1 files changed, 157 insertions, 111 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5b8f078..6069af8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -54,6 +54,7 @@
 #include <linux/kvm_irqfd.h>
 #include <linux/irqbypass.h>
 #include <linux/sched/stat.h>
+#include <linux/mem_encrypt.h>
 
 #include <trace/events/kvm.h>
 
@@ -310,13 +311,13 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
 	u64 new_state = msr_info->data &
 		(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
-	u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) |
-		0x2ff | (guest_cpuid_has_x2apic(vcpu) ? 0 : X2APIC_ENABLE);
+	u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff |
+		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
 
+	if ((msr_info->data & reserved_bits) || new_state == X2APIC_ENABLE)
+		return 1;
 	if (!msr_info->host_initiated &&
-	    ((msr_info->data & reserved_bits) != 0 ||
-	     new_state == X2APIC_ENABLE ||
-	     (new_state == MSR_IA32_APICBASE_ENABLE &&
+	    ((new_state == MSR_IA32_APICBASE_ENABLE &&
 	      old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) ||
 	     (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) &&
 	      old_state == 0)))
@@ -389,15 +390,28 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
-	if (!vcpu->arch.exception.pending) {
+	if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
 	queue:
 		if (has_error && !is_protmode(vcpu))
 			has_error = false;
-		vcpu->arch.exception.pending = true;
+		if (reinject) {
+			/*
+			 * On vmentry, vcpu->arch.exception.pending is only
+			 * true if an event injection was blocked by
+			 * nested_run_pending.  In that case, however,
+			 * vcpu_enter_guest requests an immediate exit,
+			 * and the guest shouldn't proceed far enough to
+			 * need reinjection.
+			 */
+			WARN_ON_ONCE(vcpu->arch.exception.pending);
+			vcpu->arch.exception.injected = true;
+		} else {
+			vcpu->arch.exception.pending = true;
+			vcpu->arch.exception.injected = false;
+		}
 		vcpu->arch.exception.has_error_code = has_error;
 		vcpu->arch.exception.nr = nr;
 		vcpu->arch.exception.error_code = error_code;
-		vcpu->arch.exception.reinject = reinject;
 		return;
 	}
 
@@ -412,8 +426,13 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 	class2 = exception_class(nr);
 	if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY)
 		|| (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
-		/* generate double fault per SDM Table 5-5 */
+		/*
+		 * Generate double fault per SDM Table 5-5.  Set
+		 * exception.pending = true so that the double fault
+		 * can trigger a nested vmexit.
+		 */
 		vcpu->arch.exception.pending = true;
+		vcpu->arch.exception.injected = false;
 		vcpu->arch.exception.has_error_code = true;
 		vcpu->arch.exception.nr = DF_VECTOR;
 		vcpu->arch.exception.error_code = 0;
@@ -597,8 +616,8 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 		      (unsigned long *)&vcpu->arch.regs_avail))
 		return true;
 
-	gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT;
-	offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1);
+	gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
+	offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1);
 	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
 				       PFERR_USER_MASK | PFERR_WRITE_MASK);
 	if (r < 0)
@@ -754,19 +773,22 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (cr4 & CR4_RESERVED_BITS)
 		return 1;
 
-	if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE))
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
 		return 1;
 
-	if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP))
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
 		return 1;
 
-	if (!guest_cpuid_has_smap(vcpu) && (cr4 & X86_CR4_SMAP))
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
 		return 1;
 
-	if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE))
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
 		return 1;
 
-	if (!guest_cpuid_has_pku(vcpu) && (cr4 & X86_CR4_PKE))
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
+		return 1;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
 		return 1;
 
 	if (is_long_mode(vcpu)) {
@@ -779,7 +801,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 		return 1;
 
 	if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) {
-		if (!guest_cpuid_has_pcid(vcpu))
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID))
 			return 1;
 
 		/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
@@ -813,10 +835,10 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 		return 0;
 	}
 
-	if (is_long_mode(vcpu)) {
-		if (cr3 & CR3_L_MODE_RESERVED_BITS)
-			return 1;
-	} else if (is_pae(vcpu) && is_paging(vcpu) &&
+	if (is_long_mode(vcpu) &&
+	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 62)))
+		return 1;
+	else if (is_pae(vcpu) && is_paging(vcpu) &&
 		   !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
 		return 1;
 
