7 files changed, 250 insertions, 171 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 82055b90a8b3..92bf2f2e7cdd 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -379,7 +379,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	/* cpuid 0x80000008.ebx */
 	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
-		F(IBPB) | F(IBRS);
+		F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD);
 
 	/* cpuid 0xC0000001.edx */
 	const u32 kvm_cpuid_C000_0001_edx_x86_features =
@@ -408,7 +408,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	/* cpuid 7.0.edx*/
 	const u32 kvm_cpuid_7_0_edx_x86_features =
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
-		F(ARCH_CAPABILITIES);
+		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
@@ -495,6 +495,11 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 				entry->ecx &= ~F(PKU);
 			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
 			cpuid_mask(&entry->edx, CPUID_7_EDX);
+			/*
+			 * We emulate ARCH_CAPABILITIES in software even
+			 * if the host doesn't support it.
+			 */
+			entry->edx |= F(ARCH_CAPABILITIES);
 		} else {
 			entry->ebx = 0;
 			entry->ecx = 0;
@@ -647,13 +652,20 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			g_phys_as = phys_as;
 		entry->eax = g_phys_as | (virt_as << 8);
 		entry->edx = 0;
-		/* IBRS and IBPB aren't necessarily present in hardware cpuid */
-		if (boot_cpu_has(X86_FEATURE_IBPB))
-			entry->ebx |= F(IBPB);
-		if (boot_cpu_has(X86_FEATURE_IBRS))
-			entry->ebx |= F(IBRS);
+		/*
+		 * IBRS, IBPB and VIRT_SSBD aren't necessarily present in
+		 * hardware cpuid
+		 */
+		if (boot_cpu_has(X86_FEATURE_AMD_IBPB))
+			entry->ebx |= F(AMD_IBPB);
+		if (boot_cpu_has(X86_FEATURE_AMD_IBRS))
+			entry->ebx |= F(AMD_IBRS);
+		if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
 		entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
 		cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX);
+		if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
 		break;
 	}
 	case 0x80000019:
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 98618e397342..46ff64da44ca 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1260,12 +1260,16 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 	}
 }
 
-static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
 {
-	struct kvm_run *run = vcpu->run;
+	kvm_hv_hypercall_set_result(vcpu, result);
+	++vcpu->stat.hypercalls;
+	return kvm_skip_emulated_instruction(vcpu);
+}
 
-	kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result);
-	return 1;
+static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+{
+	return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result);
 }
 
 static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
@@ -1296,8 +1300,10 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
 	if (param & ~KVM_HYPERV_CONN_ID_MASK)
 		return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
-	/* conn_to_evt is protected by vcpu->kvm->srcu */
+	/* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */
+	rcu_read_lock();
 	eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param);
+	rcu_read_unlock();
 	if (!eventfd)
 		return HV_STATUS_INVALID_PORT_ID;
 
@@ -1348,7 +1354,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	/* Hypercall continuation is not supported yet */
 	if (rep_cnt || rep_idx) {
 		ret = HV_STATUS_INVALID_HYPERCALL_CODE;
-		goto set_result;
+		goto out;
 	}
 
 	switch (code) {
@@ -1379,9 +1385,8 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-set_result:
-	kvm_hv_hypercall_set_result(vcpu, ret);
-	return 1;
+out:
+	return kvm_hv_hypercall_complete(vcpu, ret);
 }
 
 void kvm_hv_init_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 70dcb5548022..3773c4625114 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1463,23 +1463,6 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 	local_irq_restore(flags);
 }
 
-static void start_sw_period(struct kvm_lapic *apic)
-{
-	if (!apic->lapic_timer.period)
-		return;
-
-	if (apic_lvtt_oneshot(apic) &&
-	    ktime_after(ktime_get(),
-			apic->lapic_timer.target_expiration)) {
-		apic_timer_expired(apic);
-		return;
-	}
-
-	hrtimer_start(&apic->lapic_timer.timer,
-		apic->lapic_timer.target_expiration,
-		HRTIMER_MODE_ABS_PINNED);
-}
-
 static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor)
 {
 	ktime_t now, remaining;
@@ -1539,11 +1522,43 @@ static bool set_target_expiration(struct kvm_lapic *apic)
 
