1 files changed, 258 insertions, 114 deletions

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 122d4ce3b1ab..24c0b2ba8fb9 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -57,11 +57,13 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+#ifdef MODULE
 static const struct x86_cpu_id svm_cpu_id[] = {
 	X86_FEATURE_MATCH(X86_FEATURE_SVM),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
+#endif
 
 #define IOPM_ALLOC_ORDER 2
 #define MSRPM_ALLOC_ORDER 1
@@ -387,6 +389,8 @@ static u8 rsm_ins_bytes[] = "\x0f\xaa";
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
+static void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate);
+static inline void avic_post_state_restore(struct kvm_vcpu *vcpu);
 
 static int nested_svm_exit_handled(struct vcpu_svm *svm);
 static int nested_svm_intercept(struct vcpu_svm *svm);
@@ -1003,33 +1007,32 @@ static void svm_cpu_uninit(int cpu)
 static int svm_cpu_init(int cpu)
 {
 	struct svm_cpu_data *sd;
-	int r;
 
 	sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
 	if (!sd)
 		return -ENOMEM;
 	sd->cpu = cpu;
-	r = -ENOMEM;
 	sd->save_area = alloc_page(GFP_KERNEL);
 	if (!sd->save_area)
-		goto err_1;
+		goto free_cpu_data;
 
 	if (svm_sev_enabled()) {
-		r = -ENOMEM;
 		sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
 					      sizeof(void *),
 					      GFP_KERNEL);
 		if (!sd->sev_vmcbs)
-			goto err_1;
+			goto free_save_area;
 	}
 
 	per_cpu(svm_data, cpu) = sd;
 
 	return 0;
 
-err_1:
+free_save_area:
+	__free_page(sd->save_area);
+free_cpu_data:
 	kfree(sd);
-	return r;
+	return -ENOMEM;
 
 }
 
@@ -1307,6 +1310,65 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 	}
 }
 
+/*
+ * The default MMIO mask is a single bit (excluding the present bit),
+ * which could conflict with the memory encryption bit. Check for
+ * memory encryption support and override the default MMIO mask if
+ * memory encryption is enabled.
+ */
+static __init void svm_adjust_mmio_mask(void)
+{
+	unsigned int enc_bit, mask_bit;
+	u64 msr, mask;
+
+	/* If there is no memory encryption support, use existing mask */
+	if (cpuid_eax(0x80000000) < 0x8000001f)
+		return;
+
+	/* If memory encryption is not enabled, use existing mask */
+	rdmsrl(MSR_K8_SYSCFG, msr);
+	if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+		return;
+
+	enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
+	mask_bit = boot_cpu_data.x86_phys_bits;
+
+	/* Increment the mask bit if it is the same as the encryption bit */
+	if (enc_bit == mask_bit)
+		mask_bit++;
+
+	/*
+	 * If the mask bit location is below 52, then some bits above the
+	 * physical addressing limit will always be reserved, so use the
+	 * rsvd_bits() function to generate the mask. This mask, along with
+	 * the present bit, will be used to generate a page fault with
+	 * PFER.RSV = 1.
+	 *
+	 * If the mask bit location is 52 (or above), then clear the mask.
+	 */
+	mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
+
+	kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
+}
+
+static void svm_hardware_teardown(void)
+{
+	int cpu;
+
+	if (svm_sev_enabled()) {
+		bitmap_free(sev_asid_bitmap);
+		bitmap_free(sev_reclaim_asid_bitmap);
+
+		sev_flush_asids();
+	}
+
+	for_each_possible_cpu(cpu)
+		svm_cpu_uninit(cpu);
+
+	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
+	iopm_base = 0;
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -1361,6 +1423,8 @@ static __init int svm_hardware_setup(void)
 		}
 	}
 
+	svm_adjust_mmio_mask();
+
 	for_each_possible_cpu(cpu) {
 		r = svm_cpu_init(cpu);
 		if (r)
@@ -1418,29 +1482,10 @@ static __init int svm_hardware_setup(void)
 	return 0;
 
 err:
-	__free_pages(iopm_pages, IOPM_ALLOC_ORDER);
-	iopm_base = 0;
+	svm_hardware_teardown();
 	return r;
 }
 