@@ -883,7 +905,7 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
 {
 	u64 fixed = DR6_FIXED_1;
 
-	if (!guest_cpuid_has_rtm(vcpu))
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM))
 		fixed |= DR6_RTM;
 	return fixed;
 }
@@ -993,6 +1015,7 @@ static u32 emulated_msrs[] = {
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
 	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
+	HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY,
 	HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2,
 	HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL,
 	HV_X64_MSR_RESET,
@@ -1021,21 +1044,11 @@ bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 	if (efer & efer_reserved_bits)
 		return false;
 
-	if (efer & EFER_FFXSR) {
-		struct kvm_cpuid_entry2 *feat;
-
-		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
-		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT)))
+	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
 			return false;
-	}
-
-	if (efer & EFER_SVME) {
-		struct kvm_cpuid_entry2 *feat;
 
-		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
-		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM)))
+	if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
 			return false;
-	}
 
 	return true;
 }
@@ -1083,7 +1096,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_KERNEL_GS_BASE:
 	case MSR_CSTAR:
 	case MSR_LSTAR:
-		if (is_noncanonical_address(msr->data))
+		if (is_noncanonical_address(msr->data, vcpu))
 			return 1;
 		break;
 	case MSR_IA32_SYSENTER_EIP:
@@ -1100,7 +1113,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 * value, and that something deterministic happens if the guest
 		 * invokes 64-bit SYSENTER.
 		 */
-		msr->data = get_canonical(msr->data);
+		msr->data = get_canonical(msr->data, vcpu_virt_addr_bits(vcpu));
 	}
 	return kvm_x86_ops->set_msr(vcpu, msr);
 }
@@ -1533,8 +1546,9 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
 	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
 
-	if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated)
+	if (!msr->host_initiated && guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST))
 		update_ia32_tsc_adjust_msr(vcpu, offset);
+
 	kvm_vcpu_write_tsc_offset(vcpu, offset);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
@@ -2184,7 +2198,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
 		break;
 	case MSR_IA32_TSC_ADJUST:
-		if (guest_cpuid_has_tsc_adjust(vcpu)) {
+		if (guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST)) {
 			if (!msr_info->host_initiated) {
 				s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
 				adjust_tsc_offset_guest(vcpu, adj);
@@ -2306,12 +2320,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
 		break;
 	case MSR_AMD64_OSVW_ID_LENGTH:
-		if (!guest_cpuid_has_osvw(vcpu))
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
 			return 1;
 		vcpu->arch.osvw.length = data;
 		break;
 	case MSR_AMD64_OSVW_STATUS:
-		if (!guest_cpuid_has_osvw(vcpu))
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
 			return 1;
 		vcpu->arch.osvw.status = data;
 		break;
@@ -2536,12 +2550,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = 0xbe702111;
 		break;
 	case MSR_AMD64_OSVW_ID_LENGTH:
-		if (!guest_cpuid_has_osvw(vcpu))
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
 			return 1;
 		msr_info->data = vcpu->arch.osvw.length;
 		break;
 	case MSR_AMD64_OSVW_STATUS:
-		if (!guest_cpuid_has_osvw(vcpu))
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
 			return 1;
 		msr_info->data = vcpu->arch.osvw.status;
 		break;
@@ -2881,6 +2895,10 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	int idx;
+
+	if (vcpu->preempted)
+		vcpu->arch.preempted_in_kernel = !kvm_x86_ops->get_cpl(vcpu);
+
 	/*
 	 * Disable page faults because we're in atomic context here.
 	 * kvm_write_guest_offset_cached() would call might_fault()
@@ -3073,8 +3091,14 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 					       struct kvm_vcpu_events *events)
 {
 	process_nmi(vcpu);
+	/*
+	 * FIXME: pass injected and pending separately.  This is only
+	 * needed for nested virtualization, whose state cannot be
+	 * migrated yet.  For now we can combine them.
+	 */
 	events->exception.injected =
-		vcpu->arch.exception.pending &&
+		(vcpu->arch.exception.pending ||
+		 vcpu->arch.exception.injected) &&
 		!kvm_exception_is_soft(vcpu->arch.exception.nr);
 	events->exception.nr = vcpu->arch.exception.nr;
 	events->exception.has_error_code = vcpu->arch.exception.has_error_code;
@@ -3129,6 +3153,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	process_nmi(vcpu);
+	vcpu->arch.exception.injected = false;
 	vcpu->arch.exception.pending = events->exception.injected;
 	vcpu->arch.exception.nr = events->exception.nr;
 	vcpu->arch.exception.has_error_code = events->exception.has_error_code;
@@ -3159,15 +3184,18 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		kvm_set_hflags(vcpu, hflags);
 
