1 files changed, 321 insertions, 144 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index d05ddf751491..5504d9e9fd32 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -7,15 +7,16 @@
 #include <asm/debugreg.h>
 #include <asm/mmu_context.h>
 
+#include "x86.h"
 #include "cpuid.h"
 #include "hyperv.h"
 #include "mmu.h"
 #include "nested.h"
 #include "pmu.h"
+#include "posted_intr.h"
 #include "sgx.h"
 #include "trace.h"
 #include "vmx.h"
-#include "x86.h"
 #include "smm.h"
 
 static bool __read_mostly enable_shadow_vmcs = 1;
@@ -230,11 +231,8 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (nested_vmx_is_evmptr12_valid(vmx)) {
-		kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
-		vmx->nested.hv_evmcs = NULL;
-	}
-
+	kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map);
+	vmx->nested.hv_evmcs = NULL;
 	vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
 
 	if (hv_vcpu) {
@@ -259,7 +257,7 @@ static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr)
 	 * state. It is possible that the area will stay mapped as
 	 * vmx->nested.hv_evmcs but this shouldn't be a problem.
 	 */
-	if (!guest_cpuid_has_evmcs(vcpu) ||
+	if (!guest_cpu_cap_has_evmcs(vcpu) ||
 	    !evmptr_is_valid(nested_get_evmptr(vcpu)))
 		return false;
 
@@ -316,6 +314,16 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 	vcpu->arch.regs_dirty = 0;
 }
 
+static void nested_put_vmcs12_pages(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map);
+	vmx->nested.pi_desc = NULL;
+}
+
 /*
  * Free whatever needs to be freed from vmx->nested when L1 goes down, or
  * just stops using VMX.
@@ -348,15 +356,8 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	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.  The APIC access
-	 * page's backing page (yeah, confusing) shouldn't actually be accessed,
-	 * and if it is written, the contents are irrelevant.
-	 */
-	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
-	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;
+
+	nested_put_vmcs12_pages(vcpu);
 
 	kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
 
@@ -409,18 +410,40 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long exit_qualification;
 	u32 vm_exit_reason;
-	unsigned long exit_qualification = vcpu->arch.exit_qualification;
 
 	if (vmx->nested.pml_full) {
 		vm_exit_reason = EXIT_REASON_PML_FULL;
 		vmx->nested.pml_full = false;
-		exit_qualification &= INTR_INFO_UNBLOCK_NMI;
+
+		/*
+		 * It should be impossible to trigger a nested PML Full VM-Exit
+		 * for anything other than an EPT Violation from L2.  KVM *can*
+		 * trigger nEPT page fault injection in response to an EPT
+		 * Misconfig, e.g. if the MMIO SPTE was stale and L1's EPT
+		 * tables also changed, but KVM should not treat EPT Misconfig
+		 * VM-Exits as writes.
+		 */
+		WARN_ON_ONCE(vmx->exit_reason.basic != EXIT_REASON_EPT_VIOLATION);
+
+		/*
+		 * PML Full and EPT Violation VM-Exits both use bit 12 to report
+		 * "NMI unblocking due to IRET", i.e. the bit can be propagated
+		 * as-is from the original EXIT_QUALIFICATION.
+		 */
+		exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI;
 	} else {
-		if (fault->error_code & PFERR_RSVD_MASK)
+		if (fault->error_code & PFERR_RSVD_MASK) {
 			vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
-		else
+			exit_qualification = 0;
+		} else {
+			exit_qualification = fault->exit_qualification;
+			exit_qualification |= vmx_get_exit_qual(vcpu) &
+					      (EPT_VIOLATION_GVA_IS_VALID |
+					       EPT_VIOLATION_GVA_TRANSLATED);
 			vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+		}
 
 		/*
 		 * Although the caller (kvm_inject_emulated_page_fault) would
@@ -601,7 +624,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	int msr;
 	unsigned long *msr_bitmap_l1;
 	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
-	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;
+	struct kvm_host_map map;
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
 	if (!cpu_has_vmx_msr_bitmap() ||
@@ -624,10 +647,10 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 			return true;
 	}
 
-	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
+	if (kvm_vcpu_map_readonly(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), &map))
 		return false;
 
-	msr_bitmap_l1 = (unsigned long *)map->hva;
+	msr_bitmap_l1 = (unsigned long *)map.hva;
 