-static __exit void svm_hardware_unsetup(void)
-{
-	int cpu;
-
-	if (svm_sev_enabled()) {
-		bitmap_free(sev_asid_bitmap);
-		bitmap_free(sev_reclaim_asid_bitmap);
-
-		sev_flush_asids();
-	}
-
-	for_each_possible_cpu(cpu)
-		svm_cpu_uninit(cpu);
-
-	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
-	iopm_base = 0;
-}
-
 static void init_seg(struct vmcb_seg *seg)
 {
 	seg->selector = 0;
@@ -1502,7 +1547,10 @@ static void avic_init_vmcb(struct vcpu_svm *svm)
 	vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK;
 	vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK;
 	vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT;
-	vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
+	if (kvm_apicv_activated(svm->vcpu.kvm))
+		vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
+	else
+		vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
 }
 
 static void init_vmcb(struct vcpu_svm *svm)
@@ -1686,23 +1734,28 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
  * field of the VMCB. Therefore, we set up the
  * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here.
  */
-static int avic_init_access_page(struct kvm_vcpu *vcpu)
+static int avic_update_access_page(struct kvm *kvm, bool activate)
 {
-	struct kvm *kvm = vcpu->kvm;
 	int ret = 0;
 
 	mutex_lock(&kvm->slots_lock);
-	if (kvm->arch.apic_access_page_done)
+	/*
+	 * During kvm_destroy_vm(), kvm_pit_set_reinject() could trigger
+	 * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT
+	 * memory region. So, we need to ensure that kvm->mm == current->mm.
+	 */
+	if ((kvm->arch.apic_access_page_done == activate) ||
+	    (kvm->mm != current->mm))
 		goto out;
 
 	ret = __x86_set_memory_region(kvm,
 				      APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
 				      APIC_DEFAULT_PHYS_BASE,
-				      PAGE_SIZE);
+				      activate ? PAGE_SIZE : 0);
 	if (ret)
 		goto out;
 
-	kvm->arch.apic_access_page_done = true;
+	kvm->arch.apic_access_page_done = activate;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return ret;
@@ -1710,21 +1763,24 @@ out:
 
 static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 {
-	int ret;
 	u64 *entry, new_entry;
 	int id = vcpu->vcpu_id;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	ret = avic_init_access_page(vcpu);
-	if (ret)
-		return ret;
-
 	if (id >= AVIC_MAX_PHYSICAL_ID_COUNT)
 		return -EINVAL;
 
 	if (!svm->vcpu.arch.apic->regs)
 		return -EINVAL;
 
+	if (kvm_apicv_activated(vcpu->kvm)) {
+		int ret;
+
+		ret = avic_update_access_page(vcpu->kvm, true);
+		if (ret)
+			return ret;
+	}
+
 	svm->avic_backing_page = virt_to_page(svm->vcpu.arch.apic->regs);
 
 	/* Setting AVIC backing page address in the phy APIC ID table */
@@ -2009,6 +2065,18 @@ free_avic:
 	return err;
 }
 
+static int svm_vm_init(struct kvm *kvm)
+{
+	if (avic) {
+		int ret = avic_vm_init(kvm);
+		if (ret)
+			return ret;
+	}
+
+	kvm_apicv_init(kvm, avic);
+	return 0;
+}
+
 static inline int
 avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 {
@@ -2107,7 +2175,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	u32 dummy;
 	u32 eax = 1;
 
-	vcpu->arch.microcode_version = 0x01000065;
 	svm->spec_ctrl = 0;
 	svm->virt_spec_ctrl = 0;
 
@@ -2129,8 +2196,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 static int avic_init_vcpu(struct vcpu_svm *svm)
 {
 	int ret;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 
-	if (!kvm_vcpu_apicv_active(&svm->vcpu))
+	if (!avic || !irqchip_in_kernel(vcpu->kvm))
 		return 0;
 
 	ret = avic_init_backing_page(&svm->vcpu);
@@ -2144,7 +2212,7 @@ static int avic_init_vcpu(struct vcpu_svm *svm)
 	return ret;
 }
 
-static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
+static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm;
 	struct page *page;
@@ -2153,39 +2221,13 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	struct page *nested_msrpm_pages;
 	int err;
 
