1 files changed, 223 insertions, 197 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02159c967d29..5bdb5b854924 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -578,7 +578,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) {
 		values = &msrs->values[slot];
 		if (values->host != values->curr) {
-			wrmsrl(kvm_uret_msrs_list[slot], values->host);
+			wrmsrq(kvm_uret_msrs_list[slot], values->host);
 			values->curr = values->host;
 		}
 	}
@@ -590,10 +590,10 @@ static int kvm_probe_user_return_msr(u32 msr)
 	int ret;
 
 	preempt_disable();
-	ret = rdmsrl_safe(msr, &val);
+	ret = rdmsrq_safe(msr, &val);
 	if (ret)
 		goto out;
-	ret = wrmsrl_safe(msr, val);
+	ret = wrmsrq_safe(msr, val);
 out:
 	preempt_enable();
 	return ret;
@@ -630,7 +630,7 @@ static void kvm_user_return_msr_cpu_online(void)
 	int i;
 
 	for (i = 0; i < kvm_nr_uret_msrs; ++i) {
-		rdmsrl_safe(kvm_uret_msrs_list[i], &value);
+		rdmsrq_safe(kvm_uret_msrs_list[i], &value);
 		msrs->values[i].host = value;
 		msrs->values[i].curr = value;
 	}
@@ -644,7 +644,7 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
 	value = (value & mask) | (msrs->values[slot].host & ~mask);
 	if (value == msrs->values[slot].curr)
 		return 0;
-	err = wrmsrl_safe(kvm_uret_msrs_list[slot], value);
+	err = wrmsrq_safe(kvm_uret_msrs_list[slot], value);
 	if (err)
 		return 1;
 
@@ -800,9 +800,9 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto
 	ex->payload = payload;
 }
 
-static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
-		unsigned nr, bool has_error, u32 error_code,
-	        bool has_payload, unsigned long payload, bool reinject)
+static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned int nr,
+				   bool has_error, u32 error_code,
+				   bool has_payload, unsigned long payload)
 {
 	u32 prev_nr;
 	int class1, class2;
@@ -810,13 +810,10 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	/*
-	 * If the exception is destined for L2 and isn't being reinjected,
-	 * morph it to a VM-Exit if L1 wants to intercept the exception.  A
-	 * previously injected exception is not checked because it was checked
-	 * when it was original queued, and re-checking is incorrect if _L1_
-	 * injected the exception, in which case it's exempt from interception.
+	 * If the exception is destined for L2, morph it to a VM-Exit if L1
+	 * wants to intercept the exception.
 	 */
-	if (!reinject && is_guest_mode(vcpu) &&
+	if (is_guest_mode(vcpu) &&
 	    kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) {
 		kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code,
 					   has_payload, payload);
@@ -825,28 +822,9 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 
 	if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
 	queue:
-		if (reinject) {
-			/*
-			 * On VM-Entry, an exception can be pending if and only
-			 * if 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(kvm_is_exception_pending(vcpu));
-			vcpu->arch.exception.injected = true;
-			if (WARN_ON_ONCE(has_payload)) {
-				/*
-				 * A reinjected event has already
-				 * delivered its payload.
-				 */
-				has_payload = false;
-				payload = 0;
-			}
-		} else {
-			vcpu->arch.exception.pending = true;
-			vcpu->arch.exception.injected = false;
-		}
+		vcpu->arch.exception.pending = true;
+		vcpu->arch.exception.injected = false;
+
 		vcpu->arch.exception.has_error_code = has_error;
 		vcpu->arch.exception.vector = nr;
 		vcpu->arch.exception.error_code = error_code;
@@ -887,30 +865,53 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 {
-	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false);
+	kvm_multiple_exception(vcpu, nr, false, 0, false, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception);
 
-void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
-{
-	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true);
-}
-EXPORT_SYMBOL_GPL(kvm_requeue_exception);
 
 void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
 			   unsigned long payload)
 {
-	kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false);
+	kvm_multiple_exception(vcpu, nr, false, 0, true, payload);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception_p);
 
 static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
 				    u32 error_code, unsigned long payload)
 {
-	kvm_multiple_exception(vcpu, nr, true, error_code,
-			       true, payload, false);
+	kvm_multiple_exception(vcpu, nr, true, error_code, true, payload);
 }
 