 		vcpu->arch.smi_pending = events->smi.pending;
-		if (events->smi.smm_inside_nmi)
-			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
-		else
-			vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-		if (lapic_in_kernel(vcpu)) {
-			if (events->smi.latched_init)
-				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+
+		if (events->smi.smm) {
+			if (events->smi.smm_inside_nmi)
+				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
-				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
+			if (lapic_in_kernel(vcpu)) {
+				if (events->smi.latched_init)
+					set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+				else
+					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			}
 		}
 	}
 
@@ -3242,7 +3270,12 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 			u32 size, offset, ecx, edx;
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
-			memcpy(dest + offset, src, size);
+			if (feature == XFEATURE_MASK_PKRU)
+				memcpy(dest + offset, &vcpu->arch.pkru,
+				       sizeof(vcpu->arch.pkru));
+			else
+				memcpy(dest + offset, src, size);
+
 		}
 
 		valid -= feature;
@@ -3280,7 +3313,11 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 			u32 size, offset, ecx, edx;
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
-			memcpy(dest, src + offset, size);
+			if (feature == XFEATURE_MASK_PKRU)
+				memcpy(&vcpu->arch.pkru, src + offset,
+				       sizeof(vcpu->arch.pkru));
+			else
+				memcpy(dest, src + offset, size);
 		}
 
 		valid -= feature;
@@ -4658,25 +4695,18 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
 	 */
 	if (vcpu->arch.gpa_available &&
 	    emulator_can_use_gpa(ctxt) &&
-	    vcpu_is_mmio_gpa(vcpu, addr, exception->address, write) &&
-	    (addr & ~PAGE_MASK) == (exception->address & ~PAGE_MASK)) {
-		gpa = exception->address;
-		goto mmio;
+	    (addr & ~PAGE_MASK) == (vcpu->arch.gpa_val & ~PAGE_MASK)) {
+		gpa = vcpu->arch.gpa_val;
+		ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write);
+	} else {
+		ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
+		if (ret < 0)
+			return X86EMUL_PROPAGATE_FAULT;
 	}
 
-	ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
-
-	if (ret < 0)
-		return X86EMUL_PROPAGATE_FAULT;
-
-	/* For APIC access vmexit */
-	if (ret)
-		goto mmio;
-
-	if (ops->read_write_emulate(vcpu, gpa, val, bytes))
+	if (!ret && ops->read_write_emulate(vcpu, gpa, val, bytes))
 		return X86EMUL_CONTINUE;
 
-mmio:
 	/*
 	 * Is this MMIO handled locally?
 	 */
@@ -5214,10 +5244,10 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
 	return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage);
 }
 
-static void emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
-			       u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
+			u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit)
 {
-	kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx);
+	return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit);
 }
 
 static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
@@ -6113,7 +6143,7 @@ int kvm_arch_init(void *opaque)
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0,
-			PT_PRESENT_MASK, 0);
+			PT_PRESENT_MASK, 0, sme_me_mask);
 	kvm_timer_init();
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);
@@ -6215,6 +6245,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 
 	lapic_irq.shorthand = 0;
 	lapic_irq.dest_mode = 0;
+	lapic_irq.level = 0;
 	lapic_irq.dest_id = apicid;
 	lapic_irq.msi_redir_hint = false;
 
@@ -6348,11 +6379,42 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	int r;
 
 	/* try to reinject previous events if any */
+	if (vcpu->arch.exception.injected) {
+		kvm_x86_ops->queue_exception(vcpu);
+		return 0;
+	}
+
+	/*
+	 * Exceptions must be injected immediately, or the exception
+	 * frame will have the address of the NMI or interrupt handler.
+	 */
+	if (!vcpu->arch.exception.pending) {
+		if (vcpu->arch.nmi_injected) {
+			kvm_x86_ops->set_nmi(vcpu);
+			return 0;
+		}
+
+		if (vcpu->arch.interrupt.pending) {
+			kvm_x86_ops->set_irq(vcpu);
+			return 0;
+		}
+	}
+
+	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+		r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+		if (r != 0)
+			return r;
+	}
+
+	/* try to inject new event if pending */
 	if (vcpu->arch.exception.pending) {
 		trace_kvm_inj_exception(vcpu->arch.exception.nr,
 					vcpu->arch.exception.has_error_code,
 					vcpu->arch.exception.error_code);
 
