1 files changed, 328 insertions, 296 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 7eec0226d56a..bcac3efcde41 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -12,6 +12,7 @@
  *   Avi Kivity   <avi@qumranet.com>
  *   Yaniv Kamay  <yaniv@qumranet.com>
  */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/highmem.h>
 #include <linux/hrtimer.h>
@@ -444,36 +445,36 @@ void vmread_error(unsigned long field, bool fault)
 	if (fault)
 		kvm_spurious_fault();
 	else
-		vmx_insn_failed("kvm: vmread failed: field=%lx\n", field);
+		vmx_insn_failed("vmread failed: field=%lx\n", field);
 }
 
 noinline void vmwrite_error(unsigned long field, unsigned long value)
 {
-	vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%u\n",
+	vmx_insn_failed("vmwrite failed: field=%lx val=%lx err=%u\n",
 			field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
 }
 
 noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr)
 {
-	vmx_insn_failed("kvm: vmclear failed: %p/%llx err=%u\n",
+	vmx_insn_failed("vmclear failed: %p/%llx err=%u\n",
 			vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR));
 }
 
 noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr)
 {
-	vmx_insn_failed("kvm: vmptrld failed: %p/%llx err=%u\n",
+	vmx_insn_failed("vmptrld failed: %p/%llx err=%u\n",
 			vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR));
 }
 
 noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva)
 {
-	vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n",
+	vmx_insn_failed("invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n",
 			ext, vpid, gva);
 }
 
 noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa)
 {
-	vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n",
+	vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n",
 			ext, eptp, gpa);
 }
 
@@ -488,8 +489,8 @@ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
 static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
 static DEFINE_SPINLOCK(vmx_vpid_lock);
 
-struct vmcs_config vmcs_config;
-struct vmx_capability vmx_capability;
+struct vmcs_config vmcs_config __ro_after_init;
+struct vmx_capability vmx_capability __ro_after_init;
 
 #define VMX_SEGMENT_FIELD(seg)					\
 	[VCPU_SREG_##seg] = {                                   \
@@ -523,6 +524,8 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
 static unsigned long host_idt_base;
 
 #if IS_ENABLED(CONFIG_HYPERV)
+static struct kvm_x86_ops vmx_x86_ops __initdata;
+
 static bool __read_mostly enlightened_vmcs = true;
 module_param(enlightened_vmcs, bool, 0444);
 
@@ -551,6 +554,71 @@ static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static __init void hv_init_evmcs(void)
+{
+	int cpu;
+
+	if (!enlightened_vmcs)
+		return;
+
+	/*
+	 * Enlightened VMCS usage should be recommended and the host needs
+	 * to support eVMCS v1 or above.
+	 */
+	if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED &&
+	    (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >=
+	     KVM_EVMCS_VERSION) {
+
+		/* Check that we have assist pages on all online CPUs */
+		for_each_online_cpu(cpu) {
+			if (!hv_get_vp_assist_page(cpu)) {
+				enlightened_vmcs = false;
+				break;
+			}
+		}
+
+		if (enlightened_vmcs) {
+			pr_info("Using Hyper-V Enlightened VMCS\n");
+			static_branch_enable(&enable_evmcs);
+		}
+
+		if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH)
+			vmx_x86_ops.enable_l2_tlb_flush
+				= hv_enable_l2_tlb_flush;
+
+	} else {
+		enlightened_vmcs = false;
+	}
+}
+
+static void hv_reset_evmcs(void)
+{
+	struct hv_vp_assist_page *vp_ap;
+
+	if (!static_branch_unlikely(&enable_evmcs))
+		return;
+
+	/*
+	 * KVM should enable eVMCS if and only if all CPUs have a VP assist
+	 * page, and should reject CPU onlining if eVMCS is enabled the CPU
+	 * doesn't have a VP assist page allocated.
+	 */
+	vp_ap = hv_get_vp_assist_page(smp_processor_id());
+	if (WARN_ON_ONCE(!vp_ap))
+		return;
+
+	/*
+	 * Reset everything to support using non-enlightened VMCS access later
+	 * (e.g. when we reload the module with enlightened_vmcs=0)
+	 */
+	vp_ap->nested_control.features.directhypercall = 0;
+	vp_ap->current_nested_vmcs = 0;
+	vp_ap->enlighten_vmentry = 0;
+}
+
+#else /* IS_ENABLED(CONFIG_HYPERV) */
+static void hv_init_evmcs(void) {}
+static void hv_reset_evmcs(void) {}
 #endif /* IS_ENABLED(CONFIG_HYPERV) */
 
