4 files changed, 60 insertions, 28 deletions

diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 35be0e2a4639..f4ce08c0d0be 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -459,6 +459,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 		}
 
 		irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
+
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->pending_latch = pendmask & (1U << bit_nr);
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
@@ -581,7 +584,11 @@ static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db,
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+
 	irq = __vgic_its_check_cache(dist, db, devid, eventid);
+	if (irq)
+		vgic_get_irq_kref(irq);
+
 	raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	return irq;
@@ -761,6 +768,7 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi)
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->pending_latch = true;
 	vgic_queue_irq_unlock(kvm, irq, flags);
+	vgic_put_irq(kvm, irq);
 
 	return 0;
 }
@@ -1368,6 +1376,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
 
 	for (i = 0; i < irq_count; i++) {
 		irq = vgic_get_irq(kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
 
 		update_affinity(irq, vcpu2);
 
@@ -2095,7 +2105,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz,
 
 	memset(entry, 0, esz);
 
-	while (len > 0) {
+	while (true) {
 		int next_offset;
 		size_t byte_offset;
 
@@ -2108,6 +2118,9 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz,
 			return next_offset;
 
 		byte_offset = next_offset * esz;
+		if (byte_offset >= len)
+			break;
+
 		id += next_offset;
 		gpa += byte_offset;
 		len -= byte_offset;
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index d8ef708a2ef6..9e6532488c47 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -98,7 +98,27 @@ static void async_pf_execute(struct work_struct *work)
 		swake_up_one(&vcpu->wq);
 
 	mmput(mm);
-	kvm_put_kvm(vcpu->kvm);
+}
+
+static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work)
+{
+	/*
+	 * The async #PF is "done", but KVM must wait for the work item itself,
+	 * i.e. async_pf_execute(), to run to completion.  If KVM is a module,
+	 * KVM must ensure *no* code owned by the KVM (the module) can be run
+	 * after the last call to module_put().  Note, flushing the work item
+	 * is always required when the item is taken off the completion queue.
+	 * E.g. even if the vCPU handles the item in the "normal" path, the VM
+	 * could be terminated before async_pf_execute() completes.
+	 *
+	 * Wake all events skip the queue and go straight done, i.e. don't
+	 * need to be flushed (but sanity check that the work wasn't queued).
+	 */
+	if (work->wakeup_all)
+		WARN_ON_ONCE(work->work.func);
+	else
+		flush_work(&work->work);
+	kmem_cache_free(async_pf_cache, work);
 }
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
@@ -125,7 +145,6 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 #else
 		if (cancel_work_sync(&work->work)) {
 			mmput(work->mm);
-			kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
 			kmem_cache_free(async_pf_cache, work);
 		}
 #endif
@@ -137,7 +156,10 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 			list_first_entry(&vcpu->async_pf.done,
 					 typeof(*work), link);
 		list_del(&work->link);
-		kmem_cache_free(async_pf_cache, work);
+
+		spin_unlock(&vcpu->async_pf.lock);
+		kvm_flush_and_free_async_pf_work(work);
+		spin_lock(&vcpu->async_pf.lock);
 	}
 	spin_unlock(&vcpu->async_pf.lock);
 
@@ -161,7 +183,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 
 		list_del(&work->queue);
 		vcpu->async_pf.queued--;
-		kmem_cache_free(async_pf_cache, work);
+		kvm_flush_and_free_async_pf_work(work);
 	}
 }
 
@@ -173,7 +195,9 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	if (vcpu->async_pf.queued >= ASYNC_PF_PER_VCPU)
 		return 0;
 
-	/* setup delayed work */
+	/* Arch specific code should not do async PF in this case */
+	if (unlikely(kvm_is_error_hva(hva)))
+		return 0;
 
 	/*
 	 * do alloc nowait since if we are going to sleep anyway we
@@ -190,26 +214,16 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	work->arch = *arch;
 	work->mm = current->mm;
 	mmget(work->mm);
-	kvm_get_kvm(work->vcpu->kvm);
-
-	/* this can't really happen otherwise gfn_to_pfn_async
-	   would succeed */
-	if (unlikely(kvm_is_error_hva(work->addr)))
-		goto retry_sync;
 
 	INIT_WORK(&work->work, async_pf_execute);
-	if (!schedule_work(&work->work))
-		goto retry_sync;
 
 	list_add_tail(&work->queue, &vcpu->async_pf.queue);
 	vcpu->async_pf.queued++;
 	kvm_arch_async_page_not_present(vcpu, work);
+
+	schedule_work(&work->work);
+
 	return 1;
-retry_sync:
-	kvm_put_kvm(work->vcpu->kvm);
-	mmput(work->mm);
-	kmem_cache_free(async_pf_cache, work);
-	return 0;
 }
 
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 8d606997c299..c94e97b351ee 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -191,15 +191,17 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 			r = kvm_io_bus_unregister_dev(kvm,
 				zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
 
+			kvm_iodevice_destructor(&dev->dev);
+
 			/*
 			 * On failure, unregister destroys all devices on the
 			 * bus _except_ the target device, i.e. coalesced_zones
-			 * has been modified.  No need to restart the walk as
-			 * there aren't any zones left.
+			 * has been modified.  Bail after destroying the target
+			 * device, there's no need to restart the walk as there
+			 * aren't any zones left.
 			 */
 			if (r)
 				break;
-			kvm_iodevice_destructor(&dev->dev);
 		}
 	}
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 287444e52ccf..0008fc49528a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2937,7 +2937,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	struct kvm_fpu *fpu = NULL;
 	struct kvm_sregs *kvm_sregs = NULL;
 
-	if (vcpu->kvm->mm != current->mm)
+	if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged)
 		return -EIO;
 
 	if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
@@ -3144,7 +3144,7 @@ static long kvm_vcpu_compat_ioctl(struct file *filp,
 	void __user *argp = compat_ptr(arg);
 	int r;
 
-	if (vcpu->kvm->mm != current->mm)
+	if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged)
 		return -EIO;
 
 	switch (ioctl) {
@@ -3209,7 +3209,7 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl,
 {
 	struct kvm_device *dev = filp->private_data;
 
-	if (dev->kvm->mm != current->mm)
+	if (dev->kvm->mm != current->mm || dev->kvm->vm_bugged)
 		return -EIO;
 
 	switch (ioctl) {
@@ -3329,8 +3329,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 		kvm_put_kvm(kvm);
 		mutex_lock(&kvm->lock);
 		list_del(&dev->vm_node);
+		if (ops->release)
+			ops->release(dev);
 		mutex_unlock(&kvm->lock);
-		ops->destroy(dev);
+		if (ops->destroy)
+			ops->destroy(dev);
 		return ret;
 	}
 
@@ -3410,7 +3413,7 @@ static long kvm_vm_ioctl(struct file *filp,
 	void __user *argp = (void __user *)arg;
 	int r;
 
-	if (kvm->mm != current->mm)
+	if (kvm->mm != current->mm || kvm->vm_bugged)
 		return -EIO;
 	switch (ioctl) {
 	case KVM_CREATE_VCPU:
@@ -3618,7 +3621,7 @@ static long kvm_vm_compat_ioctl(struct file *filp,
 	struct kvm *kvm = filp->private_data;
 	int r;
 
-	if (kvm->mm != current->mm)
+	if (kvm->mm != current->mm || kvm->vm_bugged)
 		return -EIO;
 	switch (ioctl) {
 #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT