = evmcs->guest_ss_base;
+		vmcs12->guest_ds_base = evmcs->guest_ds_base;
+		vmcs12->guest_fs_base = evmcs->guest_fs_base;
+		vmcs12->guest_gs_base = evmcs->guest_gs_base;
+		vmcs12->guest_ldtr_base = evmcs->guest_ldtr_base;
+		vmcs12->guest_tr_base = evmcs->guest_tr_base;
+		vmcs12->guest_gdtr_base = evmcs->guest_gdtr_base;
+		vmcs12->guest_idtr_base = evmcs->guest_idtr_base;
+		vmcs12->guest_es_limit = evmcs->guest_es_limit;
+		vmcs12->guest_cs_limit = evmcs->guest_cs_limit;
+		vmcs12->guest_ss_limit = evmcs->guest_ss_limit;
+		vmcs12->guest_ds_limit = evmcs->guest_ds_limit;
+		vmcs12->guest_fs_limit = evmcs->guest_fs_limit;
+		vmcs12->guest_gs_limit = evmcs->guest_gs_limit;
+		vmcs12->guest_ldtr_limit = evmcs->guest_ldtr_limit;
+		vmcs12->guest_tr_limit = evmcs->guest_tr_limit;
+		vmcs12->guest_gdtr_limit = evmcs->guest_gdtr_limit;
+		vmcs12->guest_idtr_limit = evmcs->guest_idtr_limit;
+		vmcs12->guest_es_ar_bytes = evmcs->guest_es_ar_bytes;
+		vmcs12->guest_cs_ar_bytes = evmcs->guest_cs_ar_bytes;
+		vmcs12->guest_ss_ar_bytes = evmcs->guest_ss_ar_bytes;
+		vmcs12->guest_ds_ar_bytes = evmcs->guest_ds_ar_bytes;
+		vmcs12->guest_fs_ar_bytes = evmcs->guest_fs_ar_bytes;
+		vmcs12->guest_gs_ar_bytes = evmcs->guest_gs_ar_bytes;
+		vmcs12->guest_ldtr_ar_bytes = evmcs->guest_ldtr_ar_bytes;
+		vmcs12->guest_tr_ar_bytes = evmcs->guest_tr_ar_bytes;
+		vmcs12->guest_es_selector = evmcs->guest_es_selector;
+		vmcs12->guest_cs_selector = evmcs->guest_cs_selector;
+		vmcs12->guest_ss_selector = evmcs->guest_ss_selector;
+		vmcs12->guest_ds_selector = evmcs->guest_ds_selector;
+		vmcs12->guest_fs_selector = evmcs->guest_fs_selector;
+		vmcs12->guest_gs_selector = evmcs->guest_gs_selector;
+		vmcs12->guest_ldtr_selector = evmcs->guest_ldtr_selector;
+		vmcs12->guest_tr_selector = evmcs->guest_tr_selector;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) {
+		vmcs12->tsc_offset = evmcs->tsc_offset;
+		vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr;
+		vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) {
+		vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask;
+		vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask;
+		vmcs12->cr0_read_shadow = evmcs->cr0_read_shadow;
+		vmcs12->cr4_read_shadow = evmcs->cr4_read_shadow;
+		vmcs12->guest_cr0 = evmcs->guest_cr0;
+		vmcs12->guest_cr3 = evmcs->guest_cr3;
+		vmcs12->guest_cr4 = evmcs->guest_cr4;
+		vmcs12->guest_dr7 = evmcs->guest_dr7;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) {
+		vmcs12->host_fs_base = evmcs->host_fs_base;
+		vmcs12->host_gs_base = evmcs->host_gs_base;
+		vmcs12->host_tr_base = evmcs->host_tr_base;
+		vmcs12->host_gdtr_base = evmcs->host_gdtr_base;
+		vmcs12->host_idtr_base = evmcs->host_idtr_base;
+		vmcs12->host_rsp = evmcs->host_rsp;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) {
+		vmcs12->ept_pointer = evmcs->ept_pointer;
+		vmcs12->virtual_processor_id = evmcs->virtual_processor_id;
+	}
+
+	if (unlikely(!(evmcs->hv_clean_fields &
+		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) {
+		vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer;
+		vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl;
+		vmcs12->guest_ia32_pat = evmcs->guest_ia32_pat;
+		vmcs12->guest_ia32_efer = evmcs->guest_ia32_efer;
+		vmcs12->guest_pdptr0 = evmcs->guest_pdptr0;
+		vmcs12->guest_pdptr1 = evmcs->guest_pdptr1;
+		vmcs12->guest_pdptr2 = evmcs->guest_pdptr2;
+		vmcs12->guest_pdptr3 = evmcs->guest_pdptr3;
+		vmcs12->guest_pending_dbg_exceptions =
+			evmcs->guest_pending_dbg_exceptions;
+		vmcs12->guest_sysenter_esp = evmcs->guest_sysenter_esp;
+		vmcs12->guest_sysenter_eip = evmcs->guest_sysenter_eip;
+		vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs;
+		vmcs12->guest_activity_state = evmcs->guest_activity_state;
+		vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs;
+	}
+
+	/*
+	 * Not used?
+	 * vmcs12->vm_exit_msr_store_addr = evmcs->vm_exit_msr_store_addr;
+	 * vmcs12->vm_exit_msr_load_addr = evmcs->vm_exit_msr_load_addr;
+	 * vmcs12->vm_entry_msr_load_addr = evmcs->vm_entry_msr_load_addr;
+	 * vmcs12->cr3_target_value0 = evmcs->cr3_target_value0;
+	 * vmcs12->cr3_target_value1 = evmcs->cr3_target_value1;
+	 * vmcs12->cr3_target_value2 = evmcs->cr3_target_value2;
+	 * vmcs12->cr3_target_value3 = evmcs->cr3_target_value3;
+	 * vmcs12->page_fault_error_code_mask =
+	 *		evmcs->page_fault_error_code_mask;
+	 * vmcs12->page_fault_error_code_match =
+	 *		evmcs->page_fault_error_code_match;
+	 * vmcs12->cr3_target_count = evmcs->cr3_target_count;
+	 * vmcs12->vm_exit_msr_store_count = evmcs->vm_exit_msr_store_count;
+	 * vmcs12->vm_exit_msr_load_count = evmcs->vm_exit_msr_load_count;
+	 * vmcs12->vm_entry_msr_load_count = evmcs->vm_entry_msr_load_count;
+	 */
+
+	/*
+	 * Read only fields:
+	 * vmcs12->guest_physical_address = evmcs->guest_physical_address;
+	 * vmcs12->vm_instruction_error = evmcs->vm_instruction_error;
+	 * vmcs12->vm_exit_reason = evmcs->vm_exit_reason;
+	 * vmcs12->vm_exit_intr_info = evmcs->vm_exit_intr_info;
+	 * vmcs12->vm_exit_intr_error_code = evmcs->vm_exit_intr_error_code;
+	 * vmcs12->idt_vectoring_info_field = evmcs->idt_vectoring_info_field;
+	 * vmcs12->idt_vectoring_error_code = evmcs->idt_vectoring_error_code;
+	 * vmcs12->vm_exit_instruction_len = evmcs->vm_exit_instruction_len;
+	 * vmcs12->vmx_instruction_info = evmcs->vmx_instruction_info;
+	 * vmcs12->exit_qualification = evmcs->exit_qualification;
+	 * vmcs12->guest_linear_address = evmcs->guest_linear_address;
+	 *
+	 * Not present in struct vmcs12:
+	 * vmcs12->exit_io_instruction_ecx = evmcs->exit_io_instruction_ecx;
+	 * vmcs12->exit_io_instruction_esi = evmcs->exit_io_instruction_esi;
+	 * vmcs12->exit_io_instruction_edi = evmcs->exit_io_instruction_edi;
+	 * vmcs12->exit_io_instruction_eip = evmcs->exit_io_instruction_eip;
+	 */
+
+	return 0;
+}
+
+static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
+{
+	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
+	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+
+	/*
+	 * Should not be changed by KVM:
+	 *
+	 * evmcs->host_es_selector = vmcs12->host_es_selector;
+	 * evmcs->host_cs_selector = vmcs12->host_cs_selector;
+	 * evmcs->host_ss_selector = vmcs12->host_ss_selector;
+	 * evmcs->host_ds_selector = vmcs12->host_ds_selector;
+	 * evmcs->host_fs_selector = vmcs12->host_fs_selector;
+	 * evmcs->host_gs_selector = vmcs12->host_gs_selector;
+	 * evmcs->host_tr_selector = vmcs12->host_tr_selector;
+	 * evmcs->host_ia32_pat = vmcs12->host_ia32_pat;
+	 * evmcs->host_ia32_efer = vmcs12->host_ia32_efer;
+	 * evmcs->host_cr0 = vmcs12->host_cr0;
+	 * evmcs->host_cr3 = vmcs12->host_cr3;
+	 * evmcs->host_cr4 = vmcs12->host_cr4;
+	 * evmcs->host_ia32_sysenter_esp = vmcs12->host_ia32_sysenter_esp;
+	 * evmcs->host_ia32_sysenter_eip = vmcs12->host_ia32_sysenter_eip;
+	 * evmcs->host_rip = vmcs12->host_rip;
+	 * evmcs->host_ia32_sysenter_cs = vmcs12->host_ia32_sysenter_cs;
+	 * evmcs->host_fs_base = vmcs12->host_fs_base;
+	 * evmcs->host_gs_base = vmcs12->host_gs_base;
+	 * evmcs->host_tr_base = vmcs12->host_tr_base;
+	 * evmcs->host_gdtr_base = vmcs12->host_gdtr_base;
+	 * evmcs->host_idtr_base = vmcs12->host_idtr_base;
+	 * evmcs->host_rsp = vmcs12->host_rsp;
+	 * sync_vmcs02_to_vmcs12() doesn't read these:
+	 * evmcs->io_bitmap_a = vmcs12->io_bitmap_a;
+	 * evmcs->io_bitmap_b = vmcs12->io_bitmap_b;
+	 * evmcs->msr_bitmap = vmcs12->msr_bitmap;
+	 * evmcs->ept_pointer = vmcs12->ept_pointer;
+	 * evmcs->xss_exit_bitmap = vmcs12->xss_exit_bitmap;
+	 * evmcs->vm_exit_msr_store_addr = vmcs12->vm_exit_msr_store_addr;
+	 * evmcs->vm_exit_msr_load_addr = vmcs12->vm_exit_msr_load_addr;
+	 * evmcs->vm_entry_msr_load_addr = vmcs12->vm_entry_msr_load_addr;
+	 * evmcs->cr3_target_value0 = vmcs12->cr3_target_value0;
+	 * evmcs->cr3_target_value1 = vmcs12->cr3_target_value1;
+	 * evmcs->cr3_target_value2 = vmcs12->cr3_target_value2;
+	 * evmcs->cr3_target_value3 = vmcs12->cr3_target_value3;
+	 * evmcs->tpr_threshold = vmcs12->tpr_threshold;
+	 * evmcs->virtual_processor_id = vmcs12->virtual_processor_id;
+	 * evmcs->exception_bitmap = vmcs12->exception_bitmap;
+	 * evmcs->vmcs_link_pointer = vmcs12->vmcs_link_pointer;
+	 * evmcs->pin_based_vm_exec_control = vmcs12->pin_based_vm_exec_control;
+	 * evmcs->vm_exit_controls = vmcs12->vm_exit_controls;
+	 * evmcs->secondary_vm_exec_control = vmcs12->secondary_vm_exec_control;
+	 * evmcs->page_fault_error_code_mask =
+	 *		vmcs12->page_fault_error_code_mask;
+	 * evmcs->page_fault_error_code_match =
+	 *		vmcs12->page_fault_error_code_match;
+	 * evmcs->cr3_target_count = vmcs12->cr3_target_count;
+	 * evmcs->virtual_apic_page_addr = vmcs12->virtual_apic_page_addr;
+	 * evmcs->tsc_offset = vmcs12->tsc_offset;
+	 * evmcs->guest_ia32_debugctl = vmcs12->guest_ia32_debugctl;
+	 * evmcs->cr0_guest_host_mask = vmcs12->cr0_guest_host_mask;
+	 * evmcs->cr4_guest_host_mask = vmcs12->cr4_guest_host_mask;
+	 * evmcs->cr0_read_shadow = vmcs12->cr0_read_shadow;
+	 * evmcs->cr4_read_shadow = vmcs12->cr4_read_shadow;
+	 * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count;
+	 * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count;
+	 * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count;
+	 *
+	 * Not present in struct vmcs12:
+	 * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx;
+	 * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi;
+	 * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi;
+	 * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip;
+	 */
+
+	evmcs->guest_es_selector = vmcs12->guest_es_selector;
+	evmcs->guest_cs_selector = vmcs12->guest_cs_selector;
+	evmcs->guest_ss_selector = vmcs12->guest_ss_selector;
+	evmcs->guest_ds_selector = vmcs12->guest_ds_selector;
+	evmcs->guest_fs_selector = vmcs12->guest_fs_selector;
+	evmcs->guest_gs_selector = vmcs12->guest_gs_selector;
+	evmcs->guest_ldtr_selector = vmcs12->guest_ldtr_selector;
+	evmcs->guest_tr_selector = vmcs12->guest_tr_selector;
+
+	evmcs->guest_es_limit = vmcs12->guest_es_limit;
+	evmcs->guest_cs_limit = vmcs12->guest_cs_limit;
+	evmcs->guest_ss_limit = vmcs12->guest_ss_limit;
+	evmcs->guest_ds_limit = vmcs12->guest_ds_limit;
+	evmcs->guest_fs_limit = vmcs12->guest_fs_limit;
+	evmcs->guest_gs_limit = vmcs12->guest_gs_limit;
+	evmcs->guest_ldtr_limit = vmcs12->guest_ldtr_limit;
+	evmcs->guest_tr_limit = vmcs12->guest_tr_limit;
+	evmcs->guest_gdtr_limit = vmcs12->guest_gdtr_limit;
+	evmcs->guest_idtr_limit = vmcs12->guest_idtr_limit;
+
+	evmcs->guest_es_ar_bytes = vmcs12->guest_es_ar_bytes;
+	evmcs->guest_cs_ar_bytes = vmcs12->guest_cs_ar_bytes;
+	evmcs->guest_ss_ar_bytes = vmcs12->guest_ss_ar_bytes;
+	evmcs->guest_ds_ar_bytes = vmcs12->guest_ds_ar_bytes;
+	evmcs->guest_fs_ar_bytes = vmcs12->guest_fs_ar_bytes;
+	evmcs->guest_gs_ar_bytes = vmcs12->guest_gs_ar_bytes;
+	evmcs->guest_ldtr_ar_bytes = vmcs12->guest_ldtr_ar_bytes;
+	evmcs->guest_tr_ar_bytes = vmcs12->guest_tr_ar_bytes;
+
+	evmcs->guest_es_base = vmcs12->guest_es_base;
+	evmcs->guest_cs_base = vmcs12->guest_cs_base;
+	evmcs->guest_ss_base = vmcs12->guest_ss_base;
+	evmcs->guest_ds_base = vmcs12->guest_ds_base;
+	evmcs->guest_fs_base = vmcs12->guest_fs_base;
+	evmcs->guest_gs_base = vmcs12->guest_gs_base;
+	evmcs->guest_ldtr_base = vmcs12->guest_ldtr_base;
+	evmcs->guest_tr_base = vmcs12->guest_tr_base;
+	evmcs->guest_gdtr_base = vmcs12->guest_gdtr_base;
+	evmcs->guest_idtr_base = vmcs12->guest_idtr_base;
+
+	evmcs->guest_ia32_pat = vmcs12->guest_ia32_pat;
+	evmcs->guest_ia32_efer = vmcs12->guest_ia32_efer;
+
+	evmcs->guest_pdptr0 = vmcs12->guest_pdptr0;
+	evmcs->guest_pdptr1 = vmcs12->guest_pdptr1;
+	evmcs->guest_pdptr2 = vmcs12->guest_pdptr2;
+	evmcs->guest_pdptr3 = vmcs12->guest_pdptr3;
+
+	evmcs->guest_pending_dbg_exceptions =
+		vmcs12->guest_pending_dbg_exceptions;
+	evmcs->guest_sysenter_esp = vmcs12->guest_sysenter_esp;
+	evmcs->guest_sysenter_eip = vmcs12->guest_sysenter_eip;
+
+	evmcs->guest_activity_state = vmcs12->guest_activity_state;
+	evmcs->guest_sysenter_cs = vmcs12->guest_sysenter_cs;
+
+	evmcs->guest_cr0 = vmcs12->guest_cr0;
+	evmcs->guest_cr3 = vmcs12->guest_cr3;
+	evmcs->guest_cr4 = vmcs12->guest_cr4;
+	evmcs->guest_dr7 = vmcs12->guest_dr7;
+
+	evmcs->guest_physical_address = vmcs12->guest_physical_address;
+
+	evmcs->vm_instruction_error = vmcs12->vm_instruction_error;
+	evmcs->vm_exit_reason = vmcs12->vm_exit_reason;
+	evmcs->vm_exit_intr_info = vmcs12->vm_exit_intr_info;
+	evmcs->vm_exit_intr_error_code = vmcs12->vm_exit_intr_error_code;
+	evmcs->idt_vectoring_info_field = vmcs12->idt_vectoring_info_field;
+	evmcs->idt_vectoring_error_code = vmcs12->idt_vectoring_error_code;
+	evmcs->vm_exit_instruction_len = vmcs12->vm_exit_instruction_len;
+	evmcs->vmx_instruction_info = vmcs12->vmx_instruction_info;
+
+	evmcs->exit_qualification = vmcs12->exit_qualification;
+
+	evmcs->guest_linear_address = vmcs12->guest_linear_address;
+	evmcs->guest_rsp = vmcs12->guest_rsp;
+	evmcs->guest_rflags = vmcs12->guest_rflags;
+
+	evmcs->guest_interruptibility_info =
+		vmcs12->guest_interruptibility_info;
+	evmcs->cpu_based_vm_exec_control = vmcs12->cpu_based_vm_exec_control;
+	evmcs->vm_entry_controls = vmcs12->vm_entry_controls;
+	evmcs->vm_entry_intr_info_field = vmcs12->vm_entry_intr_info_field;
+	evmcs->vm_entry_exception_error_code =
+		vmcs12->vm_entry_exception_error_code;
+	evmcs->vm_entry_instruction_len = vmcs12->vm_entry_instruction_len;
+
+	evmcs->guest_rip = vmcs12->guest_rip;
+
+	evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs;
+
+	return 0;
+}
+
+/*
+ * This is an equivalent of the nested hypervisor executing the vmptrld
+ * instruction.
+ */
+static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
+						 bool from_launch)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool evmcs_gpa_changed = false;
+	u64 evmcs_gpa;
+
+	if (likely(!vmx->nested.enlightened_vmcs_enabled))
+		return 1;
+
+	if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa))
+		return 1;
+
+	if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
+		if (!vmx->nested.hv_evmcs)
+			vmx->nested.current_vmptr = -1ull;
+
+		nested_release_evmcs(vcpu);
+
+		if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa),
+				 &vmx->nested.hv_evmcs_map))
+			return 0;
+
+		vmx->nested.hv_evmcs = vmx->nested.hv_evmcs_map.hva;
+
+		/*
+		 * Currently, KVM only supports eVMCS version 1
+		 * (== KVM_EVMCS_VERSION) and thus we expect guest to set this
+		 * value to first u32 field of eVMCS which should specify eVMCS
+		 * VersionNumber.
+		 *
+		 * Guest should be aware of supported eVMCS versions by host by
+		 * examining CPUID.0x4000000A.EAX[0:15]. Host userspace VMM is
+		 * expected to set this CPUID leaf according to the value
+		 * returned in vmcs_version from nested_enable_evmcs().
+		 *
+		 * However, it turns out that Microsoft Hyper-V fails to comply
+		 * to their own invented interface: When Hyper-V use eVMCS, it
+		 * just sets first u32 field of eVMCS to revision_id specified
+		 * in MSR_IA32_VMX_BASIC. Instead of used eVMCS version number
+		 * which is one of the supported versions specified in
+		 * CPUID.0x4000000A.EAX[0:15].
+		 *
+		 * To overcome Hyper-V bug, we accept here either a supported
+		 * eVMCS version or VMCS12 revision_id as valid values for first
+		 * u32 field of eVMCS.
+		 */
+		if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) &&
+		    (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) {
+			nested_release_evmcs(vcpu);
+			return 0;
+		}
+
+		vmx->nested.dirty_vmcs12 = true;
+		vmx->nested.hv_evmcs_vmptr = evmcs_gpa;
+
+		evmcs_gpa_changed = true;
+		/*
+		 * Unlike normal vmcs12, enlightened vmcs12 is not fully
+		 * reloaded from guest's memory (read only fields, fields not
+		 * present in struct hv_enlightened_vmcs, ...). Make sure there
+		 * are no leftovers.
+		 */
+		if (from_launch) {
+			struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+			memset(vmcs12, 0, sizeof(*vmcs12));
+			vmcs12->hdr.revision_id = VMCS12_REVISION;
+		}
+
+	}
+
+	/*
+	 * Clean fields data can't de used on VMLAUNCH and when we switch
+	 * between different L2 guests as KVM keeps a single VMCS12 per L1.
+	 */
+	if (from_launch || evmcs_gpa_changed)
+		vmx->nested.hv_evmcs->hv_clean_fields &=
+			~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+
+	return 1;
+}
+
+void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * hv_evmcs may end up being not mapped after migration (when
+	 * L2 was running), map it here to make sure vmcs12 changes are
+	 * properly reflected.
+	 */
+	if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs)
+		nested_vmx_handle_enlightened_vmptrld(vcpu, false);
+
+	if (vmx->nested.hv_evmcs) {
+		copy_vmcs12_to_enlightened(vmx);
+		/* All fields are clean */
+		vmx->nested.hv_evmcs->hv_clean_fields |=
+			HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+	} else {
+		copy_vmcs12_to_shadow(vmx);
+	}
+
+	vmx->nested.need_vmcs12_to_shadow_sync = false;
+}
+
+static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
+{
+	struct vcpu_vmx *vmx =
+		container_of(timer, struct vcpu_vmx, nested.preemption_timer);
+
+	vmx->nested.preemption_timer_expired = true;
+	kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu);
+	kvm_vcpu_kick(&vmx->vcpu);
+
+	return HRTIMER_NORESTART;
+}
+
+static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
+{
+	u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * A timer value of zero is architecturally guaranteed to cause
+	 * a VMExit prior to executing any instructions in the guest.
+	 */
+	if (preemption_timeout == 0) {
+		vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
+		return;
+	}
+
+	if (vcpu->arch.virtual_tsc_khz == 0)
+		return;
+
+	preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
+	preemption_timeout *= 1000000;
+	do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
+	hrtimer_start(&vmx->nested.preemption_timer,
+		      ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
+}
+
+static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
+{
+	if (vmx->nested.nested_run_pending &&
+	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
+		return vmcs12->guest_ia32_efer;
+	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
+		return vmx->vcpu.arch.efer | (EFER_LMA | EFER_LME);
+	else
+		return vmx->vcpu.arch.efer & ~(EFER_LMA | EFER_LME);
+}
+
+static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
+{
+	/*
+	 * If vmcs02 hasn't been initialized, set the constant vmcs02 state
+	 * according to L0's settings (vmcs12 is irrelevant here).  Host
+	 * fields that come from L0 and are not constant, e.g. HOST_CR3,
+	 * will be set as needed prior to VMLAUNCH/VMRESUME.
+	 */
+	if (vmx->nested.vmcs02_initialized)
+		return;
+	vmx->nested.vmcs02_initialized = true;
+
+	/*
+	 * We don't care what the EPTP value is we just need to guarantee
+	 * it's valid so we don't get a false positive when doing early
+	 * consistency checks.
+	 */
+	if (enable_ept && nested_early_check)
+		vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0));
+
+	/* All VMFUNCs are currently emulated through L0 vmexits.  */
+	if (cpu_has_vmx_vmfunc())
+		vmcs_write64(VM_FUNCTION_CONTROL, 0);
+
+	if (cpu_has_vmx_posted_intr())
+		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
+
+	if (cpu_has_vmx_msr_bitmap())
+		vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
+
+	/*
+	 * The PML address never changes, so it is constant in vmcs02.
+	 * Conceptually we want to copy the PML index from vmcs01 here,
+	 * and then back to vmcs01 on nested vmexit.  But since we flush
+	 * the log and reset GUEST_PML_INDEX on each vmexit, the PML
+	 * index is also effectively constant in vmcs02.
+	 */
+	if (enable_pml) {
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
+	if (cpu_has_vmx_encls_vmexit())
+		vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);
+
+	/*
+	 * Set the MSR load/store lists to match L0's settings.  Only the
+	 * addresses are constant (for vmcs02), the counts can change based
+	 * on L2's behavior, e.g. switching to/from long mode.
+	 */
+	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
+
+	vmx_set_constant_host_state(vmx);
+}
+
+static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
+				      struct vmcs12 *vmcs12)
+{
+	prepare_vmcs02_constant_state(vmx);
+
+	vmcs_write64(VMCS_LINK_POINTER, -1ull);
+
+	if (enable_vpid) {
+		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
+			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
+		else
+			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+	}
+}
+
+static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
+{
+	u32 exec_control, vmcs12_exec_ctrl;
+	u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12);
+
+	if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs)
+		prepare_vmcs02_early_rare(vmx, vmcs12);
+
+	/*
+	 * PIN CONTROLS
+	 */
+	exec_control = vmx_pin_based_exec_ctrl(vmx);
+	exec_control |= (vmcs12->pin_based_vm_exec_control &
+			 ~PIN_BASED_VMX_PREEMPTION_TIMER);
+
+	/* Posted interrupts setting is only taken from vmcs12.  */
+	if (nested_cpu_has_posted_intr(vmcs12)) {
+		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
+		vmx->nested.pi_pending = false;
+	} else {
+		exec_control &= ~PIN_BASED_POSTED_INTR;
+	}
+	pin_controls_set(vmx, exec_control);
+
+	/*
+	 * EXEC CONTROLS
+	 */
+	exec_control = vmx_exec_control(vmx); /* L0's desires */
+	exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
+	exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
+	exec_control &= ~CPU_BASED_TPR_SHADOW;
+	exec_control |= vmcs12->cpu_based_vm_exec_control;
+
+	if (exec_control & CPU_BASED_TPR_SHADOW)
+		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+#ifdef CONFIG_X86_64
+	else
+		exec_control |= CPU_BASED_CR8_LOAD_EXITING |
+				CPU_BASED_CR8_STORE_EXITING;
+#endif
+
+	/*
+	 * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
+	 * for I/O port accesses.
+	 */
+	exec_control |= CPU_BASED_UNCOND_IO_EXITING;
+	exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
+
+	/*
+	 * This bit will be computed in nested_get_vmcs12_pages, because
+	 * we do not have access to L1's MSR bitmap yet.  For now, keep
+	 * the same bit as before, hoping to avoid multiple VMWRITEs that
+	 * only set/clear this bit.
+	 */
+	exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
+	exec_control |= exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS;
+
+	exec_controls_set(vmx, exec_control);
+
+	/*
+	 * SECONDARY EXEC CONTROLS
+	 */
+	if (cpu_has_secondary_exec_ctrls()) {
+		exec_control = vmx->secondary_exec_control;
+
+		/* Take the following fields only from vmcs12 */
+		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+				  SECONDARY_EXEC_ENABLE_INVPCID |
+				  SECONDARY_EXEC_RDTSCP |
+				  SECONDARY_EXEC_XSAVES |
+				  SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
+				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
+				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				  SECONDARY_EXEC_ENABLE_VMFUNC);
+		if (nested_cpu_has(vmcs12,
+				   CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
+			vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
+				~SECONDARY_EXEC_ENABLE_PML;
+			exec_control |= vmcs12_exec_ctrl;
+		}
+
+		/* VMCS shadowing for L2 is emulated for now */
+		exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
+
+		/*
+		 * Preset *DT exiting when emulating UMIP, so that vmx_set_cr4()
+		 * will not have to rewrite the controls just for this bit.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated() &&
+		    (vmcs12->guest_cr4 & X86_CR4_UMIP))
+			exec_control |= SECONDARY_EXEC_DESC;
+
+		if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
+			vmcs_write16(GUEST_INTR_STATUS,
+				vmcs12->guest_intr_status);
+
+		secondary_exec_controls_set(vmx, exec_control);
+	}
+
+	/*
+	 * ENTRY CONTROLS
+	 *
+	 * vmcs12's VM_{ENTRY,EXIT}_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE
+	 * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate
+	 * on the related bits (if supported by the CPU) in the hope that
+	 * we can avoid VMWrites during vmx_set_efer().
+	 */
+	exec_control = (vmcs12->vm_entry_controls | vmx_vmentry_ctrl()) &
+			~VM_ENTRY_IA32E_MODE & ~VM_ENTRY_LOAD_IA32_EFER;
+	if (cpu_has_load_ia32_efer()) {
+		if (guest_efer & EFER_LMA)
+			exec_control |= VM_ENTRY_IA32E_MODE;
+		if (guest_efer != host_efer)
+			exec_control |= VM_ENTRY_LOAD_IA32_EFER;
+	}
+	vm_entry_controls_set(vmx, exec_control);
+
+	/*
+	 * EXIT CONTROLS
+	 *
+	 * L2->L1 exit controls are emulated - the hardware exit is to L0 so
+	 * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
+	 * bits may be modified by vmx_set_efer() in prepare_vmcs02().
+	 */
+	exec_control = vmx_vmexit_ctrl();
+	if (cpu_has_load_ia32_efer() && guest_efer != host_efer)
+		exec_control |= VM_EXIT_LOAD_IA32_EFER;
+	vm_exit_controls_set(vmx, exec_control);
+
+	/*
+	 * Interrupt/Exception Fields
+	 */
+	if (vmx->nested.nested_run_pending) {
+		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+			     vmcs12->vm_entry_intr_info_field);
+		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
+			     vmcs12->vm_entry_exception_error_code);
+		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+			     vmcs12->vm_entry_instruction_len);
+		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
+			     vmcs12->guest_interruptibility_info);
+		vmx->loaded_vmcs->nmi_known_unmasked =
+			!(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
+	} else {
+		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
+	}
+}
+
+static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
+{
+	struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+
+	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
+		vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
+		vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
+		vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
+		vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
+		vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
+		vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
+		vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
+		vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
+		vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
+		vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
+		vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
+		vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
+		vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
+		vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
+		vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
+		vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
+		vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
+		vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
+		vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
+		vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
+		vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
+		vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
+		vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
+		vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
+		vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
+		vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
+		vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
+		vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
+		vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
+		vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
+		vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
+		vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
+		vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
+		vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
+		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
+		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+	}
+
+	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1)) {
+		vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
+		vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+			    vmcs12->guest_pending_dbg_exceptions);
+		vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
+		vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+
+		/*
+		 * L1 may access the L2's PDPTR, so save them to construct
+		 * vmcs12
+		 */
+		if (enable_ept) {
+			vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+			vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+			vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+			vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+		}
+
+		if (kvm_mpx_supported() && vmx->nested.nested_run_pending &&
+		    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+			vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+	}
+
+	if (nested_cpu_has_xsaves(vmcs12))
+		vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
+
+	/*
+	 * Whether page-faults are trapped is determined by a combination of
+	 * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
+	 * If enable_ept, L0 doesn't care about page faults and we should
+	 * set all of these to L1's desires. However, if !enable_ept, L0 does
+	 * care about (at least some) page faults, and because it is not easy
+	 * (if at all possible?) to merge L0 and L1's desires, we simply ask
+	 * to exit on each and every L2 page fault. This is done by setting
+	 * MASK=MATCH=0 and (see below) EB.PF=1.
+	 * Note that below we don't need special code to set EB.PF beyond the
+	 * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
+	 * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
+	 * !enable_ept, EB.PF is 1, so the "or" will always be 1.
+	 */
+	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
+		enable_ept ? vmcs12->page_fault_error_code_mask : 0);
+	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
+		enable_ept ? vmcs12->page_fault_error_code_match : 0);
+
+	if (cpu_has_vmx_apicv()) {
+		vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
+		vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
+		vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
+		vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
+	}
+
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+
+	set_cr4_guest_host_mask(vmx);
+}
+
+/*
+ * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
+ * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
+ * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
+ * guest in a way that will both be appropriate to L1's requests, and our
+ * needs. In addition to modifying the active vmcs (which is vmcs02), this
+ * function also has additional necessary side-effects, like setting various
+ * vcpu->arch fields.
+ * Returns 0 on success, 1 on failure. Invalid state exit qualification code
+ * is assigned to entry_failure_code on failure.
+ */
+static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
+			  u32 *entry_failure_code)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+	bool load_guest_pdptrs_vmcs12 = false;
+
+	if (vmx->nested.dirty_vmcs12 || hv_evmcs) {
+		prepare_vmcs02_rare(vmx, vmcs12);
+		vmx->nested.dirty_vmcs12 = false;
+
+		load_guest_pdptrs_vmcs12 = !hv_evmcs ||
+			!(hv_evmcs->hv_clean_fields &
+			  HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1);
+	}
+
+	if (vmx->nested.nested_run_pending &&
+	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
+		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+	} else {
+		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
+	}
+	if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
+	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
+		vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
+	vmx_set_rflags(vcpu, vmcs12->guest_rflags);
+
+	/* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
+	 * bitwise-or of what L1 wants to trap for L2, and what we want to
+	 * trap. Note that CR0.TS also needs updating - we do this later.
+	 */
+	update_exception_bitmap(vcpu);
+	vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
+	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
+
+	if (vmx->nested.nested_run_pending &&
+	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) {
+		vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
+		vcpu->arch.pat = vmcs12->guest_ia32_pat;
+	} else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
+	}
+
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
+	if (kvm_has_tsc_control)
+		decache_tsc_multiplier(vmx);
+
+	if (enable_vpid) {
+		/*
+		 * There is no direct mapping between vpid02 and vpid12, the
+		 * vpid02 is per-vCPU for L0 and reused while the value of
+		 * vpid12 is changed w/ one invvpid during nested vmentry.
+		 * The vpid12 is allocated by L1 for L2, so it will not
+		 * influence global bitmap(for vpid01 and vpid02 allocation)
+		 * even if spawn a lot of nested vCPUs.
+		 */
+		if (nested_cpu_has_vpid(vmcs12) && nested_has_guest_tlb_tag(vcpu)) {
+			if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
+				vmx->nested.last_vpid = vmcs12->virtual_processor_id;
+				__vmx_flush_tlb(vcpu, nested_get_vpid02(vcpu), false);
+			}
+		} else {
+			/*
+			 * If L1 use EPT, then L0 needs to execute INVEPT on
+			 * EPTP02 instead of EPTP01. Therefore, delay TLB
+			 * flush until vmcs02->eptp is fully updated by
+			 * KVM_REQ_LOAD_CR3. Note that this assumes
+			 * KVM_REQ_TLB_FLUSH is evaluated after
+			 * KVM_REQ_LOAD_CR3 in vcpu_enter_guest().
+			 */
+			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+		}
+	}
+
+	if (nested_cpu_has_ept(vmcs12))
+		nested_ept_init_mmu_context(vcpu);
+	else if (nested_cpu_has2(vmcs12,
+				 SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+		vmx_flush_tlb(vcpu, true);
+
+	/*
+	 * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
+	 * bits which we consider mandatory enabled.
+	 * The CR0_READ_SHADOW is what L2 should have expected to read given
+	 * the specifications by L1; It's not enough to take
+	 * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we
+	 * have more bits than L1 expected.
+	 */
+	vmx_set_cr0(vcpu, vmcs12->guest_cr0);
+	vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12));
+
+	vmx_set_cr4(vcpu, vmcs12->guest_cr4);
+	vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));
+
+	vcpu->arch.efer = nested_vmx_calc_efer(vmx, vmcs12);
+	/* Note: may modify VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
+	vmx_set_efer(vcpu, vcpu->arch.efer);
+
+	/*
+	 * Guest state is invalid and unrestricted guest is disabled,
+	 * which means L1 attempted VMEntry to L2 with invalid state.
+	 * Fail the VMEntry.
+	 */
+	if (vmx->emulation_required) {
+		*entry_failure_code = ENTRY_FAIL_DEFAULT;
+		return -EINVAL;
+	}
+
+	/* Shadow page tables on either EPT or shadow page tables. */
+	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
+				entry_failure_code))
+		return -EINVAL;
+
+	/* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */
+	if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) &&
+	    is_pae_paging(vcpu)) {
+		vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+	}
+
+	if (!enable_ept)
+		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
+
+	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
+	kvm_rip_write(vcpu, vmcs12->guest_rip);
+	return 0;
+}
+
+static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12)
+{
+	if (CC(!nested_cpu_has_nmi_exiting(vmcs12) &&
+	       nested_cpu_has_virtual_nmis(vmcs12)))
+		return -EINVAL;
+
+	if (CC(!nested_cpu_has_virtual_nmis(vmcs12) &&
+	       nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+	/* Check for memory type validity */
+	switch (address & VMX_EPTP_MT_MASK) {
+	case VMX_EPTP_MT_UC:
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT)))
+			return false;
+		break;
+	case VMX_EPTP_MT_WB:
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT)))
+			return false;
+		break;
+	default:
+		return false;
+	}
+
+	/* only 4 levels page-walk length are valid */
+	if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4))
+		return false;
+
+	/* Reserved bits should not be set */
+	if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f)))
+		return false;
+
+	/* AD, if set, should be supported */
+	if (address & VMX_EPTP_AD_ENABLE_BIT) {
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT)))
+			return false;
+	}
+
+	return true;
+}
+
+/*
+ * Checks related to VM-Execution Control Fields
+ */
+static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu,
+                                              struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (CC(!vmx_control_verify(vmcs12->pin_based_vm_exec_control,
+				   vmx->nested.msrs.pinbased_ctls_low,
+				   vmx->nested.msrs.pinbased_ctls_high)) ||
+	    CC(!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
+				   vmx->nested.msrs.procbased_ctls_low,
+				   vmx->nested.msrs.procbased_ctls_high)))
+		return -EINVAL;
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
+	    CC(!vmx_control_verify(vmcs12->secondary_vm_exec_control,
+				   vmx->nested.msrs.secondary_ctls_low,
+				   vmx->nested.msrs.secondary_ctls_high)))
+		return -EINVAL;
+
+	if (CC(vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu)) ||
+	    nested_vmx_check_io_bitmap_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_apic_access_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_apicv_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_nmi_controls(vmcs12) ||
+	    nested_vmx_check_pml_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_unrestricted_guest_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_mode_based_ept_exec_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_shadow_vmcs_controls(vcpu, vmcs12) ||
+	    CC(nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id))
+		return -EINVAL;
+
+	if (!nested_cpu_has_preemption_timer(vmcs12) &&
+	    nested_cpu_has_save_preemption_timer(vmcs12))
+		return -EINVAL;
+
+	if (nested_cpu_has_ept(vmcs12) &&
+	    CC(!valid_ept_address(vcpu, vmcs12->ept_pointer)))
+		return -EINVAL;
+
+	if (nested_cpu_has_vmfunc(vmcs12)) {
+		if (CC(vmcs12->vm_function_control &
+		       ~vmx->nested.msrs.vmfunc_controls))
+			return -EINVAL;
+
+		if (nested_cpu_has_eptp_switching(vmcs12)) {
+			if (CC(!nested_cpu_has_ept(vmcs12)) ||
+			    CC(!page_address_valid(vcpu, vmcs12->eptp_list_address)))
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Checks related to VM-Exit Control Fields
+ */
+static int nested_check_vm_exit_controls(struct kvm_vcpu *vcpu,
+                                         struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (CC(!vmx_control_verify(vmcs12->vm_exit_controls,
+				    vmx->nested.msrs.exit_ctls_low,
+				    vmx->nested.msrs.exit_ctls_high)) ||
+	    CC(nested_vmx_check_exit_msr_switch_controls(vcpu, vmcs12)))
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Checks related to VM-Entry Control Fields
+ */
+static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (CC(!vmx_control_verify(vmcs12->vm_entry_controls,
+				    vmx->nested.msrs.entry_ctls_low,
+				    vmx->nested.msrs.entry_ctls_high)))
+		return -EINVAL;
+
+	/*
+	 * From the Intel SDM, volume 3:
+	 * Fields relevant to VM-entry event injection must be set properly.
+	 * These fields are the VM-entry interruption-information field, the
+	 * VM-entry exception error code, and the VM-entry instruction length.
+	 */
+	if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
+		u32 intr_info = vmcs12->vm_entry_intr_info_field;
+		u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
+		u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
+		bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
+		bool should_have_error_code;
+		bool urg = nested_cpu_has2(vmcs12,
+					   SECONDARY_EXEC_UNRESTRICTED_GUEST);
+		bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;
+
+		/* VM-entry interruption-info field: interruption type */
+		if (CC(intr_type == INTR_TYPE_RESERVED) ||
+		    CC(intr_type == INTR_TYPE_OTHER_EVENT &&
+		       !nested_cpu_supports_monitor_trap_flag(vcpu)))
+			return -EINVAL;
+
+		/* VM-entry interruption-info field: vector */
+		if (CC(intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) ||
+		    CC(intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) ||
+		    CC(intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
+			return -EINVAL;
+
+		/* VM-entry interruption-info field: deliver error code */
+		should_have_error_code =
+			intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
+			x86_exception_has_error_code(vector);
+		if (CC(has_error_code != should_have_error_code))
+			return -EINVAL;
+
+		/* VM-entry exception error code */
+		if (CC(has_error_code &&
+		       vmcs12->vm_entry_exception_error_code & GENMASK(31, 16)))
+			return -EINVAL;
+
+		/* VM-entry interruption-info field: reserved bits */
+		if (CC(intr_info & INTR_INFO_RESVD_BITS_MASK))
+			return -EINVAL;
+
+		/* VM-entry instruction length */
+		switch (intr_type) {
+		case INTR_TYPE_SOFT_EXCEPTION:
+		case INTR_TYPE_SOFT_INTR:
+		case INTR_TYPE_PRIV_SW_EXCEPTION:
+			if (CC(vmcs12->vm_entry_instruction_len > 15) ||
+			    CC(vmcs12->vm_entry_instruction_len == 0 &&
+			    CC(!nested_cpu_has_zero_length_injection(vcpu))))
+				return -EINVAL;
+		}
+	}
+
+	if (nested_vmx_check_entry_msr_switch_controls(vcpu, vmcs12))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
+				     struct vmcs12 *vmcs12)
+{
+	if (nested_check_vm_execution_controls(vcpu, vmcs12) ||
+	    nested_check_vm_exit_controls(vcpu, vmcs12) ||
+	    nested_check_vm_entry_controls(vcpu, vmcs12))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	bool ia32e;
+
+	if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) ||
+	    CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) ||
+	    CC(!nested_cr3_valid(vcpu, vmcs12->host_cr3)))
+		return -EINVAL;
+
+	if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
+	    CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
+		return -EINVAL;
+
+	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) &&
+	    CC(!kvm_pat_valid(vmcs12->host_ia32_pat)))
+		return -EINVAL;
+
+#ifdef CONFIG_X86_64
+	ia32e = !!(vcpu->arch.efer & EFER_LMA);
+#else
+	ia32e = false;
+#endif
+
+	if (ia32e) {
+		if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) ||
+		    CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
+			return -EINVAL;
+	} else {
+		if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) ||
+		    CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
+		    CC(vmcs12->host_cr4 & X86_CR4_PCIDE) ||
+		    CC((vmcs12->host_rip) >> 32))
+			return -EINVAL;
+	}
+
+	if (CC(vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
+	    CC(vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
+	    CC(vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
+	    CC(vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
+	    CC(vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
+	    CC(vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
+	    CC(vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) ||
+	    CC(vmcs12->host_cs_selector == 0) ||
+	    CC(vmcs12->host_tr_selector == 0) ||
+	    CC(vmcs12->host_ss_selector == 0 && !ia32e))
+		return -EINVAL;
+
+#ifdef CONFIG_X86_64
+	if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) ||
+	    CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) ||
+	    CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) ||
+	    CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) ||
+	    CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) ||
+	    CC(is_noncanonical_address(vmcs12->host_rip, vcpu)))
+		return -EINVAL;
+#endif
+
+	/*
+	 * If the load IA32_EFER VM-exit control is 1, bits reserved in the
+	 * IA32_EFER MSR must be 0 in the field for that register. In addition,
+	 * the values of the LMA and LME bits in the field must each be that of
+	 * the host address-space size VM-exit control.
+	 */
+	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) {
+		if (CC(!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer)) ||
+		    CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA)) ||
+		    CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	int r = 0;
+	struct vmcs12 *shadow;
+	struct kvm_host_map map;
+
+	if (vmcs12->vmcs_link_pointer == -1ull)
+		return 0;
+
+	if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)))
+		return -EINVAL;
+
+	if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)))
+		return -EINVAL;
+
+	shadow = map.hva;
+
+	if (CC(shadow->hdr.revision_id != VMCS12_REVISION) ||
+	    CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
+		r = -EINVAL;
+
+	kvm_vcpu_unmap(vcpu, &map, false);
+	return r;
+}
+
+/*
+ * Checks related to Guest Non-register State
+ */
+static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12)
+{
+	if (CC(vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
+	       vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
+					struct vmcs12 *vmcs12,
+					u32 *exit_qual)
+{
+	bool ia32e;
+
+	*exit_qual = ENTRY_FAIL_DEFAULT;
+
+	if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) ||
+	    CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)))
+		return -EINVAL;
+
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
+	    CC(!kvm_pat_valid(vmcs12->guest_ia32_pat)))
+		return -EINVAL;
+
+	if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) {
+		*exit_qual = ENTRY_FAIL_VMCS_LINK_PTR;
+		return -EINVAL;
+	}
+
+	/*
+	 * If the load IA32_EFER VM-entry control is 1, the following checks
+	 * are performed on the field for the IA32_EFER MSR:
+	 * - Bits reserved in the IA32_EFER MSR must be 0.
+	 * - Bit 10 (corresponding to IA32_EFER.LMA) must equal the value of
+	 *   the IA-32e mode guest VM-exit control. It must also be identical
+	 *   to bit 8 (LME) if bit 31 in the CR0 field (corresponding to
+	 *   CR0.PG) is 1.
+	 */
+	if (to_vmx(vcpu)->nested.nested_run_pending &&
+	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
+		ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
+		if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) ||
+		    CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) ||
+		    CC(((vmcs12->guest_cr0 & X86_CR0_PG) &&
+		     ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))))
+			return -EINVAL;
+	}
+
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
+	    (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
+	     CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD))))
+		return -EINVAL;
+
+	if (nested_check_guest_non_reg_state(vmcs12))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long cr3, cr4;
+	bool vm_fail;
+
+	if (!nested_early_check)
+		return 0;
+
+	if (vmx->msr_autoload.host.nr)
+		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+	if (vmx->msr_autoload.guest.nr)
+		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+
+	preempt_disable();
+
+	vmx_prepare_switch_to_guest(vcpu);
+
+	/*
+	 * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS,
+	 * which is reserved to '1' by hardware.  GUEST_RFLAGS is guaranteed to
+	 * be written (by preparve_vmcs02()) before the "real" VMEnter, i.e.
+	 * there is no need to preserve other bits or save/restore the field.
+	 */
+	vmcs_writel(GUEST_RFLAGS, 0);
+
+	cr3 = __get_current_cr3_fast();
+	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		vmx->loaded_vmcs->host_state.cr3 = cr3;
+	}
+
+	cr4 = cr4_read_shadow();
+	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
+		vmcs_writel(HOST_CR4, cr4);
+		vmx->loaded_vmcs->host_state.cr4 = cr4;
+	}
+
+	asm(
+		"sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */
+		"cmp %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t"
+		"je 1f \n\t"
+		__ex("vmwrite %%" _ASM_SP ", %[HOST_RSP]") "\n\t"
+		"mov %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t"
+		"1: \n\t"
+		"add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */
+
+		/* Check if vmlaunch or vmresume is needed */
+		"cmpb $0, %c[launched](%[loaded_vmcs])\n\t"
+
+		/*
+		 * VMLAUNCH and VMRESUME clear RFLAGS.{CF,ZF} on VM-Exit, set
+		 * RFLAGS.CF on VM-Fail Invalid and set RFLAGS.ZF on VM-Fail
+		 * Valid.  vmx_vmenter() directly "returns" RFLAGS, and so the
+		 * results of VM-Enter is captured via CC_{SET,OUT} to vm_fail.
+		 */
+		"call vmx_vmenter\n\t"
+
+		CC_SET(be)
+	      : ASM_CALL_CONSTRAINT, CC_OUT(be) (vm_fail)
+	      :	[HOST_RSP]"r"((unsigned long)HOST_RSP),
+		[loaded_vmcs]"r"(vmx->loaded_vmcs),
+		[launched]"i"(offsetof(struct loaded_vmcs, launched)),
+		[host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)),
+		[wordsize]"i"(sizeof(ulong))
+	      : "memory"
+	);
+
+	if (vmx->msr_autoload.host.nr)
+		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	if (vmx->msr_autoload.guest.nr)
+		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+
+	if (vm_fail) {
+		u32 error = vmcs_read32(VM_INSTRUCTION_ERROR);
+
+		preempt_enable();
+
+		trace_kvm_nested_vmenter_failed(
+			"early hardware check VM-instruction error: ", error);
+		WARN_ON_ONCE(error != VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+		return 1;
+	}
+
+	/*
+	 * VMExit clears RFLAGS.IF and DR7, even on a consistency check.
+	 */
+	local_irq_enable();
+	if (hw_breakpoint_active())
+		set_debugreg(__this_cpu_read(cpu_dr7), 7);
+	preempt_enable();
+
+	/*
+	 * A non-failing VMEntry means we somehow entered guest mode with
+	 * an illegal RIP, and that's just the tip of the iceberg.  There
+	 * is no telling what memory has been modified or what state has
+	 * been exposed to unknown code.  Hitting this all but guarantees
+	 * a (very critical) hardware issue.
+	 */
+	WARN_ON(!(vmcs_read32(VM_EXIT_REASON) &
+		VMX_EXIT_REASONS_FAILED_VMENTRY));
+
+	return 0;
+}
+
+static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
+						 struct vmcs12 *vmcs12);
+
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_host_map *map;
+	struct page *page;
+	u64 hpa;
+
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		/*
+		 * Translate L1 physical address to host physical
+		 * address for vmcs02. Keep the page pinned, so this
+		 * physical address remains valid. We keep a reference
+		 * to it so we can release it later.
+		 */
+		if (vmx->nested.apic_access_page) { /* shouldn't happen */
+			kvm_release_page_dirty(vmx->nested.apic_access_page);
+			vmx->nested.apic_access_page = NULL;
+		}
+		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
+		if (!is_error_page(page)) {
+			vmx->nested.apic_access_page = page;
+			hpa = page_to_phys(vmx->nested.apic_access_page);
+			vmcs_write64(APIC_ACCESS_ADDR, hpa);
+		} else {
+			pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n",
+					     __func__);
+			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+			vcpu->run->internal.suberror =
+				KVM_INTERNAL_ERROR_EMULATION;
+			vcpu->run->internal.ndata = 0;
+			return false;
+		}
+	}
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+		map = &vmx->nested.virtual_apic_map;
+
+		if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->virtual_apic_page_addr), map)) {
+			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, pfn_to_hpa(map->pfn));
+		} else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+		           nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+			   !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+			/*
+			 * The processor will never use the TPR shadow, simply
+			 * clear the bit from the execution control.  Such a
+			 * configuration is useless, but it happens in tests.
+			 * For any other configuration, failing the vm entry is
+			 * _not_ what the processor does but it's basically the
+			 * only possibility we have.
+			 */
+			exec_controls_clearbit(vmx, CPU_BASED_TPR_SHADOW);
+		} else {
+			/*
+			 * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR to
+			 * force VM-Entry to fail.
+			 */
+			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
+		}
+	}
+
+	if (nested_cpu_has_posted_intr(vmcs12)) {
+		map = &vmx->nested.pi_desc_map;
+
+		if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->posted_intr_desc_addr), map)) {
+			vmx->nested.pi_desc =
+				(struct pi_desc *)(((void *)map->hva) +
+				offset_in_page(vmcs12->posted_intr_desc_addr));
+			vmcs_write64(POSTED_INTR_DESC_ADDR,
+				     pfn_to_hpa(map->pfn) + offset_in_page(vmcs12->posted_intr_desc_addr));
+		}
+	}
+	if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12))
+		exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
+	else
+		exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
+	return true;
+}
+
+/*
+ * Intel's VMX Instruction Reference specifies a common set of prerequisites
+ * for running VMX instructions (except VMXON, whose prerequisites are
+ * slightly different). It also specifies what exception to inject otherwise.
+ * Note that many of these exceptions have priority over VM exits, so they
+ * don't have to be checked again here.
+ */
+static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
+{
+	if (!to_vmx(vcpu)->nested.vmxon) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 0;
+	}
+
+	if (vmx_get_cpl(vcpu)) {
+		kvm_inject_gp(vcpu, 0);
+		return 0;
+	}
+
+	return 1;
+}
+
+static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu)
+{
+	u8 rvi = vmx_get_rvi();
+	u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI);
+
+	return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
+static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
+				   struct vmcs12 *vmcs12);
+
+/*
+ * If from_vmentry is false, this is being called from state restore (either RSM
+ * or KVM_SET_NESTED_STATE).  Otherwise it's called from vmlaunch/vmresume.
+ *
+ * Returns:
+ *	NVMX_ENTRY_SUCCESS: Entered VMX non-root mode
+ *	NVMX_ENTRY_VMFAIL:  Consistency check VMFail
+ *	NVMX_ENTRY_VMEXIT:  Consistency check VMExit
+ *	NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error
+ */
+enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+							bool from_vmentry)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	bool evaluate_pending_interrupts;
+	u32 exit_reason = EXIT_REASON_INVALID_STATE;
+	u32 exit_qual;
+
+	evaluate_pending_interrupts = exec_controls_get(vmx) &
+		(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
+	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
+		evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
+
+	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
+		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+	if (kvm_mpx_supported() &&
+		!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+		vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
+
+	/*
+	 * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and*
+	 * nested early checks are disabled.  In the event of a "late" VM-Fail,
+	 * i.e. a VM-Fail detected by hardware but not KVM, KVM must unwind its
+	 * software model to the pre-VMEntry host state.  When EPT is disabled,
+	 * GUEST_CR3 holds KVM's shadow CR3, not L1's "real" CR3, which causes
+	 * nested_vmx_restore_host_state() to corrupt vcpu->arch.cr3.  Stuffing
+	 * vmcs01.GUEST_CR3 results in the unwind naturally setting arch.cr3 to
+	 * the correct value.  Smashing vmcs01.GUEST_CR3 is safe because nested
+	 * VM-Exits, and the unwind, reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is
+	 * guaranteed to be overwritten with a shadow CR3 prior to re-entering
+	 * L1.  Don't stuff vmcs01.GUEST_CR3 when using nested early checks as
+	 * KVM modifies vcpu->arch.cr3 if and only if the early hardware checks
+	 * pass, and early VM-Fails do not reset KVM's MMU, i.e. the VM-Fail
+	 * path would need to manually save/restore vmcs01.GUEST_CR3.
+	 */
+	if (!enable_ept && !nested_early_check)
+		vmcs_writel(GUEST_CR3, vcpu->arch.cr3);
+
+	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
+
+	prepare_vmcs02_early(vmx, vmcs12);
+
+	if (from_vmentry) {
+		if (unlikely(!nested_get_vmcs12_pages(vcpu)))
+			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
+
+		if (nested_vmx_check_vmentry_hw(vcpu)) {
+			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+			return NVMX_VMENTRY_VMFAIL;
+		}
+
+		if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
+			goto vmentry_fail_vmexit;
+	}
+
+	enter_guest_mode(vcpu);
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
+
+	if (prepare_vmcs02(vcpu, vmcs12, &exit_qual))
+		goto vmentry_fail_vmexit_guest_mode;
+
+	if (from_vmentry) {
+		exit_reason = EXIT_REASON_MSR_LOAD_FAIL;
+		exit_qual = nested_vmx_load_msr(vcpu,
+						vmcs12->vm_entry_msr_load_addr,
+						vmcs12->vm_entry_msr_load_count);
+		if (exit_qual)
+			goto vmentry_fail_vmexit_guest_mode;
+	} else {
+		/*
+		 * The MMU is not initialized to point at the right entities yet and
+		 * "get pages" would need to read data from the guest (i.e. we will
+		 * need to perform gpa to hpa translation). Request a call
+		 * to nested_get_vmcs12_pages before the next VM-entry.  The MSRs
+		 * have already been set at vmentry time and should not be reset.
+		 */
+		kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+	}
+
+	/*
+	 * If L1 had a pending IRQ/NMI until it executed
+	 * VMLAUNCH/VMRESUME which wasn't delivered because it was
+	 * disallowed (e.g. interrupts disabled), L0 needs to
+	 * evaluate if this pending event should cause an exit from L2
+	 * to L1 or delivered directly to L2 (e.g. In case L1 don't
+	 * intercept EXTERNAL_INTERRUPT).
+	 *
+	 * Usually this would be handled by the processor noticing an
+	 * IRQ/NMI window request, or checking RVI during evaluation of
+	 * pending virtual interrupts.  However, this setting was done
+	 * on VMCS01 and now VMCS02 is active instead. Thus, we force L0
+	 * to perform pending event evaluation by requesting a KVM_REQ_EVENT.
+	 */
+	if (unlikely(evaluate_pending_interrupts))
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	/*
+	 * Do not start the preemption timer hrtimer until after we know
+	 * we are successful, so that only nested_vmx_vmexit needs to cancel
+	 * the timer.
+	 */
+	vmx->nested.preemption_timer_expired = false;
+	if (nested_cpu_has_preemption_timer(vmcs12))
+		vmx_start_preemption_timer(vcpu);
+
+	/*
+	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
+	 * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet
+	 * returned as far as L1 is concerned. It will only return (and set
+	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
+	 */
+	return NVMX_VMENTRY_SUCCESS;
+
+	/*
+	 * A failed consistency check that leads to a VMExit during L1's
+	 * VMEnter to L2 is a variation of a normal VMexit, as explained in
+	 * 26.7 "VM-entry failures during or after loading guest state".
+	 */
+vmentry_fail_vmexit_guest_mode:
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+	leave_guest_mode(vcpu);
+
+vmentry_fail_vmexit:
+	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+
+	if (!from_vmentry)
+		return NVMX_VMENTRY_VMEXIT;
+
+	load_vmcs12_host_state(vcpu, vmcs12);
+	vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
+	vmcs12->exit_qualification = exit_qual;
+	if (enable_shadow_vmcs || vmx->nested.hv_evmcs)
+		vmx->nested.need_vmcs12_to_shadow_sync = true;
+	return NVMX_VMENTRY_VMEXIT;
+}
+
+/*
+ * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1
+ * for running an L2 nested guest.
+ */
+static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
+{
+	struct vmcs12 *vmcs12;
+	enum nvmx_vmentry_status status;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (!nested_vmx_handle_enlightened_vmptrld(vcpu, launch))
+		return 1;
+
+	if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull)
+		return nested_vmx_failInvalid(vcpu);
+
+	vmcs12 = get_vmcs12(vcpu);
+
+	/*
+	 * Can't VMLAUNCH or VMRESUME a shadow VMCS. Despite the fact
+	 * that there *is* a valid VMCS pointer, RFLAGS.CF is set
+	 * rather than RFLAGS.ZF, and no error number is stored to the
+	 * VM-instruction error field.
+	 */
+	if (vmcs12->hdr.shadow_vmcs)
+		return nested_vmx_failInvalid(vcpu);
+
+	if (vmx->nested.hv_evmcs) {
+		copy_enlightened_to_vmcs12(vmx);
+		/* Enlightened VMCS doesn't have launch state */
+		vmcs12->launch_state = !launch;
+	} else if (enable_shadow_vmcs) {
+		copy_shadow_to_vmcs12(vmx);
+	}
+
+	/*
+	 * The nested entry process starts with enforcing various prerequisites
+	 * on vmcs12 as required by the Intel SDM, and act appropriately when
+	 * they fail: As the SDM explains, some conditions should cause the
+	 * instruction to fail, while others will cause the instruction to seem
+	 * to succeed, but return an EXIT_REASON_INVALID_STATE.
+	 * To speed up the normal (success) code path, we should avoid checking
+	 * for misconfigurations which will anyway be caught by the processor
+	 * when using the merged vmcs02.
+	 */
+	if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
+
+	if (vmcs12->launch_state == launch)
+		return nested_vmx_failValid(vcpu,
+			launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
+			       : VMXERR_VMRESUME_NONLAUNCHED_VMCS);
+
+	if (nested_vmx_check_controls(vcpu, vmcs12))
+		return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+	if (nested_vmx_check_host_state(vcpu, vmcs12))
+		return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
+
+	/*
+	 * We're finally done with prerequisite checking, and can start with
+	 * the nested entry.
+	 */
+	vmx->nested.nested_run_pending = 1;
+	status = nested_vmx_enter_non_root_mode(vcpu, true);
+	if (unlikely(status != NVMX_VMENTRY_SUCCESS))
+		goto vmentry_failed;
+
+	/* Hide L1D cache contents from the nested guest.  */
+	vmx->vcpu.arch.l1tf_flush_l1d = true;
+
+	/*
+	 * Must happen outside of nested_vmx_enter_non_root_mode() as it will
+	 * also be used as part of restoring nVMX state for
+	 * snapshot restore (migration).
+	 *
+	 * In this flow, it is assumed that vmcs12 cache was
+	 * trasferred as part of captured nVMX state and should
+	 * therefore not be read from guest memory (which may not
+	 * exist on destination host yet).
+	 */
+	nested_cache_shadow_vmcs12(vcpu, vmcs12);
+
+	/*
+	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be
+	 * awakened by event injection or by an NMI-window VM-exit or
+	 * by an interrupt-window VM-exit, halt the vcpu.
+	 */
+	if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
+	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
+	    !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_NMI_PENDING) &&
+	    !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_INTR_PENDING) &&
+	      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
+		vmx->nested.nested_run_pending = 0;
+		return kvm_vcpu_halt(vcpu);
+	}
+	return 1;
+
+vmentry_failed:
+	vmx->nested.nested_run_pending = 0;
+	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR)
+		return 0;
+	if (status == NVMX_VMENTRY_VMEXIT)
+		return 1;
+	WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);
+	return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+}
+
+/*
+ * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date
+ * because L2 may have changed some cr0 bits directly (CRO_GUEST_HOST_MASK).
+ * This function returns the new value we should put in vmcs12.guest_cr0.
+ * It's not enough to just return the vmcs02 GUEST_CR0. Rather,
+ *  1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now
+ *     available in vmcs02 GUEST_CR0. (Note: It's enough to check that L0
+ *     didn't trap the bit, because if L1 did, so would L0).
+ *  2. Bits that L1 asked to trap (and therefore L0 also did) could not have
+ *     been modified by L2, and L1 knows it. So just leave the old value of
+ *     the bit from vmcs12.guest_cr0. Note that the bit from vmcs02 GUEST_CR0
+ *     isn't relevant, because if L0 traps this bit it can set it to anything.
+ *  3. Bits that L1 didn't trap, but L0 did. L1 believes the guest could have
+ *     changed these bits, and therefore they need to be updated, but L0
+ *     didn't necessarily allow them to be changed in GUEST_CR0 - and rather
+ *     put them in vmcs02 CR0_READ_SHADOW. So take these bits from there.
+ */
+static inline unsigned long
+vmcs12_guest_cr0(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+	return
+	/*1*/	(vmcs_readl(GUEST_CR0) & vcpu->arch.cr0_guest_owned_bits) |
+	/*2*/	(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask) |
+	/*3*/	(vmcs_readl(CR0_READ_SHADOW) & ~(vmcs12->cr0_guest_host_mask |
+			vcpu->arch.cr0_guest_owned_bits));
+}
+
+static inline unsigned long
+vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+	return
+	/*1*/	(vmcs_readl(GUEST_CR4) & vcpu->arch.cr4_guest_owned_bits) |
+	/*2*/	(vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask) |
+	/*3*/	(vmcs_readl(CR4_READ_SHADOW) & ~(vmcs12->cr4_guest_host_mask |
+			vcpu->arch.cr4_guest_owned_bits));
+}
+
+static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
+				      struct vmcs12 *vmcs12)
+{
+	u32 idt_vectoring;
+	unsigned int nr;
+
+	if (vcpu->arch.exception.injected) {
+		nr = vcpu->arch.exception.nr;
+		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
+
+		if (kvm_exception_is_soft(nr)) {
+			vmcs12->vm_exit_instruction_len =
+				vcpu->arch.event_exit_inst_len;
+			idt_vectoring |= INTR_TYPE_SOFT_EXCEPTION;
+		} else
+			idt_vectoring |= INTR_TYPE_HARD_EXCEPTION;
+
+		if (vcpu->arch.exception.has_error_code) {
+			idt_vectoring |= VECTORING_INFO_DELIVER_CODE_MASK;
+			vmcs12->idt_vectoring_error_code =
+				vcpu->arch.exception.error_code;
+		}
+
+		vmcs12->idt_vectoring_info_field = idt_vectoring;
+	} else if (vcpu->arch.nmi_injected) {
+		vmcs12->idt_vectoring_info_field =
+			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR;
+	} else if (vcpu->arch.interrupt.injected) {
+		nr = vcpu->arch.interrupt.nr;
+		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
+
+		if (vcpu->arch.interrupt.soft) {
+			idt_vectoring |= INTR_TYPE_SOFT_INTR;
+			vmcs12->vm_entry_instruction_len =
+				vcpu->arch.event_exit_inst_len;
+		} else
+			idt_vectoring |= INTR_TYPE_EXT_INTR;
+
+		vmcs12->idt_vectoring_info_field = idt_vectoring;
+	}
+}
+
+
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	gfn_t gfn;
+
+	/*
+	 * Don't need to mark the APIC access page dirty; it is never
+	 * written to by the CPU during APIC virtualization.
+	 */
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+		gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+
+	if (nested_cpu_has_posted_intr(vmcs12)) {
+		gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+}
+
+static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int max_irr;
+	void *vapic_page;
+	u16 status;
+
+	if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+		return;
+
+	vmx->nested.pi_pending = false;
+	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+		return;
+
+	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (max_irr != 256) {
+		vapic_page = vmx->nested.virtual_apic_map.hva;
+		if (!vapic_page)
+			return;
+
+		__kvm_apic_update_irr(vmx->nested.pi_desc->pir,
+			vapic_page, &max_irr);
+		status = vmcs_read16(GUEST_INTR_STATUS);
+		if ((u8)max_irr > ((u8)status & 0xff)) {
+			status &= ~0xff;
+			status |= (u8)max_irr;
+			vmcs_write16(GUEST_INTR_STATUS, status);
+		}
+	}
+
+	nested_mark_vmcs12_pages_dirty(vcpu);
+}
+
+static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
+					       unsigned long exit_qual)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned int nr = vcpu->arch.exception.nr;
+	u32 intr_info = nr | INTR_INFO_VALID_MASK;
+
+	if (vcpu->arch.exception.has_error_code) {
+		vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
+		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+	}
+
+	if (kvm_exception_is_soft(nr))
+		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+	else
+		intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+	if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) &&
+	    vmx_get_nmi_mask(vcpu))
+		intr_info |= INTR_INFO_UNBLOCK_NMI;
+
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
+}
+
+static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long exit_qual;
+	bool block_nested_events =
+	    vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	if (lapic_in_kernel(vcpu) &&
+		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
+		return 0;
+	}
+
+	if (vcpu->arch.exception.pending &&
+		nested_vmx_check_exception(vcpu, &exit_qual)) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+		return 0;
+	}
+
+	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
+	    vmx->nested.preemption_timer_expired) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
+		return 0;
+	}
+
+	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+				  NMI_VECTOR | INTR_TYPE_NMI_INTR |
+				  INTR_INFO_VALID_MASK, 0);
+		/*
+		 * The NMI-triggered VM exit counts as injection:
+		 * clear this one and block further NMIs.
+		 */
+		vcpu->arch.nmi_pending = 0;
+		vmx_set_nmi_mask(vcpu, true);
+		return 0;
+	}
+
+	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
+	    nested_exit_on_intr(vcpu)) {
+		if (block_nested_events)
+			return -EBUSY;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
+		return 0;
+	}
+
+	vmx_complete_nested_posted_interrupt(vcpu);
+	return 0;
+}
+
+static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)
+{
+	ktime_t remaining =
+		hrtimer_get_remaining(&to_vmx(vcpu)->nested.preemption_timer);
+	u64 value;
+
+	if (ktime_to_ns(remaining) <= 0)
+		return 0;
+
+	value = ktime_to_ns(remaining) * vcpu->arch.virtual_tsc_khz;
+	do_div(value, 1000000);
+	return value >> VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
+}
+
+static bool is_vmcs12_ext_field(unsigned long field)
+{
+	switch (field) {
+	case GUEST_ES_SELECTOR:
+	case GUEST_CS_SELECTOR:
+	case GUEST_SS_SELECTOR:
+	case GUEST_DS_SELECTOR:
+	case GUEST_FS_SELECTOR:
+	case GUEST_GS_SELECTOR:
+	case GUEST_LDTR_SELECTOR:
+	case GUEST_TR_SELECTOR:
+	case GUEST_ES_LIMIT:
+	case GUEST_CS_LIMIT:
+	case GUEST_SS_LIMIT:
+	case GUEST_DS_LIMIT:
+	case GUEST_FS_LIMIT:
+	case GUEST_GS_LIMIT:
+	case GUEST_LDTR_LIMIT:
+	case GUEST_TR_LIMIT:
+	case GUEST_GDTR_LIMIT:
+	case GUEST_IDTR_LIMIT:
+	case GUEST_ES_AR_BYTES:
+	case GUEST_DS_AR_BYTES:
+	case GUEST_FS_AR_BYTES:
+	case GUEST_GS_AR_BYTES:
+	case GUEST_LDTR_AR_BYTES:
+	case GUEST_TR_AR_BYTES:
+	case GUEST_ES_BASE:
+	case GUEST_CS_BASE:
+	case GUEST_SS_BASE:
+	case GUEST_DS_BASE:
+	case GUEST_FS_BASE:
+	case GUEST_GS_BASE:
+	case GUEST_LDTR_BASE:
+	case GUEST_TR_BASE:
+	case GUEST_GDTR_BASE:
+	case GUEST_IDTR_BASE:
+	case GUEST_PENDING_DBG_EXCEPTIONS:
+	case GUEST_BNDCFGS:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	vmcs12->guest_es_selector = vmcs_read16(GUEST_ES_SELECTOR);
+	vmcs12->guest_cs_selector = vmcs_read16(GUEST_CS_SELECTOR);
+	vmcs12->guest_ss_selector = vmcs_read16(GUEST_SS_SELECTOR);
+	vmcs12->guest_ds_selector = vmcs_read16(GUEST_DS_SELECTOR);
+	vmcs12->guest_fs_selector = vmcs_read16(GUEST_FS_SELECTOR);
+	vmcs12->guest_gs_selector = vmcs_read16(GUEST_GS_SELECTOR);
+	vmcs12->guest_ldtr_selector = vmcs_read16(GUEST_LDTR_SELECTOR);
+	vmcs12->guest_tr_selector = vmcs_read16(GUEST_TR_SELECTOR);
+	vmcs12->guest_es_limit = vmcs_read32(GUEST_ES_LIMIT);
+	vmcs12->guest_cs_limit = vmcs_read32(GUEST_CS_LIMIT);
+	vmcs12->guest_ss_limit = vmcs_read32(GUEST_SS_LIMIT);
+	vmcs12->guest_ds_limit = vmcs_read32(GUEST_DS_LIMIT);
+	vmcs12->guest_fs_limit = vmcs_read32(GUEST_FS_LIMIT);
+	vmcs12->guest_gs_limit = vmcs_read32(GUEST_GS_LIMIT);
+	vmcs12->guest_ldtr_limit = vmcs_read32(GUEST_LDTR_LIMIT);
+	vmcs12->guest_tr_limit = vmcs_read32(GUEST_TR_LIMIT);
+	vmcs12->guest_gdtr_limit = vmcs_read32(GUEST_GDTR_LIMIT);
+	vmcs12->guest_idtr_limit = vmcs_read32(GUEST_IDTR_LIMIT);
+	vmcs12->guest_es_ar_bytes = vmcs_read32(GUEST_ES_AR_BYTES);
+	vmcs12->guest_ds_ar_bytes = vmcs_read32(GUEST_DS_AR_BYTES);
+	vmcs12->guest_fs_ar_bytes = vmcs_read32(GUEST_FS_AR_BYTES);
+	vmcs12->guest_gs_ar_bytes = vmcs_read32(GUEST_GS_AR_BYTES);
+	vmcs12->guest_ldtr_ar_bytes = vmcs_read32(GUEST_LDTR_AR_BYTES);
+	vmcs12->guest_tr_ar_bytes = vmcs_read32(GUEST_TR_AR_BYTES);
+	vmcs12->guest_es_base = vmcs_readl(GUEST_ES_BASE);
+	vmcs12->guest_cs_base = vmcs_readl(GUEST_CS_BASE);
+	vmcs12->guest_ss_base = vmcs_readl(GUEST_SS_BASE);
+	vmcs12->guest_ds_base = vmcs_readl(GUEST_DS_BASE);
+	vmcs12->guest_fs_base = vmcs_readl(GUEST_FS_BASE);
+	vmcs12->guest_gs_base = vmcs_readl(GUEST_GS_BASE);
+	vmcs12->guest_ldtr_base = vmcs_readl(GUEST_LDTR_BASE);
+	vmcs12->guest_tr_base = vmcs_readl(GUEST_TR_BASE);
+	vmcs12->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE);
+	vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE);
+	vmcs12->guest_pending_dbg_exceptions =
+		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
+	if (kvm_mpx_supported())
+		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
+
+	vmx->nested.need_sync_vmcs02_to_vmcs12_rare = false;
+}
+
+static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int cpu;
+
+	if (!vmx->nested.need_sync_vmcs02_to_vmcs12_rare)
+		return;
+
+
+	WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01);
+
+	cpu = get_cpu();
+	vmx->loaded_vmcs = &vmx->nested.vmcs02;
+	vmx_vcpu_load(&vmx->vcpu, cpu);
+
+	sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
+
+	vmx->loaded_vmcs = &vmx->vmcs01;
+	vmx_vcpu_load(&vmx->vcpu, cpu);
+	put_cpu();
+}
+
+/*
+ * Update the guest state fields of vmcs12 to reflect changes that
+ * occurred while L2 was running. (The "IA-32e mode guest" bit of the
+ * VM-entry controls is also updated, since this is really a guest
+ * state bit.)
+ */
+static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (vmx->nested.hv_evmcs)
+		sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
+
+	vmx->nested.need_sync_vmcs02_to_vmcs12_rare = !vmx->nested.hv_evmcs;
+
+	vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
+	vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);
+
+	vmcs12->guest_rsp = kvm_rsp_read(vcpu);
+	vmcs12->guest_rip = kvm_rip_read(vcpu);
+	vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS);
+
+	vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES);
+	vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES);
+
+	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
+	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
+	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
+
+	vmcs12->guest_interruptibility_info =
+		vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
+
+	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
+		vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT;
+	else
+		vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE;
+
+	if (nested_cpu_has_preemption_timer(vmcs12) &&
+	    vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
+			vmcs12->vmx_preemption_timer_value =
+				vmx_get_preemption_timer_value(vcpu);
+
+	/*
+	 * In some cases (usually, nested EPT), L2 is allowed to change its
+	 * own CR3 without exiting. If it has changed it, we must keep it.
+	 * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined
+	 * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12.
+	 *
+	 * Additionally, restore L2's PDPTR to vmcs12.
+	 */
+	if (enable_ept) {
+		vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3);
+		if (nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) {
+			vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0);
+			vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1);
+			vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2);
+			vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
+		}
+	}
+
+	vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS);
+
+	if (nested_cpu_has_vid(vmcs12))
+		vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS);
+
+	vmcs12->vm_entry_controls =
+		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
+		(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+
+	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
+		kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7);
+
+	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER)
+		vmcs12->guest_ia32_efer = vcpu->arch.efer;
+}
+
+/*
+ * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits
+ * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12),
+ * and this function updates it to reflect the changes to the guest state while
+ * L2 was running (and perhaps made some exits which were handled directly by L0
+ * without going back to L1), and to reflect the exit reason.
+ * Note that we do not have to copy here all VMCS fields, just those that
+ * could have changed by the L2 guest or the exit - i.e., the guest-state and
+ * exit-information fields only. Other fields are modified by L1 with VMWRITE,
+ * which already writes to vmcs12 directly.
+ */
+static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
+			   u32 exit_reason, u32 exit_intr_info,
+			   unsigned long exit_qualification)
+{
+	/* update exit information fields: */
+	vmcs12->vm_exit_reason = exit_reason;
+	vmcs12->exit_qualification = exit_qualification;
+	vmcs12->vm_exit_intr_info = exit_intr_info;
+
+	vmcs12->idt_vectoring_info_field = 0;
+	vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+	vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+
+	if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) {
+		vmcs12->launch_state = 1;
+
+		/* vm_entry_intr_info_field is cleared on exit. Emulate this
+		 * instead of reading the real value. */
+		vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK;
+
+		/*
+		 * Transfer the event that L0 or L1 may wanted to inject into
+		 * L2 to IDT_VECTORING_INFO_FIELD.
+		 */
+		vmcs12_save_pending_event(vcpu, vmcs12);
+
+		/*
+		 * According to spec, there's no need to store the guest's
+		 * MSRs if the exit is due to a VM-entry failure that occurs
+		 * during or after loading the guest state. Since this exit
+		 * does not fall in that category, we need to save the MSRs.
+		 */
+		if (nested_vmx_store_msr(vcpu,
+					 vmcs12->vm_exit_msr_store_addr,
+					 vmcs12->vm_exit_msr_store_count))
+			nested_vmx_abort(vcpu,
+					 VMX_ABORT_SAVE_GUEST_MSR_FAIL);
+	}
+
+	/*
+	 * Drop what we picked up for L2 via vmx_complete_interrupts. It is
+	 * preserved above and would only end up incorrectly in L1.
+	 */
+	vcpu->arch.nmi_injected = false;
+	kvm_clear_exception_queue(vcpu);
+	kvm_clear_interrupt_queue(vcpu);
+}
+
+/*
+ * A part of what we need to when the nested L2 guest exits and we want to
+ * run its L1 parent, is to reset L1's guest state to the host state specified
+ * in vmcs12.
+ * This function is to be called not only on normal nested exit, but also on
+ * a nested entry failure, as explained in Intel's spec, 3B.23.7 ("VM-Entry
+ * Failures During or After Loading Guest State").
+ * This function should be called when the active VMCS is L1's (vmcs01).
+ */
+static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
+				   struct vmcs12 *vmcs12)
+{
+	struct kvm_segment seg;
+	u32 entry_failure_code;
+
+	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
+		vcpu->arch.efer = vmcs12->host_ia32_efer;
+	else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
+		vcpu->arch.efer |= (EFER_LMA | EFER_LME);
+	else
+		vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
+	vmx_set_efer(vcpu, vcpu->arch.efer);
+
+	kvm_rsp_write(vcpu, vmcs12->host_rsp);
+	kvm_rip_write(vcpu, vmcs12->host_rip);
+	vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
+	vmx_set_interrupt_shadow(vcpu, 0);
+
+	/*
+	 * Note that calling vmx_set_cr0 is important, even if cr0 hasn't
+	 * actually changed, because vmx_set_cr0 refers to efer set above.
+	 *
+	 * CR0_GUEST_HOST_MASK is already set in the original vmcs01
+	 * (KVM doesn't change it);
+	 */
+	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vmx_set_cr0(vcpu, vmcs12->host_cr0);
+
+	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
+	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
+	vmx_set_cr4(vcpu, vmcs12->host_cr4);
+
+	nested_ept_uninit_mmu_context(vcpu);
+
+	/*
+	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
+	 * couldn't have changed.
+	 */
+	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
+
+	if (!enable_ept)
+		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+
+	/*
+	 * If vmcs01 doesn't use VPID, CPU flushes TLB on every
+	 * VMEntry/VMExit. Thus, no need to flush TLB.
+	 *
+	 * If vmcs12 doesn't use VPID, L1 expects TLB to be
+	 * flushed on every VMEntry/VMExit.
+	 *
+	 * Otherwise, we can preserve TLB entries as long as we are
+	 * able to tag L1 TLB entries differently than L2 TLB entries.
+	 *
+	 * If vmcs12 uses EPT, we need to execute this flush on EPTP01
+	 * and therefore we request the TLB flush to happen only after VMCS EPTP
+	 * has been set by KVM_REQ_LOAD_CR3.
+	 */
+	if (enable_vpid &&
+	    (!nested_cpu_has_vpid(vmcs12) || !nested_has_guest_tlb_tag(vcpu))) {
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+	}
+
+	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
+	vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
+	vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
+	vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
+	vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
+	vmcs_write32(GUEST_IDTR_LIMIT, 0xFFFF);
+	vmcs_write32(GUEST_GDTR_LIMIT, 0xFFFF);
+
+	/* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1.  */
+	if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS)
+		vmcs_write64(GUEST_BNDCFGS, 0);
+
+	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) {
+		vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
+		vcpu->arch.pat = vmcs12->host_ia32_pat;
+	}
+	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+		vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
+			vmcs12->host_ia32_perf_global_ctrl);
+
+	/* Set L1 segment info according to Intel SDM
+	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
+	seg = (struct kvm_segment) {
+		.base = 0,
+		.limit = 0xFFFFFFFF,
+		.selector = vmcs12->host_cs_selector,
+		.type = 11,
+		.present = 1,
+		.s = 1,
+		.g = 1
+	};
+	if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
+		seg.l = 1;
+	else
+		seg.db = 1;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_CS);