 /*
@@ -1613,8 +1681,8 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 		if (!instr_len)
 			goto rip_updated;
 
-		WARN(exit_reason.enclave_mode,
-		     "KVM: skipping instruction after SGX enclave VM-Exit");
+		WARN_ONCE(exit_reason.enclave_mode,
+			  "skipping instruction after SGX enclave VM-Exit");
 
 		orig_rip = kvm_rip_read(vcpu);
 		rip = orig_rip + instr_len;
@@ -2138,9 +2206,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
 		if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
-			if (report_ignored_msrs)
-				vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n",
-					    __func__, data);
+			kvm_pr_unimpl_wrmsr(vcpu, msr_index, data);
 			data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
 			invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
 		}
@@ -2448,88 +2514,6 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 	}
 }
 
-static __init int cpu_has_kvm_support(void)
-{
-	return cpu_has_vmx();
-}
-
-static __init int vmx_disabled_by_bios(void)
-{
-	return !boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) ||
-	       !boot_cpu_has(X86_FEATURE_VMX);
-}
-
-static int kvm_cpu_vmxon(u64 vmxon_pointer)
-{
-	u64 msr;
-
-	cr4_set_bits(X86_CR4_VMXE);
-
-	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);
-	cr4_clear_bits(X86_CR4_VMXE);
-
-	return -EFAULT;
-}
-
-static int vmx_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;
-
-	/*
-	 * This can happen if we hot-added a CPU but failed to allocate
-	 * VP assist page for it.
-	 */
-	if (static_branch_unlikely(&enable_evmcs) &&
-	    !hv_get_vp_assist_page(cpu))
-		return -EFAULT;
-
-	intel_pt_handle_vmx(1);
-
-	r = kvm_cpu_vmxon(phys_addr);
-	if (r) {
-		intel_pt_handle_vmx(0);
-		return r;
-	}
-
-	if (enable_ept)
-		ept_sync_global();
-
-	return 0;
-}
-
-static void vmclear_local_loaded_vmcss(void)
-{
-	int cpu = raw_smp_processor_id();
-	struct loaded_vmcs *v, *n;
-
-	list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu),
-				 loaded_vmcss_on_cpu_link)
-		__loaded_vmcs_clear(v);
-}
-
-static void vmx_hardware_disable(void)
-{
-	vmclear_local_loaded_vmcss();
-
-	if (cpu_vmxoff())
-		kvm_spurious_fault();
-
-	intel_pt_handle_vmx(0);
-}
-
 /*
  * 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
@@ -2565,8 +2549,7 @@ static bool cpu_has_perf_global_ctrl_bug(void)
 	return false;
 }
 
-static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
-				      u32 msr, u32 *result)
+static int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result)
 {
 	u32 vmx_msr_low, vmx_msr_high;
 	u32 ctl = ctl_min | ctl_opt;
@@ -2584,7 +2567,7 @@ static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
 	return 0;
 }
 
-static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr)
+static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr)
 {
 	u64 allowed;
 
@@ -2593,8 +2576,8 @@ static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr)
 	return  ctl_opt & allowed;
 }
 
-static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
-				    struct vmx_capability *vmx_cap)
+static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
+			     struct vmx_capability *vmx_cap)
 {
 	u32 vmx_msr_low, vmx_msr_high;
 	u32 _pin_based_exec_control = 0;
@@ -2752,9 +2735,127 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	vmcs_conf->vmentry_ctrl        = _vmentry_control;
 	vmcs_conf->misc	= misc_msr;
 
