1 files changed, 471 insertions, 356 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9a6664886f2e..91749f1254e8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -31,6 +31,7 @@
 #include <asm/apic.h>
 #include <asm/asm.h>
 #include <asm/cpu.h>
+#include <asm/cpu_device_id.h>
 #include <asm/debugreg.h>
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
@@ -41,6 +42,7 @@
 #include <asm/mce.h>
 #include <asm/mmu_context.h>
 #include <asm/mshyperv.h>
+#include <asm/mwait.h>
 #include <asm/spec-ctrl.h>
 #include <asm/virtext.h>
 #include <asm/vmx.h>
@@ -64,11 +66,13 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+#ifdef MODULE
 static const struct x86_cpu_id vmx_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_VMX),
+	X86_MATCH_FEATURE(X86_FEATURE_VMX, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+#endif
 
 bool __read_mostly enable_vpid = 1;
 module_param_named(vpid, enable_vpid, bool, 0444);
@@ -95,7 +99,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
-static bool __read_mostly enable_apicv = 1;
+bool __read_mostly enable_apicv = 1;
 module_param(enable_apicv, bool, S_IRUGO);
 
 /*
@@ -433,7 +437,6 @@ static const struct kvm_vmx_segment_field {
 	VMX_SEGMENT_FIELD(LDTR),
 };
 
-u64 host_efer;
 static unsigned long host_idt_base;
 
 /*
@@ -654,53 +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)
@@ -712,19 +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)
@@ -808,7 +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
@@ -1059,7 +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);
 }
 
@@ -1093,7 +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;
 
 	/*
@@ -1110,7 +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) {
@@ -1175,6 +1146,10 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 					   vmx->guest_msrs[i].mask);
 
 	}
+
+    	if (vmx->nested.need_vmcs12_to_shadow_sync)
+		nested_sync_vmcs12_to_shadow(vcpu);
+
 	if (vmx->guest_state_loaded)
 		return;
 
@@ -1339,18 +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();
 	}
 
@@ -1599,6 +1573,40 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+
+/*
+ * Recognizes a pending MTF VM-exit and records the nested state for later
+ * delivery.
+ */
+static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!is_guest_mode(vcpu))
+		return;
+
+	/*
+	 * Per the SDM, MTF takes priority over debug-trap exceptions besides
+	 * T-bit traps. As instruction emulation is completed (i.e. at the
+	 * instruction boundary), any #DB exception pending delivery must be a
+	 * debug-trap. Record the pending MTF state to be delivered in
+	 * vmx_check_nested_events().
+	 */
+	if (nested_cpu_has_mtf(vmcs12) &&
+	    (!vcpu->arch.exception.pending ||
+	     vcpu->arch.exception.nr == DB_VECTOR))
+		vmx->nested.mtf_pending = true;
+	else
+		vmx->nested.mtf_pending = false;
+}
+
+static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	vmx_update_emulated_instruction(vcpu);
+	return skip_emulated_instruction(vcpu);
+}
+
 static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -1649,16 +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.
  */
@@ -1866,24 +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,
@@ -1892,7 +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,
@@ -1902,7 +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;
@@ -2108,7 +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;
@@ -2224,18 +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;
@@ -2252,18 +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();
 
@@ -2298,6 +2303,17 @@ static void hardware_disable(void)
 	kvm_cpu_vmxoff();
 }
 
+/*
+ * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID
+ * directly instead of going through cpu_has(), to ensure KVM is trapping
+ * ENCLS whenever it's supported in hardware.  It does not matter whether
+ * the host OS supports or has enabled SGX.
+ */
+static bool cpu_has_sgx(void)
+{
+	return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0));
+}
+
 static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
 				      u32 msr, u32 *result)
 {
@@ -2378,8 +2394,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 			SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
 			SECONDARY_EXEC_PT_USE_GPA |
 			SECONDARY_EXEC_PT_CONCEAL_VMX |
-			SECONDARY_EXEC_ENABLE_VMFUNC |
-			SECONDARY_EXEC_ENCLS_EXITING;
+			SECONDARY_EXEC_ENABLE_VMFUNC;
+		if (cpu_has_sgx())
+			opt2 |= SECONDARY_EXEC_ENCLS_EXITING;
 		if (adjust_vmx_controls(min2, opt2,
 					MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)
@@ -2563,9 +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 *)
@@ -2947,6 +2967,8 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 static int get_ept_level(struct kvm_vcpu *vcpu)
 {
+	if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
+		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;
@@ -2966,7 +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;
@@ -2978,7 +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
@@ -3815,24 +3837,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
  * 2. If target vcpu isn't running(root mode), kick it to pick up the
  * interrupt from PIR in next vmentry.
  */
-static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int r;
 
 	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
 	if (!r)
-		return;
+		return 0;
+
+	if (!vcpu->arch.apicv_active)
+		return -1;
 
 	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
-		return;
+		return 0;
 
 	/* If a previous notification has sent the IPI, nothing to do.  */
 	if (pi_test_and_set_on(&vmx->pi_desc))
-		return;
+		return 0;
 
 	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
+
+	return 0;
 }
 
 /*
@@ -3978,7 +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;
@@ -4033,7 +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;
@@ -4048,7 +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) &&
@@ -4219,7 +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;
@@ -4238,7 +4265,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	vmx->msr_ia32_umwait_control = 0;
 
