Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - GICv4.1 support

   - 32bit host removal

  PPC:
   - secure (encrypted) using under the Protected Execution Framework
     ultravisor

  s390:
   - allow disabling GISA (hardware interrupt injection) and protected
     VMs/ultravisor support.

  x86:
   - New dirty bitmap flag that sets all bits in the bitmap when dirty
     page logging is enabled; this is faster because it doesn't require
     bulk modification of the page tables.

   - Initial work on making nested SVM event injection more similar to
     VMX, and less buggy.

   - Various cleanups to MMU code (though the big ones and related
     optimizations were delayed to 5.8). Instead of using cr3 in
     function names which occasionally means eptp, KVM too has
     standardized on "pgd".

   - A large refactoring of CPUID features, which now use an array that
     parallels the core x86_features.

   - Some removal of pointer chasing from kvm_x86_ops, which will also
     be switched to static calls as soon as they are available.

   - New Tigerlake CPUID features.

   - More bugfixes, optimizations and cleanups.

  Generic:
   - selftests: cleanups, new MMU notifier stress test, steal-time test

   - CSV output for kvm_stat"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (277 commits)
  x86/kvm: fix a missing-prototypes "vmread_error"
  KVM: x86: Fix BUILD_BUG() in __cpuid_entry_get_reg() w/ CONFIG_UBSAN=y
  KVM: VMX: Add a trampoline to fix VMREAD error handling
  KVM: SVM: Annotate svm_x86_ops as __initdata
  KVM: VMX: Annotate vmx_x86_ops as __initdata
  KVM: x86: Drop __exit from kvm_x86_ops' hardware_unsetup()
  KVM: x86: Copy kvm_x86_ops by value to eliminate layer of indirection
  KVM: x86: Set kvm_x86_ops only after ->hardware_setup() completes
  KVM: VMX: Configure runtime hooks using vmx_x86_ops
  KVM: VMX: Move hardware_setup() definition below vmx_x86_ops
  KVM: x86: Move init-only kvm_x86_ops to separate struct
  KVM: Pass kvm_init()'s opaque param to additional arch funcs
  s390/gmap: return proper error code on ksm unsharing
  KVM: selftests: Fix cosmetic copy-paste error in vm_mem_region_move()
  KVM: Fix out of range accesses to memslots
  KVM: X86: Micro-optimize IPI fastpath delay
  KVM: X86: Delay read msr data iff writes ICR MSR
  KVM: PPC: Book3S HV: Add a capability for enabling secure guests
  KVM: arm64: GICv4.1: Expose HW-based SGIs in debugfs
  KVM: arm64: GICv4.1: Allow non-trapping WFI when using HW SGIs
  ...

9 files changed, 551 insertions, 452 deletions

diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index f486e2606247..8903475f751e 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -101,7 +101,7 @@ static inline bool cpu_has_load_perf_global_ctrl(void)
 	       (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
 }
 
-static inline bool vmx_mpx_supported(void)
+static inline bool cpu_has_vmx_mpx(void)
 {
 	return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) &&
 		(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS);
@@ -146,11 +146,6 @@ static inline bool vmx_umip_emulated(void)
 		SECONDARY_EXEC_DESC;
 }
 
-static inline bool vmx_pku_supported(void)
-{
-	return boot_cpu_has(X86_FEATURE_PKU);
-}
-
 static inline bool cpu_has_vmx_rdtscp(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -354,4 +349,22 @@ static inline bool cpu_has_vmx_intel_pt(void)
 		(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL);
 }
 
+/*
+ * Processor Trace can operate in one of three modes:
+ *  a. system-wide: trace both host/guest and output to host buffer
+ *  b. host-only:   only trace host and output to host buffer
+ *  c. host-guest:  trace host and guest simultaneously and output to their
+ *                  respective buffer
+ *
+ * KVM currently only supports (a) and (c).
+ */
+static inline bool vmx_pt_mode_is_system(void)
+{
+	return pt_mode == PT_MODE_SYSTEM;
+}
+static inline bool vmx_pt_mode_is_host_guest(void)
+{
+	return pt_mode == PT_MODE_HOST_GUEST;
+}
+
 #endif /* __KVM_X86_VMX_CAPS_H */
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
index 6de47f2569c9..e5f7a7ebf27d 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -198,6 +198,13 @@ 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) */
 
+enum nested_evmptrld_status {
+	EVMPTRLD_DISABLED,
+	EVMPTRLD_SUCCEEDED,
+	EVMPTRLD_VMFAIL,
+	EVMPTRLD_ERROR,
+};
+
 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,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 9750e590c89d..de232306561a 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -353,9 +353,8 @@ static void nested_ept_init_mmu_context(struct kvm_vcpu *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;
+			nested_ept_get_eptp(vcpu));
+	vcpu->arch.mmu->get_guest_pgd     = nested_ept_get_eptp;
 	vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
 	vcpu->arch.mmu->get_pdptr         = kvm_pdptr_read;
 
@@ -1910,18 +1909,18 @@ static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
  * 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)
+static enum nested_evmptrld_status 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;
+		return EVMPTRLD_DISABLED;
 
 	if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa))
-		return 1;
+		return EVMPTRLD_DISABLED;
 
 	if (unlikely(!vmx->nested.hv_evmcs ||
 		     evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
@@ -1932,7 +1931,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
 
 		if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa),
 				 &vmx->nested.hv_evmcs_map))
-			return 0;
+			return EVMPTRLD_ERROR;
 
 		vmx->nested.hv_evmcs = vmx->nested.hv_evmcs_map.hva;
 