+	seg = (struct kvm_segment) {
+		.base = 0,
+		.limit = 0xFFFFFFFF,
+		.type = 3,
+		.present = 1,
+		.s = 1,
+		.db = 1,
+		.g = 1
+	};
+	seg.selector = vmcs12->host_ds_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_DS);
+	seg.selector = vmcs12->host_es_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_ES);
+	seg.selector = vmcs12->host_ss_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_SS);
+	seg.selector = vmcs12->host_fs_selector;
+	seg.base = vmcs12->host_fs_base;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_FS);
+	seg.selector = vmcs12->host_gs_selector;
+	seg.base = vmcs12->host_gs_base;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_GS);
+	seg = (struct kvm_segment) {
+		.base = vmcs12->host_tr_base,
+		.limit = 0x67,
+		.selector = vmcs12->host_tr_selector,
+		.type = 11,
+		.present = 1
+	};
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_TR);
+
+	kvm_set_dr(vcpu, 7, 0x400);
+	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+
+	if (cpu_has_vmx_msr_bitmap())
+		vmx_update_msr_bitmap(vcpu);
+
+	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
+				vmcs12->vm_exit_msr_load_count))
+		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
+}
+
+static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
+{
+	struct shared_msr_entry *efer_msr;
+	unsigned int i;
+
+	if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER)
+		return vmcs_read64(GUEST_IA32_EFER);
+
+	if (cpu_has_load_ia32_efer())
+		return host_efer;
+
+	for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) {
+		if (vmx->msr_autoload.guest.val[i].index == MSR_EFER)
+			return vmx->msr_autoload.guest.val[i].value;
+	}
+
+	efer_msr = find_msr_entry(vmx, MSR_EFER);
+	if (efer_msr)
+		return efer_msr->data;
+
+	return host_efer;
+}
+
+static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmx_msr_entry g, h;
+	gpa_t gpa;
+	u32 i, j;
+
+	vcpu->arch.pat = vmcs_read64(GUEST_IA32_PAT);
+
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) {
+		/*
+		 * L1's host DR7 is lost if KVM_GUESTDBG_USE_HW_BP is set
+		 * as vmcs01.GUEST_DR7 contains a userspace defined value
+		 * and vcpu->arch.dr7 is not squirreled away before the
+		 * nested VMENTER (not worth adding a variable in nested_vmx).
+		 */
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+			kvm_set_dr(vcpu, 7, DR7_FIXED_1);
+		else
+			WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
+	}
+
+	/*
+	 * Note that calling vmx_set_{efer,cr0,cr4} is important as they
+	 * handle a variety of side effects to KVM's software model.
+	 */
+	vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
+
+	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
+
+	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
+	vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
+
+	nested_ept_uninit_mmu_context(vcpu);
+	vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+	/*
+	 * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
+	 * from vmcs01 (if necessary).  The PDPTRs are not loaded on
+	 * VMFail, like everything else we just need to ensure our
+	 * software model is up-to-date.
+	 */
+	if (enable_ept)
+		ept_save_pdptrs(vcpu);
+
+	kvm_mmu_reset_context(vcpu);
+
+	if (cpu_has_vmx_msr_bitmap())
+		vmx_update_msr_bitmap(vcpu);
+
+	/*
+	 * This nasty bit of open coding is a compromise between blindly
+	 * loading L1's MSRs using the exit load lists (incorrect emulation
+	 * of VMFail), leaving the nested VM's MSRs in the software model
+	 * (incorrect behavior) and snapshotting the modified MSRs (too
+	 * expensive since the lists are unbound by hardware).  For each
+	 * MSR that was (prematurely) loaded from the nested VMEntry load
+	 * list, reload it from the exit load list if it exists and differs
+	 * from the guest value.  The intent is to stuff host state as
+	 * silently as possible, not to fully process the exit load list.
+	 */
+	for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) {
+		gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g));
+		if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) {
+			pr_debug_ratelimited(
+				"%s read MSR index failed (%u, 0x%08llx)\n",
+				__func__, i, gpa);
+			goto vmabort;
+		}
+
+		for (j = 0; j < vmcs12->vm_exit_msr_load_count; j++) {
+			gpa = vmcs12->vm_exit_msr_load_addr + (j * sizeof(h));
+			if (kvm_vcpu_read_guest(vcpu, gpa, &h, sizeof(h))) {
+				pr_debug_ratelimited(
+					"%s read MSR failed (%u, 0x%08llx)\n",
+					__func__, j, gpa);
+				goto vmabort;
+			}
+			if (h.index != g.index)
+				continue;
+			if (h.value == g.value)
+				break;
+
+			if (nested_vmx_load_msr_check(vcpu, &h)) {
+				pr_debug_ratelimited(
+					"%s check failed (%u, 0x%x, 0x%x)\n",
+					__func__, j, h.index, h.reserved);
+				goto vmabort;
+			}
+
+			if (kvm_set_msr(vcpu, h.index, h.value)) {
+				pr_debug_ratelimited(
+					"%s WRMSR failed (%u, 0x%x, 0x%llx)\n",
+					__func__, j, h.index, h.value);
+				goto vmabort;
+			}
+		}
+	}
+
+	return;
+
+vmabort:
+	nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
+}
+
+/*
+ * Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1
+ * and modify vmcs12 to make it see what it would expect to see there if
+ * L2 was its real guest. Must only be called when in L2 (is_guest_mode())
+ */
+void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
+		       u32 exit_intr_info, unsigned long exit_qualification)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	/* trying to cancel vmlaunch/vmresume is a bug */
+	WARN_ON_ONCE(vmx->nested.nested_run_pending);
+
+	leave_guest_mode(vcpu);
+
+	if (nested_cpu_has_preemption_timer(vmcs12))
+		hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer);
+
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+
+	if (likely(!vmx->fail)) {
+		sync_vmcs02_to_vmcs12(vcpu, vmcs12);
+
+		if (exit_reason != -1)
+			prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
+				       exit_qualification);
+
+		/*
+		 * Must happen outside of sync_vmcs02_to_vmcs12() as it will
+		 * also be used to capture vmcs12 cache as part of
+		 * capturing nVMX state for snapshot (migration).
+		 *
+		 * Otherwise, this flush will dirty guest memory at a
+		 * point it is already assumed by user-space to be
+		 * immutable.
+		 */
+		nested_flush_cached_shadow_vmcs12(vcpu, vmcs12);
+	} else {
+		/*
+		 * The only expected VM-instruction error is "VM entry with
+		 * invalid control field(s)." Anything else indicates a
+		 * problem with L0.  And we should never get here with a
+		 * VMFail of any type if early consistency checks are enabled.
+		 */
+		WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
+			     VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+		WARN_ON_ONCE(nested_early_check);
+	}
+
+	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+
+	/* Update any VMCS fields that might have changed while L2 ran */
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
+	if (kvm_has_tsc_control)
+		decache_tsc_multiplier(vmx);
+
+	if (vmx->nested.change_vmcs01_virtual_apic_mode) {
+		vmx->nested.change_vmcs01_virtual_apic_mode = false;
+		vmx_set_virtual_apic_mode(vcpu);
+	} else if (!nested_cpu_has_ept(vmcs12) &&
+		   nested_cpu_has2(vmcs12,
+				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		vmx_flush_tlb(vcpu, true);
+	}
+
+	/* Unpin physical memory we referred to in vmcs02 */
+	if (vmx->nested.apic_access_page) {
+		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		vmx->nested.apic_access_page = NULL;
+	}
+	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
+	vmx->nested.pi_desc = NULL;
+
+	/*
+	 * We are now running in L2, mmu_notifier will force to reload the
+	 * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1.
+	 */
+	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
+
+	if ((exit_reason != -1) && (enable_shadow_vmcs || vmx->nested.hv_evmcs))
+		vmx->nested.need_vmcs12_to_shadow_sync = true;
+
+	/* in case we halted in L2 */
+	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+	if (likely(!vmx->fail)) {
+		/*
+		 * TODO: SDM says that with acknowledge interrupt on
+		 * exit, bit 31 of the VM-exit interrupt information
+		 * (valid interrupt) is always set to 1 on
+		 * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't
+		 * need kvm_cpu_has_interrupt().  See the commit
+		 * message for details.
+		 */
+		if (nested_exit_intr_ack_set(vcpu) &&
+		    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+		    kvm_cpu_has_interrupt(vcpu)) {
+			int irq = kvm_cpu_get_interrupt(vcpu);
+			WARN_ON(irq < 0);
+			vmcs12->vm_exit_intr_info = irq |
+				INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
+		}
+
+		if (exit_reason != -1)
+			trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
+						       vmcs12->exit_qualification,
+						       vmcs12->idt_vectoring_info_field,
+						       vmcs12->vm_exit_intr_info,
+						       vmcs12->vm_exit_intr_error_code,
+						       KVM_ISA_VMX);
+
+		load_vmcs12_host_state(vcpu, vmcs12);
+
+		return;
+	}
+
+	/*
+	 * After an early L2 VM-entry failure, we're now back
+	 * in L1 which thinks it just finished a VMLAUNCH or
+	 * VMRESUME instruction, so we need to set the failure
+	 * flag and the VM-instruction error field of the VMCS
+	 * accordingly, and skip the emulated instruction.
+	 */
+	(void)nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+	/*
+	 * Restore L1's host state to KVM's software model.  We're here
+	 * because a consistency check was caught by hardware, which
+	 * means some amount of guest state has been propagated to KVM's
+	 * model and needs to be unwound to the host's state.
+	 */
+	nested_vmx_restore_host_state(vcpu);
+
+	vmx->fail = 0;
+}
+
+/*
+ * Decode the memory-address operand of a vmx instruction, as recorded on an
+ * exit caused by such an instruction (run by a guest hypervisor).
+ * On success, returns 0. When the operand is invalid, returns 1 and throws
+ * #UD or #GP.
+ */
+int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
+			u32 vmx_instruction_info, bool wr, int len, gva_t *ret)
+{
+	gva_t off;
+	bool exn;
+	struct kvm_segment s;
+
+	/*
+	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
+	 * Execution", on an exit, vmx_instruction_info holds most of the
+	 * addressing components of the operand. Only the displacement part
+	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
+	 * For how an actual address is calculated from all these components,
+	 * refer to Vol. 1, "Operand Addressing".
+	 */
+	int  scaling = vmx_instruction_info & 3;
+	int  addr_size = (vmx_instruction_info >> 7) & 7;
+	bool is_reg = vmx_instruction_info & (1u << 10);
+	int  seg_reg = (vmx_instruction_info >> 15) & 7;
+	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
+	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
+	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
+	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));
+
+	if (is_reg) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	/* Addr = segment_base + offset */
+	/* offset = base + [index * scale] + displacement */
+	off = exit_qualification; /* holds the displacement */
+	if (addr_size == 1)
+		off = (gva_t)sign_extend64(off, 31);
+	else if (addr_size == 0)
+		off = (gva_t)sign_extend64(off, 15);
+	if (base_is_valid)
+		off += kvm_register_read(vcpu, base_reg);
+	if (index_is_valid)
+		off += kvm_register_read(vcpu, index_reg)<<scaling;
+	vmx_get_segment(vcpu, &s, seg_reg);
+
+	/*
+	 * The effective address, i.e. @off, of a memory operand is truncated
+	 * based on the address size of the instruction.  Note that this is
+	 * the *effective address*, i.e. the address prior to accounting for
+	 * the segment's base.
+	 */
+	if (addr_size == 1) /* 32 bit */
+		off &= 0xffffffff;
+	else if (addr_size == 0) /* 16 bit */
+		off &= 0xffff;
+
+	/* Checks for #GP/#SS exceptions. */
+	exn = false;
+	if (is_long_mode(vcpu)) {
+		/*
+		 * The virtual/linear address is never truncated in 64-bit
+		 * mode, e.g. a 32-bit address size can yield a 64-bit virtual
+		 * address when using FS/GS with a non-zero base.
+		 */
+		if (seg_reg == VCPU_SREG_FS || seg_reg == VCPU_SREG_GS)
+			*ret = s.base + off;
+		else
+			*ret = off;
+
+		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
+		 * non-canonical form. This is the only check on the memory
+		 * destination for long mode!
+		 */
+		exn = is_noncanonical_address(*ret, vcpu);
+	} else {
+		/*
+		 * When not in long mode, the virtual/linear address is
+		 * unconditionally truncated to 32 bits regardless of the
+		 * address size.
+		 */
+		*ret = (s.base + off) & 0xffffffff;
+
+		/* Protected mode: apply checks for segment validity in the
+		 * following order:
+		 * - segment type check (#GP(0) may be thrown)
+		 * - usability check (#GP(0)/#SS(0))
+		 * - limit check (#GP(0)/#SS(0))
+		 */
+		if (wr)
+			/* #GP(0) if the destination operand is located in a
+			 * read-only data segment or any code segment.
+			 */
+			exn = ((s.type & 0xa) == 0 || (s.type & 8));
+		else
+			/* #GP(0) if the source operand is located in an
+			 * execute-only code segment
+			 */
+			exn = ((s.type & 0xa) == 8);
+		if (exn) {
+			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+			return 1;
+		}
+		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
+		 */
+		exn = (s.unusable != 0);
+
+		/*
+		 * Protected mode: #GP(0)/#SS(0) if the memory operand is
+		 * outside the segment limit.  All CPUs that support VMX ignore
+		 * limit checks for flat segments, i.e. segments with base==0,
+		 * limit==0xffffffff and of type expand-up data or code.
+		 */
+		if (!(s.base == 0 && s.limit == 0xffffffff &&
+		     ((s.type & 8) || !(s.type & 4))))
+			exn = exn || ((u64)off + len - 1 > s.limit);
+	}
+	if (exn) {
+		kvm_queue_exception_e(vcpu,
+				      seg_reg == VCPU_SREG_SS ?
+						SS_VECTOR : GP_VECTOR,
+				      0);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
+{
+	gva_t gva;
+	struct x86_exception e;
+
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+				vmcs_read32(VMX_INSTRUCTION_INFO), false,
+				sizeof(*vmpointer), &gva))
+		return 1;
+
+	if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Allocate a shadow VMCS and associate it with the currently loaded
+ * VMCS, unless such a shadow VMCS already exists. The newly allocated
+ * VMCS is also VMCLEARed, so that it is ready for use.
+ */
+static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs;
+
+	/*
+	 * We should allocate a shadow vmcs for vmcs01 only when L1
+	 * executes VMXON and free it when L1 executes VMXOFF.
+	 * As it is invalid to execute VMXON twice, we shouldn't reach
+	 * here when vmcs01 already have an allocated shadow vmcs.
+	 */
+	WARN_ON(loaded_vmcs == &vmx->vmcs01 && loaded_vmcs->shadow_vmcs);
+
+	if (!loaded_vmcs->shadow_vmcs) {
+		loaded_vmcs->shadow_vmcs = alloc_vmcs(true);
+		if (loaded_vmcs->shadow_vmcs)
+			vmcs_clear(loaded_vmcs->shadow_vmcs);
+	}
+	return loaded_vmcs->shadow_vmcs;
+}
+
+static int enter_vmx_operation(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int r;
+
+	r = alloc_loaded_vmcs(&vmx->nested.vmcs02);
+	if (r < 0)
+		goto out_vmcs02;
+
+	vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT);
+	if (!vmx->nested.cached_vmcs12)
+		goto out_cached_vmcs12;
+
+	vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT);
+	if (!vmx->nested.cached_shadow_vmcs12)
+		goto out_cached_shadow_vmcs12;
+
+	if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu))
+		goto out_shadow_vmcs;
+
+	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL_PINNED);
+	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
+
+	vmx->nested.vpid02 = allocate_vpid();
+
+	vmx->nested.vmcs02_initialized = false;
+	vmx->nested.vmxon = true;
+
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		vmx->pt_desc.guest.ctl = 0;
+		pt_update_intercept_for_msr(vmx);
+	}
+
+	return 0;
+
+out_shadow_vmcs:
+	kfree(vmx->nested.cached_shadow_vmcs12);
+
+out_cached_shadow_vmcs12:
+	kfree(vmx->nested.cached_vmcs12);
+
+out_cached_vmcs12:
+	free_loaded_vmcs(&vmx->nested.vmcs02);
+
+out_vmcs02:
+	return -ENOMEM;
+}
+
+/*
+ * Emulate the VMXON instruction.
+ * Currently, we just remember that VMX is active, and do not save or even
+ * inspect the argument to VMXON (the so-called "VMXON pointer") because we
+ * do not currently need to store anything in that guest-allocated memory
+ * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their
+ * argument is different from the VMXON pointer (which the spec says they do).
+ */
+static int handle_vmon(struct kvm_vcpu *vcpu)
+{
+	int ret;
+	gpa_t vmptr;
+	uint32_t revision;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
+		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+
+	/*
+	 * The Intel VMX Instruction Reference lists a bunch of bits that are
+	 * prerequisite to running VMXON, most notably cr4.VMXE must be set to
+	 * 1 (see vmx_set_cr4() for when we allow the guest to set this).
+	 * Otherwise, we should fail with #UD.  But most faulting conditions
+	 * have already been checked by hardware, prior to the VM-exit for
+	 * VMXON.  We do test guest cr4.VMXE because processor CR4 always has
+	 * that bit set to 1 in non-root mode.
+	 */
+	if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	/* CPL=0 must be checked manually. */
+	if (vmx_get_cpl(vcpu)) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	if (vmx->nested.vmxon)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
+
+	if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
+			!= VMXON_NEEDED_FEATURES) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
+		return 1;
+
+	/*
+	 * SDM 3: 24.11.5
+	 * The first 4 bytes of VMXON region contain the supported
+	 * VMCS revision identifier
+	 *
+	 * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
+	 * which replaces physical address width with 32
+	 */
+	if (!page_address_valid(vcpu, vmptr))
+		return nested_vmx_failInvalid(vcpu);
+
+	if (kvm_read_guest(vcpu->kvm, vmptr, &revision, sizeof(revision)) ||
+	    revision != VMCS12_REVISION)
+		return nested_vmx_failInvalid(vcpu);
+
+	vmx->nested.vmxon_ptr = vmptr;
+	ret = enter_vmx_operation(vcpu);
+	if (ret)
+		return ret;
+
+	return nested_vmx_succeed(vcpu);
+}
+
+static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (vmx->nested.current_vmptr == -1ull)
+		return;
+
+	copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));
+
+	if (enable_shadow_vmcs) {
+		/* copy to memory all shadowed fields in case
+		   they were modified */
+		copy_shadow_to_vmcs12(vmx);
+		vmx_disable_shadow_vmcs(vmx);
+	}
+	vmx->nested.posted_intr_nv = -1;
+
+	/* Flush VMCS12 to guest memory */
+	kvm_vcpu_write_guest_page(vcpu,
+				  vmx->nested.current_vmptr >> PAGE_SHIFT,
+				  vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
+
+	kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
+	vmx->nested.current_vmptr = -1ull;
+}
+
+/* Emulate the VMXOFF instruction */
+static int handle_vmoff(struct kvm_vcpu *vcpu)
+{
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	free_nested(vcpu);
+
+	/* Process a latched INIT during time CPU was in VMX operation */
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	return nested_vmx_succeed(vcpu);
+}
+
+/* Emulate the VMCLEAR instruction */
+static int handle_vmclear(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 zero = 0;
+	gpa_t vmptr;
+	u64 evmcs_gpa;
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
+		return 1;
+
+	if (!page_address_valid(vcpu, vmptr))
+		return nested_vmx_failValid(vcpu,
+			VMXERR_VMCLEAR_INVALID_ADDRESS);
+
+	if (vmptr == vmx->nested.vmxon_ptr)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_VMCLEAR_VMXON_POINTER);
+
+	/*
+	 * When Enlightened VMEntry is enabled on the calling CPU we treat
+	 * memory area pointer by vmptr as Enlightened VMCS (as there's no good
+	 * way to distinguish it from VMCS12) and we must not corrupt it by
+	 * writing to the non-existent 'launch_state' field. The area doesn't
+	 * have to be the currently active EVMCS on the calling CPU and there's
+	 * nothing KVM has to do to transition it from 'active' to 'non-active'
+	 * state. It is possible that the area will stay mapped as
+	 * vmx->nested.hv_evmcs but this shouldn't be a problem.
+	 */
+	if (likely(!vmx->nested.enlightened_vmcs_enabled ||
+		   !nested_enlightened_vmentry(vcpu, &evmcs_gpa))) {
+		if (vmptr == vmx->nested.current_vmptr)
+			nested_release_vmcs12(vcpu);
+
+		kvm_vcpu_write_guest(vcpu,
+				     vmptr + offsetof(struct vmcs12,
+						      launch_state),
+				     &zero, sizeof(zero));
+	}
+
+	return nested_vmx_succeed(vcpu);
+}
+
+static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);
+
+/* Emulate the VMLAUNCH instruction */
+static int handle_vmlaunch(struct kvm_vcpu *vcpu)
+{
+	return nested_vmx_run(vcpu, true);
+}
+
+/* Emulate the VMRESUME instruction */
+static int handle_vmresume(struct kvm_vcpu *vcpu)
+{
+
+	return nested_vmx_run(vcpu, false);
+}
+
+static int handle_vmread(struct kvm_vcpu *vcpu)
+{
+	unsigned long field;
+	u64 field_value;
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	int len;
+	gva_t gva = 0;
+	struct vmcs12 *vmcs12;
+	struct x86_exception e;
+	short offset;
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (to_vmx(vcpu)->nested.current_vmptr == -1ull)
+		return nested_vmx_failInvalid(vcpu);
+
+	if (!is_guest_mode(vcpu))
+		vmcs12 = get_vmcs12(vcpu);
+	else {
+		/*
+		 * When vmcs->vmcs_link_pointer is -1ull, any VMREAD
+		 * to shadowed-field sets the ALU flags for VMfailInvalid.
+		 */
+		if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
+			return nested_vmx_failInvalid(vcpu);
+		vmcs12 = get_shadow_vmcs12(vcpu);
+	}
+
+	/* Decode instruction info and find the field to read */
+	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+
+	offset = vmcs_field_to_offset(field);
+	if (offset < 0)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
+	if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field))
+		copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
+
+	/* Read the field, zero-extended to a u64 field_value */
+	field_value = vmcs12_read_any(vmcs12, field, offset);
+
+	/*
+	 * Now copy part of this value to register or memory, as requested.
+	 * Note that the number of bits actually copied is 32 or 64 depending
+	 * on the guest's mode (32 or 64 bit), not on the given field's length.
+	 */
+	if (vmx_instruction_info & (1u << 10)) {
+		kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf),
+			field_value);
+	} else {
+		len = is_64_bit_mode(vcpu) ? 8 : 4;
+		if (get_vmx_mem_address(vcpu, exit_qualification,
+				vmx_instruction_info, true, len, &gva))
+			return 1;
+		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
+		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e))
+			kvm_inject_page_fault(vcpu, &e);
+	}
+
+	return nested_vmx_succeed(vcpu);
+}
+
+static bool is_shadow_field_rw(unsigned long field)
+{
+	switch (field) {
+#define SHADOW_FIELD_RW(x, y) case x:
+#include "vmcs_shadow_fields.h"
+		return true;
+	default:
+		break;
+	}
+	return false;
+}
+
+static bool is_shadow_field_ro(unsigned long field)
+{
+	switch (field) {
+#define SHADOW_FIELD_RO(x, y) case x:
+#include "vmcs_shadow_fields.h"
+		return true;
+	default:
+		break;
+	}
+	return false;
+}
+
+static int handle_vmwrite(struct kvm_vcpu *vcpu)
+{
+	unsigned long field;
+	int len;
+	gva_t gva;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+
+	/* The value to write might be 32 or 64 bits, depending on L1's long
+	 * mode, and eventually we need to write that into a field of several
+	 * possible lengths. The code below first zero-extends the value to 64
+	 * bit (field_value), and then copies only the appropriate number of
+	 * bits into the vmcs12 field.
+	 */
+	u64 field_value = 0;
+	struct x86_exception e;
+	struct vmcs12 *vmcs12;
+	short offset;
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (vmx->nested.current_vmptr == -1ull)
+		return nested_vmx_failInvalid(vcpu);
+
+	if (vmx_instruction_info & (1u << 10))
+		field_value = kvm_register_readl(vcpu,
+			(((vmx_instruction_info) >> 3) & 0xf));
+	else {
+		len = is_64_bit_mode(vcpu) ? 8 : 4;
+		if (get_vmx_mem_address(vcpu, exit_qualification,
+				vmx_instruction_info, false, len, &gva))
+			return 1;
+		if (kvm_read_guest_virt(vcpu, gva, &field_value, len, &e)) {
+			kvm_inject_page_fault(vcpu, &e);
+			return 1;
+		}
+	}
+
+
+	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+	/*
+	 * If the vCPU supports "VMWRITE to any supported field in the
+	 * VMCS," then the "read-only" fields are actually read/write.
+	 */
+	if (vmcs_field_readonly(field) &&
+	    !nested_cpu_has_vmwrite_any_field(vcpu))
+		return nested_vmx_failValid(vcpu,
+			VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
+
+	if (!is_guest_mode(vcpu)) {
+		vmcs12 = get_vmcs12(vcpu);
+
+		/*
+		 * Ensure vmcs12 is up-to-date before any VMWRITE that dirties
+		 * vmcs12, else we may crush a field or consume a stale value.
+		 */
+		if (!is_shadow_field_rw(field))
+			copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
+	} else {
+		/*
+		 * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE
+		 * to shadowed-field sets the ALU flags for VMfailInvalid.
+		 */
+		if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
+			return nested_vmx_failInvalid(vcpu);
+		vmcs12 = get_shadow_vmcs12(vcpu);
+	}
+
+	offset = vmcs_field_to_offset(field);
+	if (offset < 0)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
+	/*
+	 * Some Intel CPUs intentionally drop the reserved bits of the AR byte
+	 * fields on VMWRITE.  Emulate this behavior to ensure consistent KVM
+	 * behavior regardless of the underlying hardware, e.g. if an AR_BYTE
+	 * field is intercepted for VMWRITE but not VMREAD (in L1), then VMREAD
+	 * from L1 will return a different value than VMREAD from L2 (L1 sees
+	 * the stripped down value, L2 sees the full value as stored by KVM).
+	 */
+	if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES)
+		field_value &= 0x1f0ff;
+
+	vmcs12_write_any(vmcs12, field, offset, field_value);
+
+	/*
+	 * Do not track vmcs12 dirty-state if in guest-mode as we actually
+	 * dirty shadow vmcs12 instead of vmcs12.  Fields that can be updated
+	 * by L1 without a vmexit are always updated in the vmcs02, i.e. don't
+	 * "dirty" vmcs12, all others go down the prepare_vmcs02() slow path.
+	 */
+	if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) {
+		/*
+		 * L1 can read these fields without exiting, ensure the
+		 * shadow VMCS is up-to-date.
+		 */
+		if (enable_shadow_vmcs && is_shadow_field_ro(field)) {
+			preempt_disable();
+			vmcs_load(vmx->vmcs01.shadow_vmcs);
+
+			__vmcs_writel(field, field_value);
+
+			vmcs_clear(vmx->vmcs01.shadow_vmcs);
+			vmcs_load(vmx->loaded_vmcs->vmcs);
+			preempt_enable();
+		}
+		vmx->nested.dirty_vmcs12 = true;
+	}
+
+	return nested_vmx_succeed(vcpu);
+}
+
+static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
+{
+	vmx->nested.current_vmptr = vmptr;
+	if (enable_shadow_vmcs) {
+		secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
+		vmcs_write64(VMCS_LINK_POINTER,
+			     __pa(vmx->vmcs01.shadow_vmcs));
+		vmx->nested.need_vmcs12_to_shadow_sync = true;
+	}
+	vmx->nested.dirty_vmcs12 = true;
+}
+
+/* Emulate the VMPTRLD instruction */
+static int handle_vmptrld(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	gpa_t vmptr;
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
+		return 1;
+
+	if (!page_address_valid(vcpu, vmptr))
+		return nested_vmx_failValid(vcpu,
+			VMXERR_VMPTRLD_INVALID_ADDRESS);
+
+	if (vmptr == vmx->nested.vmxon_ptr)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_VMPTRLD_VMXON_POINTER);
+
+	/* Forbid normal VMPTRLD if Enlightened version was used */
+	if (vmx->nested.hv_evmcs)
+		return 1;
+
+	if (vmx->nested.current_vmptr != vmptr) {
+		struct kvm_host_map map;
+		struct vmcs12 *new_vmcs12;
+
+		if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmptr), &map)) {
+			/*
+			 * Reads from an unbacked page return all 1s,
+			 * which means that the 32 bits located at the
+			 * given physical address won't match the required
+			 * VMCS12_REVISION identifier.
+			 */
+			return nested_vmx_failValid(vcpu,
+				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+		}
+
+		new_vmcs12 = map.hva;
+
+		if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
+		    (new_vmcs12->hdr.shadow_vmcs &&
+		     !nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
+			kvm_vcpu_unmap(vcpu, &map, false);
+			return nested_vmx_failValid(vcpu,
+				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+		}
+
+		nested_release_vmcs12(vcpu);
+
+		/*
+		 * Load VMCS12 from guest memory since it is not already
+		 * cached.
+		 */
+		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
+		kvm_vcpu_unmap(vcpu, &map, false);
+
+		set_current_vmptr(vmx, vmptr);
+	}
+
+	return nested_vmx_succeed(vcpu);
+}
+
+/* Emulate the VMPTRST instruction */
+static int handle_vmptrst(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION);
+	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
+	struct x86_exception e;
+	gva_t gva;
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (unlikely(to_vmx(vcpu)->nested.hv_evmcs))
+		return 1;
+
+	if (get_vmx_mem_address(vcpu, exit_qual, instr_info,
+				true, sizeof(gpa_t), &gva))
+		return 1;
+	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
+	if (kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
+					sizeof(gpa_t), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+	return nested_vmx_succeed(vcpu);
+}
+
+/* Emulate the INVEPT instruction */
+static int handle_invept(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 vmx_instruction_info, types;
+	unsigned long type;
+	gva_t gva;
+	struct x86_exception e;
+	struct {
+		u64 eptp, gpa;
+	} operand;
+
+	if (!(vmx->nested.msrs.secondary_ctls_high &
+	      SECONDARY_EXEC_ENABLE_EPT) ||
+	    !(vmx->nested.msrs.ept_caps & VMX_EPT_INVEPT_BIT)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
+
+	types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
+
+	if (type >= 32 || !(types & (1 << type)))
+		return nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+
+	/* According to the Intel VMX instruction reference, the memory
+	 * operand is read even if it isn't needed (e.g., for type==global)
+	 */
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmx_instruction_info, false, sizeof(operand), &gva))
+		return 1;
+	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	switch (type) {
+	case VMX_EPT_EXTENT_GLOBAL:
+	case VMX_EPT_EXTENT_CONTEXT:
+	/*
+	 * TODO: Sync the necessary shadow EPT roots here, rather than
+	 * at the next emulated VM-entry.
+	 */
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
+
+	return nested_vmx_succeed(vcpu);
+}
+
+static int handle_invvpid(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 vmx_instruction_info;
+	unsigned long type, types;
+	gva_t gva;
+	struct x86_exception e;
+	struct {
+		u64 vpid;
+		u64 gla;
+	} operand;
+	u16 vpid02;
+
+	if (!(vmx->nested.msrs.secondary_ctls_high &
+	      SECONDARY_EXEC_ENABLE_VPID) ||
+			!(vmx->nested.msrs.vpid_caps & VMX_VPID_INVVPID_BIT)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
+
+	types = (vmx->nested.msrs.vpid_caps &
+			VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
+
+	if (type >= 32 || !(types & (1 << type)))
+		return nested_vmx_failValid(vcpu,
+			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+
+	/* according to the intel vmx instruction reference, the memory
+	 * operand is read even if it isn't needed (e.g., for type==global)
+	 */
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmx_instruction_info, false, sizeof(operand), &gva))
+		return 1;
+	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+	if (operand.vpid >> 16)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+
+	vpid02 = nested_get_vpid02(vcpu);
+	switch (type) {
+	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
+		if (!operand.vpid ||
+		    is_noncanonical_address(operand.gla, vcpu))
+			return nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		if (cpu_has_vmx_invvpid_individual_addr()) {
+			__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR,
+				vpid02, operand.gla);
+		} else
+			__vmx_flush_tlb(vcpu, vpid02, false);
+		break;
+	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
+	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
+		if (!operand.vpid)
+			return nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		__vmx_flush_tlb(vcpu, vpid02, false);
+		break;
+	case VMX_VPID_EXTENT_ALL_CONTEXT:
+		__vmx_flush_tlb(vcpu, vpid02, false);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
+	return nested_vmx_succeed(vcpu);
+}
+
+static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
+				     struct vmcs12 *vmcs12)
+{
+	u32 index = kvm_rcx_read(vcpu);
+	u64 address;
+	bool accessed_dirty;
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
+	if (!nested_cpu_has_eptp_switching(vmcs12) ||
+	    !nested_cpu_has_ept(vmcs12))
+		return 1;
+
+	if (index >= VMFUNC_EPTP_ENTRIES)
+		return 1;
+
+
+	if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT,
+				     &address, index * 8, 8))
+		return 1;
+
+	accessed_dirty = !!(address & VMX_EPTP_AD_ENABLE_BIT);
+
+	/*
+	 * If the (L2) guest does a vmfunc to the currently
+	 * active ept pointer, we don't have to do anything else
+	 */
+	if (vmcs12->ept_pointer != address) {
+		if (!valid_ept_address(vcpu, address))
+			return 1;
+
+		kvm_mmu_unload(vcpu);
+		mmu->ept_ad = accessed_dirty;
+		mmu->mmu_role.base.ad_disabled = !accessed_dirty;
+		vmcs12->ept_pointer = address;
+		/*
+		 * TODO: Check what's the correct approach in case
+		 * mmu reload fails. Currently, we just let the next
+		 * reload potentially fail
+		 */
+		kvm_mmu_reload(vcpu);
+	}
+
+	return 0;
+}
+
+static int handle_vmfunc(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmcs12 *vmcs12;
+	u32 function = kvm_rax_read(vcpu);
+
+	/*
+	 * VMFUNC is only supported for nested guests, but we always enable the
+	 * secondary control for simplicity; for non-nested mode, fake that we
+	 * didn't by injecting #UD.
+	 */
+	if (!is_guest_mode(vcpu)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	vmcs12 = get_vmcs12(vcpu);
+	if ((vmcs12->vm_function_control & (1 << function)) == 0)
+		goto fail;
+
+	switch (function) {
+	case 0:
+		if (nested_vmx_eptp_switching(vcpu, vmcs12))
+			goto fail;
+		break;
+	default:
+		goto fail;
+	}
+	return kvm_skip_emulated_instruction(vcpu);
+
+fail:
+	nested_vmx_vmexit(vcpu, vmx->exit_reason,
+			  vmcs_read32(VM_EXIT_INTR_INFO),
+			  vmcs_readl(EXIT_QUALIFICATION));
+	return 1;
+}
+
+
+static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	unsigned long exit_qualification;
+	gpa_t bitmap, last_bitmap;
+	unsigned int port;
+	int size;
+	u8 b;
+
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
+
+	last_bitmap = (gpa_t)-1;
+	b = -1;
+
+	while (size > 0) {
+		if (port < 0x8000)
+			bitmap = vmcs12->io_bitmap_a;
+		else if (port < 0x10000)
+			bitmap = vmcs12->io_bitmap_b;
+		else
+			return true;
+		bitmap += (port & 0x7fff) / 8;
+
+		if (last_bitmap != bitmap)
+			if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1))
+				return true;
+		if (b & (1 << (port & 7)))
+			return true;
+
+		port++;
+		size--;
+		last_bitmap = bitmap;
+	}
+
+	return false;
+}
+
+/*
+ * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
+ * rather than handle it ourselves in L0. I.e., check whether L1 expressed
+ * disinterest in the current event (read or write a specific MSR) by using an
+ * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps.
+ */
+static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
+	struct vmcs12 *vmcs12, u32 exit_reason)
+{
+	u32 msr_index = kvm_rcx_read(vcpu);
+	gpa_t bitmap;
+
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
+		return true;
+
+	/*
+	 * The MSR_BITMAP page is divided into four 1024-byte bitmaps,
+	 * for the four combinations of read/write and low/high MSR numbers.
+	 * First we need to figure out which of the four to use:
+	 */
+	bitmap = vmcs12->msr_bitmap;
+	if (exit_reason == EXIT_REASON_MSR_WRITE)
+		bitmap += 2048;
+	if (msr_index >= 0xc0000000) {
+		msr_index -= 0xc0000000;
+		bitmap += 1024;
+	}
+
+	/* Then read the msr_index'th bit from this bitmap: */
+	if (msr_index < 1024*8) {
+		unsigned char b;
+		if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1))
+			return true;
+		return 1 & (b >> (msr_index & 7));
+	} else
+		return true; /* let L1 handle the wrong parameter */
+}
+
+/*
+ * Return 1 if we should exit from L2 to L1 to handle a CR access exit,
+ * rather than handle it ourselves in L0. I.e., check if L1 wanted to
+ * intercept (via guest_host_mask etc.) the current event.
+ */
+static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
+	struct vmcs12 *vmcs12)
+{
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	int cr = exit_qualification & 15;
+	int reg;
+	unsigned long val;
+
+	switch ((exit_qualification >> 4) & 3) {
+	case 0: /* mov to cr */
+		reg = (exit_qualification >> 8) & 15;
+		val = kvm_register_readl(vcpu, reg);
+		switch (cr) {
+		case 0:
+			if (vmcs12->cr0_guest_host_mask &
+			    (val ^ vmcs12->cr0_read_shadow))
+				return true;
+			break;
+		case 3:
+			if ((vmcs12->cr3_target_count >= 1 &&
+					vmcs12->cr3_target_value0 == val) ||
+				(vmcs12->cr3_target_count >= 2 &&
+					vmcs12->cr3_target_value1 == val) ||
+				(vmcs12->cr3_target_count >= 3 &&
+					vmcs12->cr3_target_value2 == val) ||
+				(vmcs12->cr3_target_count >= 4 &&
+					vmcs12->cr3_target_value3 == val))
+				return false;
+			if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING))
+				return true;
+			break;
+		case 4:
+			if (vmcs12->cr4_guest_host_mask &
+			    (vmcs12->cr4_read_shadow ^ val))
+				return true;
+			break;
+		case 8:
+			if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING))
+				return true;
+			break;
+		}
+		break;
+	case 2: /* clts */
+		if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) &&
+		    (vmcs12->cr0_read_shadow & X86_CR0_TS))
+			return true;
+		break;
+	case 1: /* mov from cr */
+		switch (cr) {
+		case 3:
+			if (vmcs12->cpu_based_vm_exec_control &
+			    CPU_BASED_CR3_STORE_EXITING)
+				return true;
+			break;
+		case 8:
+			if (vmcs12->cpu_based_vm_exec_control &
+			    CPU_BASED_CR8_STORE_EXITING)
+				return true;
+			break;
+		}
+		break;
+	case 3: /* lmsw */
+		/*
+		 * lmsw can change bits 1..3 of cr0, and only set bit 0 of
+		 * cr0. Other attempted changes are ignored, with no exit.
+		 */
+		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
+		if (vmcs12->cr0_guest_host_mask & 0xe &
+		    (val ^ vmcs12->cr0_read_shadow))
+			return true;
+		if ((vmcs12->cr0_guest_host_mask & 0x1) &&
+		    !(vmcs12->cr0_read_shadow & 0x1) &&
+		    (val & 0x1))
+			return true;
+		break;
+	}
+	return false;
+}
+
+static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu,
+	struct vmcs12 *vmcs12, gpa_t bitmap)
+{
+	u32 vmx_instruction_info;
+	unsigned long field;
+	u8 b;
+
+	if (!nested_cpu_has_shadow_vmcs(vmcs12))
+		return true;
+
+	/* Decode instruction info and find the field to access */
+	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+
+	/* Out-of-range fields always cause a VM exit from L2 to L1 */
+	if (field >> 15)
+		return true;
+
+	if (kvm_vcpu_read_guest(vcpu, bitmap + field/8, &b, 1))
+		return true;
+
+	return 1 & (b >> (field & 7));
+}
+
+/*
+ * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we
+ * should handle it ourselves in L0 (and then continue L2). Only call this
+ * when in is_guest_mode (L2).
+ */
+bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
+{
+	u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (vmx->nested.nested_run_pending)
+		return false;
+
+	if (unlikely(vmx->fail)) {
+		trace_kvm_nested_vmenter_failed(
+			"hardware VM-instruction error: ",
+			vmcs_read32(VM_INSTRUCTION_ERROR));
+		return true;
+	}
+
+	/*
+	 * The host physical addresses of some pages of guest memory
+	 * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
+	 * Page). The CPU may write to these pages via their host
+	 * physical address while L2 is running, bypassing any
+	 * address-translation-based dirty tracking (e.g. EPT write
+	 * protection).
+	 *
+	 * Mark them dirty on every exit from L2 to prevent them from
+	 * getting out of sync with dirty tracking.
+	 */
+	nested_mark_vmcs12_pages_dirty(vcpu);
+
+	trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
+				vmcs_readl(EXIT_QUALIFICATION),
+				vmx->idt_vectoring_info,
+				intr_info,
+				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
+				KVM_ISA_VMX);
+
+	switch (exit_reason) {
+	case EXIT_REASON_EXCEPTION_NMI:
+		if (is_nmi(intr_info))
+			return false;
+		else if (is_page_fault(intr_info))
+			return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept;
+		else if (is_debug(intr_info) &&
+			 vcpu->guest_debug &
+			 (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			return false;
+		else if (is_breakpoint(intr_info) &&
+			 vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			return false;
+		return vmcs12->exception_bitmap &
+				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
+	case EXIT_REASON_EXTERNAL_INTERRUPT:
+		return false;
+	case EXIT_REASON_TRIPLE_FAULT:
+		return true;
+	case EXIT_REASON_PENDING_INTERRUPT:
+		return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING);
+	case EXIT_REASON_NMI_WINDOW:
+		return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING);
+	case EXIT_REASON_TASK_SWITCH:
+		return true;
+	case EXIT_REASON_CPUID:
+		return true;
+	case EXIT_REASON_HLT:
+		return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
+	case EXIT_REASON_INVD:
+		return true;
+	case EXIT_REASON_INVLPG:
+		return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
+	case EXIT_REASON_RDPMC:
+		return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING);
+	case EXIT_REASON_RDRAND:
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDRAND_EXITING);
+	case EXIT_REASON_RDSEED:
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDSEED_EXITING);
+	case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP:
+		return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING);
+	case EXIT_REASON_VMREAD:
+		return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12,
+			vmcs12->vmread_bitmap);
+	case EXIT_REASON_VMWRITE:
+		return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12,
+			vmcs12->vmwrite_bitmap);
+	case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR:
+	case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD:
+	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMRESUME:
+	case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
+	case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID:
+		/*
+		 * VMX instructions trap unconditionally. This allows L1 to
+		 * emulate them for its L2 guest, i.e., allows 3-level nesting!
+		 */
+		return true;
+	case EXIT_REASON_CR_ACCESS:
+		return nested_vmx_exit_handled_cr(vcpu, vmcs12);
+	case EXIT_REASON_DR_ACCESS:
+		return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING);
+	case EXIT_REASON_IO_INSTRUCTION:
+		return nested_vmx_exit_handled_io(vcpu, vmcs12);
+	case EXIT_REASON_GDTR_IDTR: case EXIT_REASON_LDTR_TR:
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC);
+	case EXIT_REASON_MSR_READ:
+	case EXIT_REASON_MSR_WRITE:
+		return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason);
+	case EXIT_REASON_INVALID_STATE:
+		return true;
+	case EXIT_REASON_MWAIT_INSTRUCTION:
+		return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
+	case EXIT_REASON_MONITOR_TRAP_FLAG:
+		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
+	case EXIT_REASON_MONITOR_INSTRUCTION:
+		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
+	case EXIT_REASON_PAUSE_INSTRUCTION:
+		return nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING) ||
+			nested_cpu_has2(vmcs12,
+				SECONDARY_EXEC_PAUSE_LOOP_EXITING);
+	case EXIT_REASON_MCE_DURING_VMENTRY:
+		return false;
+	case EXIT_REASON_TPR_BELOW_THRESHOLD:
+		return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
+	case EXIT_REASON_APIC_ACCESS:
+	case EXIT_REASON_APIC_WRITE:
+	case EXIT_REASON_EOI_INDUCED:
+		/*
+		 * The controls for "virtualize APIC accesses," "APIC-
+		 * register virtualization," and "virtual-interrupt
+		 * delivery" only come from vmcs12.
+		 */
+		return true;
+	case EXIT_REASON_EPT_VIOLATION:
+		/*
+		 * L0 always deals with the EPT violation. If nested EPT is
+		 * used, and the nested mmu code discovers that the address is
+		 * missing in the guest EPT table (EPT12), the EPT violation
+		 * will be injected with nested_ept_inject_page_fault()
+		 */
+		return false;
+	case EXIT_REASON_EPT_MISCONFIG:
+		/*
+		 * L2 never uses directly L1's EPT, but rather L0's own EPT
+		 * table (shadow on EPT) or a merged EPT table that L0 built
+		 * (EPT on EPT). So any problems with the structure of the
+		 * table is L0's fault.
+		 */
+		return false;
+	case EXIT_REASON_INVPCID:
+		return
+			nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_INVPCID) &&
+			nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
+	case EXIT_REASON_WBINVD:
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING);
+	case EXIT_REASON_XSETBV:
+		return true;
+	case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS:
+		/*
+		 * This should never happen, since it is not possible to
+		 * set XSS to a non-zero value---neither in L1 nor in L2.
+		 * If if it were, XSS would have to be checked against
+		 * the XSS exit bitmap in vmcs12.
+		 */
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
+	case EXIT_REASON_PREEMPTION_TIMER:
+		return false;
+	case EXIT_REASON_PML_FULL:
+		/* We emulate PML support to L1. */
+		return false;
+	case EXIT_REASON_VMFUNC:
+		/* VM functions are emulated through L2->L0 vmexits. */
+		return false;
+	case EXIT_REASON_ENCLS:
+		/* SGX is never exposed to L1 */
+		return false;
+	case EXIT_REASON_UMWAIT:
+	case EXIT_REASON_TPAUSE:
+		return nested_cpu_has2(vmcs12,
+			SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE);
+	default:
+		return true;
+	}
+}
+
+
+static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
+				struct kvm_nested_state __user *user_kvm_nested_state,
+				u32 user_data_size)
+{
+	struct vcpu_vmx *vmx;
+	struct vmcs12 *vmcs12;
+	struct kvm_nested_state kvm_state = {
+		.flags = 0,
+		.format = KVM_STATE_NESTED_FORMAT_VMX,
+		.size = sizeof(kvm_state),
+		.hdr.vmx.vmxon_pa = -1ull,
+		.hdr.vmx.vmcs12_pa = -1ull,
+	};
+	struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
+		&user_kvm_nested_state->data.vmx[0];
+
+	if (!vcpu)
+		return kvm_state.size + sizeof(*user_vmx_nested_state);
+
+	vmx = to_vmx(vcpu);
+	vmcs12 = get_vmcs12(vcpu);
+
+	if (nested_vmx_allowed(vcpu) &&
+	    (vmx->nested.vmxon || vmx->nested.smm.vmxon)) {
+		kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
+		kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr;
+
+		if (vmx_has_valid_vmcs12(vcpu)) {
+			kvm_state.size += sizeof(user_vmx_nested_state->vmcs12);
+
+			if (vmx->nested.hv_evmcs)
+				kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
+
+			if (is_guest_mode(vcpu) &&
+			    nested_cpu_has_shadow_vmcs(vmcs12) &&
+			    vmcs12->vmcs_link_pointer != -1ull)
+				kvm_state.size += sizeof(user_vmx_nested_state->shadow_vmcs12);
+		}
+
+		if (vmx->nested.smm.vmxon)
+			kvm_state.hdr.vmx.smm.flags |= KVM_STATE_NESTED_SMM_VMXON;
+
+		if (vmx->nested.smm.guest_mode)
+			kvm_state.hdr.vmx.smm.flags |= KVM_STATE_NESTED_SMM_GUEST_MODE;
+
+		if (is_guest_mode(vcpu)) {
+			kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
+
+			if (vmx->nested.nested_run_pending)
+				kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
+		}
+	}
+
+	if (user_data_size < kvm_state.size)
+		goto out;
+
+	if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state)))
+		return -EFAULT;
+
+	if (!vmx_has_valid_vmcs12(vcpu))
+		goto out;
+
+	/*
+	 * When running L2, the authoritative vmcs12 state is in the
+	 * vmcs02. When running L1, the authoritative vmcs12 state is
+	 * in the shadow or enlightened vmcs linked to vmcs01, unless
+	 * need_vmcs12_to_shadow_sync is set, in which case, the authoritative
+	 * vmcs12 state is in the vmcs12 already.
+	 */
+	if (is_guest_mode(vcpu)) {
+		sync_vmcs02_to_vmcs12(vcpu, vmcs12);
+		sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
+	} else if (!vmx->nested.need_vmcs12_to_shadow_sync) {
+		if (vmx->nested.hv_evmcs)
+			copy_enlightened_to_vmcs12(vmx);
+		else if (enable_shadow_vmcs)
+			copy_shadow_to_vmcs12(vmx);
+	}
+
+	BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE);
+	BUILD_BUG_ON(sizeof(user_vmx_nested_state->shadow_vmcs12) < VMCS12_SIZE);
+
+	/*
+	 * Copy over the full allocated size of vmcs12 rather than just the size
+	 * of the struct.
+	 */
+	if (copy_to_user(user_vmx_nested_state->vmcs12, vmcs12, VMCS12_SIZE))
+		return -EFAULT;
+
+	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
+	    vmcs12->vmcs_link_pointer != -1ull) {
+		if (copy_to_user(user_vmx_nested_state->shadow_vmcs12,
+				 get_shadow_vmcs12(vcpu), VMCS12_SIZE))
+			return -EFAULT;
+	}
+
+out:
+	return kvm_state.size;
+}
+
+/*
+ * Forcibly leave nested mode in order to be able to reset the VCPU later on.
+ */
+void vmx_leave_nested(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.nested_run_pending = 0;
+		nested_vmx_vmexit(vcpu, -1, 0, 0);
+	}
+	free_nested(vcpu);
+}
+
+static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
+				struct kvm_nested_state __user *user_kvm_nested_state,
+				struct kvm_nested_state *kvm_state)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmcs12 *vmcs12;
+	u32 exit_qual;
+	struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
+		&user_kvm_nested_state->data.vmx[0];
+	int ret;
+
+	if (kvm_state->format != KVM_STATE_NESTED_FORMAT_VMX)
+		return -EINVAL;
+
+	if (kvm_state->hdr.vmx.vmxon_pa == -1ull) {
+		if (kvm_state->hdr.vmx.smm.flags)
+			return -EINVAL;
+
+		if (kvm_state->hdr.vmx.vmcs12_pa != -1ull)
+			return -EINVAL;
+
+		/*
+		 * KVM_STATE_NESTED_EVMCS used to signal that KVM should
+		 * enable eVMCS capability on vCPU. However, since then
+		 * code was changed such that flag signals vmcs12 should
+		 * be copied into eVMCS in guest memory.
+		 *
+		 * To preserve backwards compatability, allow user
+		 * to set this flag even when there is no VMXON region.
+		 */
+		if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS)
+			return -EINVAL;
+	} else {
+		if (!nested_vmx_allowed(vcpu))
+			return -EINVAL;
+
+		if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa))
+			return -EINVAL;
+	}
+
+	if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
+	    (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
+		return -EINVAL;
+
+	if (kvm_state->hdr.vmx.smm.flags &
+	    ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
+		return -EINVAL;
+
+	/*
+	 * SMM temporarily disables VMX, so we cannot be in guest mode,
+	 * nor can VMLAUNCH/VMRESUME be pending.  Outside SMM, SMM flags
+	 * must be zero.
+	 */
+	if (is_smm(vcpu) ?
+		(kvm_state->flags &
+		 (KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_RUN_PENDING))
+		: kvm_state->hdr.vmx.smm.flags)
+		return -EINVAL;
+
+	if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
+	    !(kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
+		return -EINVAL;
+
+	if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) &&
+		(!nested_vmx_allowed(vcpu) || !vmx->nested.enlightened_vmcs_enabled))
+			return -EINVAL;
+
+	vmx_leave_nested(vcpu);
+
+	if (kvm_state->hdr.vmx.vmxon_pa == -1ull)
+		return 0;
+
+	vmx->nested.vmxon_ptr = kvm_state->hdr.vmx.vmxon_pa;
+	ret = enter_vmx_operation(vcpu);
+	if (ret)
+		return ret;
+
+	/* Empty 'VMXON' state is permitted */
+	if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
+		return 0;
+
+	if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) {
+		if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa ||
+		    !page_address_valid(vcpu, kvm_state->hdr.vmx.vmcs12_pa))
+			return -EINVAL;
+
+		set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa);
+	} else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
+		/*
+		 * Sync eVMCS upon entry as we may not have
+		 * HV_X64_MSR_VP_ASSIST_PAGE set up yet.
+		 */
+		vmx->nested.need_vmcs12_to_shadow_sync = true;
+	} else {
+		return -EINVAL;
+	}
+
+	if (kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) {
+		vmx->nested.smm.vmxon = true;
+		vmx->nested.vmxon = false;
+
+		if (kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE)
+			vmx->nested.smm.guest_mode = true;
+	}
+
+	vmcs12 = get_vmcs12(vcpu);
+	if (copy_from_user(vmcs12, user_vmx_nested_state->vmcs12, sizeof(*vmcs12)))
+		return -EFAULT;
+
+	if (vmcs12->hdr.revision_id != VMCS12_REVISION)
+		return -EINVAL;
+
+	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
+		return 0;
+
+	vmx->nested.nested_run_pending =
+		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
+
+	ret = -EINVAL;
+	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
+	    vmcs12->vmcs_link_pointer != -1ull) {
+		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
+
+		if (kvm_state->size <
+		    sizeof(*kvm_state) +
+		    sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12))
+			goto error_guest_mode;
+
+		if (copy_from_user(shadow_vmcs12,
+				   user_vmx_nested_state->shadow_vmcs12,
+				   sizeof(*shadow_vmcs12))) {
+			ret = -EFAULT;
+			goto error_guest_mode;
+		}
+
+		if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
+		    !shadow_vmcs12->hdr.shadow_vmcs)
+			goto error_guest_mode;
+	}
+
+	if (nested_vmx_check_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_host_state(vcpu, vmcs12) ||
+	    nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
+		goto error_guest_mode;
+
+	vmx->nested.dirty_vmcs12 = true;
+	ret = nested_vmx_enter_non_root_mode(vcpu, false);
+	if (ret)
+		goto error_guest_mode;
+
+	return 0;
+
+error_guest_mode:
+	vmx->nested.nested_run_pending = 0;
+	return ret;
+}
+
+void nested_vmx_vcpu_setup(void)
+{
+	if (enable_shadow_vmcs) {
+		vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
+		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
+	}
+}
+
+/*
+ * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be
+ * returned for the various VMX controls MSRs when nested VMX is enabled.
+ * The same values should also be used to verify that vmcs12 control fields are
+ * valid during nested entry from L1 to L2.
+ * Each of these control msrs has a low and high 32-bit half: A low bit is on
+ * if the corresponding bit in the (32-bit) control field *must* be on, and a
+ * bit in the high half is on if the corresponding bit in the control field
+ * may be on. See also vmx_control_verify().
+ */
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
+				bool apicv)
+{
+	/*
+	 * Note that as a general rule, the high half of the MSRs (bits in
+	 * the control fields which may be 1) should be initialized by the
+	 * intersection of the underlying hardware's MSR (i.e., features which
+	 * can be supported) and the list of features we want to expose -
+	 * because they are known to be properly supported in our code.
+	 * Also, usually, the low half of the MSRs (bits which must be 1) can
+	 * be set to 0, meaning that L1 may turn off any of these bits. The
+	 * reason is that if one of these bits is necessary, it will appear
+	 * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
+	 * fields of vmcs01 and vmcs02, will turn these bits off - and
+	 * nested_vmx_exit_reflected() will not pass related exits to L1.
+	 * These rules have exceptions below.
+	 */
+
+	/* pin-based controls */
+	rdmsr(MSR_IA32_VMX_PINBASED_CTLS,
+		msrs->pinbased_ctls_low,
+		msrs->pinbased_ctls_high);
+	msrs->pinbased_ctls_low |=
+		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
+	msrs->pinbased_ctls_high &=
+		PIN_BASED_EXT_INTR_MASK |
+		PIN_BASED_NMI_EXITING |
+		PIN_BASED_VIRTUAL_NMIS |
+		(apicv ? PIN_BASED_POSTED_INTR : 0);
+	msrs->pinbased_ctls_high |=
+		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
+		PIN_BASED_VMX_PREEMPTION_TIMER;
+
+	/* exit controls */
+	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
+		msrs->exit_ctls_low,
+		msrs->exit_ctls_high);
+	msrs->exit_ctls_low =
+		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
+
+	msrs->exit_ctls_high &=
+#ifdef CONFIG_X86_64
+		VM_EXIT_HOST_ADDR_SPACE_SIZE |
+#endif
+		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+	msrs->exit_ctls_high |=
+		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
+		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
+		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
+
+	/* We support free control of debug control saving. */
+	msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
+
+	/* entry controls */
+	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
+		msrs->entry_ctls_low,
+		msrs->entry_ctls_high);
+	msrs->entry_ctls_low =
+		VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
+	msrs->entry_ctls_high &=
+#ifdef CONFIG_X86_64
+		VM_ENTRY_IA32E_MODE |
+#endif
+		VM_ENTRY_LOAD_IA32_PAT;
+	msrs->entry_ctls_high |=
+		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
+
+	/* We support free control of debug control loading. */
+	msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
+
+	/* cpu-based controls */
+	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
+		msrs->procbased_ctls_low,
+		msrs->procbased_ctls_high);
+	msrs->procbased_ctls_low =
+		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
+	msrs->procbased_ctls_high &=
+		CPU_BASED_VIRTUAL_INTR_PENDING |
+		CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING |
+		CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING |
+		CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING |
+		CPU_BASED_CR3_STORE_EXITING |
+#ifdef CONFIG_X86_64
+		CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING |
+#endif
+		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
+		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG |
+		CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING |
+		CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING |
+		CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+	/*
+	 * We can allow some features even when not supported by the
+	 * hardware. For example, L1 can specify an MSR bitmap - and we
+	 * can use it to avoid exits to L1 - even when L0 runs L2
+	 * without MSR bitmaps.
+	 */
+	msrs->procbased_ctls_high |=
+		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
+		CPU_BASED_USE_MSR_BITMAPS;
+
+	/* We support free control of CR3 access interception. */
+	msrs->procbased_ctls_low &=
+		~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING);
+
+	/*
+	 * secondary cpu-based controls.  Do not include those that
+	 * depend on CPUID bits, they are added later by vmx_cpuid_update.
+	 */
+	if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
+		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+		      msrs->secondary_ctls_low,
+		      msrs->secondary_ctls_high);
+
+	msrs->secondary_ctls_low = 0;
+	msrs->secondary_ctls_high &=
+		SECONDARY_EXEC_DESC |
+		SECONDARY_EXEC_RDTSCP |
+		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+		SECONDARY_EXEC_WBINVD_EXITING |
+		SECONDARY_EXEC_APIC_REGISTER_VIRT |
+		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
+		SECONDARY_EXEC_RDRAND_EXITING |
+		SECONDARY_EXEC_ENABLE_INVPCID |
+		SECONDARY_EXEC_RDSEED_EXITING |
+		SECONDARY_EXEC_XSAVES;
+
+	/*
+	 * We can emulate "VMCS shadowing," even if the hardware
+	 * doesn't support it.
+	 */
+	msrs->secondary_ctls_high |=
+		SECONDARY_EXEC_SHADOW_VMCS;
+
+	if (enable_ept) {
+		/* nested EPT: emulate EPT also to L1 */
+		msrs->secondary_ctls_high |=
+			SECONDARY_EXEC_ENABLE_EPT;
+		msrs->ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
+			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
+		if (cpu_has_vmx_ept_execute_only())
+			msrs->ept_caps |=
+				VMX_EPT_EXECUTE_ONLY_BIT;
+		msrs->ept_caps &= ept_caps;
+		msrs->ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
+			VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT |
+			VMX_EPT_1GB_PAGE_BIT;
+		if (enable_ept_ad_bits) {
+			msrs->secondary_ctls_high |=
+				SECONDARY_EXEC_ENABLE_PML;
+			msrs->ept_caps |= VMX_EPT_AD_BIT;
+		}
+	}
+
+	if (cpu_has_vmx_vmfunc()) {
+		msrs->secondary_ctls_high |=
+			SECONDARY_EXEC_ENABLE_VMFUNC;
+		/*
+		 * Advertise EPTP switching unconditionally
+		 * since we emulate it
+		 */
+		if (enable_ept)
+			msrs->vmfunc_controls =
+				VMX_VMFUNC_EPTP_SWITCHING;
+	}
+
+	/*
+	 * Old versions of KVM use the single-context version without
+	 * checking for support, so declare that it is supported even
+	 * though it is treated as global context.  The alternative is
+	 * not failing the single-context invvpid, and it is worse.
+	 */
+	if (enable_vpid) {
+		msrs->secondary_ctls_high |=
+			SECONDARY_EXEC_ENABLE_VPID;
+		msrs->vpid_caps = VMX_VPID_INVVPID_BIT |
+			VMX_VPID_EXTENT_SUPPORTED_MASK;
+	}
+
+	if (enable_unrestricted_guest)
+		msrs->secondary_ctls_high |=
+			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
+	if (flexpriority_enabled)
+		msrs->secondary_ctls_high |=
+			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+
+	/* miscellaneous data */
+	rdmsr(MSR_IA32_VMX_MISC,
+		msrs->misc_low,
+		msrs->misc_high);
+	msrs->misc_low &= VMX_MISC_SAVE_EFER_LMA;
+	msrs->misc_low |=
+		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
+		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
+		VMX_MISC_ACTIVITY_HLT;
+	msrs->misc_high = 0;
+
+	/*
+	 * This MSR reports some information about VMX support. We
+	 * should return information about the VMX we emulate for the
+	 * guest, and the VMCS structure we give it - not about the
+	 * VMX support of the underlying hardware.
+	 */
+	msrs->basic =
+		VMCS12_REVISION |
+		VMX_BASIC_TRUE_CTLS |
+		((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
+		(VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
+
+	if (cpu_has_vmx_basic_inout())
+		msrs->basic |= VMX_BASIC_INOUT;
+
+	/*
+	 * These MSRs specify bits which the guest must keep fixed on
+	 * while L1 is in VMXON mode (in L1's root mode, or running an L2).
+	 * We picked the standard core2 setting.
+	 */
+#define VMXON_CR0_ALWAYSON     (X86_CR0_PE | X86_CR0_PG | X86_CR0_NE)
+#define VMXON_CR4_ALWAYSON     X86_CR4_VMXE
+	msrs->cr0_fixed0 = VMXON_CR0_ALWAYSON;
+	msrs->cr4_fixed0 = VMXON_CR4_ALWAYSON;
+
+	/* These MSRs specify bits which the guest must keep fixed off. */
+	rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1);
+	rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1);
+
+	/* highest index: VMX_PREEMPTION_TIMER_VALUE */
+	msrs->vmcs_enum = VMCS12_MAX_FIELD_INDEX << 1;
+}
+
+void nested_vmx_hardware_unsetup(void)
+{
+	int i;
+
+	if (enable_shadow_vmcs) {
+		for (i = 0; i < VMX_BITMAP_NR; i++)
+			free_page((unsigned long)vmx_bitmap[i]);
+	}
+}
+
+__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
+{
+	int i;
+
+	if (!cpu_has_vmx_shadow_vmcs())
+		enable_shadow_vmcs = 0;
+	if (enable_shadow_vmcs) {
+		for (i = 0; i < VMX_BITMAP_NR; i++) {
+			/*
+			 * The vmx_bitmap is not tied to a VM and so should
+			 * not be charged to a memcg.
+			 */
+			vmx_bitmap[i] = (unsigned long *)
+				__get_free_page(GFP_KERNEL);
+			if (!vmx_bitmap[i]) {
+				nested_vmx_hardware_unsetup();
+				return -ENOMEM;
+			}
+		}
+
+		init_vmcs_shadow_fields();
+	}
+
+	exit_handlers[EXIT_REASON_VMCLEAR]	= handle_vmclear,
+	exit_handlers[EXIT_REASON_VMLAUNCH]	= handle_vmlaunch,
+	exit_handlers[EXIT_REASON_VMPTRLD]	= handle_vmptrld,
+	exit_handlers[EXIT_REASON_VMPTRST]	= handle_vmptrst,
+	exit_handlers[EXIT_REASON_VMREAD]	= handle_vmread,
+	exit_handlers[EXIT_REASON_VMRESUME]	= handle_vmresume,
+	exit_handlers[EXIT_REASON_VMWRITE]	= handle_vmwrite,
+	exit_handlers[EXIT_REASON_VMOFF]	= handle_vmoff,
+	exit_handlers[EXIT_REASON_VMON]		= handle_vmon,
+	exit_handlers[EXIT_REASON_INVEPT]	= handle_invept,
+	exit_handlers[EXIT_REASON_INVVPID]	= handle_invvpid,
+	exit_handlers[EXIT_REASON_VMFUNC]	= handle_vmfunc,
+
+	kvm_x86_ops->check_nested_events = vmx_check_nested_events;
+	kvm_x86_ops->get_nested_state = vmx_get_nested_state;
+	kvm_x86_ops->set_nested_state = vmx_set_nested_state;
+	kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages,
+	kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs;
+	kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version;
+
+	return 0;
+}
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
new file mode 100644
index 0000000..6280f33
--- /dev/null
+++ b/arch/x86/kvm/vmx/nested.h
@@ -0,0 +1,293 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_NESTED_H
+#define __KVM_X86_VMX_NESTED_H
+
+#include "kvm_cache_regs.h"
+#include "vmcs12.h"
+#include "vmx.h"
+
+/*
+ * Status returned by nested_vmx_enter_non_root_mode():
+ */
+enum nvmx_vmentry_status {
+	NVMX_VMENTRY_SUCCESS,		/* Entered VMX non-root mode */
+	NVMX_VMENTRY_VMFAIL,		/* Consistency check VMFail */
+	NVMX_VMENTRY_VMEXIT,		/* Consistency check VMExit */
+	NVMX_VMENTRY_KVM_INTERNAL_ERROR,/* KVM internal error */
+};
+
+void vmx_leave_nested(struct kvm_vcpu *vcpu);
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
+				bool apicv);
+void nested_vmx_hardware_unsetup(void);
+__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
+void nested_vmx_vcpu_setup(void);
+void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
+enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+						     bool from_vmentry);
+bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason);
+void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
+		       u32 exit_intr_info, unsigned long exit_qualification);
+void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu);
+int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
+int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
+int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
+			u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
+
+static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.cached_vmcs12;
+}
+
+static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.cached_shadow_vmcs12;
+}
+
+static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * In case we do two consecutive get/set_nested_state()s while L2 was
+	 * running hv_evmcs may end up not being mapped (we map it from
+	 * nested_vmx_run()/vmx_vcpu_run()). Check is_guest_mode() as we always
+	 * have vmcs12 if it is true.
+	 */
+	return is_guest_mode(vcpu) || vmx->nested.current_vmptr != -1ull ||
+		vmx->nested.hv_evmcs;
+}
+
+static inline unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
+{
+	/* return the page table to be shadowed - in our case, EPT12 */
+	return get_vmcs12(vcpu)->ept_pointer;
+}
+
+static inline bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu)
+{
+	return nested_ept_get_cr3(vcpu) & VMX_EPTP_AD_ENABLE_BIT;
+}
+
+/*
+ * Reflect a VM Exit into L1.
+ */
+static inline int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu,
+					    u32 exit_reason)
+{
+	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+	/*
+	 * At this point, the exit interruption info in exit_intr_info
+	 * is only valid for EXCEPTION_NMI exits.  For EXTERNAL_INTERRUPT
+	 * we need to query the in-kernel LAPIC.
+	 */
+	WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT);
+	if ((exit_intr_info &
+	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
+	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
+		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+		vmcs12->vm_exit_intr_error_code =
+			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+	}
+
+	nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info,
+			  vmcs_readl(EXIT_QUALIFICATION));
+	return 1;
+}
+
+/*
+ * Return the cr0 value that a nested guest would read. This is a combination
+ * of the real cr0 used to run the guest (guest_cr0), and the bits shadowed by
+ * its hypervisor (cr0_read_shadow).
+ */
+static inline unsigned long nested_read_cr0(struct vmcs12 *fields)
+{
+	return (fields->guest_cr0 & ~fields->cr0_guest_host_mask) |
+		(fields->cr0_read_shadow & fields->cr0_guest_host_mask);
+}
+static inline unsigned long nested_read_cr4(struct vmcs12 *fields)
+{
+	return (fields->guest_cr4 & ~fields->cr4_guest_host_mask) |
+		(fields->cr4_read_shadow & fields->cr4_guest_host_mask);
+}
+
+static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
+{
+	return vmx_misc_cr3_count(to_vmx(vcpu)->nested.msrs.misc_low);
+}
+
+/*
+ * Do the virtual VMX capability MSRs specify that L1 can use VMWRITE
+ * to modify any valid field of the VMCS, or are the VM-exit
+ * information fields read-only?
+ */
+static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.msrs.misc_low &
+		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
+}
+
+static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS;
+}
+
+static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.msrs.procbased_ctls_high &
+			CPU_BASED_MONITOR_TRAP_FLAG;
+}
+
+static inline bool nested_cpu_has_vmx_shadow_vmcs(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.msrs.secondary_ctls_high &
+		SECONDARY_EXEC_SHADOW_VMCS;
+}
+
+static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
+{
+	return vmcs12->cpu_based_vm_exec_control & bit;
+}
+
+static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
+{
+	return (vmcs12->cpu_based_vm_exec_control &
+			CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
+		(vmcs12->secondary_vm_exec_control & bit);
+}
+
+static inline bool nested_cpu_has_preemption_timer(struct vmcs12 *vmcs12)
+{
+	return vmcs12->pin_based_vm_exec_control &
+		PIN_BASED_VMX_PREEMPTION_TIMER;
+}
+
+static inline bool nested_cpu_has_nmi_exiting(struct vmcs12 *vmcs12)
+{
+	return vmcs12->pin_based_vm_exec_control & PIN_BASED_NMI_EXITING;
+}
+
+static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
+{
+	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
+}
+
+static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
+}
+
+static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
+}
+
+static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML);
+}
+
+static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
+}
+
+static inline bool nested_cpu_has_vpid(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VPID);
+}
+
+static inline bool nested_cpu_has_apic_reg_virt(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_APIC_REGISTER_VIRT);
+}
+
+static inline bool nested_cpu_has_vid(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+}
+
+static inline bool nested_cpu_has_posted_intr(struct vmcs12 *vmcs12)
+{
+	return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR;
+}
+
+static inline bool nested_cpu_has_vmfunc(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VMFUNC);
+}
+
+static inline bool nested_cpu_has_eptp_switching(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has_vmfunc(vmcs12) &&
+		(vmcs12->vm_function_control &
+		 VMX_VMFUNC_EPTP_SWITCHING);
+}
+
+static inline bool nested_cpu_has_shadow_vmcs(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS);
+}
+
+static inline bool nested_cpu_has_save_preemption_timer(struct vmcs12 *vmcs12)
+{
+	return vmcs12->vm_exit_controls &
+	    VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+}
+
+/*
+ * In nested virtualization, check if L1 asked to exit on external interrupts.
+ * For most existing hypervisors, this will always return true.
+ */
+static inline bool nested_exit_on_intr(struct kvm_vcpu *vcpu)
+{
+	return get_vmcs12(vcpu)->pin_based_vm_exec_control &
+		PIN_BASED_EXT_INTR_MASK;
+}
+
+/*
+ * if fixed0[i] == 1: val[i] must be 1
+ * if fixed1[i] == 0: val[i] must be 0
+ */
+static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1)
+{
+	return ((val & fixed1) | fixed0) == val;
+}
+
+static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
+	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (to_vmx(vcpu)->nested.msrs.secondary_ctls_high &
+		SECONDARY_EXEC_UNRESTRICTED_GUEST &&
+	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
+		fixed0 &= ~(X86_CR0_PE | X86_CR0_PG);
+
+	return fixed_bits_valid(val, fixed0, fixed1);
+}
+
+static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
+	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
+
+	return fixed_bits_valid(val, fixed0, fixed1);
+}
+
+static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0;
+	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1;
+
+	return fixed_bits_valid(val, fixed0, fixed1);
+}
+
+/* No difference in the restrictions on guest and host CR4 in VMX operation. */
+#define nested_guest_cr4_valid	nested_cr4_valid
+#define nested_host_cr4_valid	nested_cr4_valid
+
+#endif /* __KVM_X86_VMX_NESTED_H */
diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/ops.h
new file mode 100644
index 0000000..45eaede
--- /dev/null
+++ b/arch/x86/kvm/vmx/ops.h
@@ -0,0 +1,305 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_INSN_H
+#define __KVM_X86_VMX_INSN_H
+
+#include <linux/nospec.h>
+
+#include <asm/kvm_host.h>
+#include <asm/vmx.h>
+
+#include "evmcs.h"
+#include "vmcs.h"
+
+#define __ex(x) __kvm_handle_fault_on_reboot(x)
+
+asmlinkage void vmread_error(unsigned long field, bool fault);
+void vmwrite_error(unsigned long field, unsigned long value);
+void vmclear_error(struct vmcs *vmcs, u64 phys_addr);
+void vmptrld_error(struct vmcs *vmcs, u64 phys_addr);
+void invvpid_error(unsigned long ext, u16 vpid, gva_t gva);
+void invept_error(unsigned long ext, u64 eptp, gpa_t gpa);
+
+static __always_inline void vmcs_check16(unsigned long field)
+{
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000,
+			 "16-bit accessor invalid for 64-bit field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
+			 "16-bit accessor invalid for 64-bit high field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
+			 "16-bit accessor invalid for 32-bit high field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
+			 "16-bit accessor invalid for natural width field");
+}
+
+static __always_inline void vmcs_check32(unsigned long field)
+{
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
+			 "32-bit accessor invalid for 16-bit field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
+			 "32-bit accessor invalid for natural width field");
+}
+
+static __always_inline void vmcs_check64(unsigned long field)
+{
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
+			 "64-bit accessor invalid for 16-bit field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
+			 "64-bit accessor invalid for 64-bit high field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
+			 "64-bit accessor invalid for 32-bit field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
+			 "64-bit accessor invalid for natural width field");
+}
+
+static __always_inline void vmcs_checkl(unsigned long field)
+{
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
+			 "Natural width accessor invalid for 16-bit field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000,
+			 "Natural width accessor invalid for 64-bit field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
+			 "Natural width accessor invalid for 64-bit high field");
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
+			 "Natural width accessor invalid for 32-bit field");
+}
+
+static __always_inline unsigned long __vmcs_readl(unsigned long field)
+{
+	unsigned long value;
+
+	asm volatile("1: vmread %2, %1\n\t"
+		     ".byte 0x3e\n\t" /* branch taken hint */
+		     "ja 3f\n\t"
+		     "mov %2, %%" _ASM_ARG1 "\n\t"
+		     "xor %%" _ASM_ARG2 ", %%" _ASM_ARG2 "\n\t"
+		     "2: call vmread_error\n\t"
+		     "xor %k1, %k1\n\t"
+		     "3:\n\t"
+
+		     ".pushsection .fixup, \"ax\"\n\t"
+		     "4: mov %2, %%" _ASM_ARG1 "\n\t"
+		     "mov $1, %%" _ASM_ARG2 "\n\t"
+		     "jmp 2b\n\t"
+		     ".popsection\n\t"
+		     _ASM_EXTABLE(1b, 4b)
+		     : ASM_CALL_CONSTRAINT, "=r"(value) : "r"(field) : "cc");
+	return value;
+}
+
+static __always_inline u16 vmcs_read16(unsigned long field)
+{
+	vmcs_check16(field);
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_read16(field);
+	return __vmcs_readl(field);
+}
+
+static __always_inline u32 vmcs_read32(unsigned long field)
+{
+	vmcs_check32(field);
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_read32(field);
+	return __vmcs_readl(field);
+}
+
+static __always_inline u64 vmcs_read64(unsigned long field)
+{
+	vmcs_check64(field);
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_read64(field);
+#ifdef CONFIG_X86_64
+	return __vmcs_readl(field);
+#else
+	return __vmcs_readl(field) | ((u64)__vmcs_readl(field+1) << 32);
+#endif
+}
+
+static __always_inline unsigned long vmcs_readl(unsigned long field)
+{
+	vmcs_checkl(field);
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_read64(field);
+	return __vmcs_readl(field);
+}
+
+#define vmx_asm1(insn, op1, error_args...)				\
+do {									\
+	asm_volatile_goto("1: " __stringify(insn) " %0\n\t"		\
+			  ".byte 0x2e\n\t" /* branch not taken hint */	\
+			  "jna %l[error]\n\t"				\
+			  _ASM_EXTABLE(1b, %l[fault])			\
+			  : : op1 : "cc" : error, fault);		\
+	return;								\
+error:									\
+	insn##_error(error_args);					\
+	return;								\
+fault:									\
+	kvm_spurious_fault();						\
+} while (0)
+
+#define vmx_asm2(insn, op1, op2, error_args...)				\
+do {									\
+	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+			  ".byte 0x2e\n\t" /* branch not taken hint */	\
+			  "jna %l[error]\n\t"				\
+			  _ASM_EXTABLE(1b, %l[fault])			\
+			  : : op1, op2 : "cc" : error, fault);		\
+	return;								\
+error:									\
+	insn##_error(error_args);					\
+	return;								\
+fault:									\
+	kvm_spurious_fault();						\
+} while (0)
+
+static __always_inline void __vmcs_writel(unsigned long field, unsigned long value)
+{
+	vmx_asm2(vmwrite, "r"(field), "rm"(value), field, value);
+}
+
+static __always_inline void vmcs_write16(unsigned long field, u16 value)
+{
+	vmcs_check16(field);
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_write16(field, value);
+
+	__vmcs_writel(field, value);
+}
+
+static __always_inline void vmcs_write32(unsigned long field, u32 value)
+{
+	vmcs_check32(field);
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_write32(field, value);
+
+	__vmcs_writel(field, value);
+}
+
+static __always_inline void vmcs_write64(unsigned long field, u64 value)
+{
+	vmcs_check64(field);
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_write64(field, value);
+
+	__vmcs_writel(field, value);
+#ifndef CONFIG_X86_64
+	__vmcs_writel(field+1, value >> 32);
+#endif
+}
+
+static __always_inline void vmcs_writel(unsigned long field, unsigned long value)
+{
+	vmcs_checkl(field);
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_write64(field, value);
+
+	__vmcs_writel(field, value);
+}
+
+static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask)
+{
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000,
+			 "vmcs_clear_bits does not support 64-bit fields");
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_write32(field, evmcs_read32(field) & ~mask);
+
+	__vmcs_writel(field, __vmcs_readl(field) & ~mask);
+}
+
+static __always_inline void vmcs_set_bits(unsigned long field, u32 mask)
+{
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000,
+			 "vmcs_set_bits does not support 64-bit fields");
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_write32(field, evmcs_read32(field) | mask);
+
+	__vmcs_writel(field, __vmcs_readl(field) | mask);
+}
+
+static inline void vmcs_clear(struct vmcs *vmcs)
+{
+	u64 phys_addr = __pa(vmcs);
+
+	vmx_asm1(vmclear, "m"(phys_addr), vmcs, phys_addr);
+}
+
+static inline void vmcs_load(struct vmcs *vmcs)
+{
+	u64 phys_addr = __pa(vmcs);
+
+	if (static_branch_unlikely(&enable_evmcs))
+		return evmcs_load(phys_addr);
+
+	vmx_asm1(vmptrld, "m"(phys_addr), vmcs, phys_addr);
+}
+
+static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva)
+{
+	struct {
+		u64 vpid : 16;
+		u64 rsvd : 48;
+		u64 gva;
+	} operand = { vpid, 0, gva };
+
+	vmx_asm2(invvpid, "r"(ext), "m"(operand), ext, vpid, gva);
+}
+
+static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa)
+{
+	struct {
+		u64 eptp, gpa;
+	} operand = {eptp, gpa};
+
+	vmx_asm2(invept, "r"(ext), "m"(operand), ext, eptp, gpa);
+}
+
+static inline bool vpid_sync_vcpu_addr(int vpid, gva_t addr)
+{
+	if (vpid == 0)
+		return true;
+
+	if (cpu_has_vmx_invvpid_individual_addr()) {
+		__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR, vpid, addr);
+		return true;
+	}
+
+	return false;
+}
+
+static inline void vpid_sync_vcpu_single(int vpid)
+{
+	if (vpid == 0)
+		return;
+
+	if (cpu_has_vmx_invvpid_single())
+		__invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0);
+}
+
+static inline void vpid_sync_vcpu_global(void)
+{
+	if (cpu_has_vmx_invvpid_global())
+		__invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0);
+}
+
+static inline void vpid_sync_context(int vpid)
+{
+	if (cpu_has_vmx_invvpid_single())
+		vpid_sync_vcpu_single(vpid);
+	else
+		vpid_sync_vcpu_global();
+}
+
+static inline void ept_sync_global(void)
+{
+	__invept(VMX_EPT_EXTENT_GLOBAL, 0, 0);
+}
+
+static inline void ept_sync_context(u64 eptp)
+{
+	if (cpu_has_vmx_invept_context())
+		__invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0);
+	else
+		ept_sync_global();
+}
+
+#endif /* __KVM_X86_VMX_INSN_H */
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
similarity index 86%
rename from arch/x86/kvm/pmu_intel.c
rename to arch/x86/kvm/vmx/pmu_intel.c
index 5ab4a36..3e9c059 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * KVM PMU support for Intel CPUs
  *
@@ -6,10 +7,6 @@
  * Authors:
  *   Avi Kivity   <avi@redhat.com>
  *   Gleb Natapov <gleb@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 #include <linux/types.h>
 #include <linux/kvm_host.h>
@@ -126,7 +123,7 @@
 }
 
