Merge v5.19-rc3 into usb-next

We need the USB fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

13 files changed, 318 insertions, 161 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index f1bdac3f5aa8..0e68b4c937fc 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2039,6 +2039,19 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 	}
 }
 
+static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic)
+{
+	struct kvm *kvm = apic->vcpu->kvm;
+
+	if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm))
+		return;
+
+	if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id)
+		return;
+
+	kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED);
+}
+
 static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 {
 	int ret = 0;
@@ -2047,10 +2060,12 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 	switch (reg) {
 	case APIC_ID:		/* Local APIC ID */
-		if (!apic_x2apic_mode(apic))
+		if (!apic_x2apic_mode(apic)) {
 			kvm_apic_set_xapic_id(apic, val >> 24);
-		else
+			kvm_lapic_xapic_id_updated(apic);
+		} else {
 			ret = 1;
+		}
 		break;
 
 	case APIC_TASKPRI:
@@ -2336,8 +2351,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 			     MSR_IA32_APICBASE_BASE;
 
 	if ((value & MSR_IA32_APICBASE_ENABLE) &&
-	     apic->base_address != APIC_DEFAULT_PHYS_BASE)
-		pr_warn_once("APIC base relocation is unsupported by KVM");
+	     apic->base_address != APIC_DEFAULT_PHYS_BASE) {
+		kvm_set_apicv_inhibit(apic->vcpu->kvm,
+				      APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
+	}
 }
 
 void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
@@ -2648,6 +2665,8 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 			icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
 			__kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
 		}
+	} else {
+		kvm_lapic_xapic_id_updated(vcpu->arch.apic);
 	}
 
 	return 0;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f4653688fa6d..17252f39bd7c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3411,7 +3411,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 			root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT),
 					      i << 30, PT32_ROOT_LEVEL, true);
 			mmu->pae_root[i] = root | PT_PRESENT_MASK |
-					   shadow_me_mask;
+					   shadow_me_value;
 		}
 		mmu->root.hpa = __pa(mmu->pae_root);
 	} else {
@@ -5179,7 +5179,7 @@ static void __kvm_mmu_free_obsolete_roots(struct kvm *kvm, struct kvm_mmu *mmu)
 		roots_to_free |= KVM_MMU_ROOT_CURRENT;
 
 	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
-		if (is_obsolete_root(kvm, mmu->root.hpa))
+		if (is_obsolete_root(kvm, mmu->prev_roots[i].hpa))
 			roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
 	}
 
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index 6d3b3e5a5533..ee4802d7b36c 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -146,6 +146,15 @@ static bool try_step_up(struct tdp_iter *iter)
 }
 
 /*
+ * Step the iterator back up a level in the paging structure. Should only be
+ * used when the iterator is below the root level.
+ */
+void tdp_iter_step_up(struct tdp_iter *iter)
+{
+	WARN_ON(!try_step_up(iter));
+}
+
+/*
  * Step to the next SPTE in a pre-order traversal of the paging structure.
  * To get to the next SPTE, the iterator either steps down towards the goal
  * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index f0af385c56e0..adfca0cf94d3 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -114,5 +114,6 @@ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root,
 		    int min_level, gfn_t next_last_level_gfn);
 void tdp_iter_next(struct tdp_iter *iter);
 void tdp_iter_restart(struct tdp_iter *iter);
+void tdp_iter_step_up(struct tdp_iter *iter);
 
 #endif /* __KVM_X86_MMU_TDP_ITER_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 841feaa48be5..7b9265d67131 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1742,12 +1742,12 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
 	gfn_t start = slot->base_gfn;
 	gfn_t end = start + slot->npages;
 	struct tdp_iter iter;
+	int max_mapping_level;
 	kvm_pfn_t pfn;
 
 	rcu_read_lock();
 
 	tdp_root_for_each_pte(iter, root, start, end) {
-retry:
 		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
 