 	/*
 	 * To keep the control flow simple, pay eight 8-byte writes (sixteen
@@ -691,7 +714,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
 					 MSR_IA32_FLUSH_CMD, MSR_TYPE_W);
 
-	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);
+	kvm_vcpu_unmap(vcpu, &map);
 
 	vmx->nested.force_msr_bitmap_recalc = false;
 
@@ -958,7 +981,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 				__func__, i, e.index, e.reserved);
 			goto fail;
 		}
-		if (kvm_set_msr(vcpu, e.index, e.value)) {
+		if (kvm_set_msr_with_filter(vcpu, e.index, e.value)) {
 			pr_debug_ratelimited(
 				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
 				__func__, i, e.index, e.value);
@@ -994,7 +1017,7 @@ static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu,
 		}
 	}
 
-	if (kvm_get_msr(vcpu, msr_index, data)) {
+	if (kvm_get_msr_with_filter(vcpu, msr_index, data)) {
 		pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__,
 			msr_index);
 		return false;
@@ -1089,9 +1112,9 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
 			/*
 			 * Emulated VMEntry does not fail here.  Instead a less
 			 * accurate value will be returned by
-			 * nested_vmx_get_vmexit_msr_value() using kvm_get_msr()
-			 * instead of reading the value from the vmcs02 VMExit
-			 * MSR-store area.
+			 * nested_vmx_get_vmexit_msr_value() by reading KVM's
+			 * internal MSR state instead of reading the value from
+			 * the vmcs02 VMExit MSR-store area.
 			 */
 			pr_warn_ratelimited(
 				"Not enough msr entries in msr_autostore.  Can't add msr %x\n",
@@ -1174,11 +1197,14 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept);
 
 	/*
-	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
-	 * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a
-	 * full TLB flush from the guest's perspective.  This is required even
-	 * if VPID is disabled in the host as KVM may need to synchronize the
-	 * MMU in response to the guest TLB flush.
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host, and so architecturally, linear and combined
+	 * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit.  KVM
+	 * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2,
+	 * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01.  This
+	 * is required if VPID is disabled in KVM, as a TLB flush (there are no
+	 * VPIDs) still occurs from L1's perspective, and KVM may need to
+	 * synchronize the MMU in response to the guest TLB flush.
 	 *
 	 * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use.
 	 * EPT is a special snowflake, as guest-physical mappings aren't
@@ -1228,21 +1254,32 @@ static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
 
 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);
+	const u64 feature_bits = VMX_BASIC_DUAL_MONITOR_TREATMENT |
+				 VMX_BASIC_INOUT |
+				 VMX_BASIC_TRUE_CTLS;
+
+	const u64 reserved_bits = GENMASK_ULL(63, 56) |
+				  GENMASK_ULL(47, 45) |
+				  BIT_ULL(31);
+
 	u64 vmx_basic = vmcs_config.nested.basic;
 
-	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
+	BUILD_BUG_ON(feature_bits & reserved_bits);
+
+	/*
+	 * Except for 32BIT_PHYS_ADDR_ONLY, which is an anti-feature bit (has
+	 * inverted polarity), the incoming value must not set feature bits or
+	 * reserved bits that aren't allowed/supported by KVM.  Fields, i.e.
+	 * multi-bit values, are explicitly checked below.
+	 */
+	if (!is_bitwise_subset(vmx_basic, data, feature_bits | reserved_bits))
 		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))
+	if (data & VMX_BASIC_32BIT_PHYS_ADDR_ONLY)
 		return -EINVAL;
 
 	if (vmx_basic_vmcs_revision_id(vmx_basic) !=
@@ -1311,16 +1348,29 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
 
 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);
+	const u64 feature_bits = VMX_MISC_SAVE_EFER_LMA |
+				 VMX_MISC_ACTIVITY_HLT |
+				 VMX_MISC_ACTIVITY_SHUTDOWN |
+				 VMX_MISC_ACTIVITY_WAIT_SIPI |
+				 VMX_MISC_INTEL_PT |
+				 VMX_MISC_RDMSR_IN_SMM |
+				 VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
+				 VMX_MISC_VMXOFF_BLOCK_SMI |
+				 VMX_MISC_ZERO_LEN_INS;
+
+	const u64 reserved_bits = BIT_ULL(31) | GENMASK_ULL(13, 9);
+
 	u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low,
 				       vmcs_config.nested.misc_high);
 