 static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
-					    unsigned idx)
+					    unsigned idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
@@ -138,6 +135,7 @@
 	if (fixed && idx >= pmu->nr_arch_fixed_counters)
 		return NULL;
 	counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
+	*mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP];
 
 	return &counters[idx];
 }
@@ -183,9 +181,13 @@
 		*data = pmu->global_ovf_ctrl;
 		return 0;
 	default:
-		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
-		    (pmc = get_fixed_pmc(pmu, msr))) {
-			*data = pmc_read_counter(pmc);
+		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) {
+			u64 val = pmc_read_counter(pmc);
+			*data = val & pmu->counter_bitmask[KVM_PMC_GP];
+			return 0;
+		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
+			u64 val = pmc_read_counter(pmc);
+			*data = val & pmu->counter_bitmask[KVM_PMC_FIXED];
 			return 0;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			*data = pmc->eventsel;
@@ -227,7 +229,7 @@
 		}
 		break;
 	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
-		if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) {
+		if (!(data & pmu->global_ovf_ctrl_mask)) {
 			if (!msr_info->host_initiated)
 				pmu->global_status &= ~data;
 			pmu->global_ovf_ctrl = data;
@@ -235,11 +237,14 @@
 		}
 		break;
 	default:
-		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
-		    (pmc = get_fixed_pmc(pmu, msr))) {
-			if (!msr_info->host_initiated)
-				data = (s64)(s32)data;
-			pmc->counter += data - pmc_read_counter(pmc);
+		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) {
+			if (msr_info->host_initiated)
+				pmc->counter = data;
+			else
+				pmc->counter = (s32)data;
+			return 0;
+		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
+			pmc->counter = data;
 			return 0;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)
@@ -257,6 +262,7 @@
 static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct x86_pmu_capability x86_pmu;
 	struct kvm_cpuid_entry2 *entry;
 	union cpuid10_eax eax;
 	union cpuid10_edx edx;
@@ -278,8 +284,10 @@
 	if (!pmu->version)
 		return;
 
+	perf_get_x86_pmu_capability(&x86_pmu);
+
 	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
-					INTEL_PMC_MAX_GENERIC);
+					 x86_pmu.num_counters_gp);
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
 	pmu->available_event_types = ~entry->ebx &
 					((1ull << eax.split.mask_length) - 1);
@@ -289,7 +297,7 @@
 	} else {
 		pmu->nr_arch_fixed_counters =
 			min_t(int, edx.split.num_counters_fixed,
-				INTEL_PMC_MAX_FIXED);
+			      x86_pmu.num_counters_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
@@ -297,6 +305,12 @@
 	pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
+	pmu->global_ovf_ctrl_mask = pmu->global_ctrl_mask
+			& ~(MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF |
+			    MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD);
+	if (kvm_x86_ops->pt_supported())
+		pmu->global_ovf_ctrl_mask &=
+				~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI;
 
 	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
 	if (entry &&
@@ -326,17 +340,22 @@
 static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc = NULL;
 	int i;
 
 	for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
-		struct kvm_pmc *pmc = &pmu->gp_counters[i];
+		pmc = &pmu->gp_counters[i];
 
 		pmc_stop_counter(pmc);
 		pmc->counter = pmc->eventsel = 0;
 	}
 
-	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++)
-		pmc_stop_counter(&pmu->fixed_counters[i]);
+	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
+		pmc = &pmu->fixed_counters[i];
+
+		pmc_stop_counter(pmc);
+		pmc->counter = 0;
+	}
 