+void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned int nr,
+			   bool has_error_code, u32 error_code)
+{
+
+	/*
+	 * On VM-Entry, an exception can be pending if and only if 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(kvm_is_exception_pending(vcpu));
+
+	/*
+	 * Do not check for interception when injecting an event for L2, as the
+	 * exception was checked for intercept when it was original queued, and
+	 * re-checking is incorrect if _L1_ injected the exception, in which
+	 * case it's exempt from interception.
+	 */
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	vcpu->arch.exception.injected = true;
+	vcpu->arch.exception.has_error_code = has_error_code;
+	vcpu->arch.exception.vector = nr;
+	vcpu->arch.exception.error_code = error_code;
+	vcpu->arch.exception.has_payload = false;
+	vcpu->arch.exception.payload = 0;
+}
+EXPORT_SYMBOL_GPL(kvm_requeue_exception);
+
 int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
 {
 	if (err)
@@ -980,16 +981,10 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu)
 
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
 {
-	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false);
+	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
 
-void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
-{
-	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true);
-}
-EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
-
 /*
  * Checks if cpl <= required_cpl; if true, return true.  Otherwise queue
  * a #GP and return false.
@@ -1179,7 +1174,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 
 		if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
 		    vcpu->arch.ia32_xss != kvm_host.xss)
-			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
+			wrmsrq(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
 
 	if (cpu_feature_enabled(X86_FEATURE_PKU) &&
@@ -1210,7 +1205,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 
 		if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
 		    vcpu->arch.ia32_xss != kvm_host.xss)
-			wrmsrl(MSR_IA32_XSS, kvm_host.xss);
+			wrmsrq(MSR_IA32_XSS, kvm_host.xss);
 	}
 
 }
@@ -1264,7 +1259,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	vcpu->arch.xcr0 = xcr0;
 
 	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 	return 0;
 }
 
@@ -1589,7 +1584,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc);
 	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
 	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
 	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
-	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
+	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO)
 
 static u64 kvm_get_arch_capabilities(void)
 {
@@ -1623,6 +1618,8 @@ static u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_MDS_NO;
 	if (!boot_cpu_has_bug(X86_BUG_RFDS))
 		data |= ARCH_CAP_RFDS_NO;
+	if (!boot_cpu_has_bug(X86_BUG_ITS))
+		data |= ARCH_CAP_ITS_NO;
 
 	if (!boot_cpu_has(X86_FEATURE_RTM)) {
 		/*
@@ -1665,7 +1662,7 @@ static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
 		*data = MSR_PLATFORM_INFO_CPUID_FAULT;
 		break;
 	case MSR_IA32_UCODE_REV:
-		rdmsrl_safe(index, data);
+		rdmsrq_safe(index, data);
 		break;
 	default:
 		return kvm_x86_call(get_feature_msr)(index, data);
@@ -2080,10 +2077,20 @@ EXPORT_SYMBOL_GPL(kvm_handle_invalid_op);
 
 static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn)
 {
-	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) &&
-	    !guest_cpu_cap_has(vcpu, X86_FEATURE_MWAIT))
+	bool enabled;
+
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS))
+		goto emulate_as_nop;
+
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT))
+		enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_MWAIT);
+	else
+		enabled = vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT;
+
+	if (!enabled)
 		return kvm_handle_invalid_op(vcpu);
 
+emulate_as_nop:
 	pr_warn_once("%s instruction emulated as NOP!\n", insn);
 	return kvm_emulate_as_nop(vcpu);
 }
@@ -2569,6 +2576,9 @@ EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier);
 
 static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset)
 {
+	if (vcpu->arch.guest_tsc_protected)
+		return;
+
 	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
 				   vcpu->arch.l1_tsc_offset,
 				   l1_offset);
@@ -2626,12 +2636,18 @@ static inline bool kvm_check_tsc_unstable(void)
  * participates in.
  */
 static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
-				  u64 ns, bool matched)
+				  u64 ns, bool matched, bool user_set_tsc)
 {
 	struct kvm *kvm = vcpu->kvm;
 
 	lockdep_assert_held(&kvm->arch.tsc_write_lock);
 