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (enlightened_vmcs)
+		evmcs_sanitize_exec_ctrls(vmcs_conf);
+#endif
+
+	return 0;
+}
+
+static bool kvm_is_vmx_supported(void)
+{
+	int cpu = raw_smp_processor_id();
+
+	if (!cpu_has_vmx()) {
+		pr_err("VMX not supported by CPU %d\n", cpu);
+		return false;
+	}
+
+	if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) ||
+	    !this_cpu_has(X86_FEATURE_VMX)) {
+		pr_err("VMX not enabled (by BIOS) in MSR_IA32_FEAT_CTL on CPU %d\n", cpu);
+		return false;
+	}
+
+	return true;
+}
+
+static int vmx_check_processor_compat(void)
+{
+	int cpu = raw_smp_processor_id();
+	struct vmcs_config vmcs_conf;
+	struct vmx_capability vmx_cap;
+
+	if (!kvm_is_vmx_supported())
+		return -EIO;
+
+	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) {
+		pr_err("Failed to setup VMCS config on CPU %d\n", cpu);
+		return -EIO;
+	}
+	if (nested)
+		nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept);
+	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config))) {
+		pr_err("Inconsistent VMCS config on CPU %d\n", cpu);
+		return -EIO;
+	}
+	return 0;
+}
+
+static int kvm_cpu_vmxon(u64 vmxon_pointer)
+{
+	u64 msr;
+
+	cr4_set_bits(X86_CR4_VMXE);
+
+	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);
+	cr4_clear_bits(X86_CR4_VMXE);
+
+	return -EFAULT;
+}
+
+static int vmx_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;
+
+	/*
+	 * This can happen if we hot-added a CPU but failed to allocate
+	 * VP assist page for it.
+	 */
+	if (static_branch_unlikely(&enable_evmcs) &&
+	    !hv_get_vp_assist_page(cpu))
+		return -EFAULT;
+
+	intel_pt_handle_vmx(1);
+
+	r = kvm_cpu_vmxon(phys_addr);
+	if (r) {
+		intel_pt_handle_vmx(0);
+		return r;
+	}
+
+	if (enable_ept)
+		ept_sync_global();
+
 	return 0;
 }
 
+static void vmclear_local_loaded_vmcss(void)
+{
+	int cpu = raw_smp_processor_id();
+	struct loaded_vmcs *v, *n;
+
+	list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu),
+				 loaded_vmcss_on_cpu_link)
+		__loaded_vmcs_clear(v);
+}
+
+static void vmx_hardware_disable(void)
+{
+	vmclear_local_loaded_vmcss();
+
+	if (cpu_vmxoff())
+		kvm_spurious_fault();
+
+	hv_reset_evmcs();
+
+	intel_pt_handle_vmx(0);
+}
+
 struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags)
 {
 	int node = cpu_to_node(cpu);
@@ -2950,9 +3051,8 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save)
 		var.type = 0x3;
 		var.avl = 0;
 		if (save->base & 0xf)
-			printk_once(KERN_WARNING "kvm: segment base is not "
-					"paragraph aligned when entering "
-					"protected mode (seg=%d)", seg);
+			pr_warn_once("segment base is not paragraph aligned "
+				     "when entering protected mode (seg=%d)", seg);
 	}
 
 	vmcs_write16(sf->selector, var.selector);
@@ -2982,8 +3082,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 	 * vcpu. Warn the user that an update is overdue.
 	 */
 	if (!kvm_vmx->tss_addr)
-		printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be "
-			     "called before entering vcpu\n");
+		pr_warn_once("KVM_SET_TSS_ADDR needs to be called before running vCPU\n");
 
 	vmx_segment_cache_clear(vmx);
 
@@ -3800,39 +3899,6 @@ static void seg_setup(int seg)
 	vmcs_write32(sf->ar_bytes, ar);
 }
 
-static int alloc_apic_access_page(struct kvm *kvm)
-{
-	struct page *page;
-	void __user *hva;
-	int ret = 0;
-
-	mutex_lock(&kvm->slots_lock);
-	if (kvm->arch.apic_access_memslot_enabled)
-		goto out;
-	hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
-				      APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
-	if (IS_ERR(hva)) {
-		ret = PTR_ERR(hva);
-		goto out;
-	}
-
-	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
-	if (is_error_page(page)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	/*
-	 * Do not pin the page in memory, so that memory hot-unplug
-	 * is able to migrate it.
-	 */
-	put_page(page);
-	kvm->arch.apic_access_memslot_enabled = true;
-out:
-	mutex_unlock(&kvm->slots_lock);
-	return ret;
-}
-
 int allocate_vpid(void)
 {
 	int vpid;
@@ -3865,8 +3931,13 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx)
 	 * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR
 	 * bitmap has changed.
 	 */
-	if (static_branch_unlikely(&enable_evmcs))
-		evmcs_touch_msr_bitmap();
+	if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs)) {
+		struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs;
+
+		if (evmcs->hv_enlightenments_control.msr_bitmap)
+			evmcs->hv_clean_fields &=
+				~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
+	}
 
