Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Radim Krčmář:
 "ARM:

   - Yet another race with VM destruction plugged

   - A set of small vgic fixes

  x86:

   - Preserve pending INIT

   - RCU fixes in paravirtual async pf, VM teardown, and VMXOFF
     emulation

   - nVMX interrupt injection and dirty tracking fixes

   - initialize to make UBSAN happy"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: arm/arm64: vgic: Use READ_ONCE fo cmpxchg
  KVM: nVMX: Fix interrupt window request with "Acknowledge interrupt on exit"
  KVM: nVMX: mark vmcs12 pages dirty on L2 exit
  kvm: nVMX: don't flush VMCS12 during VMXOFF or VCPU teardown
  KVM: nVMX: do not pin the VMCS12
  KVM: avoid using rcu_dereference_protected
  KVM: X86: init irq->level in kvm_pv_kick_cpu_op
  KVM: X86: Fix loss of pending INIT due to race
  KVM: async_pf: make rcu irq exit if not triggered from idle task
  KVM: nVMX: fixes to nested virt interrupt injection
  KVM: nVMX: do not fill vm_exit_intr_error_code in prepare_vmcs12
  KVM: arm/arm64: Handle hva aging while destroying the vm
  KVM: arm/arm64: PMU: Fix overflow interrupt injection
  KVM: arm/arm64: Fix bug in advertising KVM_CAP_MSI_DEVID capability

arch/arm64/kvm/sys_regs.c

@@ -764,7 +764,7 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (p->is_write) {
 		if (r->CRm & 0x2)
 			/* accessing PMOVSSET_EL0 */
-			kvm_pmu_overflow_set(vcpu, p->regval & mask);
+			vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
 		else
 			/* accessing PMOVSCLR_EL0 */
 			vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);

arch/x86/kernel/kvm.c

@@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token)
 		if (hlist_unhashed(&n.link))
 			break;
 
+		rcu_irq_exit();
+
 		if (!n.halted) {
 			local_irq_enable();
 			schedule();
@@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token)
 			/*
 			 * We cannot reschedule. So halt.
 			 */
-			rcu_irq_exit();
 			native_safe_halt();
 			local_irq_disable();
-			rcu_irq_enter();
 		}
+
+		rcu_irq_enter();
 	}
 	if (!n.halted)
 		finish_swait(&n.wq, &wait);

arch/x86/kvm/svm.c

@@ -2430,6 +2430,16 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 	svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
 	svm->vmcb->control.exit_code_hi = 0;
 	svm->vmcb->control.exit_info_1 = error_code;
+
+	/*
+	 * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception.
+	 * The fix is to add the ancillary datum (CR2 or DR6) to structs
+	 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be
+	 * written only when inject_pending_event runs (DR6 would written here
+	 * too).  This should be conditional on a new capability---if the
+	 * capability is disabled, kvm_multiple_exception would write the
+	 * ancillary information to CR2 or DR6, for backwards ABI-compatibility.
+	 */
 	if (svm->vcpu.arch.exception.nested_apf)
 		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
 	else

arch/x86/kvm/vmx.c

@@ -416,13 +416,10 @@ struct nested_vmx {
 
 	/* The guest-physical address of the current VMCS L1 keeps for L2 */
 	gpa_t current_vmptr;
-	/* The host-usable pointer to the above */
-	struct page *current_vmcs12_page;
-	struct vmcs12 *current_vmcs12;
 	/*
 	 * Cache of the guest's VMCS, existing outside of guest memory.
 	 * Loaded from guest memory during VMPTRLD. Flushed to guest
-	 * memory during VMXOFF, VMCLEAR, VMPTRLD.
+	 * memory during VMCLEAR and VMPTRLD.
 	 */
 	struct vmcs12 *cached_vmcs12;
 	/*
@@ -927,6 +924,10 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static int alloc_identity_pagetable(struct kvm *kvm);
+static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
+static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
+static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
+					    u16 error_code);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -2428,6 +2429,30 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	vmx_set_interrupt_shadow(vcpu, 0);
 }
 