+	if (vcpu->arch.guest_tsc_protected)
+		return;
+
+	if (user_set_tsc)
+		vcpu->kvm->arch.user_set_tsc = true;
+
 	/*
 	 * We also track th most recent recorded KHZ, write and time to
 	 * allow the matching interval to be extended at each write.
@@ -2717,8 +2733,6 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
 		}
 	}
 
-	if (user_value)
-		kvm->arch.user_set_tsc = true;
 
 	/*
 	 * For a reliable TSC, we can match TSC offsets, and for an unstable
@@ -2738,7 +2752,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
 		matched = true;
 	}
 
-	__kvm_synchronize_tsc(vcpu, offset, data, ns, matched);
+	__kvm_synchronize_tsc(vcpu, offset, data, ns, matched, !!user_value);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 }
 
@@ -3116,15 +3130,17 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	return data.clock;
 }
 
-static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
+static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock,
+				    struct kvm_vcpu *vcpu,
 				    struct gfn_to_pfn_cache *gpc,
-				    unsigned int offset,
-				    bool force_tsc_unstable)
+				    unsigned int offset)
 {
-	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct pvclock_vcpu_time_info *guest_hv_clock;
+	struct pvclock_vcpu_time_info hv_clock;
 	unsigned long flags;
 
+	memcpy(&hv_clock, ref_hv_clock, sizeof(hv_clock));
+
 	read_lock_irqsave(&gpc->lock, flags);
 	while (!kvm_gpc_check(gpc, offset + sizeof(*guest_hv_clock))) {
 		read_unlock_irqrestore(&gpc->lock, flags);
@@ -3144,52 +3160,34 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 	 * it is consistent.
 	 */
 
-	guest_hv_clock->version = vcpu->hv_clock.version = (guest_hv_clock->version + 1) | 1;
+	guest_hv_clock->version = hv_clock.version = (guest_hv_clock->version + 1) | 1;
 	smp_wmb();
 
 	/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
-	vcpu->hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
+	hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
 
-	if (vcpu->pvclock_set_guest_stopped_request) {
-		vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
-		vcpu->pvclock_set_guest_stopped_request = false;
-	}
-
-	memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock));
-
-	if (force_tsc_unstable)
-		guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT;
+	memcpy(guest_hv_clock, &hv_clock, sizeof(*guest_hv_clock));
 
 	smp_wmb();
 
-	guest_hv_clock->version = ++vcpu->hv_clock.version;
+	guest_hv_clock->version = ++hv_clock.version;
 
 	kvm_gpc_mark_dirty_in_slot(gpc);
 	read_unlock_irqrestore(&gpc->lock, flags);
 
-	trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
+	trace_kvm_pvclock_update(vcpu->vcpu_id, &hv_clock);
 }
 
-static int kvm_guest_time_update(struct kvm_vcpu *v)
+int kvm_guest_time_update(struct kvm_vcpu *v)
 {
+	struct pvclock_vcpu_time_info hv_clock = {};
 	unsigned long flags, tgt_tsc_khz;
 	unsigned seq;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct kvm_arch *ka = &v->kvm->arch;
 	s64 kernel_ns;
 	u64 tsc_timestamp, host_tsc;
-	u8 pvclock_flags;
 	bool use_master_clock;
-#ifdef CONFIG_KVM_XEN
-	/*
-	 * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless
-	 * explicitly told to use TSC as its clocksource Xen will not set this bit.
-	 * This default behaviour led to bugs in some guest kernels which cause
-	 * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags.
-	 */
-	bool xen_pvclock_tsc_unstable =
-		ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
-#endif
 
 	kernel_ns = 0;
 	host_tsc = 0;
@@ -3250,35 +3248,57 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
 		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
-				   &vcpu->hv_clock.tsc_shift,
-				   &vcpu->hv_clock.tsc_to_system_mul);
+				   &vcpu->pvclock_tsc_shift,
+				   &vcpu->pvclock_tsc_mul);
 		vcpu->hw_tsc_khz = tgt_tsc_khz;
-		kvm_xen_update_tsc_info(v);
 	}
 
-	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
-	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
+	hv_clock.tsc_shift = vcpu->pvclock_tsc_shift;
+	hv_clock.tsc_to_system_mul = vcpu->pvclock_tsc_mul;
+	hv_clock.tsc_timestamp = tsc_timestamp;
+	hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
 	vcpu->last_guest_tsc = tsc_timestamp;
 