+		vcpu->arch.exception.pending = false;
+		vcpu->arch.exception.injected = true;
+
 		if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
 			__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
 					     X86_EFLAGS_RF);
@@ -6364,27 +6426,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 		}
 
 		kvm_x86_ops->queue_exception(vcpu);
-		return 0;
-	}
-
-	if (vcpu->arch.nmi_injected) {
-		kvm_x86_ops->set_nmi(vcpu);
-		return 0;
-	}
-
-	if (vcpu->arch.interrupt.pending) {
-		kvm_x86_ops->set_irq(vcpu);
-		return 0;
-	}
-
-	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
-		r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
-		if (r != 0)
-			return r;
-	}
-
-	/* try to inject new event if pending */
-	if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
+	} else if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
 		vcpu->arch.smi_pending = false;
 		enter_smm(vcpu);
 	} else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
@@ -6601,7 +6643,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
 	trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
 	vcpu->arch.hflags |= HF_SMM_MASK;
 	memset(buf, 0, 512);
-	if (guest_cpuid_has_longmode(vcpu))
+	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		enter_smm_save_state_64(vcpu, buf);
 	else
 		enter_smm_save_state_32(vcpu, buf);
@@ -6653,7 +6695,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
 
-	if (guest_cpuid_has_longmode(vcpu))
+	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		kvm_x86_ops->set_efer(vcpu, 0);
 
 	kvm_update_cpuid(vcpu);
@@ -6721,17 +6763,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
 
-void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
-					   unsigned long address)
-{
-	/*
-	 * The physical address of apic access page is stored in the VMCS.
-	 * Update it when it becomes invalid.
-	 */
-	if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT))
-		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
-}
-
 /*
  * Returns 1 to let vcpu_run() continue the guest execution loop without
  * exiting to the userspace.  Otherwise, the value will be returned to the
@@ -6771,6 +6802,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+			vcpu->mmio_needed = 0;
 			r = 0;
 			goto out;
 		}
@@ -6859,6 +6891,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 				kvm_x86_ops->enable_nmi_window(vcpu);
 			if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
 				kvm_x86_ops->enable_irq_window(vcpu);
+			WARN_ON(vcpu->arch.exception.pending);
 		}
 
 		if (kvm_lapic_enabled(vcpu)) {
@@ -7001,6 +7034,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.apic_attention)
 		kvm_lapic_sync_from_vapic(vcpu);
 
+	vcpu->arch.gpa_available = false;
 	r = kvm_x86_ops->handle_exit(vcpu);
 	return r;
 
@@ -7419,7 +7453,13 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 
-	if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+			(sregs->cr4 & X86_CR4_OSXSAVE))
+		return -EINVAL;
+
+	apic_base_msr.data = sregs->apic_base;
+	apic_base_msr.host_initiated = true;
+	if (kvm_set_apic_base(vcpu, &apic_base_msr))
 		return -EINVAL;
 
 	dt.size = sregs->idt.limit;
@@ -7438,9 +7478,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
 	kvm_x86_ops->set_efer(vcpu, sregs->efer);
-	apic_base_msr.data = sregs->apic_base;
-	apic_base_msr.host_initiated = true;
-	kvm_set_apic_base(vcpu, &apic_base_msr);
 
 	mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
 	kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
@@ -7629,7 +7666,9 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 */
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
-	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
+	/* PKRU is separately restored in kvm_x86_ops->run.  */
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+				~XFEATURE_MASK_PKRU);
 	trace_kvm_fpu(1);
 }
 
@@ -7729,6 +7768,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vcpu->arch.nmi_injected = false;
 	kvm_clear_interrupt_queue(vcpu);
 	kvm_clear_exception_queue(vcpu);
+	vcpu->arch.exception.pending = false;
 
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
@@ -7988,6 +8028,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_pmu_init(vcpu);
 
 	vcpu->arch.pending_external_vector = -1;
+	vcpu->arch.preempted_in_kernel = false;
 
 	kvm_hv_vcpu_init(vcpu);
 
@@ -8435,6 +8476,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.preempted_in_kernel;
+}
+
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;