@@ -1961,7 +1960,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
 		if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) &&
 		    (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) {
 			nested_release_evmcs(vcpu);
-			return 0;
+			return EVMPTRLD_VMFAIL;
 		}
 
 		vmx->nested.dirty_vmcs12 = true;
@@ -1990,21 +1989,13 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
 		vmx->nested.hv_evmcs->hv_clean_fields &=
 			~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 
-	return 1;
+	return EVMPTRLD_SUCCEEDED;
 }
 
 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 */
@@ -2475,9 +2466,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			 * 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_LOAD_MMU_PGD. Note that this assumes
 			 * KVM_REQ_TLB_FLUSH is evaluated after
-			 * KVM_REQ_LOAD_CR3 in vcpu_enter_guest().
+			 * KVM_REQ_LOAD_MMU_PGD in vcpu_enter_guest().
 			 */
 			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		}
@@ -2522,7 +2513,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	/*
 	 * Immediately write vmcs02.GUEST_CR3.  It will be propagated to vmcs12
 	 * on nested VM-Exit, which can occur without actually running L2 and
-	 * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with
+	 * thus without hitting vmx_load_mmu_pgd(), e.g. if L1 is entering L2 with
 	 * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the
 	 * transition to HLT instead of running L2.
 	 */
@@ -2564,13 +2555,13 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12)
 	return 0;
 }
 
-static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
+static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 
 	/* Check for memory type validity */
-	switch (address & VMX_EPTP_MT_MASK) {
+	switch (new_eptp & VMX_EPTP_MT_MASK) {
 	case VMX_EPTP_MT_UC:
 		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT)))
 			return false;
@@ -2583,16 +2574,26 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
 		return false;
 	}
 
-	/* only 4 levels page-walk length are valid */
-	if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4))
+	/* Page-walk levels validity. */
+	switch (new_eptp & VMX_EPTP_PWL_MASK) {
+	case VMX_EPTP_PWL_5:
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_5_BIT)))
+			return false;
+		break;
+	case VMX_EPTP_PWL_4:
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_4_BIT)))
+			return false;
+		break;
+	default:
 		return false;
+	}
 
 	/* Reserved bits should not be set */
-	if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f)))
+	if (CC(new_eptp >> maxphyaddr || ((new_eptp >> 7) & 0x1f)))
 		return false;
 
 	/* AD, if set, should be supported */
-	if (address & VMX_EPTP_AD_ENABLE_BIT) {
+	if (new_eptp & VMX_EPTP_AD_ENABLE_BIT) {
 		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT)))
 			return false;
 	}
@@ -2641,7 +2642,7 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	if (nested_cpu_has_ept(vmcs12) &&
-	    CC(!valid_ept_address(vcpu, vmcs12->ept_pointer)))
+	    CC(!nested_vmx_check_eptp(vcpu, vmcs12->ept_pointer)))
 		return -EINVAL;
 
 	if (nested_cpu_has_vmfunc(vmcs12)) {
@@ -2961,7 +2962,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *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.
+	 * be written (by prepare_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);
@@ -3053,6 +3054,27 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 	struct page *page;
 	u64 hpa;
 
+	/*
+	 * 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) {
+		enum nested_evmptrld_status evmptrld_status =
+			nested_vmx_handle_enlightened_vmptrld(vcpu, false);
+
+		if (evmptrld_status == EVMPTRLD_VMFAIL ||
+		    evmptrld_status == EVMPTRLD_ERROR) {
+			pr_debug_ratelimited("%s: enlightened vmptrld failed\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_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		/*
 		 * Translate L1 physical address to host physical
@@ -3316,12 +3338,18 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	enum nvmx_vmentry_status status;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
+	enum nested_evmptrld_status evmptrld_status;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (!nested_vmx_handle_enlightened_vmptrld(vcpu, launch))
+	evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, launch);
+	if (evmptrld_status == EVMPTRLD_ERROR) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
+	} else if (evmptrld_status == EVMPTRLD_VMFAIL) {
+		return nested_vmx_failInvalid(vcpu);
+	}
 
 	if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull)
 		return nested_vmx_failInvalid(vcpu);
@@ -3499,7 +3527,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 }
 
 
-static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	gfn_t gfn;
@@ -3604,7 +3632,7 @@ static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu)
 			    vcpu->arch.exception.payload);
 }
 
-static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
+static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qual;
@@ -3680,8 +3708,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		return 0;
 	}
 
-	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
-	    nested_exit_on_intr(vcpu)) {
+	if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) {
 		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
@@ -4024,7 +4051,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 *
 	 * 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.
+	 * has been set by KVM_REQ_LOAD_MMU_PGD.
 	 */
 	if (enable_vpid &&
 	    (!nested_cpu_has_vpid(vmcs12) || !nested_has_guest_tlb_tag(vcpu))) {
@@ -4329,17 +4356,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	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)) {
+		if (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 |
@@ -4383,7 +4401,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
  * 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.
+ * #UD, #GP, or #SS.
  */
 int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 			u32 vmx_instruction_info, bool wr, int len, gva_t *ret)
@@ -4424,7 +4442,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 	if (base_is_valid)
 		off += kvm_register_read(vcpu, base_reg);
 	if (index_is_valid)
-		off += kvm_register_read(vcpu, index_reg)<<scaling;
+		off += kvm_register_read(vcpu, index_reg) << scaling;
 	vmx_get_segment(vcpu, &s, seg_reg);
 