 	/* If the host uses TSC clocksource, then it is stable */
-	pvclock_flags = 0;
+	hv_clock.flags = 0;
 	if (use_master_clock)
-		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
+		hv_clock.flags |= PVCLOCK_TSC_STABLE_BIT;
 
-	vcpu->hv_clock.flags = pvclock_flags;
+	if (vcpu->pv_time.active) {
+		/*
+		 * GUEST_STOPPED is only supported by kvmclock, and KVM's
+		 * historic behavior is to only process the request if kvmclock
+		 * is active/enabled.
+		 */
+		if (vcpu->pvclock_set_guest_stopped_request) {
+			hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
+			vcpu->pvclock_set_guest_stopped_request = false;
+		}
+		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->pv_time, 0);
+
+		hv_clock.flags &= ~PVCLOCK_GUEST_STOPPED;
+	}
+
+	kvm_hv_setup_tsc_page(v->kvm, &hv_clock);
 
-	if (vcpu->pv_time.active)
-		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false);
 #ifdef CONFIG_KVM_XEN
+	/*
+	 * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless
+	 * explicitly told to use TSC as its clocksource Xen will not set this bit.
+	 * This default behaviour led to bugs in some guest kernels which cause
+	 * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags.
+	 *
+	 * Note!  Clear TSC_STABLE only for Xen clocks, i.e. the order matters!
+	 */
+	if (ka->xen.hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE)
+		hv_clock.flags &= ~PVCLOCK_TSC_STABLE_BIT;
+
 	if (vcpu->xen.vcpu_info_cache.active)
-		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache,
-					offsetof(struct compat_vcpu_info, time),
-					xen_pvclock_tsc_unstable);
+		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_info_cache,
+					offsetof(struct compat_vcpu_info, time));
 	if (vcpu->xen.vcpu_time_info_cache.active)
-		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0,
-					xen_pvclock_tsc_unstable);
+		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_time_info_cache, 0);
 #endif
-	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
 }
 
@@ -3544,7 +3564,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 					sizeof(u64)))
 		return 1;
 
-	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+	vcpu->arch.apf.send_always = (data & KVM_ASYNC_PF_SEND_ALWAYS);
 	vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
 
 	kvm_async_pf_wakeup_all(vcpu);
@@ -3733,7 +3753,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	u32 msr = msr_info->index;
 	u64 data = msr_info->data;
 
-	if (msr && msr == vcpu->kvm->arch.xen_hvm_config.msr)
+	/*
+	 * Do not allow host-initiated writes to trigger the Xen hypercall
+	 * page setup; it could incur locking paths which are not expected
+	 * if userspace sets the MSR in an unusual location.
+	 */
+	if (kvm_xen_is_hypercall_page_msr(vcpu->kvm, msr) &&
+	    !msr_info->host_initiated)
 		return kvm_xen_write_hypercall_page(vcpu, data);
 
 	switch (msr) {
@@ -3803,7 +3829,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!data)
 			break;
 
-		wrmsrl(MSR_IA32_PRED_CMD, data);
+		wrmsrq(MSR_IA32_PRED_CMD, data);
 		break;
 	}
 	case MSR_IA32_FLUSH_CMD:
@@ -3816,7 +3842,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!data)
 			break;
 
-		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
 		break;
 	case MSR_EFER:
 		return set_efer(vcpu, msr_info);
@@ -3889,7 +3915,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XMM3))
 				return 1;
 			vcpu->arch.ia32_misc_enable_msr = data;
-			kvm_update_cpuid_runtime(vcpu);
+			vcpu->arch.cpuid_dynamic_bits_dirty = true;
 		} else {
 			vcpu->arch.ia32_misc_enable_msr = data;
 		}
@@ -3906,7 +3932,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		if (msr_info->host_initiated) {
 			kvm_synchronize_tsc(vcpu, &data);
-		} else {
+		} else if (!vcpu->arch.guest_tsc_protected) {
 			u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset;
 			adjust_tsc_offset_guest(vcpu, adj);
 			vcpu->arch.ia32_tsc_adjust_msr += adj;
@@ -3924,7 +3950,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (data & ~kvm_caps.supported_xss)
 			return 1;
 		vcpu->arch.ia32_xss = data;
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
@@ -4573,6 +4599,11 @@ static bool kvm_is_vm_type_supported(unsigned long type)
 	return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
 }
 