-	if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
+	BUILD_BUG_ON(feature_bits & reserved_bits);
+
+	/*
+	 * The incoming value must not set feature bits or reserved bits that
+	 * aren't allowed/supported by KVM.  Fields, i.e. multi-bit values, are
+	 * explicitly checked below.
+	 */
+	if (!is_bitwise_subset(vmx_misc, data, feature_bits | reserved_bits))
 		return -EINVAL;
 
 	if ((vmx->nested.msrs.pinbased_ctls_high &
@@ -2039,7 +2089,7 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
 	bool evmcs_gpa_changed = false;
 	u64 evmcs_gpa;
 
-	if (likely(!guest_cpuid_has_evmcs(vcpu)))
+	if (likely(!guest_cpu_cap_has_evmcs(vcpu)))
 		return EVMPTRLD_DISABLED;
 
 	evmcs_gpa = nested_get_evmptr(vcpu);
@@ -2220,6 +2270,9 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
 		vmcs_write64(EPT_POINTER,
 			     construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));
 
+	if (vmx->ve_info)
+		vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info));
+
 	/* All VMFUNCs are currently emulated through L0 vmexits.  */
 	if (cpu_has_vmx_vmfunc())
 		vmcs_write64(VM_FUNCTION_CONTROL, 0);
@@ -2265,6 +2318,17 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
 
 	vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA);
 
+	/*
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host.  Emulate this behavior by using vpid01 for L2
+	 * if VPID is disabled in vmcs12.  Note, if VPID is disabled, VM-Enter
+	 * and VM-Exit are architecturally required to flush VPID=0, but *only*
+	 * VPID=0.  I.e. using vpid02 would be ok (so long as KVM emulates the
+	 * required flushes), but doing so would cause KVM to over-flush.  E.g.
+	 * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled,
+	 * and then runs L2 X again, then KVM can and should retain TLB entries
+	 * for VPID12=1.
+	 */
 	if (enable_vpid) {
 		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
 			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
@@ -2291,10 +2355,12 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 
 	/* Posted interrupts setting is only taken from vmcs12.  */
 	vmx->nested.pi_pending = false;
-	if (nested_cpu_has_posted_intr(vmcs12))
+	if (nested_cpu_has_posted_intr(vmcs12)) {
 		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
-	else
+	} else {
+		vmx->nested.posted_intr_nv = -1;
 		exec_control &= ~PIN_BASED_POSTED_INTR;
+	}
 	pin_controls_set(vmx, exec_control);
 
 	/*
@@ -2400,7 +2466,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 	if (cpu_has_load_ia32_efer()) {
 		if (guest_efer & EFER_LMA)
 			exec_control |= VM_ENTRY_IA32E_MODE;
-		if (guest_efer != host_efer)
+		if (guest_efer != kvm_host.efer)
 			exec_control |= VM_ENTRY_LOAD_IA32_EFER;
 	}
 	vm_entry_controls_set(vmx, exec_control);
@@ -2413,7 +2479,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 	 * bits may be modified by vmx_set_efer() in prepare_vmcs02().
 	 */
 	exec_control = __vm_exit_controls_get(vmcs01);
-	if (cpu_has_load_ia32_efer() && guest_efer != host_efer)
+	if (cpu_has_load_ia32_efer() && guest_efer != kvm_host.efer)
 		exec_control |= VM_EXIT_LOAD_IA32_EFER;
 	else
 		exec_control &= ~VM_EXIT_LOAD_IA32_EFER;
@@ -2444,6 +2510,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 
 	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);
@@ -2481,7 +2548,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
 		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
 
-		vmx->segment_cache.bitmask = 0;
+		vmx_segment_cache_clear(vmx);
 	}
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
@@ -2903,7 +2970,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
 		case INTR_TYPE_SOFT_EXCEPTION:
 		case INTR_TYPE_SOFT_INTR:
 		case INTR_TYPE_PRIV_SW_EXCEPTION:
-			if (CC(vmcs12->vm_entry_instruction_len > 15) ||
+			if (CC(vmcs12->vm_entry_instruction_len > X86_MAX_INSTRUCTION_LENGTH) ||
 			    CC(vmcs12->vm_entry_instruction_len == 0 &&
 			    CC(!nested_cpu_has_zero_length_injection(vcpu))))
 				return -EINVAL;
@@ -2925,7 +2992,7 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 #ifdef CONFIG_KVM_HYPERV
-	if (guest_cpuid_has_evmcs(vcpu))
+	if (guest_cpu_cap_has_evmcs(vcpu))
 		return nested_evmcs_check_controls(vmcs12);
 #endif
 