+static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
+					       unsigned long exit_qual)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned int nr = vcpu->arch.exception.nr;
+	u32 intr_info = nr | INTR_INFO_VALID_MASK;
+
+	if (vcpu->arch.exception.has_error_code) {
+		vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
+		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+	}
+
+	if (kvm_exception_is_soft(nr))
+		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+	else
+		intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+	if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) &&
+	    vmx_get_nmi_mask(vcpu))
+		intr_info |= INTR_INFO_UNBLOCK_NMI;
+
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
+}
+
 /*
  * KVM wants to inject page-faults which it got to the guest. This function
  * checks whether in a nested guest, we need to inject them to L1 or L2.
@@ -2437,23 +2462,38 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	unsigned int nr = vcpu->arch.exception.nr;
 
-	if (!((vmcs12->exception_bitmap & (1u << nr)) ||
-		(nr == PF_VECTOR && vcpu->arch.exception.nested_apf)))
-		return 0;
+	if (nr == PF_VECTOR) {
+		if (vcpu->arch.exception.nested_apf) {
+			nested_vmx_inject_exception_vmexit(vcpu,
+							   vcpu->arch.apf.nested_apf_token);
+			return 1;
+		}
+		/*
+		 * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
+		 * The fix is to add the ancillary datum (CR2 or DR6) to structs
+		 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
+		 * can be written only when inject_pending_event runs.  This should be
+		 * conditional on a new capability---if the capability is disabled,
+		 * kvm_multiple_exception would write the ancillary information to
+		 * CR2 or DR6, for backwards ABI-compatibility.
+		 */
+		if (nested_vmx_is_page_fault_vmexit(vmcs12,
+						    vcpu->arch.exception.error_code)) {
+			nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2);
+			return 1;
+		}
+	} else {
+		unsigned long exit_qual = 0;
+		if (nr == DB_VECTOR)
+			exit_qual = vcpu->arch.dr6;
 
-	if (vcpu->arch.exception.nested_apf) {
-		vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code);
-		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-			PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
-			INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
-			vcpu->arch.apf.nested_apf_token);
-		return 1;
+		if (vmcs12->exception_bitmap & (1u << nr)) {
+			nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+			return 1;
+		}
 	}
 
-	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-			  vmcs_read32(VM_EXIT_INTR_INFO),
-			  vmcs_readl(EXIT_QUALIFICATION));
-	return 1;
+	return 0;
 }
 
 static void vmx_queue_exception(struct kvm_vcpu *vcpu)
@@ -2667,7 +2707,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 * reason is that if one of these bits is necessary, it will appear
 	 * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
 	 * fields of vmcs01 and vmcs02, will turn these bits off - and
-	 * nested_vmx_exit_handled() will not pass related exits to L1.
+	 * nested_vmx_exit_reflected() will not pass related exits to L1.
 	 * These rules have exceptions below.
 	 */
 
@@ -4955,6 +4995,28 @@ static bool vmx_get_enable_apicv(void)
 	return enable_apicv;
 }
 
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	gfn_t gfn;
+
+	/*
+	 * Don't need to mark the APIC access page dirty; it is never
+	 * written to by the CPU during APIC virtualization.
+	 */
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+		gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+
+	if (nested_cpu_has_posted_intr(vmcs12)) {
+		gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+}
+
+
 static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4962,18 +5024,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	void *vapic_page;
 	u16 status;
 
-	if (vmx->nested.pi_desc &&
-	    vmx->nested.pi_pending) {
-		vmx->nested.pi_pending = false;
-		if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-			return;
-
-		max_irr = find_last_bit(
-			(unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+		return;
 
-		if (max_irr == 256)
-			return;
+	vmx->nested.pi_pending = false;
+	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+		return;
 
+	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (max_irr != 256) {
 		vapic_page = kmap(vmx->nested.virtual_apic_page);
 		__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
 		kunmap(vmx->nested.virtual_apic_page);
@@ -4985,6 +5044,8 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 			vmcs_write16(GUEST_INTR_STATUS, status);
 		}
 	}
+
+	nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
@@ -7134,34 +7195,32 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
+{
+	vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
+	vmcs_write64(VMCS_LINK_POINTER, -1ull);
+}
+
 static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
 {
 	if (vmx->nested.current_vmptr == -1ull)
 		return;
 
-	/* current_vmptr and current_vmcs12 are always set/reset together */
-	if (WARN_ON(vmx->nested.current_vmcs12 == NULL))
-		return;
-
 	if (enable_shadow_vmcs) {
 		/* copy to memory all shadowed fields in case
 		   they were modified */
 		copy_shadow_to_vmcs12(vmx);
 		vmx->nested.sync_shadow_vmcs = false;
-		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
-				SECONDARY_EXEC_SHADOW_VMCS);
-		vmcs_write64(VMCS_LINK_POINTER, -1ull);
+		vmx_disable_shadow_vmcs(vmx);
 	}
 	vmx->nested.posted_intr_nv = -1;
 