 static void advance_periodic_target_expiration(struct kvm_lapic *apic)
 {
-	apic->lapic_timer.tscdeadline +=
-		nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+	ktime_t now = ktime_get();
+	u64 tscl = rdtsc();
+	ktime_t delta;
+
+	/*
+	 * Synchronize both deadlines to the same time source or
+	 * differences in the periods (caused by differences in the
+	 * underlying clocks or numerical approximation errors) will
+	 * cause the two to drift apart over time as the errors
+	 * accumulate.
+	 */
 	apic->lapic_timer.target_expiration =
 		ktime_add_ns(apic->lapic_timer.target_expiration,
 				apic->lapic_timer.period);
+	delta = ktime_sub(apic->lapic_timer.target_expiration, now);
+	apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
+		nsec_to_cycles(apic->vcpu, delta);
+}
+
+static void start_sw_period(struct kvm_lapic *apic)
+{
+	if (!apic->lapic_timer.period)
+		return;
+
+	if (ktime_after(ktime_get(),
+			apic->lapic_timer.target_expiration)) {
+		apic_timer_expired(apic);
+
+		if (apic_lvtt_oneshot(apic))
+			return;
+
+		advance_periodic_target_expiration(apic);
+	}
+
+	hrtimer_start(&apic->lapic_timer.timer,
+		apic->lapic_timer.target_expiration,
+		HRTIMER_MODE_ABS_PINNED);
 }
 
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b58787daf9f8..26110c202b19 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -49,7 +49,7 @@
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
 #include <asm/irq_remapping.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 
 #include <asm/virtext.h>
 #include "trace.h"
@@ -213,6 +213,12 @@ struct vcpu_svm {
 	} host;
 
 	u64 spec_ctrl;
+	/*
+	 * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
+	 * translated into the appropriate L2_CFG bits on the host to
+	 * perform speculative control.
+	 */
+	u64 virt_spec_ctrl;
 
 	u32 *msrpm;
 
@@ -1423,12 +1429,23 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
 	seg->base = 0;
 }
 
+static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (is_guest_mode(vcpu))
+		return svm->nested.hsave->control.tsc_offset;
+
+	return vcpu->arch.tsc_offset;
+}
+
 static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 g_tsc_offset = 0;
 
 	if (is_guest_mode(vcpu)) {
+		/* Write L1's TSC offset.  */
 		g_tsc_offset = svm->vmcb->control.tsc_offset -
 			       svm->nested.hsave->control.tsc_offset;
 		svm->nested.hsave->control.tsc_offset = offset;
@@ -2049,6 +2066,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	vcpu->arch.microcode_version = 0x01000065;
 	svm->spec_ctrl = 0;
+	svm->virt_spec_ctrl = 0;
 
 	if (!init_event) {
 		svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
@@ -3322,6 +3340,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Restore the original control entries */
 	copy_vmcb_control_area(vmcb, hsave);
 
+	svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset;
 	kvm_clear_exception_queue(&svm->vcpu);
 	kvm_clear_interrupt_queue(&svm->vcpu);
 
@@ -3482,10 +3501,12 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	/* We don't want to see VMMCALLs from a nested guest */
 	clr_intercept(svm, INTERCEPT_VMMCALL);
 
+	svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset;
+	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset;
+
 	svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext;
 	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
 	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
-	svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
 	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
 	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
 
@@ -4035,12 +4056,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	switch (msr_info->index) {
-	case MSR_IA32_TSC: {
-		msr_info->data = svm->vmcb->control.tsc_offset +
-			kvm_scale_tsc(vcpu, rdtsc());
-
-		break;
-	}
 	case MSR_STAR:
 		msr_info->data = svm->vmcb->save.star;
 		break;
@@ -4100,11 +4115,18 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
+		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
 			return 1;
 
 		msr_info->data = svm->spec_ctrl;
 		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+			return 1;
+
+		msr_info->data = svm->virt_spec_ctrl;
+		break;
 	case MSR_F15H_IC_CFG: {
 
 		int family, model;
@@ -4193,12 +4215,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		svm->vmcb->save.g_pat = data;
 		mark_dirty(svm->vmcb, VMCB_NPT);
 		break;
-	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
+		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
 			return 1;
 
 		/* The STIBP bit doesn't fault even if it's not advertised */
@@ -4225,7 +4244,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBPB))
+		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB))
 			return 1;
 
 		if (data & ~PRED_CMD_IBPB)
@@ -4239,6 +4258,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			break;
 		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
 		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+			return 1;
+
+		if (data & ~SPEC_CTRL_SSBD)
+			return 1;
+
+		svm->virt_spec_ctrl = data;
+		break;
 	case MSR_STAR:
 		svm->vmcb->save.star = data;
 		break;
@@ -5265,9 +5294,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		}
 
 		if (!ret && svm) {
-			trace_kvm_pi_irte_update(svm->vcpu.vcpu_id,
-						 host_irq, e->gsi,
-						 vcpu_info.vector,
+			trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
+						 e->gsi, vcpu_info.vector,
 						 vcpu_info.pi_desc_addr, set);
 		}
 