@@ -1755,15 +1755,41 @@ retry:
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
+		/*
+		 * This is a leaf SPTE. Check if the PFN it maps can
+		 * be mapped at a higher level.
+		 */
 		pfn = spte_to_pfn(iter.old_spte);
-		if (kvm_is_reserved_pfn(pfn) ||
-		    iter.level >= kvm_mmu_max_mapping_level(kvm, slot, iter.gfn,
-							    pfn, PG_LEVEL_NUM))
+
+		if (kvm_is_reserved_pfn(pfn))
 			continue;
 
+		max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
+				iter.gfn, pfn, PG_LEVEL_NUM);
+
+		WARN_ON(max_mapping_level < iter.level);
+
+		/*
+		 * If this page is already mapped at the highest
+		 * viable level, there's nothing more to do.
+		 */
+		if (max_mapping_level == iter.level)
+			continue;
+
+		/*
+		 * The page can be remapped at a higher level, so step
+		 * up to zap the parent SPTE.
+		 */
+		while (max_mapping_level > iter.level)
+			tdp_iter_step_up(&iter);
+
 		/* Note, a successful atomic zap also does a remote TLB flush. */
-		if (tdp_mmu_zap_spte_atomic(kvm, &iter))
-			goto retry;
+		tdp_mmu_zap_spte_atomic(kvm, &iter);
+
+		/*
+		 * If the atomic zap fails, the iter will recurse back into
+		 * the same subtree to retry.
+		 */
 	}
 
 	rcu_read_unlock();
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 54fe03714f8a..d1bc5820ea46 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -291,58 +291,91 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu)
 static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source,
 				       u32 icrl, u32 icrh, u32 index)
 {
-	u32 dest, apic_id;
-	struct kvm_vcpu *vcpu;
+	u32 l1_physical_id, dest;
+	struct kvm_vcpu *target_vcpu;
 	int dest_mode = icrl & APIC_DEST_MASK;
 	int shorthand = icrl & APIC_SHORT_MASK;
 	struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
-	u32 *avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page);
 
 	if (shorthand != APIC_DEST_NOSHORT)
 		return -EINVAL;
 
-	/*
-	 * The AVIC incomplete IPI #vmexit info provides index into
-	 * the physical APIC ID table, which can be used to derive
-	 * guest physical APIC ID.
-	 */
+	if (apic_x2apic_mode(source))
+		dest = icrh;
+	else
+		dest = GET_APIC_DEST_FIELD(icrh);
+
 	if (dest_mode == APIC_DEST_PHYSICAL) {
-		apic_id = index;
+		/* broadcast destination, use slow path */
+		if (apic_x2apic_mode(source) && dest == X2APIC_BROADCAST)
+			return -EINVAL;
+		if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST)
+			return -EINVAL;
+
+		l1_physical_id = dest;
+
+		if (WARN_ON_ONCE(l1_physical_id != index))
+			return -EINVAL;
+
 	} else {
-		if (!apic_x2apic_mode(source)) {
-			/* For xAPIC logical mode, the index is for logical APIC table. */
-			apic_id = avic_logical_id_table[index] & 0x1ff;
+		u32 bitmap, cluster;
+		int logid_index;
+
+		if (apic_x2apic_mode(source)) {
+			/* 16 bit dest mask, 16 bit cluster id */
+			bitmap = dest & 0xFFFF0000;
+			cluster = (dest >> 16) << 4;
+		} else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) {
+			/* 8 bit dest mask*/
+			bitmap = dest;
+			cluster = 0;
 		} else {
-			return -EINVAL;
+			/* 4 bit desk mask, 4 bit cluster id */
+			bitmap = dest & 0xF;
+			cluster = (dest >> 4) << 2;
 		}
-	}
 
-	/*
-	 * Assuming vcpu ID is the same as physical apic ID,
-	 * and use it to retrieve the target vCPU.
-	 */
-	vcpu = kvm_get_vcpu_by_id(kvm, apic_id);
-	if (!vcpu)
-		return -EINVAL;
+		if (unlikely(!bitmap))
+			/* guest bug: nobody to send the logical interrupt to */
+			return 0;
 