@@ -2943,6 +3010,17 @@ static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static bool is_l1_noncanonical_address_on_vmexit(u64 la, struct vmcs12 *vmcs12)
+{
+	/*
+	 * Check that the given linear address is canonical after a VM exit
+	 * from L2, based on HOST_CR4.LA57 value that will be loaded for L1.
+	 */
+	u8 l1_address_bits_on_exit = (vmcs12->host_cr4 & X86_CR4_LA57) ? 57 : 48;
+
+	return !__is_canonical_address(la, l1_address_bits_on_exit);
+}
+
 static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
@@ -2953,8 +3031,8 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(!kvm_vcpu_is_legal_cr3(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)))
+	if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
+	    CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
 		return -EINVAL;
 
 	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) &&
@@ -2988,12 +3066,12 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(vmcs12->host_ss_selector == 0 && !ia32e))
 		return -EINVAL;
 
-	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)))
+	if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) ||
+	    CC(is_l1_noncanonical_address_on_vmexit(vmcs12->host_rip, vmcs12)))
 		return -EINVAL;
 
 	/*
@@ -3111,7 +3189,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	}
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
-	    (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
+	    (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
 	     CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD))))
 		return -EINVAL;
 
@@ -3209,7 +3287,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
 	 * L2 was running), map it here to make sure vmcs12 changes are
 	 * properly reflected.
 	 */
-	if (guest_cpuid_has_evmcs(vcpu) &&
+	if (guest_cpu_cap_has_evmcs(vcpu) &&
 	    vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) {
 		enum nested_evmptrld_status evmptrld_status =
 			nested_vmx_handle_enlightened_vmptrld(vcpu, false);
@@ -3364,7 +3442,7 @@ static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 	if (!nested_cpu_has_pml(vmcs12))
 		return 0;
 
-	if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
+	if (vmcs12->guest_pml_index >= PML_LOG_NR_ENTRIES) {
 		vmx->nested.pml_full = true;
 		return 1;
 	}
@@ -3403,14 +3481,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
 	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);
 
@@ -3430,7 +3500,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	enum vm_entry_failure_code entry_failure_code;
-	bool evaluate_pending_interrupts;
 	union vmx_exit_reason exit_reason = {
 		.basic = EXIT_REASON_INVALID_STATE,
 		.failed_vmentry = 1,
@@ -3449,13 +3518,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 
 	kvm_service_local_tlb_flush_requests(vcpu);
 
-	evaluate_pending_interrupts = exec_controls_get(vmx) &
-		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
-	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
-		evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
-	if (!evaluate_pending_interrupts)
-		evaluate_pending_interrupts |= kvm_apic_has_pending_init_or_sipi(vcpu);
-
 	if (!vmx->nested.nested_run_pending ||
 	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
 		vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
@@ -3538,9 +3600,13 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	 * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI
 	 * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can
 	 * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit
-	 * unconditionally.
+	 * unconditionally.  Take care to pull data from vmcs01 as appropriate,
+	 * e.g. when checking for interrupt windows, as vmcs02 is now loaded.
 	 */
-	if (unlikely(evaluate_pending_interrupts))
+	if ((__exec_controls_get(&vmx->vmcs01) & (CPU_BASED_INTR_WINDOW_EXITING |
+						  CPU_BASED_NMI_WINDOW_EXITING)) ||
+	    kvm_apic_has_pending_init_or_sipi(vcpu) ||
+	    kvm_apic_has_interrupt(vcpu))
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	/*
@@ -3673,14 +3739,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (unlikely(status != NVMX_VMENTRY_SUCCESS))
 		goto vmentry_failed;
 
-	/* Emulate processing of posted interrupts on VM-Enter. */
-	if (nested_cpu_has_posted_intr(vmcs12) &&
-	    kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) {
-		vmx->nested.pi_pending = true;
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
-		kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv);
-	}
-
 	/* Hide L1D cache contents from the nested guest.  */
 	vmx->vcpu.arch.l1tf_flush_l1d = true;
 
@@ -3713,7 +3771,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		break;
 	case GUEST_ACTIVITY_WAIT_SIPI:
 		vmx->nested.nested_run_pending = 0;
-		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED);
 		break;
 	default:
 		break;
@@ -3874,8 +3932,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
 		return 0;
 