 	/*
@@ -4517,7 +4535,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
 		return;
 
 	vmx = to_vmx(vcpu);
-	if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) {
+	if (kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) {
 		vmx->nested.msrs.entry_ctls_high |=
 				VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
 		vmx->nested.msrs.exit_ctls_high |=
@@ -4603,7 +4621,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	vmx->nested.vmcs02_initialized = false;
 	vmx->nested.vmxon = true;
 
-	if (pt_mode == PT_MODE_HOST_GUEST) {
+	if (vmx_pt_mode_is_host_guest()) {
 		vmx->pt_desc.guest.ctl = 0;
 		pt_update_intercept_for_msr(vmx);
 	}
@@ -5235,7 +5253,7 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
 				     struct vmcs12 *vmcs12)
 {
 	u32 index = kvm_rcx_read(vcpu);
-	u64 address;
+	u64 new_eptp;
 	bool accessed_dirty;
 	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
 
@@ -5248,23 +5266,23 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
 
 
 	if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT,
-				     &address, index * 8, 8))
+				     &new_eptp, index * 8, 8))
 		return 1;
 
-	accessed_dirty = !!(address & VMX_EPTP_AD_ENABLE_BIT);
+	accessed_dirty = !!(new_eptp & 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))
+	if (vmcs12->ept_pointer != new_eptp) {
+		if (!nested_vmx_check_eptp(vcpu, new_eptp))
 			return 1;
 
 		kvm_mmu_unload(vcpu);
 		mmu->ept_ad = accessed_dirty;
 		mmu->mmu_role.base.ad_disabled = !accessed_dirty;
-		vmcs12->ept_pointer = address;
+		vmcs12->ept_pointer = new_eptp;
 		/*
 		 * TODO: Check what's the correct approach in case
 		 * mmu reload fails. Currently, we just let the next
@@ -5525,8 +5543,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	if (vmx->nested.nested_run_pending)
-		return false;
+	WARN_ON_ONCE(vmx->nested.nested_run_pending);
 
 	if (unlikely(vmx->fail)) {
 		trace_kvm_nested_vmenter_failed(
@@ -5535,19 +5552,6 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 		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,
@@ -5628,7 +5632,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 	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);
+		return nested_cpu_has_mtf(vmcs12);
 	case EXIT_REASON_MONITOR_INSTRUCTION:
 		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
 	case EXIT_REASON_PAUSE_INSTRUCTION:
@@ -5905,10 +5909,12 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		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.
+		 * nested_vmx_handle_enlightened_vmptrld() cannot be called
+		 * directly from here as HV_X64_MSR_VP_ASSIST_PAGE may not be
+		 * restored yet. EVMCS will be mapped from
+		 * nested_get_vmcs12_pages().
 		 */
-		vmx->nested.need_vmcs12_to_shadow_sync = true;
+		kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
 	} else {
 		return -EINVAL;
 	}
@@ -6130,11 +6136,13 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 		/* 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_EPT_PAGE_WALK_4_BIT |
+			VMX_EPT_PAGE_WALK_5_BIT |
+			VMX_EPTP_WB_BIT |
+			VMX_EPT_INVEPT_BIT |
+			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 |
@@ -6233,7 +6241,8 @@ void nested_vmx_hardware_unsetup(void)
 	}
 }
 
-__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
+__init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops,
+				     int (*exit_handlers[])(struct kvm_vcpu *))
 {
 	int i;
 
@@ -6269,12 +6278,12 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 	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;
+	ops->check_nested_events = vmx_check_nested_events;
+	ops->get_nested_state = vmx_get_nested_state;
+	ops->set_nested_state = vmx_set_nested_state;
+	ops->get_vmcs12_pages = nested_get_vmcs12_pages;
+	ops->nested_enable_evmcs = nested_enable_evmcs;
+	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
index 9aeda46f473e..ac56aefa49e3 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -19,7 +19,8 @@ enum nvmx_vmentry_status {
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
 void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
-__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
+__init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops,
+				     int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_set_vmcs_shadowing_bitmap(void);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
 enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
@@ -33,6 +34,7 @@ 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);
 void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu);
+void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu);
 bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
 				 int size);
 
@@ -60,7 +62,7 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu)
 		vmx->nested.hv_evmcs;
 }
 
-static inline unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
+static inline unsigned long nested_ept_get_eptp(struct kvm_vcpu *vcpu)
 {
 	/* return the page table to be shadowed - in our case, EPT12 */
 	return get_vmcs12(vcpu)->ept_pointer;
@@ -68,7 +70,7 @@ static inline unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
 
 static inline bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu)
 {
-	return nested_ept_get_cr3(vcpu) & VMX_EPTP_AD_ENABLE_BIT;
+	return nested_ept_get_eptp(vcpu) & VMX_EPTP_AD_ENABLE_BIT;
 }
 