 	/* Flush VMCS12 to guest memory */
-	memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12,
-	       VMCS12_SIZE);
+	kvm_vcpu_write_guest_page(&vmx->vcpu,
+				  vmx->nested.current_vmptr >> PAGE_SHIFT,
+				  vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
 
-	kunmap(vmx->nested.current_vmcs12_page);
-	nested_release_page(vmx->nested.current_vmcs12_page);
 	vmx->nested.current_vmptr = -1ull;
-	vmx->nested.current_vmcs12 = NULL;
 }
 
 /*
@@ -7175,12 +7234,14 @@ static void free_nested(struct vcpu_vmx *vmx)
 
 	vmx->nested.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
-	nested_release_vmcs12(vmx);
+	vmx->nested.posted_intr_nv = -1;
+	vmx->nested.current_vmptr = -1ull;
 	if (vmx->nested.msr_bitmap) {
 		free_page((unsigned long)vmx->nested.msr_bitmap);
 		vmx->nested.msr_bitmap = NULL;
 	}
 	if (enable_shadow_vmcs) {
+		vmx_disable_shadow_vmcs(vmx);
 		vmcs_clear(vmx->vmcs01.shadow_vmcs);
 		free_vmcs(vmx->vmcs01.shadow_vmcs);
 		vmx->vmcs01.shadow_vmcs = NULL;
@@ -7579,14 +7640,14 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		}
 
 		nested_release_vmcs12(vmx);
-		vmx->nested.current_vmcs12 = new_vmcs12;
-		vmx->nested.current_vmcs12_page = page;
 		/*
 		 * Load VMCS12 from guest memory since it is not already
 		 * cached.
 		 */
-		memcpy(vmx->nested.cached_vmcs12,
-		       vmx->nested.current_vmcs12, VMCS12_SIZE);
+		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
+		kunmap(page);
+		nested_release_page_clean(page);
+
 		set_current_vmptr(vmx, vmptr);
 	}
 
@@ -8019,12 +8080,11 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
  * should handle it ourselves in L0 (and then continue L2). Only call this
  * when in is_guest_mode (L2).
  */
-static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
+static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 {
 	u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	u32 exit_reason = vmx->exit_reason;
 
 	trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
 				vmcs_readl(EXIT_QUALIFICATION),
@@ -8033,6 +8093,18 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
+	/*
+	 * The host physical addresses of some pages of guest memory
+	 * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU
+	 * may write to these pages via their host physical address while
+	 * L2 is running, bypassing any address-translation-based dirty
+	 * tracking (e.g. EPT write protection).
+	 *
+	 * Mark them dirty on every exit from L2 to prevent them from
+	 * getting out of sync with dirty tracking.
+	 */
+	nested_mark_vmcs12_pages_dirty(vcpu);
+
 	if (vmx->nested.nested_run_pending)
 		return false;
 
@@ -8169,6 +8241,29 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	}
 }
 
+static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason)
+{
+	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+	/*
+	 * At this point, the exit interruption info in exit_intr_info
+	 * is only valid for EXCEPTION_NMI exits.  For EXTERNAL_INTERRUPT
+	 * we need to query the in-kernel LAPIC.
+	 */
+	WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT);
+	if ((exit_intr_info &
+	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
+	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
+		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+		vmcs12->vm_exit_intr_error_code =
+			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+	}
+
+	nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info,
+			  vmcs_readl(EXIT_QUALIFICATION));
+	return 1;
+}
+
 static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 {
 	*info1 = vmcs_readl(EXIT_QUALIFICATION);
@@ -8415,12 +8510,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if (vmx->emulation_required)
 		return handle_invalid_guest_state(vcpu);
 
-	if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
-		nested_vmx_vmexit(vcpu, exit_reason,
-				  vmcs_read32(VM_EXIT_INTR_INFO),
-				  vmcs_readl(EXIT_QUALIFICATION));
-		return 1;
-	}
+	if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason))
+		return nested_vmx_reflect_vmexit(vcpu, exit_reason);
 
 	if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
 		dump_vmcs();
@@ -9223,7 +9314,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
-	vmx->nested.current_vmcs12 = NULL;
 
 	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
 
@@ -9509,12 +9599,15 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
 
 	WARN_ON(!is_guest_mode(vcpu));
 