-	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
-	if (max_irr != 256) {
+	max_irr = pi_find_highest_vector(vmx->nested.pi_desc);
+	if (max_irr > 0) {
 		vapic_page = vmx->nested.virtual_apic_map.hva;
 		if (!vapic_page)
 			goto mmio_needed;
@@ -4006,10 +4064,46 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
 	       to_vmx(vcpu)->nested.preemption_timer_expired;
 }
 
-static bool vmx_has_nested_events(struct kvm_vcpu *vcpu)
+static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection)
 {
-	return nested_vmx_preemption_timer_pending(vcpu) ||
-	       to_vmx(vcpu)->nested.mtf_pending;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	void *vapic = vmx->nested.virtual_apic_map.hva;
+	int max_irr, vppr;
+
+	if (nested_vmx_preemption_timer_pending(vcpu) ||
+	    vmx->nested.mtf_pending)
+		return true;
+
+	/*
+	 * Virtual Interrupt Delivery doesn't require manual injection.  Either
+	 * the interrupt is already in GUEST_RVI and will be recognized by CPU
+	 * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move
+	 * the interrupt from the PIR to RVI prior to entering the guest.
+	 */
+	if (for_injection)
+		return false;
+
+	if (!nested_cpu_has_vid(get_vmcs12(vcpu)) ||
+	    __vmx_interrupt_blocked(vcpu))
+		return false;
+
+	if (!vapic)
+		return false;
+
+	vppr = *((u32 *)(vapic + APIC_PROCPRI));
+
+	max_irr = vmx_get_rvi();
+	if ((max_irr & 0xf0) > (vppr & 0xf0))
+		return true;
+
+	if (vmx->nested.pi_pending && vmx->nested.pi_desc &&
+	    pi_test_on(vmx->nested.pi_desc)) {
+		max_irr = pi_find_highest_vector(vmx->nested.pi_desc);
+		if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0))
+			return true;
+	}
+
+	return false;
 }
 
 /*
@@ -4106,13 +4200,25 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 	 */
 	bool block_nested_exceptions = vmx->nested.nested_run_pending;
 	/*
-	 * New events (not exceptions) are only recognized at instruction
+	 * Events that don't require injection, i.e. that are virtualized by
+	 * hardware, aren't blocked by a pending VM-Enter as KVM doesn't need
+	 * to regain control in order to deliver the event, and hardware will
+	 * handle event ordering, e.g. with respect to injected exceptions.
+	 *
+	 * But, new events (not exceptions) are only recognized at instruction
 	 * boundaries.  If an event needs reinjection, then KVM is handling a
-	 * VM-Exit that occurred _during_ instruction execution; new events are
-	 * blocked until the instruction completes.
+	 * VM-Exit that occurred _during_ instruction execution; new events,
+	 * irrespective of whether or not they're injected, are blocked until
+	 * the instruction completes.
+	 */
+	bool block_non_injected_events = kvm_event_needs_reinjection(vcpu);
+	/*
+	 * Inject events are blocked by nested VM-Enter, as KVM is responsible
+	 * for managing priority between concurrent events, i.e. KVM needs to
+	 * wait until after VM-Enter completes to deliver injected events.
 	 */
 	bool block_nested_events = block_nested_exceptions ||
-				   kvm_event_needs_reinjection(vcpu);
+				   block_non_injected_events;
 
 	if (lapic_in_kernel(vcpu) &&
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
@@ -4222,11 +4328,71 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 	}
 