 /*
diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/ops.h
index 45eaedee2ac0..19717d0a1100 100644
--- a/arch/x86/kvm/vmx/ops.h
+++ b/arch/x86/kvm/vmx/ops.h
@@ -13,6 +13,8 @@
 #define __ex(x) __kvm_handle_fault_on_reboot(x)
 
 asmlinkage void vmread_error(unsigned long field, bool fault);
+__attribute__((regparm(0))) void vmread_error_trampoline(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);
@@ -70,15 +72,28 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
 	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"
+
+		     /*
+		      * VMREAD failed.  Push '0' for @fault, push the failing
+		      * @field, and bounce through the trampoline to preserve
+		      * volatile registers.
+		      */
+		     "push $0\n\t"
+		     "push %2\n\t"
+		     "2:call vmread_error_trampoline\n\t"
+
+		     /*
+		      * Unwind the stack.  Note, the trampoline zeros out the
+		      * memory for @fault so that the result is '0' on error.
+		      */
+		     "pop %2\n\t"
+		     "pop %1\n\t"
 		     "3:\n\t"
 
+		     /* VMREAD faulted.  As above, except push '1' for @fault. */
 		     ".pushsection .fixup, \"ax\"\n\t"
-		     "4: mov %2, %%" _ASM_ARG1 "\n\t"
-		     "mov $1, %%" _ASM_ARG2 "\n\t"
+		     "4: push $1\n\t"
+		     "push %2\n\t"
 		     "jmp 2b\n\t"
 		     ".popsection\n\t"
 		     _ASM_EXTABLE(1b, 4b)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index fd21cdb10b79..7c857737b438 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -263,9 +263,15 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			if (!msr_info->host_initiated)
 				data = (s64)(s32)data;
 			pmc->counter += data - pmc_read_counter(pmc);
+			if (pmc->perf_event)
+				perf_event_period(pmc->perf_event,
+						  get_sample_period(pmc, data));
 			return 0;
 		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
 			pmc->counter += data - pmc_read_counter(pmc);
+			if (pmc->perf_event)
+				perf_event_period(pmc->perf_event,
+						  get_sample_period(pmc, data));
 			return 0;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)
@@ -329,7 +335,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	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())
+	if (vmx_pt_mode_is_host_guest())
 		pmu->global_ovf_ctrl_mask &=
 				~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI;
 
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 81ada2ce99e7..9651ba388ba9 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -135,12 +135,12 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	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_RBX(%_ASM_AX), %_ASM_BX
+	mov VCPU_RBP(%_ASM_AX), %_ASM_BP
 	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
@@ -168,12 +168,12 @@ SYM_FUNC_START(__vmx_vcpu_run)
 
 	/* 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_BX,   VCPU_RBX(%_ASM_AX)
+	mov %_ASM_BP,   VCPU_RBP(%_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)
@@ -197,12 +197,12 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	 * 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
+1:	xor %ecx, %ecx
 	xor %edx, %edx
+	xor %ebx, %ebx
+	xor %ebp, %ebp
 	xor %esi, %esi
 	xor %edi, %edi
-	xor %ebp, %ebp
 #ifdef CONFIG_X86_64
 	xor %r8d,  %r8d
 	xor %r9d,  %r9d
@@ -234,3 +234,61 @@ SYM_FUNC_START(__vmx_vcpu_run)
 2:	mov $1, %eax
 	jmp 1b
 SYM_FUNC_END(__vmx_vcpu_run)
+
+/**
+ * vmread_error_trampoline - Trampoline from inline asm to vmread_error()
+ * @field:	VMCS field encoding that failed
+ * @fault:	%true if the VMREAD faulted, %false if it failed
+
+ * Save and restore volatile registers across a call to vmread_error().  Note,
+ * all parameters are passed on the stack.
+ */
+SYM_FUNC_START(vmread_error_trampoline)
+	push %_ASM_BP
+	mov  %_ASM_SP, %_ASM_BP
+
+	push %_ASM_AX
+	push %_ASM_CX
+	push %_ASM_DX
+#ifdef CONFIG_X86_64
+	push %rdi
+	push %rsi
+	push %r8
+	push %r9
+	push %r10
+	push %r11
+#endif
+#ifdef CONFIG_X86_64
+	/* Load @field and @fault to arg1 and arg2 respectively. */
+	mov 3*WORD_SIZE(%rbp), %_ASM_ARG2
+	mov 2*WORD_SIZE(%rbp), %_ASM_ARG1
+#else
+	/* Parameters are passed on the stack for 32-bit (see asmlinkage). */
+	push 3*WORD_SIZE(%ebp)
+	push 2*WORD_SIZE(%ebp)
+#endif
+
+	call vmread_error
+
+#ifndef CONFIG_X86_64
+	add $8, %esp
+#endif
+
+	/* Zero out @fault, which will be popped into the result register. */
+	_ASM_MOV $0, 3*WORD_SIZE(%_ASM_BP)
+
+#ifdef CONFIG_X86_64
+	pop %r11
+	pop %r10
+	pop %r9
+	pop %r8
+	pop %rsi
+	pop %rdi
+#endif
+	pop %_ASM_DX
+	pop %_ASM_CX
+	pop %_ASM_AX
+	pop %_ASM_BP
+
+	ret
+SYM_FUNC_END(vmread_error_trampoline)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 458e684dfbdc..91749f1254e8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -437,7 +437,6 @@ static const struct kvm_vmx_segment_field {
 	VMX_SEGMENT_FIELD(LDTR),
 };
 
-u64 host_efer;
 static unsigned long host_idt_base;
 
