Merge tag 'vfio-v4.13-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Include Intel XXV710 in INTx workaround (Alex Williamson)

 - Make use of ERR_CAST() for error return (Dan Carpenter)

 - Fix vfio_group release deadlock from iommu notifier (Alex Williamson)

 - Unset KVM-VFIO attributes only on group match (Alex Williamson)

 - Fix release path group/file matching with KVM-VFIO (Alex Williamson)

 - Remove unnecessary lock uses triggering lockdep splat (Alex Williamson)

* tag 'vfio-v4.13-rc1' of git://github.com/awilliam/linux-vfio:
  vfio: Remove unnecessary uses of vfio_container.group_lock
  vfio: New external user group/file match
  kvm-vfio: Decouple only when we match a group
  vfio: Fix group release deadlock
  vfio: Use ERR_CAST() instead of open coding it
  vfio/pci: Add Intel XXV710 to hidden INTx devices

drivers/vfio/pci/vfio_pci.c

@@ -195,11 +195,11 @@ static bool vfio_pci_nointx(struct pci_dev *pdev)
 	switch (pdev->vendor) {
 	case PCI_VENDOR_ID_INTEL:
 		switch (pdev->device) {
-		/* All i40e (XL710/X710) 10/20/40GbE NICs */
+		/* All i40e (XL710/X710/XXV710) 10/20/25/40GbE NICs */
 		case 0x1572:
 		case 0x1574:
 		case 0x1580 ... 0x1581:
-		case 0x1583 ... 0x1589:
+		case 0x1583 ... 0x158b:
 		case 0x37d0 ... 0x37d2:
 			return true;
 		default:

drivers/vfio/vfio.c

@@ -382,7 +382,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
 	if (IS_ERR(dev)) {
 		vfio_free_group_minor(minor);
 		vfio_group_unlock_and_free(group);
-		return (struct vfio_group *)dev; /* ERR_PTR */
+		return ERR_CAST(dev);
 	}
 
 	group->minor = minor;
@@ -423,6 +423,34 @@ static void vfio_group_put(struct vfio_group *group)
 	kref_put_mutex(&group->kref, vfio_group_release, &vfio.group_lock);
 }
 
+struct vfio_group_put_work {
+	struct work_struct work;
+	struct vfio_group *group;
+};
+
+static void vfio_group_put_bg(struct work_struct *work)
+{
+	struct vfio_group_put_work *do_work;
+
+	do_work = container_of(work, struct vfio_group_put_work, work);
+
+	vfio_group_put(do_work->group);
+	kfree(do_work);
+}
+
+static void vfio_group_schedule_put(struct vfio_group *group)
+{
+	struct vfio_group_put_work *do_work;
+
+	do_work = kmalloc(sizeof(*do_work), GFP_KERNEL);
+	if (WARN_ON(!do_work))
+		return;
+
+	INIT_WORK(&do_work->work, vfio_group_put_bg);
+	do_work->group = group;
+	schedule_work(&do_work->work);
+}
+
 /* Assume group_lock or group reference is held */
 static void vfio_group_get(struct vfio_group *group)
 {
@@ -762,7 +790,14 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 		break;
 	}
 
-	vfio_group_put(group);
+	/*
+	 * If we're the last reference to the group, the group will be
+	 * released, which includes unregistering the iommu group notifier.
+	 * We hold a read-lock on that notifier list, unregistering needs
+	 * a write-lock... deadlock.  Release our reference asynchronously
+	 * to avoid that situation.
+	 */
+	vfio_group_schedule_put(group);
 	return NOTIFY_OK;
 }
 
@@ -1140,15 +1175,11 @@ static long vfio_fops_unl_ioctl(struct file *filep,
 		ret = vfio_ioctl_set_iommu(container, arg);
 		break;
 	default:
-		down_read(&container->group_lock);
-
 		driver = container->iommu_driver;
 		data = container->iommu_data;
 
 		if (driver) /* passthrough all unrecognized ioctls */
 			ret = driver->ops->ioctl(data, cmd, arg);
-
-		up_read(&container->group_lock);
 	}
 
 	return ret;
@@ -1202,15 +1233,11 @@ static ssize_t vfio_fops_read(struct file *filep, char __user *buf,
 	struct vfio_iommu_driver *driver;
 	ssize_t ret = -EINVAL;
 