 	if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) {
+		int irq;
+
+		if (!nested_exit_on_intr(vcpu)) {
+			if (block_nested_events)
+				return -EBUSY;
+
+			goto no_vmexit;
+		}
+
+		if (!nested_exit_intr_ack_set(vcpu)) {
+			if (block_nested_events)
+				return -EBUSY;
+
+			nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
+			return 0;
+		}
+
+		irq = kvm_cpu_get_extint(vcpu);
+		if (irq != -1) {
+			if (block_nested_events)
+				return -EBUSY;
+
+			nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT,
+					  INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0);
+			return 0;
+		}
+
+		irq = kvm_apic_has_interrupt(vcpu);
+		if (WARN_ON_ONCE(irq < 0))
+			goto no_vmexit;
+
+		/*
+		 * If the IRQ is L2's PI notification vector, process posted
+		 * interrupts for L2 instead of injecting VM-Exit, as the
+		 * detection/morphing architecturally occurs when the IRQ is
+		 * delivered to the CPU.  Note, only interrupts that are routed
+		 * through the local APIC trigger posted interrupt processing,
+		 * and enabling posted interrupts requires ACK-on-exit.
+		 */
+		if (irq == vmx->nested.posted_intr_nv) {
+			/*
+			 * Nested posted interrupts are delivered via RVI, i.e.
+			 * aren't injected by KVM, and so can be queued even if
+			 * manual event injection is disallowed.
+			 */
+			if (block_non_injected_events)
+				return -EBUSY;
+
+			vmx->nested.pi_pending = true;
+			kvm_apic_clear_irr(vcpu, irq);
+			goto no_vmexit;
+		}
+
 		if (block_nested_events)
 			return -EBUSY;
-		if (!nested_exit_on_intr(vcpu))
-			goto no_vmexit;
-		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
+
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT,
+				  INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0);
+
+		/*
+		 * ACK the interrupt _after_ emulating VM-Exit, as the IRQ must
+		 * be marked as in-service in vmcs01.GUEST_INTERRUPT_STATUS.SVI
+		 * if APICv is active.
+		 */
+		kvm_apic_ack_interrupt(vcpu, irq);
 		return 0;
 	}
 
@@ -4452,7 +4618,7 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
  */
 static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			   u32 vm_exit_reason, u32 exit_intr_info,
-			   unsigned long exit_qualification)
+			   unsigned long exit_qualification, u32 exit_insn_len)
 {
 	/* update exit information fields: */
 	vmcs12->vm_exit_reason = vm_exit_reason;
@@ -4480,7 +4646,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 					  vm_exit_reason, exit_intr_info);
 
 		vmcs12->vm_exit_intr_info = exit_intr_info;
-		vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		vmcs12->vm_exit_instruction_len = exit_insn_len;
 		vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 
 		/*
@@ -4640,7 +4806,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
 		return vmcs_read64(GUEST_IA32_EFER);
 
 	if (cpu_has_load_ia32_efer())
-		return host_efer;
+		return kvm_host.efer;
 
 	for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) {
 		if (vmx->msr_autoload.guest.val[i].index == MSR_EFER)
@@ -4651,7 +4817,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
 	if (efer_msr)
 		return efer_msr->data;
 
-	return host_efer;
+	return kvm_host.efer;
 }
 
 static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
@@ -4744,7 +4910,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 				goto vmabort;
 			}
 
-			if (kvm_set_msr(vcpu, h.index, h.value)) {
+			if (kvm_set_msr_with_filter(vcpu, h.index, h.value)) {
 				pr_debug_ratelimited(
 					"%s WRMSR failed (%u, 0x%x, 0x%llx)\n",
 					__func__, j, h.index, h.value);
@@ -4764,8 +4930,9 @@ vmabort:
  * 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 vm_exit_reason,
-		       u32 exit_intr_info, unsigned long exit_qualification)
+void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
+			 u32 exit_intr_info, unsigned long exit_qualification,
+			 u32 exit_insn_len)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -4815,7 +4982,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		if (vm_exit_reason != -1)
 			prepare_vmcs12(vcpu, vmcs12, vm_exit_reason,
-				       exit_intr_info, exit_qualification);
+				       exit_intr_info, exit_qualification,
+				       exit_insn_len);
 
 		/*
 		 * Must happen outside of sync_vmcs02_to_vmcs12() as it will
@@ -4860,7 +5028,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	 * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
 	 * separate modes for L2 vs L1.
 	 */
-	if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL))
 		indirect_branch_prediction_barrier();
 
 	/* Update any VMCS fields that might have changed while L2 ran */
@@ -4883,11 +5051,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		vmx_update_cpu_dirty_logging(vcpu);
 	}
 
-	/* Unpin physical memory we referred to in vmcs02 */
-	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
-	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;
+	nested_put_vmcs12_pages(vcpu);
 
 	if (vmx->nested.reload_vmcs01_apic_access_page) {
 		vmx->nested.reload_vmcs01_apic_access_page = false;
@@ -4899,22 +5063,19 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
 	}
 
+	if (vmx->nested.update_vmcs01_hwapic_isr) {
+		vmx->nested.update_vmcs01_hwapic_isr = false;
+		kvm_apic_update_hwapic_isr(vcpu);
+	}
+
 	if ((vm_exit_reason != -1) &&
 	    (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)))
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
 