 	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
 		pmu->global_ovf_ctrl = 0;
diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h
new file mode 100644
index 0000000..481ad87
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmcs.h
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_VMCS_H
+#define __KVM_X86_VMX_VMCS_H
+
+#include <linux/ktime.h>
+#include <linux/list.h>
+#include <linux/nospec.h>
+
+#include <asm/kvm.h>
+#include <asm/vmx.h>
+
+#include "capabilities.h"
+
+struct vmcs_hdr {
+	u32 revision_id:31;
+	u32 shadow_vmcs:1;
+};
+
+struct vmcs {
+	struct vmcs_hdr hdr;
+	u32 abort;
+	char data[0];
+};
+
+DECLARE_PER_CPU(struct vmcs *, current_vmcs);
+
+/*
+ * vmcs_host_state tracks registers that are loaded from the VMCS on VMEXIT
+ * and whose values change infrequently, but are not constant.  I.e. this is
+ * used as a write-through cache of the corresponding VMCS fields.
+ */
+struct vmcs_host_state {
+	unsigned long cr3;	/* May not match real cr3 */
+	unsigned long cr4;	/* May not match real cr4 */
+	unsigned long gs_base;
+	unsigned long fs_base;
+	unsigned long rsp;
+
+	u16           fs_sel, gs_sel, ldt_sel;
+#ifdef CONFIG_X86_64
+	u16           ds_sel, es_sel;
+#endif
+};
+
+struct vmcs_controls_shadow {
+	u32 vm_entry;
+	u32 vm_exit;
+	u32 pin;
+	u32 exec;
+	u32 secondary_exec;
+};
+
+/*
+ * Track a VMCS that may be loaded on a certain CPU. If it is (cpu!=-1), also
+ * remember whether it was VMLAUNCHed, and maintain a linked list of all VMCSs
+ * loaded on this CPU (so we can clear them if the CPU goes down).
+ */
+struct loaded_vmcs {
+	struct vmcs *vmcs;
+	struct vmcs *shadow_vmcs;
+	int cpu;
+	bool launched;
+	bool nmi_known_unmasked;
+	bool hv_timer_soft_disabled;
+	/* Support for vnmi-less CPUs */
+	int soft_vnmi_blocked;
+	ktime_t entry_time;
+	s64 vnmi_blocked_time;
+	unsigned long *msr_bitmap;
+	struct list_head loaded_vmcss_on_cpu_link;
+	struct vmcs_host_state host_state;
+	struct vmcs_controls_shadow controls_shadow;
+};
+
+static inline bool is_exception_n(u32 intr_info, u8 vector)
+{
+	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
+			     INTR_INFO_VALID_MASK)) ==
+		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+}
+
+static inline bool is_debug(u32 intr_info)
+{
+	return is_exception_n(intr_info, DB_VECTOR);
+}
+
+static inline bool is_breakpoint(u32 intr_info)
+{
+	return is_exception_n(intr_info, BP_VECTOR);
+}
+
+static inline bool is_page_fault(u32 intr_info)
+{
+	return is_exception_n(intr_info, PF_VECTOR);
+}
+
+static inline bool is_invalid_opcode(u32 intr_info)
+{
+	return is_exception_n(intr_info, UD_VECTOR);
+}
+
+static inline bool is_gp_fault(u32 intr_info)
+{
+	return is_exception_n(intr_info, GP_VECTOR);
+}
+
+static inline bool is_machine_check(u32 intr_info)
+{
+	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
+			     INTR_INFO_VALID_MASK)) ==
+		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
+}
+
+/* Undocumented: icebp/int1 */
+static inline bool is_icebp(u32 intr_info)
+{
+	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
+		== (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+}
+
+static inline bool is_nmi(u32 intr_info)
+{
+	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
+		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
+}
+
+static inline bool is_external_intr(u32 intr_info)
+{
+	return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
+		== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR);
+}
+
+enum vmcs_field_width {
+	VMCS_FIELD_WIDTH_U16 = 0,
+	VMCS_FIELD_WIDTH_U64 = 1,
+	VMCS_FIELD_WIDTH_U32 = 2,
+	VMCS_FIELD_WIDTH_NATURAL_WIDTH = 3
+};
+
+static inline int vmcs_field_width(unsigned long field)
+{
+	if (0x1 & field)	/* the *_HIGH fields are all 32 bit */
+		return VMCS_FIELD_WIDTH_U32;
+	return (field >> 13) & 0x3;
+}
+
+static inline int vmcs_field_readonly(unsigned long field)
+{
+	return (((field >> 10) & 0x3) == 1);
+}
+
+#endif /* __KVM_X86_VMX_VMCS_H */
diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c
new file mode 100644
index 0000000..53dfb40
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmcs12.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmcs12.h"
+
+#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n)))))
+#define VMCS12_OFFSET(x) offsetof(struct vmcs12, x)
+#define FIELD(number, name)	[ROL16(number, 6)] = VMCS12_OFFSET(name)
+#define FIELD64(number, name)						\
+	FIELD(number, name),						\
+	[ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32)
+
+const unsigned short vmcs_field_to_offset_table[] = {
+	FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id),
+	FIELD(POSTED_INTR_NV, posted_intr_nv),
+	FIELD(GUEST_ES_SELECTOR, guest_es_selector),
+	FIELD(GUEST_CS_SELECTOR, guest_cs_selector),
+	FIELD(GUEST_SS_SELECTOR, guest_ss_selector),
+	FIELD(GUEST_DS_SELECTOR, guest_ds_selector),
+	FIELD(GUEST_FS_SELECTOR, guest_fs_selector),
+	FIELD(GUEST_GS_SELECTOR, guest_gs_selector),
+	FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector),
+	FIELD(GUEST_TR_SELECTOR, guest_tr_selector),
+	FIELD(GUEST_INTR_STATUS, guest_intr_status),
+	FIELD(GUEST_PML_INDEX, guest_pml_index),
+	FIELD(HOST_ES_SELECTOR, host_es_selector),
+	FIELD(HOST_CS_SELECTOR, host_cs_selector),
+	FIELD(HOST_SS_SELECTOR, host_ss_selector),
+	FIELD(HOST_DS_SELECTOR, host_ds_selector),
+	FIELD(HOST_FS_SELECTOR, host_fs_selector),
+	FIELD(HOST_GS_SELECTOR, host_gs_selector),
+	FIELD(HOST_TR_SELECTOR, host_tr_selector),
+	FIELD64(IO_BITMAP_A, io_bitmap_a),
+	FIELD64(IO_BITMAP_B, io_bitmap_b),
+	FIELD64(MSR_BITMAP, msr_bitmap),
+	FIELD64(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr),
+	FIELD64(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr),
+	FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr),
+	FIELD64(PML_ADDRESS, pml_address),
+	FIELD64(TSC_OFFSET, tsc_offset),
+	FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr),
+	FIELD64(APIC_ACCESS_ADDR, apic_access_addr),
+	FIELD64(POSTED_INTR_DESC_ADDR, posted_intr_desc_addr),
+	FIELD64(VM_FUNCTION_CONTROL, vm_function_control),
+	FIELD64(EPT_POINTER, ept_pointer),
+	FIELD64(EOI_EXIT_BITMAP0, eoi_exit_bitmap0),
+	FIELD64(EOI_EXIT_BITMAP1, eoi_exit_bitmap1),
+	FIELD64(EOI_EXIT_BITMAP2, eoi_exit_bitmap2),
+	FIELD64(EOI_EXIT_BITMAP3, eoi_exit_bitmap3),
+	FIELD64(EPTP_LIST_ADDRESS, eptp_list_address),
+	FIELD64(VMREAD_BITMAP, vmread_bitmap),
+	FIELD64(VMWRITE_BITMAP, vmwrite_bitmap),
+	FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
+	FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
+	FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
+	FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
+	FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
+	FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
+	FIELD64(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl),
+	FIELD64(GUEST_PDPTR0, guest_pdptr0),
+	FIELD64(GUEST_PDPTR1, guest_pdptr1),
+	FIELD64(GUEST_PDPTR2, guest_pdptr2),
+	FIELD64(GUEST_PDPTR3, guest_pdptr3),
+	FIELD64(GUEST_BNDCFGS, guest_bndcfgs),
+	FIELD64(HOST_IA32_PAT, host_ia32_pat),
+	FIELD64(HOST_IA32_EFER, host_ia32_efer),
+	FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl),
+	FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control),
+	FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control),
+	FIELD(EXCEPTION_BITMAP, exception_bitmap),
+	FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask),
+	FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match),
+	FIELD(CR3_TARGET_COUNT, cr3_target_count),
+	FIELD(VM_EXIT_CONTROLS, vm_exit_controls),
+	FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count),
+	FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count),
+	FIELD(VM_ENTRY_CONTROLS, vm_entry_controls),
+	FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count),
+	FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field),
+	FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, vm_entry_exception_error_code),
+	FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len),
+	FIELD(TPR_THRESHOLD, tpr_threshold),
+	FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control),
+	FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error),
+	FIELD(VM_EXIT_REASON, vm_exit_reason),
+	FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info),
+	FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code),
+	FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field),
+	FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code),
+	FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len),
+	FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info),
+	FIELD(GUEST_ES_LIMIT, guest_es_limit),
+	FIELD(GUEST_CS_LIMIT, guest_cs_limit),
+	FIELD(GUEST_SS_LIMIT, guest_ss_limit),
+	FIELD(GUEST_DS_LIMIT, guest_ds_limit),
+	FIELD(GUEST_FS_LIMIT, guest_fs_limit),
+	FIELD(GUEST_GS_LIMIT, guest_gs_limit),
+	FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit),
+	FIELD(GUEST_TR_LIMIT, guest_tr_limit),
+	FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit),
+	FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit),
+	FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes),
+	FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes),
+	FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes),
+	FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes),
+	FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes),
+	FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes),
+	FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes),
+	FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes),
+	FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info),
+	FIELD(GUEST_ACTIVITY_STATE, guest_activity_state),
+	FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs),
+	FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs),
+	FIELD(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value),
+	FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask),
+	FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask),
+	FIELD(CR0_READ_SHADOW, cr0_read_shadow),
+	FIELD(CR4_READ_SHADOW, cr4_read_shadow),
+	FIELD(CR3_TARGET_VALUE0, cr3_target_value0),
+	FIELD(CR3_TARGET_VALUE1, cr3_target_value1),
+	FIELD(CR3_TARGET_VALUE2, cr3_target_value2),
+	FIELD(CR3_TARGET_VALUE3, cr3_target_value3),
+	FIELD(EXIT_QUALIFICATION, exit_qualification),
+	FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address),
+	FIELD(GUEST_CR0, guest_cr0),
+	FIELD(GUEST_CR3, guest_cr3),
+	FIELD(GUEST_CR4, guest_cr4),
+	FIELD(GUEST_ES_BASE, guest_es_base),
+	FIELD(GUEST_CS_BASE, guest_cs_base),
+	FIELD(GUEST_SS_BASE, guest_ss_base),
+	FIELD(GUEST_DS_BASE, guest_ds_base),
+	FIELD(GUEST_FS_BASE, guest_fs_base),
+	FIELD(GUEST_GS_BASE, guest_gs_base),
+	FIELD(GUEST_LDTR_BASE, guest_ldtr_base),
+	FIELD(GUEST_TR_BASE, guest_tr_base),
+	FIELD(GUEST_GDTR_BASE, guest_gdtr_base),
+	FIELD(GUEST_IDTR_BASE, guest_idtr_base),
+	FIELD(GUEST_DR7, guest_dr7),
+	FIELD(GUEST_RSP, guest_rsp),
+	FIELD(GUEST_RIP, guest_rip),
+	FIELD(GUEST_RFLAGS, guest_rflags),
+	FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions),
+	FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp),
+	FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip),
+	FIELD(HOST_CR0, host_cr0),
+	FIELD(HOST_CR3, host_cr3),
+	FIELD(HOST_CR4, host_cr4),
+	FIELD(HOST_FS_BASE, host_fs_base),
+	FIELD(HOST_GS_BASE, host_gs_base),
+	FIELD(HOST_TR_BASE, host_tr_base),
+	FIELD(HOST_GDTR_BASE, host_gdtr_base),
+	FIELD(HOST_IDTR_BASE, host_idtr_base),
+	FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp),
+	FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip),
+	FIELD(HOST_RSP, host_rsp),
+	FIELD(HOST_RIP, host_rip),
+};
+const unsigned int nr_vmcs12_fields = ARRAY_SIZE(vmcs_field_to_offset_table);
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
new file mode 100644
index 0000000..d0c6df3
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -0,0 +1,442 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_VMCS12_H
+#define __KVM_X86_VMX_VMCS12_H
+
+#include <linux/build_bug.h>
+
+#include "vmcs.h"
+
+/*
+ * struct vmcs12 describes the state that our guest hypervisor (L1) keeps for a
+ * single nested guest (L2), hence the name vmcs12. Any VMX implementation has
+ * a VMCS structure, and vmcs12 is our emulated VMX's VMCS. This structure is
+ * stored in guest memory specified by VMPTRLD, but is opaque to the guest,
+ * which must access it using VMREAD/VMWRITE/VMCLEAR instructions.
+ * More than one of these structures may exist, if L1 runs multiple L2 guests.
+ * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the
+ * underlying hardware which will be used to run L2.
+ * This structure is packed to ensure that its layout is identical across
+ * machines (necessary for live migration).
+ *
+ * IMPORTANT: Changing the layout of existing fields in this structure
+ * will break save/restore compatibility with older kvm releases. When
+ * adding new fields, either use space in the reserved padding* arrays
+ * or add the new fields to the end of the structure.
+ */
+typedef u64 natural_width;
+struct __packed vmcs12 {
+	/* According to the Intel spec, a VMCS region must start with the
+	 * following two fields. Then follow implementation-specific data.
+	 */
+	struct vmcs_hdr hdr;
+	u32 abort;
+
+	u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */
+	u32 padding[7]; /* room for future expansion */
+
+	u64 io_bitmap_a;
+	u64 io_bitmap_b;
+	u64 msr_bitmap;
+	u64 vm_exit_msr_store_addr;
+	u64 vm_exit_msr_load_addr;
+	u64 vm_entry_msr_load_addr;
+	u64 tsc_offset;
+	u64 virtual_apic_page_addr;
+	u64 apic_access_addr;
+	u64 posted_intr_desc_addr;
+	u64 ept_pointer;
+	u64 eoi_exit_bitmap0;
+	u64 eoi_exit_bitmap1;
+	u64 eoi_exit_bitmap2;
+	u64 eoi_exit_bitmap3;
+	u64 xss_exit_bitmap;
+	u64 guest_physical_address;
+	u64 vmcs_link_pointer;
+	u64 guest_ia32_debugctl;
+	u64 guest_ia32_pat;
+	u64 guest_ia32_efer;
+	u64 guest_ia32_perf_global_ctrl;
+	u64 guest_pdptr0;
+	u64 guest_pdptr1;
+	u64 guest_pdptr2;
+	u64 guest_pdptr3;
+	u64 guest_bndcfgs;
+	u64 host_ia32_pat;
+	u64 host_ia32_efer;
+	u64 host_ia32_perf_global_ctrl;
+	u64 vmread_bitmap;
+	u64 vmwrite_bitmap;
+	u64 vm_function_control;
+	u64 eptp_list_address;
+	u64 pml_address;
+	u64 padding64[3]; /* room for future expansion */
+	/*
+	 * To allow migration of L1 (complete with its L2 guests) between
+	 * machines of different natural widths (32 or 64 bit), we cannot have
+	 * unsigned long fields with no explicit size. We use u64 (aliased
+	 * natural_width) instead. Luckily, x86 is little-endian.
+	 */
+	natural_width cr0_guest_host_mask;
+	natural_width cr4_guest_host_mask;
+	natural_width cr0_read_shadow;
+	natural_width cr4_read_shadow;
+	natural_width cr3_target_value0;
+	natural_width cr3_target_value1;
+	natural_width cr3_target_value2;
+	natural_width cr3_target_value3;
+	natural_width exit_qualification;
+	natural_width guest_linear_address;
+	natural_width guest_cr0;
+	natural_width guest_cr3;
+	natural_width guest_cr4;
+	natural_width guest_es_base;
+	natural_width guest_cs_base;
+	natural_width guest_ss_base;
+	natural_width guest_ds_base;
+	natural_width guest_fs_base;
+	natural_width guest_gs_base;
+	natural_width guest_ldtr_base;
+	natural_width guest_tr_base;
+	natural_width guest_gdtr_base;
+	natural_width guest_idtr_base;
+	natural_width guest_dr7;
+	natural_width guest_rsp;
+	natural_width guest_rip;
+	natural_width guest_rflags;
+	natural_width guest_pending_dbg_exceptions;
+	natural_width guest_sysenter_esp;
+	natural_width guest_sysenter_eip;
+	natural_width host_cr0;
+	natural_width host_cr3;
+	natural_width host_cr4;
+	natural_width host_fs_base;
+	natural_width host_gs_base;
+	natural_width host_tr_base;
+	natural_width host_gdtr_base;
+	natural_width host_idtr_base;
+	natural_width host_ia32_sysenter_esp;
+	natural_width host_ia32_sysenter_eip;
+	natural_width host_rsp;
+	natural_width host_rip;
+	natural_width paddingl[8]; /* room for future expansion */
+	u32 pin_based_vm_exec_control;
+	u32 cpu_based_vm_exec_control;
+	u32 exception_bitmap;
+	u32 page_fault_error_code_mask;
+	u32 page_fault_error_code_match;
+	u32 cr3_target_count;
+	u32 vm_exit_controls;
+	u32 vm_exit_msr_store_count;
+	u32 vm_exit_msr_load_count;
+	u32 vm_entry_controls;
+	u32 vm_entry_msr_load_count;
+	u32 vm_entry_intr_info_field;
+	u32 vm_entry_exception_error_code;
+	u32 vm_entry_instruction_len;
+	u32 tpr_threshold;
+	u32 secondary_vm_exec_control;
+	u32 vm_instruction_error;
+	u32 vm_exit_reason;
+	u32 vm_exit_intr_info;
+	u32 vm_exit_intr_error_code;
+	u32 idt_vectoring_info_field;
+	u32 idt_vectoring_error_code;
+	u32 vm_exit_instruction_len;
+	u32 vmx_instruction_info;
+	u32 guest_es_limit;
+	u32 guest_cs_limit;
+	u32 guest_ss_limit;
+	u32 guest_ds_limit;
+	u32 guest_fs_limit;
+	u32 guest_gs_limit;
+	u32 guest_ldtr_limit;
+	u32 guest_tr_limit;
+	u32 guest_gdtr_limit;
+	u32 guest_idtr_limit;
+	u32 guest_es_ar_bytes;
+	u32 guest_cs_ar_bytes;
+	u32 guest_ss_ar_bytes;
+	u32 guest_ds_ar_bytes;
+	u32 guest_fs_ar_bytes;
+	u32 guest_gs_ar_bytes;
+	u32 guest_ldtr_ar_bytes;
+	u32 guest_tr_ar_bytes;
+	u32 guest_interruptibility_info;
+	u32 guest_activity_state;
+	u32 guest_sysenter_cs;
+	u32 host_ia32_sysenter_cs;
+	u32 vmx_preemption_timer_value;
+	u32 padding32[7]; /* room for future expansion */
+	u16 virtual_processor_id;
+	u16 posted_intr_nv;
+	u16 guest_es_selector;
+	u16 guest_cs_selector;
+	u16 guest_ss_selector;
+	u16 guest_ds_selector;
+	u16 guest_fs_selector;
+	u16 guest_gs_selector;
+	u16 guest_ldtr_selector;
+	u16 guest_tr_selector;
+	u16 guest_intr_status;
+	u16 host_es_selector;
+	u16 host_cs_selector;
+	u16 host_ss_selector;
+	u16 host_ds_selector;
+	u16 host_fs_selector;
+	u16 host_gs_selector;
+	u16 host_tr_selector;
+	u16 guest_pml_index;
+};
+
+/*
+ * VMCS12_REVISION is an arbitrary id that should be changed if the content or
+ * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and
+ * VMPTRLD verifies that the VMCS region that L1 is loading contains this id.
+ *
+ * IMPORTANT: Changing this value will break save/restore compatibility with
+ * older kvm releases.
+ */
+#define VMCS12_REVISION 0x11e57ed0
+
+/*
+ * VMCS12_SIZE is the number of bytes L1 should allocate for the VMXON region
+ * and any VMCS region. Although only sizeof(struct vmcs12) are used by the
+ * current implementation, 4K are reserved to avoid future complications and
+ * to preserve userspace ABI.
+ */
+#define VMCS12_SIZE		KVM_STATE_NESTED_VMX_VMCS_SIZE
+
+/*
+ * VMCS12_MAX_FIELD_INDEX is the highest index value used in any
+ * supported VMCS12 field encoding.
+ */
+#define VMCS12_MAX_FIELD_INDEX 0x17
+
+/*
+ * For save/restore compatibility, the vmcs12 field offsets must not change.
+ */
+#define CHECK_OFFSET(field, loc)				\
+	BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc),	\
+		"Offset of " #field " in struct vmcs12 has changed.")
+
+static inline void vmx_check_vmcs12_offsets(void)
+{
+	CHECK_OFFSET(hdr, 0);
+	CHECK_OFFSET(abort, 4);
+	CHECK_OFFSET(launch_state, 8);
+	CHECK_OFFSET(io_bitmap_a, 40);
+	CHECK_OFFSET(io_bitmap_b, 48);
+	CHECK_OFFSET(msr_bitmap, 56);
+	CHECK_OFFSET(vm_exit_msr_store_addr, 64);
+	CHECK_OFFSET(vm_exit_msr_load_addr, 72);
+	CHECK_OFFSET(vm_entry_msr_load_addr, 80);
+	CHECK_OFFSET(tsc_offset, 88);
+	CHECK_OFFSET(virtual_apic_page_addr, 96);
+	CHECK_OFFSET(apic_access_addr, 104);
+	CHECK_OFFSET(posted_intr_desc_addr, 112);
+	CHECK_OFFSET(ept_pointer, 120);
+	CHECK_OFFSET(eoi_exit_bitmap0, 128);
+	CHECK_OFFSET(eoi_exit_bitmap1, 136);
+	CHECK_OFFSET(eoi_exit_bitmap2, 144);
+	CHECK_OFFSET(eoi_exit_bitmap3, 152);
+	CHECK_OFFSET(xss_exit_bitmap, 160);
+	CHECK_OFFSET(guest_physical_address, 168);
+	CHECK_OFFSET(vmcs_link_pointer, 176);
+	CHECK_OFFSET(guest_ia32_debugctl, 184);
+	CHECK_OFFSET(guest_ia32_pat, 192);
+	CHECK_OFFSET(guest_ia32_efer, 200);
+	CHECK_OFFSET(guest_ia32_perf_global_ctrl, 208);
+	CHECK_OFFSET(guest_pdptr0, 216);
+	CHECK_OFFSET(guest_pdptr1, 224);
+	CHECK_OFFSET(guest_pdptr2, 232);
+	CHECK_OFFSET(guest_pdptr3, 240);
+	CHECK_OFFSET(guest_bndcfgs, 248);
+	CHECK_OFFSET(host_ia32_pat, 256);
+	CHECK_OFFSET(host_ia32_efer, 264);
+	CHECK_OFFSET(host_ia32_perf_global_ctrl, 272);
+	CHECK_OFFSET(vmread_bitmap, 280);
+	CHECK_OFFSET(vmwrite_bitmap, 288);
+	CHECK_OFFSET(vm_function_control, 296);
+	CHECK_OFFSET(eptp_list_address, 304);
+	CHECK_OFFSET(pml_address, 312);
+	CHECK_OFFSET(cr0_guest_host_mask, 344);
+	CHECK_OFFSET(cr4_guest_host_mask, 352);
+	CHECK_OFFSET(cr0_read_shadow, 360);
+	CHECK_OFFSET(cr4_read_shadow, 368);
+	CHECK_OFFSET(cr3_target_value0, 376);
+	CHECK_OFFSET(cr3_target_value1, 384);
+	CHECK_OFFSET(cr3_target_value2, 392);
+	CHECK_OFFSET(cr3_target_value3, 400);
+	CHECK_OFFSET(exit_qualification, 408);
+	CHECK_OFFSET(guest_linear_address, 416);
+	CHECK_OFFSET(guest_cr0, 424);
+	CHECK_OFFSET(guest_cr3, 432);
+	CHECK_OFFSET(guest_cr4, 440);
+	CHECK_OFFSET(guest_es_base, 448);
+	CHECK_OFFSET(guest_cs_base, 456);
+	CHECK_OFFSET(guest_ss_base, 464);
+	CHECK_OFFSET(guest_ds_base, 472);
+	CHECK_OFFSET(guest_fs_base, 480);
+	CHECK_OFFSET(guest_gs_base, 488);
+	CHECK_OFFSET(guest_ldtr_base, 496);
+	CHECK_OFFSET(guest_tr_base, 504);
+	CHECK_OFFSET(guest_gdtr_base, 512);
+	CHECK_OFFSET(guest_idtr_base, 520);
+	CHECK_OFFSET(guest_dr7, 528);
+	CHECK_OFFSET(guest_rsp, 536);
+	CHECK_OFFSET(guest_rip, 544);
+	CHECK_OFFSET(guest_rflags, 552);
+	CHECK_OFFSET(guest_pending_dbg_exceptions, 560);
+	CHECK_OFFSET(guest_sysenter_esp, 568);
+	CHECK_OFFSET(guest_sysenter_eip, 576);
+	CHECK_OFFSET(host_cr0, 584);
+	CHECK_OFFSET(host_cr3, 592);
+	CHECK_OFFSET(host_cr4, 600);
+	CHECK_OFFSET(host_fs_base, 608);
+	CHECK_OFFSET(host_gs_base, 616);
+	CHECK_OFFSET(host_tr_base, 624);
+	CHECK_OFFSET(host_gdtr_base, 632);
+	CHECK_OFFSET(host_idtr_base, 640);
+	CHECK_OFFSET(host_ia32_sysenter_esp, 648);
+	CHECK_OFFSET(host_ia32_sysenter_eip, 656);
+	CHECK_OFFSET(host_rsp, 664);
+	CHECK_OFFSET(host_rip, 672);
+	CHECK_OFFSET(pin_based_vm_exec_control, 744);
+	CHECK_OFFSET(cpu_based_vm_exec_control, 748);
+	CHECK_OFFSET(exception_bitmap, 752);
+	CHECK_OFFSET(page_fault_error_code_mask, 756);
+	CHECK_OFFSET(page_fault_error_code_match, 760);
+	CHECK_OFFSET(cr3_target_count, 764);
+	CHECK_OFFSET(vm_exit_controls, 768);
+	CHECK_OFFSET(vm_exit_msr_store_count, 772);
+	CHECK_OFFSET(vm_exit_msr_load_count, 776);
+	CHECK_OFFSET(vm_entry_controls, 780);
+	CHECK_OFFSET(vm_entry_msr_load_count, 784);
+	CHECK_OFFSET(vm_entry_intr_info_field, 788);
+	CHECK_OFFSET(vm_entry_exception_error_code, 792);
+	CHECK_OFFSET(vm_entry_instruction_len, 796);
+	CHECK_OFFSET(tpr_threshold, 800);
+	CHECK_OFFSET(secondary_vm_exec_control, 804);
+	CHECK_OFFSET(vm_instruction_error, 808);
+	CHECK_OFFSET(vm_exit_reason, 812);
+	CHECK_OFFSET(vm_exit_intr_info, 816);
+	CHECK_OFFSET(vm_exit_intr_error_code, 820);
+	CHECK_OFFSET(idt_vectoring_info_field, 824);
+	CHECK_OFFSET(idt_vectoring_error_code, 828);
+	CHECK_OFFSET(vm_exit_instruction_len, 832);
+	CHECK_OFFSET(vmx_instruction_info, 836);
+	CHECK_OFFSET(guest_es_limit, 840);
+	CHECK_OFFSET(guest_cs_limit, 844);
+	CHECK_OFFSET(guest_ss_limit, 848);
+	CHECK_OFFSET(guest_ds_limit, 852);
+	CHECK_OFFSET(guest_fs_limit, 856);
+	CHECK_OFFSET(guest_gs_limit, 860);
+	CHECK_OFFSET(guest_ldtr_limit, 864);
+	CHECK_OFFSET(guest_tr_limit, 868);
+	CHECK_OFFSET(guest_gdtr_limit, 872);
+	CHECK_OFFSET(guest_idtr_limit, 876);
+	CHECK_OFFSET(guest_es_ar_bytes, 880);
+	CHECK_OFFSET(guest_cs_ar_bytes, 884);
+	CHECK_OFFSET(guest_ss_ar_bytes, 888);
+	CHECK_OFFSET(guest_ds_ar_bytes, 892);
+	CHECK_OFFSET(guest_fs_ar_bytes, 896);
+	CHECK_OFFSET(guest_gs_ar_bytes, 900);
+	CHECK_OFFSET(guest_ldtr_ar_bytes, 904);
+	CHECK_OFFSET(guest_tr_ar_bytes, 908);
+	CHECK_OFFSET(guest_interruptibility_info, 912);
+	CHECK_OFFSET(guest_activity_state, 916);
+	CHECK_OFFSET(guest_sysenter_cs, 920);
+	CHECK_OFFSET(host_ia32_sysenter_cs, 924);
+	CHECK_OFFSET(vmx_preemption_timer_value, 928);
+	CHECK_OFFSET(virtual_processor_id, 960);
+	CHECK_OFFSET(posted_intr_nv, 962);
+	CHECK_OFFSET(guest_es_selector, 964);
+	CHECK_OFFSET(guest_cs_selector, 966);
+	CHECK_OFFSET(guest_ss_selector, 968);
+	CHECK_OFFSET(guest_ds_selector, 970);
+	CHECK_OFFSET(guest_fs_selector, 972);
+	CHECK_OFFSET(guest_gs_selector, 974);
+	CHECK_OFFSET(guest_ldtr_selector, 976);
+	CHECK_OFFSET(guest_tr_selector, 978);
+	CHECK_OFFSET(guest_intr_status, 980);
+	CHECK_OFFSET(host_es_selector, 982);
+	CHECK_OFFSET(host_cs_selector, 984);
+	CHECK_OFFSET(host_ss_selector, 986);
+	CHECK_OFFSET(host_ds_selector, 988);
+	CHECK_OFFSET(host_fs_selector, 990);
+	CHECK_OFFSET(host_gs_selector, 992);
+	CHECK_OFFSET(host_tr_selector, 994);
+	CHECK_OFFSET(guest_pml_index, 996);
+}
+
+extern const unsigned short vmcs_field_to_offset_table[];
+extern const unsigned int nr_vmcs12_fields;
+
+#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n)))))
+
+static inline short vmcs_field_to_offset(unsigned long field)
+{
+	unsigned short offset;
+	unsigned int index;
+
+	if (field >> 15)
+		return -ENOENT;
+
+	index = ROL16(field, 6);
+	if (index >= nr_vmcs12_fields)
+		return -ENOENT;
+
+	index = array_index_nospec(index, nr_vmcs12_fields);
+	offset = vmcs_field_to_offset_table[index];
+	if (offset == 0)
+		return -ENOENT;
+	return offset;
+}
+
+#undef ROL16
+
+static inline u64 vmcs12_read_any(struct vmcs12 *vmcs12, unsigned long field,
+				  u16 offset)
+{
+	char *p = (char *)vmcs12 + offset;
+
+	switch (vmcs_field_width(field)) {
+	case VMCS_FIELD_WIDTH_NATURAL_WIDTH:
+		return *((natural_width *)p);
+	case VMCS_FIELD_WIDTH_U16:
+		return *((u16 *)p);
+	case VMCS_FIELD_WIDTH_U32:
+		return *((u32 *)p);
+	case VMCS_FIELD_WIDTH_U64:
+		return *((u64 *)p);
+	default:
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+}
+
+static inline void vmcs12_write_any(struct vmcs12 *vmcs12, unsigned long field,
+				    u16 offset, u64 field_value)
+{
+	char *p = (char *)vmcs12 + offset;
+
+	switch (vmcs_field_width(field)) {
+	case VMCS_FIELD_WIDTH_U16:
+		*(u16 *)p = field_value;
+		break;
+	case VMCS_FIELD_WIDTH_U32:
+		*(u32 *)p = field_value;
+		break;
+	case VMCS_FIELD_WIDTH_U64:
+		*(u64 *)p = field_value;
+		break;
+	case VMCS_FIELD_WIDTH_NATURAL_WIDTH:
+		*(natural_width *)p = field_value;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+}
+
+#endif /* __KVM_X86_VMX_VMCS12_H */
diff --git a/arch/x86/kvm/vmx/vmcs_shadow_fields.h b/arch/x86/kvm/vmx/vmcs_shadow_fields.h
new file mode 100644
index 0000000..eb1ecd1
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmcs_shadow_fields.h
@@ -0,0 +1,79 @@
+#if !defined(SHADOW_FIELD_RO) && !defined(SHADOW_FIELD_RW)
+BUILD_BUG_ON(1)
+#endif
+
+#ifndef SHADOW_FIELD_RO
+#define SHADOW_FIELD_RO(x, y)
+#endif
+#ifndef SHADOW_FIELD_RW
+#define SHADOW_FIELD_RW(x, y)
+#endif
+
+/*
+ * We do NOT shadow fields that are modified when L0
+ * traps and emulates any vmx instruction (e.g. VMPTRLD,
+ * VMXON...) executed by L1.
+ * For example, VM_INSTRUCTION_ERROR is read
+ * by L1 if a vmx instruction fails (part of the error path).
+ * Note the code assumes this logic. If for some reason
+ * we start shadowing these fields then we need to
+ * force a shadow sync when L0 emulates vmx instructions
+ * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified
+ * by nested_vmx_failValid)
+ *
+ * When adding or removing fields here, note that shadowed
+ * fields must always be synced by prepare_vmcs02, not just
+ * prepare_vmcs02_full.
+ */
+
+/*
+ * Keeping the fields ordered by size is an attempt at improving
+ * branch prediction in vmcs_read_any and vmcs_write_any.
+ */
+
+/* 16-bits */
+SHADOW_FIELD_RW(GUEST_INTR_STATUS, guest_intr_status)
+SHADOW_FIELD_RW(GUEST_PML_INDEX, guest_pml_index)
+SHADOW_FIELD_RW(HOST_FS_SELECTOR, host_fs_selector)
+SHADOW_FIELD_RW(HOST_GS_SELECTOR, host_gs_selector)
+
+/* 32-bits */
+SHADOW_FIELD_RO(VM_EXIT_REASON, vm_exit_reason)
+SHADOW_FIELD_RO(VM_EXIT_INTR_INFO, vm_exit_intr_info)
+SHADOW_FIELD_RO(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len)
+SHADOW_FIELD_RO(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field)
+SHADOW_FIELD_RO(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code)
+SHADOW_FIELD_RO(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code)
+SHADOW_FIELD_RO(GUEST_CS_AR_BYTES, guest_cs_ar_bytes)
+SHADOW_FIELD_RO(GUEST_SS_AR_BYTES, guest_ss_ar_bytes)
+SHADOW_FIELD_RW(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control)
+SHADOW_FIELD_RW(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control)
+SHADOW_FIELD_RW(EXCEPTION_BITMAP, exception_bitmap)
+SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE, vm_entry_exception_error_code)
+SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field)
+SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len)
+SHADOW_FIELD_RW(TPR_THRESHOLD, tpr_threshold)
+SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info)
+SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value)
+
+/* Natural width */
+SHADOW_FIELD_RO(EXIT_QUALIFICATION, exit_qualification)
+SHADOW_FIELD_RO(GUEST_LINEAR_ADDRESS, guest_linear_address)
+SHADOW_FIELD_RW(GUEST_RIP, guest_rip)
+SHADOW_FIELD_RW(GUEST_RSP, guest_rsp)
+SHADOW_FIELD_RW(GUEST_CR0, guest_cr0)
+SHADOW_FIELD_RW(GUEST_CR3, guest_cr3)
+SHADOW_FIELD_RW(GUEST_CR4, guest_cr4)
+SHADOW_FIELD_RW(GUEST_RFLAGS, guest_rflags)
+SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK, cr0_guest_host_mask)
+SHADOW_FIELD_RW(CR0_READ_SHADOW, cr0_read_shadow)
+SHADOW_FIELD_RW(CR4_READ_SHADOW, cr4_read_shadow)
+SHADOW_FIELD_RW(HOST_FS_BASE, host_fs_base)
+SHADOW_FIELD_RW(HOST_GS_BASE, host_gs_base)
+
+/* 64-bit */
+SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS, guest_physical_address)
+SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS_HIGH, guest_physical_address)
+
+#undef SHADOW_FIELD_RO
+#undef SHADOW_FIELD_RW
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
new file mode 100644
index 0000000..751a384
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -0,0 +1,236 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/bitsperlong.h>
+#include <asm/kvm_vcpu_regs.h>
+#include <asm/nospec-branch.h>
+
+#define WORD_SIZE (BITS_PER_LONG / 8)
+
+#define VCPU_RAX	__VCPU_REGS_RAX * WORD_SIZE
+#define VCPU_RCX	__VCPU_REGS_RCX * WORD_SIZE
+#define VCPU_RDX	__VCPU_REGS_RDX * WORD_SIZE
+#define VCPU_RBX	__VCPU_REGS_RBX * WORD_SIZE
+/* Intentionally omit RSP as it's context switched by hardware */
+#define VCPU_RBP	__VCPU_REGS_RBP * WORD_SIZE
+#define VCPU_RSI	__VCPU_REGS_RSI * WORD_SIZE
+#define VCPU_RDI	__VCPU_REGS_RDI * WORD_SIZE
+
+#ifdef CONFIG_X86_64
+#define VCPU_R8		__VCPU_REGS_R8  * WORD_SIZE
+#define VCPU_R9		__VCPU_REGS_R9  * WORD_SIZE
+#define VCPU_R10	__VCPU_REGS_R10 * WORD_SIZE
+#define VCPU_R11	__VCPU_REGS_R11 * WORD_SIZE
+#define VCPU_R12	__VCPU_REGS_R12 * WORD_SIZE
+#define VCPU_R13	__VCPU_REGS_R13 * WORD_SIZE
+#define VCPU_R14	__VCPU_REGS_R14 * WORD_SIZE
+#define VCPU_R15	__VCPU_REGS_R15 * WORD_SIZE
+#endif
+
+	.text
+
+/**
+ * vmx_vmenter - VM-Enter the current loaded VMCS
+ *
+ * %RFLAGS.ZF:	!VMCS.LAUNCHED, i.e. controls VMLAUNCH vs. VMRESUME
+ *
+ * Returns:
+ *	%RFLAGS.CF is set on VM-Fail Invalid
+ *	%RFLAGS.ZF is set on VM-Fail Valid
+ *	%RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit
+ *
+ * Note that VMRESUME/VMLAUNCH fall-through and return directly if
+ * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump
+ * to vmx_vmexit.
+ */
+ENTRY(vmx_vmenter)
+	/* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */
+	je 2f
+
+1:	vmresume
+	ret
+
+2:	vmlaunch
+	ret
+
+3:	cmpb $0, kvm_rebooting
+	je 4f
+	ret
+4:	ud2
+
+	.pushsection .fixup, "ax"
+5:	jmp 3b
+	.popsection
+
+	_ASM_EXTABLE(1b, 5b)
+	_ASM_EXTABLE(2b, 5b)
+
+ENDPROC(vmx_vmenter)
+
+/**
+ * vmx_vmexit - Handle a VMX VM-Exit
+ *
+ * Returns:
+ *	%RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit
+ *
+ * This is vmx_vmenter's partner in crime.  On a VM-Exit, control will jump
+ * here after hardware loads the host's state, i.e. this is the destination
+ * referred to by VMCS.HOST_RIP.
+ */
+ENTRY(vmx_vmexit)
+#ifdef CONFIG_RETPOLINE
+	ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE
+	/* Preserve guest's RAX, it's used to stuff the RSB. */
+	push %_ASM_AX
+
+	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+
+	pop %_ASM_AX
+.Lvmexit_skip_rsb:
+#endif
+	ret
+ENDPROC(vmx_vmexit)
+
+/**
+ * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode
+ * @vmx:	struct vcpu_vmx * (forwarded to vmx_update_host_rsp)
+ * @regs:	unsigned long * (to guest registers)
+ * @launched:	%true if the VMCS has been launched
+ *
+ * Returns:
+ *	0 on VM-Exit, 1 on VM-Fail
+ */
+ENTRY(__vmx_vcpu_run)
+	push %_ASM_BP
+	mov  %_ASM_SP, %_ASM_BP
+#ifdef CONFIG_X86_64
+	push %r15
+	push %r14
+	push %r13
+	push %r12
+#else
+	push %edi
+	push %esi
+#endif
+	push %_ASM_BX
+
+	/*
+	 * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and
+	 * @regs is needed after VM-Exit to save the guest's register values.
+	 */
+	push %_ASM_ARG2
+
+	/* Copy @launched to BL, _ASM_ARG3 is volatile. */
+	mov %_ASM_ARG3B, %bl
+
+	/* Adjust RSP to account for the CALL to vmx_vmenter(). */
+	lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2
+	call vmx_update_host_rsp
+
+	/* Load @regs to RAX. */
+	mov (%_ASM_SP), %_ASM_AX
+
+	/* Check if vmlaunch or vmresume is needed */
+	cmpb $0, %bl
+
+	/* Load guest registers.  Don't clobber flags. */
+	mov VCPU_RBX(%_ASM_AX), %_ASM_BX
+	mov VCPU_RCX(%_ASM_AX), %_ASM_CX
+	mov VCPU_RDX(%_ASM_AX), %_ASM_DX
+	mov VCPU_RSI(%_ASM_AX), %_ASM_SI
+	mov VCPU_RDI(%_ASM_AX), %_ASM_DI
+	mov VCPU_RBP(%_ASM_AX), %_ASM_BP
+#ifdef CONFIG_X86_64
+	mov VCPU_R8 (%_ASM_AX),  %r8
+	mov VCPU_R9 (%_ASM_AX),  %r9
+	mov VCPU_R10(%_ASM_AX), %r10
+	mov VCPU_R11(%_ASM_AX), %r11
+	mov VCPU_R12(%_ASM_AX), %r12
+	mov VCPU_R13(%_ASM_AX), %r13
+	mov VCPU_R14(%_ASM_AX), %r14
+	mov VCPU_R15(%_ASM_AX), %r15
+#endif
+	/* Load guest RAX.  This kills the @regs pointer! */
+	mov VCPU_RAX(%_ASM_AX), %_ASM_AX
+
+	/* Enter guest mode */
+	call vmx_vmenter
+
+	/* Jump on VM-Fail. */
+	jbe 2f
+
+	/* Temporarily save guest's RAX. */
+	push %_ASM_AX
+
+	/* Reload @regs to RAX. */
+	mov WORD_SIZE(%_ASM_SP), %_ASM_AX
+
+	/* Save all guest registers, including RAX from the stack */
+	__ASM_SIZE(pop) VCPU_RAX(%_ASM_AX)
+	mov %_ASM_BX,   VCPU_RBX(%_ASM_AX)
+	mov %_ASM_CX,   VCPU_RCX(%_ASM_AX)
+	mov %_ASM_DX,   VCPU_RDX(%_ASM_AX)
+	mov %_ASM_SI,   VCPU_RSI(%_ASM_AX)
+	mov %_ASM_DI,   VCPU_RDI(%_ASM_AX)
+	mov %_ASM_BP,   VCPU_RBP(%_ASM_AX)
+#ifdef CONFIG_X86_64
+	mov %r8,  VCPU_R8 (%_ASM_AX)
+	mov %r9,  VCPU_R9 (%_ASM_AX)
+	mov %r10, VCPU_R10(%_ASM_AX)
+	mov %r11, VCPU_R11(%_ASM_AX)
+	mov %r12, VCPU_R12(%_ASM_AX)
+	mov %r13, VCPU_R13(%_ASM_AX)
+	mov %r14, VCPU_R14(%_ASM_AX)
+	mov %r15, VCPU_R15(%_ASM_AX)
+#endif
+
+	/* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */
+	xor %eax, %eax
+
+	/*
+	 * Clear all general purpose registers except RSP and RAX to prevent
+	 * speculative use of the guest's values, even those that are reloaded
+	 * via the stack.  In theory, an L1 cache miss when restoring registers
+	 * could lead to speculative execution with the guest's values.
+	 * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially
+	 * free.  RSP and RAX are exempt as RSP is restored by hardware during
+	 * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail.
+	 */
+1:	xor %ebx, %ebx
+	xor %ecx, %ecx
+	xor %edx, %edx
+	xor %esi, %esi
+	xor %edi, %edi
+	xor %ebp, %ebp
+#ifdef CONFIG_X86_64
+	xor %r8d,  %r8d
+	xor %r9d,  %r9d
+	xor %r10d, %r10d
+	xor %r11d, %r11d
+	xor %r12d, %r12d
+	xor %r13d, %r13d
+	xor %r14d, %r14d
+	xor %r15d, %r15d
+#endif
+
+	/* "POP" @regs. */
+	add $WORD_SIZE, %_ASM_SP
+	pop %_ASM_BX
+
+#ifdef CONFIG_X86_64
+	pop %r12
+	pop %r13
+	pop %r14
+	pop %r15
+#else
+	pop %esi
+	pop %edi
+#endif
+	pop %_ASM_BP
+	ret
+
+	/* VM-Fail.  Out-of-line to avoid a taken Jcc after VM-Exit. */
+2:	mov $1, %eax
+	jmp 1b
+ENDPROC(__vmx_vcpu_run)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
new file mode 100644
index 0000000..04a8212
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -0,0 +1,8014 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Kernel-based Virtual Machine driver for Linux
+ *
+ * This module enables machines with Intel VT-x extensions to run virtual
+ * machines without emulation or binary translation.
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * Authors:
+ *   Avi Kivity   <avi@qumranet.com>
+ *   Yaniv Kamay  <yaniv@qumranet.com>
+ */
+
+#include <linux/frame.h>
+#include <linux/highmem.h>
+#include <linux/hrtimer.h>
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/mod_devicetable.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/sched/smt.h>
+#include <linux/slab.h>
+#include <linux/tboot.h>
+#include <linux/trace_events.h>
+
+#include <asm/apic.h>
+#include <asm/asm.h>
+#include <asm/cpu.h>
+#include <asm/debugreg.h>
+#include <asm/desc.h>
+#include <asm/fpu/internal.h>
+#include <asm/io.h>
+#include <asm/irq_remapping.h>
+#include <asm/kexec.h>
+#include <asm/perf_event.h>
+#include <asm/mce.h>
+#include <asm/mmu_context.h>
+#include <asm/mshyperv.h>
+#include <asm/spec-ctrl.h>
+#include <asm/virtext.h>
+#include <asm/vmx.h>
+
+#include "capabilities.h"
+#include "cpuid.h"
+#include "evmcs.h"
+#include "irq.h"
+#include "kvm_cache_regs.h"
+#include "lapic.h"
+#include "mmu.h"
+#include "nested.h"
+#include "ops.h"
+#include "pmu.h"
+#include "trace.h"
+#include "vmcs.h"
+#include "vmcs12.h"
+#include "vmx.h"
+#include "x86.h"
+
+MODULE_AUTHOR("Qumranet");
+MODULE_LICENSE("GPL");
+
+static const struct x86_cpu_id vmx_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_VMX),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+
+bool __read_mostly enable_vpid = 1;
+module_param_named(vpid, enable_vpid, bool, 0444);
+
+static bool __read_mostly enable_vnmi = 1;
+module_param_named(vnmi, enable_vnmi, bool, S_IRUGO);
+
+bool __read_mostly flexpriority_enabled = 1;
+module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);
+
+bool __read_mostly enable_ept = 1;
+module_param_named(ept, enable_ept, bool, S_IRUGO);
+
+bool __read_mostly enable_unrestricted_guest = 1;
+module_param_named(unrestricted_guest,
+			enable_unrestricted_guest, bool, S_IRUGO);
+
+bool __read_mostly enable_ept_ad_bits = 1;
+module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO);
+
+static bool __read_mostly emulate_invalid_guest_state = true;
+module_param(emulate_invalid_guest_state, bool, S_IRUGO);
+
+static bool __read_mostly fasteoi = 1;
+module_param(fasteoi, bool, S_IRUGO);
+
+static bool __read_mostly enable_apicv = 1;
+module_param(enable_apicv, bool, S_IRUGO);
+
+/*
+ * If nested=1, nested virtualization is supported, i.e., guests may use
+ * VMX and be a hypervisor for its own guests. If nested=0, guests may not
+ * use VMX instructions.
+ */
+static bool __read_mostly nested = 1;
+module_param(nested, bool, S_IRUGO);
+
+static u64 __read_mostly host_xss;
+
+bool __read_mostly enable_pml = 1;
+module_param_named(pml, enable_pml, bool, S_IRUGO);
+
+static bool __read_mostly dump_invalid_vmcs = 0;
+module_param(dump_invalid_vmcs, bool, 0644);
+
+#define MSR_BITMAP_MODE_X2APIC		1
+#define MSR_BITMAP_MODE_X2APIC_APICV	2
+
+#define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL
+
+/* Guest_tsc -> host_tsc conversion requires 64-bit division.  */
+static int __read_mostly cpu_preemption_timer_multi;
+static bool __read_mostly enable_preemption_timer = 1;
+#ifdef CONFIG_X86_64
+module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
+#endif
+
+#define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
+#define KVM_VM_CR0_ALWAYS_ON				\
+	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | 	\
+	 X86_CR0_WP | X86_CR0_PG | X86_CR0_PE)
+#define KVM_CR4_GUEST_OWNED_BITS				      \
+	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
+	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD)
+
+#define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE
+#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
+#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
+
+#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
+
+#define MSR_IA32_RTIT_STATUS_MASK (~(RTIT_STATUS_FILTEREN | \
+	RTIT_STATUS_CONTEXTEN | RTIT_STATUS_TRIGGEREN | \
+	RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \
+	RTIT_STATUS_BYTECNT))
+
+#define MSR_IA32_RTIT_OUTPUT_BASE_MASK \
+	(~((1UL << cpuid_query_maxphyaddr(vcpu)) - 1) | 0x7f)
+
+/*
+ * These 2 parameters are used to config the controls for Pause-Loop Exiting:
+ * ple_gap:    upper bound on the amount of time between two successive
+ *             executions of PAUSE in a loop. Also indicate if ple enabled.
+ *             According to test, this time is usually smaller than 128 cycles.
+ * ple_window: upper bound on the amount of time a guest is allowed to execute
+ *             in a PAUSE loop. Tests indicate that most spinlocks are held for
+ *             less than 2^12 cycles
+ * Time is measured based on a counter that runs at the same rate as the TSC,
+ * refer SDM volume 3b section 21.6.13 & 22.1.3.
+ */
+static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP;
+module_param(ple_gap, uint, 0444);
+
+static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
+module_param(ple_window, uint, 0444);
+
+/* Default doubles per-vcpu window every exit. */
+static unsigned int ple_window_grow = KVM_DEFAULT_PLE_WINDOW_GROW;
+module_param(ple_window_grow, uint, 0444);
+
+/* Default resets per-vcpu window every exit to ple_window. */
+static unsigned int ple_window_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK;
+module_param(ple_window_shrink, uint, 0444);
+
+/* Default is to compute the maximum so we can never overflow. */
+static unsigned int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
+module_param(ple_window_max, uint, 0444);
+
+/* Default is SYSTEM mode, 1 for host-guest mode */
+int __read_mostly pt_mode = PT_MODE_SYSTEM;
+module_param(pt_mode, int, S_IRUGO);
+
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
+static DEFINE_MUTEX(vmx_l1d_flush_mutex);
+
+/* Storage for pre module init parameter parsing */
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;
+
+static const struct {
+	const char *option;
+	bool for_parse;
+} vmentry_l1d_param[] = {
+	[VMENTER_L1D_FLUSH_AUTO]	 = {"auto", true},
+	[VMENTER_L1D_FLUSH_NEVER]	 = {"never", true},
+	[VMENTER_L1D_FLUSH_COND]	 = {"cond", true},
+	[VMENTER_L1D_FLUSH_ALWAYS]	 = {"always", true},
+	[VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false},
+	[VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false},
+};
+
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
+{
+	struct page *page;
+	unsigned int i;
+
+	if (!boot_cpu_has_bug(X86_BUG_L1TF)) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+		return 0;
+	}
+
+	if (!enable_ept) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
+		return 0;
+	}
+
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
+		u64 msr;
+
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+		if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
+			l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+			return 0;
+		}
+	}
+
+	/* If set to auto use the default l1tf mitigation method */
+	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+			l1tf = VMENTER_L1D_FLUSH_NEVER;
+			break;
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+			l1tf = VMENTER_L1D_FLUSH_COND;
+			break;
+		case L1TF_MITIGATION_FULL:
+		case L1TF_MITIGATION_FULL_FORCE:
+			l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+			break;
+		}
+	} else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) {
+		l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+	}
+
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
+	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		/*
+		 * This allocation for vmx_l1d_flush_pages is not tied to a VM
+		 * lifetime and so should not be charged to a memcg.
+		 */
+		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+		if (!page)
+			return -ENOMEM;
+		vmx_l1d_flush_pages = page_address(page);
+
+		/*
+		 * Initialize each page with a different pattern in
+		 * order to protect against KSM in the nested
+		 * virtualization case.
+		 */
+		for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) {
+			memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1,
+			       PAGE_SIZE);
+		}
+	}
+
+	l1tf_vmx_mitigation = l1tf;
+
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER)
+		static_branch_enable(&vmx_l1d_should_flush);
+	else
+		static_branch_disable(&vmx_l1d_should_flush);
+
+	if (l1tf == VMENTER_L1D_FLUSH_COND)
+		static_branch_enable(&vmx_l1d_flush_cond);
+	else
+		static_branch_disable(&vmx_l1d_flush_cond);
+	return 0;
+}
+
+static int vmentry_l1d_flush_parse(const char *s)
+{
+	unsigned int i;
+
+	if (s) {
+		for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+			if (vmentry_l1d_param[i].for_parse &&
+			    sysfs_streq(s, vmentry_l1d_param[i].option))
+				return i;
+		}
+	}
+	return -EINVAL;
+}
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+	int l1tf, ret;
+
+	l1tf = vmentry_l1d_flush_parse(s);
+	if (l1tf < 0)
+		return l1tf;
+
+	if (!boot_cpu_has(X86_BUG_L1TF))
+		return 0;
+
+	/*
+	 * Has vmx_init() run already? If not then this is the pre init
+	 * parameter parsing. In that case just store the value and let
+	 * vmx_init() do the proper setup after enable_ept has been
+	 * established.
+	 */
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) {
+		vmentry_l1d_flush_param = l1tf;
+		return 0;
+	}
+
+	mutex_lock(&vmx_l1d_flush_mutex);
+	ret = vmx_setup_l1d_flush(l1tf);
+	mutex_unlock(&vmx_l1d_flush_mutex);
+	return ret;
+}
+
+static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
+{
+	if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param)))
+		return sprintf(s, "???\n");
+
+	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
+}
+
+static const struct kernel_param_ops vmentry_l1d_flush_ops = {
+	.set = vmentry_l1d_flush_set,
+	.get = vmentry_l1d_flush_get,
+};
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);
+
+static bool guest_state_valid(struct kvm_vcpu *vcpu);
+static u32 vmx_segment_access_rights(struct kvm_segment *var);
+static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+							  u32 msr, int type);
+
+void vmx_vmexit(void);
+
+#define vmx_insn_failed(fmt...)		\
+do {					\
+	WARN_ONCE(1, fmt);		\
+	pr_warn_ratelimited(fmt);	\
+} while (0)
+
+asmlinkage void vmread_error(unsigned long field, bool fault)
+{
+	if (fault)
+		kvm_spurious_fault();
+	else
+		vmx_insn_failed("kvm: vmread failed: field=%lx\n", field);
+}
+
+noinline void vmwrite_error(unsigned long field, unsigned long value)
+{
+	vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%d\n",
+			field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
+}
+
+noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr)
+{
+	vmx_insn_failed("kvm: vmclear failed: %p/%llx\n", vmcs, phys_addr);
+}
+
+noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr)
+{
+	vmx_insn_failed("kvm: vmptrld failed: %p/%llx\n", vmcs, phys_addr);
+}
+
+noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva)
+{
+	vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n",
+			ext, vpid, gva);
+}
+
+noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa)
+{
+	vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n",
+			ext, eptp, gpa);
+}
+
+static DEFINE_PER_CPU(struct vmcs *, vmxarea);
+DEFINE_PER_CPU(struct vmcs *, current_vmcs);
+/*
+ * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed
+ * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it.
+ */
+static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
+
+/*
+ * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we
+ * can find which vCPU should be waken up.
+ */
+static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
+static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
+
+static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
+static DEFINE_SPINLOCK(vmx_vpid_lock);
+
+struct vmcs_config vmcs_config;
+struct vmx_capability vmx_capability;
+
+#define VMX_SEGMENT_FIELD(seg)					\
+	[VCPU_SREG_##seg] = {                                   \
+		.selector = GUEST_##seg##_SELECTOR,		\
+		.base = GUEST_##seg##_BASE,		   	\
+		.limit = GUEST_##seg##_LIMIT,		   	\
+		.ar_bytes = GUEST_##seg##_AR_BYTES,	   	\
+	}
+
+static const struct kvm_vmx_segment_field {
+	unsigned selector;
+	unsigned base;
+	unsigned limit;
+	unsigned ar_bytes;
+} kvm_vmx_segment_fields[] = {
+	VMX_SEGMENT_FIELD(CS),
+	VMX_SEGMENT_FIELD(DS),
+	VMX_SEGMENT_FIELD(ES),
+	VMX_SEGMENT_FIELD(FS),
+	VMX_SEGMENT_FIELD(GS),
+	VMX_SEGMENT_FIELD(SS),
+	VMX_SEGMENT_FIELD(TR),
+	VMX_SEGMENT_FIELD(LDTR),
+};
+
+u64 host_efer;
+static unsigned long host_idt_base;
+
+/*
+ * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm
+ * will emulate SYSCALL in legacy mode if the vendor string in guest
+ * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To
+ * support this emulation, IA32_STAR must always be included in
+ * vmx_msr_index[], even in i386 builds.
+ */
+const u32 vmx_msr_index[] = {
+#ifdef CONFIG_X86_64
+	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
+#endif
+	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
+};
+
+#if IS_ENABLED(CONFIG_HYPERV)
+static bool __read_mostly enlightened_vmcs = true;
+module_param(enlightened_vmcs, bool, 0444);
+
+/* check_ept_pointer() should be under protection of ept_pointer_lock. */
+static void check_ept_pointer_match(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	u64 tmp_eptp = INVALID_PAGE;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!VALID_PAGE(tmp_eptp)) {
+			tmp_eptp = to_vmx(vcpu)->ept_pointer;
+		} else if (tmp_eptp != to_vmx(vcpu)->ept_pointer) {
+			to_kvm_vmx(kvm)->ept_pointers_match
+				= EPT_POINTERS_MISMATCH;
+			return;
+		}
+	}
+
+	to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH;
+}
+
+static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
+		void *data)
+{
+	struct kvm_tlb_range *range = data;
+
+	return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn,
+			range->pages);
+}
+
+static inline int __hv_remote_flush_tlb_with_range(struct kvm *kvm,
+		struct kvm_vcpu *vcpu, struct kvm_tlb_range *range)
+{
+	u64 ept_pointer = to_vmx(vcpu)->ept_pointer;
+
+	/*
+	 * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs address
+	 * of the base of EPT PML4 table, strip off EPT configuration
+	 * information.
+	 */
+	if (range)
+		return hyperv_flush_guest_mapping_range(ept_pointer & PAGE_MASK,
+				kvm_fill_hv_flush_list_func, (void *)range);
+	else
+		return hyperv_flush_guest_mapping(ept_pointer & PAGE_MASK);
+}
+
+static int hv_remote_flush_tlb_with_range(struct kvm *kvm,
+		struct kvm_tlb_range *range)
+{
+	struct kvm_vcpu *vcpu;
+	int ret = 0, i;
+
+	spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock);
+
+	if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK)
+		check_ept_pointer_match(kvm);
+
+	if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) {
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			/* If ept_pointer is invalid pointer, bypass flush request. */
+			if (VALID_PAGE(to_vmx(vcpu)->ept_pointer))
+				ret |= __hv_remote_flush_tlb_with_range(
+					kvm, vcpu, range);
+		}
+	} else {
+		ret = __hv_remote_flush_tlb_with_range(kvm,
+				kvm_get_vcpu(kvm, 0), range);
+	}
+
+	spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
+	return ret;
+}
+static int hv_remote_flush_tlb(struct kvm *kvm)
+{
+	return hv_remote_flush_tlb_with_range(kvm, NULL);
+}
+
+static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu)
+{
+	struct hv_enlightened_vmcs *evmcs;
+	struct hv_partition_assist_pg **p_hv_pa_pg =
+			&vcpu->kvm->arch.hyperv.hv_pa_pg;
+	/*
+	 * Synthetic VM-Exit is not enabled in current code and so All
+	 * evmcs in singe VM shares same assist page.
+	 */
+	if (!*p_hv_pa_pg)
+		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL);
+
+	if (!*p_hv_pa_pg)
+		return -ENOMEM;
+
+	evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs;
+
+	evmcs->partition_assist_page =
+		__pa(*p_hv_pa_pg);
+	evmcs->hv_vm_id = (unsigned long)vcpu->kvm;
+	evmcs->hv_enlightenments_control.nested_flush_hypercall = 1;
+
+	return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_HYPERV) */
+
+/*
+ * Comment's format: document - errata name - stepping - processor name.
+ * Refer from
+ * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp
+ */
+static u32 vmx_preemption_cpu_tfms[] = {
+/* 323344.pdf - BA86   - D0 - Xeon 7500 Series */
+0x000206E6,
+/* 323056.pdf - AAX65  - C2 - Xeon L3406 */
+/* 322814.pdf - AAT59  - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */
+/* 322911.pdf - AAU65  - C2 - i5-600, i3-500 Desktop and Pentium G6950 */
+0x00020652,
+/* 322911.pdf - AAU65  - K0 - i5-600, i3-500 Desktop and Pentium G6950 */
+0x00020655,
+/* 322373.pdf - AAO95  - B1 - Xeon 3400 Series */
+/* 322166.pdf - AAN92  - B1 - i7-800 and i5-700 Desktop */
+/*
+ * 320767.pdf - AAP86  - B1 -
+ * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile
+ */
+0x000106E5,
+/* 321333.pdf - AAM126 - C0 - Xeon 3500 */
+0x000106A0,
+/* 321333.pdf - AAM126 - C1 - Xeon 3500 */
+0x000106A1,
+/* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */
+0x000106A4,
+ /* 321333.pdf - AAM126 - D0 - Xeon 3500 */
+ /* 321324.pdf - AAK139 - D0 - Xeon 5500 */
+ /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */
+0x000106A5,
+ /* Xeon E3-1220 V2 */
+0x000306A8,
+};
+
+static inline bool cpu_has_broken_vmx_preemption_timer(void)
+{
+	u32 eax = cpuid_eax(0x00000001), i;
+
+	/* Clear the reserved bits */
+	eax &= ~(0x3U << 14 | 0xfU << 28);
+	for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++)
+		if (eax == vmx_preemption_cpu_tfms[i])
+			return true;
+
+	return false;
+}
+
+static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
+{
+	return flexpriority_enabled && lapic_in_kernel(vcpu);
+}
+
+static inline bool report_flexpriority(void)
+{
+	return flexpriority_enabled;
+}
+
+static inline int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
+{
+	int i;
+
+	for (i = 0; i < vmx->nmsrs; ++i)
+		if (vmx_msr_index[vmx->guest_msrs[i].index] == msr)
+			return i;
+	return -1;
+}
+
+struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
+{
+	int i;
+
+	i = __find_msr_index(vmx, msr);
+	if (i >= 0)
+		return &vmx->guest_msrs[i];
+	return NULL;
+}
+
+void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
+{
+	vmcs_clear(loaded_vmcs->vmcs);
+	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
+	loaded_vmcs->cpu = -1;
+	loaded_vmcs->launched = 0;
+}
+
+#ifdef CONFIG_KEXEC_CORE
+/*
+ * This bitmap is used to indicate whether the vmclear
+ * operation is enabled on all cpus. All disabled by
+ * default.
+ */
+static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
+
+static inline void crash_enable_local_vmclear(int cpu)
+{
+	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static inline void crash_disable_local_vmclear(int cpu)
+{
+	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static inline int crash_local_vmclear_enabled(int cpu)
+{
+	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static void crash_vmclear_local_loaded_vmcss(void)
+{
+	int cpu = raw_smp_processor_id();
+	struct loaded_vmcs *v;
+
+	if (!crash_local_vmclear_enabled(cpu))
+		return;
+
+	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
+			    loaded_vmcss_on_cpu_link)
+		vmcs_clear(v->vmcs);
+}
+#else
+static inline void crash_enable_local_vmclear(int cpu) { }
+static inline void crash_disable_local_vmclear(int cpu) { }
+#endif /* CONFIG_KEXEC_CORE */
+
+static void __loaded_vmcs_clear(void *arg)
+{
+	struct loaded_vmcs *loaded_vmcs = arg;
+	int cpu = raw_smp_processor_id();
+
+	if (loaded_vmcs->cpu != cpu)
+		return; /* vcpu migration can race with cpu offline */
+	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
+		per_cpu(current_vmcs, cpu) = NULL;
+	crash_disable_local_vmclear(cpu);
+	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
+
+	/*
+	 * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link
+	 * is before setting loaded_vmcs->vcpu to -1 which is done in
+	 * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist
+	 * then adds the vmcs into percpu list before it is deleted.
+	 */
+	smp_wmb();
+
+	loaded_vmcs_init(loaded_vmcs);
+	crash_enable_local_vmclear(cpu);
+}
+
+void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
+{
+	int cpu = loaded_vmcs->cpu;
+
+	if (cpu != -1)
+		smp_call_function_single(cpu,
+			 __loaded_vmcs_clear, loaded_vmcs, 1);
+}
+
+static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg,
+				       unsigned field)
+{
+	bool ret;
+	u32 mask = 1 << (seg * SEG_FIELD_NR + field);
+
+	if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) {
+		vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS);
+		vmx->segment_cache.bitmask = 0;
+	}
+	ret = vmx->segment_cache.bitmask & mask;
+	vmx->segment_cache.bitmask |= mask;
+	return ret;
+}
+
+static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg)
+{
+	u16 *p = &vmx->segment_cache.seg[seg].selector;
+
+	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL))
+		*p = vmcs_read16(kvm_vmx_segment_fields[seg].selector);
+	return *p;
+}
+
+static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg)
+{
+	ulong *p = &vmx->segment_cache.seg[seg].base;
+
+	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE))
+		*p = vmcs_readl(kvm_vmx_segment_fields[seg].base);
+	return *p;
+}
+
+static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg)
+{
+	u32 *p = &vmx->segment_cache.seg[seg].limit;
+
+	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT))
+		*p = vmcs_read32(kvm_vmx_segment_fields[seg].limit);
+	return *p;
+}
+
+static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg)
+{
+	u32 *p = &vmx->segment_cache.seg[seg].ar;
+
+	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR))
+		*p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes);
+	return *p;
+}
+
+void update_exception_bitmap(struct kvm_vcpu *vcpu)
+{
+	u32 eb;
+
+	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
+	     (1u << DB_VECTOR) | (1u << AC_VECTOR);
+	/*
+	 * Guest access to VMware backdoor ports could legitimately
+	 * trigger #GP because of TSS I/O permission bitmap.
+	 * We intercept those #GP and allow access to them anyway
+	 * as VMware does.
+	 */
+	if (enable_vmware_backdoor)
+		eb |= (1u << GP_VECTOR);
+	if ((vcpu->guest_debug &
+	     (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
+	    (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP))
+		eb |= 1u << BP_VECTOR;
+	if (to_vmx(vcpu)->rmode.vm86_active)
+		eb = ~0;
+	if (enable_ept)
+		eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
+
+	/* When we are running a nested L2 guest and L1 specified for it a
+	 * certain exception bitmap, we must trap the same exceptions and pass
+	 * them to L1. When running L2, we will only handle the exceptions
+	 * specified above if L1 did not want them.
+	 */
+	if (is_guest_mode(vcpu))
+		eb |= get_vmcs12(vcpu)->exception_bitmap;
+
+	vmcs_write32(EXCEPTION_BITMAP, eb);
+}
+
+/*
+ * Check if MSR is intercepted for currently loaded MSR bitmap.
+ */
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
+{
+	unsigned long *msr_bitmap;
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return true;
+
+	msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap;
+
+	if (msr <= 0x1fff) {
+		return !!test_bit(msr, msr_bitmap + 0x800 / f);
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+	}
+
+	return true;
+}
+
+static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
+		unsigned long entry, unsigned long exit)
+{
+	vm_entry_controls_clearbit(vmx, entry);
+	vm_exit_controls_clearbit(vmx, exit);
+}
+
+static int find_msr(struct vmx_msrs *m, unsigned int msr)
+{
+	unsigned int i;
+
+	for (i = 0; i < m->nr; ++i) {
+		if (m->val[i].index == msr)
+			return i;
+	}
+	return -ENOENT;
+}
+
+static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
+{
+	int i;
+	struct msr_autoload *m = &vmx->msr_autoload;
+
+	switch (msr) {
+	case MSR_EFER:
+		if (cpu_has_load_ia32_efer()) {
+			clear_atomic_switch_msr_special(vmx,
+					VM_ENTRY_LOAD_IA32_EFER,
+					VM_EXIT_LOAD_IA32_EFER);
+			return;
+		}
+		break;
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+		if (cpu_has_load_perf_global_ctrl()) {
+			clear_atomic_switch_msr_special(vmx,
+					VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+					VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
+			return;
+		}
+		break;
+	}
+	i = find_msr(&m->guest, msr);
+	if (i < 0)
+		goto skip_guest;
+	--m->guest.nr;
+	m->guest.val[i] = m->guest.val[m->guest.nr];
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+
+skip_guest:
+	i = find_msr(&m->host, msr);
+	if (i < 0)
+		return;
+
+	--m->host.nr;
+	m->host.val[i] = m->host.val[m->host.nr];
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
+}
+
+static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
+		unsigned long entry, unsigned long exit,
+		unsigned long guest_val_vmcs, unsigned long host_val_vmcs,
+		u64 guest_val, u64 host_val)
+{
+	vmcs_write64(guest_val_vmcs, guest_val);
+	if (host_val_vmcs != HOST_IA32_EFER)
+		vmcs_write64(host_val_vmcs, host_val);
+	vm_entry_controls_setbit(vmx, entry);
+	vm_exit_controls_setbit(vmx, exit);
+}
+
+static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
+				  u64 guest_val, u64 host_val, bool entry_only)
+{
+	int i, j = 0;
+	struct msr_autoload *m = &vmx->msr_autoload;
+
+	switch (msr) {
+	case MSR_EFER:
+		if (cpu_has_load_ia32_efer()) {
+			add_atomic_switch_msr_special(vmx,
+					VM_ENTRY_LOAD_IA32_EFER,
+					VM_EXIT_LOAD_IA32_EFER,
+					GUEST_IA32_EFER,
+					HOST_IA32_EFER,
+					guest_val, host_val);
+			return;
+		}
+		break;
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+		if (cpu_has_load_perf_global_ctrl()) {
+			add_atomic_switch_msr_special(vmx,
+					VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+					VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL,
+					GUEST_IA32_PERF_GLOBAL_CTRL,
+					HOST_IA32_PERF_GLOBAL_CTRL,
+					guest_val, host_val);
+			return;
+		}
+		break;
+	case MSR_IA32_PEBS_ENABLE:
+		/* PEBS needs a quiescent period after being disabled (to write
+		 * a record).  Disabling PEBS through VMX MSR swapping doesn't
+		 * provide that period, so a CPU could write host's record into
+		 * guest's memory.
+		 */
+		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+	}
+
+	i = find_msr(&m->guest, msr);
+	if (!entry_only)
+		j = find_msr(&m->host, msr);
+
+	if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) ||
+		(j < 0 &&  m->host.nr == NR_AUTOLOAD_MSRS)) {
+		printk_once(KERN_WARNING "Not enough msr switch entries. "
+				"Can't add msr %x\n", msr);
+		return;
+	}
+	if (i < 0) {
+		i = m->guest.nr++;
+		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+	}
+	m->guest.val[i].index = msr;
+	m->guest.val[i].value = guest_val;
+
+	if (entry_only)
+		return;
+
+	if (j < 0) {
+		j = m->host.nr++;
+		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
+	}
+	m->host.val[j].index = msr;
+	m->host.val[j].value = host_val;
+}
+
+static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
+{
+	u64 guest_efer = vmx->vcpu.arch.efer;
+	u64 ignore_bits = 0;
+
+	/* Shadow paging assumes NX to be available.  */
+	if (!enable_ept)
+		guest_efer |= EFER_NX;
+
+	/*
+	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
+	 */
+	ignore_bits |= EFER_SCE;
+#ifdef CONFIG_X86_64
+	ignore_bits |= EFER_LMA | EFER_LME;
+	/* SCE is meaningful only in long mode on Intel */
+	if (guest_efer & EFER_LMA)
+		ignore_bits &= ~(u64)EFER_SCE;
+#endif
+
+	/*
+	 * On EPT, we can't emulate NX, so we must switch EFER atomically.
+	 * On CPUs that support "load IA32_EFER", always switch EFER
+	 * atomically, since it's faster than switching it manually.
+	 */
+	if (cpu_has_load_ia32_efer() ||
+	    (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
+		if (!(guest_efer & EFER_LMA))
+			guest_efer &= ~EFER_LME;
+		if (guest_efer != host_efer)
+			add_atomic_switch_msr(vmx, MSR_EFER,
+					      guest_efer, host_efer, false);
+		else
+			clear_atomic_switch_msr(vmx, MSR_EFER);
+		return false;
+	} else {
+		clear_atomic_switch_msr(vmx, MSR_EFER);
+
+		guest_efer &= ~ignore_bits;
+		guest_efer |= host_efer & ignore_bits;
+
+		vmx->guest_msrs[efer_offset].data = guest_efer;
+		vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+		return true;
+	}
+}
+
+#ifdef CONFIG_X86_32
+/*
+ * On 32-bit kernels, VM exits still load the FS and GS bases from the
+ * VMCS rather than the segment table.  KVM uses this helper to figure
+ * out the current bases to poke them into the VMCS before entry.
+ */
+static unsigned long segment_base(u16 selector)
+{
+	struct desc_struct *table;
+	unsigned long v;
+
+	if (!(selector & ~SEGMENT_RPL_MASK))
+		return 0;
+
+	table = get_current_gdt_ro();
+
+	if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+		u16 ldt_selector = kvm_read_ldt();
+
+		if (!(ldt_selector & ~SEGMENT_RPL_MASK))
+			return 0;
+
+		table = (struct desc_struct *)segment_base(ldt_selector);
+	}
+	v = get_desc_base(&table[selector >> 3]);
+	return v;
+}
+#endif
+
+static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range)
+{
+	u32 i;
+
+	wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
+	wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+	wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+	wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+	for (i = 0; i < addr_range; i++) {
+		wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
+		wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
+	}
+}
+
+static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range)
+{
+	u32 i;
+
+	rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
+	rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+	rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+	for (i = 0; i < addr_range; i++) {
+		rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
+		rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
+	}
+}
+
+static void pt_guest_enter(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_SYSTEM)
+		return;
+
+	/*
+	 * GUEST_IA32_RTIT_CTL is already set in the VMCS.
+	 * Save host state before VM entry.
+	 */
+	rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		wrmsrl(MSR_IA32_RTIT_CTL, 0);
+		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
+		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
+	}
+}
+
+static void pt_guest_exit(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_SYSTEM)
+		return;
+
+	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
+		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
+	}
+
+	/* Reload host state (IA32_RTIT_CTL will be cleared on VM exit). */
+	wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+}
+
+void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
+			unsigned long fs_base, unsigned long gs_base)
+{
+	if (unlikely(fs_sel != host->fs_sel)) {
+		if (!(fs_sel & 7))
+			vmcs_write16(HOST_FS_SELECTOR, fs_sel);
+		else
+			vmcs_write16(HOST_FS_SELECTOR, 0);
+		host->fs_sel = fs_sel;
+	}
+	if (unlikely(gs_sel != host->gs_sel)) {
+		if (!(gs_sel & 7))
+			vmcs_write16(HOST_GS_SELECTOR, gs_sel);
+		else
+			vmcs_write16(HOST_GS_SELECTOR, 0);
+		host->gs_sel = gs_sel;
+	}
+	if (unlikely(fs_base != host->fs_base)) {
+		vmcs_writel(HOST_FS_BASE, fs_base);
+		host->fs_base = fs_base;
+	}
+	if (unlikely(gs_base != host->gs_base)) {
+		vmcs_writel(HOST_GS_BASE, gs_base);
+		host->gs_base = gs_base;
+	}
+}
+
+void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmcs_host_state *host_state;
+#ifdef CONFIG_X86_64
+	int cpu = raw_smp_processor_id();
+#endif
+	unsigned long fs_base, gs_base;
+	u16 fs_sel, gs_sel;
+	int i;
+
+	vmx->req_immediate_exit = false;
+
+	/*
+	 * Note that guest MSRs to be saved/restored can also be changed
+	 * when guest state is loaded. This happens when guest transitions
+	 * to/from long-mode by setting MSR_EFER.LMA.
+	 */
+	if (!vmx->guest_msrs_ready) {
+		vmx->guest_msrs_ready = true;
+		for (i = 0; i < vmx->save_nmsrs; ++i)
+			kvm_set_shared_msr(vmx->guest_msrs[i].index,
+					   vmx->guest_msrs[i].data,
+					   vmx->guest_msrs[i].mask);
+
+	}
+	if (vmx->guest_state_loaded)
+		return;
+
+	host_state = &vmx->loaded_vmcs->host_state;
+
+	/*
+	 * Set host fs and gs selectors.  Unfortunately, 22.2.3 does not
+	 * allow segment selectors with cpl > 0 or ti == 1.
+	 */
+	host_state->ldt_sel = kvm_read_ldt();
+
+#ifdef CONFIG_X86_64
+	savesegment(ds, host_state->ds_sel);
+	savesegment(es, host_state->es_sel);
+
+	gs_base = cpu_kernelmode_gs_base(cpu);
+	if (likely(is_64bit_mm(current->mm))) {
+		save_fsgs_for_kvm();
+		fs_sel = current->thread.fsindex;
+		gs_sel = current->thread.gsindex;
+		fs_base = current->thread.fsbase;
+		vmx->msr_host_kernel_gs_base = current->thread.gsbase;
+	} else {
+		savesegment(fs, fs_sel);
+		savesegment(gs, gs_sel);
+		fs_base = read_msr(MSR_FS_BASE);
+		vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+	}
+
+	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+#else
+	savesegment(fs, fs_sel);
+	savesegment(gs, gs_sel);
+	fs_base = segment_base(fs_sel);
+	gs_base = segment_base(gs_sel);
+#endif
+
+	vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base);
+	vmx->guest_state_loaded = true;
+}
+
+static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
+{
+	struct vmcs_host_state *host_state;
+
+	if (!vmx->guest_state_loaded)
+		return;
+
+	host_state = &vmx->loaded_vmcs->host_state;
+
+	++vmx->vcpu.stat.host_state_reload;
+
+#ifdef CONFIG_X86_64
+	rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+#endif
+	if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
+		kvm_load_ldt(host_state->ldt_sel);
+#ifdef CONFIG_X86_64
+		load_gs_index(host_state->gs_sel);
+#else
+		loadsegment(gs, host_state->gs_sel);
+#endif
+	}
+	if (host_state->fs_sel & 7)
+		loadsegment(fs, host_state->fs_sel);
+#ifdef CONFIG_X86_64
+	if (unlikely(host_state->ds_sel | host_state->es_sel)) {
+		loadsegment(ds, host_state->ds_sel);
+		loadsegment(es, host_state->es_sel);
+	}
+#endif
+	invalidate_tss_limit();
+#ifdef CONFIG_X86_64
+	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+#endif
+	load_fixmap_gdt(raw_smp_processor_id());
+	vmx->guest_state_loaded = false;
+	vmx->guest_msrs_ready = false;
+}
+
+#ifdef CONFIG_X86_64
+static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
+{
+	preempt_disable();
+	if (vmx->guest_state_loaded)
+		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+	preempt_enable();
+	return vmx->msr_guest_kernel_gs_base;
+}
+
+static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
+{
+	preempt_disable();
+	if (vmx->guest_state_loaded)
+		wrmsrl(MSR_KERNEL_GS_BASE, data);
+	preempt_enable();
+	vmx->msr_guest_kernel_gs_base = data;
+}
+#endif
+
+static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	/*
+	 * In case of hot-plug or hot-unplug, we may have to undo
+	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
+	 * always keep PI.NDST up to date for simplicity: it makes the
+	 * code easier, and CPU migration is not a fast path.
+	 */
+	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
+		return;
+
+	/*
+	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+	 * PI.NDST: pi_post_block is the one expected to change PID.NDST and the
+	 * wakeup handler expects the vCPU to be on the blocked_vcpu_list that
+	 * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
+	 * correctly.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
+		pi_clear_sn(pi_desc);
+		goto after_clear_sn;
+	}
+
+	/* The full case.  */
+	do {
+		old.control = new.control = pi_desc->control;
+
+		dest = cpu_physical_id(cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		new.sn = 0;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+after_clear_sn:
+
+	/*
+	 * Clear SN before reading the bitmap.  The VT-d firmware
+	 * writes the bitmap and reads SN atomically (5.2.3 in the
+	 * spec), so it doesn't really have a memory barrier that
+	 * pairs with this, but we cannot do that and we need one.
+	 */
+	smp_mb__after_atomic();
+
+	if (!pi_is_pir_empty(pi_desc))
+		pi_set_on(pi_desc);
+}
+
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
+
+	if (!already_loaded) {
+		loaded_vmcs_clear(vmx->loaded_vmcs);
+		local_irq_disable();
+		crash_disable_local_vmclear(cpu);
+
+		/*
+		 * Read loaded_vmcs->cpu should be before fetching
+		 * loaded_vmcs->loaded_vmcss_on_cpu_link.
+		 * See the comments in __loaded_vmcs_clear().
+		 */
+		smp_rmb();
+
+		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
+			 &per_cpu(loaded_vmcss_on_cpu, cpu));
+		crash_enable_local_vmclear(cpu);
+		local_irq_enable();
+	}
+
+	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
+		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
+		vmcs_load(vmx->loaded_vmcs->vmcs);
+		indirect_branch_prediction_barrier();
+	}
+
+	if (!already_loaded) {
+		void *gdt = get_current_gdt_ro();
+		unsigned long sysenter_esp;
+
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+
+		/*
+		 * Linux uses per-cpu TSS and GDT, so set these when switching
+		 * processors.  See 22.2.4.
+		 */
+		vmcs_writel(HOST_TR_BASE,
+			    (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
+		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */
+
+		/*
+		 * VM exits change the host TR limit to 0x67 after a VM
+		 * exit.  This is okay, since 0x67 covers everything except
+		 * the IO bitmap and have have code to handle the IO bitmap
+		 * being lost after a VM exit.
+		 */
+		BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67);
+
+		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
+		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
+
+		vmx->loaded_vmcs->cpu = cpu;
+	}
+
+	/* Setup TSC multiplier */
+	if (kvm_has_tsc_control &&
+	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio)
+		decache_tsc_multiplier(vmx);
+}
+
+/*
+ * Switches to specified vcpu, until a matching vcpu_put(), but assumes
+ * vcpu mutex is already taken.
+ */
+void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	vmx_vcpu_load_vmcs(vcpu, cpu);
+
+	vmx_vcpu_pi_load(vcpu, cpu);
+
+	vmx->host_pkru = read_pkru();
+	vmx->host_debugctlmsr = get_debugctlmsr();
+}
+
+static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	/* Set SN when the vCPU is preempted */
+	if (vcpu->preempted)
+		pi_set_sn(pi_desc);
+}
+
+static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vmx_vcpu_pi_put(vcpu);
+
+	vmx_prepare_switch_to_host(to_vmx(vcpu));
+}
+
+static bool emulation_required(struct kvm_vcpu *vcpu)
+{
+	return emulate_invalid_guest_state && !guest_state_valid(vcpu);
+}
+
+static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
+
+unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
+{
+	unsigned long rflags, save_rflags;
+
+	if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) {
+		__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
+		rflags = vmcs_readl(GUEST_RFLAGS);
+		if (to_vmx(vcpu)->rmode.vm86_active) {
+			rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+			save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+			rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+		}
+		to_vmx(vcpu)->rflags = rflags;
+	}
+	return to_vmx(vcpu)->rflags;
+}
+
+void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+	unsigned long old_rflags = vmx_get_rflags(vcpu);
+
+	__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
+	to_vmx(vcpu)->rflags = rflags;
+	if (to_vmx(vcpu)->rmode.vm86_active) {
+		to_vmx(vcpu)->rmode.save_rflags = rflags;
+		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
+	}
+	vmcs_writel(GUEST_RFLAGS, rflags);
+
+	if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM)
+		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
+}
+
+u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
+{
+	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
+	int ret = 0;
+
+	if (interruptibility & GUEST_INTR_STATE_STI)
+		ret |= KVM_X86_SHADOW_INT_STI;
+	if (interruptibility & GUEST_INTR_STATE_MOV_SS)
+		ret |= KVM_X86_SHADOW_INT_MOV_SS;
+
+	return ret;
+}
+
+void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
+{
+	u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
+	u32 interruptibility = interruptibility_old;
+
+	interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
+
+	if (mask & KVM_X86_SHADOW_INT_MOV_SS)
+		interruptibility |= GUEST_INTR_STATE_MOV_SS;
+	else if (mask & KVM_X86_SHADOW_INT_STI)
+		interruptibility |= GUEST_INTR_STATE_STI;
+
+	if ((interruptibility != interruptibility_old))
+		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility);
+}
+
+static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long value;
+
+	/*
+	 * Any MSR write that attempts to change bits marked reserved will
+	 * case a #GP fault.
+	 */
+	if (data & vmx->pt_desc.ctl_bitmask)
+		return 1;
+
+	/*
+	 * Any attempt to modify IA32_RTIT_CTL while TraceEn is set will
+	 * result in a #GP unless the same write also clears TraceEn.
+	 */
+	if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) &&
+		((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN))
+		return 1;
+
+	/*
+	 * WRMSR to IA32_RTIT_CTL that sets TraceEn but clears this bit
+	 * and FabricEn would cause #GP, if
+	 * CPUID.(EAX=14H, ECX=0):ECX.SNGLRGNOUT[bit 2] = 0
+	 */
+	if ((data & RTIT_CTL_TRACEEN) && !(data & RTIT_CTL_TOPA) &&
+		!(data & RTIT_CTL_FABRIC_EN) &&
+		!intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_single_range_output))
+		return 1;
+
+	/*
+	 * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that
+	 * utilize encodings marked reserved will casue a #GP fault.
+	 */
+	value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods);
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) &&
+			!test_bit((data & RTIT_CTL_MTC_RANGE) >>
+			RTIT_CTL_MTC_RANGE_OFFSET, &value))
+		return 1;
+	value = intel_pt_validate_cap(vmx->pt_desc.caps,
+						PT_CAP_cycle_thresholds);
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) &&
+			!test_bit((data & RTIT_CTL_CYC_THRESH) >>
+			RTIT_CTL_CYC_THRESH_OFFSET, &value))
+		return 1;
+	value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_periods);
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) &&
+			!test_bit((data & RTIT_CTL_PSB_FREQ) >>
+			RTIT_CTL_PSB_FREQ_OFFSET, &value))
+		return 1;
+
+	/*
+	 * If ADDRx_CFG is reserved or the encodings is >2 will
+	 * cause a #GP fault.
+	 */
+	value = (data & RTIT_CTL_ADDR0) >> RTIT_CTL_ADDR0_OFFSET;
+	if ((value && (vmx->pt_desc.addr_range < 1)) || (value > 2))
+		return 1;
+	value = (data & RTIT_CTL_ADDR1) >> RTIT_CTL_ADDR1_OFFSET;
+	if ((value && (vmx->pt_desc.addr_range < 2)) || (value > 2))
+		return 1;
+	value = (data & RTIT_CTL_ADDR2) >> RTIT_CTL_ADDR2_OFFSET;
+	if ((value && (vmx->pt_desc.addr_range < 3)) || (value > 2))
+		return 1;
+	value = (data & RTIT_CTL_ADDR3) >> RTIT_CTL_ADDR3_OFFSET;
+	if ((value && (vmx->pt_desc.addr_range < 4)) || (value > 2))
+		return 1;
+
+	return 0;
+}
+
+static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	unsigned long rip;
+
+	/*
+	 * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on
+	 * undefined behavior: Intel's SDM doesn't mandate the VMCS field be
+	 * set when EPT misconfig occurs.  In practice, real hardware updates
+	 * VM_EXIT_INSTRUCTION_LEN on EPT misconfig, but other hypervisors
+	 * (namely Hyper-V) don't set it due to it being undefined behavior,
+	 * i.e. we end up advancing IP with some random value.
+	 */
+	if (!static_cpu_has(X86_FEATURE_HYPERVISOR) ||
+	    to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) {
+		rip = kvm_rip_read(vcpu);
+		rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		kvm_rip_write(vcpu, rip);
+	} else {
+		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
+			return 0;
+	}
+
+	/* skipping an emulated instruction also counts */
+	vmx_set_interrupt_shadow(vcpu, 0);
+
+	return 1;
+}
+
+static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Ensure that we clear the HLT state in the VMCS.  We don't need to
+	 * explicitly skip the instruction because if the HLT state is set,
+	 * then the instruction is already executing and RIP has already been
+	 * advanced.
+	 */
+	if (kvm_hlt_in_guest(vcpu->kvm) &&
+			vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT)
+		vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
+}
+
+static void vmx_queue_exception(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned nr = vcpu->arch.exception.nr;
+	bool has_error_code = vcpu->arch.exception.has_error_code;
+	u32 error_code = vcpu->arch.exception.error_code;
+	u32 intr_info = nr | INTR_INFO_VALID_MASK;
+
+	kvm_deliver_exception_payload(vcpu);
+
+	if (has_error_code) {
+		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
+		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+	}
+
+	if (vmx->rmode.vm86_active) {
+		int inc_eip = 0;
+		if (kvm_exception_is_soft(nr))
+			inc_eip = vcpu->arch.event_exit_inst_len;
+		kvm_inject_realmode_interrupt(vcpu, nr, inc_eip);
+		return;
+	}
+
+	WARN_ON_ONCE(vmx->emulation_required);
+
+	if (kvm_exception_is_soft(nr)) {
+		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+			     vmx->vcpu.arch.event_exit_inst_len);
+		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+	} else
+		intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
+
+	vmx_clear_hlt(vcpu);
+}
+
+static bool vmx_rdtscp_supported(void)
+{
+	return cpu_has_vmx_rdtscp();
+}
+
+static bool vmx_invpcid_supported(void)
+{
+	return cpu_has_vmx_invpcid();
+}
+
+/*
+ * Swap MSR entry in host/guest MSR entry array.
+ */
+static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
+{
+	struct shared_msr_entry tmp;
+
+	tmp = vmx->guest_msrs[to];
+	vmx->guest_msrs[to] = vmx->guest_msrs[from];
+	vmx->guest_msrs[from] = tmp;
+}
+
+/*
+ * Set up the vmcs to automatically save and restore system
+ * msrs.  Don't touch the 64-bit msrs if the guest is in legacy
+ * mode, as fiddling with msrs is very expensive.
+ */
+static void setup_msrs(struct vcpu_vmx *vmx)
+{
+	int save_nmsrs, index;
+
+	save_nmsrs = 0;
+#ifdef CONFIG_X86_64
+	/*
+	 * The SYSCALL MSRs are only needed on long mode guests, and only
+	 * when EFER.SCE is set.
+	 */
+	if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) {
+		index = __find_msr_index(vmx, MSR_STAR);
+		if (index >= 0)
+			move_msr_up(vmx, index, save_nmsrs++);
+		index = __find_msr_index(vmx, MSR_LSTAR);
+		if (index >= 0)
+			move_msr_up(vmx, index, save_nmsrs++);
+		index = __find_msr_index(vmx, MSR_SYSCALL_MASK);
+		if (index >= 0)
+			move_msr_up(vmx, index, save_nmsrs++);
+	}
+#endif
+	index = __find_msr_index(vmx, MSR_EFER);
+	if (index >= 0 && update_transition_efer(vmx, index))
+		move_msr_up(vmx, index, save_nmsrs++);
+	index = __find_msr_index(vmx, MSR_TSC_AUX);
+	if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
+		move_msr_up(vmx, index, save_nmsrs++);
+
+	vmx->save_nmsrs = save_nmsrs;
+	vmx->guest_msrs_ready = false;
+
+	if (cpu_has_vmx_msr_bitmap())
+		vmx_update_msr_bitmap(&vmx->vcpu);
+}
+
+static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (is_guest_mode(vcpu) &&
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
+
+	return vcpu->arch.tsc_offset;
+}
+
+static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	u64 g_tsc_offset = 0;
+
+	/*
+	 * We're here if L1 chose not to trap WRMSR to TSC. According
+	 * to the spec, this should set L1's TSC; The offset that L1
+	 * set for L2 remains unchanged, and still needs to be added
+	 * to the newly set TSC to get L2's TSC.
+	 */
+	if (is_guest_mode(vcpu) &&
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+		g_tsc_offset = vmcs12->tsc_offset;
+
+	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
+				   vcpu->arch.tsc_offset - g_tsc_offset,
+				   offset);
+	vmcs_write64(TSC_OFFSET, offset + g_tsc_offset);
+	return offset + g_tsc_offset;
+}
+
+/*
+ * nested_vmx_allowed() checks whether a guest should be allowed to use VMX
+ * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for
+ * all guests if the "nested" module option is off, and can also be disabled
+ * for a single guest by disabling its VMX cpuid bit.
+ */
+bool nested_vmx_allowed(struct kvm_vcpu *vcpu)
+{
+	return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX);
+}
+
+static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu,
+						 uint64_t val)
+{
+	uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits;
+
+	return !(val & ~valid_bits);
+}
+
+static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
+{
+	switch (msr->index) {
+	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
+		if (!nested)
+			return 1;
+		return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data);
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Reads an msr value (of 'msr_index') into 'pdata'.
+ * Returns 0 on success, non-0 otherwise.
+ * Assumes vcpu_load() was already called.
+ */
+static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct shared_msr_entry *msr;
+	u32 index;
+
+	switch (msr_info->index) {
+#ifdef CONFIG_X86_64
+	case MSR_FS_BASE:
+		msr_info->data = vmcs_readl(GUEST_FS_BASE);
+		break;
+	case MSR_GS_BASE:
+		msr_info->data = vmcs_readl(GUEST_GS_BASE);
+		break;
+	case MSR_KERNEL_GS_BASE:
+		msr_info->data = vmx_read_guest_kernel_gs_base(vmx);
+		break;
+#endif
+	case MSR_EFER:
+		return kvm_get_msr_common(vcpu, msr_info);
+	case MSR_IA32_UMWAIT_CONTROL:
+		if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
+			return 1;
+
+		msr_info->data = vmx->msr_ia32_umwait_control;
+		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+			return 1;
+
+		msr_info->data = to_vmx(vcpu)->spec_ctrl;
+		break;
+	case MSR_IA32_SYSENTER_CS:
+		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
+		break;
+	case MSR_IA32_SYSENTER_EIP:
+		msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP);
+		break;
+	case MSR_IA32_SYSENTER_ESP:
+		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
+		break;
+	case MSR_IA32_BNDCFGS:
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated &&
+		     !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
+			return 1;
+		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
+		break;
+	case MSR_IA32_MCG_EXT_CTL:
+		if (!msr_info->host_initiated &&
+		    !(vmx->msr_ia32_feature_control &
+		      FEATURE_CONTROL_LMCE))
+			return 1;
+		msr_info->data = vcpu->arch.mcg_ext_ctl;
+		break;
+	case MSR_IA32_FEATURE_CONTROL:
+		msr_info->data = vmx->msr_ia32_feature_control;
+		break;
+	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
+		if (!nested_vmx_allowed(vcpu))
+			return 1;
+		return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
+				       &msr_info->data);
+	case MSR_IA32_XSS:
+		if (!vmx_xsaves_supported() ||
+		    (!msr_info->host_initiated &&
+		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
+			return 1;
+		msr_info->data = vcpu->arch.ia32_xss;
+		break;
+	case MSR_IA32_RTIT_CTL:
+		if (pt_mode != PT_MODE_HOST_GUEST)
+			return 1;
+		msr_info->data = vmx->pt_desc.guest.ctl;
+		break;
+	case MSR_IA32_RTIT_STATUS:
+		if (pt_mode != PT_MODE_HOST_GUEST)
+			return 1;
+		msr_info->data = vmx->pt_desc.guest.status;
+		break;
+	case MSR_IA32_RTIT_CR3_MATCH:
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			!intel_pt_validate_cap(vmx->pt_desc.caps,
+						PT_CAP_cr3_filtering))
+			return 1;
+		msr_info->data = vmx->pt_desc.guest.cr3_match;
+		break;
+	case MSR_IA32_RTIT_OUTPUT_BASE:
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			(!intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_topa_output) &&
+			 !intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_single_range_output)))
+			return 1;
+		msr_info->data = vmx->pt_desc.guest.output_base;
+		break;
+	case MSR_IA32_RTIT_OUTPUT_MASK:
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			(!intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_topa_output) &&
+			 !intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_single_range_output)))
+			return 1;
+		msr_info->data = vmx->pt_desc.guest.output_mask;
+		break;
+	case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
+		index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_num_address_ranges)))
+			return 1;
+		if (index % 2)
+			msr_info->data = vmx->pt_desc.guest.addr_b[index / 2];
+		else
+			msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
+		break;
+	case MSR_TSC_AUX:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
+			return 1;
+		/* Else, falls through */
+	default:
+		msr = find_msr_entry(vmx, msr_info->index);
+		if (msr) {
+			msr_info->data = msr->data;
+			break;
+		}
+		return kvm_get_msr_common(vcpu, msr_info);
+	}
+
+	return 0;
+}
+
+/*
+ * Writes msr value into into the appropriate "register".
+ * Returns 0 on success, non-0 otherwise.
+ * Assumes vcpu_load() was already called.
+ */
+static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct shared_msr_entry *msr;
+	int ret = 0;
+	u32 msr_index = msr_info->index;
+	u64 data = msr_info->data;
+	u32 index;
+
+	switch (msr_index) {
+	case MSR_EFER:
+		ret = kvm_set_msr_common(vcpu, msr_info);
+		break;
+#ifdef CONFIG_X86_64
+	case MSR_FS_BASE:
+		vmx_segment_cache_clear(vmx);
+		vmcs_writel(GUEST_FS_BASE, data);
+		break;
+	case MSR_GS_BASE:
+		vmx_segment_cache_clear(vmx);
+		vmcs_writel(GUEST_GS_BASE, data);
+		break;
+	case MSR_KERNEL_GS_BASE:
+		vmx_write_guest_kernel_gs_base(vmx, data);
+		break;
+#endif
+	case MSR_IA32_SYSENTER_CS:
+		if (is_guest_mode(vcpu))
+			get_vmcs12(vcpu)->guest_sysenter_cs = data;
+		vmcs_write32(GUEST_SYSENTER_CS, data);
+		break;
+	case MSR_IA32_SYSENTER_EIP:
+		if (is_guest_mode(vcpu))
+			get_vmcs12(vcpu)->guest_sysenter_eip = data;
+		vmcs_writel(GUEST_SYSENTER_EIP, data);
+		break;
+	case MSR_IA32_SYSENTER_ESP:
+		if (is_guest_mode(vcpu))
+			get_vmcs12(vcpu)->guest_sysenter_esp = data;
+		vmcs_writel(GUEST_SYSENTER_ESP, data);
+		break;
+	case MSR_IA32_DEBUGCTLMSR:
+		if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls &
+						VM_EXIT_SAVE_DEBUG_CONTROLS)
+			get_vmcs12(vcpu)->guest_ia32_debugctl = data;
+
+		ret = kvm_set_msr_common(vcpu, msr_info);
+		break;
+
+	case MSR_IA32_BNDCFGS:
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated &&
+		     !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
+			return 1;
+		if (is_noncanonical_address(data & PAGE_MASK, vcpu) ||
+		    (data & MSR_IA32_BNDCFGS_RSVD))
+			return 1;
+		vmcs_write64(GUEST_BNDCFGS, data);
+		break;
+	case MSR_IA32_UMWAIT_CONTROL:
+		if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
+			return 1;
+
+		/* The reserved bit 1 and non-32 bit [63:32] should be zero */
+		if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32)))
+			return 1;
+
+		vmx->msr_ia32_umwait_control = data;
+		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+			return 1;
+
+		/* The STIBP bit doesn't fault even if it's not advertised */
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+			return 1;
+
+		vmx->spec_ctrl = data;
+
+		if (!data)
+			break;
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_vmx_merge_msr_bitmap. We should not touch the
+		 * vmcs02.msr_bitmap here since it gets completely overwritten
+		 * in the merging. We update the vmcs01 here for L1 as well
+		 * since it will end up touching the MSR anyway now.
+		 */
+		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
+					      MSR_IA32_SPEC_CTRL,
+					      MSR_TYPE_RW);
+		break;
+	case MSR_IA32_PRED_CMD:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+			return 1;
+
+		if (data & ~PRED_CMD_IBPB)
+			return 1;
+
+		if (!data)
+			break;
+
+		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_vmx_merge_msr_bitmap. We should not touch the
+		 * vmcs02.msr_bitmap here since it gets completely overwritten