-	if (apic_x2apic_mode(vcpu->arch.apic))
-		dest = icrh;
-	else
-		dest = GET_APIC_DEST_FIELD(icrh);
+		if (!is_power_of_2(bitmap))
+			/* multiple logical destinations, use slow path */
+			return -EINVAL;
 
-	/*
-	 * Try matching the destination APIC ID with the vCPU.
-	 */
-	if (kvm_apic_match_dest(vcpu, source, shorthand, dest, dest_mode)) {
-		vcpu->arch.apic->irr_pending = true;
-		svm_complete_interrupt_delivery(vcpu,
-						icrl & APIC_MODE_MASK,
-						icrl & APIC_INT_LEVELTRIG,
-						icrl & APIC_VECTOR_MASK);
-		return 0;
+		logid_index = cluster + __ffs(bitmap);
+
+		if (apic_x2apic_mode(source)) {
+			l1_physical_id = logid_index;
+		} else {
+			u32 *avic_logical_id_table =
+				page_address(kvm_svm->avic_logical_id_table_page);
+
+			u32 logid_entry = avic_logical_id_table[logid_index];
+
+			if (WARN_ON_ONCE(index != logid_index))
+				return -EINVAL;
+
+			/* guest bug: non existing/reserved logical destination */
+			if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK)))
+				return 0;
+
+			l1_physical_id = logid_entry &
+					 AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
+		}
 	}
 
-	return -EINVAL;
+	target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id);
+	if (unlikely(!target_vcpu))
+		/* guest bug: non existing vCPU is a target of this IPI*/
+		return 0;
+
+	target_vcpu->arch.apic->irr_pending = true;
+	svm_complete_interrupt_delivery(target_vcpu,
+					icrl & APIC_MODE_MASK,
+					icrl & APIC_INT_LEVELTRIG,
+					icrl & APIC_VECTOR_MASK);
+	return 0;
 }
 
 static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source,
@@ -508,35 +541,6 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
-{
-	u64 *old, *new;
-	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 id = kvm_xapic_id(vcpu->arch.apic);
-
-	if (vcpu->vcpu_id == id)
-		return 0;
-
-	old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id);
-	new = avic_get_physical_id_entry(vcpu, id);
-	if (!new || !old)
-		return 1;
-
-	/* We need to move physical_id_entry to new offset */
-	*new = *old;
-	*old = 0ULL;
-	to_svm(vcpu)->avic_physical_id_cache = new;
-
-	/*
-	 * Also update the guest physical APIC ID in the logical
-	 * APIC ID table entry if already setup the LDR.
-	 */
-	if (svm->ldr_reg)
-		avic_handle_ldr_update(vcpu);
-
-	return 0;
-}
-
 static void avic_handle_dfr_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -555,10 +559,6 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu)
 				AVIC_UNACCEL_ACCESS_OFFSET_MASK;
 
 	switch (offset) {
-	case APIC_ID:
-		if (avic_handle_apic_id_update(vcpu))
-			return 0;
-		break;
 	case APIC_LDR:
 		if (avic_handle_ldr_update(vcpu))
 			return 0;
@@ -650,8 +650,6 @@ int avic_init_vcpu(struct vcpu_svm *svm)
 
 void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 {
-	if (avic_handle_apic_id_update(vcpu) != 0)
-		return;
 	avic_handle_dfr_update(vcpu);
 	avic_handle_ldr_update(vcpu);
 }
@@ -910,7 +908,9 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
 			  BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
 			  BIT(APICV_INHIBIT_REASON_X2APIC) |
 			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
-			  BIT(APICV_INHIBIT_REASON_SEV);
+			  BIT(APICV_INHIBIT_REASON_SEV)      |
+			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
+			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
 
 	return supported & BIT(reason);
 }
@@ -946,7 +946,7 @@ out:
 	return ret;
 }
 
-void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	u64 entry;
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
@@ -978,7 +978,7 @@ void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
 }
 