-	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
 	vmx->hv_deadline_tsc = -1;
 	kvm_set_cr8(vcpu, 0);
@@ -4448,8 +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));
 }
@@ -4505,7 +4536,6 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
 	case GP_VECTOR:
 	case MF_VECTOR:
 		return true;
-	break;
 	}
 	return false;
 }
@@ -5282,7 +5312,6 @@ static void vmx_enable_tdp(void)
 		VMX_EPT_RWX_MASK, 0ull);
 
 	ept_set_mmio_spte_mask();
-	kvm_enable_tdp();
 }
 
 /*
@@ -5815,8 +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();
@@ -6176,15 +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);
@@ -6228,7 +6270,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 #endif
 		ASM_CALL_CONSTRAINT
 		:
-		THUNK_TARGET(entry),
+		[thunk_target]"r"(entry),
 		[ss]"i"(__KERNEL_DS),
 		[cs]"i"(__KERNEL_CS)
 	);
@@ -6270,11 +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;
@@ -6480,8 +6517,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmcs_write32(PLE_WINDOW, vmx->ple_window);
 	}
 
-	if (vmx->nested.need_vmcs12_to_shadow_sync)
-		nested_sync_vmcs12_to_shadow(vcpu);
+	/*
+	 * We did this in prepare_switch_to_guest, because it needs to
+	 * be within srcu_read_lock.
+	 */
+	WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync);
 
 	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP))
 		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
@@ -6517,7 +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)
@@ -6634,20 +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);
@@ -6755,14 +6782,14 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 
 	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
-					   vmx_capability.ept,
-					   kvm_vcpu_apicv_active(vcpu));
+					   vmx_capability.ept);
 	else
 		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
 
+	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
 
 	/*
@@ -6836,8 +6863,7 @@ static int __init vmx_check_processor_compat(void)
 	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
 		return -EIO;
 	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
-					   enable_apicv);
+		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
 	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
 		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
 				smp_processor_id());
@@ -6851,17 +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;
@@ -6888,15 +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)
 {
 	/*
@@ -7087,10 +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)
@@ -7098,26 +7149,86 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
 	to_vmx(vcpu)->req_immediate_exit = true;
 }
 
+static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
+				  struct x86_instruction_info *info)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned short port;
+	bool intercept;
+	int size;
+
+	if (info->intercept == x86_intercept_in ||
+	    info->intercept == x86_intercept_ins) {
+		port = info->src_val;
+		size = info->dst_bytes;
+	} else {
+		port = info->dst_val;
+		size = info->src_bytes;
+	}
+
+	/*
+	 * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
+	 * VM-exits depend on the 'unconditional IO exiting' VM-execution
+	 * control.
+	 *
+	 * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
+	 */
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		intercept = nested_cpu_has(vmcs12,
+					   CPU_BASED_UNCOND_IO_EXITING);
+	else
+		intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
+
+	/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
+	return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+}
+
 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) {
 	/*
 	 * RDPID causes #UD if disabled through secondary execution controls.
 	 * Because it is marked as EmulateOnUD, we need to intercept it here.
 	 */
-	if (info->intercept == x86_intercept_rdtscp &&
-	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
-		ctxt->exception.vector = UD_VECTOR;
-		ctxt->exception.error_code_valid = false;
-		return X86EMUL_PROPAGATE_FAULT;
-	}
+	case x86_intercept_rdtscp:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+			exception->vector = UD_VECTOR;
+			exception->error_code_valid = false;
+			return X86EMUL_PROPAGATE_FAULT;
+		}
+		break;
+
+	case x86_intercept_in:
+	case x86_intercept_ins:
+	case x86_intercept_out:
+	case x86_intercept_outs:
+		return vmx_check_intercept_io(vcpu, info);
+
+	case x86_intercept_lgdt:
+	case x86_intercept_lidt:
+	case x86_intercept_lldt:
+	case x86_intercept_ltr:
+	case x86_intercept_sgdt:
+	case x86_intercept_sidt:
+	case x86_intercept_sldt:
+	case x86_intercept_str:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC))
+			return X86EMUL_CONTINUE;
+
+		/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
+		break;
 
 	/* TODO: check more intercepts... */
-	return X86EMUL_CONTINUE;
+	default:
+		break;
+	}
+
+	return X86EMUL_UNHANDLEABLE;
 }
 
 #ifdef CONFIG_X86_64
@@ -7198,7 +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);
 }
 
@@ -7381,7 +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);
@@ -7548,13 +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;
@@ -7573,6 +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;
@@ -7601,19 +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
@@ -7628,7 +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()) {
@@ -7641,8 +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
@@ -7652,10 +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())
@@ -7683,9 +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);
@@ -7699,186 +7971,29 @@ static __init int hardware_setup(void)
 
 	if (nested) {
 		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
-					   vmx_capability.ept, enable_apicv);
+					   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 = skip_emulated_instruction,
-	.set_interrupt_shadow = vmx_set_interrupt_shadow,
-	.get_interrupt_shadow = vmx_get_interrupt_shadow,
-	.patch_hypercall = vmx_patch_hypercall,
-	.set_irq = vmx_inject_irq,
-	.set_nmi = vmx_inject_nmi,
-	.queue_exception = vmx_queue_exception,
-	.cancel_injection = vmx_cancel_injection,
-	.interrupt_allowed = vmx_interrupt_allowed,
-	.nmi_allowed = vmx_nmi_allowed,
-	.get_nmi_mask = vmx_get_nmi_mask,
-	.set_nmi_mask = vmx_set_nmi_mask,
-	.enable_nmi_window = enable_nmi_window,
-	.enable_irq_window = enable_irq_window,
-	.update_cr8_intercept = update_cr8_intercept,
-	.set_virtual_apic_mode = vmx_set_virtual_apic_mode,
-	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
-	.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)
@@ -7965,7 +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;