+		 * in the merging.
+		 */
+		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
+					      MSR_TYPE_W);
+		break;
+	case MSR_IA32_CR_PAT:
+		if (!kvm_pat_valid(data))
+			return 1;
+
+		if (is_guest_mode(vcpu) &&
+		    get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT)
+			get_vmcs12(vcpu)->guest_ia32_pat = data;
+
+		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+			vmcs_write64(GUEST_IA32_PAT, data);
+			vcpu->arch.pat = data;
+			break;
+		}
+		ret = kvm_set_msr_common(vcpu, msr_info);
+		break;
+	case MSR_IA32_TSC_ADJUST:
+		ret = kvm_set_msr_common(vcpu, msr_info);
+		break;
+	case MSR_IA32_MCG_EXT_CTL:
+		if ((!msr_info->host_initiated &&
+		     !(to_vmx(vcpu)->msr_ia32_feature_control &
+		       FEATURE_CONTROL_LMCE)) ||
+		    (data & ~MCG_EXT_CTL_LMCE_EN))
+			return 1;
+		vcpu->arch.mcg_ext_ctl = data;
+		break;
+	case MSR_IA32_FEATURE_CONTROL:
+		if (!vmx_feature_control_msr_valid(vcpu, data) ||
+		    (to_vmx(vcpu)->msr_ia32_feature_control &
+		     FEATURE_CONTROL_LOCKED && !msr_info->host_initiated))
+			return 1;
+		vmx->msr_ia32_feature_control = data;
+		if (msr_info->host_initiated && data == 0)
+			vmx_leave_nested(vcpu);
+		break;
+	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
+		if (!msr_info->host_initiated)
+			return 1; /* they are read-only */
+		if (!nested_vmx_allowed(vcpu))
+			return 1;
+		return vmx_set_vmx_msr(vcpu, msr_index, data);
+	case MSR_IA32_XSS:
+		if (!vmx_xsaves_supported() ||
+		    (!msr_info->host_initiated &&
+		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
+			return 1;
+		/*
+		 * The only supported bit as of Skylake is bit 8, but
+		 * it is not supported on KVM.
+		 */
+		if (data != 0)
+			return 1;
+		vcpu->arch.ia32_xss = data;
+		if (vcpu->arch.ia32_xss != host_xss)
+			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
+				vcpu->arch.ia32_xss, host_xss, false);
+		else
+			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
+		break;
+	case MSR_IA32_RTIT_CTL:
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			vmx_rtit_ctl_check(vcpu, data) ||
+			vmx->nested.vmxon)
+			return 1;
+		vmcs_write64(GUEST_IA32_RTIT_CTL, data);
+		vmx->pt_desc.guest.ctl = data;
+		pt_update_intercept_for_msr(vmx);
+		break;
+	case MSR_IA32_RTIT_STATUS:
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
+			(data & MSR_IA32_RTIT_STATUS_MASK))
+			return 1;
+		vmx->pt_desc.guest.status = data;
+		break;
+	case MSR_IA32_RTIT_CR3_MATCH:
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
+			!intel_pt_validate_cap(vmx->pt_desc.caps,
+						PT_CAP_cr3_filtering))
+			return 1;
+		vmx->pt_desc.guest.cr3_match = data;
+		break;
+	case MSR_IA32_RTIT_OUTPUT_BASE:
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
+			(!intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_topa_output) &&
+			 !intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_single_range_output)) ||
+			(data & MSR_IA32_RTIT_OUTPUT_BASE_MASK))
+			return 1;
+		vmx->pt_desc.guest.output_base = data;
+		break;
+	case MSR_IA32_RTIT_OUTPUT_MASK:
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
+			(!intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_topa_output) &&
+			 !intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_single_range_output)))
+			return 1;
+		vmx->pt_desc.guest.output_mask = data;
+		break;
+	case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
+		index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
+		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
+			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
+					PT_CAP_num_address_ranges)))
+			return 1;
+		if (index % 2)
+			vmx->pt_desc.guest.addr_b[index / 2] = data;
+		else
+			vmx->pt_desc.guest.addr_a[index / 2] = data;
+		break;
+	case MSR_TSC_AUX:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
+			return 1;
+		/* Check reserved bit, higher 32 bits should be zero */
+		if ((data >> 32) != 0)
+			return 1;
+		/* Else, falls through */
+	default:
+		msr = find_msr_entry(vmx, msr_index);
+		if (msr) {
+			u64 old_msr_data = msr->data;
+			msr->data = data;
+			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+				preempt_disable();
+				ret = kvm_set_shared_msr(msr->index, msr->data,
+							 msr->mask);
+				preempt_enable();
+				if (ret)
+					msr->data = old_msr_data;
+			}
+			break;
+		}
+		ret = kvm_set_msr_common(vcpu, msr_info);
+	}
+
+	return ret;
+}
+
+static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	switch (reg) {
+	case VCPU_REGS_RSP:
+		vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP);
+		break;
+	case VCPU_REGS_RIP:
+		vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP);
+		break;
+	case VCPU_EXREG_PDPTR:
+		if (enable_ept)
+			ept_save_pdptrs(vcpu);
+		break;
+	default:
+		break;
+	}
+}
+
+static __init int cpu_has_kvm_support(void)
+{
+	return cpu_has_vmx();
+}
+
+static __init int vmx_disabled_by_bios(void)
+{
+	u64 msr;
+
+	rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
+	if (msr & FEATURE_CONTROL_LOCKED) {
+		/* launched w/ TXT and VMX disabled */
+		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
+			&& tboot_enabled())
+			return 1;
+		/* launched w/o TXT and VMX only enabled w/ TXT */
+		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
+			&& (msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
+			&& !tboot_enabled()) {
+			printk(KERN_WARNING "kvm: disable TXT in the BIOS or "
+				"activate TXT before enabling KVM\n");
+			return 1;
+		}
+		/* launched w/o TXT and VMX disabled */
+		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
+			&& !tboot_enabled())
+			return 1;
+	}
+
+	return 0;
+}
+
+static void kvm_cpu_vmxon(u64 addr)
+{
+	cr4_set_bits(X86_CR4_VMXE);
+	intel_pt_handle_vmx(1);
+
+	asm volatile ("vmxon %0" : : "m"(addr));
+}
+
+static int hardware_enable(void)
+{
+	int cpu = raw_smp_processor_id();
+	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
+	u64 old, test_bits;
+
+	if (cr4_read_shadow() & X86_CR4_VMXE)
+		return -EBUSY;
+
+	/*
+	 * This can happen if we hot-added a CPU but failed to allocate
+	 * VP assist page for it.
+	 */
+	if (static_branch_unlikely(&enable_evmcs) &&
+	    !hv_get_vp_assist_page(cpu))
+		return -EFAULT;
+
+	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+
+	/*
+	 * Now we can enable the vmclear operation in kdump
+	 * since the loaded_vmcss_on_cpu list on this cpu
+	 * has been initialized.
+	 *
+	 * Though the cpu is not in VMX operation now, there
+	 * is no problem to enable the vmclear operation
+	 * for the loaded_vmcss_on_cpu list is empty!
+	 */
+	crash_enable_local_vmclear(cpu);
+
+	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
+
+	test_bits = FEATURE_CONTROL_LOCKED;
+	test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	if (tboot_enabled())
+		test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX;
+
+	if ((old & test_bits) != test_bits) {
+		/* enable and lock */
+		wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
+	}
+	kvm_cpu_vmxon(phys_addr);
+	if (enable_ept)
+		ept_sync_global();
+
+	return 0;
+}
+
+static void vmclear_local_loaded_vmcss(void)
+{
+	int cpu = raw_smp_processor_id();
+	struct loaded_vmcs *v, *n;
+
+	list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu),
+				 loaded_vmcss_on_cpu_link)
+		__loaded_vmcs_clear(v);
+}
+
+
+/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot()
+ * tricks.
+ */
+static void kvm_cpu_vmxoff(void)
+{
+	asm volatile (__ex("vmxoff"));
+
+	intel_pt_handle_vmx(0);
+	cr4_clear_bits(X86_CR4_VMXE);
+}
+
+static void hardware_disable(void)
+{
+	vmclear_local_loaded_vmcss();
+	kvm_cpu_vmxoff();
+}
+
+static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
+				      u32 msr, u32 *result)
+{
+	u32 vmx_msr_low, vmx_msr_high;
+	u32 ctl = ctl_min | ctl_opt;
+
+	rdmsr(msr, vmx_msr_low, vmx_msr_high);
+
+	ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */
+	ctl |= vmx_msr_low;  /* bit == 1 in low word  ==> must be one  */
+
+	/* Ensure minimum (required) set of control bits are supported. */
+	if (ctl_min & ~ctl)
+		return -EIO;
+
+	*result = ctl;
+	return 0;
+}
+
+static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
+				    struct vmx_capability *vmx_cap)
+{
+	u32 vmx_msr_low, vmx_msr_high;
+	u32 min, opt, min2, opt2;
+	u32 _pin_based_exec_control = 0;
+	u32 _cpu_based_exec_control = 0;
+	u32 _cpu_based_2nd_exec_control = 0;
+	u32 _vmexit_control = 0;
+	u32 _vmentry_control = 0;
+
+	memset(vmcs_conf, 0, sizeof(*vmcs_conf));
+	min = CPU_BASED_HLT_EXITING |
+#ifdef CONFIG_X86_64
+	      CPU_BASED_CR8_LOAD_EXITING |
+	      CPU_BASED_CR8_STORE_EXITING |
+#endif
+	      CPU_BASED_CR3_LOAD_EXITING |
+	      CPU_BASED_CR3_STORE_EXITING |
+	      CPU_BASED_UNCOND_IO_EXITING |
+	      CPU_BASED_MOV_DR_EXITING |
+	      CPU_BASED_USE_TSC_OFFSETING |
+	      CPU_BASED_MWAIT_EXITING |
+	      CPU_BASED_MONITOR_EXITING |
+	      CPU_BASED_INVLPG_EXITING |
+	      CPU_BASED_RDPMC_EXITING;
+
+	opt = CPU_BASED_TPR_SHADOW |
+	      CPU_BASED_USE_MSR_BITMAPS |
+	      CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
+				&_cpu_based_exec_control) < 0)
+		return -EIO;
+#ifdef CONFIG_X86_64
+	if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
+		_cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING &
+					   ~CPU_BASED_CR8_STORE_EXITING;
+#endif
+	if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
+		min2 = 0;
+		opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+			SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+			SECONDARY_EXEC_WBINVD_EXITING |
+			SECONDARY_EXEC_ENABLE_VPID |
+			SECONDARY_EXEC_ENABLE_EPT |
+			SECONDARY_EXEC_UNRESTRICTED_GUEST |
+			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
+			SECONDARY_EXEC_DESC |
+			SECONDARY_EXEC_RDTSCP |
+			SECONDARY_EXEC_ENABLE_INVPCID |
+			SECONDARY_EXEC_APIC_REGISTER_VIRT |
+			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
+			SECONDARY_EXEC_SHADOW_VMCS |
+			SECONDARY_EXEC_XSAVES |
+			SECONDARY_EXEC_RDSEED_EXITING |
+			SECONDARY_EXEC_RDRAND_EXITING |
+			SECONDARY_EXEC_ENABLE_PML |
+			SECONDARY_EXEC_TSC_SCALING |
+			SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
+			SECONDARY_EXEC_PT_USE_GPA |
+			SECONDARY_EXEC_PT_CONCEAL_VMX |
+			SECONDARY_EXEC_ENABLE_VMFUNC |
+			SECONDARY_EXEC_ENCLS_EXITING;
+		if (adjust_vmx_controls(min2, opt2,
+					MSR_IA32_VMX_PROCBASED_CTLS2,
+					&_cpu_based_2nd_exec_control) < 0)
+			return -EIO;
+	}
+#ifndef CONFIG_X86_64
+	if (!(_cpu_based_2nd_exec_control &
+				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+		_cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW;
+#endif
+
+	if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
+		_cpu_based_2nd_exec_control &= ~(
+				SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+				SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+
+	rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP,
+		&vmx_cap->ept, &vmx_cap->vpid);
+
+	if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
+		/* CR3 accesses and invlpg don't need to cause VM Exits when EPT
+		   enabled */
+		_cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING |
+					     CPU_BASED_CR3_STORE_EXITING |
+					     CPU_BASED_INVLPG_EXITING);
+	} else if (vmx_cap->ept) {
+		vmx_cap->ept = 0;
+		pr_warn_once("EPT CAP should not exist if not support "
+				"1-setting enable EPT VM-execution control\n");
+	}
+	if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) &&
+		vmx_cap->vpid) {
+		vmx_cap->vpid = 0;
+		pr_warn_once("VPID CAP should not exist if not support "
+				"1-setting enable VPID VM-execution control\n");
+	}
+
+	min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT;
+#ifdef CONFIG_X86_64
+	min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
+#endif
+	opt = VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |
+	      VM_EXIT_LOAD_IA32_PAT |
+	      VM_EXIT_LOAD_IA32_EFER |
+	      VM_EXIT_CLEAR_BNDCFGS |
+	      VM_EXIT_PT_CONCEAL_PIP |
+	      VM_EXIT_CLEAR_IA32_RTIT_CTL;
+	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
+				&_vmexit_control) < 0)
+		return -EIO;
+
+	min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
+	opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
+		 PIN_BASED_VMX_PREEMPTION_TIMER;
+	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
+				&_pin_based_exec_control) < 0)
+		return -EIO;
+
+	if (cpu_has_broken_vmx_preemption_timer())
+		_pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+	if (!(_cpu_based_2nd_exec_control &
+		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY))
+		_pin_based_exec_control &= ~PIN_BASED_POSTED_INTR;
+
+	min = VM_ENTRY_LOAD_DEBUG_CONTROLS;
+	opt = VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |
+	      VM_ENTRY_LOAD_IA32_PAT |
+	      VM_ENTRY_LOAD_IA32_EFER |
+	      VM_ENTRY_LOAD_BNDCFGS |
+	      VM_ENTRY_PT_CONCEAL_PIP |
+	      VM_ENTRY_LOAD_IA32_RTIT_CTL;
+	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
+				&_vmentry_control) < 0)
+		return -EIO;
+
+	/*
+	 * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they
+	 * can't be used due to an errata where VM Exit may incorrectly clear
+	 * IA32_PERF_GLOBAL_CTRL[34:32].  Workaround the errata by using the
+	 * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL.
+	 */
+	if (boot_cpu_data.x86 == 0x6) {
+		switch (boot_cpu_data.x86_model) {
+		case 26: /* AAK155 */
+		case 30: /* AAP115 */
+		case 37: /* AAT100 */
+		case 44: /* BC86,AAY89,BD102 */
+		case 46: /* BA97 */
+			_vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+			_vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+			pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
+					"does not work properly. Using workaround\n");
+			break;
+		default:
+			break;
+		}
+	}
+
+
+	rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high);
+
+	/* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */
+	if ((vmx_msr_high & 0x1fff) > PAGE_SIZE)
+		return -EIO;
+
+#ifdef CONFIG_X86_64
+	/* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */
+	if (vmx_msr_high & (1u<<16))
+		return -EIO;
+#endif
+
+	/* Require Write-Back (WB) memory type for VMCS accesses. */
+	if (((vmx_msr_high >> 18) & 15) != 6)
+		return -EIO;
+
+	vmcs_conf->size = vmx_msr_high & 0x1fff;
+	vmcs_conf->order = get_order(vmcs_conf->size);
+	vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
+
+	vmcs_conf->revision_id = vmx_msr_low;
+
+	vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
+	vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
+	vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control;
+	vmcs_conf->vmexit_ctrl         = _vmexit_control;
+	vmcs_conf->vmentry_ctrl        = _vmentry_control;
+
+	if (static_branch_unlikely(&enable_evmcs))
+		evmcs_sanitize_exec_ctrls(vmcs_conf);
+
+	return 0;
+}
+
+struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags)
+{
+	int node = cpu_to_node(cpu);
+	struct page *pages;
+	struct vmcs *vmcs;
+
+	pages = __alloc_pages_node(node, flags, vmcs_config.order);
+	if (!pages)
+		return NULL;
+	vmcs = page_address(pages);
+	memset(vmcs, 0, vmcs_config.size);
+
+	/* KVM supports Enlightened VMCS v1 only */
+	if (static_branch_unlikely(&enable_evmcs))
+		vmcs->hdr.revision_id = KVM_EVMCS_VERSION;
+	else
+		vmcs->hdr.revision_id = vmcs_config.revision_id;
+
+	if (shadow)
+		vmcs->hdr.shadow_vmcs = 1;
+	return vmcs;
+}
+
+void free_vmcs(struct vmcs *vmcs)
+{
+	free_pages((unsigned long)vmcs, vmcs_config.order);
+}
+
+/*
+ * Free a VMCS, but before that VMCLEAR it on the CPU where it was last loaded
+ */
+void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
+{
+	if (!loaded_vmcs->vmcs)
+		return;
+	loaded_vmcs_clear(loaded_vmcs);
+	free_vmcs(loaded_vmcs->vmcs);
+	loaded_vmcs->vmcs = NULL;
+	if (loaded_vmcs->msr_bitmap)
+		free_page((unsigned long)loaded_vmcs->msr_bitmap);
+	WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
+}
+
+int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
+{
+	loaded_vmcs->vmcs = alloc_vmcs(false);
+	if (!loaded_vmcs->vmcs)
+		return -ENOMEM;
+
+	loaded_vmcs->shadow_vmcs = NULL;
+	loaded_vmcs->hv_timer_soft_disabled = false;
+	loaded_vmcs_init(loaded_vmcs);
+
+	if (cpu_has_vmx_msr_bitmap()) {
+		loaded_vmcs->msr_bitmap = (unsigned long *)
+				__get_free_page(GFP_KERNEL_ACCOUNT);
+		if (!loaded_vmcs->msr_bitmap)
+			goto out_vmcs;
+		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
+
+		if (IS_ENABLED(CONFIG_HYPERV) &&
+		    static_branch_unlikely(&enable_evmcs) &&
+		    (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
+			struct hv_enlightened_vmcs *evmcs =
+				(struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;
+
+			evmcs->hv_enlightenments_control.msr_bitmap = 1;
+		}
+	}
+
+	memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state));
+	memset(&loaded_vmcs->controls_shadow, 0,
+		sizeof(struct vmcs_controls_shadow));
+
+	return 0;
+
+out_vmcs:
+	free_loaded_vmcs(loaded_vmcs);
+	return -ENOMEM;
+}
+
+static void free_kvm_area(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		free_vmcs(per_cpu(vmxarea, cpu));
+		per_cpu(vmxarea, cpu) = NULL;
+	}
+}
+
+static __init int alloc_kvm_area(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct vmcs *vmcs;
+
+		vmcs = alloc_vmcs_cpu(false, cpu, GFP_KERNEL);
+		if (!vmcs) {
+			free_kvm_area();
+			return -ENOMEM;
+		}
+
+		/*
+		 * When eVMCS is enabled, alloc_vmcs_cpu() sets
+		 * vmcs->revision_id to KVM_EVMCS_VERSION instead of
+		 * revision_id reported by MSR_IA32_VMX_BASIC.
+		 *
+		 * However, even though not explicitly documented by
+		 * TLFS, VMXArea passed as VMXON argument should
+		 * still be marked with revision_id reported by
+		 * physical CPU.
+		 */
+		if (static_branch_unlikely(&enable_evmcs))
+			vmcs->hdr.revision_id = vmcs_config.revision_id;
+
+		per_cpu(vmxarea, cpu) = vmcs;
+	}
+	return 0;
+}
+
+static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg,
+		struct kvm_segment *save)
+{
+	if (!emulate_invalid_guest_state) {
+		/*
+		 * CS and SS RPL should be equal during guest entry according
+		 * to VMX spec, but in reality it is not always so. Since vcpu
+		 * is in the middle of the transition from real mode to
+		 * protected mode it is safe to assume that RPL 0 is a good
+		 * default value.
+		 */
+		if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS)
+			save->selector &= ~SEGMENT_RPL_MASK;
+		save->dpl = save->selector & SEGMENT_RPL_MASK;
+		save->s = 1;
+	}
+	vmx_set_segment(vcpu, save, seg);
+}
+
+static void enter_pmode(struct kvm_vcpu *vcpu)
+{
+	unsigned long flags;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * Update real mode segment cache. It may be not up-to-date if sement
+	 * register was written while vcpu was in a guest mode.
+	 */
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS);
+
+	vmx->rmode.vm86_active = 0;
+
+	vmx_segment_cache_clear(vmx);
+
+	vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
+
+	flags = vmcs_readl(GUEST_RFLAGS);
+	flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+	flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+	vmcs_writel(GUEST_RFLAGS, flags);
+
+	vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
+			(vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME));
+
+	update_exception_bitmap(vcpu);
+
+	fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]);
+	fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]);
+	fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
+	fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
+	fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
+	fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
+}
+
+static void fix_rmode_seg(int seg, struct kvm_segment *save)
+{
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	struct kvm_segment var = *save;
+
+	var.dpl = 0x3;
+	if (seg == VCPU_SREG_CS)
+		var.type = 0x3;
+
+	if (!emulate_invalid_guest_state) {
+		var.selector = var.base >> 4;
+		var.base = var.base & 0xffff0;
+		var.limit = 0xffff;
+		var.g = 0;
+		var.db = 0;
+		var.present = 1;
+		var.s = 1;
+		var.l = 0;
+		var.unusable = 0;
+		var.type = 0x3;
+		var.avl = 0;
+		if (save->base & 0xf)
+			printk_once(KERN_WARNING "kvm: segment base is not "
+					"paragraph aligned when entering "
+					"protected mode (seg=%d)", seg);
+	}
+
+	vmcs_write16(sf->selector, var.selector);
+	vmcs_writel(sf->base, var.base);
+	vmcs_write32(sf->limit, var.limit);
+	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var));
+}
+
+static void enter_rmode(struct kvm_vcpu *vcpu)
+{
+	unsigned long flags;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm);
+
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS);
+
+	vmx->rmode.vm86_active = 1;
+
+	/*
+	 * Very old userspace does not call KVM_SET_TSS_ADDR before entering
+	 * vcpu. Warn the user that an update is overdue.
+	 */
+	if (!kvm_vmx->tss_addr)
+		printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be "
+			     "called before entering vcpu\n");
+
+	vmx_segment_cache_clear(vmx);
+
+	vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr);
+	vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);
+	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
+
+	flags = vmcs_readl(GUEST_RFLAGS);
+	vmx->rmode.save_rflags = flags;
+
+	flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
+
+	vmcs_writel(GUEST_RFLAGS, flags);
+	vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
+	update_exception_bitmap(vcpu);
+
+	fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]);
+	fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]);
+	fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
+	fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
+	fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
+	fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
+
+	kvm_mmu_reset_context(vcpu);
+}
+
+void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
+
+	if (!msr)
+		return;
+
+	vcpu->arch.efer = efer;
+	if (efer & EFER_LMA) {
+		vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
+		msr->data = efer;
+	} else {
+		vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
+
+		msr->data = efer & ~EFER_LME;
+	}
+	setup_msrs(vmx);
+}
+
+#ifdef CONFIG_X86_64
+
+static void enter_lmode(struct kvm_vcpu *vcpu)
+{
+	u32 guest_tr_ar;
+
+	vmx_segment_cache_clear(to_vmx(vcpu));
+
+	guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
+	if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) {
+		pr_debug_ratelimited("%s: tss fixup for long mode. \n",
+				     __func__);
+		vmcs_write32(GUEST_TR_AR_BYTES,
+			     (guest_tr_ar & ~VMX_AR_TYPE_MASK)
+			     | VMX_AR_TYPE_BUSY_64_TSS);
+	}
+	vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
+}
+
+static void exit_lmode(struct kvm_vcpu *vcpu)
+{
+	vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
+	vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA);
+}
+
+#endif
+
+static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
+{
+	int vpid = to_vmx(vcpu)->vpid;
+
+	if (!vpid_sync_vcpu_addr(vpid, addr))
+		vpid_sync_context(vpid);
+
+	/*
+	 * If VPIDs are not supported or enabled, then the above is a no-op.
+	 * But we don't really need a TLB flush in that case anyway, because
+	 * each VM entry/exit includes an implicit flush when VPID is 0.
+	 */
+}
+
+static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
+{
+	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
+
+	vcpu->arch.cr0 &= ~cr0_guest_owned_bits;
+	vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
+}
+
+static void vmx_decache_cr3(struct kvm_vcpu *vcpu)
+{
+	if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
+		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+}
+
+static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
+{
+	ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
+
+	vcpu->arch.cr4 &= ~cr4_guest_owned_bits;
+	vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits;
+}
+
+static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
+	if (!test_bit(VCPU_EXREG_PDPTR,
+		      (unsigned long *)&vcpu->arch.regs_dirty))
+		return;
+
+	if (is_pae_paging(vcpu)) {
+		vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
+		vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
+		vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
+		vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
+	}
+}
+
+void ept_save_pdptrs(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
+	if (is_pae_paging(vcpu)) {
+		mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+		mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+		mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+	}
+
+	__set_bit(VCPU_EXREG_PDPTR,
+		  (unsigned long *)&vcpu->arch.regs_avail);
+	__set_bit(VCPU_EXREG_PDPTR,
+		  (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
+					unsigned long cr0,
+					struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+		vmx_decache_cr3(vcpu);
+	if (!(cr0 & X86_CR0_PG)) {
+		/* From paging/starting to nonpaging */
+		exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING |
+					  CPU_BASED_CR3_STORE_EXITING);
+		vcpu->arch.cr0 = cr0;
+		vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
+	} else if (!is_paging(vcpu)) {
+		/* From nonpaging to paging */
+		exec_controls_clearbit(vmx, CPU_BASED_CR3_LOAD_EXITING |
+					    CPU_BASED_CR3_STORE_EXITING);
+		vcpu->arch.cr0 = cr0;
+		vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
+	}
+
+	if (!(cr0 & X86_CR0_WP))
+		*hw_cr0 &= ~X86_CR0_WP;
+}
+
+void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long hw_cr0;
+
+	hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF);
+	if (enable_unrestricted_guest)
+		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
+	else {
+		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON;
+
+		if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
+			enter_pmode(vcpu);
+
+		if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE))
+			enter_rmode(vcpu);
+	}
+
+#ifdef CONFIG_X86_64
+	if (vcpu->arch.efer & EFER_LME) {
+		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG))
+			enter_lmode(vcpu);
+		if (is_paging(vcpu) && !(cr0 & X86_CR0_PG))
+			exit_lmode(vcpu);
+	}
+#endif
+
+	if (enable_ept && !enable_unrestricted_guest)
+		ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
+
+	vmcs_writel(CR0_READ_SHADOW, cr0);
+	vmcs_writel(GUEST_CR0, hw_cr0);
+	vcpu->arch.cr0 = cr0;
+
+	/* depends on vcpu->arch.cr0 to be set to a new value */
+	vmx->emulation_required = emulation_required(vcpu);
+}
+
+static int get_ept_level(struct kvm_vcpu *vcpu)
+{
+	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
+		return 5;
+	return 4;
+}
+
+u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
+{
+	u64 eptp = VMX_EPTP_MT_WB;
+
+	eptp |= (get_ept_level(vcpu) == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;
+
+	if (enable_ept_ad_bits &&
+	    (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu)))
+		eptp |= VMX_EPTP_AD_ENABLE_BIT;
+	eptp |= (root_hpa & PAGE_MASK);
+
+	return eptp;
+}
+
+void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long guest_cr3;
+	u64 eptp;
+
+	guest_cr3 = cr3;
+	if (enable_ept) {
+		eptp = construct_eptp(vcpu, cr3);
+		vmcs_write64(EPT_POINTER, eptp);
+
+		if (kvm_x86_ops->tlb_remote_flush) {
+			spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock);
+			to_vmx(vcpu)->ept_pointer = eptp;
+			to_kvm_vmx(kvm)->ept_pointers_match
+				= EPT_POINTERS_CHECK;
+			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
+		}
+
+		if (enable_unrestricted_guest || is_paging(vcpu) ||
+		    is_guest_mode(vcpu))
+			guest_cr3 = kvm_read_cr3(vcpu);
+		else
+			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
+		ept_load_pdptrs(vcpu);
+	}
+
+	vmcs_writel(GUEST_CR3, guest_cr3);
+}
+
+int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	/*
+	 * Pass through host's Machine Check Enable value to hw_cr4, which
+	 * is in force while we are in guest mode.  Do not let guests control
+	 * this bit, even if host CR4.MCE == 0.
+	 */
+	unsigned long hw_cr4;
+
+	hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE);
+	if (enable_unrestricted_guest)
+		hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST;
+	else if (vmx->rmode.vm86_active)
+		hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON;
+	else
+		hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
+
+	if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
+		if (cr4 & X86_CR4_UMIP) {
+			secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC);
+			hw_cr4 &= ~X86_CR4_UMIP;
+		} else if (!is_guest_mode(vcpu) ||
+			!nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) {
+			secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_DESC);
+		}
+	}
+
+	if (cr4 & X86_CR4_VMXE) {
+		/*
+		 * To use VMXON (and later other VMX instructions), a guest
+		 * must first be able to turn on cr4.VMXE (see handle_vmon()).
+		 * So basically the check on whether to allow nested VMX
+		 * is here.  We operate under the default treatment of SMM,
+		 * so VMX cannot be enabled under SMM.
+		 */
+		if (!nested_vmx_allowed(vcpu) || is_smm(vcpu))
+			return 1;
+	}
+
+	if (vmx->nested.vmxon && !nested_cr4_valid(vcpu, cr4))
+		return 1;
+
+	vcpu->arch.cr4 = cr4;
+
+	if (!enable_unrestricted_guest) {
+		if (enable_ept) {
+			if (!is_paging(vcpu)) {
+				hw_cr4 &= ~X86_CR4_PAE;
+				hw_cr4 |= X86_CR4_PSE;
+			} else if (!(cr4 & X86_CR4_PAE)) {
+				hw_cr4 &= ~X86_CR4_PAE;
+			}
+		}
+
+		/*
+		 * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in
+		 * hardware.  To emulate this behavior, SMEP/SMAP/PKU needs
+		 * to be manually disabled when guest switches to non-paging
+		 * mode.
+		 *
+		 * If !enable_unrestricted_guest, the CPU is always running
+		 * with CR0.PG=1 and CR4 needs to be modified.
+		 * If enable_unrestricted_guest, the CPU automatically
+		 * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0.
+		 */
+		if (!is_paging(vcpu))
+			hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE);
+	}
+
+	vmcs_writel(CR4_READ_SHADOW, cr4);
+	vmcs_writel(GUEST_CR4, hw_cr4);
+	return 0;
+}
+
+void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 ar;
+
+	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
+		*var = vmx->rmode.segs[seg];
+		if (seg == VCPU_SREG_TR
+		    || var->selector == vmx_read_guest_seg_selector(vmx, seg))
+			return;
+		var->base = vmx_read_guest_seg_base(vmx, seg);
+		var->selector = vmx_read_guest_seg_selector(vmx, seg);
+		return;
+	}
+	var->base = vmx_read_guest_seg_base(vmx, seg);
+	var->limit = vmx_read_guest_seg_limit(vmx, seg);
+	var->selector = vmx_read_guest_seg_selector(vmx, seg);
+	ar = vmx_read_guest_seg_ar(vmx, seg);
+	var->unusable = (ar >> 16) & 1;
+	var->type = ar & 15;
+	var->s = (ar >> 4) & 1;
+	var->dpl = (ar >> 5) & 3;
+	/*
+	 * Some userspaces do not preserve unusable property. Since usable
+	 * segment has to be present according to VMX spec we can use present
+	 * property to amend userspace bug by making unusable segment always
+	 * nonpresent. vmx_segment_access_rights() already marks nonpresent
+	 * segment as unusable.
+	 */
+	var->present = !var->unusable;
+	var->avl = (ar >> 12) & 1;
+	var->l = (ar >> 13) & 1;
+	var->db = (ar >> 14) & 1;
+	var->g = (ar >> 15) & 1;
+}
+
+static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
+{
+	struct kvm_segment s;
+
+	if (to_vmx(vcpu)->rmode.vm86_active) {
+		vmx_get_segment(vcpu, &s, seg);
+		return s.base;
+	}
+	return vmx_read_guest_seg_base(to_vmx(vcpu), seg);
+}
+
+int vmx_get_cpl(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (unlikely(vmx->rmode.vm86_active))
+		return 0;
+	else {
+		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
+		return VMX_AR_DPL(ar);
+	}
+}
+
+static u32 vmx_segment_access_rights(struct kvm_segment *var)
+{
+	u32 ar;
+
+	if (var->unusable || !var->present)
+		ar = 1 << 16;
+	else {
+		ar = var->type & 15;
+		ar |= (var->s & 1) << 4;
+		ar |= (var->dpl & 3) << 5;
+		ar |= (var->present & 1) << 7;
+		ar |= (var->avl & 1) << 12;
+		ar |= (var->l & 1) << 13;
+		ar |= (var->db & 1) << 14;
+		ar |= (var->g & 1) << 15;
+	}
+
+	return ar;
+}
+
+void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+
+	vmx_segment_cache_clear(vmx);
+
+	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
+		vmx->rmode.segs[seg] = *var;
+		if (seg == VCPU_SREG_TR)
+			vmcs_write16(sf->selector, var->selector);
+		else if (var->s)
+			fix_rmode_seg(seg, &vmx->rmode.segs[seg]);
+		goto out;
+	}
+
+	vmcs_writel(sf->base, var->base);
+	vmcs_write32(sf->limit, var->limit);
+	vmcs_write16(sf->selector, var->selector);
+
+	/*
+	 *   Fix the "Accessed" bit in AR field of segment registers for older
+	 * qemu binaries.
+	 *   IA32 arch specifies that at the time of processor reset the
+	 * "Accessed" bit in the AR field of segment registers is 1. And qemu
+	 * is setting it to 0 in the userland code. This causes invalid guest
+	 * state vmexit when "unrestricted guest" mode is turned on.
+	 *    Fix for this setup issue in cpu_reset is being pushed in the qemu
+	 * tree. Newer qemu binaries with that qemu fix would not need this
+	 * kvm hack.
+	 */
+	if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR))
+		var->type |= 0x1; /* Accessed */
+
+	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var));
+
+out:
+	vmx->emulation_required = emulation_required(vcpu);
+}
+
+static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
+{
+	u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS);
+
+	*db = (ar >> 14) & 1;
+	*l = (ar >> 13) & 1;
+}
+
+static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+	dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
+	dt->address = vmcs_readl(GUEST_IDTR_BASE);
+}
+
+static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+	vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
+	vmcs_writel(GUEST_IDTR_BASE, dt->address);
+}
+
+static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+	dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
+	dt->address = vmcs_readl(GUEST_GDTR_BASE);
+}
+
+static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+	vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
+	vmcs_writel(GUEST_GDTR_BASE, dt->address);
+}
+
+static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
+{
+	struct kvm_segment var;
+	u32 ar;
+
+	vmx_get_segment(vcpu, &var, seg);
+	var.dpl = 0x3;
+	if (seg == VCPU_SREG_CS)
+		var.type = 0x3;
+	ar = vmx_segment_access_rights(&var);
+
+	if (var.base != (var.selector << 4))
+		return false;
+	if (var.limit != 0xffff)
+		return false;
+	if (ar != 0xf3)
+		return false;
+
+	return true;
+}
+
+static bool code_segment_valid(struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment cs;
+	unsigned int cs_rpl;
+
+	vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
+	cs_rpl = cs.selector & SEGMENT_RPL_MASK;
+
+	if (cs.unusable)
+		return false;
+	if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK))
+		return false;
+	if (!cs.s)
+		return false;
+	if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) {
+		if (cs.dpl > cs_rpl)
+			return false;
+	} else {
+		if (cs.dpl != cs_rpl)
+			return false;
+	}
+	if (!cs.present)
+		return false;
+
+	/* TODO: Add Reserved field check, this'll require a new member in the kvm_segment_field structure */
+	return true;
+}
+
+static bool stack_segment_valid(struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment ss;
+	unsigned int ss_rpl;
+
+	vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
+	ss_rpl = ss.selector & SEGMENT_RPL_MASK;
+
+	if (ss.unusable)
+		return true;
+	if (ss.type != 3 && ss.type != 7)
+		return false;
+	if (!ss.s)
+		return false;
+	if (ss.dpl != ss_rpl) /* DPL != RPL */
+		return false;
+	if (!ss.present)
+		return false;
+
+	return true;
+}
+
+static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
+{
+	struct kvm_segment var;
+	unsigned int rpl;
+
+	vmx_get_segment(vcpu, &var, seg);
+	rpl = var.selector & SEGMENT_RPL_MASK;
+
+	if (var.unusable)
+		return true;
+	if (!var.s)
+		return false;
+	if (!var.present)
+		return false;
+	if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) {
+		if (var.dpl < rpl) /* DPL < RPL */
+			return false;
+	}
+
+	/* TODO: Add other members to kvm_segment_field to allow checking for other access
+	 * rights flags
+	 */
+	return true;
+}
+
+static bool tr_valid(struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment tr;
+
+	vmx_get_segment(vcpu, &tr, VCPU_SREG_TR);
+
+	if (tr.unusable)
+		return false;
+	if (tr.selector & SEGMENT_TI_MASK)	/* TI = 1 */
+		return false;
+	if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */
+		return false;
+	if (!tr.present)
+		return false;
+
+	return true;
+}
+
+static bool ldtr_valid(struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment ldtr;
+
+	vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR);
+
+	if (ldtr.unusable)
+		return true;
+	if (ldtr.selector & SEGMENT_TI_MASK)	/* TI = 1 */
+		return false;
+	if (ldtr.type != 2)
+		return false;
+	if (!ldtr.present)
+		return false;
+
+	return true;
+}
+
+static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment cs, ss;
+
+	vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
+	vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
+
+	return ((cs.selector & SEGMENT_RPL_MASK) ==
+		 (ss.selector & SEGMENT_RPL_MASK));
+}
+
+/*
+ * Check if guest state is valid. Returns true if valid, false if
+ * not.
+ * We assume that registers are always usable
+ */
+static bool guest_state_valid(struct kvm_vcpu *vcpu)
+{
+	if (enable_unrestricted_guest)
+		return true;
+
+	/* real mode guest state checks */
+	if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) {
+		if (!rmode_segment_valid(vcpu, VCPU_SREG_CS))
+			return false;
+		if (!rmode_segment_valid(vcpu, VCPU_SREG_SS))
+			return false;
+		if (!rmode_segment_valid(vcpu, VCPU_SREG_DS))
+			return false;
+		if (!rmode_segment_valid(vcpu, VCPU_SREG_ES))
+			return false;
+		if (!rmode_segment_valid(vcpu, VCPU_SREG_FS))
+			return false;
+		if (!rmode_segment_valid(vcpu, VCPU_SREG_GS))
+			return false;
+	} else {
+	/* protected mode guest state checks */
+		if (!cs_ss_rpl_check(vcpu))
+			return false;
+		if (!code_segment_valid(vcpu))
+			return false;
+		if (!stack_segment_valid(vcpu))
+			return false;
+		if (!data_segment_valid(vcpu, VCPU_SREG_DS))
+			return false;
+		if (!data_segment_valid(vcpu, VCPU_SREG_ES))
+			return false;
+		if (!data_segment_valid(vcpu, VCPU_SREG_FS))
+			return false;
+		if (!data_segment_valid(vcpu, VCPU_SREG_GS))
+			return false;
+		if (!tr_valid(vcpu))
+			return false;
+		if (!ldtr_valid(vcpu))
+			return false;
+	}
+	/* TODO:
+	 * - Add checks on RIP
+	 * - Add checks on RFLAGS
+	 */
+
+	return true;
+}
+
+static int init_rmode_tss(struct kvm *kvm)
+{
+	gfn_t fn;
+	u16 data = 0;
+	int idx, r;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	fn = to_kvm_vmx(kvm)->tss_addr >> PAGE_SHIFT;
+	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
+	if (r < 0)
+		goto out;
+	data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
+	r = kvm_write_guest_page(kvm, fn++, &data,
+			TSS_IOPB_BASE_OFFSET, sizeof(u16));
+	if (r < 0)
+		goto out;
+	r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE);
+	if (r < 0)
+		goto out;
+	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
+	if (r < 0)
+		goto out;
+	data = ~0;
+	r = kvm_write_guest_page(kvm, fn, &data,
+				 RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
+				 sizeof(u8));
+out:
+	srcu_read_unlock(&kvm->srcu, idx);
+	return r;
+}
+
+static int init_rmode_identity_map(struct kvm *kvm)
+{
+	struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
+	int i, idx, r = 0;
+	kvm_pfn_t identity_map_pfn;
+	u32 tmp;
+
+	/* Protect kvm_vmx->ept_identity_pagetable_done. */
+	mutex_lock(&kvm->slots_lock);
+
+	if (likely(kvm_vmx->ept_identity_pagetable_done))
+		goto out2;
+
+	if (!kvm_vmx->ept_identity_map_addr)
+		kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR;
+	identity_map_pfn = kvm_vmx->ept_identity_map_addr >> PAGE_SHIFT;
+
+	r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
+				    kvm_vmx->ept_identity_map_addr, PAGE_SIZE);
+	if (r < 0)
+		goto out2;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
+	if (r < 0)
+		goto out;
+	/* Set up identity-mapping pagetable for EPT in real mode */
+	for (i = 0; i < PT32_ENT_PER_PAGE; i++) {
+		tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
+			_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
+		r = kvm_write_guest_page(kvm, identity_map_pfn,
+				&tmp, i * sizeof(tmp), sizeof(tmp));
+		if (r < 0)
+			goto out;
+	}
+	kvm_vmx->ept_identity_pagetable_done = true;
+
+out:
+	srcu_read_unlock(&kvm->srcu, idx);
+
+out2:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
+static void seg_setup(int seg)
+{
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	unsigned int ar;
+
+	vmcs_write16(sf->selector, 0);
+	vmcs_writel(sf->base, 0);
+	vmcs_write32(sf->limit, 0xffff);
+	ar = 0x93;
+	if (seg == VCPU_SREG_CS)
+		ar |= 0x08; /* code segment */
+
+	vmcs_write32(sf->ar_bytes, ar);
+}
+
+static int alloc_apic_access_page(struct kvm *kvm)
+{
+	struct page *page;
+	int r = 0;
+
+	mutex_lock(&kvm->slots_lock);
+	if (kvm->arch.apic_access_page_done)
+		goto out;
+	r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+				    APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
+	if (r)
+		goto out;
+
+	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	/*
+	 * Do not pin the page in memory, so that memory hot-unplug
+	 * is able to migrate it.
+	 */
+	put_page(page);
+	kvm->arch.apic_access_page_done = true;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
+int allocate_vpid(void)
+{
+	int vpid;
+
+	if (!enable_vpid)
+		return 0;
+	spin_lock(&vmx_vpid_lock);
+	vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
+	if (vpid < VMX_NR_VPIDS)
+		__set_bit(vpid, vmx_vpid_bitmap);
+	else
+		vpid = 0;
+	spin_unlock(&vmx_vpid_lock);
+	return vpid;
+}
+
+void free_vpid(int vpid)
+{
+	if (!enable_vpid || vpid == 0)
+		return;
+	spin_lock(&vmx_vpid_lock);
+	__clear_bit(vpid, vmx_vpid_bitmap);
+	spin_unlock(&vmx_vpid_lock);
+}
+
+static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+							  u32 msr, int type)
+{
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return;
+
+	if (static_branch_unlikely(&enable_evmcs))
+		evmcs_touch_msr_bitmap();
+
+	/*
+	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+	 * have the write-low and read-high bitmap offsets the wrong way round.
+	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+	 */
+	if (msr <= 0x1fff) {
+		if (type & MSR_TYPE_R)
+			/* read-low */
+			__clear_bit(msr, msr_bitmap + 0x000 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-low */
+			__clear_bit(msr, msr_bitmap + 0x800 / f);
+
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		if (type & MSR_TYPE_R)
+			/* read-high */
+			__clear_bit(msr, msr_bitmap + 0x400 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-high */
+			__clear_bit(msr, msr_bitmap + 0xc00 / f);
+
+	}
+}
+
+static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+							 u32 msr, int type)
+{
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return;
+
+	if (static_branch_unlikely(&enable_evmcs))
+		evmcs_touch_msr_bitmap();
+
+	/*
+	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+	 * have the write-low and read-high bitmap offsets the wrong way round.
+	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+	 */
+	if (msr <= 0x1fff) {
+		if (type & MSR_TYPE_R)
+			/* read-low */
+			__set_bit(msr, msr_bitmap + 0x000 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-low */
+			__set_bit(msr, msr_bitmap + 0x800 / f);
+
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		if (type & MSR_TYPE_R)
+			/* read-high */
+			__set_bit(msr, msr_bitmap + 0x400 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-high */
+			__set_bit(msr, msr_bitmap + 0xc00 / f);
+
+	}
+}
+
+static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
+			     			      u32 msr, int type, bool value)
+{
+	if (value)
+		vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
+	else
+		vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
+}
+
+static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
+{
+	u8 mode = 0;
+
+	if (cpu_has_secondary_exec_ctrls() &&
+	    (secondary_exec_controls_get(to_vmx(vcpu)) &
+	     SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
+		mode |= MSR_BITMAP_MODE_X2APIC;
+		if (enable_apicv && kvm_vcpu_apicv_active(vcpu))
+			mode |= MSR_BITMAP_MODE_X2APIC_APICV;
+	}
+
+	return mode;
+}
+
+static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
+					 u8 mode)
+{
+	int msr;
+
+	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+		unsigned word = msr / BITS_PER_LONG;
+		msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
+		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+	}
+
+	if (mode & MSR_BITMAP_MODE_X2APIC) {
+		/*
+		 * TPR reads and writes can be virtualized even if virtual interrupt
+		 * delivery is not in use.
+		 */
+		vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
+		if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
+			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
+			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
+			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
+		}
+	}
+}
+
+void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	u8 mode = vmx_msr_bitmap_mode(vcpu);
+	u8 changed = mode ^ vmx->msr_bitmap_mode;
+
+	if (!changed)
+		return;
+
+	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
+		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
+
+	vmx->msr_bitmap_mode = mode;
+}
+
+void pt_update_intercept_for_msr(struct vcpu_vmx *vmx)
+{
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN);
+	u32 i;
+
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_STATUS,
+							MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_BASE,
+							MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_MASK,
+							MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_CR3_MATCH,
+							MSR_TYPE_RW, flag);
+	for (i = 0; i < vmx->pt_desc.addr_range; i++) {
+		vmx_set_intercept_for_msr(msr_bitmap,
+			MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
+		vmx_set_intercept_for_msr(msr_bitmap,
+			MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
+	}
+}
+
+static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
+{
+	return enable_apicv;
+}
+
+static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	void *vapic_page;
+	u32 vppr;
+	int rvi;
+
+	if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
+		!nested_cpu_has_vid(get_vmcs12(vcpu)) ||
+		WARN_ON_ONCE(!vmx->nested.virtual_apic_map.gfn))
+		return false;
+
+	rvi = vmx_get_rvi();
+
+	vapic_page = vmx->nested.virtual_apic_map.hva;
+	vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
+
+	return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
+						     bool nested)
+{
+#ifdef CONFIG_SMP
+	int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
+
+	if (vcpu->mode == IN_GUEST_MODE) {
+		/*
+		 * The vector of interrupt to be delivered to vcpu had
+		 * been set in PIR before this function.
+		 *
+		 * Following cases will be reached in this block, and
+		 * we always send a notification event in all cases as
+		 * explained below.
+		 *
+		 * Case 1: vcpu keeps in non-root mode. Sending a
+		 * notification event posts the interrupt to vcpu.
+		 *
+		 * Case 2: vcpu exits to root mode and is still
+		 * runnable. PIR will be synced to vIRR before the
+		 * next vcpu entry. Sending a notification event in
+		 * this case has no effect, as vcpu is not in root
+		 * mode.
+		 *
+		 * Case 3: vcpu exits to root mode and is blocked.
+		 * vcpu_block() has already synced PIR to vIRR and
+		 * never blocks vcpu if vIRR is not cleared. Therefore,
+		 * a blocked vcpu here does not wait for any requested
+		 * interrupts in PIR, and sending a notification event
+		 * which has no effect is safe here.
+		 */
+
+		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
+		return true;
+	}
+#endif
+	return false;
+}
+
+static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
+						int vector)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (is_guest_mode(vcpu) &&
+	    vector == vmx->nested.posted_intr_nv) {
+		/*
+		 * If a posted intr is not recognized by hardware,
+		 * we will accomplish it in the next vmentry.
+		 */
+		vmx->nested.pi_pending = true;
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		/* the PIR and ON have been set by L1. */
+		if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))
+			kvm_vcpu_kick(vcpu);
+		return 0;
+	}
+	return -1;
+}
+/*
+ * Send interrupt to vcpu via posted interrupt way.
+ * 1. If target vcpu is running(non-root mode), send posted interrupt
+ * notification to vcpu and hardware will sync PIR to vIRR atomically.
+ * 2. If target vcpu isn't running(root mode), kick it to pick up the
+ * interrupt from PIR in next vmentry.
+ */
+static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int r;
+
+	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
+	if (!r)
+		return;
+
+	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
+		return;
+
+	/* If a previous notification has sent the IPI, nothing to do.  */
+	if (pi_test_and_set_on(&vmx->pi_desc))
+		return;
+
+	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
+		kvm_vcpu_kick(vcpu);
+}
+
+/*
+ * Set up the vmcs's constant host-state fields, i.e., host-state fields that
+ * will not change in the lifetime of the guest.
+ * Note that host-state that does change is set elsewhere. E.g., host-state
+ * that is set differently for each CPU is set in vmx_vcpu_load(), not here.
+ */
+void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
+{
+	u32 low32, high32;
+	unsigned long tmpl;
+	unsigned long cr0, cr3, cr4;
+
+	cr0 = read_cr0();
+	WARN_ON(cr0 & X86_CR0_TS);
+	vmcs_writel(HOST_CR0, cr0);  /* 22.2.3 */
+
+	/*
+	 * Save the most likely value for this task's CR3 in the VMCS.
+	 * We can't use __get_current_cr3_fast() because we're not atomic.
+	 */
+	cr3 = __read_cr3();
+	vmcs_writel(HOST_CR3, cr3);		/* 22.2.3  FIXME: shadow tables */
+	vmx->loaded_vmcs->host_state.cr3 = cr3;
+
+	/* Save the most likely value for this task's CR4 in the VMCS. */
+	cr4 = cr4_read_shadow();
+	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
+	vmx->loaded_vmcs->host_state.cr4 = cr4;
+
+	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
+#ifdef CONFIG_X86_64
+	/*
+	 * Load null selectors, so we can avoid reloading them in
+	 * vmx_prepare_switch_to_host(), in case userspace uses
+	 * the null selectors too (the expected case).
+	 */
+	vmcs_write16(HOST_DS_SELECTOR, 0);
+	vmcs_write16(HOST_ES_SELECTOR, 0);
+#else
+	vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
+	vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
+#endif
+	vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
+	vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8);  /* 22.2.4 */
+
+	vmcs_writel(HOST_IDTR_BASE, host_idt_base);   /* 22.2.4 */
+
+	vmcs_writel(HOST_RIP, (unsigned long)vmx_vmexit); /* 22.2.5 */
+
+	rdmsr(MSR_IA32_SYSENTER_CS, low32, high32);
+	vmcs_write32(HOST_IA32_SYSENTER_CS, low32);
+	rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl);
+	vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl);   /* 22.2.3 */
+
+	if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
+		rdmsr(MSR_IA32_CR_PAT, low32, high32);
+		vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32));
+	}
+
+	if (cpu_has_load_ia32_efer())
+		vmcs_write64(HOST_IA32_EFER, host_efer);
+}
+
+void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
+{
+	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
+	if (enable_ept)
+		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
+	if (is_guest_mode(&vmx->vcpu))
+		vmx->vcpu.arch.cr4_guest_owned_bits &=
+			~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask;
+	vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits);
+}
+
+u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
+{
+	u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl;
+
+	if (!kvm_vcpu_apicv_active(&vmx->vcpu))
+		pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
+
+	if (!enable_vnmi)
+		pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS;
+
+	if (!enable_preemption_timer)
+		pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+
+	return pin_based_exec_ctrl;
+}
+
+static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
+	if (cpu_has_secondary_exec_ctrls()) {
+		if (kvm_vcpu_apicv_active(vcpu))
+			secondary_exec_controls_setbit(vmx,
+				      SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				      SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+		else
+			secondary_exec_controls_clearbit(vmx,
+					SECONDARY_EXEC_APIC_REGISTER_VIRT |
+					SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+	}
+
+	if (cpu_has_vmx_msr_bitmap())
+		vmx_update_msr_bitmap(vcpu);
+}
+
+u32 vmx_exec_control(struct vcpu_vmx *vmx)
+{
+	u32 exec_control = vmcs_config.cpu_based_exec_ctrl;
+
+	if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)
+		exec_control &= ~CPU_BASED_MOV_DR_EXITING;
+
+	if (!cpu_need_tpr_shadow(&vmx->vcpu)) {
+		exec_control &= ~CPU_BASED_TPR_SHADOW;
+#ifdef CONFIG_X86_64
+		exec_control |= CPU_BASED_CR8_STORE_EXITING |
+				CPU_BASED_CR8_LOAD_EXITING;
+#endif
+	}
+	if (!enable_ept)
+		exec_control |= CPU_BASED_CR3_STORE_EXITING |
+				CPU_BASED_CR3_LOAD_EXITING  |
+				CPU_BASED_INVLPG_EXITING;
+	if (kvm_mwait_in_guest(vmx->vcpu.kvm))
+		exec_control &= ~(CPU_BASED_MWAIT_EXITING |
+				CPU_BASED_MONITOR_EXITING);
+	if (kvm_hlt_in_guest(vmx->vcpu.kvm))
+		exec_control &= ~CPU_BASED_HLT_EXITING;
+	return exec_control;
+}
+
+
+static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
+{
+	struct kvm_vcpu *vcpu = &vmx->vcpu;
+
+	u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
+
+	if (pt_mode == PT_MODE_SYSTEM)
+		exec_control &= ~(SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX);
+	if (!cpu_need_virtualize_apic_accesses(vcpu))
+		exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+	if (vmx->vpid == 0)
+		exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
+	if (!enable_ept) {
+		exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
+		enable_unrestricted_guest = 0;
+	}
+	if (!enable_unrestricted_guest)
+		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
+	if (kvm_pause_in_guest(vmx->vcpu.kvm))
+		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
+	if (!kvm_vcpu_apicv_active(vcpu))
+		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+
+	/* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP,
+	 * in vmx_set_cr4.  */
+	exec_control &= ~SECONDARY_EXEC_DESC;
+
+	/* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD
+	   (handle_vmptrld).
+	   We can NOT enable shadow_vmcs here because we don't have yet
+	   a current VMCS12
+	*/
+	exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
+
+	if (!enable_pml)
+		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
+
+	if (vmx_xsaves_supported()) {
+		/* Exposing XSAVES only when XSAVE is exposed */
+		bool xsaves_enabled =
+			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
+
+		if (!xsaves_enabled)
+			exec_control &= ~SECONDARY_EXEC_XSAVES;
+
+		if (nested) {
+			if (xsaves_enabled)
+				vmx->nested.msrs.secondary_ctls_high |=
+					SECONDARY_EXEC_XSAVES;
+			else
+				vmx->nested.msrs.secondary_ctls_high &=
+					~SECONDARY_EXEC_XSAVES;
+		}
+	}
+
+	if (vmx_rdtscp_supported()) {
+		bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP);
+		if (!rdtscp_enabled)
+			exec_control &= ~SECONDARY_EXEC_RDTSCP;
+
+		if (nested) {
+			if (rdtscp_enabled)
+				vmx->nested.msrs.secondary_ctls_high |=
+					SECONDARY_EXEC_RDTSCP;
+			else
+				vmx->nested.msrs.secondary_ctls_high &=
+					~SECONDARY_EXEC_RDTSCP;
+		}
+	}
+
+	if (vmx_invpcid_supported()) {
+		/* Exposing INVPCID only when PCID is exposed */
+		bool invpcid_enabled =
+			guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) &&
+			guest_cpuid_has(vcpu, X86_FEATURE_PCID);
+
+		if (!invpcid_enabled) {
+			exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
+			guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID);
+		}
+
+		if (nested) {
+			if (invpcid_enabled)
+				vmx->nested.msrs.secondary_ctls_high |=
+					SECONDARY_EXEC_ENABLE_INVPCID;
+			else
+				vmx->nested.msrs.secondary_ctls_high &=
+					~SECONDARY_EXEC_ENABLE_INVPCID;
+		}
+	}
+
+	if (vmx_rdrand_supported()) {
+		bool rdrand_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDRAND);
+		if (rdrand_enabled)
+			exec_control &= ~SECONDARY_EXEC_RDRAND_EXITING;
+
+		if (nested) {
+			if (rdrand_enabled)
+				vmx->nested.msrs.secondary_ctls_high |=
+					SECONDARY_EXEC_RDRAND_EXITING;
+			else
+				vmx->nested.msrs.secondary_ctls_high &=
+					~SECONDARY_EXEC_RDRAND_EXITING;
+		}
+	}
+
+	if (vmx_rdseed_supported()) {
+		bool rdseed_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDSEED);
+		if (rdseed_enabled)
+			exec_control &= ~SECONDARY_EXEC_RDSEED_EXITING;
+
+		if (nested) {
+			if (rdseed_enabled)
+				vmx->nested.msrs.secondary_ctls_high |=
+					SECONDARY_EXEC_RDSEED_EXITING;
+			else
+				vmx->nested.msrs.secondary_ctls_high &=
+					~SECONDARY_EXEC_RDSEED_EXITING;
+		}
+	}
+
+	if (vmx_waitpkg_supported()) {
+		bool waitpkg_enabled =
+			guest_cpuid_has(vcpu, X86_FEATURE_WAITPKG);
+
+		if (!waitpkg_enabled)
+			exec_control &= ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+
+		if (nested) {
+			if (waitpkg_enabled)
+				vmx->nested.msrs.secondary_ctls_high |=
+					SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+			else
+				vmx->nested.msrs.secondary_ctls_high &=
+					~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+		}
+	}
+
+	vmx->secondary_exec_control = exec_control;
+}
+
+static void ept_set_mmio_spte_mask(void)
+{
+	/*
+	 * EPT Misconfigurations can be generated if the value of bits 2:0
+	 * of an EPT paging-structure entry is 110b (write/execute).
+	 */
+	kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK,
+				   VMX_EPT_MISCONFIG_WX_VALUE, 0);
+}
+
+#define VMX_XSS_EXIT_BITMAP 0
+
+/*
+ * Sets up the vmcs for emulated real mode.
+ */
+static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
+{
+	int i;
+
+	if (nested)
+		nested_vmx_vcpu_setup();
+
+	if (cpu_has_vmx_msr_bitmap())
+		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
+
+	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
+
+	/* Control */
+	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
+	vmx->hv_deadline_tsc = -1;
+
+	exec_controls_set(vmx, vmx_exec_control(vmx));
+
+	if (cpu_has_secondary_exec_ctrls()) {
+		vmx_compute_secondary_exec_control(vmx);
+		secondary_exec_controls_set(vmx, vmx->secondary_exec_control);
+	}
+
+	if (kvm_vcpu_apicv_active(&vmx->vcpu)) {
+		vmcs_write64(EOI_EXIT_BITMAP0, 0);
+		vmcs_write64(EOI_EXIT_BITMAP1, 0);
+		vmcs_write64(EOI_EXIT_BITMAP2, 0);
+		vmcs_write64(EOI_EXIT_BITMAP3, 0);
+
+		vmcs_write16(GUEST_INTR_STATUS, 0);
+
+		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
+		vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
+	}
+
+	if (!kvm_pause_in_guest(vmx->vcpu.kvm)) {
+		vmcs_write32(PLE_GAP, ple_gap);
+		vmx->ple_window = ple_window;
+		vmx->ple_window_dirty = true;
+	}
+
+	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
+	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
+	vmcs_write32(CR3_TARGET_COUNT, 0);           /* 22.2.1 */
+
+	vmcs_write16(HOST_FS_SELECTOR, 0);            /* 22.2.4 */
+	vmcs_write16(HOST_GS_SELECTOR, 0);            /* 22.2.4 */
+	vmx_set_constant_host_state(vmx);
+	vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */
+	vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */
+
+	if (cpu_has_vmx_vmfunc())
+		vmcs_write64(VM_FUNCTION_CONTROL, 0);
+
+	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
+
+	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
+		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
+
+	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
+		u32 index = vmx_msr_index[i];
+		u32 data_low, data_high;
+		int j = vmx->nmsrs;
+
+		if (rdmsr_safe(index, &data_low, &data_high) < 0)
+			continue;
+		if (wrmsr_safe(index, data_low, data_high) < 0)
+			continue;
+		vmx->guest_msrs[j].index = i;
+		vmx->guest_msrs[j].data = 0;
+		vmx->guest_msrs[j].mask = -1ull;
+		++vmx->nmsrs;
+	}
+
+	vm_exit_controls_set(vmx, vmx_vmexit_ctrl());
+
+	/* 22.2.1, 20.8.1 */
+	vm_entry_controls_set(vmx, vmx_vmentry_ctrl());
+
+	vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS);
+
+	set_cr4_guest_host_mask(vmx);
+
+	if (vmx_xsaves_supported())
+		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
+
+	if (enable_pml) {
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
+	if (cpu_has_vmx_encls_vmexit())
+		vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);
+
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc));
+		/* Bit[6~0] are forced to 1, writes are ignored. */
+		vmx->pt_desc.guest.output_mask = 0x7F;
+		vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
+	}
+}
+
+static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct msr_data apic_base_msr;
+	u64 cr0;
+
+	vmx->rmode.vm86_active = 0;
+	vmx->spec_ctrl = 0;
+
+	vmx->msr_ia32_umwait_control = 0;
+
+	vcpu->arch.microcode_version = 0x100000000ULL;
+	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
+	vmx->hv_deadline_tsc = -1;
+	kvm_set_cr8(vcpu, 0);
+
+	if (!init_event) {
+		apic_base_msr.data = APIC_DEFAULT_PHYS_BASE |
+				     MSR_IA32_APICBASE_ENABLE;
+		if (kvm_vcpu_is_reset_bsp(vcpu))
+			apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
+		apic_base_msr.host_initiated = true;
+		kvm_set_apic_base(vcpu, &apic_base_msr);
+	}
+
+	vmx_segment_cache_clear(vmx);
+
+	seg_setup(VCPU_SREG_CS);
+	vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
+	vmcs_writel(GUEST_CS_BASE, 0xffff0000ul);
+
+	seg_setup(VCPU_SREG_DS);
+	seg_setup(VCPU_SREG_ES);
+	seg_setup(VCPU_SREG_FS);
+	seg_setup(VCPU_SREG_GS);
+	seg_setup(VCPU_SREG_SS);
+
+	vmcs_write16(GUEST_TR_SELECTOR, 0);
+	vmcs_writel(GUEST_TR_BASE, 0);
+	vmcs_write32(GUEST_TR_LIMIT, 0xffff);
+	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
+
+	vmcs_write16(GUEST_LDTR_SELECTOR, 0);
+	vmcs_writel(GUEST_LDTR_BASE, 0);
+	vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
+	vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);
+
+	if (!init_event) {
+		vmcs_write32(GUEST_SYSENTER_CS, 0);
+		vmcs_writel(GUEST_SYSENTER_ESP, 0);
+		vmcs_writel(GUEST_SYSENTER_EIP, 0);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+	}
+
+	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
+	kvm_rip_write(vcpu, 0xfff0);
+
+	vmcs_writel(GUEST_GDTR_BASE, 0);
+	vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);
+
+	vmcs_writel(GUEST_IDTR_BASE, 0);
+	vmcs_write32(GUEST_IDTR_LIMIT, 0xffff);
+
+	vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
+	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
+	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+	if (kvm_mpx_supported())
+		vmcs_write64(GUEST_BNDCFGS, 0);
+
+	setup_msrs(vmx);
+
+	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);  /* 22.2.1 */
+
+	if (cpu_has_vmx_tpr_shadow() && !init_event) {
+		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
+		if (cpu_need_tpr_shadow(vcpu))
+			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
+				     __pa(vcpu->arch.apic->regs));
+		vmcs_write32(TPR_THRESHOLD, 0);
+	}
+
+	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
+
+	if (vmx->vpid != 0)
+		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+
+	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+	vmx->vcpu.arch.cr0 = cr0;
+	vmx_set_cr0(vcpu, cr0); /* enter rmode */
+	vmx_set_cr4(vcpu, 0);
+	vmx_set_efer(vcpu, 0);
+
+	update_exception_bitmap(vcpu);
+
+	vpid_sync_context(vmx->vpid);
+	if (init_event)
+		vmx_clear_hlt(vcpu);
+}
+
+static void enable_irq_window(struct kvm_vcpu *vcpu)
+{
+	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING);
+}
+
+static void enable_nmi_window(struct kvm_vcpu *vcpu)
+{
+	if (!enable_vnmi ||
+	    vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
+		enable_irq_window(vcpu);
+		return;
+	}
+
+	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING);
+}
+
+static void vmx_inject_irq(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	uint32_t intr;
+	int irq = vcpu->arch.interrupt.nr;
+
+	trace_kvm_inj_virq(irq);
+
+	++vcpu->stat.irq_injections;
+	if (vmx->rmode.vm86_active) {
+		int inc_eip = 0;
+		if (vcpu->arch.interrupt.soft)
+			inc_eip = vcpu->arch.event_exit_inst_len;
+		kvm_inject_realmode_interrupt(vcpu, irq, inc_eip);
+		return;
+	}
+	intr = irq | INTR_INFO_VALID_MASK;
+	if (vcpu->arch.interrupt.soft) {
+		intr |= INTR_TYPE_SOFT_INTR;
+		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+			     vmx->vcpu.arch.event_exit_inst_len);
+	} else
+		intr |= INTR_TYPE_EXT_INTR;
+	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr);
+
+	vmx_clear_hlt(vcpu);
+}
+
+static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!enable_vnmi) {
+		/*
+		 * Tracking the NMI-blocked state in software is built upon
+		 * finding the next open IRQ window. This, in turn, depends on
+		 * well-behaving guests: They have to keep IRQs disabled at
+		 * least as long as the NMI handler runs. Otherwise we may
+		 * cause NMI nesting, maybe breaking the guest. But as this is
+		 * highly unlikely, we can live with the residual risk.
+		 */
+		vmx->loaded_vmcs->soft_vnmi_blocked = 1;
+		vmx->loaded_vmcs->vnmi_blocked_time = 0;
+	}
+
+	++vcpu->stat.nmi_injections;
+	vmx->loaded_vmcs->nmi_known_unmasked = false;
+
+	if (vmx->rmode.vm86_active) {
+		kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0);
+		return;
+	}
+
+	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
+
+	vmx_clear_hlt(vcpu);
+}
+
+bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool masked;
+
+	if (!enable_vnmi)
+		return vmx->loaded_vmcs->soft_vnmi_blocked;
+	if (vmx->loaded_vmcs->nmi_known_unmasked)
+		return false;
+	masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
+	vmx->loaded_vmcs->nmi_known_unmasked = !masked;
+	return masked;
+}
+
+void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!enable_vnmi) {
+		if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) {
+			vmx->loaded_vmcs->soft_vnmi_blocked = masked;
+			vmx->loaded_vmcs->vnmi_blocked_time = 0;
+		}
+	} else {
+		vmx->loaded_vmcs->nmi_known_unmasked = !masked;
+		if (masked)
+			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+				      GUEST_INTR_STATE_NMI);
+		else
+			vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+					GUEST_INTR_STATE_NMI);
+	}
+}
+
+static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
+{
+	if (to_vmx(vcpu)->nested.nested_run_pending)
+		return 0;
+
+	if (!enable_vnmi &&
+	    to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked)
+		return 0;
+
+	return	!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+		  (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI
+		   | GUEST_INTR_STATE_NMI));
+}
+
+static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
+{
+	return (!to_vmx(vcpu)->nested.nested_run_pending &&
+		vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
+}
+
+static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
+{
+	int ret;
+
+	if (enable_unrestricted_guest)
+		return 0;
+
+	ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr,
+				    PAGE_SIZE * 3);
+	if (ret)
+		return ret;
+	to_kvm_vmx(kvm)->tss_addr = addr;
+	return init_rmode_tss(kvm);
+}
+
+static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
+{
+	to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr;
+	return 0;
+}
+
+static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
+{
+	switch (vec) {
+	case BP_VECTOR:
+		/*
+		 * Update instruction length as we may reinject the exception
+		 * from user space while in guest debugging mode.
+		 */
+		to_vmx(vcpu)->vcpu.arch.event_exit_inst_len =
+			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			return false;
+		/* fall through */
+	case DB_VECTOR:
+		if (vcpu->guest_debug &
+			(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			return false;
+		/* fall through */
+	case DE_VECTOR:
+	case OF_VECTOR:
+	case BR_VECTOR:
+	case UD_VECTOR:
+	case DF_VECTOR:
+	case SS_VECTOR:
+	case GP_VECTOR:
+	case MF_VECTOR:
+		return true;
+	break;
+	}
+	return false;
+}
+
+static int handle_rmode_exception(struct kvm_vcpu *vcpu,
+				  int vec, u32 err_code)
+{
+	/*
+	 * Instruction with address size override prefix opcode 0x67
+	 * Cause the #SS fault with 0 error code in VM86 mode.
+	 */
+	if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) {
+		if (kvm_emulate_instruction(vcpu, 0)) {
+			if (vcpu->arch.halt_request) {
+				vcpu->arch.halt_request = 0;
+				return kvm_vcpu_halt(vcpu);
+			}
+			return 1;
+		}
+		return 0;
+	}
+
+	/*
+	 * Forward all other exceptions that are valid in real mode.
+	 * FIXME: Breaks guest debugging in real mode, needs to be fixed with
+	 *        the required debugging infrastructure rework.
+	 */
+	kvm_queue_exception(vcpu, vec);
+	return 1;
+}
+
+/*
+ * Trigger machine check on the host. We assume all the MSRs are already set up
+ * by the CPU and that we still run on the same CPU as the MCE occurred on.
+ * We pass a fake environment to the machine check handler because we want
+ * the guest to be always treated like user space, no matter what context
+ * it used internally.
+ */
+static void kvm_machine_check(void)
+{
+#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
+	struct pt_regs regs = {
+		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
+		.flags = X86_EFLAGS_IF,
+	};
+
+	do_machine_check(&regs, 0);
+#endif
+}
+
+static int handle_machine_check(struct kvm_vcpu *vcpu)
+{
+	/* handled by vmx_vcpu_run() */
+	return 1;
+}
+
+static int handle_exception_nmi(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_run *kvm_run = vcpu->run;
+	u32 intr_info, ex_no, error_code;
+	unsigned long cr2, rip, dr6;
+	u32 vect_info;
+
+	vect_info = vmx->idt_vectoring_info;
+	intr_info = vmx->exit_intr_info;
+
+	if (is_machine_check(intr_info) || is_nmi(intr_info))
+		return 1; /* handled by handle_exception_nmi_irqoff() */
+
+	if (is_invalid_opcode(intr_info))
+		return handle_ud(vcpu);
+
+	error_code = 0;
+	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
+		error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+
+	if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) {
+		WARN_ON_ONCE(!enable_vmware_backdoor);
+
+		/*
+		 * VMware backdoor emulation on #GP interception only handles
+		 * IN{S}, OUT{S}, and RDPMC, none of which generate a non-zero
+		 * error code on #GP.
+		 */
+		if (error_code) {
+			kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
+			return 1;
+		}
+		return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP);
+	}
+
+	/*
+	 * The #PF with PFEC.RSVD = 1 indicates the guest is accessing
+	 * MMIO, it is better to report an internal error.
+	 * See the comments in vmx_handle_exit.
+	 */
+	if ((vect_info & VECTORING_INFO_VALID_MASK) &&
+	    !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX;
+		vcpu->run->internal.ndata = 3;
+		vcpu->run->internal.data[0] = vect_info;
+		vcpu->run->internal.data[1] = intr_info;
+		vcpu->run->internal.data[2] = error_code;
+		return 0;
+	}
+
+	if (is_page_fault(intr_info)) {
+		cr2 = vmcs_readl(EXIT_QUALIFICATION);
+		/* EPT won't cause page fault directly */
+		WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept);
+		return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0);
+	}
+
+	ex_no = intr_info & INTR_INFO_VECTOR_MASK;
+
+	if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no))
+		return handle_rmode_exception(vcpu, ex_no, error_code);
+
+	switch (ex_no) {
+	case AC_VECTOR:
+		kvm_queue_exception_e(vcpu, AC_VECTOR, error_code);
+		return 1;
+	case DB_VECTOR:
+		dr6 = vmcs_readl(EXIT_QUALIFICATION);
+		if (!(vcpu->guest_debug &
+		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
+			vcpu->arch.dr6 &= ~DR_TRAP_BITS;
+			vcpu->arch.dr6 |= dr6 | DR6_RTM;
+			if (is_icebp(intr_info))
+				WARN_ON(!skip_emulated_instruction(vcpu));
+
+			kvm_queue_exception(vcpu, DB_VECTOR);
+			return 1;
+		}
+		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+		kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
+		/* fall through */
+	case BP_VECTOR:
+		/*
+		 * Update instruction length as we may reinject #BP from
+		 * user space while in guest debugging mode. Reading it for
+		 * #DB as well causes no harm, it is not used in that case.
+		 */
+		vmx->vcpu.arch.event_exit_inst_len =
+			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		rip = kvm_rip_read(vcpu);
+		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
+		kvm_run->debug.arch.exception = ex_no;
+		break;
+	default:
+		kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
+		kvm_run->ex.exception = ex_no;
+		kvm_run->ex.error_code = error_code;
+		break;
+	}
+	return 0;
+}
+
+static int handle_external_interrupt(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.irq_exits;
+	return 1;
+}
+
+static int handle_triple_fault(struct kvm_vcpu *vcpu)
+{
+	vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+	vcpu->mmio_needed = 0;
+	return 0;
+}
+
+static int handle_io(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification;
+	int size, in, string;
+	unsigned port;
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	string = (exit_qualification & 16) != 0;
+
+	++vcpu->stat.io_exits;
+
+	if (string)
+		return kvm_emulate_instruction(vcpu, 0);
+
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
+	in = (exit_qualification & 8) != 0;
+
+	return kvm_fast_pio(vcpu, size, port, in);
+}
+
+static void
+vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
+{
+	/*
+	 * Patch in the VMCALL instruction:
+	 */
+	hypercall[0] = 0x0f;
+	hypercall[1] = 0x01;
+	hypercall[2] = 0xc1;
+}
+
+/* called to set cr0 as appropriate for a mov-to-cr0 exit. */
+static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	if (is_guest_mode(vcpu)) {
+		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+		unsigned long orig_val = val;
+
+		/*
+		 * We get here when L2 changed cr0 in a way that did not change
+		 * any of L1's shadowed bits (see nested_vmx_exit_handled_cr),
+		 * but did change L0 shadowed bits. So we first calculate the
+		 * effective cr0 value that L1 would like to write into the
+		 * hardware. It consists of the L2-owned bits from the new
+		 * value combined with the L1-owned bits from L1's guest_cr0.
+		 */
+		val = (val & ~vmcs12->cr0_guest_host_mask) |
+			(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask);
+
+		if (!nested_guest_cr0_valid(vcpu, val))
+			return 1;
+
+		if (kvm_set_cr0(vcpu, val))
+			return 1;
+		vmcs_writel(CR0_READ_SHADOW, orig_val);
+		return 0;
+	} else {
+		if (to_vmx(vcpu)->nested.vmxon &&
+		    !nested_host_cr0_valid(vcpu, val))
+			return 1;
+
+		return kvm_set_cr0(vcpu, val);
+	}
+}
+
+static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	if (is_guest_mode(vcpu)) {
+		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+		unsigned long orig_val = val;
+
+		/* analogously to handle_set_cr0 */
+		val = (val & ~vmcs12->cr4_guest_host_mask) |
+			(vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask);
+		if (kvm_set_cr4(vcpu, val))
+			return 1;
+		vmcs_writel(CR4_READ_SHADOW, orig_val);
+		return 0;
+	} else
+		return kvm_set_cr4(vcpu, val);
+}
+
+static int handle_desc(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
+	return kvm_emulate_instruction(vcpu, 0);
+}
+
+static int handle_cr(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification, val;
+	int cr;
+	int reg;
+	int err;
+	int ret;
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	cr = exit_qualification & 15;
+	reg = (exit_qualification >> 8) & 15;
+	switch ((exit_qualification >> 4) & 3) {
+	case 0: /* mov to cr */
+		val = kvm_register_readl(vcpu, reg);
+		trace_kvm_cr_write(cr, val);
+		switch (cr) {
+		case 0:
+			err = handle_set_cr0(vcpu, val);
+			return kvm_complete_insn_gp(vcpu, err);
+		case 3:
+			WARN_ON_ONCE(enable_unrestricted_guest);
+			err = kvm_set_cr3(vcpu, val);
+			return kvm_complete_insn_gp(vcpu, err);
+		case 4:
+			err = handle_set_cr4(vcpu, val);
+			return kvm_complete_insn_gp(vcpu, err);
+		case 8: {
+				u8 cr8_prev = kvm_get_cr8(vcpu);
+				u8 cr8 = (u8)val;
+				err = kvm_set_cr8(vcpu, cr8);
+				ret = kvm_complete_insn_gp(vcpu, err);
+				if (lapic_in_kernel(vcpu))
+					return ret;
+				if (cr8_prev <= cr8)
+					return ret;
+				/*
+				 * TODO: we might be squashing a
+				 * KVM_GUESTDBG_SINGLESTEP-triggered
+				 * KVM_EXIT_DEBUG here.
+				 */
+				vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
+				return 0;
+			}
+		}
+		break;
+	case 2: /* clts */
+		WARN_ONCE(1, "Guest should always own CR0.TS");
+		vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
+		trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
+		return kvm_skip_emulated_instruction(vcpu);
+	case 1: /*mov from cr*/
+		switch (cr) {
+		case 3:
+			WARN_ON_ONCE(enable_unrestricted_guest);
+			val = kvm_read_cr3(vcpu);
+			kvm_register_write(vcpu, reg, val);
+			trace_kvm_cr_read(cr, val);
+			return kvm_skip_emulated_instruction(vcpu);
+		case 8:
+			val = kvm_get_cr8(vcpu);
+			kvm_register_write(vcpu, reg, val);
+			trace_kvm_cr_read(cr, val);
+			return kvm_skip_emulated_instruction(vcpu);
+		}
+		break;
+	case 3: /* lmsw */
+		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
+		trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val);
+		kvm_lmsw(vcpu, val);
+
+		return kvm_skip_emulated_instruction(vcpu);
+	default:
+		break;
+	}
+	vcpu->run->exit_reason = 0;
+	vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n",
+	       (int)(exit_qualification >> 4) & 3, cr);
+	return 0;
+}
+
+static int handle_dr(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification;
+	int dr, dr7, reg;
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
+
+	/* First, if DR does not exist, trigger UD */
+	if (!kvm_require_dr(vcpu, dr))
+		return 1;
+
+	/* Do not handle if the CPL > 0, will trigger GP on re-entry */
+	if (!kvm_require_cpl(vcpu, 0))
+		return 1;
+	dr7 = vmcs_readl(GUEST_DR7);
+	if (dr7 & DR7_GD) {
+		/*
+		 * As the vm-exit takes precedence over the debug trap, we
+		 * need to emulate the latter, either for the host or the
+		 * guest debugging itself.
+		 */
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
+			vcpu->run->debug.arch.dr6 = vcpu->arch.dr6;
+			vcpu->run->debug.arch.dr7 = dr7;
+			vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu);
+			vcpu->run->debug.arch.exception = DB_VECTOR;
+			vcpu->run->exit_reason = KVM_EXIT_DEBUG;
+			return 0;
+		} else {
+			vcpu->arch.dr6 &= ~DR_TRAP_BITS;
+			vcpu->arch.dr6 |= DR6_BD | DR6_RTM;
+			kvm_queue_exception(vcpu, DB_VECTOR);
+			return 1;
+		}
+	}
+
+	if (vcpu->guest_debug == 0) {
+		exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING);
+
+		/*
+		 * No more DR vmexits; force a reload of the debug registers
+		 * and reenter on this instruction.  The next vmexit will
+		 * retrieve the full state of the debug registers.
+		 */
+		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT;
+		return 1;
+	}
+
+	reg = DEBUG_REG_ACCESS_REG(exit_qualification);
+	if (exit_qualification & TYPE_MOV_FROM_DR) {
+		unsigned long val;
+
+		if (kvm_get_dr(vcpu, dr, &val))
+			return 1;
+		kvm_register_write(vcpu, reg, val);
+	} else
+		if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg)))
+			return 1;
+
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static u64 vmx_get_dr6(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.dr6;
+}
+
+static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
+{
+}
+
+static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
+{
+	get_debugreg(vcpu->arch.db[0], 0);
+	get_debugreg(vcpu->arch.db[1], 1);
+	get_debugreg(vcpu->arch.db[2], 2);
+	get_debugreg(vcpu->arch.db[3], 3);
+	get_debugreg(vcpu->arch.dr6, 6);
+	vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
+
+	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
+	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING);
+}
+
+static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	vmcs_writel(GUEST_DR7, val);
+}
+
+static int handle_cpuid(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_cpuid(vcpu);
+}
+
+static int handle_rdmsr(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_rdmsr(vcpu);
+}
+
+static int handle_wrmsr(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_wrmsr(vcpu);
+}
+
+static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
+{
+	kvm_apic_update_ppr(vcpu);
+	return 1;
+}
+
+static int handle_interrupt_window(struct kvm_vcpu *vcpu)
+{
+	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING);
+
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	++vcpu->stat.irq_window_exits;
+	return 1;
+}
+
+static int handle_halt(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_halt(vcpu);
+}
+
+static int handle_vmcall(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_hypercall(vcpu);
+}
+
+static int handle_invd(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_instruction(vcpu, 0);
+}
+
+static int handle_invlpg(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	kvm_mmu_invlpg(vcpu, exit_qualification);
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int handle_rdpmc(struct kvm_vcpu *vcpu)
+{
+	int err;
+
+	err = kvm_rdpmc(vcpu);
+	return kvm_complete_insn_gp(vcpu, err);
+}
+
+static int handle_wbinvd(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_wbinvd(vcpu);
+}
+
+static int handle_xsetbv(struct kvm_vcpu *vcpu)
+{
+	u64 new_bv = kvm_read_edx_eax(vcpu);
+	u32 index = kvm_rcx_read(vcpu);
+
+	if (kvm_set_xcr(vcpu, index, new_bv) == 0)
+		return kvm_skip_emulated_instruction(vcpu);
+	return 1;
+}
+
+static int handle_apic_access(struct kvm_vcpu *vcpu)
+{
+	if (likely(fasteoi)) {
+		unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+		int access_type, offset;
+
+		access_type = exit_qualification & APIC_ACCESS_TYPE;
+		offset = exit_qualification & APIC_ACCESS_OFFSET;
+		/*
+		 * Sane guest uses MOV to write EOI, with written value
+		 * not cared. So make a short-circuit here by avoiding
+		 * heavy instruction emulation.
+		 */
+		if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) &&
+		    (offset == APIC_EOI)) {
+			kvm_lapic_set_eoi(vcpu);
+			return kvm_skip_emulated_instruction(vcpu);
+		}
+	}
+	return kvm_emulate_instruction(vcpu, 0);
+}
+
+static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	int vector = exit_qualification & 0xff;
+
+	/* EOI-induced VM exit is trap-like and thus no need to adjust IP */
+	kvm_apic_set_eoi_accelerated(vcpu, vector);
+	return 1;
+}
+
+static int handle_apic_write(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	u32 offset = exit_qualification & 0xfff;
+
+	/* APIC-write VM exit is trap-like and thus no need to adjust IP */
+	kvm_apic_write_nodecode(vcpu, offset);
+	return 1;
+}
+
+static int handle_task_switch(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long exit_qualification;
+	bool has_error_code = false;
+	u32 error_code = 0;
+	u16 tss_selector;
+	int reason, type, idt_v, idt_index;
+
+	idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK);
+	idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK);
+	type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK);
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	reason = (u32)exit_qualification >> 30;
+	if (reason == TASK_SWITCH_GATE && idt_v) {
+		switch (type) {
+		case INTR_TYPE_NMI_INTR:
+			vcpu->arch.nmi_injected = false;
+			vmx_set_nmi_mask(vcpu, true);
+			break;
+		case INTR_TYPE_EXT_INTR:
+		case INTR_TYPE_SOFT_INTR:
+			kvm_clear_interrupt_queue(vcpu);
+			break;
+		case INTR_TYPE_HARD_EXCEPTION:
+			if (vmx->idt_vectoring_info &
+			    VECTORING_INFO_DELIVER_CODE_MASK) {
+				has_error_code = true;
+				error_code =
+					vmcs_read32(IDT_VECTORING_ERROR_CODE);
+			}
+			/* fall through */
+		case INTR_TYPE_SOFT_EXCEPTION:
+			kvm_clear_exception_queue(vcpu);
+			break;
+		default:
+			break;
+		}
+	}
+	tss_selector = exit_qualification;
+
+	if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION &&
+		       type != INTR_TYPE_EXT_INTR &&
+		       type != INTR_TYPE_NMI_INTR))
+		WARN_ON(!skip_emulated_instruction(vcpu));
+
+	/*
+	 * TODO: What about debug traps on tss switch?
+	 *       Are we supposed to inject them and update dr6?
+	 */
+	return kvm_task_switch(vcpu, tss_selector,
+			       type == INTR_TYPE_SOFT_INTR ? idt_index : -1,
+			       reason, has_error_code, error_code);
+}
+
+static int handle_ept_violation(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification;
+	gpa_t gpa;
+	u64 error_code;
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	/*
+	 * EPT violation happened while executing iret from NMI,
+	 * "blocked by NMI" bit has to be set before next VM entry.
+	 * There are errata that may cause this bit to not be set:
+	 * AAK134, BY25.
+	 */
+	if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+			enable_vnmi &&
+			(exit_qualification & INTR_INFO_UNBLOCK_NMI))
+		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
+
+	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+	trace_kvm_page_fault(gpa, exit_qualification);
+
+	/* Is it a read fault? */
+	error_code = (exit_qualification & EPT_VIOLATION_ACC_READ)
+		     ? PFERR_USER_MASK : 0;
+	/* Is it a write fault? */
+	error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE)
+		      ? PFERR_WRITE_MASK : 0;
+	/* Is it a fetch fault? */
+	error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
+		      ? PFERR_FETCH_MASK : 0;
+	/* ept page table entry is present? */
+	error_code |= (exit_qualification &
+		       (EPT_VIOLATION_READABLE | EPT_VIOLATION_WRITABLE |
+			EPT_VIOLATION_EXECUTABLE))
+		      ? PFERR_PRESENT_MASK : 0;
+
+	error_code |= (exit_qualification & 0x100) != 0 ?
+	       PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
+
+	vcpu->arch.exit_qualification = exit_qualification;
+	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
+}
+
+static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
+{
+	gpa_t gpa;
+
+	/*
+	 * A nested guest cannot optimize MMIO vmexits, because we have an
+	 * nGPA here instead of the required GPA.
+	 */
+	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+	if (!is_guest_mode(vcpu) &&
+	    !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+		trace_kvm_fast_mmio(gpa);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
+	return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
+}
+
+static int handle_nmi_window(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(!enable_vnmi);
+	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING);
+	++vcpu->stat.nmi_window_exits;
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	return 1;
+}
+
+static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool intr_window_requested;
+	unsigned count = 130;
+
+	/*
+	 * We should never reach the point where we are emulating L2
+	 * due to invalid guest state as that means we incorrectly
+	 * allowed a nested VMEntry with an invalid vmcs12.
+	 */
+	WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending);
+
+	intr_window_requested = exec_controls_get(vmx) &
+				CPU_BASED_VIRTUAL_INTR_PENDING;
+
+	while (vmx->emulation_required && count-- != 0) {
+		if (intr_window_requested && vmx_interrupt_allowed(vcpu))
+			return handle_interrupt_window(&vmx->vcpu);
+
+		if (kvm_test_request(KVM_REQ_EVENT, vcpu))
+			return 1;
+
+		if (!kvm_emulate_instruction(vcpu, 0))
+			return 0;
+
+		if (vmx->emulation_required && !vmx->rmode.vm86_active &&
+		    vcpu->arch.exception.pending) {
+			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+			vcpu->run->internal.suberror =
+						KVM_INTERNAL_ERROR_EMULATION;
+			vcpu->run->internal.ndata = 0;
+			return 0;
+		}
+
+		if (vcpu->arch.halt_request) {
+			vcpu->arch.halt_request = 0;
+			return kvm_vcpu_halt(vcpu);
+		}
+
+		/*
+		 * Note, return 1 and not 0, vcpu_run() is responsible for
+		 * morphing the pending signal into the proper return code.
+		 */
+		if (signal_pending(current))
+			return 1;
+
+		if (need_resched())
+			schedule();
+	}
+
+	return 1;
+}
+
+static void grow_ple_window(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned int old = vmx->ple_window;
+
+	vmx->ple_window = __grow_ple_window(old, ple_window,
+					    ple_window_grow,
+					    ple_window_max);
+
+	if (vmx->ple_window != old) {
+		vmx->ple_window_dirty = true;
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    vmx->ple_window, old);
+	}
+}
+
+static void shrink_ple_window(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned int old = vmx->ple_window;
+
+	vmx->ple_window = __shrink_ple_window(old, ple_window,
+					      ple_window_shrink,
+					      ple_window);
+
+	if (vmx->ple_window != old) {
+		vmx->ple_window_dirty = true;
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    vmx->ple_window, old);
+	}
+}
+
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+static void wakeup_handler(void)
+{
+	struct kvm_vcpu *vcpu;
+	int cpu = smp_processor_id();
+
+	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
+			blocked_vcpu_list) {
+		struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+		if (pi_test_on(pi_desc) == 1)
+			kvm_vcpu_kick(vcpu);
+	}
+	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+}
+
+static void vmx_enable_tdp(void)
+{
+	kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK,
+		enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull,
+		enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull,
+		0ull, VMX_EPT_EXECUTABLE_MASK,
+		cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK,
+		VMX_EPT_RWX_MASK, 0ull);
+
+	ept_set_mmio_spte_mask();
+	kvm_enable_tdp();
+}
+
+/*
+ * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
+ * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
+ */
+static int handle_pause(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_pause_in_guest(vcpu->kvm))
+		grow_ple_window(vcpu);
+
+	/*
+	 * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting"
+	 * VM-execution control is ignored if CPL > 0. OTOH, KVM
+	 * never set PAUSE_EXITING and just set PLE if supported,
+	 * so the vcpu must be CPL=0 if it gets a PAUSE exit.
+	 */
+	kvm_vcpu_on_spin(vcpu, true);
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int handle_nop(struct kvm_vcpu *vcpu)
+{
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int handle_mwait(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
+static int handle_invalid_op(struct kvm_vcpu *vcpu)
+{
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
+static int handle_monitor_trap(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
+static int handle_monitor(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
+static int handle_invpcid(struct kvm_vcpu *vcpu)
+{
+	u32 vmx_instruction_info;
+	unsigned long type;
+	bool pcid_enabled;
+	gva_t gva;
+	struct x86_exception e;
+	unsigned i;
+	unsigned long roots_to_free = 0;
+	struct {
+		u64 pcid;
+		u64 gla;
+	} operand;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
+
+	if (type > 3) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	/* According to the Intel instruction reference, the memory operand
+	 * is read even if it isn't needed (e.g., for type==all)
+	 */
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+				vmx_instruction_info, false,
+				sizeof(operand), &gva))
+		return 1;
+
+	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	if (operand.pcid >> 12 != 0) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+	switch (type) {
+	case INVPCID_TYPE_INDIV_ADDR:
+		if ((!pcid_enabled && (operand.pcid != 0)) ||