-	BUILD_BUG_ON_MSG(offsetof(struct vcpu_svm, vcpu) != 0,
-		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
-
-	svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
-	if (!svm) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
-						     GFP_KERNEL_ACCOUNT);
-	if (!svm->vcpu.arch.user_fpu) {
-		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
-		err = -ENOMEM;
-		goto free_partial_svm;
-	}
-
-	svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
-						     GFP_KERNEL_ACCOUNT);
-	if (!svm->vcpu.arch.guest_fpu) {
-		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
-		err = -ENOMEM;
-		goto free_user_fpu;
-	}
-
-	err = kvm_vcpu_init(&svm->vcpu, kvm, id);
-	if (err)
-		goto free_svm;
+	BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0);
+	svm = to_svm(vcpu);
 
 	err = -ENOMEM;
 	page = alloc_page(GFP_KERNEL_ACCOUNT);
 	if (!page)
-		goto uninit;
+		goto out;
 
 	msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
 	if (!msrpm_pages)
@@ -2206,7 +2248,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	/* We initialize this flag to true to make sure that the is_running
 	 * bit would be set the first time the vcpu is loaded.
 	 */
-	svm->avic_is_running = true;
+	if (irqchip_in_kernel(vcpu->kvm) && kvm_apicv_activated(vcpu->kvm))
+		svm->avic_is_running = true;
 
 	svm->nested.hsave = page_address(hsave_page);
 
@@ -2222,9 +2265,10 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	svm->asid_generation = 0;
 	init_vmcb(svm);
 
-	svm_init_osvw(&svm->vcpu);
+	svm_init_osvw(vcpu);
+	vcpu->arch.microcode_version = 0x01000065;
 
-	return &svm->vcpu;
+	return 0;
 
 free_page4:
 	__free_page(hsave_page);
@@ -2234,16 +2278,8 @@ free_page2:
 	__free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
 free_page1:
 	__free_page(page);
-uninit:
-	kvm_vcpu_uninit(&svm->vcpu);
-free_svm:
-	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
-free_user_fpu:
-	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
-free_partial_svm:
-	kmem_cache_free(kvm_vcpu_cache, svm);
 out:
-	return ERR_PTR(err);
+	return err;
 }
 
 static void svm_clear_current_vmcb(struct vmcb *vmcb)
@@ -2269,10 +2305,6 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
-	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
-	kmem_cache_free(kvm_vcpu_cache, svm);
 }
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -2343,6 +2375,8 @@ static void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
 
 static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
+	if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
+		kvm_vcpu_update_apicv(vcpu);
 	avic_set_running(vcpu, true);
 }
 
@@ -4192,6 +4226,8 @@ 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_SPEC_CTRL) &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD))
 			return 1;
@@ -4277,16 +4313,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD))
 			return 1;
 
-		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+		if (data & ~kvm_spec_ctrl_valid_bits(vcpu))
 			return 1;
 
 		svm->spec_ctrl = data;
-
 		if (!data)
 			break;
 
@@ -4310,13 +4346,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 		if (data & ~PRED_CMD_IBPB)
 			return 1;
-
+		if (!boot_cpu_has(X86_FEATURE_AMD_IBPB))
+			return 1;
 		if (!data)
 			break;
 
 		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
-		if (is_guest_mode(vcpu))
-			break;
 		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
@@ -4438,6 +4473,14 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
 {
 	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 	svm_clear_vintr(svm);
+
+	/*
+	 * For AVIC, the only reason to end up here is ExtINTs.
+	 * In this case AVIC was temporarily disabled for
+	 * requesting the IRQ window and we have to re-enable it.
+	 */
+	svm_toggle_avic_for_irq_window(&svm->vcpu, true);
+
 	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 	mark_dirty(svm->vmcb, VMCB_INTR);
 	++svm->vcpu.stat.irq_window_exits;
@@ -4519,9 +4562,9 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
 		 */
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			bool m = kvm_apic_match_dest(vcpu, apic,
-						     icrl & KVM_APIC_SHORT_MASK,
+						     icrl & APIC_SHORT_MASK,
 						     GET_APIC_DEST_FIELD(icrh),
-						     icrl & KVM_APIC_DEST_MASK);
+						     icrl & APIC_DEST_MASK);
 
 			if (m && !avic_vcpu_is_running(vcpu))
 				kvm_vcpu_wake_up(vcpu);
@@ -4935,7 +4978,8 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = control->exit_info_2;
 }
 