-void __avic_vcpu_put(struct kvm_vcpu *vcpu)
+void avic_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	u64 entry;
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -997,25 +997,6 @@ void __avic_vcpu_put(struct kvm_vcpu *vcpu)
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 }
 
-static void avic_vcpu_load(struct kvm_vcpu *vcpu)
-{
-	int cpu = get_cpu();
-
-	WARN_ON(cpu != vcpu->cpu);
-
-	__avic_vcpu_load(vcpu, cpu);
-
-	put_cpu();
-}
-
-static void avic_vcpu_put(struct kvm_vcpu *vcpu)
-{
-	preempt_disable();
-
-	__avic_vcpu_put(vcpu);
-
-	preempt_enable();
-}
 
 void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
@@ -1042,7 +1023,7 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 	vmcb_mark_dirty(vmcb, VMCB_AVIC);
 
 	if (activated)
-		avic_vcpu_load(vcpu);
+		avic_vcpu_load(vcpu, vcpu->cpu);
 	else
 		avic_vcpu_put(vcpu);
 
@@ -1075,5 +1056,5 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu)
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
-	avic_vcpu_load(vcpu);
+	avic_vcpu_load(vcpu, vcpu->cpu);
 }
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index bed5e1692cef..ba7cd26f438f 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -616,6 +616,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	struct vmcb *vmcb01 = svm->vmcb01.ptr;
 	struct vmcb *vmcb02 = svm->nested.vmcb02.ptr;
+	u32 pause_count12;
+	u32 pause_thresh12;
 
 	/*
 	 * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2,
@@ -671,27 +673,25 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	if (!nested_vmcb_needs_vls_intercept(svm))
 		vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
 
+	pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0;
+	pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 0;
 	if (kvm_pause_in_guest(svm->vcpu.kvm)) {
-		/* use guest values since host doesn't use them */
-		vmcb02->control.pause_filter_count =
-				svm->pause_filter_enabled ?
-				svm->nested.ctl.pause_filter_count : 0;
+		/* use guest values since host doesn't intercept PAUSE */
+		vmcb02->control.pause_filter_count = pause_count12;
+		vmcb02->control.pause_filter_thresh = pause_thresh12;
 
-		vmcb02->control.pause_filter_thresh =
-				svm->pause_threshold_enabled ?
-				svm->nested.ctl.pause_filter_thresh : 0;
-
-	} else if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) {
-		/* use host values when guest doesn't use them */
+	} else {
+		/* start from host values otherwise */
 		vmcb02->control.pause_filter_count = vmcb01->control.pause_filter_count;
 		vmcb02->control.pause_filter_thresh = vmcb01->control.pause_filter_thresh;
-	} else {
-		/*
-		 * Intercept every PAUSE otherwise and
-		 * ignore both host and guest values
-		 */
-		vmcb02->control.pause_filter_count = 0;
-		vmcb02->control.pause_filter_thresh = 0;
+
+		/* ... but ensure filtering is disabled if so requested.  */
+		if (vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) {
+			if (!pause_count12)
+				vmcb02->control.pause_filter_count = 0;
+			if (!pause_thresh12)
+				vmcb02->control.pause_filter_thresh = 0;
+		}
 	}
 
 	nested_svm_transition_tlb_flush(vcpu);
@@ -951,8 +951,11 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	vmcb12->control.event_inj         = svm->nested.ctl.event_inj;
 	vmcb12->control.event_inj_err     = svm->nested.ctl.event_inj_err;
 
-	if (!kvm_pause_in_guest(vcpu->kvm) && vmcb02->control.pause_filter_count)
+	if (!kvm_pause_in_guest(vcpu->kvm)) {
 		vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count;
+		vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS);
+
+	}
 
 	nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr);
 