 	vmx->nested.force_msr_bitmap_recalc = true;
 }
@@ -3947,29 +4018,20 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 		vmx_set_msr_bitmap_write(msr_bitmap, msr);
 }
 
-static void vmx_reset_x2apic_msrs(struct kvm_vcpu *vcpu, u8 mode)
-{
-	unsigned long *msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
-	unsigned long read_intercept;
-	int msr;
-
-	read_intercept = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
-
-	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-		unsigned int read_idx = msr / BITS_PER_LONG;
-		unsigned int write_idx = read_idx + (0x800 / sizeof(long));
-
-		msr_bitmap[read_idx] = read_intercept;
-		msr_bitmap[write_idx] = ~0ul;
-	}
-}
-
 static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * x2APIC indices for 64-bit accesses into the RDMSR and WRMSR halves
+	 * of the MSR bitmap.  KVM emulates APIC registers up through 0x3f0,
+	 * i.e. MSR 0x83f, and so only needs to dynamically manipulate 64 bits.
+	 */
+	const int read_idx = APIC_BASE_MSR / BITS_PER_LONG_LONG;
+	const int write_idx = read_idx + (0x800 / sizeof(u64));
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 *msr_bitmap = (u64 *)vmx->vmcs01.msr_bitmap;
 	u8 mode;
 
-	if (!cpu_has_vmx_msr_bitmap())
+	if (!cpu_has_vmx_msr_bitmap() || WARN_ON_ONCE(!lapic_in_kernel(vcpu)))
 		return;
 
 	if (cpu_has_secondary_exec_ctrls() &&
@@ -3987,7 +4049,18 @@ static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu)
 
 	vmx->x2apic_msr_bitmap_mode = mode;
 
-	vmx_reset_x2apic_msrs(vcpu, mode);
+	/*
+	 * Reset the bitmap for MSRs 0x800 - 0x83f.  Leave AMD's uber-extended
+	 * registers (0x840 and above) intercepted, KVM doesn't support them.
+	 * Intercept all writes by default and poke holes as needed.  Pass
+	 * through reads for all valid registers by default in x2APIC+APICv
+	 * mode, only the current timer count needs on-demand emulation by KVM.
+	 */
+	if (mode & MSR_BITMAP_MODE_X2APIC_APICV)
+		msr_bitmap[read_idx] = ~kvm_lapic_readable_reg_mask(vcpu->arch.apic);
+	else
+		msr_bitmap[read_idx] = ~0ull;
+	msr_bitmap[write_idx] = ~0ull;
 
 	/*
 	 * TPR reads and writes can be virtualized even if virtual interrupt
@@ -4519,6 +4592,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
 	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 
+	/*
+	 * KVM doesn't support VMFUNC for L1, but the control is set in KVM's
+	 * base configuration as KVM emulates VMFUNC[EPTP_SWITCHING] for L2.
+	 */
+	exec_control &= ~SECONDARY_EXEC_ENABLE_VMFUNC;
+
 	/* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP,
 	 * in vmx_set_cr4.  */
 	exec_control &= ~SECONDARY_EXEC_DESC;
@@ -4535,7 +4614,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 	 * it needs to be set here when dirty logging is already active, e.g.
 	 * if this vCPU was created after dirty logging was enabled.
 	 */
-	if (!vcpu->kvm->arch.cpu_dirty_logging_count)
+	if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging))
 		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
 
 	if (cpu_has_vmx_xsaves()) {
@@ -5099,8 +5178,13 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	vect_info = vmx->idt_vectoring_info;
 	intr_info = vmx_get_intr_info(vcpu);
 