 /*
@@ -658,53 +657,16 @@ static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr,
 	return ret;
 }
 
-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)
@@ -716,19 +678,24 @@ static void __loaded_vmcs_clear(void *arg)
 		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);
+
+	vmcs_clear(loaded_vmcs->vmcs);
+	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
+
 	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.
+	 * Ensure all writes to loaded_vmcs, including deleting it from its
+	 * current percpu list, complete before setting loaded_vmcs->vcpu to
+	 * -1, otherwise a different cpu can see vcpu == -1 first and add
+	 * loaded_vmcs to its percpu list before it's deleted from this cpu's
+	 * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs().
 	 */
 	smp_wmb();
 
-	loaded_vmcs_init(loaded_vmcs);
-	crash_enable_local_vmclear(cpu);
+	loaded_vmcs->cpu = -1;
+	loaded_vmcs->launched = 0;
 }
 
 void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
@@ -812,7 +779,7 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	if (to_vmx(vcpu)->rmode.vm86_active)
 		eb = ~0;
 	if (enable_ept)
-		eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
+		eb &= ~(1u << PF_VECTOR);
 
 	/* 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
@@ -1063,7 +1030,7 @@ static unsigned long segment_base(u16 selector)
 
 static inline bool pt_can_write_msr(struct vcpu_vmx *vmx)
 {
-	return (pt_mode == PT_MODE_HOST_GUEST) &&
+	return vmx_pt_mode_is_host_guest() &&
 	       !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN);
 }
 
@@ -1097,7 +1064,7 @@ static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range)
 
 static void pt_guest_enter(struct vcpu_vmx *vmx)
 {
-	if (pt_mode == PT_MODE_SYSTEM)
+	if (vmx_pt_mode_is_system())
 		return;
 
 	/*
@@ -1114,7 +1081,7 @@ static void pt_guest_enter(struct vcpu_vmx *vmx)
 
 static void pt_guest_exit(struct vcpu_vmx *vmx)
 {
-	if (pt_mode == PT_MODE_SYSTEM)
+	if (vmx_pt_mode_is_system())
 		return;
 
 	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
@@ -1347,18 +1314,17 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int 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().
+		 * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to
+		 * this cpu's percpu list, otherwise it may not yet be deleted
+		 * from its previous cpu's percpu list.  Pairs with the
+		 * smb_wmb() 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();
 	}
 
@@ -1691,16 +1657,6 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 	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.
  */
@@ -1908,24 +1864,24 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 							&msr_info->data);
 		break;
 	case MSR_IA32_RTIT_CTL:
-		if (pt_mode != PT_MODE_HOST_GUEST)
+		if (!vmx_pt_mode_is_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)
+		if (!vmx_pt_mode_is_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) ||
+		if (!vmx_pt_mode_is_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) ||
+		if (!vmx_pt_mode_is_host_guest() ||
 			(!intel_pt_validate_cap(vmx->pt_desc.caps,
 					PT_CAP_topa_output) &&
 			 !intel_pt_validate_cap(vmx->pt_desc.caps,
@@ -1934,7 +1890,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vmx->pt_desc.guest.output_base;
 		break;
 	case MSR_IA32_RTIT_OUTPUT_MASK:
-		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+		if (!vmx_pt_mode_is_host_guest() ||
 			(!intel_pt_validate_cap(vmx->pt_desc.caps,
 					PT_CAP_topa_output) &&
 			 !intel_pt_validate_cap(vmx->pt_desc.caps,
@@ -1944,7 +1900,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		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) ||
+		if (!vmx_pt_mode_is_host_guest() ||
 			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
 					PT_CAP_num_address_ranges)))
 			return 1;
@@ -2150,7 +2106,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		return vmx_set_vmx_msr(vcpu, msr_index, data);
 	case MSR_IA32_RTIT_CTL:
-		if ((pt_mode != PT_MODE_HOST_GUEST) ||
+		if (!vmx_pt_mode_is_host_guest() ||
 			vmx_rtit_ctl_check(vcpu, data) ||
 			vmx->nested.vmxon)
 			return 1;
@@ -2266,18 +2222,33 @@ static __init int vmx_disabled_by_bios(void)
 	       !boot_cpu_has(X86_FEATURE_VMX);
 }
 
-static void kvm_cpu_vmxon(u64 addr)
+static int kvm_cpu_vmxon(u64 vmxon_pointer)
 {
+	u64 msr;
+
 	cr4_set_bits(X86_CR4_VMXE);
 	intel_pt_handle_vmx(1);
 
-	asm volatile ("vmxon %0" : : "m"(addr));
+	asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t"
+			  _ASM_EXTABLE(1b, %l[fault])
+			  : : [vmxon_pointer] "m"(vmxon_pointer)
+			  : : fault);
+	return 0;
+
+fault:
+	WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n",
+		  rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr);
+	intel_pt_handle_vmx(0);
+	cr4_clear_bits(X86_CR4_VMXE);
+
+	return -EFAULT;
 }
 
 static int hardware_enable(void)
 {
 	int cpu = raw_smp_processor_id();
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
+	int r;
 
 	if (cr4_read_shadow() & X86_CR4_VMXE)
 		return -EBUSY;
@@ -2294,18 +2265,10 @@ static int hardware_enable(void)
 	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);
+	r = kvm_cpu_vmxon(phys_addr);
+	if (r)
+		return r;
 