+static inline u64 kvm_sync_valid_fields(struct kvm *kvm)
+{
+	return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS;
+}
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r = 0;
@@ -4681,7 +4712,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_REGS:
-		r = KVM_SYNC_X86_VALID_FIELDS;
+		r = kvm_sync_valid_fields(kvm);
 		break;
 	case KVM_CAP_ADJUST_CLOCK:
 		r = KVM_CLOCK_VALID_FLAGS;
@@ -4986,7 +5017,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			u64 offset = kvm_compute_l1_tsc_offset(vcpu,
 						vcpu->arch.last_guest_tsc);
 			kvm_vcpu_write_tsc_offset(vcpu, offset);
-			vcpu->arch.tsc_catchup = 1;
+			if (!vcpu->arch.guest_tsc_protected)
+				vcpu->arch.tsc_catchup = 1;
 		}
 
 		if (kvm_lapic_hv_timer_in_use(vcpu))
@@ -5725,8 +5757,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu,
 		tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset;
 		ns = get_kvmclock_base_ns();
 
-		kvm->arch.user_set_tsc = true;
-		__kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched);
+		__kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched, true);
 		raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
 		r = 0;
@@ -6905,23 +6936,15 @@ static int kvm_arch_suspend_notifier(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
-	int ret = 0;
 
-	mutex_lock(&kvm->lock);
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (!vcpu->arch.pv_time.active)
-			continue;
-
-		ret = kvm_set_guest_paused(vcpu);
-		if (ret) {
-			kvm_err("Failed to pause guest VCPU%d: %d\n",
-				vcpu->vcpu_id, ret);
-			break;
-		}
-	}
-	mutex_unlock(&kvm->lock);
+	/*
+	 * Ignore the return, marking the guest paused only "fails" if the vCPU
+	 * isn't using kvmclock; continuing on is correct and desirable.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		(void)kvm_set_guest_paused(vcpu);
 
-	return ret ? NOTIFY_BAD : NOTIFY_DONE;
+	return NOTIFY_DONE;
 }
 
 int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state)
@@ -9715,7 +9738,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 	 * with an exception.  PAT[0] is set to WB on RESET and also by the
 	 * kernel, i.e. failure indicates a kernel bug or broken firmware.
 	 */
-	if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) ||
+	if (rdmsrq_safe(MSR_IA32_CR_PAT, &host_pat) ||
 	    (host_pat & GENMASK(2, 0)) != 6) {
 		pr_err("host PAT[0] is not WB\n");
 		return -EIO;
@@ -9749,15 +9772,15 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 		kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0;
 	}
 
-	rdmsrl_safe(MSR_EFER, &kvm_host.efer);
+	rdmsrq_safe(MSR_EFER, &kvm_host.efer);
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		rdmsrl(MSR_IA32_XSS, kvm_host.xss);
+		rdmsrq(MSR_IA32_XSS, kvm_host.xss);
 
 	kvm_init_pmu_capability(ops->pmu_ops);
 
 	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
+		rdmsrq(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
 
 	r = ops->hardware_setup();
 	if (r != 0)
@@ -10953,7 +10976,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		switch_fpu_return();
 
 	if (vcpu->arch.guest_fpu.xfd_err)
-		wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+		wrmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -10968,6 +10991,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(0, 7);
 	}
 
+	vcpu->arch.host_debugctl = get_debugctlmsr();
+
 	guest_timing_enter_irqoff();
 
 	for (;;) {
@@ -11037,7 +11062,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_call(handle_exit_irqoff)(vcpu);
 
 	if (vcpu->arch.guest_fpu.xfd_err)
-		wrmsrl(MSR_IA32_XFD_ERR, 0);
+		wrmsrq(MSR_IA32_XFD_ERR, 0);
 