-	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code))
-		nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
-				  vmcs_read32(VM_EXIT_INTR_INFO),
-				  vmcs_readl(EXIT_QUALIFICATION));
-	else
+	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+		vmcs12->vm_exit_intr_error_code = fault->error_code;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+				  INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+				  fault->address);
+	} else {
 		kvm_inject_page_fault(vcpu, fault);
+	}
 }
 
 static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
@@ -10094,12 +10187,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
 	 * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
 	 * !enable_ept, EB.PF is 1, so the "or" will always be 1.
-	 *
-	 * A problem with this approach (when !enable_ept) is that L1 may be
-	 * injected with more page faults than it asked for. This could have
-	 * caused problems, but in practice existing hypervisors don't care.
-	 * To fix this, we will need to emulate the PFEC checking (on the L1
-	 * page tables), using walk_addr(), when injecting PFs to L1.
 	 */
 	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
 		enable_ept ? vmcs12->page_fault_error_code_mask : 0);
@@ -10847,13 +10934,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	vmcs12->vm_exit_reason = exit_reason;
 	vmcs12->exit_qualification = exit_qualification;
-
 	vmcs12->vm_exit_intr_info = exit_intr_info;
-	if ((vmcs12->vm_exit_intr_info &
-	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
-	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK))
-		vmcs12->vm_exit_intr_error_code =
-			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+
 	vmcs12->idt_vectoring_info_field = 0;
 	vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 	vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
@@ -11049,8 +11131,15 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
-	if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
-	    && nested_exit_intr_ack_set(vcpu)) {
+	/*
+	 * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of
+	 * the VM-exit interrupt information (valid interrupt) is always set to
+	 * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need
+	 * kvm_cpu_has_interrupt().  See the commit message for details.
+	 */
+	if (nested_exit_intr_ack_set(vcpu) &&
+	    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+	    kvm_cpu_has_interrupt(vcpu)) {
 		int irq = kvm_cpu_get_interrupt(vcpu);
 		WARN_ON(irq < 0);
 		vmcs12->vm_exit_intr_info = irq |

arch/x86/kvm/x86.c

@@ -3159,15 +3159,18 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		kvm_set_hflags(vcpu, hflags);
 
 		vcpu->arch.smi_pending = events->smi.pending;
-		if (events->smi.smm_inside_nmi)
-			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
-		else
-			vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-		if (lapic_in_kernel(vcpu)) {
-			if (events->smi.latched_init)
-				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+
+		if (events->smi.smm) {
+			if (events->smi.smm_inside_nmi)
+				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
-				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
+			if (lapic_in_kernel(vcpu)) {
+				if (events->smi.latched_init)
+					set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+				else
+					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			}
 		}
 	}
 
@@ -6215,6 +6218,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 
 	lapic_irq.shorthand = 0;
 	lapic_irq.dest_mode = 0;
+	lapic_irq.level = 0;
 	lapic_irq.dest_id = apicid;
 	lapic_irq.msi_redir_hint = false;
 

include/kvm/arm_pmu.h

@@ -48,7 +48,6 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
-void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu);
 bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu);
@@ -86,7 +85,6 @@ static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val) {}
-static inline void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {}
 static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)

include/linux/kvm_host.h

@@ -477,7 +477,8 @@ struct kvm {
 static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
 {
 	return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
-				      lockdep_is_held(&kvm->slots_lock));
+				      lockdep_is_held(&kvm->slots_lock) ||
+				      !refcount_read(&kvm->users_count));
 }
 
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
@@ -570,7 +571,8 @@ void kvm_put_kvm(struct kvm *kvm);
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
-			lockdep_is_held(&kvm->slots_lock));
+			lockdep_is_held(&kvm->slots_lock) ||
+			!refcount_read(&kvm->users_count));
 }
 
 static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)

virt/kvm/arm/mmu.c

@@ -1718,12 +1718,16 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
+	if (!kvm->arch.pgd)
+		return 0;
 	trace_kvm_age_hva(start, end);
 	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
+	if (!kvm->arch.pgd)
+		return 0;
 	trace_kvm_test_age_hva(hva);
 	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
 }

virt/kvm/arm/pmu.c

@@ -203,11 +203,15 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
 	return reg;
 }
 
-static void kvm_pmu_check_overflow(struct kvm_vcpu *vcpu)
+static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	bool overflow = !!kvm_pmu_overflow_status(vcpu);
+	bool overflow;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return;
 