-static int handle_exit(struct kvm_vcpu *vcpu)
+static int handle_exit(struct kvm_vcpu *vcpu,
+	enum exit_fastpath_completion exit_fastpath)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct kvm_run *kvm_run = vcpu->run;
@@ -4993,7 +5037,10 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 		       __func__, svm->vmcb->control.exit_int_info,
 		       exit_code);
 
-	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
+	if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) {
+		kvm_skip_emulated_instruction(vcpu);
+		return 1;
+	} else if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
 	    || !svm_exit_handlers[exit_code]) {
 		vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code);
 		dump_vmcb(vcpu);
@@ -5129,30 +5176,82 @@ static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	return;
 }
 
-static bool svm_get_enable_apicv(struct kvm *kvm)
+static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
 {
-	return avic && irqchip_split(kvm);
 }
 
-static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
+static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
 {
 }
 
-static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
+static void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate)
 {
+	if (!avic || !lapic_in_kernel(vcpu))
+		return;
+
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_request_apicv_update(vcpu->kvm, activate,
+				 APICV_INHIBIT_REASON_IRQWIN);
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+}
+
+static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
+{
+	int ret = 0;
+	unsigned long flags;
+	struct amd_svm_iommu_ir *ir;
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm))
+		return 0;
+
+	/*
+	 * Here, we go through the per-vcpu ir_list to update all existing
+	 * interrupt remapping table entry targeting this vcpu.
+	 */
+	spin_lock_irqsave(&svm->ir_list_lock, flags);
+
+	if (list_empty(&svm->ir_list))
+		goto out;
+
+	list_for_each_entry(ir, &svm->ir_list, node) {
+		if (activate)
+			ret = amd_iommu_activate_guest_mode(ir->data);
+		else
+			ret = amd_iommu_deactivate_guest_mode(ir->data);
+		if (ret)
+			break;
+	}
+out:
+	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+	return ret;
 }
 
-/* Note: Currently only used by Hyper-V. */
 static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb;
+	bool activated = kvm_vcpu_apicv_active(vcpu);
 
-	if (kvm_vcpu_apicv_active(vcpu))
+	if (!avic)
+		return;
+
+	if (activated) {
+		/**
+		 * During AVIC temporary deactivation, guest could update
+		 * APIC ID, DFR and LDR registers, which would not be trapped
+		 * by avic_unaccelerated_access_interception(). In this case,
+		 * we need to check and update the AVIC logical APIC ID table
+		 * accordingly before re-activating.
+		 */
+		avic_post_state_restore(vcpu);
 		vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
-	else
+	} else {
 		vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
+	}
 	mark_dirty(vmcb, VMCB_AVIC);
+
+	svm_set_pi_irte_mode(vcpu, activated);
 }
 
 static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
@@ -5160,8 +5259,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 	return;
 }
 
-static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
+static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 {
+	if (!vcpu->arch.apicv_active)
+		return -1;
+
 	kvm_lapic_set_irr(vec, vcpu->arch.apic);
 	smp_mb__after_atomic();
 
@@ -5173,6 +5275,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		put_cpu();
 	} else
 		kvm_vcpu_wake_up(vcpu);
+
+	return 0;
 }
 
 static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
@@ -5439,9 +5543,6 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (kvm_vcpu_apicv_active(vcpu))
-		return;
-
 	/*
 	 * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
 	 * 1, because that's a separate STGI/VMRUN intercept.  The next time we
@@ -5451,6 +5552,13 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
 	 * window under the assumption that the hardware will set the GIF.
 	 */
 	if ((vgif_enabled(svm) || gif_set(svm)) && nested_svm_intr(svm)) {
+		/*
+		 * IRQ window is not needed when AVIC is enabled,
+		 * unless we have pending ExtINT since it cannot be injected
+		 * via AVIC. In such case, we need to temporarily disable AVIC,
+		 * and fallback to injecting IRQ via V_IRQ.
+		 */
+		svm_toggle_avic_for_irq_window(vcpu, false);
 		svm_set_vintr(svm);
 		svm_inject_irq(svm, 0x0);
 	}
@@ -5913,6 +6021,7 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+				    boot_cpu_has(X86_FEATURE_XSAVE) &&
 				    boot_cpu_has(X86_FEATURE_XSAVES);
 