-	kvm_cpu_vmxon(phys_addr);
 	if (enable_ept)
 		ept_sync_global();
 
@@ -2617,9 +2580,12 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 	if (!loaded_vmcs->vmcs)
 		return -ENOMEM;
 
+	vmcs_clear(loaded_vmcs->vmcs);
+
 	loaded_vmcs->shadow_vmcs = NULL;
 	loaded_vmcs->hv_timer_soft_disabled = false;
-	loaded_vmcs_init(loaded_vmcs);
+	loaded_vmcs->cpu = -1;
+	loaded_vmcs->launched = 0;
 
 	if (cpu_has_vmx_msr_bitmap()) {
 		loaded_vmcs->msr_bitmap = (unsigned long *)
@@ -3001,9 +2967,8 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 static int get_ept_level(struct kvm_vcpu *vcpu)
 {
-	/* Nested EPT currently only supports 4-level walks. */
 	if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
-		return 4;
+		return vmx_eptp_page_walk_level(nested_ept_get_eptp(vcpu));
 	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
 		return 5;
 	return 4;
@@ -3023,7 +2988,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
 	return eptp;
 }
 
-void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
+void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	struct kvm *kvm = vcpu->kvm;
 	bool update_guest_cr3 = true;
@@ -3035,7 +3000,7 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 		eptp = construct_eptp(vcpu, cr3);
 		vmcs_write64(EPT_POINTER, eptp);
 
-		if (kvm_x86_ops->tlb_remote_flush) {
+		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
@@ -4040,7 +4005,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 
 	u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
 
-	if (pt_mode == PT_MODE_SYSTEM)
+	if (vmx_pt_mode_is_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;
@@ -4095,7 +4060,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 		}
 	}
 
-	if (vmx_rdtscp_supported()) {
+	if (cpu_has_vmx_rdtscp()) {
 		bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP);
 		if (!rdtscp_enabled)
 			exec_control &= ~SECONDARY_EXEC_RDTSCP;
@@ -4110,7 +4075,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 		}
 	}
 
-	if (vmx_invpcid_supported()) {
+	if (cpu_has_vmx_invpcid()) {
 		/* Exposing INVPCID only when PCID is exposed */
 		bool invpcid_enabled =
 			guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) &&
@@ -4281,7 +4246,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	if (cpu_has_vmx_encls_vmexit())
 		vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);
 
-	if (pt_mode == PT_MODE_HOST_GUEST) {
+	if (vmx_pt_mode_is_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;
@@ -4509,8 +4474,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
 
 static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
-	return (!to_vmx(vcpu)->nested.nested_run_pending &&
-		vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+	if (to_vmx(vcpu)->nested.nested_run_pending)
+		return false;
+
+	if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
+		return true;
+
+	return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
 		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
 			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
 }
@@ -4566,7 +4536,6 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
 	case GP_VECTOR:
 	case MF_VECTOR:
 		return true;
-	break;
 	}
 	return false;
 }
@@ -5343,7 +5312,6 @@ static void vmx_enable_tdp(void)
 		VMX_EPT_RWX_MASK, 0ull);
 
 	ept_set_mmio_spte_mask();
-	kvm_enable_tdp();
 }
 
 /*
@@ -5876,8 +5844,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu,
 	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 (is_guest_mode(vcpu)) {
+		/*
+		 * The host physical addresses of some pages of guest memory
+		 * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
+		 * Page). The CPU may write to these pages via their host
+		 * physical address while L2 is running, bypassing any
+		 * address-translation-based dirty tracking (e.g. EPT write
+		 * protection).
+		 *
+		 * Mark them dirty on every exit from L2 to prevent them from
+		 * getting out of sync with dirty tracking.
+		 */
+		nested_mark_vmcs12_pages_dirty(vcpu);
+
+		if (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();
@@ -6237,15 +6220,13 @@ 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))
+	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))
+	} else 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)) {
+	} else if (is_nmi(vmx->exit_intr_info)) {
 		kvm_before_interrupt(&vmx->vcpu);
 		asm("int $2");
 		kvm_after_interrupt(&vmx->vcpu);
@@ -6331,11 +6312,6 @@ static bool vmx_has_emulated_msr(int index)
 	}
 }
 
-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;
@@ -6581,7 +6557,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	pt_guest_enter(vmx);
 
-	atomic_switch_perf_msrs(vmx);
+	if (vcpu_to_pmu(vcpu)->version)
+		atomic_switch_perf_msrs(vmx);
 	atomic_switch_umwait_control_msr(vmx);
 