 	/*
 	 * Consume any pending interrupts, including the possible source of
@@ -11075,7 +11100,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	/*
 	 * Profile KVM exit RIPs:
 	 */
-	if (unlikely(prof_on == KVM_PROFILING)) {
+	if (unlikely(prof_on == KVM_PROFILING &&
+		     !vcpu->arch.guest_state_protected)) {
 		unsigned long rip = kvm_rip_read(vcpu);
 		profile_hit(KVM_PROFILING, (void *)rip);
 	}
@@ -11218,9 +11244,7 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu)
 	switch(vcpu->arch.mp_state) {
 	case KVM_MP_STATE_HALTED:
 	case KVM_MP_STATE_AP_RESET_HOLD:
-		vcpu->arch.pv.pv_unhalted = false;
-		vcpu->arch.mp_state =
-			KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 		fallthrough;
 	case KVM_MP_STATE_RUNNABLE:
 		vcpu->arch.apf.halted = false;
@@ -11297,9 +11321,8 @@ static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason)
 	++vcpu->stat.halt_exits;
 	if (lapic_in_kernel(vcpu)) {
 		if (kvm_vcpu_has_events(vcpu))
-			vcpu->arch.pv.pv_unhalted = false;
-		else
-			vcpu->arch.mp_state = state;
+			state = KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, state);
 		return 1;
 	} else {
 		vcpu->run->exit_reason = reason;
@@ -11472,6 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_queued_exception *ex = &vcpu->arch.exception;
 	struct kvm_run *kvm_run = vcpu->run;
+	u64 sync_valid_fields;
 	int r;
 
 	r = kvm_mmu_post_init_vm(vcpu->kvm);
@@ -11517,8 +11541,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	if ((kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) ||
-	    (kvm_run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)) {
+	sync_valid_fields = kvm_sync_valid_fields(vcpu->kvm);
+	if ((kvm_run->kvm_valid_regs & ~sync_valid_fields) ||
+	    (kvm_run->kvm_dirty_regs & ~sync_valid_fields)) {
 		r = -EINVAL;
 		goto out;
 	}
@@ -11576,7 +11601,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 out:
 	kvm_put_guest_fpu(vcpu);
-	if (kvm_run->kvm_valid_regs)
+	if (kvm_run->kvm_valid_regs && likely(!vcpu->arch.guest_state_protected))
 		store_regs(vcpu);
 	post_kvm_run_save(vcpu);
 	kvm_vcpu_srcu_read_unlock(vcpu);
@@ -11764,6 +11789,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 	if (kvm_mpx_supported())
 		kvm_load_guest_fpu(vcpu);
 
+	kvm_vcpu_srcu_read_lock(vcpu);
+
 	r = kvm_apic_accept_events(vcpu);
 	if (r < 0)
 		goto out;
@@ -11777,6 +11804,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 		mp_state->mp_state = vcpu->arch.mp_state;
 
 out:
+	kvm_vcpu_srcu_read_unlock(vcpu);
+
 	if (kvm_mpx_supported())
 		kvm_put_guest_fpu(vcpu);
 	vcpu_put(vcpu);
@@ -11819,10 +11848,10 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 		goto out;
 
 	if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
-		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED);
 		set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
 	} else
-		vcpu->arch.mp_state = mp_state->mp_state;
+		kvm_set_mp_state(vcpu, mp_state->mp_state);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	ret = 0;
@@ -11949,7 +11978,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs,
 	if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 &&
 	    sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 &&
 	    !is_protmode(vcpu))
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 
 	return 0;
 }
@@ -12252,9 +12281,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm);
 
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 	else
-		vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_UNINITIALIZED);
 
 	r = kvm_mmu_create(vcpu);
 	if (r < 0)
@@ -12361,6 +12390,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
+	kvm_clear_async_pf_completion_queue(vcpu);
+	kvm_mmu_unload(vcpu);
+
 	kvmclock_reset(vcpu);
 
 	kvm_x86_call(vcpu_free)(vcpu);
@@ -12754,31 +12786,6 @@ out:
 	return ret;
 }
 
-static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
-{
-	vcpu_load(vcpu);
-	kvm_mmu_unload(vcpu);
-	vcpu_put(vcpu);
-}
-
-static void kvm_unload_vcpu_mmus(struct kvm *kvm)
-{
-	unsigned long i;
-	struct kvm_vcpu *vcpu;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		kvm_clear_async_pf_completion_queue(vcpu);
-		kvm_unload_vcpu_mmu(vcpu);
-	}
-}
-
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
-	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
-	kvm_free_pit(kvm);
-}
-
 /**
  * __x86_set_memory_region: Setup KVM internal memory slot
  *
@@ -12857,6 +12864,17 @@ EXPORT_SYMBOL_GPL(__x86_set_memory_region);
 
 void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 {
+	/*
+	 * Stop all background workers and kthreads before destroying vCPUs, as
+	 * iterating over vCPUs in a different task while vCPUs are being freed
+	 * is unsafe, i.e. will lead to use-after-free.  The PIT also needs to
+	 * be stopped before IRQ routing is freed.
+	 */
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
+
+	kvm_free_pit(kvm);
+
 	kvm_mmu_pre_destroy_vm(kvm);
 }
 