 	/* in case we halted in L2 */
-	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 
 	if (likely(!vmx->fail)) {
-		if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
-		    nested_exit_intr_ack_set(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 (vm_exit_reason != -1)
 			trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
 						       vmcs12->exit_qualification,
@@ -4925,6 +5086,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		load_vmcs12_host_state(vcpu, vmcs12);
 
+		/*
+		 * Process events if an injectable IRQ or NMI is pending, even
+		 * if the event is blocked (RFLAGS.IF is cleared on VM-Exit).
+		 * If an event became pending while L2 was active, KVM needs to
+		 * either inject the event or request an IRQ/NMI window.  SMIs
+		 * don't need to be processed as SMM is mutually exclusive with
+		 * non-root mode.  INIT/SIPI don't need to be checked as INIT
+		 * is blocked post-VMXON, and SIPIs are ignored.
+		 */
+		if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 		return;
 	}
 
@@ -5031,7 +5203,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 		 * non-canonical form. This is the only check on the memory
 		 * destination for long mode!
 		 */
-		exn = is_noncanonical_address(*ret, vcpu);
+		exn = is_noncanonical_address(*ret, vcpu, 0);
 	} else {
 		/*
 		 * When not in long mode, the virtual/linear address is
@@ -5157,9 +5329,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu))
 		goto out_shadow_vmcs;
 
-	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_PINNED);
-	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
+	hrtimer_setup(&vmx->nested.preemption_timer, vmx_preemption_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED);
 
 	vmx->nested.vpid02 = allocate_vpid();
 
@@ -5828,6 +5999,12 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		return nested_vmx_fail(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 
+	/*
+	 * Always flush the effective vpid02, i.e. never flush the current VPID
+	 * and never explicitly flush vpid01.  INVVPID targets a VPID, not a
+	 * VMCS, and so whether or not the current vmcs12 has VPID enabled is
+	 * irrelevant (and there may not be a loaded vmcs12).
+	 */
 	vpid02 = nested_get_vpid02(vcpu);
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
@@ -5836,7 +6013,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		 * invalidation.
 		 */
 		if (!operand.vpid ||
-		    is_noncanonical_address(operand.gla, vcpu))
+		    is_noncanonical_invlpg_address(operand.gla, vcpu))
 			return nested_vmx_fail(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		vpid_sync_vcpu_addr(vpid02, operand.gla);
@@ -6130,7 +6307,7 @@ static bool nested_vmx_exit_handled_encls(struct kvm_vcpu *vcpu,
 {
 	u32 encls_leaf;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_SGX) ||
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) ||
 	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENCLS_EXITING))
 		return false;
 
@@ -6208,6 +6385,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 		else if (is_alignment_check(intr_info) &&
 			 !vmx_guest_inject_ac(vcpu))
 			return true;
+		else if (is_ve_fault(intr_info))
+			return true;
 		return false;
 	case EXIT_REASON_EXTERNAL_INTERRUPT:
 		return true;
@@ -6466,7 +6645,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 	vmx = to_vmx(vcpu);
 	vmcs12 = get_vmcs12(vcpu);
 
-	if (guest_can_use(vcpu, X86_FEATURE_VMX) &&
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) &&
 	    (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;
@@ -6607,7 +6786,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS)
 			return -EINVAL;
 	} else {
-		if (!guest_can_use(vcpu, X86_FEATURE_VMX))
+		if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX))
 			return -EINVAL;
 
 		if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa))
@@ -6641,7 +6820,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) &&
-	    (!guest_can_use(vcpu, X86_FEATURE_VMX) ||
+	    (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) ||
 	     !vmx->nested.enlightened_vmcs_enabled))
 			return -EINVAL;
 
@@ -6987,7 +7166,7 @@ static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf,
 {
 	msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA;
 	msrs->misc_low |=
-		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
+		VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
 		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
 		VMX_MISC_ACTIVITY_HLT |
 		VMX_MISC_ACTIVITY_WAIT_SIPI;
@@ -7002,12 +7181,10 @@ static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs)
 	 * 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);
+	msrs->basic = vmx_basic_encode_vmcs_info(VMCS12_REVISION, VMCS12_SIZE,
+						 X86_MEMTYPE_WB);
 
+	msrs->basic |= VMX_BASIC_TRUE_CTLS;
 	if (cpu_has_vmx_basic_inout())
 		msrs->basic |= VMX_BASIC_INOUT;
 }