+	/*
+	 * Machine checks are handled by handle_exception_irqoff(), or by
+	 * vmx_vcpu_run() if a #MC occurs on VM-Entry.  NMIs are handled by
+	 * vmx_vcpu_enter_exit().
+	 */
 	if (is_machine_check(intr_info) || is_nmi(intr_info))
-		return 1; /* handled by handle_exception_nmi_irqoff() */
+		return 1;
 
 	/*
 	 * Queue the exception here instead of in handle_nm_fault_irqoff().
@@ -6790,17 +6874,8 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 	memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
 }
 
-void vmx_do_interrupt_nmi_irqoff(unsigned long entry);
-
-static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
-					unsigned long entry)
-{
-	bool is_nmi = entry == (unsigned long)asm_exc_nmi_noist;
-
-	kvm_before_interrupt(vcpu, is_nmi ? KVM_HANDLING_NMI : KVM_HANDLING_IRQ);
-	vmx_do_interrupt_nmi_irqoff(entry);
-	kvm_after_interrupt(vcpu);
-}
+void vmx_do_interrupt_irqoff(unsigned long entry);
+void vmx_do_nmi_irqoff(void);
 
 static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
 {
@@ -6822,9 +6897,8 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
 		rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
 }
 
-static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
+static void handle_exception_irqoff(struct vcpu_vmx *vmx)
 {
-	const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist;
 	u32 intr_info = vmx_get_intr_info(&vmx->vcpu);
 
 	/* if exit due to PF check for async PF */
@@ -6836,9 +6910,6 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
 	/* Handle machine checks before interrupts are enabled */
 	else if (is_machine_check(intr_info))
 		kvm_machine_check();
-	/* We need to handle NMIs before interrupts are enabled */
-	else if (is_nmi(intr_info))
-		handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry);
 }
 
 static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
@@ -6848,10 +6919,13 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 	gate_desc *desc = (gate_desc *)host_idt_base + vector;
 
 	if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm,
-	    "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info))
+	    "unexpected VM-Exit interrupt info: 0x%x", intr_info))
 		return;
 
-	handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc));
+	kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
+	vmx_do_interrupt_irqoff(gate_offset(desc));
+	kvm_after_interrupt(vcpu);
+
 	vcpu->arch.at_instruction_boundary = true;
 }
 
@@ -6865,7 +6939,7 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 	if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT)
 		handle_external_interrupt_irqoff(vcpu);
 	else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI)
-		handle_exception_nmi_irqoff(vmx);
+		handle_exception_irqoff(vmx);
 }
 
 /*
@@ -7100,9 +7174,10 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 }
 
 static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
-					struct vcpu_vmx *vmx,
-					unsigned long flags)
+					unsigned int flags)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
 	guest_state_enter_irqoff();
 
 	/* L1D Flush includes CPU buffer clear to mitigate MDS */
@@ -7126,6 +7201,18 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	vmx_enable_fb_clear(vmx);
 
+	if (unlikely(vmx->fail))
+		vmx->exit_reason.full = 0xdead;
+	else
+		vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON);
+
+	if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI &&
+	    is_nmi(vmx_get_intr_info(vcpu))) {
+		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
+		vmx_do_nmi_irqoff();
+		kvm_after_interrupt(vcpu);
+	}
+
 	guest_state_exit_irqoff();
 }
 
@@ -7220,7 +7307,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	kvm_wait_lapic_expire(vcpu);
 
 	/* The actual VMENTER/EXIT is in the .noinstr.text section. */
-	vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx));
+	vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx));
 
 	/* All fields are clean at this point */
 	if (static_branch_unlikely(&enable_evmcs)) {
@@ -7267,12 +7354,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	vmx->idt_vectoring_info = 0;
 
-	if (unlikely(vmx->fail)) {
-		vmx->exit_reason.full = 0xdead;
+	if (unlikely(vmx->fail))
 		return EXIT_FASTPATH_NONE;
-	}
 
-	vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON);
 	if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY))
 		kvm_machine_check();
 