@@ -12876,18 +12894,17 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		__x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
 		mutex_unlock(&kvm->slots_lock);
 	}
-	kvm_unload_vcpu_mmus(kvm);
-	kvm_x86_call(vm_destroy)(kvm);
+	kvm_destroy_vcpus(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
-	kvm_destroy_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
 	kvm_page_track_cleanup(kvm);
 	kvm_xen_destroy_vm(kvm);
 	kvm_hv_destroy_vm(kvm);
+	kvm_x86_call(vm_destroy)(kvm);
 }
 
 static void memslot_rmap_free(struct kvm_memory_slot *slot)
@@ -13381,8 +13398,8 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
 	if (!kvm_pv_async_pf_enabled(vcpu))
 		return false;
 
-	if (vcpu->arch.apf.send_user_only &&
-	    kvm_x86_call(get_cpl)(vcpu) == 0)
+	if (!vcpu->arch.apf.send_always &&
+	    (vcpu->arch.guest_state_protected || !kvm_x86_call(get_cpl)(vcpu)))
 		return false;
 
 	if (is_guest_mode(vcpu)) {
@@ -13472,7 +13489,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 	}
 
 	vcpu->arch.apf.halted = false;
-	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 }
 
 void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu)
@@ -13542,25 +13559,27 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
 
-bool kvm_arch_has_irq_bypass(void)
-{
-	return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
-}
-
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm *kvm = irqfd->kvm;
 	int ret;
 
-	irqfd->producer = prod;
 	kvm_arch_start_assignment(irqfd->kvm);
+
+	spin_lock_irq(&kvm->irqfds.lock);
+	irqfd->producer = prod;
+
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 1);
 	if (ret)
 		kvm_arch_end_assignment(irqfd->kvm);
 
+	spin_unlock_irq(&kvm->irqfds.lock);
+
+
 	return ret;
 }
 
@@ -13570,9 +13589,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	int ret;
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm *kvm = irqfd->kvm;
 
 	WARN_ON(irqfd->producer != prod);
-	irqfd->producer = NULL;
 
 	/*
 	 * When producer of consumer is unregistered, we change back to
@@ -13580,12 +13599,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	 * when the irq is masked/disabled or the consumer side (KVM
 	 * int this case doesn't want to receive the interrupts.
 	*/
+	spin_lock_irq(&kvm->irqfds.lock);
+	irqfd->producer = NULL;
+
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 0);
 	if (ret)
 		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
 		       " fails: %d\n", irqfd->consumer.token, ret);
 
+	spin_unlock_irq(&kvm->irqfds.lock);
+
+
 	kvm_arch_end_assignment(irqfd->kvm);
 }
 
@@ -13598,7 +13623,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
 				  struct kvm_kernel_irq_routing_entry *new)
 {
-	if (new->type != KVM_IRQ_ROUTING_MSI)
+	if (old->type != KVM_IRQ_ROUTING_MSI ||
+	    new->type != KVM_IRQ_ROUTING_MSI)
 		return true;
 
 	return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
@@ -13642,12 +13668,12 @@ int kvm_spec_ctrl_test_value(u64 value)
 
 	local_irq_save(flags);
 
-	if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value))
+	if (rdmsrq_safe(MSR_IA32_SPEC_CTRL, &saved_value))
 		ret = 1;
-	else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value))
+	else if (wrmsrq_safe(MSR_IA32_SPEC_CTRL, value))
 		ret = 1;
 	else
-		wrmsrl(MSR_IA32_SPEC_CTRL, saved_value);
+		wrmsrq(MSR_IA32_SPEC_CTRL, saved_value);
 
 	local_irq_restore(flags);