+	overflow = !!kvm_pmu_overflow_status(vcpu);
 	if (pmu->irq_level == overflow)
 		return;
 
@@ -215,33 +219,11 @@ static void kvm_pmu_check_overflow(struct kvm_vcpu *vcpu)
 
 	if (likely(irqchip_in_kernel(vcpu->kvm))) {
 		int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
-					      pmu->irq_num, overflow,
-					      &vcpu->arch.pmu);
+					      pmu->irq_num, overflow, pmu);
 		WARN_ON(ret);
 	}
 }
 
-/**
- * kvm_pmu_overflow_set - set PMU overflow interrupt
- * @vcpu: The vcpu pointer
- * @val: the value guest writes to PMOVSSET register
- */
-void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val)
-{
-	if (val == 0)
-		return;
-
-	vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= val;
-	kvm_pmu_check_overflow(vcpu);
-}
-
-static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
-{
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return;
-	kvm_pmu_check_overflow(vcpu);
-}
-
 bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
@@ -303,7 +285,7 @@ static inline struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
 }
 
 /**
- * When perf event overflows, call kvm_pmu_overflow_set to set overflow status.
+ * When the perf event overflows, set the overflow status and inform the vcpu.
  */
 static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 				  struct perf_sample_data *data,
@@ -313,7 +295,12 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
 	int idx = pmc->idx;
 
-	kvm_pmu_overflow_set(vcpu, BIT(idx));
+	vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
+
+	if (kvm_pmu_overflow_status(vcpu)) {
+		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
+		kvm_vcpu_kick(vcpu);
+	}
 }
 
 /**
@@ -341,7 +328,7 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 			reg = lower_32_bits(reg);
 			vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
 			if (!reg)
-				kvm_pmu_overflow_set(vcpu, BIT(i));
+				vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
 		}
 	}
 }

virt/kvm/arm/vgic/vgic-init.c

@@ -285,9 +285,6 @@ int vgic_init(struct kvm *kvm)
 	if (ret)
 		goto out;
 
-	if (vgic_has_its(kvm))
-		dist->msis_require_devid = true;
-
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_vgic_vcpu_enable(vcpu);
 

virt/kvm/arm/vgic/vgic-its.c

@@ -1598,6 +1598,7 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
 	INIT_LIST_HEAD(&its->device_list);
 	INIT_LIST_HEAD(&its->collection_list);
 
+	dev->kvm->arch.vgic.msis_require_devid = true;
 	dev->kvm->arch.vgic.has_its = true;
 	its->enabled = false;
 	its->dev = dev;

virt/kvm/arm/vgic/vgic-mmio-v3.c

@@ -369,7 +369,7 @@ static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu,
 		return;
 
 	do {
-		old_propbaser = dist->propbaser;
+		old_propbaser = READ_ONCE(dist->propbaser);
 		propbaser = old_propbaser;
 		propbaser = update_64bit_reg(propbaser, addr & 4, len, val);
 		propbaser = vgic_sanitise_propbaser(propbaser);
@@ -397,7 +397,7 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu,
 		return;
 
 	do {
-		old_pendbaser = vgic_cpu->pendbaser;
+		old_pendbaser = READ_ONCE(vgic_cpu->pendbaser);
 		pendbaser = old_pendbaser;
 		pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val);
 		pendbaser = vgic_sanitise_pendbaser(pendbaser);

virt/kvm/kvm_main.c

@@ -717,10 +717,9 @@ out_err_no_srcu:
 	hardware_disable_all();
 out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
-		kfree(rcu_access_pointer(kvm->buses[i]));
+		kfree(kvm_get_bus(kvm, i));
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-		kvm_free_memslots(kvm,
-			rcu_dereference_protected(kvm->memslots[i], 1));
+		kvm_free_memslots(kvm, __kvm_memslots(kvm, i));
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
 	return ERR_PTR(r);
@@ -754,9 +753,8 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
-		struct kvm_io_bus *bus;
+		struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
 
-		bus = rcu_dereference_protected(kvm->buses[i], 1);
 		if (bus)
 			kvm_io_bus_destroy(bus);
 		kvm->buses[i] = NULL;
@@ -770,8 +768,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-		kvm_free_memslots(kvm,
-			rcu_dereference_protected(kvm->memslots[i], 1));
+		kvm_free_memslots(kvm, __kvm_memslots(kvm, i));
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);