@@ -982,7 +985,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) {
 		WARN_ON(!svm->tsc_scaling_enabled);
 		vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio;
-		svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
+		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 	}
 
 	svm->nested.ctl.nested_cr3 = 0;
@@ -1387,7 +1390,7 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu)
 	vcpu->arch.tsc_scaling_ratio =
 		kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio,
 					       svm->tsc_ratio_msr);
-	svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
+	__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 }
 
 /* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 200045f71df0..87da90360bc7 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -465,11 +465,24 @@ static int has_svm(void)
 	return 1;
 }
 
+void __svm_write_tsc_multiplier(u64 multiplier)
+{
+	preempt_disable();
+
+	if (multiplier == __this_cpu_read(current_tsc_ratio))
+		goto out;
+
+	wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+	__this_cpu_write(current_tsc_ratio, multiplier);
+out:
+	preempt_enable();
+}
+
 static void svm_hardware_disable(void)
 {
 	/* Make sure we clean up behind us */
 	if (tsc_scaling)
-		wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
+		__svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT);
 
 	cpu_svm_disable();
 
@@ -515,8 +528,7 @@ static int svm_hardware_enable(void)
 		 * Set the default value, even if we don't use TSC scaling
 		 * to avoid having stale value in the msr
 		 */
-		wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
-		__this_cpu_write(current_tsc_ratio, SVM_TSC_RATIO_DEFAULT);
+		__svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT);
 	}
 
 
@@ -909,7 +921,7 @@ static void grow_ple_window(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	int old = control->pause_filter_count;
 
-	if (kvm_pause_in_guest(vcpu->kvm) || !old)
+	if (kvm_pause_in_guest(vcpu->kvm))
 		return;
 
 	control->pause_filter_count = __grow_ple_window(old,
@@ -930,7 +942,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	int old = control->pause_filter_count;
 
-	if (kvm_pause_in_guest(vcpu->kvm) || !old)
+	if (kvm_pause_in_guest(vcpu->kvm))
 		return;
 
 	control->pause_filter_count =
@@ -999,11 +1011,12 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
-void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
+static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier)
 {
-	wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+	__svm_write_tsc_multiplier(multiplier);
 }
 
+
 /* Evaluate instruction intercepts that depend on guest CPUID features. */
 static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
 					      struct vcpu_svm *svm)
@@ -1363,13 +1376,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		sev_es_prepare_switch_to_guest(hostsa);
 	}
 
-	if (tsc_scaling) {
-		u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio;
-		if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
-			__this_cpu_write(current_tsc_ratio, tsc_ratio);
-			wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
-		}
-	}
+	if (tsc_scaling)
+		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 
 	if (likely(tsc_aux_uret_slot >= 0))
 		kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
@@ -1392,13 +1400,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		indirect_branch_prediction_barrier();
 	}
 	if (kvm_vcpu_apicv_active(vcpu))
-		__avic_vcpu_load(vcpu, cpu);
+		avic_vcpu_load(vcpu, cpu);
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	if (kvm_vcpu_apicv_active(vcpu))
-		__avic_vcpu_put(vcpu);
+		avic_vcpu_put(vcpu);
 
 	svm_prepare_host_switch(vcpu);
 
@@ -4255,6 +4263,8 @@ out:
 
 static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 {
+	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR)
+		vcpu->arch.at_instruction_boundary = true;
 }
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 21c5460e947a..1bddd336a27e 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -590,7 +590,7 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 			       bool has_error_code, u32 error_code);
 int nested_svm_exit_special(struct vcpu_svm *svm);
 void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu);
-void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier);
+void __svm_write_tsc_multiplier(u64 multiplier);
 void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
 				       struct vmcb_control_area *control);
 void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm,
@@ -610,8 +610,8 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb);
 int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu);
 int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu);
 int avic_init_vcpu(struct vcpu_svm *svm);
-void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
-void __avic_vcpu_put(struct kvm_vcpu *vcpu);
+void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+void avic_vcpu_put(struct kvm_vcpu *vcpu);
 void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu);
 void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
 void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index a07e8cd753ec..3a919e49129b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -229,6 +229,9 @@ static const struct {
 #define L1D_CACHE_ORDER 4
 static void *vmx_l1d_flush_pages;
 
+/* Control for disabling CPU Fill buffer clear */
+static bool __read_mostly vmx_fb_clear_ctrl_available;
+
 static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 {
 	struct page *page;
@@ -360,6 +363,60 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
 	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
 }
 
+static void vmx_setup_fb_clear_ctrl(void)
+{
+	u64 msr;
+
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) &&
+	    !boot_cpu_has_bug(X86_BUG_MDS) &&
+	    !boot_cpu_has_bug(X86_BUG_TAA)) {
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+		if (msr & ARCH_CAP_FB_CLEAR_CTRL)
+			vmx_fb_clear_ctrl_available = true;
+	}
+}
+
+static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
+{
+	u64 msr;
+
+	if (!vmx->disable_fb_clear)
+		return;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	msr |= FB_CLEAR_DIS;
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	/* Cache the MSR value to avoid reading it later */
+	vmx->msr_ia32_mcu_opt_ctrl = msr;
+}
+
+static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
+{
+	if (!vmx->disable_fb_clear)
+		return;
+
+	vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS;
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
+}
+
+static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
+{
+	vmx->disable_fb_clear = vmx_fb_clear_ctrl_available;
+
+	/*
+	 * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS
+	 * at VMEntry. Skip the MSR read/write when a guest has no use case to
+	 * execute VERW.
+	 */
+	if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) ||
+	   ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO)))
+		vmx->disable_fb_clear = false;
+}
+
 static const struct kernel_param_ops vmentry_l1d_flush_ops = {
 	.set = vmentry_l1d_flush_set,
 	.get = vmentry_l1d_flush_get,
@@ -2252,6 +2309,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			ret = kvm_set_msr_common(vcpu, msr_info);
 	}
 
+	/* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */
+	if (msr_index == MSR_IA32_ARCH_CAPABILITIES)
+		vmx_update_fb_clear_dis(vcpu, vmx);
+
 	return ret;
 }
 
@@ -4553,6 +4614,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
 	vpid_sync_context(vmx->vpid);
+
+	vmx_update_fb_clear_dis(vcpu, vmx);
 }
 
 static void vmx_enable_irq_window(struct kvm_vcpu *vcpu)
@@ -6547,6 +6610,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 		return;
 
 	handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc));
+	vcpu->arch.at_instruction_boundary = true;
 }
 
 static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
@@ -6771,6 +6835,11 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 		vmx_l1d_flush(vcpu);
 	else if (static_branch_unlikely(&mds_user_clear))
 		mds_clear_cpu_buffers();
+	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
+		 kvm_arch_has_assigned_device(vcpu->kvm))
+		mds_clear_cpu_buffers();
+
+	vmx_disable_fb_clear(vmx);
 
 	if (vcpu->arch.cr2 != native_read_cr2())
 		native_write_cr2(vcpu->arch.cr2);
@@ -6780,6 +6849,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	vcpu->arch.cr2 = native_read_cr2();
 
+	vmx_enable_fb_clear(vmx);
+
 	guest_state_exit_irqoff();
 }
 
@@ -7708,7 +7779,9 @@ 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_BLOCKIRQ) |
+			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
+			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
 
 	return supported & BIT(reason);
 }
@@ -8211,6 +8284,8 @@ static int __init vmx_init(void)
 		return r;
 	}
 
+	vmx_setup_fb_clear_ctrl();
+
 	for_each_possible_cpu(cpu) {
 		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index b98c7e96697a..8d2342ede0c5 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -348,6 +348,8 @@ struct vcpu_vmx {
 	u64 msr_ia32_feature_control_valid_bits;
 	/* SGX Launch Control public key hash */
 	u64 msr_ia32_sgxlepubkeyhash[4];
+	u64 msr_ia32_mcu_opt_ctrl;
+	bool disable_fb_clear;
 
 	struct pt_desc pt_desc;
 	struct lbr_desc lbr_desc;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e9473c7c7390..1910e1e78b15 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -296,6 +296,8 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, nested_run),
 	STATS_DESC_COUNTER(VCPU, directed_yield_attempted),
 	STATS_DESC_COUNTER(VCPU, directed_yield_successful),
+	STATS_DESC_COUNTER(VCPU, preemption_reported),
+	STATS_DESC_COUNTER(VCPU, preemption_other),
 	STATS_DESC_ICOUNTER(VCPU, guest_mode)
 };
 
@@ -1615,6 +1617,9 @@ static u64 kvm_get_arch_capabilities(void)
 		 */
 	}
 
+	/* Guests don't need to know "Fill buffer clear control" exists */
+	data &= ~ARCH_CAP_FB_CLEAR_CTRL;
+
 	return data;
 }
 
@@ -4625,6 +4630,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 	struct kvm_memslots *slots;
 	static const u8 preempted = KVM_VCPU_PREEMPTED;
 
+	/*
+	 * The vCPU can be marked preempted if and only if the VM-Exit was on
+	 * an instruction boundary and will not trigger guest emulation of any
+	 * kind (see vcpu_run).  Vendor specific code controls (conservatively)
+	 * when this is true, for example allowing the vCPU to be marked
+	 * preempted if and only if the VM-Exit was due to a host interrupt.
+	 */
+	if (!vcpu->arch.at_instruction_boundary) {
+		vcpu->stat.preemption_other++;
+		return;
+	}
+
+	vcpu->stat.preemption_reported++;
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
@@ -4654,19 +4672,21 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
-	if (vcpu->preempted && !vcpu->arch.guest_state_protected)
-		vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
+	if (vcpu->preempted) {
+		if (!vcpu->arch.guest_state_protected)
+			vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
 
-	/*
-	 * Take the srcu lock as memslots will be accessed to check the gfn
-	 * cache generation against the memslots generation.
-	 */
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (kvm_xen_msr_enabled(vcpu->kvm))
-		kvm_xen_runstate_set_preempted(vcpu);
-	else
-		kvm_steal_time_set_preempted(vcpu);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		/*
+		 * Take the srcu lock as memslots will be accessed to check the gfn
+		 * cache generation against the memslots generation.
+		 */
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		if (kvm_xen_msr_enabled(vcpu->kvm))
+			kvm_xen_runstate_set_preempted(vcpu);
+		else
+			kvm_steal_time_set_preempted(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	}
 
 	static_call(kvm_x86_vcpu_put)(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
@@ -9833,6 +9853,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
 		return;
 
 	down_read(&vcpu->kvm->arch.apicv_update_lock);
+	preempt_disable();
 
 	activate = kvm_vcpu_apicv_activated(vcpu);
 
@@ -9853,6 +9874,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 out:
+	preempt_enable();
 	up_read(&vcpu->kvm->arch.apicv_update_lock);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv);
@@ -10422,6 +10444,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
+		/*
+		 * If another guest vCPU requests a PV TLB flush in the middle
+		 * of instruction emulation, the rest of the emulation could
+		 * use a stale page translation. Assume that any code after
+		 * this point can start executing an instruction.
+		 */
+		vcpu->arch.at_instruction_boundary = false;
 		if (kvm_vcpu_running(vcpu)) {
 			r = vcpu_enter_guest(vcpu);
 		} else {
diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index ee5c4ae0755c..532a535a9e99 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -159,8 +159,10 @@ static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu)
 	 * behalf of the vCPU. Only if the VMM does actually block
 	 * does it need to enter RUNSTATE_blocked.
 	 */
-	if (vcpu->preempted)
-		kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable);
+	if (WARN_ON_ONCE(!vcpu->preempted))
+		return;
+
+	kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable);
 }
 
 /* 32-bit compatibility definitions, also used natively in 32-bit build */