@@ -5553,8 +5581,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 * is no need to worry about the conditional branch over the wrmsr
 	 * being speculatively taken.
 	 */
-	if (svm->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
 
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
@@ -5648,6 +5675,18 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 		);
 
+	/* Eliminate branch target predictions from guest mode */
+	vmexit_fill_RSB();
+
+#ifdef CONFIG_X86_64
+	wrmsrl(MSR_GS_BASE, svm->host.gs_base);
+#else
+	loadsegment(fs, svm->host.fs);
+#ifndef CONFIG_X86_32_LAZY_GS
+	loadsegment(gs, svm->host.gs);
+#endif
+#endif
+
 	/*
 	 * We do not use IBRS in the kernel. If this vCPU has used the
 	 * SPEC_CTRL MSR it may have left it on; save the value and
@@ -5666,20 +5705,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
 		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
-	if (svm->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
-
-	/* Eliminate branch target predictions from guest mode */
-	vmexit_fill_RSB();
-
-#ifdef CONFIG_X86_64
-	wrmsrl(MSR_GS_BASE, svm->host.gs_base);
-#else
-	loadsegment(fs, svm->host.fs);
-#ifndef CONFIG_X86_32_LAZY_GS
-	loadsegment(gs, svm->host.gs);
-#endif
-#endif
+	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
 
 	reload_tss(vcpu);
 
@@ -5782,7 +5808,7 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
-static bool svm_has_high_real_mode_segbase(void)
+static bool svm_has_emulated_msr(int index)
 {
 	return true;
 }
@@ -7008,7 +7034,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
 	.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
-	.cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
+	.has_emulated_msr = svm_has_emulated_msr,
 
 	.vcpu_create = svm_create_vcpu,
 	.vcpu_free = svm_free_vcpu,
@@ -7102,6 +7128,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
+	.read_l1_tsc_offset = svm_read_l1_tsc_offset,
 	.write_tsc_offset = svm_write_tsc_offset,
 
 	.set_tdp_cr3 = set_tdp_cr3,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index aafcc9881e88..40aa29204baf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,7 +51,7 @@
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/mmu_context.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 #include <asm/mshyperv.h>
 
 #include "trace.h"
@@ -1494,6 +1494,12 @@ static inline bool cpu_has_vmx_vmfunc(void)
 		SECONDARY_EXEC_ENABLE_VMFUNC;
 }
 
+static bool vmx_umip_emulated(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_DESC;
+}
+
 static inline bool report_flexpriority(void)
 {
 	return flexpriority_enabled;
@@ -2880,18 +2886,15 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 		vmx_update_msr_bitmap(&vmx->vcpu);
 }
 
-/*
- * reads and returns guest's timestamp counter "register"
- * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
- * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
- */
-static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
+static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 {
-	u64 host_tsc, tsc_offset;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	host_tsc = rdtsc();
-	tsc_offset = vmcs_read64(TSC_OFFSET);
-	return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
+	if (is_guest_mode(vcpu) &&
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
+
+	return vcpu->arch.tsc_offset;
 }
 
 /*
@@ -3524,12 +3527,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
-	case MSR_IA32_TSC:
-		msr_info->data = guest_read_tsc(vcpu);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
@@ -3646,17 +3645,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
-	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr_info);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
 		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
 			return 1;
 
 		vmx->spec_ctrl = data;
@@ -3682,7 +3677,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
@@ -4553,12 +4547,6 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
 	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
 }
 
-static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
-{
-	if (enable_ept)
-		vmx_flush_tlb(vcpu, true);
-}
-
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -4776,14 +4764,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	else
 		hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
 
-	if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
-		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
-			      SECONDARY_EXEC_DESC);
-		hw_cr4 &= ~X86_CR4_UMIP;
-	} else if (!is_guest_mode(vcpu) ||
-	           !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
-		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+	if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
+		if (cr4 & X86_CR4_UMIP) {
+			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 				SECONDARY_EXEC_DESC);
+			hw_cr4 &= ~X86_CR4_UMIP;
+		} else if (!is_guest_mode(vcpu) ||
+			!nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
+			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+					SECONDARY_EXEC_DESC);
+	}
 
 	if (cr4 & X86_CR4_VMXE) {
 		/*
@@ -9287,7 +9277,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	} else {
 		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
@@ -9315,7 +9305,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
 			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 }
 