+		    is_noncanonical_address(operand.gla, vcpu)) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+		kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid);
+		return kvm_skip_emulated_instruction(vcpu);
+
+	case INVPCID_TYPE_SINGLE_CTXT:
+		if (!pcid_enabled && (operand.pcid != 0)) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+
+		if (kvm_get_active_pcid(vcpu) == operand.pcid) {
+			kvm_mmu_sync_roots(vcpu);
+			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+		}
+
+		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+			if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3)
+			    == operand.pcid)
+				roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
+
+		kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
+		/*
+		 * If neither the current cr3 nor any of the prev_roots use the
+		 * given PCID, then nothing needs to be done here because a
+		 * resync will happen anyway before switching to any other CR3.
+		 */
+
+		return kvm_skip_emulated_instruction(vcpu);
+
+	case INVPCID_TYPE_ALL_NON_GLOBAL:
+		/*
+		 * Currently, KVM doesn't mark global entries in the shadow
+		 * page tables, so a non-global flush just degenerates to a
+		 * global flush. If needed, we could optimize this later by
+		 * keeping track of global entries in shadow page tables.
+		 */
+
+		/* fall-through */
+	case INVPCID_TYPE_ALL_INCL_GLOBAL:
+		kvm_mmu_unload(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+
+	default:
+		BUG(); /* We have already checked above that type <= 3 */
+	}
+}
+
+static int handle_pml_full(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification;
+
+	trace_kvm_pml_full(vcpu->vcpu_id);
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	/*
+	 * PML buffer FULL happened while executing iret from NMI,
+	 * "blocked by NMI" bit has to be set before next VM entry.
+	 */
+	if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+			enable_vnmi &&
+			(exit_qualification & INTR_INFO_UNBLOCK_NMI))
+		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+				GUEST_INTR_STATE_NMI);
+
+	/*
+	 * PML buffer already flushed at beginning of VMEXIT. Nothing to do
+	 * here.., and there's no userspace involvement needed for PML.
+	 */
+	return 1;
+}
+
+static int handle_preemption_timer(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!vmx->req_immediate_exit &&
+	    !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled))
+		kvm_lapic_expired_hv_timer(vcpu);
+
+	return 1;
+}
+
+/*
+ * When nested=0, all VMX instruction VM Exits filter here.  The handlers
+ * are overwritten by nested_vmx_setup() when nested=1.
+ */
+static int handle_vmx_instruction(struct kvm_vcpu *vcpu)
+{
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
+static int handle_encls(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * SGX virtualization is not yet supported.  There is no software
+	 * enable bit for SGX, so we have to trap ENCLS and inject a #UD
+	 * to prevent the guest from executing ENCLS.
+	 */
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
+/*
+ * The exit handlers return 1 if the exit was handled fully and guest execution
+ * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
+ * to be done to userspace and return 0.
+ */
+static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
+	[EXIT_REASON_EXCEPTION_NMI]           = handle_exception_nmi,
+	[EXIT_REASON_EXTERNAL_INTERRUPT]      = handle_external_interrupt,
+	[EXIT_REASON_TRIPLE_FAULT]            = handle_triple_fault,
+	[EXIT_REASON_NMI_WINDOW]	      = handle_nmi_window,
+	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
+	[EXIT_REASON_CR_ACCESS]               = handle_cr,
+	[EXIT_REASON_DR_ACCESS]               = handle_dr,
+	[EXIT_REASON_CPUID]                   = handle_cpuid,
+	[EXIT_REASON_MSR_READ]                = handle_rdmsr,
+	[EXIT_REASON_MSR_WRITE]               = handle_wrmsr,
+	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
+	[EXIT_REASON_HLT]                     = handle_halt,
+	[EXIT_REASON_INVD]		      = handle_invd,
+	[EXIT_REASON_INVLPG]		      = handle_invlpg,
+	[EXIT_REASON_RDPMC]                   = handle_rdpmc,
+	[EXIT_REASON_VMCALL]                  = handle_vmcall,
+	[EXIT_REASON_VMCLEAR]		      = handle_vmx_instruction,
+	[EXIT_REASON_VMLAUNCH]		      = handle_vmx_instruction,
+	[EXIT_REASON_VMPTRLD]		      = handle_vmx_instruction,
+	[EXIT_REASON_VMPTRST]		      = handle_vmx_instruction,
+	[EXIT_REASON_VMREAD]		      = handle_vmx_instruction,
+	[EXIT_REASON_VMRESUME]		      = handle_vmx_instruction,
+	[EXIT_REASON_VMWRITE]		      = handle_vmx_instruction,
+	[EXIT_REASON_VMOFF]		      = handle_vmx_instruction,
+	[EXIT_REASON_VMON]		      = handle_vmx_instruction,
+	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
+	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
+	[EXIT_REASON_APIC_WRITE]              = handle_apic_write,
+	[EXIT_REASON_EOI_INDUCED]             = handle_apic_eoi_induced,
+	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
+	[EXIT_REASON_XSETBV]                  = handle_xsetbv,
+	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
+	[EXIT_REASON_MCE_DURING_VMENTRY]      = handle_machine_check,
+	[EXIT_REASON_GDTR_IDTR]		      = handle_desc,
+	[EXIT_REASON_LDTR_TR]		      = handle_desc,
+	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
+	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
+	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
+	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
+	[EXIT_REASON_MONITOR_TRAP_FLAG]       = handle_monitor_trap,
+	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
+	[EXIT_REASON_INVEPT]                  = handle_vmx_instruction,
+	[EXIT_REASON_INVVPID]                 = handle_vmx_instruction,
+	[EXIT_REASON_RDRAND]                  = handle_invalid_op,
+	[EXIT_REASON_RDSEED]                  = handle_invalid_op,
+	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
+	[EXIT_REASON_INVPCID]                 = handle_invpcid,
+	[EXIT_REASON_VMFUNC]		      = handle_vmx_instruction,
+	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
+	[EXIT_REASON_ENCLS]		      = handle_encls,
+};
+
+static const int kvm_vmx_max_exit_handlers =
+	ARRAY_SIZE(kvm_vmx_exit_handlers);
+
+static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
+{
+	*info1 = vmcs_readl(EXIT_QUALIFICATION);
+	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
+}
+
+static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
+{
+	if (vmx->pml_pg) {
+		__free_page(vmx->pml_pg);
+		vmx->pml_pg = NULL;
+	}
+}
+
+static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 *pml_buf;
+	u16 pml_idx;
+
+	pml_idx = vmcs_read16(GUEST_PML_INDEX);
+
+	/* Do nothing if PML buffer is empty */
+	if (pml_idx == (PML_ENTITY_NUM - 1))
+		return;
+
+	/* PML index always points to next available PML buffer entity */
+	if (pml_idx >= PML_ENTITY_NUM)
+		pml_idx = 0;
+	else
+		pml_idx++;
+
+	pml_buf = page_address(vmx->pml_pg);
+	for (; pml_idx < PML_ENTITY_NUM; pml_idx++) {
+		u64 gpa;
+
+		gpa = pml_buf[pml_idx];
+		WARN_ON(gpa & (PAGE_SIZE - 1));
+		kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
+	}
+
+	/* reset PML index */
+	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+}
+
+/*
+ * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap.
+ * Called before reporting dirty_bitmap to userspace.
+ */
+static void kvm_flush_pml_buffers(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+	/*
+	 * We only need to kick vcpu out of guest mode here, as PML buffer
+	 * is flushed at beginning of all VMEXITs, and it's obvious that only
+	 * vcpus running in guest are possible to have unflushed GPAs in PML
+	 * buffer.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vcpu_kick(vcpu);
+}
+
+static void vmx_dump_sel(char *name, uint32_t sel)
+{
+	pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
+	       name, vmcs_read16(sel),
+	       vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR),
+	       vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR),
+	       vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR));
+}
+
+static void vmx_dump_dtsel(char *name, uint32_t limit)
+{
+	pr_err("%s                           limit=0x%08x, base=0x%016lx\n",
+	       name, vmcs_read32(limit),
+	       vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
+}
+
+void dump_vmcs(void)
+{
+	u32 vmentry_ctl, vmexit_ctl;
+	u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control;
+	unsigned long cr4;
+	u64 efer;
+	int i, n;
+
+	if (!dump_invalid_vmcs) {
+		pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n");
+		return;
+	}
+
+	vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
+	vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
+	cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
+	cr4 = vmcs_readl(GUEST_CR4);
+	efer = vmcs_read64(GUEST_IA32_EFER);
+	secondary_exec_control = 0;
+	if (cpu_has_secondary_exec_ctrls())
+		secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+
+	pr_err("*** Guest State ***\n");
+	pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
+	       vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW),
+	       vmcs_readl(CR0_GUEST_HOST_MASK));
+	pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
+	       cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK));
+	pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3));
+	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
+	    (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA))
+	{
+		pr_err("PDPTR0 = 0x%016llx  PDPTR1 = 0x%016llx\n",
+		       vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1));
+		pr_err("PDPTR2 = 0x%016llx  PDPTR3 = 0x%016llx\n",
+		       vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3));
+	}
+	pr_err("RSP = 0x%016lx  RIP = 0x%016lx\n",
+	       vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP));
+	pr_err("RFLAGS=0x%08lx         DR7 = 0x%016lx\n",
+	       vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7));
+	pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
+	       vmcs_readl(GUEST_SYSENTER_ESP),
+	       vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP));
+	vmx_dump_sel("CS:  ", GUEST_CS_SELECTOR);
+	vmx_dump_sel("DS:  ", GUEST_DS_SELECTOR);
+	vmx_dump_sel("SS:  ", GUEST_SS_SELECTOR);
+	vmx_dump_sel("ES:  ", GUEST_ES_SELECTOR);
+	vmx_dump_sel("FS:  ", GUEST_FS_SELECTOR);
+	vmx_dump_sel("GS:  ", GUEST_GS_SELECTOR);
+	vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT);
+	vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
+	vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
+	vmx_dump_sel("TR:  ", GUEST_TR_SELECTOR);
+	if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
+	    (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
+		pr_err("EFER =     0x%016llx  PAT = 0x%016llx\n",
+		       efer, vmcs_read64(GUEST_IA32_PAT));
+	pr_err("DebugCtl = 0x%016llx  DebugExceptions = 0x%016lx\n",
+	       vmcs_read64(GUEST_IA32_DEBUGCTL),
+	       vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
+	if (cpu_has_load_perf_global_ctrl() &&
+	    vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+		pr_err("PerfGlobCtl = 0x%016llx\n",
+		       vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL));
+	if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS)
+		pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS));
+	pr_err("Interruptibility = %08x  ActivityState = %08x\n",
+	       vmcs_read32(GUEST_INTERRUPTIBILITY_INFO),
+	       vmcs_read32(GUEST_ACTIVITY_STATE));
+	if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
+		pr_err("InterruptStatus = %04x\n",
+		       vmcs_read16(GUEST_INTR_STATUS));
+
+	pr_err("*** Host State ***\n");
+	pr_err("RIP = 0x%016lx  RSP = 0x%016lx\n",
+	       vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP));
+	pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n",
+	       vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR),
+	       vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR),
+	       vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR),
+	       vmcs_read16(HOST_TR_SELECTOR));
+	pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n",
+	       vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE),
+	       vmcs_readl(HOST_TR_BASE));
+	pr_err("GDTBase=%016lx IDTBase=%016lx\n",
+	       vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE));
+	pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n",
+	       vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3),
+	       vmcs_readl(HOST_CR4));
+	pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
+	       vmcs_readl(HOST_IA32_SYSENTER_ESP),
+	       vmcs_read32(HOST_IA32_SYSENTER_CS),
+	       vmcs_readl(HOST_IA32_SYSENTER_EIP));
+	if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER))
+		pr_err("EFER = 0x%016llx  PAT = 0x%016llx\n",
+		       vmcs_read64(HOST_IA32_EFER),
+		       vmcs_read64(HOST_IA32_PAT));
+	if (cpu_has_load_perf_global_ctrl() &&
+	    vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+		pr_err("PerfGlobCtl = 0x%016llx\n",
+		       vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL));
+
+	pr_err("*** Control State ***\n");
+	pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n",
+	       pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control);
+	pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl);
+	pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n",
+	       vmcs_read32(EXCEPTION_BITMAP),
+	       vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK),
+	       vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH));
+	pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n",
+	       vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
+	       vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE),
+	       vmcs_read32(VM_ENTRY_INSTRUCTION_LEN));
+	pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n",
+	       vmcs_read32(VM_EXIT_INTR_INFO),
+	       vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
+	       vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
+	pr_err("        reason=%08x qualification=%016lx\n",
+	       vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION));
+	pr_err("IDTVectoring: info=%08x errcode=%08x\n",
+	       vmcs_read32(IDT_VECTORING_INFO_FIELD),
+	       vmcs_read32(IDT_VECTORING_ERROR_CODE));
+	pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET));
+	if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING)
+		pr_err("TSC Multiplier = 0x%016llx\n",
+		       vmcs_read64(TSC_MULTIPLIER));
+	if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) {
+		if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) {
+			u16 status = vmcs_read16(GUEST_INTR_STATUS);
+			pr_err("SVI|RVI = %02x|%02x ", status >> 8, status & 0xff);
+		}
+		pr_cont("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD));
+		if (secondary_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)
+			pr_err("APIC-access addr = 0x%016llx ", vmcs_read64(APIC_ACCESS_ADDR));
+		pr_cont("virt-APIC addr = 0x%016llx\n", vmcs_read64(VIRTUAL_APIC_PAGE_ADDR));
+	}
+	if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR)
+		pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV));
+	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT))
+		pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER));
+	n = vmcs_read32(CR3_TARGET_COUNT);
+	for (i = 0; i + 1 < n; i += 4)
+		pr_err("CR3 target%u=%016lx target%u=%016lx\n",
+		       i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2),
+		       i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2));
+	if (i < n)
+		pr_err("CR3 target%u=%016lx\n",
+		       i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2));
+	if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING)
+		pr_err("PLE Gap=%08x Window=%08x\n",
+		       vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW));
+	if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID)
+		pr_err("Virtual processor ID = 0x%04x\n",
+		       vmcs_read16(VIRTUAL_PROCESSOR_ID));
+}
+
+/*
+ * The guest has exited.  See if we can fix it or if we need userspace
+ * assistance.
+ */
+static int vmx_handle_exit(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 exit_reason = vmx->exit_reason;
+	u32 vectoring_info = vmx->idt_vectoring_info;
+
+	trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX);
+
+	/*
+	 * Flush logged GPAs PML buffer, this will make dirty_bitmap more
+	 * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before
+	 * querying dirty_bitmap, we only need to kick all vcpus out of guest
+	 * mode as if vcpus is in root mode, the PML buffer must has been
+	 * flushed already.
+	 */
+	if (enable_pml)
+		vmx_flush_pml_buffer(vcpu);
+
+	/* If guest state is invalid, start emulating */
+	if (vmx->emulation_required)
+		return handle_invalid_guest_state(vcpu);
+
+	if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason))
+		return nested_vmx_reflect_vmexit(vcpu, exit_reason);
+
+	if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
+		dump_vmcs();
+		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		vcpu->run->fail_entry.hardware_entry_failure_reason
+			= exit_reason;
+		return 0;
+	}
+
+	if (unlikely(vmx->fail)) {
+		dump_vmcs();
+		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		vcpu->run->fail_entry.hardware_entry_failure_reason
+			= vmcs_read32(VM_INSTRUCTION_ERROR);
+		return 0;
+	}
+
+	/*
+	 * Note:
+	 * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by
+	 * delivery event since it indicates guest is accessing MMIO.
+	 * The vm-exit can be triggered again after return to guest that
+	 * will cause infinite loop.
+	 */
+	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
+			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
+			exit_reason != EXIT_REASON_EPT_VIOLATION &&
+			exit_reason != EXIT_REASON_PML_FULL &&
+			exit_reason != EXIT_REASON_TASK_SWITCH)) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
+		vcpu->run->internal.ndata = 3;
+		vcpu->run->internal.data[0] = vectoring_info;
+		vcpu->run->internal.data[1] = exit_reason;
+		vcpu->run->internal.data[2] = vcpu->arch.exit_qualification;
+		if (exit_reason == EXIT_REASON_EPT_MISCONFIG) {
+			vcpu->run->internal.ndata++;
+			vcpu->run->internal.data[3] =
+				vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+		}
+		return 0;
+	}
+
+	if (unlikely(!enable_vnmi &&
+		     vmx->loaded_vmcs->soft_vnmi_blocked)) {
+		if (vmx_interrupt_allowed(vcpu)) {
+			vmx->loaded_vmcs->soft_vnmi_blocked = 0;
+		} else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL &&
+			   vcpu->arch.nmi_pending) {
+			/*
+			 * This CPU don't support us in finding the end of an
+			 * NMI-blocked window if the guest runs with IRQs
+			 * disabled. So we pull the trigger after 1 s of
+			 * futile waiting, but inform the user about this.
+			 */
+			printk(KERN_WARNING "%s: Breaking out of NMI-blocked "
+			       "state on VCPU %d after 1 s timeout\n",
+			       __func__, vcpu->vcpu_id);
+			vmx->loaded_vmcs->soft_vnmi_blocked = 0;
+		}
+	}
+
+	if (exit_reason < kvm_vmx_max_exit_handlers
+	    && kvm_vmx_exit_handlers[exit_reason])
+		return kvm_vmx_exit_handlers[exit_reason](vcpu);
+	else {
+		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
+				exit_reason);
+		dump_vmcs();
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror =
+			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+		vcpu->run->internal.ndata = 1;
+		vcpu->run->internal.data[0] = exit_reason;
+		return 0;
+	}
+}
+
+/*
+ * Software based L1D cache flush which is used when microcode providing
+ * the cache control MSR is not loaded.
+ *
+ * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
+ * flush it is required to read in 64 KiB because the replacement algorithm
+ * is not exactly LRU. This could be sized at runtime via topology
+ * information but as all relevant affected CPUs have 32KiB L1D cache size
+ * there is no point in doing so.
+ */
+static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
+{
+	int size = PAGE_SIZE << L1D_CACHE_ORDER;
+
+	/*
+	 * This code is only executed when the the flush mode is 'cond' or
+	 * 'always'
+	 */
+	if (static_branch_likely(&vmx_l1d_flush_cond)) {
+		bool flush_l1d;
+
+		/*
+		 * Clear the per-vcpu flush bit, it gets set again
+		 * either from vcpu_run() or from one of the unsafe
+		 * VMEXIT handlers.
+		 */
+		flush_l1d = vcpu->arch.l1tf_flush_l1d;
+		vcpu->arch.l1tf_flush_l1d = false;
+
+		/*
+		 * Clear the per-cpu flush bit, it gets set again from
+		 * the interrupt handlers.
+		 */
+		flush_l1d |= kvm_get_cpu_l1tf_flush_l1d();
+		kvm_clear_cpu_l1tf_flush_l1d();
+
+		if (!flush_l1d)
+			return;
+	}
+
+	vcpu->stat.l1d_flush++;
+
+	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		return;
+	}
+
+	asm volatile(
+		/* First ensure the pages are in the TLB */
+		"xorl	%%eax, %%eax\n"
+		".Lpopulate_tlb:\n\t"
+		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$4096, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lpopulate_tlb\n\t"
+		"xorl	%%eax, %%eax\n\t"
+		"cpuid\n\t"
+		/* Now fill the cache */
+		"xorl	%%eax, %%eax\n"
+		".Lfill_cache:\n"
+		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$64, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lfill_cache\n\t"
+		"lfence\n"
+		:: [flush_pages] "r" (vmx_l1d_flush_pages),
+		    [size] "r" (size)
+		: "eax", "ebx", "ecx", "edx");
+}
+
+static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (is_guest_mode(vcpu) &&
+		nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+		return;
+
+	if (irr == -1 || tpr < irr) {
+		vmcs_write32(TPR_THRESHOLD, 0);
+		return;
+	}
+
+	vmcs_write32(TPR_THRESHOLD, irr);
+}
+
+void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 sec_exec_control;
+
+	if (!lapic_in_kernel(vcpu))
+		return;
+
+	if (!flexpriority_enabled &&
+	    !cpu_has_vmx_virtualize_x2apic_mode())
+		return;
+
+	/* Postpone execution until vmcs01 is the current VMCS. */
+	if (is_guest_mode(vcpu)) {
+		vmx->nested.change_vmcs01_virtual_apic_mode = true;
+		return;
+	}
+
+	sec_exec_control = secondary_exec_controls_get(vmx);
+	sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+			      SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
+
+	switch (kvm_get_apic_mode(vcpu)) {
+	case LAPIC_MODE_INVALID:
+		WARN_ONCE(true, "Invalid local APIC state");
+	case LAPIC_MODE_DISABLED:
+		break;
+	case LAPIC_MODE_XAPIC:
+		if (flexpriority_enabled) {
+			sec_exec_control |=
+				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+			vmx_flush_tlb(vcpu, true);
+		}
+		break;
+	case LAPIC_MODE_X2APIC:
+		if (cpu_has_vmx_virtualize_x2apic_mode())
+			sec_exec_control |=
+				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+		break;
+	}
+	secondary_exec_controls_set(vmx, sec_exec_control);
+
+	vmx_update_msr_bitmap(vcpu);
+}
+
+static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
+{
+	if (!is_guest_mode(vcpu)) {
+		vmcs_write64(APIC_ACCESS_ADDR, hpa);
+		vmx_flush_tlb(vcpu, true);
+	}
+}
+
+static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
+{
+	u16 status;
+	u8 old;
+
+	if (max_isr == -1)
+		max_isr = 0;
+
+	status = vmcs_read16(GUEST_INTR_STATUS);
+	old = status >> 8;
+	if (max_isr != old) {
+		status &= 0xff;
+		status |= max_isr << 8;
+		vmcs_write16(GUEST_INTR_STATUS, status);
+	}
+}
+
+static void vmx_set_rvi(int vector)
+{
+	u16 status;
+	u8 old;
+
+	if (vector == -1)
+		vector = 0;
+
+	status = vmcs_read16(GUEST_INTR_STATUS);
+	old = (u8)status & 0xff;
+	if ((u8)vector != old) {
+		status &= ~0xff;
+		status |= (u8)vector;
+		vmcs_write16(GUEST_INTR_STATUS, status);
+	}
+}
+
+static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
+{
+	/*
+	 * When running L2, updating RVI is only relevant when
+	 * vmcs12 virtual-interrupt-delivery enabled.
+	 * However, it can be enabled only when L1 also
+	 * intercepts external-interrupts and in that case
+	 * we should not update vmcs02 RVI but instead intercept
+	 * interrupt. Therefore, do nothing when running L2.
+	 */
+	if (!is_guest_mode(vcpu))
+		vmx_set_rvi(max_irr);
+}
+
+static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int max_irr;
+	bool max_irr_updated;
+
+	WARN_ON(!vcpu->arch.apicv_active);
+	if (pi_test_on(&vmx->pi_desc)) {
+		pi_clear_on(&vmx->pi_desc);
+		/*
+		 * IOMMU can write to PID.ON, so the barrier matters even on UP.
+		 * But on x86 this is just a compiler barrier anyway.
+		 */
+		smp_mb__after_atomic();
+		max_irr_updated =
+			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
+
+		/*
+		 * If we are running L2 and L1 has a new pending interrupt
+		 * which can be injected, we should re-evaluate
+		 * what should be done with this new L1 interrupt.
+		 * If L1 intercepts external-interrupts, we should
+		 * exit from L2 to L1. Otherwise, interrupt should be
+		 * delivered directly to L2.
+		 */
+		if (is_guest_mode(vcpu) && max_irr_updated) {
+			if (nested_exit_on_intr(vcpu))
+				kvm_vcpu_exiting_guest_mode(vcpu);
+			else
+				kvm_make_request(KVM_REQ_EVENT, vcpu);
+		}
+	} else {
+		max_irr = kvm_lapic_find_highest_irr(vcpu);
+	}
+	vmx_hwapic_irr_update(vcpu, max_irr);
+	return max_irr;
+}
+
+static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	return pi_test_on(pi_desc) ||
+		(pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc));
+}
+
+static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]);
+	vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]);
+	vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]);
+	vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]);
+}
+
+static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	pi_clear_on(&vmx->pi_desc);
+	memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
+}
+
+static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
+{
+	vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+	/* if exit due to PF check for async PF */
+	if (is_page_fault(vmx->exit_intr_info))
+		vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason();
+
+	/* Handle machine checks before interrupts are enabled */
+	if (is_machine_check(vmx->exit_intr_info))
+		kvm_machine_check();
+
+	/* We need to handle NMIs before interrupts are enabled */
+	if (is_nmi(vmx->exit_intr_info)) {
+		kvm_before_interrupt(&vmx->vcpu);
+		asm("int $2");
+		kvm_after_interrupt(&vmx->vcpu);
+	}
+}
+
+static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
+{
+	unsigned int vector;
+	unsigned long entry;
+#ifdef CONFIG_X86_64
+	unsigned long tmp;
+#endif
+	gate_desc *desc;
+	u32 intr_info;
+
+	intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+	if (WARN_ONCE(!is_external_intr(intr_info),
+	    "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info))
+		return;
+
+	vector = intr_info & INTR_INFO_VECTOR_MASK;
+	desc = (gate_desc *)host_idt_base + vector;
+	entry = gate_offset(desc);
+
+	kvm_before_interrupt(vcpu);
+
+	asm volatile(
+#ifdef CONFIG_X86_64
+		"mov %%" _ASM_SP ", %[sp]\n\t"
+		"and $0xfffffffffffffff0, %%" _ASM_SP "\n\t"
+		"push $%c[ss]\n\t"
+		"push %[sp]\n\t"
+#endif
+		"pushf\n\t"
+		__ASM_SIZE(push) " $%c[cs]\n\t"
+		CALL_NOSPEC
+		:
+#ifdef CONFIG_X86_64
+		[sp]"=&r"(tmp),
+#endif
+		ASM_CALL_CONSTRAINT
+		:
+		THUNK_TARGET(entry),
+		[ss]"i"(__KERNEL_DS),
+		[cs]"i"(__KERNEL_CS)
+	);
+
+	kvm_after_interrupt(vcpu);
+}
+STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff);
+
+static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (vmx->exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+		handle_external_interrupt_irqoff(vcpu);
+	else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI)
+		handle_exception_nmi_irqoff(vmx);
+}
+
+static bool vmx_has_emulated_msr(int index)
+{
+	switch (index) {
+	case MSR_IA32_SMBASE:
+		/*
+		 * We cannot do SMM unless we can run the guest in big
+		 * real mode.
+		 */
+		return enable_unrestricted_guest || emulate_invalid_guest_state;
+	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
+		return nested;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		/* This is AMD only.  */
+		return false;
+	default:
+		return true;
+	}
+}
+
+static bool vmx_pt_supported(void)
+{
+	return pt_mode == PT_MODE_HOST_GUEST;
+}
+
+static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
+{
+	u32 exit_intr_info;
+	bool unblock_nmi;
+	u8 vector;
+	bool idtv_info_valid;
+
+	idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK;
+
+	if (enable_vnmi) {
+		if (vmx->loaded_vmcs->nmi_known_unmasked)
+			return;
+		/*
+		 * Can't use vmx->exit_intr_info since we're not sure what
+		 * the exit reason is.
+		 */
+		exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+		unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
+		vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
+		/*
+		 * SDM 3: 27.7.1.2 (September 2008)
+		 * Re-set bit "block by NMI" before VM entry if vmexit caused by
+		 * a guest IRET fault.
+		 * SDM 3: 23.2.2 (September 2008)
+		 * Bit 12 is undefined in any of the following cases:
+		 *  If the VM exit sets the valid bit in the IDT-vectoring
+		 *   information field.
+		 *  If the VM exit is due to a double fault.
+		 */
+		if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
+		    vector != DF_VECTOR && !idtv_info_valid)
+			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+				      GUEST_INTR_STATE_NMI);
+		else
+			vmx->loaded_vmcs->nmi_known_unmasked =
+				!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
+				  & GUEST_INTR_STATE_NMI);
+	} else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked))
+		vmx->loaded_vmcs->vnmi_blocked_time +=
+			ktime_to_ns(ktime_sub(ktime_get(),
+					      vmx->loaded_vmcs->entry_time));
+}
+
+static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
+				      u32 idt_vectoring_info,
+				      int instr_len_field,
+				      int error_code_field)
+{
+	u8 vector;
+	int type;
+	bool idtv_info_valid;
+
+	idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
+
+	vcpu->arch.nmi_injected = false;
+	kvm_clear_exception_queue(vcpu);
+	kvm_clear_interrupt_queue(vcpu);
+
+	if (!idtv_info_valid)
+		return;
+
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK;
+	type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK;
+
+	switch (type) {
+	case INTR_TYPE_NMI_INTR:
+		vcpu->arch.nmi_injected = true;
+		/*
+		 * SDM 3: 27.7.1.2 (September 2008)
+		 * Clear bit "block by NMI" before VM entry if a NMI
+		 * delivery faulted.
+		 */
+		vmx_set_nmi_mask(vcpu, false);
+		break;
+	case INTR_TYPE_SOFT_EXCEPTION:
+		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
+		/* fall through */
+	case INTR_TYPE_HARD_EXCEPTION:
+		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
+			u32 err = vmcs_read32(error_code_field);
+			kvm_requeue_exception_e(vcpu, vector, err);
+		} else
+			kvm_requeue_exception(vcpu, vector);
+		break;
+	case INTR_TYPE_SOFT_INTR:
+		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
+		/* fall through */
+	case INTR_TYPE_EXT_INTR:
+		kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR);
+		break;
+	default:
+		break;
+	}
+}
+
+static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
+{
+	__vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info,
+				  VM_EXIT_INSTRUCTION_LEN,
+				  IDT_VECTORING_ERROR_CODE);
+}
+
+static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
+{
+	__vmx_complete_interrupts(vcpu,
+				  vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
+				  VM_ENTRY_INSTRUCTION_LEN,
+				  VM_ENTRY_EXCEPTION_ERROR_CODE);
+
+	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
+}
+
+static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
+{
+	int i, nr_msrs;
+	struct perf_guest_switch_msr *msrs;
+
+	msrs = perf_guest_get_msrs(&nr_msrs);
+
+	if (!msrs)
+		return;
+
+	for (i = 0; i < nr_msrs; i++)
+		if (msrs[i].host == msrs[i].guest)
+			clear_atomic_switch_msr(vmx, msrs[i].msr);
+		else
+			add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
+					msrs[i].host, false);
+}
+
+static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx)
+{
+	u32 host_umwait_control;
+
+	if (!vmx_has_waitpkg(vmx))
+		return;
+
+	host_umwait_control = get_umwait_control_msr();
+
+	if (vmx->msr_ia32_umwait_control != host_umwait_control)
+		add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL,
+			vmx->msr_ia32_umwait_control,
+			host_umwait_control, false);
+	else
+		clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL);
+}
+
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 tscl;
+	u32 delta_tsc;
+
+	if (vmx->req_immediate_exit) {
+		vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0);
+		vmx->loaded_vmcs->hv_timer_soft_disabled = false;
+	} else if (vmx->hv_deadline_tsc != -1) {
+		tscl = rdtsc();
+		if (vmx->hv_deadline_tsc > tscl)
+			/* set_hv_timer ensures the delta fits in 32-bits */
+			delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+				cpu_preemption_timer_multi);
+		else
+			delta_tsc = 0;
+
+		vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+		vmx->loaded_vmcs->hv_timer_soft_disabled = false;
+	} else if (!vmx->loaded_vmcs->hv_timer_soft_disabled) {
+		vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, -1);
+		vmx->loaded_vmcs->hv_timer_soft_disabled = true;
+	}
+}
+
+void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp)
+{
+	if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) {
+		vmx->loaded_vmcs->host_state.rsp = host_rsp;
+		vmcs_writel(HOST_RSP, host_rsp);
+	}
+}
+
+bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched);
+
+static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long cr3, cr4;
+
+	/* Record the guest's net vcpu time for enforced NMI injections. */
+	if (unlikely(!enable_vnmi &&
+		     vmx->loaded_vmcs->soft_vnmi_blocked))
+		vmx->loaded_vmcs->entry_time = ktime_get();
+
+	/* Don't enter VMX if guest state is invalid, let the exit handler
+	   start emulation until we arrive back to a valid state */
+	if (vmx->emulation_required)
+		return;
+
+	if (vmx->ple_window_dirty) {
+		vmx->ple_window_dirty = false;
+		vmcs_write32(PLE_WINDOW, vmx->ple_window);
+	}
+
+	if (vmx->nested.need_vmcs12_to_shadow_sync)
+		nested_sync_vmcs12_to_shadow(vcpu);
+
+	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
+		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
+	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
+		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
+
+	cr3 = __get_current_cr3_fast();
+	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		vmx->loaded_vmcs->host_state.cr3 = cr3;
+	}
+
+	cr4 = cr4_read_shadow();
+	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
+		vmcs_writel(HOST_CR4, cr4);
+		vmx->loaded_vmcs->host_state.cr4 = cr4;
+	}
+
+	/* When single-stepping over STI and MOV SS, we must clear the
+	 * corresponding interruptibility bits in the guest state. Otherwise
+	 * vmentry fails as it then expects bit 14 (BS) in pending debug
+	 * exceptions being set, but that's not correct for the guest debugging
+	 * case. */
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vmx_set_interrupt_shadow(vcpu, 0);
+
+	kvm_load_guest_xcr0(vcpu);
+
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
+	    vcpu->arch.pkru != vmx->host_pkru)
+		__write_pkru(vcpu->arch.pkru);
+
+	pt_guest_enter(vmx);
+
+	atomic_switch_perf_msrs(vmx);
+	atomic_switch_umwait_control_msr(vmx);
+
+	if (enable_preemption_timer)
+		vmx_update_hv_timer(vcpu);
+
+	if (lapic_in_kernel(vcpu) &&
+		vcpu->arch.apic->lapic_timer.timer_advance_ns)
+		kvm_wait_lapic_expire(vcpu);
+
+	/*
+	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
+	 * is no need to worry about the conditional branch over the wrmsr
+	 * being speculatively taken.
+	 */
+	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
+
+	/* L1D Flush includes CPU buffer clear to mitigate MDS */
+	if (static_branch_unlikely(&vmx_l1d_should_flush))
+		vmx_l1d_flush(vcpu);
+	else if (static_branch_unlikely(&mds_user_clear))
+		mds_clear_cpu_buffers();
+
+	if (vcpu->arch.cr2 != read_cr2())
+		write_cr2(vcpu->arch.cr2);
+
+	vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
+				   vmx->loaded_vmcs->launched);
+
+	vcpu->arch.cr2 = read_cr2();
+
+	/*
+	 * We do not use IBRS in the kernel. If this vCPU has used the
+	 * SPEC_CTRL MSR it may have left it on; save the value and
+	 * turn it off. This is much more efficient than blindly adding
+	 * it to the atomic save/restore list. Especially as the former
+	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
+	 *
+	 * For non-nested case:
+	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 *
+	 * For nested case:
+	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 */
+	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
+
+	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
+
+	/* All fields are clean at this point */
+	if (static_branch_unlikely(&enable_evmcs))
+		current_evmcs->hv_clean_fields |=
+			HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+
+	if (static_branch_unlikely(&enable_evmcs))
+		current_evmcs->hv_vp_id = vcpu->arch.hyperv.vp_index;
+
+	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
+	if (vmx->host_debugctlmsr)
+		update_debugctlmsr(vmx->host_debugctlmsr);
+
+#ifndef CONFIG_X86_64
+	/*
+	 * The sysexit path does not restore ds/es, so we must set them to
+	 * a reasonable value ourselves.
+	 *
+	 * We can't defer this to vmx_prepare_switch_to_host() since that
+	 * function may be executed in interrupt context, which saves and
+	 * restore segments around it, nullifying its effect.
+	 */
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+#endif
+
+	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
+				  | (1 << VCPU_EXREG_RFLAGS)
+				  | (1 << VCPU_EXREG_PDPTR)
+				  | (1 << VCPU_EXREG_SEGMENTS)
+				  | (1 << VCPU_EXREG_CR3));
+	vcpu->arch.regs_dirty = 0;
+
+	pt_guest_exit(vmx);
+
+	/*
+	 * eager fpu is enabled if PKEY is supported and CR4 is switched
+	 * back on host, so it is safe to read guest PKRU from current
+	 * XSAVE.
+	 */
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
+		vcpu->arch.pkru = rdpkru();
+		if (vcpu->arch.pkru != vmx->host_pkru)
+			__write_pkru(vmx->host_pkru);
+	}
+
+	kvm_put_guest_xcr0(vcpu);
+
+	vmx->nested.nested_run_pending = 0;
+	vmx->idt_vectoring_info = 0;
+
+	vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON);
+	if ((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)
+		kvm_machine_check();
+
+	if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
+		return;
+
+	vmx->loaded_vmcs->launched = 1;
+	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
+
+	vmx_recover_nmi_blocking(vmx);
+	vmx_complete_interrupts(vmx);
+}
+
+static struct kvm *vmx_vm_alloc(void)
+{
+	struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx),
+					    GFP_KERNEL_ACCOUNT | __GFP_ZERO,
+					    PAGE_KERNEL);
+	return &kvm_vmx->kvm;
+}
+
+static void vmx_vm_free(struct kvm *kvm)
+{
+	kfree(kvm->arch.hyperv.hv_pa_pg);
+	vfree(to_kvm_vmx(kvm));
+}
+
+static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (enable_pml)
+		vmx_destroy_pml_buffer(vmx);
+	free_vpid(vmx->vpid);
+	nested_vmx_free_vcpu(vcpu);
+	free_loaded_vmcs(vmx->loaded_vmcs);
+	kfree(vmx->guest_msrs);
+	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
+	kmem_cache_free(kvm_vcpu_cache, vmx);
+}
+
+static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
+{
+	int err;
+	struct vcpu_vmx *vmx;
+	unsigned long *msr_bitmap;
+	int cpu;
+
+	BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0,
+		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
+
+	vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
+	if (!vmx)
+		return ERR_PTR(-ENOMEM);
+
+	vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+			GFP_KERNEL_ACCOUNT);
+	if (!vmx->vcpu.arch.user_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+		err = -ENOMEM;
+		goto free_partial_vcpu;
+	}
+
+	vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
+			GFP_KERNEL_ACCOUNT);
+	if (!vmx->vcpu.arch.guest_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
+		err = -ENOMEM;
+		goto free_user_fpu;
+	}
+
+	vmx->vpid = allocate_vpid();
+
+	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
+	if (err)
+		goto free_vcpu;
+
+	err = -ENOMEM;
+
+	/*
+	 * If PML is turned on, failure on enabling PML just results in failure
+	 * of creating the vcpu, therefore we can simplify PML logic (by
+	 * avoiding dealing with cases, such as enabling PML partially on vcpus
+	 * for the guest, etc.
+	 */
+	if (enable_pml) {
+		vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+		if (!vmx->pml_pg)
+			goto uninit_vcpu;
+	}
+
+	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
+	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
+		     > PAGE_SIZE);
+
+	if (!vmx->guest_msrs)
+		goto free_pml;
+
+	err = alloc_loaded_vmcs(&vmx->vmcs01);
+	if (err < 0)
+		goto free_msrs;
+
+	msr_bitmap = vmx->vmcs01.msr_bitmap;
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+	if (kvm_cstate_in_guest(kvm)) {
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
+	}
+	vmx->msr_bitmap_mode = 0;
+
+	vmx->loaded_vmcs = &vmx->vmcs01;
+	cpu = get_cpu();
+	vmx_vcpu_load(&vmx->vcpu, cpu);
+	vmx->vcpu.cpu = cpu;
+	vmx_vcpu_setup(vmx);
+	vmx_vcpu_put(&vmx->vcpu);
+	put_cpu();
+	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
+		err = alloc_apic_access_page(kvm);
+		if (err)
+			goto free_vmcs;
+	}
+
+	if (enable_ept && !enable_unrestricted_guest) {
+		err = init_rmode_identity_map(kvm);
+		if (err)
+			goto free_vmcs;
+	}
+
+	if (nested)
+		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
+					   vmx_capability.ept,
+					   kvm_vcpu_apicv_active(&vmx->vcpu));
+	else
+		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
+
+	vmx->nested.posted_intr_nv = -1;
+	vmx->nested.current_vmptr = -1ull;
+
+	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
+
+	/*
+	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+	 * or POSTED_INTR_WAKEUP_VECTOR.
+	 */
+	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+	vmx->pi_desc.sn = 1;
+
+	vmx->ept_pointer = INVALID_PAGE;
+
+	return &vmx->vcpu;
+
+free_vmcs:
+	free_loaded_vmcs(vmx->loaded_vmcs);
+free_msrs:
+	kfree(vmx->guest_msrs);
+free_pml:
+	vmx_destroy_pml_buffer(vmx);
+uninit_vcpu:
+	kvm_vcpu_uninit(&vmx->vcpu);
+free_vcpu:
+	free_vpid(vmx->vpid);
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
+free_partial_vcpu:
+	kmem_cache_free(kvm_vcpu_cache, vmx);
+	return ERR_PTR(err);
+}
+
+#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
+#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
+
+static int vmx_vm_init(struct kvm *kvm)
+{
+	spin_lock_init(&to_kvm_vmx(kvm)->ept_pointer_lock);
+
+	if (!ple_gap)
+		kvm->arch.pause_in_guest = true;
+
+	if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+			/* 'I explicitly don't care' is set */
+			break;
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+		case L1TF_MITIGATION_FULL:
+			/*
+			 * Warn upon starting the first VM in a potentially
+			 * insecure environment.
+			 */
+			if (sched_smt_active())
+				pr_warn_once(L1TF_MSG_SMT);
+			if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
+				pr_warn_once(L1TF_MSG_L1D);
+			break;
+		case L1TF_MITIGATION_FULL_FORCE:
+			/* Flush is enforced */
+			break;
+		}
+	}
+	return 0;
+}
+
+static int __init vmx_check_processor_compat(void)
+{
+	struct vmcs_config vmcs_conf;
+	struct vmx_capability vmx_cap;
+
+	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
+		return -EIO;
+	if (nested)
+		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
+					   enable_apicv);
+	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
+		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
+				smp_processor_id());
+		return -EIO;
+	}
+	return 0;
+}
+
+static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+	u8 cache;
+	u64 ipat = 0;
+
+	/* For VT-d and EPT combination
+	 * 1. MMIO: always map as UC
+	 * 2. EPT with VT-d:
+	 *   a. VT-d without snooping control feature: can't guarantee the
+	 *	result, try to trust guest.
+	 *   b. VT-d with snooping control feature: snooping control feature of
+	 *	VT-d engine can guarantee the cache correctness. Just set it
+	 *	to WB to keep consistent with host. So the same as item 3.
+	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
+	 *    consistent with host MTRR
+	 */
+	if (is_mmio) {
+		cache = MTRR_TYPE_UNCACHABLE;
+		goto exit;
+	}
+
+	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+		ipat = VMX_EPT_IPAT_BIT;
+		cache = MTRR_TYPE_WRBACK;
+		goto exit;
+	}
+
+	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
+		ipat = VMX_EPT_IPAT_BIT;
+		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+			cache = MTRR_TYPE_WRBACK;
+		else
+			cache = MTRR_TYPE_UNCACHABLE;
+		goto exit;
+	}
+
+	cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
+
+exit:
+	return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat;
+}
+
+static int vmx_get_lpage_level(void)
+{
+	if (enable_ept && !cpu_has_vmx_ept_1g_page())
+		return PT_DIRECTORY_LEVEL;
+	else
+		/* For shadow and EPT supported 1GB page */
+		return PT_PDPE_LEVEL;
+}
+
+static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx)
+{
+	/*
+	 * These bits in the secondary execution controls field
+	 * are dynamic, the others are mostly based on the hypervisor
+	 * architecture and the guest's CPUID.  Do not touch the
+	 * dynamic bits.
+	 */
+	u32 mask =
+		SECONDARY_EXEC_SHADOW_VMCS |
+		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+		SECONDARY_EXEC_DESC;
+
+	u32 new_ctl = vmx->secondary_exec_control;
+	u32 cur_ctl = secondary_exec_controls_get(vmx);
+
+	secondary_exec_controls_set(vmx, (new_ctl & ~mask) | (cur_ctl & mask));
+}
+
+/*
+ * Generate MSR_IA32_VMX_CR{0,4}_FIXED1 according to CPUID. Only set bits
+ * (indicating "allowed-1") if they are supported in the guest's CPUID.
+ */
+static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_cpuid_entry2 *entry;
+
+	vmx->nested.msrs.cr0_fixed1 = 0xffffffff;
+	vmx->nested.msrs.cr4_fixed1 = X86_CR4_PCE;
+
+#define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do {		\
+	if (entry && (entry->_reg & (_cpuid_mask)))			\
+		vmx->nested.msrs.cr4_fixed1 |= (_cr4_mask);	\
+} while (0)
+
+	entry = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+	cr4_fixed1_update(X86_CR4_VME,        edx, bit(X86_FEATURE_VME));
+	cr4_fixed1_update(X86_CR4_PVI,        edx, bit(X86_FEATURE_VME));
+	cr4_fixed1_update(X86_CR4_TSD,        edx, bit(X86_FEATURE_TSC));
+	cr4_fixed1_update(X86_CR4_DE,         edx, bit(X86_FEATURE_DE));
+	cr4_fixed1_update(X86_CR4_PSE,        edx, bit(X86_FEATURE_PSE));
+	cr4_fixed1_update(X86_CR4_PAE,        edx, bit(X86_FEATURE_PAE));
+	cr4_fixed1_update(X86_CR4_MCE,        edx, bit(X86_FEATURE_MCE));
+	cr4_fixed1_update(X86_CR4_PGE,        edx, bit(X86_FEATURE_PGE));
+	cr4_fixed1_update(X86_CR4_OSFXSR,     edx, bit(X86_FEATURE_FXSR));
+	cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM));
+	cr4_fixed1_update(X86_CR4_VMXE,       ecx, bit(X86_FEATURE_VMX));
+	cr4_fixed1_update(X86_CR4_SMXE,       ecx, bit(X86_FEATURE_SMX));
+	cr4_fixed1_update(X86_CR4_PCIDE,      ecx, bit(X86_FEATURE_PCID));
+	cr4_fixed1_update(X86_CR4_OSXSAVE,    ecx, bit(X86_FEATURE_XSAVE));
+
+	entry = kvm_find_cpuid_entry(vcpu, 0x7, 0);
+	cr4_fixed1_update(X86_CR4_FSGSBASE,   ebx, bit(X86_FEATURE_FSGSBASE));
+	cr4_fixed1_update(X86_CR4_SMEP,       ebx, bit(X86_FEATURE_SMEP));
+	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
+	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
+	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));
+
+#undef cr4_fixed1_update
+}
+
+static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (kvm_mpx_supported()) {
+		bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX);
+
+		if (mpx_enabled) {
+			vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
+			vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
+		} else {
+			vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS;
+			vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS;
+		}
+	}
+}
+
+static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_cpuid_entry2 *best = NULL;
+	int i;
+
+	for (i = 0; i < PT_CPUID_LEAVES; i++) {
+		best = kvm_find_cpuid_entry(vcpu, 0x14, i);
+		if (!best)
+			return;
+		vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax;
+		vmx->pt_desc.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM] = best->ebx;
+		vmx->pt_desc.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM] = best->ecx;
+		vmx->pt_desc.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM] = best->edx;
+	}
+
+	/* Get the number of configurable Address Ranges for filtering */
+	vmx->pt_desc.addr_range = intel_pt_validate_cap(vmx->pt_desc.caps,
+						PT_CAP_num_address_ranges);
+
+	/* Initialize and clear the no dependency bits */
+	vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS |
+			RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC);
+
+	/*
+	 * If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set otherwise
+	 * will inject an #GP
+	 */
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering))
+		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_CR3EN;
+
+	/*
+	 * If CPUID.(EAX=14H,ECX=0):EBX[1]=1 CYCEn, CycThresh and
+	 * PSBFreq can be set
+	 */
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc))
+		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_CYCLEACC |
+				RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ);
+
+	/*
+	 * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn BranchEn and
+	 * MTCFreq can be set
+	 */
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc))
+		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN |
+				RTIT_CTL_BRANCH_EN | RTIT_CTL_MTC_RANGE);
+
+	/* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_ptwrite))
+		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_FUP_ON_PTW |
+							RTIT_CTL_PTW_EN);
+
+	/* If CPUID.(EAX=14H,ECX=0):EBX[5]=1 PwrEvEn can be set */
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_power_event_trace))
+		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_PWR_EVT_EN;
+
+	/* If CPUID.(EAX=14H,ECX=0):ECX[0]=1 ToPA can be set */
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output))
+		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA;
+
+	/* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */
+	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys))
+		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN;
+
+	/* unmask address range configure area */
+	for (i = 0; i < vmx->pt_desc.addr_range; i++)
+		vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4));
+}
+
+static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (cpu_has_secondary_exec_ctrls()) {
+		vmx_compute_secondary_exec_control(vmx);
+		vmcs_set_secondary_exec_control(vmx);
+	}
+
+	if (nested_vmx_allowed(vcpu))
+		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+			FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	else
+		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
+			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+
+	if (nested_vmx_allowed(vcpu)) {
+		nested_vmx_cr_fixed1_bits_update(vcpu);
+		nested_vmx_entry_exit_ctls_update(vcpu);
+	}
+
+	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
+			guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT))
+		update_intel_pt_cfg(vcpu);
+}
+
+static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+{
+	if (func == 1 && nested)
+		entry->ecx |= bit(X86_FEATURE_VMX);
+}
+
+static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
+{
+	to_vmx(vcpu)->req_immediate_exit = true;
+}
+
+static int vmx_check_intercept(struct kvm_vcpu *vcpu,
+			       struct x86_instruction_info *info,
+			       enum x86_intercept_stage stage)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+
+	/*
+	 * RDPID causes #UD if disabled through secondary execution controls.
+	 * Because it is marked as EmulateOnUD, we need to intercept it here.
+	 */
+	if (info->intercept == x86_intercept_rdtscp &&
+	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+		ctxt->exception.vector = UD_VECTOR;
+		ctxt->exception.error_code_valid = false;
+		return X86EMUL_PROPAGATE_FAULT;
+	}
+
+	/* TODO: check more intercepts... */
+	return X86EMUL_CONTINUE;
+}
+
+#ifdef CONFIG_X86_64
+/* (a << shift) / divisor, return 1 if overflow otherwise 0 */
+static inline int u64_shl_div_u64(u64 a, unsigned int shift,
+				  u64 divisor, u64 *result)
+{
+	u64 low = a << shift, high = a >> (64 - shift);
+
+	/* To avoid the overflow on divq */
+	if (high >= divisor)
+		return 1;
+
+	/* Low hold the result, high hold rem which is discarded */
+	asm("divq %2\n\t" : "=a" (low), "=d" (high) :
+	    "rm" (divisor), "0" (low), "1" (high));
+	*result = low;
+
+	return 0;
+}
+
+static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
+			    bool *expired)
+{
+	struct vcpu_vmx *vmx;
+	u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
+	struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer;
+
+	if (kvm_mwait_in_guest(vcpu->kvm) ||
+		kvm_can_post_timer_interrupt(vcpu))
+		return -EOPNOTSUPP;
+
+	vmx = to_vmx(vcpu);
+	tscl = rdtsc();
+	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+	lapic_timer_advance_cycles = nsec_to_cycles(vcpu,
+						    ktimer->timer_advance_ns);
+
+	if (delta_tsc > lapic_timer_advance_cycles)
+		delta_tsc -= lapic_timer_advance_cycles;
+	else
+		delta_tsc = 0;
+
+	/* Convert to host delta tsc if tsc scaling is enabled */
+	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
+	    delta_tsc && u64_shl_div_u64(delta_tsc,
+				kvm_tsc_scaling_ratio_frac_bits,
+				vcpu->arch.tsc_scaling_ratio, &delta_tsc))
+		return -ERANGE;
+
+	/*
+	 * If the delta tsc can't fit in the 32 bit after the multi shift,
+	 * we can't use the preemption timer.
+	 * It's possible that it fits on later vmentries, but checking
+	 * on every vmentry is costly so we just use an hrtimer.
+	 */
+	if (delta_tsc >> (cpu_preemption_timer_multi + 32))
+		return -ERANGE;
+
+	vmx->hv_deadline_tsc = tscl + delta_tsc;
+	*expired = !delta_tsc;
+	return 0;
+}
+
+static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
+{
+	to_vmx(vcpu)->hv_deadline_tsc = -1;
+}
+#endif
+
+static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+	if (!kvm_pause_in_guest(vcpu->kvm))
+		shrink_ple_window(vcpu);
+}
+
+static void vmx_slot_enable_log_dirty(struct kvm *kvm,
+				     struct kvm_memory_slot *slot)
+{
+	kvm_mmu_slot_leaf_clear_dirty(kvm, slot);
+	kvm_mmu_slot_largepage_remove_write_access(kvm, slot);
+}
+
+static void vmx_slot_disable_log_dirty(struct kvm *kvm,
+				       struct kvm_memory_slot *slot)
+{
+	kvm_mmu_slot_set_dirty(kvm, slot);
+}
+
+static void vmx_flush_log_dirty(struct kvm *kvm)
+{
+	kvm_flush_pml_buffers(kvm);
+}
+
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	gpa_t gpa, dst;
+
+	if (is_guest_mode(vcpu)) {
+		WARN_ON_ONCE(vmx->nested.pml_full);
+
+		/*
+		 * Check if PML is enabled for the nested guest.
+		 * Whether eptp bit 6 is set is already checked
+		 * as part of A/D emulation.
+		 */
+		vmcs12 = get_vmcs12(vcpu);
+		if (!nested_cpu_has_pml(vmcs12))
+			return 0;
+
+		if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
+			vmx->nested.pml_full = true;
+			return 1;
+		}
+
+		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;
+
+		if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
+					 offset_in_page(dst), sizeof(gpa)))
+			return 0;
+
+		vmcs12->guest_pml_index--;
+	}
+
+	return 0;
+}
+
+static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
+					   struct kvm_memory_slot *memslot,
+					   gfn_t offset, unsigned long mask)
+{
+	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
+}
+
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	do {
+		old.control = new.control = pi_desc->control;
+		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+		     "Wakeup handler not enabled while the VCPU is blocked\n");
+
+		dest = cpu_physical_id(vcpu->cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'notification vector' */
+		new.nv = POSTED_INTR_VECTOR;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_del(&vcpu->blocked_vcpu_list);
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		vcpu->pre_pcpu = -1;
+	}
+}
+
+/*
+ * This routine does the following things for vCPU which is going
+ * to be blocked if VT-d PI is enabled.
+ * - Store the vCPU to the wakeup list, so when interrupts happen
+ *   we can find the right vCPU to wake up.
+ * - Change the Posted-interrupt descriptor as below:
+ *      'NDST' <-- vcpu->pre_pcpu
+ *      'NV' <-- POSTED_INTR_WAKEUP_VECTOR
+ * - If 'ON' is set during this process, which means at least one
+ *   interrupt is posted for this vCPU, we cannot block it, in
+ *   this case, return 1, otherwise, return 0.
+ *
+ */
+static int pi_pre_block(struct kvm_vcpu *vcpu)
+{
+	unsigned int dest;
+	struct pi_desc old, new;
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
+		return 0;
+
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+		vcpu->pre_pcpu = vcpu->cpu;
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_add_tail(&vcpu->blocked_vcpu_list,
+			      &per_cpu(blocked_vcpu_on_cpu,
+				       vcpu->pre_pcpu));
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+	}
+
+	do {
+		old.control = new.control = pi_desc->control;
+
+		WARN((pi_desc->sn == 1),
+		     "Warning: SN field of posted-interrupts "
+		     "is set before blocking\n");
+
+		/*
+		 * Since vCPU can be preempted during this process,
+		 * vcpu->cpu could be different with pre_pcpu, we
+		 * need to set pre_pcpu as the destination of wakeup
+		 * notification event, then we can find the right vCPU
+		 * to wakeup in wakeup handler if interrupts happen
+		 * when the vCPU is in blocked state.
+		 */
+		dest = cpu_physical_id(vcpu->pre_pcpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'wakeup vector' */
+		new.nv = POSTED_INTR_WAKEUP_VECTOR;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+	/* We should not block the vCPU if an interrupt is posted for it.  */
+	if (pi_test_on(pi_desc) == 1)
+		__pi_post_block(vcpu);
+
+	local_irq_enable();
+	return (vcpu->pre_pcpu == -1);
+}
+
+static int vmx_pre_block(struct kvm_vcpu *vcpu)
+{
+	if (pi_pre_block(vcpu))
+		return 1;
+
+	if (kvm_lapic_hv_timer_in_use(vcpu))
+		kvm_lapic_switch_to_sw_timer(vcpu);
+
+	return 0;
+}
+
+static void pi_post_block(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->pre_pcpu == -1)
+		return;
+
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	__pi_post_block(vcpu);
+	local_irq_enable();
+}
+
+static void vmx_post_block(struct kvm_vcpu *vcpu)
+{
+	if (kvm_x86_ops->set_hv_timer)
+		kvm_lapic_switch_to_hv_timer(vcpu);
+
+	pi_post_block(vcpu);
+}
+
+/*
+ * vmx_update_pi_irte - set IRTE for Posted-Interrupts
+ *
+ * @kvm: kvm
+ * @host_irq: host irq of the interrupt
+ * @guest_irq: gsi of the interrupt
+ * @set: set or unset PI
+ * returns 0 on success, < 0 on failure
+ */
+static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
+			      uint32_t guest_irq, bool set)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+	struct kvm_irq_routing_table *irq_rt;
+	struct kvm_lapic_irq irq;
+	struct kvm_vcpu *vcpu;
+	struct vcpu_data vcpu_info;
+	int idx, ret = 0;
+
+	if (!kvm_arch_has_assigned_device(kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP) ||
+		!kvm_vcpu_apicv_active(kvm->vcpus[0]))
+		return 0;
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+	if (guest_irq >= irq_rt->nr_rt_entries ||
+	    hlist_empty(&irq_rt->map[guest_irq])) {
+		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+			     guest_irq, irq_rt->nr_rt_entries);
+		goto out;
+	}
+
+	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
+		if (e->type != KVM_IRQ_ROUTING_MSI)
+			continue;
+		/*
+		 * VT-d PI cannot support posting multicast/broadcast
+		 * interrupts to a vCPU, we still use interrupt remapping
+		 * for these kind of interrupts.
+		 *
+		 * For lowest-priority interrupts, we only support
+		 * those with single CPU as the destination, e.g. user
+		 * configures the interrupts via /proc/irq or uses
+		 * irqbalance to make the interrupts single-CPU.
+		 *
+		 * We will support full lowest-priority interrupt later.
+		 *
+		 * In addition, we can only inject generic interrupts using
+		 * the PI mechanism, refuse to route others through it.
+		 */
+
+		kvm_set_msi_irq(kvm, e, &irq);
+		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
+		    !kvm_irq_is_postable(&irq)) {
+			/*
+			 * Make sure the IRTE is in remapped mode if
+			 * we don't handle it in posted mode.
+			 */
+			ret = irq_set_vcpu_affinity(host_irq, NULL);
+			if (ret < 0) {
+				printk(KERN_INFO
+				   "failed to back to remapped mode, irq: %u\n",
+				   host_irq);
+				goto out;
+			}
+
+			continue;
+		}
+
+		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
+		vcpu_info.vector = irq.vector;
+
+		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
+				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
+
+		if (set)
+			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
+		else
+			ret = irq_set_vcpu_affinity(host_irq, NULL);
+
+		if (ret < 0) {
+			printk(KERN_INFO "%s: failed to update PI IRTE\n",
+					__func__);
+			goto out;
+		}
+	}
+
+	ret = 0;
+out:
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+	return ret;
+}
+
+static void vmx_setup_mce(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.mcg_cap & MCG_LMCE_P)
+		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+			FEATURE_CONTROL_LMCE;
+	else
+		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
+			~FEATURE_CONTROL_LMCE;
+}
+
+static int vmx_smi_allowed(struct kvm_vcpu *vcpu)
+{
+	/* we need a nested vmexit to enter SMM, postpone if run is pending */
+	if (to_vmx(vcpu)->nested.nested_run_pending)
+		return 0;
+	return 1;
+}
+
+static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	vmx->nested.smm.guest_mode = is_guest_mode(vcpu);
+	if (vmx->nested.smm.guest_mode)
+		nested_vmx_vmexit(vcpu, -1, 0, 0);
+
+	vmx->nested.smm.vmxon = vmx->nested.vmxon;
+	vmx->nested.vmxon = false;
+	vmx_clear_hlt(vcpu);
+	return 0;
+}
+
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int ret;
+
+	if (vmx->nested.smm.vmxon) {
+		vmx->nested.vmxon = true;
+		vmx->nested.smm.vmxon = false;
+	}
+
+	if (vmx->nested.smm.guest_mode) {
+		ret = nested_vmx_enter_non_root_mode(vcpu, false);
+		if (ret)
+			return ret;
+
+		vmx->nested.smm.guest_mode = false;
+	}
+	return 0;
+}
+
+static int enable_smi_window(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
+static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.vmxon;
+}
+
+static __init int hardware_setup(void)
+{
+	unsigned long host_bndcfgs;
+	struct desc_ptr dt;
+	int r, i;
+
+	rdmsrl_safe(MSR_EFER, &host_efer);
+
+	store_idt(&dt);
+	host_idt_base = dt.address;
+
+	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)
+		kvm_define_shared_msr(i, vmx_msr_index[i]);
+
+	if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)
+		return -EIO;
+
+	if (boot_cpu_has(X86_FEATURE_NX))
+		kvm_enable_efer_bits(EFER_NX);
+
+	if (boot_cpu_has(X86_FEATURE_MPX)) {
+		rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs);
+		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
+	}
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		rdmsrl(MSR_IA32_XSS, host_xss);
+
+	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_ept() ||
+	    !cpu_has_vmx_ept_4levels() ||
+	    !cpu_has_vmx_ept_mt_wb() ||
+	    !cpu_has_vmx_invept_global())
+		enable_ept = 0;
+
+	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
+		enable_ept_ad_bits = 0;
+
+	if (!cpu_has_vmx_unrestricted_guest() || !enable_ept)
+		enable_unrestricted_guest = 0;
+
+	if (!cpu_has_vmx_flexpriority())
+		flexpriority_enabled = 0;
+
+	if (!cpu_has_virtual_nmis())
+		enable_vnmi = 0;
+
+	/*
+	 * set_apic_access_page_addr() is used to reload apic access
+	 * page upon invalidation.  No need to do anything if not
+	 * using the APIC_ACCESS_ADDR VMCS field.
+	 */
+	if (!flexpriority_enabled)
+		kvm_x86_ops->set_apic_access_page_addr = NULL;
+
+	if (!cpu_has_vmx_tpr_shadow())
+		kvm_x86_ops->update_cr8_intercept = NULL;
+
+	if (enable_ept && !cpu_has_vmx_ept_2m_page())
+		kvm_disable_largepages();
+
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH
+	    && enable_ept) {
+		kvm_x86_ops->tlb_remote_flush = hv_remote_flush_tlb;
+		kvm_x86_ops->tlb_remote_flush_with_range =
+				hv_remote_flush_tlb_with_range;
+	}
+#endif
+
+	if (!cpu_has_vmx_ple()) {
+		ple_gap = 0;
+		ple_window = 0;
+		ple_window_grow = 0;
+		ple_window_max = 0;
+		ple_window_shrink = 0;
+	}
+
+	if (!cpu_has_vmx_apicv()) {
+		enable_apicv = 0;
+		kvm_x86_ops->sync_pir_to_irr = NULL;
+	}
+
+	if (cpu_has_vmx_tsc_scaling()) {
+		kvm_has_tsc_control = true;
+		kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;
+		kvm_tsc_scaling_ratio_frac_bits = 48;
+	}
+
+	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
+
+	if (enable_ept)
+		vmx_enable_tdp();
+	else
+		kvm_disable_tdp();
+
+	/*
+	 * Only enable PML when hardware supports PML feature, and both EPT
+	 * and EPT A/D bit features are enabled -- PML depends on them to work.
+	 */
+	if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())
+		enable_pml = 0;
+
+	if (!enable_pml) {
+		kvm_x86_ops->slot_enable_log_dirty = NULL;
+		kvm_x86_ops->slot_disable_log_dirty = NULL;
+		kvm_x86_ops->flush_log_dirty = NULL;
+		kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
+	}
+
+	if (!cpu_has_vmx_preemption_timer())
+		enable_preemption_timer = false;
+
+	if (enable_preemption_timer) {
+		u64 use_timer_freq = 5000ULL * 1000 * 1000;
+		u64 vmx_msr;
+
+		rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
+		cpu_preemption_timer_multi =
+			vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+
+		if (tsc_khz)
+			use_timer_freq = (u64)tsc_khz * 1000;
+		use_timer_freq >>= cpu_preemption_timer_multi;
+
+		/*
+		 * KVM "disables" the preemption timer by setting it to its max
+		 * value.  Don't use the timer if it might cause spurious exits
+		 * at a rate faster than 0.1 Hz (of uninterrupted guest time).
+		 */
+		if (use_timer_freq > 0xffffffffu / 10)
+			enable_preemption_timer = false;
+	}
+
+	if (!enable_preemption_timer) {
+		kvm_x86_ops->set_hv_timer = NULL;
+		kvm_x86_ops->cancel_hv_timer = NULL;
+		kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit;
+	}
+
+	kvm_set_posted_intr_wakeup_handler(wakeup_handler);
+
+	kvm_mce_cap_supported |= MCG_LMCE_P;
+
+	if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST)
+		return -EINVAL;
+	if (!enable_ept || !cpu_has_vmx_intel_pt())
+		pt_mode = PT_MODE_SYSTEM;
+
+	if (nested) {
+		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
+					   vmx_capability.ept, enable_apicv);
+
+		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
+		if (r)
+			return r;
+	}
+
+	r = alloc_kvm_area();
+	if (r)
+		nested_vmx_hardware_unsetup();
+	return r;
+}
+
+static __exit void hardware_unsetup(void)
+{
+	if (nested)
+		nested_vmx_hardware_unsetup();
+
+	free_kvm_area();
+}
+
+static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
+	.cpu_has_kvm_support = cpu_has_kvm_support,
+	.disabled_by_bios = vmx_disabled_by_bios,
+	.hardware_setup = hardware_setup,
+	.hardware_unsetup = hardware_unsetup,
+	.check_processor_compatibility = vmx_check_processor_compat,
+	.hardware_enable = hardware_enable,
+	.hardware_disable = hardware_disable,
+	.cpu_has_accelerated_tpr = report_flexpriority,
+	.has_emulated_msr = vmx_has_emulated_msr,
+
+	.vm_init = vmx_vm_init,
+	.vm_alloc = vmx_vm_alloc,
+	.vm_free = vmx_vm_free,
+
+	.vcpu_create = vmx_create_vcpu,
+	.vcpu_free = vmx_free_vcpu,
+	.vcpu_reset = vmx_vcpu_reset,
+
+	.prepare_guest_switch = vmx_prepare_switch_to_guest,
+	.vcpu_load = vmx_vcpu_load,
+	.vcpu_put = vmx_vcpu_put,
+
+	.update_bp_intercept = update_exception_bitmap,
+	.get_msr_feature = vmx_get_msr_feature,
+	.get_msr = vmx_get_msr,
+	.set_msr = vmx_set_msr,
+	.get_segment_base = vmx_get_segment_base,
+	.get_segment = vmx_get_segment,
+	.set_segment = vmx_set_segment,
+	.get_cpl = vmx_get_cpl,
+	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
+	.decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
+	.decache_cr3 = vmx_decache_cr3,
+	.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
+	.set_cr0 = vmx_set_cr0,
+	.set_cr3 = vmx_set_cr3,
+	.set_cr4 = vmx_set_cr4,
+	.set_efer = vmx_set_efer,
+	.get_idt = vmx_get_idt,
+	.set_idt = vmx_set_idt,
+	.get_gdt = vmx_get_gdt,
+	.set_gdt = vmx_set_gdt,
+	.get_dr6 = vmx_get_dr6,
+	.set_dr6 = vmx_set_dr6,
+	.set_dr7 = vmx_set_dr7,
+	.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
+	.cache_reg = vmx_cache_reg,
+	.get_rflags = vmx_get_rflags,
+	.set_rflags = vmx_set_rflags,
+
+	.tlb_flush = vmx_flush_tlb,
+	.tlb_flush_gva = vmx_flush_tlb_gva,
+
+	.run = vmx_vcpu_run,
+	.handle_exit = vmx_handle_exit,
+	.skip_emulated_instruction = skip_emulated_instruction,
+	.set_interrupt_shadow = vmx_set_interrupt_shadow,
+	.get_interrupt_shadow = vmx_get_interrupt_shadow,
+	.patch_hypercall = vmx_patch_hypercall,
+	.set_irq = vmx_inject_irq,
+	.set_nmi = vmx_inject_nmi,
+	.queue_exception = vmx_queue_exception,
+	.cancel_injection = vmx_cancel_injection,
+	.interrupt_allowed = vmx_interrupt_allowed,
+	.nmi_allowed = vmx_nmi_allowed,
+	.get_nmi_mask = vmx_get_nmi_mask,
+	.set_nmi_mask = vmx_set_nmi_mask,
+	.enable_nmi_window = enable_nmi_window,
+	.enable_irq_window = enable_irq_window,
+	.update_cr8_intercept = update_cr8_intercept,
+	.set_virtual_apic_mode = vmx_set_virtual_apic_mode,
+	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
+	.get_enable_apicv = vmx_get_enable_apicv,
+	.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
+	.load_eoi_exitmap = vmx_load_eoi_exitmap,
+	.apicv_post_state_restore = vmx_apicv_post_state_restore,
+	.hwapic_irr_update = vmx_hwapic_irr_update,
+	.hwapic_isr_update = vmx_hwapic_isr_update,
+	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
+	.sync_pir_to_irr = vmx_sync_pir_to_irr,
+	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
+	.dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt,
+
+	.set_tss_addr = vmx_set_tss_addr,
+	.set_identity_map_addr = vmx_set_identity_map_addr,
+	.get_tdp_level = get_ept_level,
+	.get_mt_mask = vmx_get_mt_mask,
+
+	.get_exit_info = vmx_get_exit_info,
+
+	.get_lpage_level = vmx_get_lpage_level,
+
+	.cpuid_update = vmx_cpuid_update,
+
+	.rdtscp_supported = vmx_rdtscp_supported,
+	.invpcid_supported = vmx_invpcid_supported,
+
+	.set_supported_cpuid = vmx_set_supported_cpuid,
+
+	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
+
+	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
+	.write_l1_tsc_offset = vmx_write_l1_tsc_offset,
+
+	.set_tdp_cr3 = vmx_set_cr3,
+
+	.check_intercept = vmx_check_intercept,
+	.handle_exit_irqoff = vmx_handle_exit_irqoff,
+	.mpx_supported = vmx_mpx_supported,
+	.xsaves_supported = vmx_xsaves_supported,
+	.umip_emulated = vmx_umip_emulated,
+	.pt_supported = vmx_pt_supported,
+
+	.request_immediate_exit = vmx_request_immediate_exit,
+
+	.sched_in = vmx_sched_in,
+
+	.slot_enable_log_dirty = vmx_slot_enable_log_dirty,
+	.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
+	.flush_log_dirty = vmx_flush_log_dirty,
+	.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
+	.write_log_dirty = vmx_write_pml_buffer,
+
+	.pre_block = vmx_pre_block,
+	.post_block = vmx_post_block,
+
+	.pmu_ops = &intel_pmu_ops,
+
+	.update_pi_irte = vmx_update_pi_irte,
+
+#ifdef CONFIG_X86_64
+	.set_hv_timer = vmx_set_hv_timer,
+	.cancel_hv_timer = vmx_cancel_hv_timer,
+#endif
+
+	.setup_mce = vmx_setup_mce,
+
+	.smi_allowed = vmx_smi_allowed,
+	.pre_enter_smm = vmx_pre_enter_smm,
+	.pre_leave_smm = vmx_pre_leave_smm,
+	.enable_smi_window = enable_smi_window,
+
+	.check_nested_events = NULL,
+	.get_nested_state = NULL,
+	.set_nested_state = NULL,
+	.get_vmcs12_pages = NULL,
+	.nested_enable_evmcs = NULL,
+	.nested_get_evmcs_version = NULL,
+	.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
+	.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
+};
+
+static void vmx_cleanup_l1d_flush(void)
+{
+	if (vmx_l1d_flush_pages) {
+		free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
+		vmx_l1d_flush_pages = NULL;
+	}
+	/* Restore state so sysfs ignores VMX */
+	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
+}
+
+static void vmx_exit(void)
+{
+#ifdef CONFIG_KEXEC_CORE
+	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
+	synchronize_rcu();
+#endif
+
+	kvm_exit();
+
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (static_branch_unlikely(&enable_evmcs)) {
+		int cpu;
+		struct hv_vp_assist_page *vp_ap;
+		/*
+		 * Reset everything to support using non-enlightened VMCS
+		 * access later (e.g. when we reload the module with
+		 * enlightened_vmcs=0)
+		 */
+		for_each_online_cpu(cpu) {
+			vp_ap =	hv_get_vp_assist_page(cpu);
+
+			if (!vp_ap)
+				continue;
+
+			vp_ap->nested_control.features.directhypercall = 0;
+			vp_ap->current_nested_vmcs = 0;
+			vp_ap->enlighten_vmentry = 0;
+		}
+
+		static_branch_disable(&enable_evmcs);
+	}
+#endif
+	vmx_cleanup_l1d_flush();
+}
+module_exit(vmx_exit);
+
+static int __init vmx_init(void)
+{
+	int r;
+
+#if IS_ENABLED(CONFIG_HYPERV)
+	/*
+	 * Enlightened VMCS usage should be recommended and the host needs
+	 * to support eVMCS v1 or above. We can also disable eVMCS support
+	 * with module parameter.
+	 */
+	if (enlightened_vmcs &&
+	    ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED &&
+	    (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >=
+	    KVM_EVMCS_VERSION) {
+		int cpu;
+
+		/* Check that we have assist pages on all online CPUs */
+		for_each_online_cpu(cpu) {
+			if (!hv_get_vp_assist_page(cpu)) {
+				enlightened_vmcs = false;
+				break;
+			}
+		}
+
+		if (enlightened_vmcs) {
+			pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n");
+			static_branch_enable(&enable_evmcs);
+		}
+
+		if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH)
+			vmx_x86_ops.enable_direct_tlbflush
+				= hv_enable_direct_tlbflush;
+
+	} else {
+		enlightened_vmcs = false;
+	}
+#endif
+
+	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+		     __alignof__(struct vcpu_vmx), THIS_MODULE);
+	if (r)
+		return r;
+
+	/*
+	 * Must be called after kvm_init() so enable_ept is properly set
+	 * up. Hand the parameter mitigation value in which was stored in
+	 * the pre module init parser. If no parameter was given, it will
+	 * contain 'auto' which will be turned into the default 'cond'
+	 * mitigation mode.
+	 */
+	r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
+	if (r) {
+		vmx_exit();
+		return r;
+	}
+
+#ifdef CONFIG_KEXEC_CORE
+	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
+			   crash_vmclear_local_loaded_vmcss);
+#endif
+	vmx_check_vmcs12_offsets();
+
+	return 0;
+}
+module_init(vmx_init);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
new file mode 100644
index 0000000..5a0f34b
--- /dev/null
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -0,0 +1,522 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_H
+#define __KVM_X86_VMX_H
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm.h>
+#include <asm/intel_pt.h>
+
+#include "capabilities.h"
+#include "ops.h"
+#include "vmcs.h"
+
+extern const u32 vmx_msr_index[];
+extern u64 host_efer;
+
+extern u32 get_umwait_control_msr(void);
+
+#define MSR_TYPE_R	1
+#define MSR_TYPE_W	2
+#define MSR_TYPE_RW	3
+
+#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+
+#define NR_AUTOLOAD_MSRS 8
+
+struct vmx_msrs {
+	unsigned int		nr;
+	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
+};
+
+struct shared_msr_entry {
+	unsigned index;
+	u64 data;
+	u64 mask;
+};
+
+enum segment_cache_field {
+	SEG_FIELD_SEL = 0,
+	SEG_FIELD_BASE = 1,
+	SEG_FIELD_LIMIT = 2,
+	SEG_FIELD_AR = 3,
+
+	SEG_FIELD_NR = 4
+};
+
+/* Posted-Interrupt Descriptor */
+struct pi_desc {
+	u32 pir[8];     /* Posted interrupt requested */
+	union {
+		struct {
+				/* bit 256 - Outstanding Notification */
+			u16	on	: 1,
+				/* bit 257 - Suppress Notification */
+				sn	: 1,
+				/* bit 271:258 - Reserved */
+				rsvd_1	: 14;
+				/* bit 279:272 - Notification Vector */
+			u8	nv;
+				/* bit 287:280 - Reserved */
+			u8	rsvd_2;
+				/* bit 319:288 - Notification Destination */
+			u32	ndst;
+		};
+		u64 control;
+	};
+	u32 rsvd[6];
+} __aligned(64);
+
+#define RTIT_ADDR_RANGE		4
+
+struct pt_ctx {
+	u64 ctl;
+	u64 status;
+	u64 output_base;
+	u64 output_mask;
+	u64 cr3_match;
+	u64 addr_a[RTIT_ADDR_RANGE];
+	u64 addr_b[RTIT_ADDR_RANGE];
+};
+
+struct pt_desc {
+	u64 ctl_bitmask;
+	u32 addr_range;
+	u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
+	struct pt_ctx host;
+	struct pt_ctx guest;
+};
+
+/*
+ * The nested_vmx structure is part of vcpu_vmx, and holds information we need
+ * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
+ */
+struct nested_vmx {
+	/* Has the level1 guest done vmxon? */
+	bool vmxon;
+	gpa_t vmxon_ptr;
+	bool pml_full;
+
+	/* The guest-physical address of the current VMCS L1 keeps for L2 */
+	gpa_t current_vmptr;
+	/*
+	 * Cache of the guest's VMCS, existing outside of guest memory.
+	 * Loaded from guest memory during VMPTRLD. Flushed to guest
+	 * memory during VMCLEAR and VMPTRLD.
+	 */
+	struct vmcs12 *cached_vmcs12;
+	/*
+	 * Cache of the guest's shadow VMCS, existing outside of guest
+	 * memory. Loaded from guest memory during VM entry. Flushed
+	 * to guest memory during VM exit.
+	 */
+	struct vmcs12 *cached_shadow_vmcs12;
+
+	/*
+	 * Indicates if the shadow vmcs or enlightened vmcs must be updated
+	 * with the data held by struct vmcs12.
+	 */
+	bool need_vmcs12_to_shadow_sync;
+	bool dirty_vmcs12;
+
+	/*
+	 * Indicates lazily loaded guest state has not yet been decached from
+	 * vmcs02.
+	 */
+	bool need_sync_vmcs02_to_vmcs12_rare;
+
+	/*
+	 * vmcs02 has been initialized, i.e. state that is constant for
+	 * vmcs02 has been written to the backing VMCS.  Initialization
+	 * is delayed until L1 actually attempts to run a nested VM.
+	 */
+	bool vmcs02_initialized;
+
+	bool change_vmcs01_virtual_apic_mode;
+
+	/*
+	 * Enlightened VMCS has been enabled. It does not mean that L1 has to
+	 * use it. However, VMX features available to L1 will be limited based
+	 * on what the enlightened VMCS supports.
+	 */
+	bool enlightened_vmcs_enabled;
+
+	/* L2 must run next, and mustn't decide to exit to L1. */
+	bool nested_run_pending;
+
+	struct loaded_vmcs vmcs02;
+
+	/*
+	 * Guest pages referred to in the vmcs02 with host-physical
+	 * pointers, so we must keep them pinned while L2 runs.
+	 */
+	struct page *apic_access_page;
+	struct kvm_host_map virtual_apic_map;
+	struct kvm_host_map pi_desc_map;
+
+	struct kvm_host_map msr_bitmap_map;
+
+	struct pi_desc *pi_desc;
+	bool pi_pending;
+	u16 posted_intr_nv;
+
+	struct hrtimer preemption_timer;
+	bool preemption_timer_expired;
+
+	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
+	u64 vmcs01_debugctl;
+	u64 vmcs01_guest_bndcfgs;
+
+	u16 vpid02;
+	u16 last_vpid;
+
+	struct nested_vmx_msrs msrs;
+
+	/* SMM related state */
+	struct {
+		/* in VMX operation on SMM entry? */
+		bool vmxon;
+		/* in guest mode on SMM entry? */
+		bool guest_mode;
+	} smm;
+
+	gpa_t hv_evmcs_vmptr;
+	struct kvm_host_map hv_evmcs_map;
+	struct hv_enlightened_vmcs *hv_evmcs;
+};
+
+struct vcpu_vmx {
+	struct kvm_vcpu       vcpu;
+	u8                    fail;
+	u8		      msr_bitmap_mode;
+
+	/*
+	 * If true, host state has been stored in vmx->loaded_vmcs for
+	 * the CPU registers that only need to be switched when transitioning
+	 * to/from the kernel, and the registers have been loaded with guest
+	 * values.  If false, host state is loaded in the CPU registers
+	 * and vmx->loaded_vmcs->host_state is invalid.
+	 */
+	bool		      guest_state_loaded;
+
+	u32                   exit_intr_info;
+	u32                   idt_vectoring_info;
+	ulong                 rflags;
+
+	struct shared_msr_entry *guest_msrs;
+	int                   nmsrs;
+	int                   save_nmsrs;
+	bool                  guest_msrs_ready;
+#ifdef CONFIG_X86_64
+	u64		      msr_host_kernel_gs_base;
+	u64		      msr_guest_kernel_gs_base;
+#endif
+
+	u64		      spec_ctrl;
+	u32		      msr_ia32_umwait_control;
+
+	u32 secondary_exec_control;
+
+	/*
+	 * loaded_vmcs points to the VMCS currently used in this vcpu. For a
+	 * non-nested (L1) guest, it always points to vmcs01. For a nested
+	 * guest (L2), it points to a different VMCS.
+	 */
+	struct loaded_vmcs    vmcs01;
+	struct loaded_vmcs   *loaded_vmcs;
+
+	struct msr_autoload {
+		struct vmx_msrs guest;
+		struct vmx_msrs host;
+	} msr_autoload;
+
+	struct {
+		int vm86_active;
+		ulong save_rflags;
+		struct kvm_segment segs[8];
+	} rmode;
+	struct {
+		u32 bitmask; /* 4 bits per segment (1 bit per field) */
+		struct kvm_save_segment {
+			u16 selector;
+			unsigned long base;
+			u32 limit;
+			u32 ar;
+		} seg[8];
+	} segment_cache;
+	int vpid;
+	bool emulation_required;
+
+	u32 exit_reason;
+
+	/* Posted interrupt descriptor */
+	struct pi_desc pi_desc;
+
+	/* Support for a guest hypervisor (nested VMX) */
+	struct nested_vmx nested;
+
+	/* Dynamic PLE window. */
+	unsigned int ple_window;
+	bool ple_window_dirty;
+
+	bool req_immediate_exit;
+
+	/* Support for PML */
+#define PML_ENTITY_NUM		512
+	struct page *pml_pg;
+
+	/* apic deadline value in host tsc */
+	u64 hv_deadline_tsc;
+
+	u64 current_tsc_ratio;
+
+	u32 host_pkru;
+
+	unsigned long host_debugctlmsr;
+
+	/*
+	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
+	 * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
+	 * in msr_ia32_feature_control_valid_bits.
+	 */
+	u64 msr_ia32_feature_control;
+	u64 msr_ia32_feature_control_valid_bits;
+	u64 ept_pointer;
+
+	struct pt_desc pt_desc;
+};
+
+enum ept_pointers_status {
+	EPT_POINTERS_CHECK = 0,
+	EPT_POINTERS_MATCH = 1,
+	EPT_POINTERS_MISMATCH = 2
+};
+
+struct kvm_vmx {
+	struct kvm kvm;
+
+	unsigned int tss_addr;
+	bool ept_identity_pagetable_done;
+	gpa_t ept_identity_map_addr;
+
+	enum ept_pointers_status ept_pointers_match;
+	spinlock_t ept_pointer_lock;
+};
+
+bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu);
+void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+int allocate_vpid(void);
+void free_vpid(int vpid);
+void vmx_set_constant_host_state(struct vcpu_vmx *vmx);
+void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
+void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
+			unsigned long fs_base, unsigned long gs_base);
+int vmx_get_cpl(struct kvm_vcpu *vcpu);
+unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
+void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
+u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);
+void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask);
+void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer);
+void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
+void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
+int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+void set_cr4_guest_host_mask(struct vcpu_vmx *vmx);
+void ept_save_pdptrs(struct kvm_vcpu *vcpu);
+void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa);
+void update_exception_bitmap(struct kvm_vcpu *vcpu);
+void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
+bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
+void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
+void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
+struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr);
+void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
+void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
+
+#define POSTED_INTR_ON  0
+#define POSTED_INTR_SN  1
+
+static inline bool pi_test_and_set_on(struct pi_desc *pi_desc)
+{
+	return test_and_set_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc)
+{
+	return test_and_clear_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
+{
+	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
+}
+
+static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
+{
+	return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
+}
+
+static inline void pi_set_sn(struct pi_desc *pi_desc)
+{
+	set_bit(POSTED_INTR_SN,
+		(unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_set_on(struct pi_desc *pi_desc)
+{
+	set_bit(POSTED_INTR_ON,
+		(unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_clear_on(struct pi_desc *pi_desc)
+{
+	clear_bit(POSTED_INTR_ON,
+		(unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_clear_sn(struct pi_desc *pi_desc)
+{
+	clear_bit(POSTED_INTR_SN,
+		(unsigned long *)&pi_desc->control);
+}
+
+static inline int pi_test_on(struct pi_desc *pi_desc)
+{
+	return test_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline int pi_test_sn(struct pi_desc *pi_desc)
+{
+	return test_bit(POSTED_INTR_SN,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline u8 vmx_get_rvi(void)
+{
+	return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+}
+
+#define BUILD_CONTROLS_SHADOW(lname, uname)				    \
+static inline void lname##_controls_set(struct vcpu_vmx *vmx, u32 val)	    \
+{									    \
+	if (vmx->loaded_vmcs->controls_shadow.lname != val) {		    \
+		vmcs_write32(uname, val);				    \
+		vmx->loaded_vmcs->controls_shadow.lname = val;		    \
+	}								    \
+}									    \
+static inline u32 lname##_controls_get(struct vcpu_vmx *vmx)		    \
+{									    \
+	return vmx->loaded_vmcs->controls_shadow.lname;			    \
+}									    \
+static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u32 val)   \
+{									    \
+	lname##_controls_set(vmx, lname##_controls_get(vmx) | val);	    \
+}									    \
+static inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u32 val) \
+{									    \
+	lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val);	    \
+}
+BUILD_CONTROLS_SHADOW(vm_entry, VM_ENTRY_CONTROLS)
+BUILD_CONTROLS_SHADOW(vm_exit, VM_EXIT_CONTROLS)
+BUILD_CONTROLS_SHADOW(pin, PIN_BASED_VM_EXEC_CONTROL)
+BUILD_CONTROLS_SHADOW(exec, CPU_BASED_VM_EXEC_CONTROL)
+BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL)
+
+static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
+{
+	vmx->segment_cache.bitmask = 0;
+}
+
+static inline u32 vmx_vmentry_ctrl(void)
+{
+	u32 vmentry_ctrl = vmcs_config.vmentry_ctrl;
+	if (pt_mode == PT_MODE_SYSTEM)
+		vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP |
+				  VM_ENTRY_LOAD_IA32_RTIT_CTL);
+	/* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
+	return vmentry_ctrl &
+		~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER);
+}
+
+static inline u32 vmx_vmexit_ctrl(void)
+{
+	u32 vmexit_ctrl = vmcs_config.vmexit_ctrl;
+	if (pt_mode == PT_MODE_SYSTEM)
+		vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP |
+				 VM_EXIT_CLEAR_IA32_RTIT_CTL);
+	/* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
+	return vmexit_ctrl &
+		~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER);
+}
+
+u32 vmx_exec_control(struct vcpu_vmx *vmx);
+u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx);
+
+static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm)
+{
+	return container_of(kvm, struct kvm_vmx, kvm);
+}
+
+static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
+{
+	return container_of(vcpu, struct vcpu_vmx, vcpu);
+}
+
+static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
+{
+	return &(to_vmx(vcpu)->pi_desc);
+}
+
+struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags);
+void free_vmcs(struct vmcs *vmcs);
+int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs);
+void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs);
+void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs);
+void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs);
+
+static inline struct vmcs *alloc_vmcs(bool shadow)
+{
+	return alloc_vmcs_cpu(shadow, raw_smp_processor_id(),
+			      GFP_KERNEL_ACCOUNT);
+}
+
+u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa);
+
+static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid,
+				bool invalidate_gpa)
+{
+	if (enable_ept && (invalidate_gpa || !enable_vpid)) {
+		if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
+			return;
+		ept_sync_context(construct_eptp(vcpu,
+						vcpu->arch.mmu->root_hpa));
+	} else {
+		vpid_sync_context(vpid);
+	}
+}
+
+static inline void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
+{
+	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
+}
+
+static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
+{
+	vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
+	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+}
+
+static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
+{
+	return vmx->secondary_exec_control &
+		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+}
+
+void dump_vmcs(void);
+
+#endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/vmx_shadow_fields.h b/arch/x86/kvm/vmx_shadow_fields.h
deleted file mode 100644
index cd0c75f..0000000
--- a/arch/x86/kvm/vmx_shadow_fields.h
+++ /dev/null
@@ -1,77 +0,0 @@
-#ifndef SHADOW_FIELD_RO
-#define SHADOW_FIELD_RO(x)
-#endif
-#ifndef SHADOW_FIELD_RW
-#define SHADOW_FIELD_RW(x)
-#endif
-
-/*
- * We do NOT shadow fields that are modified when L0
- * traps and emulates any vmx instruction (e.g. VMPTRLD,
- * VMXON...) executed by L1.
- * For example, VM_INSTRUCTION_ERROR is read
- * by L1 if a vmx instruction fails (part of the error path).
- * Note the code assumes this logic. If for some reason
- * we start shadowing these fields then we need to
- * force a shadow sync when L0 emulates vmx instructions
- * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified
- * by nested_vmx_failValid)
- *
- * When adding or removing fields here, note that shadowed
- * fields must always be synced by prepare_vmcs02, not just
- * prepare_vmcs02_full.
- */
-
-/*
- * Keeping the fields ordered by size is an attempt at improving
- * branch prediction in vmcs_read_any and vmcs_write_any.
- */
-
-/* 16-bits */
-SHADOW_FIELD_RW(GUEST_CS_SELECTOR)
-SHADOW_FIELD_RW(GUEST_INTR_STATUS)
-SHADOW_FIELD_RW(GUEST_PML_INDEX)
-SHADOW_FIELD_RW(HOST_FS_SELECTOR)
-SHADOW_FIELD_RW(HOST_GS_SELECTOR)
-
-/* 32-bits */
-SHADOW_FIELD_RO(VM_EXIT_REASON)
-SHADOW_FIELD_RO(VM_EXIT_INTR_INFO)
-SHADOW_FIELD_RO(VM_EXIT_INSTRUCTION_LEN)
-SHADOW_FIELD_RO(IDT_VECTORING_INFO_FIELD)
-SHADOW_FIELD_RO(IDT_VECTORING_ERROR_CODE)
-SHADOW_FIELD_RO(VM_EXIT_INTR_ERROR_CODE)
-SHADOW_FIELD_RW(CPU_BASED_VM_EXEC_CONTROL)
-SHADOW_FIELD_RW(EXCEPTION_BITMAP)
-SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE)
-SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD)
-SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN)
-SHADOW_FIELD_RW(TPR_THRESHOLD)
-SHADOW_FIELD_RW(GUEST_CS_LIMIT)
-SHADOW_FIELD_RW(GUEST_CS_AR_BYTES)
-SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO)
-SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE)
-
-/* Natural width */
-SHADOW_FIELD_RO(EXIT_QUALIFICATION)
-SHADOW_FIELD_RO(GUEST_LINEAR_ADDRESS)
-SHADOW_FIELD_RW(GUEST_RIP)
-SHADOW_FIELD_RW(GUEST_RSP)
-SHADOW_FIELD_RW(GUEST_CR0)
-SHADOW_FIELD_RW(GUEST_CR3)
-SHADOW_FIELD_RW(GUEST_CR4)
-SHADOW_FIELD_RW(GUEST_RFLAGS)
-SHADOW_FIELD_RW(GUEST_CS_BASE)
-SHADOW_FIELD_RW(GUEST_ES_BASE)
-SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK)
-SHADOW_FIELD_RW(CR0_READ_SHADOW)
-SHADOW_FIELD_RW(CR4_READ_SHADOW)
-SHADOW_FIELD_RW(HOST_FS_BASE)
-SHADOW_FIELD_RW(HOST_GS_BASE)
-
-/* 64-bit */
-SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS)
-SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS_HIGH)
-
-#undef SHADOW_FIELD_RO
-#undef SHADOW_FIELD_RW
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 956eecd..5d53052 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Kernel-based Virtual Machine driver for Linux
  *
@@ -13,10 +14,6 @@
  *   Yaniv Kamay  <yaniv@qumranet.com>
  *   Amit Shah    <amit.shah@qumranet.com>
  *   Ben-Ami Yassour <benami@il.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
  */
 