-	down_read(&container->group_lock);
-
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->read))
 		ret = driver->ops->read(container->iommu_data,
 					buf, count, ppos);
 
-	up_read(&container->group_lock);
-
 	return ret;
 }
 
@@ -1221,15 +1248,11 @@ static ssize_t vfio_fops_write(struct file *filep, const char __user *buf,
 	struct vfio_iommu_driver *driver;
 	ssize_t ret = -EINVAL;
 
-	down_read(&container->group_lock);
-
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->write))
 		ret = driver->ops->write(container->iommu_data,
 					 buf, count, ppos);
 
-	up_read(&container->group_lock);
-
 	return ret;
 }
 
@@ -1239,14 +1262,10 @@ static int vfio_fops_mmap(struct file *filep, struct vm_area_struct *vma)
 	struct vfio_iommu_driver *driver;
 	int ret = -EINVAL;
 
-	down_read(&container->group_lock);
-
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->mmap))
 		ret = driver->ops->mmap(container->iommu_data, vma);
 
-	up_read(&container->group_lock);
-
 	return ret;
 }
 
@@ -1741,6 +1760,15 @@ void vfio_group_put_external_user(struct vfio_group *group)
 }
 EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
 
+bool vfio_external_group_match_file(struct vfio_group *test_group,
+				    struct file *filep)
+{
+	struct vfio_group *group = filep->private_data;
+
+	return (filep->f_op == &vfio_group_fops) && (group == test_group);
+}
+EXPORT_SYMBOL_GPL(vfio_external_group_match_file);
+
 int vfio_external_user_iommu_id(struct vfio_group *group)
 {
 	return iommu_group_id(group->iommu_group);
@@ -1949,8 +1977,6 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
 		goto err_pin_pages;
 
 	container = group->container;
-	down_read(&container->group_lock);
-
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->pin_pages))
 		ret = driver->ops->pin_pages(container->iommu_data, user_pfn,
@@ -1958,7 +1984,6 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
 	else
 		ret = -ENOTTY;
 
-	up_read(&container->group_lock);
 	vfio_group_try_dissolve_container(group);
 
 err_pin_pages:
@@ -1998,8 +2023,6 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage)
 		goto err_unpin_pages;
 
 	container = group->container;
-	down_read(&container->group_lock);
-
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->unpin_pages))
 		ret = driver->ops->unpin_pages(container->iommu_data, user_pfn,
@@ -2007,7 +2030,6 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage)
 	else
 		ret = -ENOTTY;
 
-	up_read(&container->group_lock);
 	vfio_group_try_dissolve_container(group);
 
 err_unpin_pages:
@@ -2029,8 +2051,6 @@ static int vfio_register_iommu_notifier(struct vfio_group *group,
 		return -EINVAL;
 
 	container = group->container;
-	down_read(&container->group_lock);
-
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->register_notifier))
 		ret = driver->ops->register_notifier(container->iommu_data,
@@ -2038,7 +2058,6 @@ static int vfio_register_iommu_notifier(struct vfio_group *group,
 	else
 		ret = -ENOTTY;
 
-	up_read(&container->group_lock);
 	vfio_group_try_dissolve_container(group);
 
 	return ret;
@@ -2056,8 +2075,6 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group,
 		return -EINVAL;
 
 	container = group->container;
-	down_read(&container->group_lock);
-
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->unregister_notifier))
 		ret = driver->ops->unregister_notifier(container->iommu_data,
@@ -2065,7 +2082,6 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group,
 	else
 		ret = -ENOTTY;
 