@@ -9495,9 +9485,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 }
 STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
 
-static bool vmx_has_high_real_mode_segbase(void)
+static bool vmx_has_emulated_msr(int index)
 {
-	return enable_unrestricted_guest || emulate_invalid_guest_state;
+	switch (index) {
+	case MSR_IA32_SMBASE:
+		/*
+		 * We cannot do SMM unless we can run the guest in big
+		 * real mode.
+		 */
+		return enable_unrestricted_guest || emulate_invalid_guest_state;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		/* This is AMD only.  */
+		return false;
+	default:
+		return true;
+	}
 }
 
 static bool vmx_mpx_supported(void)
@@ -9512,12 +9514,6 @@ static bool vmx_xsaves_supported(void)
 		SECONDARY_EXEC_XSAVES;
 }
 
-static bool vmx_umip_emulated(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_DESC;
-}
-
 static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -9735,8 +9731,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * is no need to worry about the conditional branch over the wrmsr
 	 * being speculatively taken.
 	 */
-	if (vmx->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 
@@ -9884,8 +9879,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
 		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
-	if (vmx->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
@@ -10608,6 +10602,16 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+	    !page_address_valid(vcpu, vmcs12->apic_access_addr))
+		return -EINVAL;
+	else
+		return 0;
+}
+
 static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
 					   struct vmcs12 *vmcs12)
 {
@@ -11176,11 +11180,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 	}
 
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
-		vmcs_write64(TSC_OFFSET,
-			vcpu->arch.tsc_offset + vmcs12->tsc_offset);
-	else
-		vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
 
@@ -11222,7 +11223,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		}
 	} else if (nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 
 	/*
@@ -11299,6 +11300,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
+	if (nested_vmx_check_apic_access_controls(vcpu, vmcs12))
+		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
 	if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
@@ -11420,6 +11424,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	u32 msr_entry_idx;
 	u32 exit_qual;
+	int r;
 
 	enter_guest_mode(vcpu);
 
@@ -11429,26 +11434,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
 	vmx_segment_cache_clear(vmx);
 
-	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
-		leave_guest_mode(vcpu);
-		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-		nested_vmx_entry_failure(vcpu, vmcs12,
-					 EXIT_REASON_INVALID_STATE, exit_qual);
-		return 1;
-	}
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
+
+	r = EXIT_REASON_INVALID_STATE;
+	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+		goto fail;
 
 	nested_get_vmcs12_pages(vcpu, vmcs12);
 
+	r = EXIT_REASON_MSR_LOAD_FAIL;
 	msr_entry_idx = nested_vmx_load_msr(vcpu,
 					    vmcs12->vm_entry_msr_load_addr,
 					    vmcs12->vm_entry_msr_load_count);
-	if (msr_entry_idx) {
-		leave_guest_mode(vcpu);
-		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-		nested_vmx_entry_failure(vcpu, vmcs12,
-				EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
-		return 1;
-	}
+	if (msr_entry_idx)
+		goto fail;
 
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
@@ -11457,6 +11457,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
 	 */
 	return 0;
+
+fail:
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+	leave_guest_mode(vcpu);
+	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+	nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual);
+	return 1;
 }
 
 /*
@@ -12028,6 +12036,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	leave_guest_mode(vcpu);
 
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+
 	if (likely(!vmx->fail)) {
 		if (exit_reason == -1)
 			sync_vmcs12(vcpu, vmcs12);
@@ -12065,7 +12076,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	} else if (!nested_cpu_has_ept(vmcs12) &&
 		   nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
@@ -12224,10 +12235,16 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
 
 static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u64 tscl = rdtsc();
-	u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
-	u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+	struct vcpu_vmx *vmx;
+	u64 tscl, guest_tscl, delta_tsc;
+
+	if (kvm_mwait_in_guest(vcpu->kvm))
+		return -EOPNOTSUPP;
+
+	vmx = to_vmx(vcpu);
+	tscl = rdtsc();
+	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
 
 	/* Convert to host delta tsc if tsc scaling is enabled */
 	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
@@ -12533,7 +12550,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
 
-		trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
+		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
 		if (set)
@@ -12622,7 +12639,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.hardware_enable = hardware_enable,
 	.hardware_disable = hardware_disable,
 	.cpu_has_accelerated_tpr = report_flexpriority,
-	.cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
+	.has_emulated_msr = vmx_has_emulated_msr,
 