@@ -7386,7 +7470,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu)
 	vmx->loaded_vmcs = &vmx->vmcs01;
 
 	if (cpu_need_virtualize_apic_accesses(vcpu)) {
-		err = alloc_apic_access_page(vcpu->kvm);
+		err = kvm_alloc_apic_access_page(vcpu->kvm);
 		if (err)
 			goto free_vmcs;
 	}
@@ -7446,29 +7530,6 @@ static int vmx_vm_init(struct kvm *kvm)
 	return 0;
 }
 
-static int __init vmx_check_processor_compat(void)
-{
-	struct vmcs_config vmcs_conf;
-	struct vmx_capability vmx_cap;
-
-	if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) ||
-	    !this_cpu_has(X86_FEATURE_VMX)) {
-		pr_err("kvm: VMX is disabled on CPU %d\n", smp_processor_id());
-		return -EIO;
-	}
-
-	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
-		return -EIO;
-	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmcs_conf, 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());
-		return -EIO;
-	}
-	return 0;
-}
-
 static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 {
 	u8 cache;
@@ -7940,17 +8001,20 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (WARN_ON_ONCE(!enable_pml))
+		return;
+
 	if (is_guest_mode(vcpu)) {
 		vmx->nested.update_vmcs01_cpu_dirty_logging = true;
 		return;
 	}
 
 	/*
-	 * Note, cpu_dirty_logging_count can be changed concurrent with this
+	 * Note, nr_memslots_dirty_logging can be changed concurrent with this
 	 * code, but in that case another update request will be made and so
 	 * the guest will never run with a stale PML value.
 	 */
-	if (vcpu->kvm->arch.cpu_dirty_logging_count)
+	if (atomic_read(&vcpu->kvm->nr_memslots_dirty_logging))
 		secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML);
 	else
 		secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML);
@@ -8048,17 +8112,16 @@ static void vmx_hardware_unsetup(void)
 	free_kvm_area();
 }
 
-static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
-{
-	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
-			  BIT(APICV_INHIBIT_REASON_ABSENT) |
-			  BIT(APICV_INHIBIT_REASON_HYPERV) |
-			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
-			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
-			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
-
-	return supported & BIT(reason);
-}
+#define VMX_REQUIRED_APICV_INHIBITS			\
+(							\
+	BIT(APICV_INHIBIT_REASON_DISABLE)|		\
+	BIT(APICV_INHIBIT_REASON_ABSENT) |		\
+	BIT(APICV_INHIBIT_REASON_HYPERV) |		\
+	BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |		\
+	BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) |	\
+	BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |	\
+	BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED)	\
+)
 
 static void vmx_vm_destroy(struct kvm *kvm)
 {
@@ -8068,7 +8131,9 @@ static void vmx_vm_destroy(struct kvm *kvm)
 }
 
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
-	.name = "kvm_intel",
+	.name = KBUILD_MODNAME,
+
+	.check_processor_compatibility = vmx_check_processor_compat,
 
 	.hardware_unsetup = vmx_hardware_unsetup,
 
@@ -8142,7 +8207,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.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,
+	.required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
 	.hwapic_irr_update = vmx_hwapic_irr_update,
 	.hwapic_isr_update = vmx_hwapic_isr_update,
 	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
@@ -8288,7 +8353,7 @@ static __init int hardware_setup(void)
 		return -EIO;
 
 	if (cpu_has_perf_global_ctrl_bug())
-		pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
+		pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
 			     "does not work properly. Using workaround\n");
 
 	if (boot_cpu_has(X86_FEATURE_NX))
@@ -8296,7 +8361,7 @@ static __init int hardware_setup(void)
 
 	if (boot_cpu_has(X86_FEATURE_MPX)) {
 		rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs);
-		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
+		WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost");
 	}
 
 	if (!cpu_has_vmx_mpx())
@@ -8315,7 +8380,7 @@ static __init int hardware_setup(void)
 
 	/* NX support is required for shadow paging. */
 	if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) {
-		pr_err_ratelimited("kvm: NX (Execute Disable) not supported\n");
+		pr_err_ratelimited("NX (Execute Disable) not supported\n");
 		return -EOPNOTSUPP;
 	}
 
@@ -8467,9 +8532,6 @@ static __init int hardware_setup(void)
 }
 
 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,
-	.check_processor_compatibility = vmx_check_processor_compat,
 	.hardware_setup = hardware_setup,
 	.handle_intel_pt_intr = NULL,
 
