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/x86.c

@@ -3159,6 +3159,8 @@ 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) {
 			if (events->smi.smm_inside_nmi)
 				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
@@ -3170,6 +3172,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 			}
 		}
+	}
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
@@ -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 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	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);