 	if (enable_preemption_timer)
@@ -6698,20 +6675,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	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);
@@ -6914,17 +6877,24 @@ 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
+	/* We wanted to honor guest CD/MTRR/PAT, but doing so could result in
+	 * memory aliases with conflicting memory types and sometimes MCEs.
+	 * We have to be careful as to what are honored and when.
+	 *
+	 * For MMIO, guest CD/MTRR are ignored.  The EPT memory type is set to
+	 * UC.  The effective memory type is UC or WC depending on guest PAT.
+	 * This was historically the source of MCEs and we want to be
+	 * conservative.
+	 *
+	 * When there is no need to deal with noncoherent DMA (e.g., no VT-d
+	 * or VT-d has snoop control), guest CD/MTRR/PAT are all ignored.  The
+	 * EPT memory type is set to WB.  The effective memory type is forced
+	 * WB.
+	 *
+	 * Otherwise, we trust guest.  Guest CD/MTRR/PAT are all honored.  The
+	 * EPT memory type is used to emulate guest CD/MTRR.
 	 */
+
 	if (is_mmio) {
 		cache = MTRR_TYPE_UNCACHABLE;
 		goto exit;
@@ -6951,15 +6921,6 @@ 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)
 {
 	/*
@@ -7150,10 +7111,37 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+static __init void vmx_set_cpu_caps(void)
 {
-	if (func == 1 && nested)
-		entry->ecx |= feature_bit(VMX);
+	kvm_set_cpu_caps();
+
+	/* CPUID 0x1 */
+	if (nested)
+		kvm_cpu_cap_set(X86_FEATURE_VMX);
+
+	/* CPUID 0x7 */
+	if (kvm_mpx_supported())
+		kvm_cpu_cap_check_and_set(X86_FEATURE_MPX);
+	if (cpu_has_vmx_invpcid())
+		kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID);
+	if (vmx_pt_mode_is_host_guest())
+		kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT);
+
+	/* PKU is not yet implemented for shadow paging. */
+	if (enable_ept && boot_cpu_has(X86_FEATURE_OSPKE))
+		kvm_cpu_cap_check_and_set(X86_FEATURE_PKU);
+
+	if (vmx_umip_emulated())
+		kvm_cpu_cap_set(X86_FEATURE_UMIP);
+
+	/* CPUID 0xD.1 */
+	supported_xss = 0;
+	if (!vmx_xsaves_supported())
+		kvm_cpu_cap_clear(X86_FEATURE_XSAVES);
+
+	/* CPUID 0x80000001 */
+	if (!cpu_has_vmx_rdtscp())
+		kvm_cpu_cap_clear(X86_FEATURE_RDTSCP);
 }
 
 static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
@@ -7197,10 +7185,10 @@ static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
 
 static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
-			       enum x86_intercept_stage stage)
+			       enum x86_intercept_stage stage,
+			       struct x86_exception *exception)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 
 	switch (info->intercept) {
 	/*
@@ -7209,8 +7197,8 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 	 */
 	case x86_intercept_rdtscp:
 		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
-			ctxt->exception.vector = UD_VECTOR;
-			ctxt->exception.error_code_valid = false;
+			exception->vector = UD_VECTOR;
+			exception->error_code_valid = false;
 			return X86EMUL_PROPAGATE_FAULT;
 		}
 		break;
@@ -7321,7 +7309,8 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
 static void vmx_slot_enable_log_dirty(struct kvm *kvm,
 				     struct kvm_memory_slot *slot)
 {
-	kvm_mmu_slot_leaf_clear_dirty(kvm, slot);
+	if (!kvm_dirty_log_manual_protect_and_init_set(kvm))
+		kvm_mmu_slot_leaf_clear_dirty(kvm, slot);
 	kvm_mmu_slot_largepage_remove_write_access(kvm, slot);
 }
 
@@ -7504,7 +7493,7 @@ static void pi_post_block(struct kvm_vcpu *vcpu)
 
 static void vmx_post_block(struct kvm_vcpu *vcpu)
 {
-	if (kvm_x86_ops->set_hv_timer)
+	if (kvm_x86_ops.set_hv_timer)
 		kvm_lapic_switch_to_hv_timer(vcpu);
 
 	pi_post_block(vcpu);
@@ -7671,13 +7660,164 @@ static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 	return to_vmx(vcpu)->nested.vmxon;
 }
 
+static void hardware_unsetup(void)
+{
+	if (nested)
+		nested_vmx_hardware_unsetup();
+
+	free_kvm_area();
+}
+
+static bool vmx_check_apicv_inhibit_reasons(ulong bit)
+{
+	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_HYPERV);
+
+	return supported & BIT(bit);
+}
+
+static struct kvm_x86_ops vmx_x86_ops __initdata = {
+	.hardware_unsetup = hardware_unsetup,
+
+	.hardware_enable = hardware_enable,
+	.hardware_disable = hardware_disable,
+	.cpu_has_accelerated_tpr = report_flexpriority,
+	.has_emulated_msr = vmx_has_emulated_msr,
+
+	.vm_size = sizeof(struct kvm_vmx),
+	.vm_init = vmx_vm_init,
+
+	.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_cr4_guest_bits = vmx_decache_cr4_guest_bits,
+	.set_cr0 = vmx_set_cr0,
+	.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 = vmx_skip_emulated_instruction,
+	.update_emulated_instruction = vmx_update_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,
+	.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,
+	.check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons,
+	.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,
+
+	.cpuid_update = vmx_cpuid_update,
+
+	.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,
+
+	.load_mmu_pgd = vmx_load_mmu_pgd,
+
+	.check_intercept = vmx_check_intercept,
+	.handle_exit_irqoff = vmx_handle_exit_irqoff,
+
+	.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 __init int hardware_setup(void)
 {
 	unsigned long host_bndcfgs;
 	struct desc_ptr dt;
-	int r, i;
-
-	rdmsrl_safe(MSR_EFER, &host_efer);
+	int r, i, ept_lpage_level;
 
 	store_idt(&dt);
 	host_idt_base = dt.address;
@@ -7696,6 +7836,10 @@ static __init int hardware_setup(void)
 		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
 	}
 
+	if (!cpu_has_vmx_mpx())
+		supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS |
+				    XFEATURE_MASK_BNDCSR);
+
 	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
 	    !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
@@ -7724,19 +7868,16 @@ static __init int hardware_setup(void)
 	 * using the APIC_ACCESS_ADDR VMCS field.
 	 */
 	if (!flexpriority_enabled)
-		kvm_x86_ops->set_apic_access_page_addr = NULL;
+		vmx_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();
+		vmx_x86_ops.update_cr8_intercept = NULL;
 
 #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 =
+		vmx_x86_ops.tlb_remote_flush = hv_remote_flush_tlb;
+		vmx_x86_ops.tlb_remote_flush_with_range =
 				hv_remote_flush_tlb_with_range;
 	}
 #endif
@@ -7751,7 +7892,7 @@ static __init int hardware_setup(void)
 
 	if (!cpu_has_vmx_apicv()) {
 		enable_apicv = 0;
-		kvm_x86_ops->sync_pir_to_irr = NULL;
+		vmx_x86_ops.sync_pir_to_irr = NULL;
 	}
 
 	if (cpu_has_vmx_tsc_scaling()) {
@@ -7764,8 +7905,16 @@ static __init int hardware_setup(void)
 
 	if (enable_ept)
 		vmx_enable_tdp();
+
+	if (!enable_ept)
+		ept_lpage_level = 0;
+	else if (cpu_has_vmx_ept_1g_page())
+		ept_lpage_level = PT_PDPE_LEVEL;
+	else if (cpu_has_vmx_ept_2m_page())
+		ept_lpage_level = PT_DIRECTORY_LEVEL;
 	else
-		kvm_disable_tdp();
+		ept_lpage_level = PT_PAGE_TABLE_LEVEL;
+	kvm_configure_mmu(enable_ept, ept_lpage_level);
 
 	/*
 	 * Only enable PML when hardware supports PML feature, and both EPT
@@ -7775,10 +7924,10 @@ static __init int hardware_setup(void)
 		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;
+		vmx_x86_ops.slot_enable_log_dirty = NULL;
+		vmx_x86_ops.slot_disable_log_dirty = NULL;
+		vmx_x86_ops.flush_log_dirty = NULL;
+		vmx_x86_ops.enable_log_dirty_pt_masked = NULL;
 	}
 
 	if (!cpu_has_vmx_preemption_timer())
@@ -7806,9 +7955,9 @@ static __init int hardware_setup(void)
 	}
 
 	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;
+		vmx_x86_ops.set_hv_timer = NULL;
+		vmx_x86_ops.cancel_hv_timer = NULL;
+		vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit;
 	}
 
 	kvm_set_posted_intr_wakeup_handler(wakeup_handler);
@@ -7824,185 +7973,27 @@ static __init int hardware_setup(void)
 		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
 					   vmx_capability.ept);
 
-		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
+		r = nested_vmx_hardware_setup(&vmx_x86_ops,
+					      kvm_vmx_exit_handlers);
 		if (r)
 			return r;
 	}
 
+	vmx_set_cpu_caps();
+
 	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 bool vmx_check_apicv_inhibit_reasons(ulong bit)
-{
-	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
-			  BIT(APICV_INHIBIT_REASON_HYPERV);
-
-	return supported & BIT(bit);
-}
-
-static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
+static struct kvm_x86_init_ops vmx_init_ops __initdata = {
 	.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_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 = vmx_skip_emulated_instruction,
-	.update_emulated_instruction = vmx_update_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,
-	.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,
-	.check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons,
-	.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,
-	.pku_supported = vmx_pku_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,
+	.hardware_setup = hardware_setup,
 
-	.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,
+	.runtime_ops = &vmx_x86_ops,
 };
 
 static void vmx_cleanup_l1d_flush(void)
@@ -8089,7 +8080,7 @@ static int __init vmx_init(void)
 	}
 #endif
 
-	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+	r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx),
 		     __alignof__(struct vcpu_vmx), THIS_MODULE);
 	if (r)
 		return r;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 0695ea177e22..aab9df55336e 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -12,7 +12,6 @@
 #include "vmcs.h"
 
 extern const u32 vmx_msr_index[];
-extern u64 host_efer;
 
 #define MSR_TYPE_R	1
 #define MSR_TYPE_W	2
@@ -333,9 +332,9 @@ 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 vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long cr3);
 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);
@@ -450,7 +449,7 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
 static inline u32 vmx_vmentry_ctrl(void)
 {
 	u32 vmentry_ctrl = vmcs_config.vmentry_ctrl;
-	if (pt_mode == PT_MODE_SYSTEM)
+	if (vmx_pt_mode_is_system())
 		vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP |
 				  VM_ENTRY_LOAD_IA32_RTIT_CTL);
 	/* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
@@ -461,7 +460,7 @@ static inline u32 vmx_vmentry_ctrl(void)
 static inline u32 vmx_vmexit_ctrl(void)
 {
 	u32 vmexit_ctrl = vmcs_config.vmexit_ctrl;
-	if (pt_mode == PT_MODE_SYSTEM)
+	if (vmx_pt_mode_is_system())
 		vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP |
 				 VM_EXIT_CLEAR_IA32_RTIT_CTL);
 	/* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
@@ -491,7 +490,6 @@ 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)