 	.vm_init = vmx_vm_init,
 	.vm_alloc = vmx_vm_alloc,
@@ -12712,6 +12729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
+	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
 	.write_tsc_offset = vmx_write_tsc_offset,
 
 	.set_tdp_cr3 = vmx_set_cr3,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b2ff74b12ec4..71e7cda6d014 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -114,7 +114,7 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
 static bool __read_mostly report_ignored_msrs = true;
 module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
 
-unsigned int min_timer_period_us = 500;
+unsigned int min_timer_period_us = 200;
 module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
 
 static bool __read_mostly kvmclock_periodic_sync = true;
@@ -843,7 +843,10 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4);
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 #ifdef CONFIG_X86_64
-	cr3 &= ~CR3_PCID_INVD;
+	bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+	if (pcid_enabled)
+		cr3 &= ~CR3_PCID_INVD;
 #endif
 
 	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
@@ -1058,6 +1061,7 @@ static u32 emulated_msrs[] = {
 	MSR_SMI_COUNT,
 	MSR_PLATFORM_INFO,
 	MSR_MISC_FEATURES_ENABLES,
+	MSR_AMD64_VIRT_SPEC_CTRL,
 };
 
 static unsigned num_emulated_msrs;
@@ -1490,7 +1494,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 
 static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
 {
-	u64 curr_offset = vcpu->arch.tsc_offset;
+	u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
 	vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
 }
 
@@ -1532,7 +1536,9 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 
 u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 {
-	return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
+	u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
+
+	return tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
 }
 EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
 
@@ -2362,6 +2368,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vcpu->arch.smbase = data;
 		break;
+	case MSR_IA32_TSC:
+		kvm_write_tsc(vcpu, msr_info);
+		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
 			return 1;
@@ -2605,6 +2614,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = vcpu->arch.microcode_version;
 		break;
+	case MSR_IA32_TSC:
+		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+		break;
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -2819,7 +2831,8 @@ out:
 static inline bool kvm_can_mwait_in_guest(void)
 {
 	return boot_cpu_has(X86_FEATURE_MWAIT) &&
-		!boot_cpu_has_bug(X86_BUG_MONITOR);
+		!boot_cpu_has_bug(X86_BUG_MONITOR) &&
+		boot_cpu_has(X86_FEATURE_ARAT);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -2894,7 +2907,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * fringe case that is not enabled except via specific settings
 		 * of the module parameters.
 		 */
-		r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+		r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
 		break;
 	case KVM_CAP_VAPIC:
 		r = !kvm_x86_ops->cpu_has_accelerated_tpr();
@@ -4594,14 +4607,8 @@ static void kvm_init_msr_list(void)
 	num_msrs_to_save = j;
 
 	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		switch (emulated_msrs[i]) {
-		case MSR_IA32_SMBASE:
-			if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
-				continue;
-			break;
-		default:
-			break;
-		}
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+			continue;
 
 		if (j < i)
 			emulated_msrs[j] = emulated_msrs[i];
@@ -6662,9 +6669,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
-	int op_64_bit, r;
-
-	r = kvm_skip_emulated_instruction(vcpu);
+	int op_64_bit;
 
 	if (kvm_hv_hypercall_enabled(vcpu->kvm))
 		return kvm_hv_hypercall(vcpu);
@@ -6712,8 +6717,9 @@ out:
 	if (!op_64_bit)
 		ret = (u32)ret;
 	kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+
 	++vcpu->stat.hypercalls;
-	return r;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
 
@@ -7970,6 +7976,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct msr_data apic_base_msr;
 	int mmu_reset_needed = 0;
+	int cpuid_update_needed = 0;
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 	int ret = -EINVAL;
@@ -8008,8 +8015,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr0 = sregs->cr0;
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
+	cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) &
+				(X86_CR4_OSXSAVE | X86_CR4_PKE));
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
-	if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE))
+	if (cpuid_update_needed)
 		kvm_update_cpuid(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 7d35ce672989..c9492f764902 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -302,13 +302,6 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 	    __rem;						\
 	 })
 
-#define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
-#define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
-#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
-#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
-                                              KVM_X86_DISABLE_EXITS_HTL | \
-                                              KVM_X86_DISABLE_EXITS_PAUSE)
-
 static inline bool kvm_mwait_in_guest(struct kvm *kvm)
 {
 	return kvm->arch.mwait_in_guest;