@@ -8487,41 +8549,23 @@ static void vmx_cleanup_l1d_flush(void)
 	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 }
 
-static void vmx_exit(void)
+static void __vmx_exit(void)
 {
+	allow_smaller_maxphyaddr = false;
+
 #ifdef CONFIG_KEXEC_CORE
 	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
 	synchronize_rcu();
 #endif
+	vmx_cleanup_l1d_flush();
+}
 
+static void vmx_exit(void)
+{
 	kvm_exit();
+	kvm_x86_vendor_exit();
 
-#if IS_ENABLED(CONFIG_HYPERV)
-	if (static_branch_unlikely(&enable_evmcs)) {
-		int cpu;
-		struct hv_vp_assist_page *vp_ap;
-		/*
-		 * Reset everything to support using non-enlightened VMCS
-		 * access later (e.g. when we reload the module with
-		 * enlightened_vmcs=0)
-		 */
-		for_each_online_cpu(cpu) {
-			vp_ap =	hv_get_vp_assist_page(cpu);
-
-			if (!vp_ap)
-				continue;
-
-			vp_ap->nested_control.features.directhypercall = 0;
-			vp_ap->current_nested_vmcs = 0;
-			vp_ap->enlighten_vmentry = 0;
-		}
-
-		static_branch_disable(&enable_evmcs);
-	}
-#endif
-	vmx_cleanup_l1d_flush();
-
-	allow_smaller_maxphyaddr = false;
+	__vmx_exit();
 }
 module_exit(vmx_exit);
 
@@ -8529,56 +8573,29 @@ static int __init vmx_init(void)
 {
 	int r, cpu;
 
-#if IS_ENABLED(CONFIG_HYPERV)
+	if (!kvm_is_vmx_supported())
+		return -EOPNOTSUPP;
+
 	/*
-	 * Enlightened VMCS usage should be recommended and the host needs
-	 * to support eVMCS v1 or above. We can also disable eVMCS support
-	 * with module parameter.
+	 * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing
+	 * to unwind if a later step fails.
 	 */
-	if (enlightened_vmcs &&
-	    ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED &&
-	    (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >=
-	    KVM_EVMCS_VERSION) {
-
-		/* Check that we have assist pages on all online CPUs */
-		for_each_online_cpu(cpu) {
-			if (!hv_get_vp_assist_page(cpu)) {
-				enlightened_vmcs = false;
-				break;
-			}
-		}
+	hv_init_evmcs();
 
-		if (enlightened_vmcs) {
-			pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n");
-			static_branch_enable(&enable_evmcs);
-		}
-
-		if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH)
-			vmx_x86_ops.enable_l2_tlb_flush
-				= hv_enable_l2_tlb_flush;
-
-	} else {
-		enlightened_vmcs = false;
-	}
-#endif
-
-	r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx),
-		     __alignof__(struct vcpu_vmx), THIS_MODULE);
+	r = kvm_x86_vendor_init(&vmx_init_ops);
 	if (r)
 		return r;
 
 	/*
-	 * Must be called after kvm_init() so enable_ept is properly set
+	 * Must be called after common x86 init so enable_ept is properly set
 	 * up. Hand the parameter mitigation value in which was stored in
 	 * the pre module init parser. If no parameter was given, it will
 	 * contain 'auto' which will be turned into the default 'cond'
 	 * mitigation mode.
 	 */
 	r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
-	if (r) {
-		vmx_exit();
-		return r;
-	}
+	if (r)
+		goto err_l1d_flush;
 
 	vmx_setup_fb_clear_ctrl();
 
@@ -8602,6 +8619,21 @@ static int __init vmx_init(void)
 	if (!enable_ept)
 		allow_smaller_maxphyaddr = true;
 
+	/*
+	 * Common KVM initialization _must_ come last, after this, /dev/kvm is
+	 * exposed to userspace!
+	 */
+	r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx),
+		     THIS_MODULE);
+	if (r)
+		goto err_kvm_init;
+
 	return 0;
+
+err_kvm_init:
+	__vmx_exit();
+err_l1d_flush:
+	kvm_x86_vendor_exit();
+	return r;
 }
 module_init(vmx_init);