 	/* Update nrips enabled cache */
@@ -5922,16 +6031,24 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 		return;
 
 	guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC);
+
+	/*
+	 * Currently, AVIC does not work with nested virtualization.
+	 * So, we disable AVIC when cpuid for SVM is set in the L1 guest.
+	 */
+	if (nested && guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+		kvm_request_apicv_update(vcpu->kvm, false,
+					 APICV_INHIBIT_REASON_NESTED);
 }
 
-#define F(x) bit(X86_FEATURE_##x)
+#define F feature_bit
 
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	switch (func) {
 	case 0x1:
 		if (avic)
-			entry->ecx &= ~bit(X86_FEATURE_X2APIC);
+			entry->ecx &= ~F(X2APIC);
 		break;
 	case 0x80000001:
 		if (nested)
@@ -6001,6 +6118,11 @@ static bool svm_has_wbinvd_exit(void)
 	return true;
 }
 
+static bool svm_pku_supported(void)
+{
+	return false;
+}
+
 #define PRE_EX(exit)  { .exit_code = (exit), \
 			.stage = X86_ICPT_PRE_EXCEPT, }
 #define POST_EX(exit) { .exit_code = (exit), \
@@ -6186,9 +6308,12 @@ out:
 	return ret;
 }
 
-static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
+static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu,
+	enum exit_fastpath_completion *exit_fastpath)
 {
-
+	if (!is_guest_mode(vcpu) &&
+		to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE)
+		*exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu);
 }
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
@@ -7242,11 +7367,27 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 		   (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT));
 }
 
+static bool svm_check_apicv_inhibit_reasons(ulong bit)
+{
+	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_HYPERV) |
+			  BIT(APICV_INHIBIT_REASON_NESTED) |
+			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
+			  BIT(APICV_INHIBIT_REASON_PIT_REINJ);
+
+	return supported & BIT(bit);
+}
+
+static void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate)
+{
+	avic_update_access_page(kvm, activate);
+}
+
 static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
 	.hardware_setup = svm_hardware_setup,
-	.hardware_unsetup = svm_hardware_unsetup,
+	.hardware_unsetup = svm_hardware_teardown,
 	.check_processor_compatibility = svm_check_processor_compat,
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
@@ -7259,7 +7400,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 
 	.vm_alloc = svm_vm_alloc,
 	.vm_free = svm_vm_free,
-	.vm_init = avic_vm_init,
+	.vm_init = svm_vm_init,
 	.vm_destroy = svm_vm_destroy,
 
 	.prepare_guest_switch = svm_prepare_guest_switch,
@@ -7301,6 +7442,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.run = svm_vcpu_run,
 	.handle_exit = handle_exit,
 	.skip_emulated_instruction = skip_emulated_instruction,
+	.update_emulated_instruction = NULL,
 	.set_interrupt_shadow = svm_set_interrupt_shadow,
 	.get_interrupt_shadow = svm_get_interrupt_shadow,
 	.patch_hypercall = svm_patch_hypercall,
@@ -7316,8 +7458,9 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
 	.set_virtual_apic_mode = svm_set_virtual_apic_mode,
-	.get_enable_apicv = svm_get_enable_apicv,
 	.refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl,
+	.check_apicv_inhibit_reasons = svm_check_apicv_inhibit_reasons,
+	.pre_update_apicv_exec_ctrl = svm_pre_update_apicv_exec_ctrl,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.hwapic_irr_update = svm_hwapic_irr_update,
 	.hwapic_isr_update = svm_hwapic_isr_update,
@@ -7341,6 +7484,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.xsaves_supported = svm_xsaves_supported,
 	.umip_emulated = svm_umip_emulated,
 	.pt_supported = svm_pt_supported,
+	.pku_supported = svm_pku_supported,
 
 	.set_supported_cpuid = svm_set_supported_cpuid,