-	up_read(&container->group_lock);
 	vfio_group_try_dissolve_container(group);
 
 	return ret;
@@ -2083,7 +2099,6 @@ static int vfio_register_group_notifier(struct vfio_group *group,
 					unsigned long *events,
 					struct notifier_block *nb)
 {
-	struct vfio_container *container;
 	int ret;
 	bool set_kvm = false;
 
@@ -2101,9 +2116,6 @@ static int vfio_register_group_notifier(struct vfio_group *group,
 	if (ret)
 		return -EINVAL;
 
-	container = group->container;
-	down_read(&container->group_lock);
-
 	ret = blocking_notifier_chain_register(&group->notifier, nb);
 
 	/*
@@ -2114,7 +2126,6 @@ static int vfio_register_group_notifier(struct vfio_group *group,
 		blocking_notifier_call_chain(&group->notifier,
 					VFIO_GROUP_NOTIFY_SET_KVM, group->kvm);
 
-	up_read(&container->group_lock);
 	vfio_group_try_dissolve_container(group);
 
 	return ret;
@@ -2123,19 +2134,14 @@ static int vfio_register_group_notifier(struct vfio_group *group,
 static int vfio_unregister_group_notifier(struct vfio_group *group,
 					 struct notifier_block *nb)
 {
-	struct vfio_container *container;
 	int ret;
 
 	ret = vfio_group_add_container_user(group);
 	if (ret)
 		return -EINVAL;
 
-	container = group->container;
-	down_read(&container->group_lock);
-
 	ret = blocking_notifier_chain_unregister(&group->notifier, nb);
 
-	up_read(&container->group_lock);
 	vfio_group_try_dissolve_container(group);
 
 	return ret;

include/linux/vfio.h

@@ -97,6 +97,8 @@ extern void vfio_unregister_iommu_driver(
  */
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
+extern bool vfio_external_group_match_file(struct vfio_group *group,
+					   struct file *filep);
 extern int vfio_external_user_iommu_id(struct vfio_group *group);
 extern long vfio_external_check_extension(struct vfio_group *group,
 					  unsigned long arg);

virt/kvm/vfio.c

@@ -51,6 +51,22 @@ static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
 	return vfio_group;
 }
 
+static bool kvm_vfio_external_group_match_file(struct vfio_group *group,
+					       struct file *filep)
+{
+	bool ret, (*fn)(struct vfio_group *, struct file *);
+
+	fn = symbol_get(vfio_external_group_match_file);
+	if (!fn)
+		return false;
+
+	ret = fn(group, filep);
+
+	symbol_put(vfio_external_group_match_file);
+
+	return ret;
+}
+
 static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
 {
 	void (*fn)(struct vfio_group *);
@@ -231,37 +247,31 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 		if (!f.file)
 			return -EBADF;
 
-		vfio_group = kvm_vfio_group_get_external_user(f.file);
-		fdput(f);
-
-		if (IS_ERR(vfio_group))
-			return PTR_ERR(vfio_group);
-
 		ret = -ENOENT;
 
 		mutex_lock(&kv->lock);
 
 		list_for_each_entry(kvg, &kv->group_list, node) {
-			if (kvg->vfio_group != vfio_group)
+			if (!kvm_vfio_external_group_match_file(kvg->vfio_group,
+								f.file))
 				continue;
 
 			list_del(&kvg->node);
+			kvm_arch_end_assignment(dev->kvm);
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+			kvm_spapr_tce_release_vfio_group(dev->kvm,
+							 kvg->vfio_group);
+#endif
+			kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
 			kvm_vfio_group_put_external_user(kvg->vfio_group);
 			kfree(kvg);
 			ret = 0;
 			break;
 		}
 
-		kvm_arch_end_assignment(dev->kvm);
-
 		mutex_unlock(&kv->lock);
 
-#ifdef CONFIG_SPAPR_TCE_IOMMU
-		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
-#endif
-		kvm_vfio_group_set_kvm(vfio_group, NULL);
-
-		kvm_vfio_group_put_external_user(vfio_group);
+		fdput(f);
 
 		kvm_vfio_update_coherency(dev);