 #include <linux/kvm_host.h>
@@ -54,6 +51,7 @@
 #include <linux/kvm_irqfd.h>
 #include <linux/irqbypass.h>
 #include <linux/sched/stat.h>
+#include <linux/sched/isolation.h>
 #include <linux/mem_encrypt.h>
 
 #include <trace/events/kvm.h>
@@ -69,6 +67,8 @@
 #include <asm/irq_remapping.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
+#include <asm/intel_pt.h>
+#include <clocksource/hyperv_timer.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -92,8 +92,8 @@
 static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
-#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
 #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
                                     KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
@@ -135,10 +135,14 @@
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
-/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 0;
-module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
-EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
+/*
+ * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
+ * adaptive tuning starting from default advancment of 1000ns.  '0' disables
+ * advancement entirely.  Any other value is used as-is and disables adaptive
+ * tuning, i.e. allows priveleged userspace to set an exact advancement time.
+ */
+static int __read_mostly lapic_timer_advance_ns = -1;
+module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR);
 
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
@@ -150,6 +154,9 @@
 static bool __read_mostly force_emulation_prefix = false;
 module_param(force_emulation_prefix, bool, S_IRUGO);
 
+int __read_mostly pi_inject_timer = -1;
+module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);
+
 #define KVM_NR_SHARED_MSRS 16
 
 struct kvm_shared_msrs_global {
@@ -205,7 +212,8 @@
 	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
-	{ "largepages", VM_STAT(lpages) },
+	{ "largepages", VM_STAT(lpages, .mode = 0444) },
+	{ "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) },
 	{ "max_mmu_page_hash_collisions",
 		VM_STAT(max_mmu_page_hash_collisions) },
 	{ NULL }
@@ -213,6 +221,9 @@
 
 u64 __read_mostly host_xcr0;
 
+struct kmem_cache *x86_fpu_cache;
+EXPORT_SYMBOL_GPL(x86_fpu_cache);
+
 static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt);
 
 static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
@@ -350,7 +361,7 @@
 asmlinkage __visible void kvm_spurious_fault(void)
 {
 	/* Fault while not rebooting.  We want the trace. */
-	BUG();
+	BUG_ON(!kvm_rebooting);
 }
 EXPORT_SYMBOL_GPL(kvm_spurious_fault);
 
@@ -400,9 +411,51 @@
 	return EXCPT_FAULT;
 }
 
+void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
+{
+	unsigned nr = vcpu->arch.exception.nr;
+	bool has_payload = vcpu->arch.exception.has_payload;
+	unsigned long payload = vcpu->arch.exception.payload;
+
+	if (!has_payload)
+		return;
+
+	switch (nr) {
+	case DB_VECTOR:
+		/*
+		 * "Certain debug exceptions may clear bit 0-3.  The
+		 * remaining contents of the DR6 register are never
+		 * cleared by the processor".
+		 */
+		vcpu->arch.dr6 &= ~DR_TRAP_BITS;
+		/*
+		 * DR6.RTM is set by all #DB exceptions that don't clear it.
+		 */
+		vcpu->arch.dr6 |= DR6_RTM;
+		vcpu->arch.dr6 |= payload;
+		/*
+		 * Bit 16 should be set in the payload whenever the #DB
+		 * exception should clear DR6.RTM. This makes the payload
+		 * compatible with the pending debug exceptions under VMX.
+		 * Though not currently documented in the SDM, this also
+		 * makes the payload compatible with the exit qualification
+		 * for #DB exceptions under VMX.
+		 */
+		vcpu->arch.dr6 ^= payload & DR6_RTM;
+		break;
+	case PF_VECTOR:
+		vcpu->arch.cr2 = payload;
+		break;
+	}
+
+	vcpu->arch.exception.has_payload = false;
+	vcpu->arch.exception.payload = 0;
+}
+EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload);
+
 static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		unsigned nr, bool has_error, u32 error_code,
-		bool reinject)
+	        bool has_payload, unsigned long payload, bool reinject)
 {
 	u32 prev_nr;
 	int class1, class2;
@@ -424,6 +477,14 @@
 			 */
 			WARN_ON_ONCE(vcpu->arch.exception.pending);
 			vcpu->arch.exception.injected = true;
+			if (WARN_ON_ONCE(has_payload)) {
+				/*
+				 * A reinjected event has already
+				 * delivered its payload.
+				 */
+				has_payload = false;
+				payload = 0;
+			}
 		} else {
 			vcpu->arch.exception.pending = true;
 			vcpu->arch.exception.injected = false;
@@ -431,6 +492,22 @@
 		vcpu->arch.exception.has_error_code = has_error;
 		vcpu->arch.exception.nr = nr;
 		vcpu->arch.exception.error_code = error_code;
+		vcpu->arch.exception.has_payload = has_payload;
+		vcpu->arch.exception.payload = payload;
+		/*
+		 * In guest mode, payload delivery should be deferred,
+		 * so that the L1 hypervisor can intercept #PF before
+		 * CR2 is modified (or intercept #DB before DR6 is
+		 * modified under nVMX).  However, for ABI
+		 * compatibility with KVM_GET_VCPU_EVENTS and
+		 * KVM_SET_VCPU_EVENTS, we can't delay payload
+		 * delivery unless userspace has enabled this
+		 * functionality via the per-VM capability,
+		 * KVM_CAP_EXCEPTION_PAYLOAD.
+		 */
+		if (!vcpu->kvm->arch.exception_payload_enabled ||
+		    !is_guest_mode(vcpu))
+			kvm_deliver_exception_payload(vcpu);
 		return;
 	}
 
@@ -455,6 +532,8 @@
 		vcpu->arch.exception.has_error_code = true;
 		vcpu->arch.exception.nr = DF_VECTOR;
 		vcpu->arch.exception.error_code = 0;
+		vcpu->arch.exception.has_payload = false;
+		vcpu->arch.exception.payload = 0;
 	} else
 		/* replace previous exception with a new one in a hope
 		   that instruction re-execution will regenerate lost
@@ -464,16 +543,29 @@
 
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 {
-	kvm_multiple_exception(vcpu, nr, false, 0, false);
+	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception);
 
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 {
-	kvm_multiple_exception(vcpu, nr, false, 0, true);
+	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true);
 }
 EXPORT_SYMBOL_GPL(kvm_requeue_exception);
 
+static void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
+				  unsigned long payload)
+{
+	kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false);
+}
+
+static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
+				    u32 error_code, unsigned long payload)
+{
+	kvm_multiple_exception(vcpu, nr, true, error_code,
+			       true, payload, false);
+}
+
 int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
 {
 	if (err)
@@ -490,11 +582,13 @@
 	++vcpu->stat.pf_guest;
 	vcpu->arch.exception.nested_apf =
 		is_guest_mode(vcpu) && fault->async_page_fault;
-	if (vcpu->arch.exception.nested_apf)
+	if (vcpu->arch.exception.nested_apf) {
 		vcpu->arch.apf.nested_apf_token = fault->address;
-	else
-		vcpu->arch.cr2 = fault->address;
-	kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
+		kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
+	} else {
+		kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code,
+					fault->address);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
 
@@ -503,7 +597,7 @@
 	if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
 		vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
 	else
-		vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+		vcpu->arch.mmu->inject_page_fault(vcpu, fault);
 
 	return fault->nested_page_fault;
 }
@@ -517,13 +611,13 @@
 
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
 {
-	kvm_multiple_exception(vcpu, nr, true, error_code, false);
+	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
 
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
 {
-	kvm_multiple_exception(vcpu, nr, true, error_code, true);
+	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true);
 }
 EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
 
@@ -581,8 +675,14 @@
 				       data, offset, len, access);
 }
 
+static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu)
+{
+	return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) |
+	       rsvd_bits(1, 2);
+}
+
 /*
- * Load the pae pdptrs.  Return true is they are all valid.
+ * Load the pae pdptrs.  Return 1 if they are all valid, 0 otherwise.
  */
 int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 {
@@ -601,8 +701,7 @@
 	}
 	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
 		if ((pdpte[i] & PT_PRESENT_MASK) &&
-		    (pdpte[i] &
-		     vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
+		    (pdpte[i] & pdptr_rsvd_bits(vcpu))) {
 			ret = 0;
 			goto out;
 		}
@@ -628,7 +727,7 @@
 	gfn_t gfn;
 	int r;
 
-	if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
+	if (!is_pae_paging(vcpu))
 		return false;
 
 	if (!test_bit(VCPU_EXREG_PDPTR,
@@ -713,7 +812,7 @@
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
 {
 	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
 			!vcpu->guest_xcr0_loaded) {
@@ -723,8 +822,9 @@
 		vcpu->guest_xcr0_loaded = 1;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
 
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->guest_xcr0_loaded) {
 		if (vcpu->arch.xcr0 != host_xcr0)
@@ -732,6 +832,7 @@
 		vcpu->guest_xcr0_loaded = 0;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
 
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
@@ -784,34 +885,42 @@
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
+static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	if (cr4 & CR4_RESERVED_BITS)
+		return -EINVAL;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
+		return -EINVAL;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
+		return -EINVAL;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
+		return -EINVAL;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
+		return -EINVAL;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
+		return -EINVAL;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
+		return -EINVAL;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+		return -EINVAL;
+
+	return 0;
+}
+
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
 				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
 
-	if (cr4 & CR4_RESERVED_BITS)
-		return 1;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
-		return 1;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
-		return 1;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
-		return 1;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
-		return 1;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
-		return 1;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
-		return 1;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
 
 	if (is_long_mode(vcpu)) {
@@ -869,8 +978,8 @@
 	if (is_long_mode(vcpu) &&
 	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
 		return 1;
-	else if (is_pae(vcpu) && is_paging(vcpu) &&
-		   !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
+	else if (is_pae_paging(vcpu) &&
+		 !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
 		return 1;
 
 	kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush);
@@ -1007,15 +1116,15 @@
 
 bool kvm_rdpmc(struct kvm_vcpu *vcpu)
 {
-	u32 ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
+	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data;
 	int err;
 
 	err = kvm_pmu_rdpmc(vcpu, ecx, &data);
 	if (err)
 		return err;
-	kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, data >> 32);
+	kvm_rax_write(vcpu, (u32)data);
+	kvm_rdx_write(vcpu, data >> 32);
 	return err;
 }
 EXPORT_SYMBOL_GPL(kvm_rdpmc);
@@ -1024,13 +1133,15 @@
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
  *
- * This list is modified at module load time to reflect the
+ * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
+ * extract the supported MSRs from the related const lists.
+ * msrs_to_save is selected from the msrs_to_save_all to reflect the
  * capabilities of the host cpu. This capabilities test skips MSRs that are
- * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
+ * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
  * may depend on host virtualization features rather than host cpu features.
  */
 
-static u32 msrs_to_save[] = {
+static const u32 msrs_to_save_all[] = {
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64
@@ -1038,12 +1149,43 @@
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
-	MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES
+	MSR_IA32_SPEC_CTRL,
+	MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH,
+	MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK,
+	MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B,
+	MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B,
+	MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B,
+	MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B,
+	MSR_IA32_UMWAIT_CONTROL,
+
+	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
+	MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3,
+	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
+	MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
+	MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
+	MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3,
+	MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5,
+	MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7,
+	MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9,
+	MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11,
+	MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13,
+	MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15,
+	MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17,
+	MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
+	MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+	MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
+	MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7,
+	MSR_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9,
+	MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11,
+	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
+	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
+	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
 };
 
+static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
 static unsigned num_msrs_to_save;
 
-static u32 emulated_msrs[] = {
+static const u32 emulated_msrs_all[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
@@ -1065,6 +1207,7 @@
 
 	MSR_IA32_TSC_ADJUST,
 	MSR_IA32_TSCDEADLINE,
+	MSR_IA32_ARCH_CAPABILITIES,
 	MSR_IA32_MISC_ENABLE,
 	MSR_IA32_MCG_STATUS,
 	MSR_IA32_MCG_CTL,
@@ -1074,15 +1217,40 @@
 	MSR_PLATFORM_INFO,
 	MSR_MISC_FEATURES_ENABLES,
 	MSR_AMD64_VIRT_SPEC_CTRL,
+	MSR_IA32_POWER_CTL,
+
+	/*
+	 * The following list leaves out MSRs whose values are determined
+	 * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
+	 * We always support the "true" VMX control MSRs, even if the host
+	 * processor does not, so I am putting these registers here rather
+	 * than in msrs_to_save_all.
+	 */
+	MSR_IA32_VMX_BASIC,
+	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
+	MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
+	MSR_IA32_VMX_TRUE_EXIT_CTLS,
+	MSR_IA32_VMX_TRUE_ENTRY_CTLS,
+	MSR_IA32_VMX_MISC,
+	MSR_IA32_VMX_CR0_FIXED0,
+	MSR_IA32_VMX_CR4_FIXED0,
+	MSR_IA32_VMX_VMCS_ENUM,
+	MSR_IA32_VMX_PROCBASED_CTLS2,
+	MSR_IA32_VMX_EPT_VPID_CAP,
+	MSR_IA32_VMX_VMFUNC,
+
+	MSR_K7_HWCR,
+	MSR_KVM_POLL_CONTROL,
 };
 
+static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
 static unsigned num_emulated_msrs;
 
 /*
  * List of msr numbers which are used to expose MSR-based features that
  * can be used by a hypervisor to validate requested CPU features.
  */
-static u32 msr_based_features[] = {
+static const u32 msr_based_features_all[] = {
 	MSR_IA32_VMX_BASIC,
 	MSR_IA32_VMX_TRUE_PINBASED_CTLS,
 	MSR_IA32_VMX_PINBASED_CTLS,
@@ -1107,13 +1275,23 @@
 	MSR_IA32_ARCH_CAPABILITIES,
 };
 
+static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
 static unsigned int num_msr_based_features;
 
-u64 kvm_get_arch_capabilities(void)
+static u64 kvm_get_arch_capabilities(void)
 {
-	u64 data;
+	u64 data = 0;
 
-	rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
+
+	/*
+	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
+	 * the nested hypervisor runs with NX huge pages.  If it is not,
+	 * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
+	 * L1 guests, so it need not worry about its own (L2) guests.
+	 */
+	data |= ARCH_CAP_PSCHANGE_MC_NO;
 
 	/*
 	 * If we're doing cache flushes (either "always" or "cond")
@@ -1127,9 +1305,34 @@
 	if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
 		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
 
+	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		data |= ARCH_CAP_RDCL_NO;
+	if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+		data |= ARCH_CAP_SSB_NO;
+	if (!boot_cpu_has_bug(X86_BUG_MDS))
+		data |= ARCH_CAP_MDS_NO;
+
+	/*
+	 * On TAA affected systems, export MDS_NO=0 when:
+	 *	- TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
+	 *	- Updated microcode is present. This is detected by
+	 *	  the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
+	 *	  that VERW clears CPU buffers.
+	 *
+	 * When MDS_NO=0 is exported, guests deploy clear CPU buffer
+	 * mitigation and don't complain:
+	 *
+	 *	"Vulnerable: Clear CPU buffers attempted, no microcode"
+	 *
+	 * If TSX is disabled on the system, guests are also mitigated against
+	 * TAA and clear CPU buffer mitigation is not required for guests.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
+	    (data & ARCH_CAP_TSX_CTRL_MSR))
+		data &= ~ARCH_CAP_MDS_NO;
+
 	return data;
 }
-EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
 
 static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 {
@@ -1162,31 +1365,49 @@
 	return 0;
 }
 
+static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
+		return false;
+
+	if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+		return false;
+
+	if (efer & (EFER_LME | EFER_LMA) &&
+	    !guest_cpuid_has(vcpu, X86_FEATURE_LM))
+		return false;
+
+	if (efer & EFER_NX && !guest_cpuid_has(vcpu, X86_FEATURE_NX))
+		return false;
+
+	return true;
+
+}
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & efer_reserved_bits)
 		return false;
 
-	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
-			return false;
-
-	if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
-			return false;
-
-	return true;
+	return __kvm_valid_efer(vcpu, efer);
 }
 EXPORT_SYMBOL_GPL(kvm_valid_efer);
 
-static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	u64 old_efer = vcpu->arch.efer;
+	u64 efer = msr_info->data;
 
-	if (!kvm_valid_efer(vcpu, efer))
+	if (efer & efer_reserved_bits)
 		return 1;
 
-	if (is_paging(vcpu)
-	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
-		return 1;
+	if (!msr_info->host_initiated) {
+		if (!__kvm_valid_efer(vcpu, efer))
+			return 1;
+
+		if (is_paging(vcpu) &&
+		    (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+			return 1;
+	}
 
 	efer &= ~EFER_LMA;
 	efer |= vcpu->arch.efer & EFER_LMA;
@@ -1207,19 +1428,23 @@
 EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
 
 /*
- * Writes msr value into into the appropriate "register".
+ * Write @data into the MSR specified by @index.  Select MSR specific fault
+ * checks are bypassed if @host_initiated is %true.
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
-int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
+			 bool host_initiated)
 {
-	switch (msr->index) {
+	struct msr_data msr;
+
+	switch (index) {
 	case MSR_FS_BASE:
 	case MSR_GS_BASE:
 	case MSR_KERNEL_GS_BASE:
 	case MSR_CSTAR:
 	case MSR_LSTAR:
-		if (is_noncanonical_address(msr->data, vcpu))
+		if (is_noncanonical_address(data, vcpu))
 			return 1;
 		break;
 	case MSR_IA32_SYSENTER_EIP:
@@ -1236,38 +1461,95 @@
 		 * value, and that something deterministic happens if the guest
 		 * invokes 64-bit SYSENTER.
 		 */
-		msr->data = get_canonical(msr->data, vcpu_virt_addr_bits(vcpu));
+		data = get_canonical(data, vcpu_virt_addr_bits(vcpu));
 	}
-	return kvm_x86_ops->set_msr(vcpu, msr);
+
+	msr.data = data;
+	msr.index = index;
+	msr.host_initiated = host_initiated;
+
+	return kvm_x86_ops->set_msr(vcpu, &msr);
+}
+
+/*
+ * Read the MSR specified by @index into @data.  Select MSR specific fault
+ * checks are bypassed if @host_initiated is %true.
+ * Returns 0 on success, non-0 otherwise.
+ * Assumes vcpu_load() was already called.
+ */
+static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
+			 bool host_initiated)
+{
+	struct msr_data msr;
+	int ret;
+
+	msr.index = index;
+	msr.host_initiated = host_initiated;
+
+	ret = kvm_x86_ops->get_msr(vcpu, &msr);
+	if (!ret)
+		*data = msr.data;
+	return ret;
+}
+
+int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
+{
+	return __kvm_get_msr(vcpu, index, data, false);
+}
+EXPORT_SYMBOL_GPL(kvm_get_msr);
+
+int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
+{
+	return __kvm_set_msr(vcpu, index, data, false);
 }
 EXPORT_SYMBOL_GPL(kvm_set_msr);
 
+int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
+{
+	u32 ecx = kvm_rcx_read(vcpu);
+	u64 data;
+
+	if (kvm_get_msr(vcpu, ecx, &data)) {
+		trace_kvm_msr_read_ex(ecx);
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	trace_kvm_msr_read(ecx, data);
+
+	kvm_rax_write(vcpu, data & -1u);
+	kvm_rdx_write(vcpu, (data >> 32) & -1u);
+	return kvm_skip_emulated_instruction(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr);
+
+int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
+{
+	u32 ecx = kvm_rcx_read(vcpu);
+	u64 data = kvm_read_edx_eax(vcpu);
+
+	if (kvm_set_msr(vcpu, ecx, data)) {
+		trace_kvm_msr_write_ex(ecx, data);
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	trace_kvm_msr_write(ecx, data);
+	return kvm_skip_emulated_instruction(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
+
 /*
  * Adapt set_msr() to msr_io()'s calling convention
  */
 static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 {
-	struct msr_data msr;
-	int r;
-
-	msr.index = index;
-	msr.host_initiated = true;
-	r = kvm_get_msr(vcpu, &msr);
-	if (r)
-		return r;
-
-	*data = msr.data;
-	return 0;
+	return __kvm_get_msr(vcpu, index, data, true);
 }
 
 static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 {
-	struct msr_data msr;
-
-	msr.data = *data;
-	msr.index = index;
-	msr.host_initiated = true;
-	return kvm_set_msr(vcpu, &msr);
+	return __kvm_set_msr(vcpu, index, *data, true);
 }
 
 #ifdef CONFIG_X86_64
@@ -1316,12 +1598,8 @@
 
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * Note: KVM_REQ_PENDING_TIMER is implicitly checked in
-	 * vcpu_enter_guest.  This function is only called from
-	 * the physical CPU that is running vcpu.
-	 */
 	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	kvm_vcpu_kick(vcpu);
 }
 
 static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
@@ -1400,9 +1678,6 @@
 
 	*pshift = shift;
 	*pmultiplier = div_frac(scaled64, tps32);
-
-	pr_debug("%s: base_hz %llu => %llu, shift %d, mul %u\n",
-		 __func__, base_hz, scaled_hz, shift, *pmultiplier);
 }
 
 #ifdef CONFIG_X86_64
@@ -1436,7 +1711,7 @@
 			vcpu->arch.tsc_always_catchup = 1;
 			return 0;
 		} else {
-			WARN(1, "user requested TSC rate below hardware speed\n");
+			pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
 			return -1;
 		}
 	}
@@ -1446,8 +1721,8 @@
 				user_tsc_khz, tsc_khz);
 
 	if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
-		WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
-			  user_tsc_khz);
+		pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
+			            user_tsc_khz);
 		return -1;
 	}
 
@@ -1610,7 +1885,7 @@
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
 	offset = kvm_compute_tsc_offset(vcpu, data);
-	ns = ktime_get_boot_ns();
+	ns = ktime_get_boottime_ns();
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
@@ -1645,12 +1920,10 @@
 	    vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
 		if (!kvm_check_tsc_unstable()) {
 			offset = kvm->arch.cur_tsc_offset;
-			pr_debug("kvm: matched tsc offset for %llu\n", data);
 		} else {
 			u64 delta = nsec_to_cycles(vcpu, elapsed);
 			data += delta;
 			offset = kvm_compute_tsc_offset(vcpu, data);
-			pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
 		}
 		matched = true;
 		already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation);
@@ -1669,8 +1942,6 @@
 		kvm->arch.cur_tsc_write = data;
 		kvm->arch.cur_tsc_offset = offset;
 		matched = false;
-		pr_debug("kvm: new tsc generation %llu, clock %llu\n",
-			 kvm->arch.cur_tsc_generation, data);
 	}
 
 	/*
@@ -1952,7 +2223,7 @@
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	if (!ka->use_master_clock) {
 		spin_unlock(&ka->pvclock_gtod_sync_lock);
-		return ktime_get_boot_ns() + ka->kvmclock_offset;
+		return ktime_get_boottime_ns() + ka->kvmclock_offset;
 	}
 
 	hv_clock.tsc_timestamp = ka->master_cycle_now;
@@ -1968,7 +2239,7 @@
 				   &hv_clock.tsc_to_system_mul);
 		ret = __pvclock_read_cycles(&hv_clock, rdtsc());
 	} else
-		ret = ktime_get_boot_ns() + ka->kvmclock_offset;
+		ret = ktime_get_boottime_ns() + ka->kvmclock_offset;
 
 	put_cpu();
 
@@ -2067,7 +2338,7 @@
 	}
 	if (!use_master_clock) {
 		host_tsc = rdtsc();
-		kernel_ns = ktime_get_boot_ns();
+		kernel_ns = ktime_get_boottime_ns();
 	}
 
 	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
@@ -2179,6 +2450,18 @@
 					KVMCLOCK_SYNC_PERIOD);
 }
 
+/*
+ * On AMD, HWCR[McStatusWrEn] controls whether setting MCi_STATUS results in #GP.
+ */
+static bool can_set_mci_status(struct kvm_vcpu *vcpu)
+{
+	/* McStatusWrEn enabled? */
+	if (guest_cpuid_is_amd(vcpu))
+		return !!(vcpu->arch.msr_hwcr & BIT_ULL(18));
+
+	return false;
+}
+
 static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	u64 mcg_cap = vcpu->arch.mcg_cap;
@@ -2210,9 +2493,14 @@
 			if ((offset & 0x3) == 0 &&
 			    data != 0 && (data | (1 << 10)) != ~(u64)0)
 				return -1;
+
+			/* MCi_STATUS */
 			if (!msr_info->host_initiated &&
-				(offset & 0x3) == 1 && data != 0)
-				return -1;
+			    (offset & 0x3) == 1 && data != 0) {
+				if (!can_set_mci_status(vcpu))
+					return -1;
+			}
+
 			vcpu->arch.mce_banks[offset] = data;
 			break;
 		}
@@ -2281,6 +2569,7 @@
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pv_time_enabled = false;
+	vcpu->arch.time = 0;
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
@@ -2302,6 +2591,8 @@
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
+	trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
+		vcpu->arch.st.steal.preempted & KVM_VCPU_FLUSH_TLB);
 	if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB)
 		kvm_vcpu_flush_tlb(vcpu, false);
 
@@ -2350,14 +2641,22 @@
 		if (msr_info->host_initiated)
 			vcpu->arch.microcode_version = data;
 		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated)
+			return 1;
+		vcpu->arch.arch_capabilities = data;
+		break;
 	case MSR_EFER:
-		return set_efer(vcpu, data);
+		return set_efer(vcpu, msr_info);
 	case MSR_K7_HWCR:
 		data &= ~(u64)0x40;	/* ignore flush filter disable */
 		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
 		data &= ~(u64)0x8;	/* ignore TLB cache disable */
-		data &= ~(u64)0x40000;  /* ignore Mc status write enable */
-		if (data != 0) {
+
+		/* Handle McStatusWrEn */
+		if (data == BIT_ULL(18)) {
+			vcpu->arch.msr_hwcr = data;
+		} else if (data != 0) {
 			vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
 				    data);
 			return 1;
@@ -2401,13 +2700,24 @@
 		}
 		break;
 	case MSR_IA32_MISC_ENABLE:
-		vcpu->arch.ia32_misc_enable_msr = data;
+		if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) &&
+		    ((vcpu->arch.ia32_misc_enable_msr ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) {
+			if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3))
+				return 1;
+			vcpu->arch.ia32_misc_enable_msr = data;
+			kvm_update_cpuid(vcpu);
+		} else {
+			vcpu->arch.ia32_misc_enable_msr = data;
+		}
 		break;
 	case MSR_IA32_SMBASE:
 		if (!msr_info->host_initiated)
 			return 1;
 		vcpu->arch.smbase = data;
 		break;
+	case MSR_IA32_POWER_CTL:
+		vcpu->arch.msr_ia32_power_ctl = data;
+		break;
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
@@ -2425,8 +2735,6 @@
 	case MSR_KVM_SYSTEM_TIME: {
 		struct kvm_arch *ka = &vcpu->kvm->arch;
 
-		kvmclock_reset(vcpu);
-
 		if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) {
 			bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
 
@@ -2440,14 +2748,13 @@
 		kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
 		/* we verify if the enable bit is set... */
+		vcpu->arch.pv_time_enabled = false;
 		if (!(data & 1))
 			break;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
-			vcpu->arch.pv_time_enabled = false;
-		else
 			vcpu->arch.pv_time_enabled = true;
 
 		break;
@@ -2478,10 +2785,18 @@
 
 		break;
 	case MSR_KVM_PV_EOI_EN:
-		if (kvm_lapic_enable_pv_eoi(vcpu, data))
+		if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8)))
 			return 1;
 		break;
 
+	case MSR_KVM_POLL_CONTROL:
+		/* only enable bit supported */
+		if (data & (-1ULL << 1))
+			return 1;
+
+		vcpu->arch.msr_kvm_poll_control = data;
+		break;
+
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
@@ -2571,18 +2886,6 @@
 }
 EXPORT_SYMBOL_GPL(kvm_set_msr_common);
 
-
-/*
- * Reads an msr value (of 'msr_index') into 'pdata'.
- * Returns 0 on success, non-0 otherwise.
- * Assumes vcpu_load() was already called.
- */
-int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
-{
-	return kvm_x86_ops->get_msr(vcpu, msr);
-}
-EXPORT_SYMBOL_GPL(kvm_get_msr);
-
 static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
 {
 	u64 data;
@@ -2631,7 +2934,6 @@
 	case MSR_K8_SYSCFG:
 	case MSR_K8_TSEG_ADDR:
 	case MSR_K8_TSEG_MASK:
-	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_K8_INT_PENDING_MSG:
 	case MSR_AMD64_NB_CFG:
@@ -2654,6 +2956,15 @@
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = vcpu->arch.microcode_version;
 		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
+			return 1;
+		msr_info->data = vcpu->arch.arch_capabilities;
+		break;
+	case MSR_IA32_POWER_CTL:
+		msr_info->data = vcpu->arch.msr_ia32_power_ctl;
+		break;
 	case MSR_IA32_TSC:
 		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
 		break;
@@ -2726,6 +3037,9 @@
 	case MSR_KVM_PV_EOI_EN:
 		msr_info->data = vcpu->arch.pv_eoi.msr_val;
 		break;
+	case MSR_KVM_POLL_CONTROL:
+		msr_info->data = vcpu->arch.msr_kvm_poll_control;
+		break;
 	case MSR_IA32_P5_MC_ADDR:
 	case MSR_IA32_P5_MC_TYPE:
 	case MSR_IA32_MCG_CAP:
@@ -2789,6 +3103,9 @@
 	case MSR_MISC_FEATURES_ENABLES:
 		msr_info->data = vcpu->arch.msr_misc_features_enables;
 		break;
+	case MSR_K7_HWCR:
+		msr_info->data = vcpu->arch.msr_hwcr;
+		break;
 	default:
 		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
 			return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -2843,7 +3160,7 @@
 	unsigned size;
 
 	r = -EFAULT;
-	if (copy_from_user(&msrs, user_msrs, sizeof msrs))
+	if (copy_from_user(&msrs, user_msrs, sizeof(msrs)))
 		goto out;
 
 	r = -E2BIG;
@@ -2914,6 +3231,8 @@
 	case KVM_CAP_HYPERV_VP_INDEX:
 	case KVM_CAP_HYPERV_EVENTFD:
 	case KVM_CAP_HYPERV_TLBFLUSH:
+	case KVM_CAP_HYPERV_SEND_IPI:
+	case KVM_CAP_HYPERV_CPUID:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -2925,13 +3244,14 @@
 	case KVM_CAP_HYPERV_TIME:
 	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 	case KVM_CAP_TSC_DEADLINE_TIMER:
-	case KVM_CAP_ENABLE_CAP_VM:
 	case KVM_CAP_DISABLE_QUIRKS:
 	case KVM_CAP_SET_BOOT_CPU_ID:
  	case KVM_CAP_SPLIT_IRQCHIP:
 	case KVM_CAP_IMMEDIATE_EXIT:
+	case KVM_CAP_PMU_EVENT_FILTER:
 	case KVM_CAP_GET_MSR_FEATURES:
 	case KVM_CAP_MSR_PLATFORM_INFO:
+	case KVM_CAP_EXCEPTION_PAYLOAD:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -2941,7 +3261,8 @@
 		r = KVM_CLOCK_TSC_STABLE;
 		break;
 	case KVM_CAP_X86_DISABLE_EXITS:
-		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE;
+		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
+		      KVM_X86_DISABLE_EXITS_CSTATE;
 		if(kvm_can_mwait_in_guest())
 			r |= KVM_X86_DISABLE_EXITS_MWAIT;
 		break;
@@ -2965,8 +3286,8 @@
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
-	case KVM_CAP_NR_MEMSLOTS:
-		r = KVM_USER_MEM_SLOTS;
+	case KVM_CAP_MAX_VCPU_ID:
+		r = KVM_MAX_VCPU_ID;
 		break;
 	case KVM_CAP_PV_MMU:	/* obsolete */
 		r = 0;
@@ -2985,7 +3306,13 @@
 		break;
 	case KVM_CAP_NESTED_STATE:
 		r = kvm_x86_ops->get_nested_state ?
-			kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+			kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
+		break;
+	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
+		r = kvm_x86_ops->enable_direct_tlbflush != NULL;
+		break;
+	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
+		r = kvm_x86_ops->nested_enable_evmcs != NULL;
 		break;
 	default:
 		break;
@@ -3007,11 +3334,11 @@
 		unsigned n;
 
 		r = -EFAULT;
-		if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
+		if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list)))
 			goto out;
 		n = msr_list.nmsrs;
 		msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs;
-		if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
+		if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list)))
 			goto out;
 		r = -E2BIG;
 		if (n < msr_list.nmsrs)
@@ -3033,7 +3360,7 @@
 		struct kvm_cpuid2 cpuid;
 
 		r = -EFAULT;
-		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
+		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
 
 		r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
@@ -3042,7 +3369,7 @@
 			goto out;
 
 		r = -EFAULT;
-		if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
+		if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
 			goto out;
 		r = 0;
 		break;
@@ -3110,6 +3437,10 @@
 
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
 
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
@@ -3306,8 +3637,7 @@
 	for (bank = 0; bank < bank_num; bank++)
 		vcpu->arch.mce_banks[bank*4] = ~(u64)0;
 
-	if (kvm_x86_ops->setup_mce)
-		kvm_x86_ops->setup_mce(vcpu);
+	kvm_x86_ops->setup_mce(vcpu);
 out:
 	return r;
 }
@@ -3364,19 +3694,33 @@
 					       struct kvm_vcpu_events *events)
 {
 	process_nmi(vcpu);
+
 	/*
-	 * FIXME: pass injected and pending separately.  This is only
-	 * needed for nested virtualization, whose state cannot be
-	 * migrated yet.  For now we can combine them.
+	 * The API doesn't provide the instruction length for software
+	 * exceptions, so don't report them. As long as the guest RIP
+	 * isn't advanced, we should expect to encounter the exception
+	 * again.
 	 */
-	events->exception.injected =
-		(vcpu->arch.exception.pending ||
-		 vcpu->arch.exception.injected) &&
-		!kvm_exception_is_soft(vcpu->arch.exception.nr);
+	if (kvm_exception_is_soft(vcpu->arch.exception.nr)) {
+		events->exception.injected = 0;
+		events->exception.pending = 0;
+	} else {
+		events->exception.injected = vcpu->arch.exception.injected;
+		events->exception.pending = vcpu->arch.exception.pending;
+		/*
+		 * For ABI compatibility, deliberately conflate
+		 * pending and injected exceptions when
+		 * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled.
+		 */
+		if (!vcpu->kvm->arch.exception_payload_enabled)
+			events->exception.injected |=
+				vcpu->arch.exception.pending;
+	}
 	events->exception.nr = vcpu->arch.exception.nr;
 	events->exception.has_error_code = vcpu->arch.exception.has_error_code;
-	events->exception.pad = 0;
 	events->exception.error_code = vcpu->arch.exception.error_code;
+	events->exception_has_payload = vcpu->arch.exception.has_payload;
+	events->exception_payload = vcpu->arch.exception.payload;
 
 	events->interrupt.injected =
 		vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
@@ -3400,10 +3744,13 @@
 	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
 			 | KVM_VCPUEVENT_VALID_SHADOW
 			 | KVM_VCPUEVENT_VALID_SMM);
+	if (vcpu->kvm->arch.exception_payload_enabled)
+		events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
+
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
 
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
@@ -3411,12 +3758,24 @@
 	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
 			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
 			      | KVM_VCPUEVENT_VALID_SHADOW
-			      | KVM_VCPUEVENT_VALID_SMM))
+			      | KVM_VCPUEVENT_VALID_SMM
+			      | KVM_VCPUEVENT_VALID_PAYLOAD))
 		return -EINVAL;
 
-	if (events->exception.injected &&
-	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR ||
-	     is_guest_mode(vcpu)))
+	if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) {
+		if (!vcpu->kvm->arch.exception_payload_enabled)
+			return -EINVAL;
+		if (events->exception.pending)
+			events->exception.injected = 0;
+		else
+			events->exception_has_payload = 0;
+	} else {
+		events->exception.pending = 0;
+		events->exception_has_payload = 0;
+	}
+
+	if ((events->exception.injected || events->exception.pending) &&
+	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
 		return -EINVAL;
 
 	/* INITs are latched while in SMM */
@@ -3426,11 +3785,13 @@
 		return -EINVAL;
 
 	process_nmi(vcpu);
-	vcpu->arch.exception.injected = false;
-	vcpu->arch.exception.pending = events->exception.injected;
+	vcpu->arch.exception.injected = events->exception.injected;
+	vcpu->arch.exception.pending = events->exception.pending;
 	vcpu->arch.exception.nr = events->exception.nr;
 	vcpu->arch.exception.has_error_code = events->exception.has_error_code;
 	vcpu->arch.exception.error_code = events->exception.error_code;
+	vcpu->arch.exception.has_payload = events->exception_has_payload;
+	vcpu->arch.exception.payload = events->exception_payload;
 
 	vcpu->arch.interrupt.injected = events->interrupt.injected;
 	vcpu->arch.interrupt.nr = events->interrupt.nr;
@@ -3449,12 +3810,13 @@
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
-		u32 hflags = vcpu->arch.hflags;
-		if (events->smi.smm)
-			hflags |= HF_SMM_MASK;
-		else
-			hflags &= ~HF_SMM_MASK;
-		kvm_set_hflags(vcpu, hflags);
+		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+			if (events->smi.smm)
+				vcpu->arch.hflags |= HF_SMM_MASK;
+			else
+				vcpu->arch.hflags &= ~HF_SMM_MASK;
+			kvm_smm_changed(vcpu);
+		}
 
 		vcpu->arch.smi_pending = events->smi.pending;
 
@@ -3515,7 +3877,7 @@
 
 static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 {
-	struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
+	struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave;
 	u64 xstate_bv = xsave->header.xfeatures;
 	u64 valid;
 
@@ -3535,15 +3897,15 @@
 	 */
 	valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
 	while (valid) {
-		u64 feature = valid & -valid;
-		int index = fls64(feature) - 1;
-		void *src = get_xsave_addr(xsave, feature);
+		u64 xfeature_mask = valid & -valid;
+		int xfeature_nr = fls64(xfeature_mask) - 1;
+		void *src = get_xsave_addr(xsave, xfeature_nr);
 
 		if (src) {
 			u32 size, offset, ecx, edx;
-			cpuid_count(XSTATE_CPUID, index,
+			cpuid_count(XSTATE_CPUID, xfeature_nr,
 				    &size, &offset, &ecx, &edx);
-			if (feature == XFEATURE_MASK_PKRU)
+			if (xfeature_nr == XFEATURE_PKRU)
 				memcpy(dest + offset, &vcpu->arch.pkru,
 				       sizeof(vcpu->arch.pkru));
 			else
@@ -3551,13 +3913,13 @@
 
 		}
 
-		valid -= feature;
+		valid -= xfeature_mask;
 	}
 }
 
 static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 {
-	struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
+	struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave;
 	u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
 	u64 valid;
 
@@ -3578,22 +3940,22 @@
 	 */
 	valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
 	while (valid) {
-		u64 feature = valid & -valid;
-		int index = fls64(feature) - 1;
-		void *dest = get_xsave_addr(xsave, feature);
+		u64 xfeature_mask = valid & -valid;
+		int xfeature_nr = fls64(xfeature_mask) - 1;
+		void *dest = get_xsave_addr(xsave, xfeature_nr);
 
 		if (dest) {
 			u32 size, offset, ecx, edx;
-			cpuid_count(XSTATE_CPUID, index,
+			cpuid_count(XSTATE_CPUID, xfeature_nr,
 				    &size, &offset, &ecx, &edx);
-			if (feature == XFEATURE_MASK_PKRU)
+			if (xfeature_nr == XFEATURE_PKRU)
 				memcpy(&vcpu->arch.pkru, src + offset,
 				       sizeof(vcpu->arch.pkru));
 			else
 				memcpy(dest, src + offset, size);
 		}
 
-		valid -= feature;
+		valid -= xfeature_mask;
 	}
 }
 
@@ -3605,7 +3967,7 @@
 		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
 		memcpy(guest_xsave->region,
-			&vcpu->arch.guest_fpu.state.fxsave,
+			&vcpu->arch.guest_fpu->state.fxsave,
 			sizeof(struct fxregs_state));
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
 			XFEATURE_MASK_FPSSE;
@@ -3635,7 +3997,7 @@
 		if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
 			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
-		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
+		memcpy(&vcpu->arch.guest_fpu->state.fxsave,
 			guest_xsave->region, sizeof(struct fxregs_state));
 	}
 	return 0;
@@ -3696,6 +4058,10 @@
 static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 				     struct kvm_enable_cap *cap)
 {
+	int r;
+	uint16_t vmcs_version;
+	void __user *user_ptr;
+
 	if (cap->flags)
 		return -EINVAL;
 
@@ -3703,11 +4069,30 @@
 	case KVM_CAP_HYPERV_SYNIC2:
 		if (cap->args[0])
 			return -EINVAL;
+		/* fall through */
+
 	case KVM_CAP_HYPERV_SYNIC:
 		if (!irqchip_in_kernel(vcpu->kvm))
 			return -EINVAL;
 		return kvm_hv_activate_synic(vcpu, cap->cap ==
 					     KVM_CAP_HYPERV_SYNIC2);
+	case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
+		if (!kvm_x86_ops->nested_enable_evmcs)
+			return -ENOTTY;
+		r = kvm_x86_ops->nested_enable_evmcs(vcpu, &vmcs_version);
+		if (!r) {
+			user_ptr = (void __user *)(uintptr_t)cap->args[0];
+			if (copy_to_user(user_ptr, &vmcs_version,
+					 sizeof(vmcs_version)))
+				r = -EFAULT;
+		}
+		return r;
+	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
+		if (!kvm_x86_ops->enable_direct_tlbflush)
+			return -ENOTTY;
+
+		return kvm_x86_ops->enable_direct_tlbflush(vcpu);
+
 	default:
 		return -EINVAL;
 	}
@@ -3734,7 +4119,8 @@
 		r = -EINVAL;
 		if (!lapic_in_kernel(vcpu))
 			goto out;
-		u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
+		u.lapic = kzalloc(sizeof(struct kvm_lapic_state),
+				GFP_KERNEL_ACCOUNT);
 
 		r = -ENOMEM;
 		if (!u.lapic)
@@ -3765,7 +4151,7 @@
 		struct kvm_interrupt irq;
 
 		r = -EFAULT;
-		if (copy_from_user(&irq, argp, sizeof irq))
+		if (copy_from_user(&irq, argp, sizeof(irq)))
 			goto out;
 		r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
 		break;
@@ -3783,7 +4169,7 @@
 		struct kvm_cpuid cpuid;
 
 		r = -EFAULT;
-		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
+		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
 		r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries);
 		break;
@@ -3793,7 +4179,7 @@
 		struct kvm_cpuid2 cpuid;
 
 		r = -EFAULT;
-		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
+		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
 		r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid,
 					      cpuid_arg->entries);
@@ -3804,14 +4190,14 @@
 		struct kvm_cpuid2 cpuid;
 
 		r = -EFAULT;
-		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
+		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
 		r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid,
 					      cpuid_arg->entries);
 		if (r)
 			goto out;
 		r = -EFAULT;
-		if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
+		if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
 			goto out;
 		r = 0;
 		break;
@@ -3832,13 +4218,13 @@
 		struct kvm_tpr_access_ctl tac;
 
 		r = -EFAULT;
-		if (copy_from_user(&tac, argp, sizeof tac))
+		if (copy_from_user(&tac, argp, sizeof(tac)))
 			goto out;
 		r = vcpu_ioctl_tpr_access_reporting(vcpu, &tac);
 		if (r)
 			goto out;
 		r = -EFAULT;
-		if (copy_to_user(argp, &tac, sizeof tac))
+		if (copy_to_user(argp, &tac, sizeof(tac)))
 			goto out;
 		r = 0;
 		break;
@@ -3851,7 +4237,7 @@
 		if (!lapic_in_kernel(vcpu))
 			goto out;
 		r = -EFAULT;
-		if (copy_from_user(&va, argp, sizeof va))
+		if (copy_from_user(&va, argp, sizeof(va)))
 			goto out;
 		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
@@ -3862,7 +4248,7 @@
 		u64 mcg_cap;
 
 		r = -EFAULT;
-		if (copy_from_user(&mcg_cap, argp, sizeof mcg_cap))
+		if (copy_from_user(&mcg_cap, argp, sizeof(mcg_cap)))
 			goto out;
 		r = kvm_vcpu_ioctl_x86_setup_mce(vcpu, mcg_cap);
 		break;
@@ -3871,7 +4257,7 @@
 		struct kvm_x86_mce mce;
 
 		r = -EFAULT;
-		if (copy_from_user(&mce, argp, sizeof mce))
+		if (copy_from_user(&mce, argp, sizeof(mce)))
 			goto out;
 		r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
 		break;
@@ -3921,7 +4307,7 @@
 		break;
 	}
 	case KVM_GET_XSAVE: {
-		u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL);
+		u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT);
 		r = -ENOMEM;
 		if (!u.xsave)
 			break;
@@ -3945,7 +4331,7 @@
 		break;
 	}
 	case KVM_GET_XCRS: {
-		u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL);
+		u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT);
 		r = -ENOMEM;
 		if (!u.xcrs)
 			break;
@@ -4049,16 +4435,37 @@
 			break;
 
 		if (kvm_state.flags &
-		    ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE))
+		    ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE
+		      | KVM_STATE_NESTED_EVMCS))
 			break;
 
 		/* nested_run_pending implies guest_mode.  */
-		if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING)
+		if ((kvm_state.flags & KVM_STATE_NESTED_RUN_PENDING)
+		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
 			break;
 
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
 		break;
 	}
+	case KVM_GET_SUPPORTED_HV_CPUID: {
+		struct kvm_cpuid2 __user *cpuid_arg = argp;
+		struct kvm_cpuid2 cpuid;
+
+		r = -EFAULT;
+		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
+			goto out;
+
+		r = kvm_vcpu_ioctl_get_hv_cpuid(vcpu, &cpuid,
+						cpuid_arg->entries);
+		if (r)
+			goto out;
+
+		r = -EFAULT;
+		if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
+			goto out;
+		r = 0;
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -4091,7 +4498,7 @@
 }
 
 static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
-					  u32 kvm_nr_mmu_pages)
+					 unsigned long kvm_nr_mmu_pages)
 {
 	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
 		return -EINVAL;
@@ -4105,7 +4512,7 @@
 	return 0;
 }
 
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
 {
 	return kvm->arch.n_max_mmu_pages;
 }
@@ -4263,7 +4670,7 @@
  */
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
-	bool is_dirty = false;
+	bool flush = false;
 	int r;
 
 	mutex_lock(&kvm->slots_lock);
@@ -4274,14 +4681,41 @@
 	if (kvm_x86_ops->flush_log_dirty)
 		kvm_x86_ops->flush_log_dirty(kvm);
 
-	r = kvm_get_dirty_log_protect(kvm, log, &is_dirty);
+	r = kvm_get_dirty_log_protect(kvm, log, &flush);
 
 	/*
 	 * All the TLBs can be flushed out of mmu lock, see the comments in
 	 * kvm_mmu_slot_remove_write_access().
 	 */
 	lockdep_assert_held(&kvm->slots_lock);
-	if (is_dirty)
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
+int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log)
+{
+	bool flush = false;
+	int r;
+
+	mutex_lock(&kvm->slots_lock);
+
+	/*
+	 * Flush potentially hardware-cached dirty pages to dirty_bitmap.
+	 */
+	if (kvm_x86_ops->flush_log_dirty)
+		kvm_x86_ops->flush_log_dirty(kvm);
+
+	r = kvm_clear_dirty_log_protect(kvm, log, &flush);
+
+	/*
+	 * All the TLBs can be flushed out of mmu lock, see the comments in
+	 * kvm_mmu_slot_remove_write_access().
+	 */
+	lockdep_assert_held(&kvm->slots_lock);
+	if (flush)
 		kvm_flush_remote_tlbs(kvm);
 
 	mutex_unlock(&kvm->slots_lock);
@@ -4300,8 +4734,8 @@
 	return 0;
 }
 
-static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
-				   struct kvm_enable_cap *cap)
+int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+			    struct kvm_enable_cap *cap)
 {
 	int r;
 
@@ -4359,12 +4793,18 @@
 			kvm->arch.hlt_in_guest = true;
 		if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
 			kvm->arch.pause_in_guest = true;
+		if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
+			kvm->arch.cstate_in_guest = true;
 		r = 0;
 		break;
 	case KVM_CAP_MSR_PLATFORM_INFO:
 		kvm->arch.guest_can_read_msr_platform_info = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_EXCEPTION_PAYLOAD:
+		kvm->arch.exception_payload_enabled = cap->args[0];
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -4401,7 +4841,7 @@
 		if (kvm->created_vcpus)
 			goto set_identity_unlock;
 		r = -EFAULT;
-		if (copy_from_user(&ident_addr, argp, sizeof ident_addr))
+		if (copy_from_user(&ident_addr, argp, sizeof(ident_addr)))
 			goto set_identity_unlock;
 		r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr);
 set_identity_unlock:
@@ -4485,7 +4925,7 @@
 		if (r)
 			goto get_irqchip_out;
 		r = -EFAULT;
-		if (copy_to_user(argp, chip, sizeof *chip))
+		if (copy_to_user(argp, chip, sizeof(*chip)))
 			goto get_irqchip_out;
 		r = 0;
 	get_irqchip_out:
@@ -4531,7 +4971,7 @@
 	}
 	case KVM_SET_PIT: {
 		r = -EFAULT;
-		if (copy_from_user(&u.ps, argp, sizeof u.ps))
+		if (copy_from_user(&u.ps, argp, sizeof(u.ps)))
 			goto out;
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
@@ -4630,15 +5070,6 @@
 		r = 0;
 		break;
 	}
-	case KVM_ENABLE_CAP: {
-		struct kvm_enable_cap cap;
-
-		r = -EFAULT;
-		if (copy_from_user(&cap, argp, sizeof(cap)))
-			goto out;
-		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
-		break;
-	}
 	case KVM_MEMORY_ENCRYPT_OP: {
 		r = -ENOTTY;
 		if (kvm_x86_ops->mem_enc_op)
@@ -4678,6 +5109,9 @@
 		r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd);
 		break;
 	}
+	case KVM_SET_PMU_EVENT_FILTER:
+		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
+		break;
 	default:
 		r = -ENOTTY;
 	}
@@ -4687,18 +5121,28 @@
 
 static void kvm_init_msr_list(void)
 {
+	struct x86_pmu_capability x86_pmu;
 	u32 dummy[2];
-	unsigned i, j;
+	unsigned i;
 
-	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
-		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
+	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
+			 "Please update the fixed PMCs in msrs_to_saved_all[]");
+
+	perf_get_x86_pmu_capability(&x86_pmu);
+
+	num_msrs_to_save = 0;
+	num_emulated_msrs = 0;
+	num_msr_based_features = 0;
+
+	for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) {
+		if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0)
 			continue;
 
 		/*
 		 * Even MSRs that are valid in the host may not be exposed
 		 * to the guests in some cases.
 		 */
-		switch (msrs_to_save[i]) {
+		switch (msrs_to_save_all[i]) {
 		case MSR_IA32_BNDCFGS:
 			if (!kvm_mpx_supported())
 				continue;
@@ -4707,38 +5151,62 @@
 			if (!kvm_x86_ops->rdtscp_supported())
 				continue;
 			break;
+		case MSR_IA32_RTIT_CTL:
+		case MSR_IA32_RTIT_STATUS:
+			if (!kvm_x86_ops->pt_supported())
+				continue;
+			break;
+		case MSR_IA32_RTIT_CR3_MATCH:
+			if (!kvm_x86_ops->pt_supported() ||
+			    !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering))
+				continue;
+			break;
+		case MSR_IA32_RTIT_OUTPUT_BASE:
+		case MSR_IA32_RTIT_OUTPUT_MASK:
+			if (!kvm_x86_ops->pt_supported() ||
+				(!intel_pt_validate_hw_cap(PT_CAP_topa_output) &&
+				 !intel_pt_validate_hw_cap(PT_CAP_single_range_output)))
+				continue;
+			break;
+		case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: {
+			if (!kvm_x86_ops->pt_supported() ||
+				msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >=
+				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
+				continue;
+			break;
+		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+				continue;
+			break;
+		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
+			if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+				continue;
+		}
 		default:
 			break;
 		}
 
-		if (j < i)
-			msrs_to_save[j] = msrs_to_save[i];
-		j++;
+		msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i];
 	}
-	num_msrs_to_save = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+	for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i]))
 			continue;
 
-		if (j < i)
-			emulated_msrs[j] = emulated_msrs[i];
-		j++;
+		emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
 	}
-	num_emulated_msrs = j;
 
-	for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+	for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
 		struct kvm_msr_entry msr;
 
-		msr.index = msr_based_features[i];
+		msr.index = msr_based_features_all[i];
 		if (kvm_get_msr_feature(&msr))
 			continue;
 
-		if (j < i)
-			msr_based_features[j] = msr_based_features[i];
-		j++;
+		msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
 	}
-	num_msr_based_features = j;
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -4805,7 +5273,7 @@
 
 	/* NPT walks are always user-walks */
 	access |= PFERR_USER_MASK;
-	t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception);
+	t_gpa  = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception);
 
 	return t_gpa;
 }
@@ -4904,6 +5372,13 @@
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
 					  exception);
 }
@@ -4982,6 +5457,13 @@
 	/* kvm_write_guest_virt_system can pull in tons of pages. */
 	vcpu->arch.l1tf_flush_l1d = true;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
 					   PFERR_WRITE_MASK, exception);
 }
@@ -4990,7 +5472,6 @@
 int handle_ud(struct kvm_vcpu *vcpu)
 {
 	int emul_type = EMULTYPE_TRAP_UD;
-	enum emulation_result er;
 	char sig[5]; /* ud2; .ascii "kvm" */
 	struct x86_exception e;
 
@@ -4999,15 +5480,10 @@
 				sig, sizeof(sig), &e) == 0 &&
 	    memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) {
 		kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig));
-		emul_type = 0;
+		emul_type = EMULTYPE_TRAP_UD_FORCED;
 	}
 
-	er = kvm_emulate_instruction(vcpu, emul_type);
-	if (er == EMULATE_USER_EXIT)
-		return 0;
-	if (er != EMULATE_DONE)
-		kvm_queue_exception(vcpu, UD_VECTOR);
-	return 1;
+	return kvm_emulate_instruction(vcpu, emul_type);
 }
 EXPORT_SYMBOL_GPL(handle_ud);
 
@@ -5040,7 +5516,7 @@
 	 */
 	if (vcpu_match_mmio_gva(vcpu, gva)
 	    && !permission_fault(vcpu, vcpu->arch.walk_mmu,
-				 vcpu->arch.access, 0, access)) {
+				 vcpu->arch.mmio_access, 0, access)) {
 		*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
 					(gva & (PAGE_SIZE - 1));
 		trace_vcpu_match_mmio(gva, *gpa, write, false);
@@ -5282,9 +5758,9 @@
 				     unsigned int bytes,
 				     struct x86_exception *exception)
 {
+	struct kvm_host_map map;
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	gpa_t gpa;
-	struct page *page;
 	char *kaddr;
 	bool exchanged;
 
@@ -5301,12 +5777,11 @@
 	if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
 		goto emul_write;
 
-	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
-	if (is_error_page(page))
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(gpa), &map))
 		goto emul_write;
 
-	kaddr = kmap_atomic(page);
-	kaddr += offset_in_page(gpa);
+	kaddr = map.hva + offset_in_page(gpa);
+
 	switch (bytes) {
 	case 1:
 		exchanged = CMPXCHG_TYPE(u8, kaddr, old, new);
@@ -5323,13 +5798,12 @@
 	default:
 		BUG();
 	}
-	kunmap_atomic(kaddr);
-	kvm_release_page_dirty(page);
+
+	kvm_vcpu_unmap(vcpu, &map, true);
 
 	if (!exchanged)
 		return X86EMUL_CMPXCHG_FAILED;
 
-	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
 	kvm_page_track_write(vcpu, gpa, new, bytes);
 
 	return X86EMUL_CONTINUE;
@@ -5636,28 +6110,13 @@
 static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 *pdata)
 {
-	struct msr_data msr;
-	int r;
-
-	msr.index = msr_index;
-	msr.host_initiated = false;
-	r = kvm_get_msr(emul_to_vcpu(ctxt), &msr);
-	if (r)
-		return r;
-
-	*pdata = msr.data;
-	return 0;
+	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
 }
 
 static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 data)
 {
-	struct msr_data msr;
-
-	msr.data = data;
-	msr.index = msr_index;
-	msr.host_initiated = false;
-	return kvm_set_msr(emul_to_vcpu(ctxt), &msr);
+	return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
 }
 
 static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
@@ -5726,12 +6185,23 @@
 
 static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
 {
-	kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+	emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
 }
 
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+				  const char *smstate)
 {
-	return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+	return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
+}
+
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
+{
+	kvm_smm_changed(emul_to_vcpu(ctxt));
+}
+
+static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr)
+{
+	return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr);
 }
 
 static const struct x86_emulate_ops emulate_ops = {
@@ -5774,6 +6244,8 @@
 	.get_hflags          = emulator_get_hflags,
 	.set_hflags          = emulator_set_hflags,
 	.pre_leave_smm       = emulator_pre_leave_smm,
+	.post_leave_smm      = emulator_post_leave_smm,
+	.set_xcr             = emulator_set_xcr,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -5833,7 +6305,7 @@
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
 }
 
-int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip)
+void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip)
 {
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 	int ret;
@@ -5845,37 +6317,43 @@
 	ctxt->_eip = ctxt->eip + inc_eip;
 	ret = emulate_int_real(ctxt, irq);
 
-	if (ret != X86EMUL_CONTINUE)
-		return EMULATE_FAIL;
-
-	ctxt->eip = ctxt->_eip;
-	kvm_rip_write(vcpu, ctxt->eip);
-	kvm_set_rflags(vcpu, ctxt->eflags);
-
-	return EMULATE_DONE;
+	if (ret != X86EMUL_CONTINUE) {
+		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+	} else {
+		ctxt->eip = ctxt->_eip;
+		kvm_rip_write(vcpu, ctxt->eip);
+		kvm_set_rflags(vcpu, ctxt->eflags);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt);
 
 static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
 {
-	int r = EMULATE_DONE;
-
 	++vcpu->stat.insn_emulation_fail;
 	trace_kvm_emulate_insn_failed(vcpu);
 
-	if (emulation_type & EMULTYPE_NO_UD_ON_FAIL)
-		return EMULATE_FAIL;
+	if (emulation_type & EMULTYPE_VMWARE_GP) {
+		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+		return 1;
+	}
+
+	if (emulation_type & EMULTYPE_SKIP) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
+		return 0;
+	}
+
+	kvm_queue_exception(vcpu, UD_VECTOR);
 
 	if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
-		r = EMULATE_USER_EXIT;
+		return 0;
 	}
 
-	kvm_queue_exception(vcpu, UD_VECTOR);
-
-	return r;
+	return 1;
 }
 
 static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
@@ -5891,7 +6369,7 @@
 	if (WARN_ON_ONCE(is_guest_mode(vcpu)))
 		return false;
 
-	if (!vcpu->arch.mmu.direct_map) {
+	if (!vcpu->arch.mmu->direct_map) {
 		/*
 		 * Write permission should be allowed since only
 		 * write access need to be emulated.
@@ -5924,7 +6402,7 @@
 	kvm_release_pfn_clean(pfn);
 
 	/* The instructions are well-emulated on direct mmu. */
-	if (vcpu->arch.mmu.direct_map) {
+	if (vcpu->arch.mmu->direct_map) {
 		unsigned int indirect_shadow_pages;
 
 		spin_lock(&vcpu->kvm->mmu_lock);
@@ -5991,7 +6469,7 @@
 	vcpu->arch.last_retry_eip = ctxt->eip;
 	vcpu->arch.last_retry_addr = cr2;
 
-	if (!vcpu->arch.mmu.direct_map)
+	if (!vcpu->arch.mmu->direct_map)
 		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
 
 	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
@@ -6015,16 +6493,6 @@
 	kvm_mmu_reset_context(vcpu);
 }
 
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
-	unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
-	vcpu->arch.hflags = emul_flags;
-
-	if (changed & HF_SMM_MASK)
-		kvm_smm_changed(vcpu);
-}
-
 static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 				unsigned long *db)
 {
@@ -6040,7 +6508,7 @@
 	return dr6;
 }
 
-static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r)
+static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
@@ -6049,25 +6517,20 @@
 		kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
 		kvm_run->debug.arch.exception = DB_VECTOR;
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
-		*r = EMULATE_USER_EXIT;
-	} else {
-		/*
-		 * "Certain debug exceptions may clear bit 0-3.  The
-		 * remaining contents of the DR6 register are never
-		 * cleared by the processor".
-		 */
-		vcpu->arch.dr6 &= ~15;
-		vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
-		kvm_queue_exception(vcpu, DB_VECTOR);
+		return 0;
 	}
+	kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS);
+	return 1;
 }
 
 int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
-	int r = EMULATE_DONE;
+	int r;
 
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	r = kvm_x86_ops->skip_emulated_instruction(vcpu);
+	if (unlikely(!r))
+		return 0;
 
 	/*
 	 * rflags is the old, "raw" value of the flags.  The new value has
@@ -6078,8 +6541,8 @@
 	 * that sets the TF flag".
 	 */
 	if (unlikely(rflags & X86_EFLAGS_TF))
-		kvm_vcpu_do_singlestep(vcpu, &r);
-	return r == EMULATE_DONE;
+		r = kvm_vcpu_do_singlestep(vcpu);
+	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);
 
@@ -6098,7 +6561,7 @@
 			kvm_run->debug.arch.pc = eip;
 			kvm_run->debug.arch.exception = DB_VECTOR;
 			kvm_run->exit_reason = KVM_EXIT_DEBUG;
-			*r = EMULATE_USER_EXIT;
+			*r = 0;
 			return true;
 		}
 	}
@@ -6111,10 +6574,10 @@
 					   vcpu->arch.db);
 
 		if (dr6 != 0) {
-			vcpu->arch.dr6 &= ~15;
+			vcpu->arch.dr6 &= ~DR_TRAP_BITS;
 			vcpu->arch.dr6 |= dr6 | DR6_RTM;
 			kvm_queue_exception(vcpu, DB_VECTOR);
-			*r = EMULATE_DONE;
+			*r = 1;
 			return true;
 		}
 	}
@@ -6198,32 +6661,48 @@
 		trace_kvm_emulate_insn_start(vcpu);
 		++vcpu->stat.insn_emulation;
 		if (r != EMULATION_OK)  {
-			if (emulation_type & EMULTYPE_TRAP_UD)
-				return EMULATE_FAIL;
+			if ((emulation_type & EMULTYPE_TRAP_UD) ||
+			    (emulation_type & EMULTYPE_TRAP_UD_FORCED)) {
+				kvm_queue_exception(vcpu, UD_VECTOR);
+				return 1;
+			}
 			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
 						emulation_type))
-				return EMULATE_DONE;
-			if (ctxt->have_exception && inject_emulated_exception(vcpu))
-				return EMULATE_DONE;
-			if (emulation_type & EMULTYPE_SKIP)
-				return EMULATE_FAIL;
+				return 1;
+			if (ctxt->have_exception) {
+				/*
+				 * #UD should result in just EMULATION_FAILED, and trap-like
+				 * exception should not be encountered during decode.
+				 */
+				WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR ||
+					     exception_type(ctxt->exception.vector) == EXCPT_TRAP);
+				inject_emulated_exception(vcpu);
+				return 1;
+			}
 			return handle_emulation_failure(vcpu, emulation_type);
 		}
 	}
 
-	if ((emulation_type & EMULTYPE_VMWARE) &&
-	    !is_vmware_backdoor_opcode(ctxt))
-		return EMULATE_FAIL;
+	if ((emulation_type & EMULTYPE_VMWARE_GP) &&
+	    !is_vmware_backdoor_opcode(ctxt)) {
+		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+		return 1;
+	}
 
+	/*
+	 * Note, EMULTYPE_SKIP is intended for use *only* by vendor callbacks
+	 * for kvm_skip_emulated_instruction().  The caller is responsible for
+	 * updating interruptibility state and injecting single-step #DBs.
+	 */
 	if (emulation_type & EMULTYPE_SKIP) {
 		kvm_rip_write(vcpu, ctxt->_eip);
 		if (ctxt->eflags & X86_EFLAGS_RF)
 			kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF);
-		return EMULATE_DONE;
+		return 1;
 	}
 
 	if (retry_instruction(ctxt, cr2, emulation_type))
-		return EMULATE_DONE;
+		return 1;
 
 	/* this is needed for vmware backdoor interface to work since it
 	   changes registers values  during IO operation */
@@ -6239,18 +6718,18 @@
 	r = x86_emulate_insn(ctxt);
 
 	if (r == EMULATION_INTERCEPTED)
-		return EMULATE_DONE;
+		return 1;
 
 	if (r == EMULATION_FAILED) {
 		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
 					emulation_type))
-			return EMULATE_DONE;
+			return 1;
 
 		return handle_emulation_failure(vcpu, emulation_type);
 	}
 
 	if (ctxt->have_exception) {
-		r = EMULATE_DONE;
+		r = 1;
 		if (inject_emulated_exception(vcpu))
 			return r;
 	} else if (vcpu->arch.pio.count) {
@@ -6261,28 +6740,30 @@
 			writeback = false;
 			vcpu->arch.complete_userspace_io = complete_emulated_pio;
 		}
-		r = EMULATE_USER_EXIT;
+		r = 0;
 	} else if (vcpu->mmio_needed) {
+		++vcpu->stat.mmio_exits;
+
 		if (!vcpu->mmio_is_write)
 			writeback = false;
-		r = EMULATE_USER_EXIT;
+		r = 0;
 		vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	} else if (r == EMULATION_RESTART)
 		goto restart;
 	else
-		r = EMULATE_DONE;
+		r = 1;
 
 	if (writeback) {
 		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
-		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE &&
-		    (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
-			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
-		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
+			kvm_rip_write(vcpu, ctxt->eip);
+			if (r && ctxt->tf)
+				r = kvm_vcpu_do_singlestep(vcpu);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
+		}
 
 		/*
 		 * For STI, interrupts are shadowed; so KVM_REQ_EVENT will
@@ -6311,15 +6792,45 @@
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
 
+static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pio.count = 0;
+	return 1;
+}
+
+static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pio.count = 0;
+
+	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip)))
+		return 1;
+
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
 static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
 			    unsigned short port)
 {
-	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
+	unsigned long val = kvm_rax_read(vcpu);
 	int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
 					    size, port, &val, 1);
-	/* do not return to emulator after return from userspace */
-	vcpu->arch.pio.count = 0;
-	return ret;
+	if (ret)
+		return ret;
+
+	/*
+	 * Workaround userspace that relies on old KVM behavior of %rip being
+	 * incremented prior to exiting to userspace to handle "OUT 0x7e".
+	 */
+	if (port == 0x7e &&
+	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
+		vcpu->arch.complete_userspace_io =
+			complete_fast_pio_out_port_0x7e;
+		kvm_skip_emulated_instruction(vcpu);
+	} else {
+		vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+		vcpu->arch.complete_userspace_io = complete_fast_pio_out;
+	}
+	return 0;
 }
 
 static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
@@ -6329,9 +6840,13 @@
 	/* We should only ever be called with arch.pio.count equal to 1 */
 	BUG_ON(vcpu->arch.pio.count != 1);
 
+	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) {
+		vcpu->arch.pio.count = 0;
+		return 1;
+	}
+
 	/* For size less than 4 we merge, else we zero extend */
-	val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
-					: 0;
+	val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0;
 
 	/*
 	 * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform
@@ -6339,9 +6854,9 @@
 	 */
 	emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size,
 				 vcpu->arch.pio.port, &val, 1);
-	kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+	kvm_rax_write(vcpu, val);
 
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
@@ -6351,15 +6866,16 @@
 	int ret;
 
 	/* For size less than 4 we merge, else we zero extend */
-	val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0;
+	val = (size < 4) ? kvm_rax_read(vcpu) : 0;
 
 	ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port,
 				       &val, 1);
 	if (ret) {
-		kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+		kvm_rax_write(vcpu, val);
 		return ret;
 	}
 
+	vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
 	vcpu->arch.complete_userspace_io = complete_fast_pio_in;
 
 	return 0;
@@ -6367,16 +6883,13 @@
 
 int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in)
 {
-	int ret = kvm_skip_emulated_instruction(vcpu);
+	int ret;
 
-	/*
-	 * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered
-	 * KVM_EXIT_DEBUG here.
-	 */
 	if (in)
-		return kvm_fast_pio_in(vcpu, size, port) && ret;
+		ret = kvm_fast_pio_in(vcpu, size, port);
 	else
-		return kvm_fast_pio_out(vcpu, size, port) && ret;
+		ret = kvm_fast_pio_out(vcpu, size, port);
+	return ret && kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio);
 
@@ -6407,7 +6920,7 @@
 	struct kvm_vcpu *vcpu;
 	int cpu;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_make_mclock_inprogress_request(kvm);
 
@@ -6433,14 +6946,12 @@
 
 		spin_unlock(&ka->pvclock_gtod_sync_lock);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 }
 #endif
 
-static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-				     void *data)
+static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu)
 {
-	struct cpufreq_freqs *freq = data;
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
 	int i, send_ipi = 0;
@@ -6484,24 +6995,19 @@
 	 *
 	 */
 
-	if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
-		return 0;
-	if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
-		return 0;
+	smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
 
-	smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
-
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
-			if (vcpu->cpu != freq->cpu)
+			if (vcpu->cpu != cpu)
 				continue;
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
-			if (vcpu->cpu != smp_processor_id())
+			if (vcpu->cpu != raw_smp_processor_id())
 				send_ipi = 1;
 		}
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -6516,8 +7022,24 @@
 		 * guest context is entered kvmclock will be updated,
 		 * so the guest will not see stale values.
 		 */
-		smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
+		smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
 	}
+}
+
+static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+				     void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	int cpu;
+
+	if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
+		return 0;
+	if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
+		return 0;
+
+	for_each_cpu(cpu, freq->policy->cpus)
+		__kvmclock_cpufreq_notifier(freq, cpu);
+
 	return 0;
 }
 
@@ -6550,7 +7072,6 @@
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
 	}
-	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 
 	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
@@ -6584,41 +7105,22 @@
 	return ip;
 }
 
+static void kvm_handle_intel_pt_intr(void)
+{
+	struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
+
+	kvm_make_request(KVM_REQ_PMI, vcpu);
+	__set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT,
+			(unsigned long *)&vcpu->arch.pmu.global_status);
+}
+
 static struct perf_guest_info_callbacks kvm_guest_cbs = {
 	.is_in_guest		= kvm_is_in_guest,
 	.is_user_mode		= kvm_is_user_mode,
 	.get_guest_ip		= kvm_get_guest_ip,
+	.handle_intel_pt_intr	= kvm_handle_intel_pt_intr,
 };
 
-static void kvm_set_mmio_spte_mask(void)
-{
-	u64 mask;
-	int maxphyaddr = boot_cpu_data.x86_phys_bits;
-
-	/*
-	 * Set the reserved bits and the present bit of an paging-structure
-	 * entry to generate page fault with PFER.RSV = 1.
-	 */
-
-	/*
-	 * Mask the uppermost physical address bit, which would be reserved as
-	 * long as the supported physical address width is less than 52.
-	 */
-	mask = 1ull << 51;
-
-	/* Set the present bit. */
-	mask |= 1ull;
-
-	/*
-	 * If reserved bit is not supported, clear the present bit to disable
-	 * mmio page fault.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && maxphyaddr == 52)
-		mask &= ~1ull;
-
-	kvm_mmu_set_mmio_spte_mask(mask, mask);
-}
-
 #ifdef CONFIG_X86_64
 static void pvclock_gtod_update_fn(struct work_struct *work)
 {
@@ -6627,12 +7129,12 @@
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 	atomic_set(&kvm_guest_has_master_clock, 0);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -6685,19 +7187,36 @@
 		goto out;
 	}
 
+	/*
+	 * KVM explicitly assumes that the guest has an FPU and
+	 * FXSAVE/FXRSTOR. For example, the KVM_GET_FPU explicitly casts the
+	 * vCPU's FPU state as a fxregs_state struct.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) {
+		printk(KERN_ERR "kvm: inadequate fpu\n");
+		r = -EOPNOTSUPP;
+		goto out;
+	}
+
 	r = -ENOMEM;
+	x86_fpu_cache = kmem_cache_create("x86_fpu", sizeof(struct fpu),
+					  __alignof__(struct fpu), SLAB_ACCOUNT,
+					  NULL);
+	if (!x86_fpu_cache) {
+		printk(KERN_ERR "kvm: failed to allocate cache for x86 fpu\n");
+		goto out;
+	}
+
 	shared_msrs = alloc_percpu(struct kvm_shared_msrs);
 	if (!shared_msrs) {
 		printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n");
-		goto out;
+		goto out_free_x86_fpu_cache;
 	}
 
 	r = kvm_mmu_module_init();
 	if (r)
 		goto out_free_percpu;
 
-	kvm_set_mmio_spte_mask();
-
 	kvm_x86_ops = ops;
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
@@ -6711,6 +7230,8 @@
 		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 
 	kvm_lapic_init();
+	if (pi_inject_timer == -1)
+		pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER);
 #ifdef CONFIG_X86_64
 	pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
 
@@ -6722,6 +7243,8 @@
 
 out_free_percpu:
 	free_percpu(shared_msrs);
+out_free_x86_fpu_cache:
+	kmem_cache_destroy(x86_fpu_cache);
 out:
 	return r;
 }
@@ -6745,6 +7268,7 @@
 	kvm_x86_ops = NULL;
 	kvm_mmu_module_exit();
 	free_percpu(shared_msrs);
+	kmem_cache_destroy(x86_fpu_cache);
 }
 
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
@@ -6822,10 +7346,34 @@
 
 void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
 {
+	if (!lapic_in_kernel(vcpu)) {
+		WARN_ON_ONCE(vcpu->arch.apicv_active);
+		return;
+	}
+	if (!vcpu->arch.apicv_active)
+		return;
+
 	vcpu->arch.apicv_active = false;
 	kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu);
 }
 
+static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id)
+{
+	struct kvm_vcpu *target = NULL;
+	struct kvm_apic_map *map;
+
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
+
+	if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id])
+		target = map->phys_map[dest_id]->vcpu;
+
+	rcu_read_unlock();
+
+	if (target && READ_ONCE(target->ready))
+		kvm_vcpu_yield_to(target);
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
@@ -6834,11 +7382,11 @@
 	if (kvm_hv_hypercall_enabled(vcpu->kvm))
 		return kvm_hv_hypercall(vcpu);
 
-	nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
-	a1 = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	a2 = kvm_register_read(vcpu, VCPU_REGS_RDX);
-	a3 = kvm_register_read(vcpu, VCPU_REGS_RSI);
+	nr = kvm_rax_read(vcpu);
+	a0 = kvm_rbx_read(vcpu);
+	a1 = kvm_rcx_read(vcpu);
+	a2 = kvm_rdx_read(vcpu);
+	a3 = kvm_rsi_read(vcpu);
 
 	trace_kvm_hypercall(nr, a0, a1, a2, a3);
 
@@ -6862,16 +7410,21 @@
 		break;
 	case KVM_HC_KICK_CPU:
 		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+		kvm_sched_yield(vcpu->kvm, a1);
 		ret = 0;
 		break;
 #ifdef CONFIG_X86_64
 	case KVM_HC_CLOCK_PAIRING:
 		ret = kvm_pv_clock_pairing(vcpu, a0, a1);
 		break;
+#endif
 	case KVM_HC_SEND_IPI:
 		ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit);
 		break;
-#endif
+	case KVM_HC_SCHED_YIELD:
+		kvm_sched_yield(vcpu->kvm, a0);
+		ret = 0;
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
@@ -6879,7 +7432,7 @@
 out:
 	if (!op_64_bit)
 		ret = (u32)ret;
-	kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+	kvm_rax_write(vcpu, ret);
 
 	++vcpu->stat.hypercalls;
 	return kvm_skip_emulated_instruction(vcpu);
@@ -6998,10 +7551,22 @@
 			__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
 					     X86_EFLAGS_RF);
 
-		if (vcpu->arch.exception.nr == DB_VECTOR &&
-		    (vcpu->arch.dr7 & DR7_GD)) {
-			vcpu->arch.dr7 &= ~DR7_GD;
-			kvm_update_dr7(vcpu);
+		if (vcpu->arch.exception.nr == DB_VECTOR) {
+			/*
+			 * This code assumes that nSVM doesn't use
+			 * check_nested_events(). If it does, the
+			 * DR6/DR7 changes should happen before L1
+			 * gets a #VMEXIT for an intercepted #DB in
+			 * L2.  (Under VMX, on the other hand, the
+			 * DR6/DR7 changes should not happen in the
+			 * event of a VM-exit to L1 for an intercepted
+			 * #DB in L2.)
+			 */
+			kvm_deliver_exception_payload(vcpu);
+			if (vcpu->arch.dr7 & DR7_GD) {
+				vcpu->arch.dr7 &= ~DR7_GD;
+				kvm_update_dr7(vcpu);
+			}
 		}
 
 		kvm_x86_ops->queue_exception(vcpu);
@@ -7160,9 +7725,9 @@
 	put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
 }
 
+#ifdef CONFIG_X86_64
 static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 {
-#ifdef CONFIG_X86_64
 	struct desc_ptr dt;
 	struct kvm_segment seg;
 	unsigned long val;
@@ -7212,10 +7777,8 @@
 
 	for (i = 0; i < 6; i++)
 		enter_smm_save_seg_64(vcpu, buf, i);
-#else
-	WARN_ON_ONCE(1);
-#endif
 }
+#endif
 
 static void enter_smm(struct kvm_vcpu *vcpu)
 {
@@ -7226,9 +7789,11 @@
 
 	trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
 	memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		enter_smm_save_state_64(vcpu, buf);
 	else
+#endif
 		enter_smm_save_state_32(vcpu, buf);
 
 	/*
@@ -7286,8 +7851,10 @@
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
 
+#ifdef CONFIG_X86_64
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		kvm_x86_ops->set_efer(vcpu, 0);
+#endif
 
 	kvm_update_cpuid(vcpu);
 	kvm_mmu_reset_context(vcpu);
@@ -7399,8 +7966,12 @@
 	bool req_immediate_exit = false;
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu))
-			kvm_x86_ops->get_vmcs12_pages(vcpu);
+		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) {
+			if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) {
+				r = 0;
+				goto out;
+			}
+		}
 		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
@@ -7556,7 +8127,7 @@
 	 * 1) We should set ->mode before checking ->requests.  Please see
 	 * the comment in kvm_vcpu_exiting_guest_mode().
 	 *
-	 * 2) For APICv, we should set ->mode before checking PIR.ON.  This
+	 * 2) For APICv, we should set ->mode before checking PID.ON. This
 	 * pairs with the memory barrier implicit in pi_test_and_set_on
 	 * (see vmx_deliver_posted_interrupt).
 	 *
@@ -7584,18 +8155,17 @@
 		goto cancel_injection;
 	}
 
-	kvm_load_guest_xcr0(vcpu);
-
 	if (req_immediate_exit) {
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		kvm_x86_ops->request_immediate_exit(vcpu);
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
-	if (lapic_timer_advance_ns)
-		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
+	/* The preempt notifier should have taken care of the FPU already.  */
+	WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
+
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
@@ -7638,15 +8208,29 @@
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
-	kvm_put_guest_xcr0(vcpu);
+	kvm_x86_ops->handle_exit_irqoff(vcpu);
 
+	/*
+	 * Consume any pending interrupts, including the possible source of
+	 * VM-Exit on SVM and any ticks that occur between VM-Exit and now.
+	 * An instruction is required after local_irq_enable() to fully unblock
+	 * interrupts on processors that implement an interrupt shadow, the
+	 * stat.exits increment will do nicely.
+	 */
 	kvm_before_interrupt(vcpu);
-	kvm_x86_ops->handle_external_intr(vcpu);
+	local_irq_enable();
+	++vcpu->stat.exits;
+	local_irq_disable();
 	kvm_after_interrupt(vcpu);
 
-	++vcpu->stat.exits;
-
 	guest_exit_irqoff();
+	if (lapic_in_kernel(vcpu)) {
+		s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta;
+		if (delta != S64_MIN) {
+			trace_kvm_wait_lapic_expire(vcpu->vcpu_id, delta);
+			vcpu->arch.apic->lapic_timer.advance_expire_delta = S64_MIN;
+		}
+	}
 
 	local_irq_enable();
 	preempt_enable();
@@ -7700,6 +8284,7 @@
 		vcpu->arch.pv.pv_unhalted = false;
 		vcpu->arch.mp_state =
 			KVM_MP_STATE_RUNNABLE;
+		/* fall through */
 	case KVM_MP_STATE_RUNNABLE:
 		vcpu->arch.apf.halted = false;
 		break;
@@ -7774,12 +8359,11 @@
 static inline int complete_emulated_io(struct kvm_vcpu *vcpu)
 {
 	int r;
+
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-	if (r != EMULATE_DONE)
-		return 0;
-	return 1;
+	return r;
 }
 
 static int complete_emulated_pio(struct kvm_vcpu *vcpu)
@@ -7855,22 +8439,30 @@
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
-	copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
+	fpregs_lock();
+
+	copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
-	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
-	preempt_enable();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+
 	trace_kvm_fpu(1);
 }
 
 /* When vcpu_run ends, restore user space FPU context. */
 static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
-	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
-	copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
-	preempt_enable();
+	fpregs_lock();
+
+	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
 }
@@ -7957,23 +8549,23 @@
 		emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 	}
-	regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX);
-	regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	regs->rdx = kvm_register_read(vcpu, VCPU_REGS_RDX);
-	regs->rsi = kvm_register_read(vcpu, VCPU_REGS_RSI);
-	regs->rdi = kvm_register_read(vcpu, VCPU_REGS_RDI);
-	regs->rsp = kvm_register_read(vcpu, VCPU_REGS_RSP);
-	regs->rbp = kvm_register_read(vcpu, VCPU_REGS_RBP);
+	regs->rax = kvm_rax_read(vcpu);
+	regs->rbx = kvm_rbx_read(vcpu);
+	regs->rcx = kvm_rcx_read(vcpu);
+	regs->rdx = kvm_rdx_read(vcpu);
+	regs->rsi = kvm_rsi_read(vcpu);
+	regs->rdi = kvm_rdi_read(vcpu);
+	regs->rsp = kvm_rsp_read(vcpu);
+	regs->rbp = kvm_rbp_read(vcpu);
 #ifdef CONFIG_X86_64
-	regs->r8 = kvm_register_read(vcpu, VCPU_REGS_R8);
-	regs->r9 = kvm_register_read(vcpu, VCPU_REGS_R9);
-	regs->r10 = kvm_register_read(vcpu, VCPU_REGS_R10);
-	regs->r11 = kvm_register_read(vcpu, VCPU_REGS_R11);
-	regs->r12 = kvm_register_read(vcpu, VCPU_REGS_R12);
-	regs->r13 = kvm_register_read(vcpu, VCPU_REGS_R13);
-	regs->r14 = kvm_register_read(vcpu, VCPU_REGS_R14);
-	regs->r15 = kvm_register_read(vcpu, VCPU_REGS_R15);
+	regs->r8 = kvm_r8_read(vcpu);
+	regs->r9 = kvm_r9_read(vcpu);
+	regs->r10 = kvm_r10_read(vcpu);
+	regs->r11 = kvm_r11_read(vcpu);
+	regs->r12 = kvm_r12_read(vcpu);
+	regs->r13 = kvm_r13_read(vcpu);
+	regs->r14 = kvm_r14_read(vcpu);
+	regs->r15 = kvm_r15_read(vcpu);
 #endif
 
 	regs->rip = kvm_rip_read(vcpu);
@@ -7993,23 +8585,23 @@
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = true;
 	vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 
-	kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, regs->rdx);
-	kvm_register_write(vcpu, VCPU_REGS_RSI, regs->rsi);
-	kvm_register_write(vcpu, VCPU_REGS_RDI, regs->rdi);
-	kvm_register_write(vcpu, VCPU_REGS_RSP, regs->rsp);
-	kvm_register_write(vcpu, VCPU_REGS_RBP, regs->rbp);
+	kvm_rax_write(vcpu, regs->rax);
+	kvm_rbx_write(vcpu, regs->rbx);
+	kvm_rcx_write(vcpu, regs->rcx);
+	kvm_rdx_write(vcpu, regs->rdx);
+	kvm_rsi_write(vcpu, regs->rsi);
+	kvm_rdi_write(vcpu, regs->rdi);
+	kvm_rsp_write(vcpu, regs->rsp);
+	kvm_rbp_write(vcpu, regs->rbp);
 #ifdef CONFIG_X86_64
-	kvm_register_write(vcpu, VCPU_REGS_R8, regs->r8);
-	kvm_register_write(vcpu, VCPU_REGS_R9, regs->r9);
-	kvm_register_write(vcpu, VCPU_REGS_R10, regs->r10);
-	kvm_register_write(vcpu, VCPU_REGS_R11, regs->r11);
-	kvm_register_write(vcpu, VCPU_REGS_R12, regs->r12);
-	kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13);
-	kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14);
-	kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15);
+	kvm_r8_write(vcpu, regs->r8);
+	kvm_r9_write(vcpu, regs->r9);
+	kvm_r10_write(vcpu, regs->r10);
+	kvm_r11_write(vcpu, regs->r11);
+	kvm_r12_write(vcpu, regs->r12);
+	kvm_r13_write(vcpu, regs->r13);
+	kvm_r14_write(vcpu, regs->r14);
+	kvm_r15_write(vcpu, regs->r15);
 #endif
 
 	kvm_rip_write(vcpu, regs->rip);
@@ -8067,7 +8659,7 @@
 	sregs->efer = vcpu->arch.efer;
 	sregs->apic_base = kvm_get_apic_base(vcpu);
 
-	memset(sregs->interrupt_bitmap, 0, sizeof sregs->interrupt_bitmap);
+	memset(sregs->interrupt_bitmap, 0, sizeof(sregs->interrupt_bitmap));
 
 	if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft)
 		set_bit(vcpu->arch.interrupt.nr,
@@ -8139,23 +8731,22 @@
 
 	ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason,
 				   has_error_code, error_code);
-
-	if (ret)
-		return EMULATE_FAIL;
+	if (ret) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
+		return 0;
+	}
 
 	kvm_rip_write(vcpu, ctxt->eip);
 	kvm_set_rflags(vcpu, ctxt->eflags);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
-	return EMULATE_DONE;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
 
 static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-			(sregs->cr4 & X86_CR4_OSXSAVE))
-		return  -EINVAL;
-
 	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
 		 * When EFER.LME and CR0.PG are set, the processor is in
@@ -8174,7 +8765,7 @@
 			return -EINVAL;
 	}
 
-	return 0;
+	return kvm_valid_cr4(vcpu, sregs->cr4);
 }
 
 static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
@@ -8223,7 +8814,7 @@
 		kvm_update_cpuid(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
+	if (is_pae_paging(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		mmu_reset_needed = 1;
 	}
@@ -8363,7 +8954,7 @@
 
 	vcpu_load(vcpu);
 
-	fxsave = &vcpu->arch.guest_fpu.state.fxsave;
+	fxsave = &vcpu->arch.guest_fpu->state.fxsave;
 	memcpy(fpu->fpr, fxsave->st_space, 128);
 	fpu->fcw = fxsave->cwd;
 	fpu->fsw = fxsave->swd;
@@ -8371,7 +8962,7 @@
 	fpu->last_opcode = fxsave->fop;
 	fpu->last_ip = fxsave->rip;
 	fpu->last_dp = fxsave->rdp;
-	memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space);
+	memcpy(fpu->xmm, fxsave->xmm_space, sizeof(fxsave->xmm_space));
 
 	vcpu_put(vcpu);
 	return 0;
@@ -8383,7 +8974,7 @@
 
 	vcpu_load(vcpu);
 
-	fxsave = &vcpu->arch.guest_fpu.state.fxsave;
+	fxsave = &vcpu->arch.guest_fpu->state.fxsave;
 
 	memcpy(fxsave->st_space, fpu->fpr, 128);
 	fxsave->cwd = fpu->fcw;
@@ -8392,7 +8983,7 @@
 	fxsave->fop = fpu->last_opcode;
 	fxsave->rip = fpu->last_ip;
 	fxsave->rdp = fpu->last_dp;
-	memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space);
+	memcpy(fxsave->xmm_space, fpu->xmm, sizeof(fxsave->xmm_space));
 
 	vcpu_put(vcpu);
 	return 0;
@@ -8439,9 +9030,9 @@
 
 static void fx_init(struct kvm_vcpu *vcpu)
 {
-	fpstate_init(&vcpu->arch.guest_fpu.state);
+	fpstate_init(&vcpu->arch.guest_fpu->state);
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
+		vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv =
 			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
@@ -8479,10 +9070,12 @@
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
+	vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
 	kvm_vcpu_mtrr_init(vcpu);
 	vcpu_load(vcpu);
 	kvm_vcpu_reset(vcpu, false);
-	kvm_mmu_setup(vcpu);
+	kvm_init_mmu(vcpu, false);
 	vcpu_put(vcpu);
 	return 0;
 }
@@ -8502,6 +9095,10 @@
 	msr.host_initiated = true;
 	kvm_write_tsc(vcpu, &msr);
 	vcpu_put(vcpu);
+
+	/* poll control enabled by default */
+	vcpu->arch.msr_kvm_poll_control = 1;
+
 	mutex_unlock(&vcpu->mutex);
 
 	if (!kvmclock_periodic_sync)
@@ -8565,12 +9162,12 @@
 		 */
 		if (init_event)
 			kvm_put_guest_fpu(vcpu);
-		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave,
-					XFEATURE_MASK_BNDREGS);
+		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
+					XFEATURE_BNDREGS);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state));
-		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave,
-					XFEATURE_MASK_BNDCSR);
+		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
+					XFEATURE_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
 		if (init_event)
@@ -8581,7 +9178,6 @@
 		kvm_pmu_reset(vcpu);
 		vcpu->arch.smbase = 0x30000;
 
-		vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
 		vcpu->arch.msr_misc_features_enables = 0;
 
 		vcpu->arch.xcr0 = XFEATURE_MASK_FP;
@@ -8644,7 +9240,7 @@
 	 * before any KVM threads can be running.  Unfortunately, we can't
 	 * bring the TSCs fully up to date with real time, as we aren't yet far
 	 * enough into CPU bringup that we know how much real time has actually
-	 * elapsed; our helper function, ktime_get_boot_ns() will be using boot
+	 * elapsed; our helper function, ktime_get_boottime_ns() will be using boot
 	 * variables that haven't been updated yet.
 	 *
 	 * So we simply find the maximum observed TSC above, then record the
@@ -8735,9 +9331,9 @@
 	kvm_x86_ops->hardware_unsetup();
 }
 
-void kvm_arch_check_processor_compat(void *rtn)
+int kvm_arch_check_processor_compat(void)
 {
-	kvm_x86_ops->check_processor_compatibility(rtn);
+	return kvm_x86_ops->check_processor_compatibility();
 }
 
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
@@ -8759,7 +9355,6 @@
 	struct page *page;
 	int r;
 
-	vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
 	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -8780,21 +9375,23 @@
 		goto fail_free_pio_data;
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
-		r = kvm_create_lapic(vcpu);
+		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
+		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
 	} else
 		static_key_slow_inc(&kvm_no_apic_vcpu);
 
 	vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4,
-				       GFP_KERNEL);
+				       GFP_KERNEL_ACCOUNT);
 	if (!vcpu->arch.mce_banks) {
 		r = -ENOMEM;
 		goto fail_free_lapic;
 	}
 	vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS;
 
-	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask,
+				GFP_KERNEL_ACCOUNT)) {
 		r = -ENOMEM;
 		goto fail_free_mce_banks;
 	}
@@ -8859,6 +9456,7 @@
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+	INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
@@ -8872,7 +9470,7 @@
 	mutex_init(&kvm->arch.apic_map_lock);
 	spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
 
-	kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
+	kvm->arch.kvmclock_offset = -ktime_get_boottime_ns();
 	pvclock_update_vm_gtod_copy(kvm);
 
 	kvm->arch.guest_can_read_msr_platform_info = true;
@@ -8884,10 +9482,12 @@
 	kvm_page_track_init(kvm);
 	kvm_mmu_init_vm(kvm);
 
-	if (kvm_x86_ops->vm_init)
-		return kvm_x86_ops->vm_init(kvm);
+	return kvm_x86_ops->vm_init(kvm);
+}
 
-	return 0;
+int kvm_arch_post_init_vm(struct kvm *kvm)
+{
+	return kvm_mmu_post_init_vm(kvm);
 }
 
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
@@ -8991,6 +9591,11 @@
 }
 EXPORT_SYMBOL_GPL(x86_set_memory_region);
 
+void kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+	kvm_mmu_pre_destroy_vm(kvm);
+}
+
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	if (current->mm == kvm->mm) {
@@ -9009,6 +9614,7 @@
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
 	kvm_page_track_cleanup(kvm);
 	kvm_hv_destroy_vm(kvm);
@@ -9053,13 +9659,13 @@
 
 		slot->arch.rmap[i] =
 			kvcalloc(lpages, sizeof(*slot->arch.rmap[i]),
-				 GFP_KERNEL);
+				 GFP_KERNEL_ACCOUNT);
 		if (!slot->arch.rmap[i])
 			goto out_free;
 		if (i == 0)
 			continue;
 
-		linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL);
+		linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT);
 		if (!linfo)
 			goto out_free;
 
@@ -9102,13 +9708,13 @@
 	return -ENOMEM;
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
+void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 {
 	/*
 	 * memslots->generation has been incremented.
 	 * mmio generation may have reached its maximum value.
 	 */
-	kvm_mmu_invalidate_mmio_sptes(kvm, slots);
+	kvm_mmu_invalidate_mmio_sptes(kvm, gen);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -9140,7 +9746,7 @@
 	 * with dirty logging disabled in order to eliminate unnecessary GPA
 	 * logging in PML buffer (and potential PML buffer full VMEXT). This
 	 * guarantees leaving PML enabled during guest's lifetime won't have
-	 * any additonal overhead from PML when guest is running with dirty
+	 * any additional overhead from PML when guest is running with dirty
 	 * logging disabled for memory slots.
 	 *
 	 * kvm_x86_ops->slot_enable_log_dirty is called when switching new slot
@@ -9175,13 +9781,9 @@
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
-	int nr_mmu_pages = 0;
-
 	if (!kvm->arch.n_requested_mmu_pages)
-		nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
-
-	if (nr_mmu_pages)
-		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
+		kvm_mmu_change_mmu_pages(kvm,
+				kvm_mmu_calculate_default_mmu_pages(kvm));
 
 	/*
 	 * Dirty logging tracks sptes in 4k granularity, meaning that large
@@ -9194,8 +9796,13 @@
 	 * Scan sptes if dirty logging has been stopped, dropping those
 	 * which can be collapsed into a single large-page spte.  Later
 	 * page faults will create the large-page sptes.
+	 *
+	 * There is no need to do this in any of the following cases:
+	 * CREATE:	No dirty mappings will already exist.
+	 * MOVE/DELETE:	The old mappings will already have been cleaned up by
+	 *		kvm_arch_flush_shadow_memslot()
 	 */
-	if ((change != KVM_MR_DELETE) &&
+	if (change == KVM_MR_FLAGS_ONLY &&
 		(old->flags & KVM_MEM_LOG_DIRTY_PAGES) &&
 		!(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
 		kvm_mmu_zap_collapsible_sptes(kvm, new);
@@ -9216,7 +9823,7 @@
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
-	kvm_mmu_invalidate_zap_all_pages(kvm);
+	kvm_mmu_zap_all(kvm);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
@@ -9271,6 +9878,22 @@
 	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	if (READ_ONCE(vcpu->arch.pv.pv_unhalted))
+		return true;
+
+	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+		kvm_test_request(KVM_REQ_SMI, vcpu) ||
+		 kvm_test_request(KVM_REQ_EVENT, vcpu))
+		return true;
+
+	if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu))
+		return true;
+
+	return false;
+}
+
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.preempted_in_kernel;
@@ -9331,7 +9954,7 @@
 {
 	int r;
 
-	if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
+	if ((vcpu->arch.mmu->direct_map != work->arch.direct_map) ||
 	      work->wakeup_all)
 		return;
 
@@ -9339,11 +9962,11 @@
 	if (unlikely(r))
 		return;
 
-	if (!vcpu->arch.mmu.direct_map &&
-	      work->arch.cr3 != vcpu->arch.mmu.get_cr3(vcpu))
+	if (!vcpu->arch.mmu->direct_map &&
+	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu.page_fault(vcpu, work->gva, 0, true);
+	vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
@@ -9421,6 +10044,36 @@
 				      sizeof(u32));
 }
 
+static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
+		return false;
+
+	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) ||
+	    (vcpu->arch.apf.send_user_only &&
+	     kvm_x86_ops->get_cpl(vcpu) == 0))
+		return false;
+
+	return true;
+}
+
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(!lapic_in_kernel(vcpu) ||
+		     kvm_event_needs_reinjection(vcpu) ||
+		     vcpu->arch.exception.pending))
+		return false;
+
+	if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu))
+		return false;
+
+	/*
+	 * If interrupts are off we cannot even use an artificial
+	 * halt state.
+	 */
+	return kvm_x86_ops->interrupt_allowed(vcpu);
+}
+
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work)
 {
@@ -9429,11 +10082,8 @@
 	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
-	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) ||
-	    (vcpu->arch.apf.send_user_only &&
-	     kvm_x86_ops->get_cpl(vcpu) == 0))
-		kvm_make_request(KVM_REQ_APF_HALT, vcpu);
-	else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) {
+	if (kvm_can_deliver_async_pf(vcpu) &&
+	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) {
 		fault.vector = PF_VECTOR;
 		fault.error_code_valid = true;
 		fault.error_code = 0;
@@ -9441,6 +10091,16 @@
 		fault.address = work->arch.token;
 		fault.async_page_fault = true;
 		kvm_inject_page_fault(vcpu, &fault);
+	} else {
+		/*
+		 * It is not possible to deliver a paravirtualized asynchronous
+		 * page fault, but putting the guest in an artificial halt state
+		 * can be beneficial nevertheless: if an interrupt arrives, we
+		 * can deliver it timely and perhaps the guest will schedule
+		 * another process.  When the instruction that triggered a page
+		 * fault is retried, hopefully the page will be ready in the host.
+		 */
+		kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 	}
 }
 
@@ -9467,6 +10127,8 @@
 			vcpu->arch.exception.nr = 0;
 			vcpu->arch.exception.has_error_code = false;
 			vcpu->arch.exception.error_code = 0;
+			vcpu->arch.exception.has_payload = false;
+			vcpu->arch.exception.payload = 0;
 		} else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
 			fault.vector = PF_VECTOR;
 			fault.error_code_valid = true;
@@ -9527,7 +10189,7 @@
 
 bool kvm_arch_has_irq_bypass(void)
 {
-	return kvm_x86_ops->update_pi_irte != NULL;
+	return true;
 }
 
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
@@ -9567,9 +10229,6 @@
 int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 				   uint32_t guest_irq, bool set)
 {
-	if (!kvm_x86_ops->update_pi_irte)
-		return -EINVAL;
-
 	return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set);
 }
 
@@ -9579,6 +10238,13 @@
 }
 EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
 
+bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.msr_kvm_poll_control & 1) == 0;
+}
+EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
+
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
@@ -9589,11 +10255,12 @@
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter_failed);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
-EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 67b9568..dbf7442 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -139,6 +139,11 @@
 	return likely(kvm_read_cr0_bits(vcpu, X86_CR0_PG));
 }
 
+static inline bool is_pae_paging(struct kvm_vcpu *vcpu)
+{
+	return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu);
+}
+
 static inline u32 bit(int bitno)
 {
 	return 1 << (bitno & 31);
@@ -181,14 +186,19 @@
 static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
 					gva_t gva, gfn_t gfn, unsigned access)
 {
+	u64 gen = kvm_memslots(vcpu->kvm)->generation;
+
+	if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS))
+		return;
+
 	/*
 	 * If this is a shadow nested page table, the "GVA" is
 	 * actually a nGPA.
 	 */
 	vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK;
-	vcpu->arch.access = access;
+	vcpu->arch.mmio_access = access;
 	vcpu->arch.mmio_gfn = gfn;
-	vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
+	vcpu->arch.mmio_gen = gen;
 }
 
 static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
@@ -251,7 +261,7 @@
 }
 
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
-int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
+void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 
 void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr);
 u64 get_kvmclock_ns(struct kvm *kvm);
@@ -266,6 +276,8 @@
 
 int handle_ud(struct kvm_vcpu *vcpu);
 
+void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu);
+
 void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
 u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data);
@@ -287,10 +299,10 @@
 
 extern unsigned int min_timer_period_us;
 
-extern unsigned int lapic_timer_advance_ns;
-
 extern bool enable_vmware_backdoor;
 
+extern int pi_inject_timer;
+
 extern struct static_key kvm_no_apic_vcpu;
 
 static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
@@ -328,6 +340,11 @@
 	return kvm->arch.pause_in_guest;
 }
 
+static inline bool kvm_cstate_in_guest(struct kvm *kvm)
+{
+	return kvm->arch.cstate_in_guest;
+}
+
 DECLARE_PER_CPU(struct kvm_vcpu *, current_vcpu);
 
 static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu)
@@ -340,4 +357,16 @@
 	__this_cpu_write(current_vcpu, NULL);
 }
 
+
+static inline bool kvm_pat_valid(u64 data)
+{
+	if (data & 0xF8F8F8F8F8F8F8F8ull)
+		return false;
+	/* 0, 1, 4, 5, 6, 7 are valid values.  */
+	return (data | ((data & 0x0202020202020202ull) << 1)) == data;
+}
+
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
+
 #endif