Merge remote-tracking branch 'iommu/vfio-notifier-fix' into v5.19/vfio/next

Merge IOMMU dependencies for vfio.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 15 insertions, 230 deletions

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 56b80c39a3c0..cc0d337f7b13 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -62,11 +62,6 @@ struct vfio_container {
 	bool				noiommu;
 };
 
-struct vfio_unbound_dev {
-	struct device			*dev;
-	struct list_head		unbound_next;
-};
-
 struct vfio_group {
 	struct device 			dev;
 	struct cdev			cdev;
@@ -76,11 +71,8 @@ struct vfio_group {
 	struct vfio_container		*container;
 	struct list_head		device_list;
 	struct mutex			device_lock;
-	struct notifier_block		nb;
 	struct list_head		vfio_next;
 	struct list_head		container_next;
-	struct list_head		unbound_list;
-	struct mutex			unbound_lock;
 	atomic_t			opened;
 	wait_queue_head_t		container_q;
 	enum vfio_group_type		type;
@@ -281,8 +273,6 @@ void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops)
 }
 EXPORT_SYMBOL_GPL(vfio_unregister_iommu_driver);
 
-static int vfio_iommu_group_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data);
 static void vfio_group_get(struct vfio_group *group);
 
 /*
@@ -340,16 +330,8 @@ vfio_group_get_from_iommu(struct iommu_group *iommu_group)
 static void vfio_group_release(struct device *dev)
 {
 	struct vfio_group *group = container_of(dev, struct vfio_group, dev);
-	struct vfio_unbound_dev *unbound, *tmp;
-
-	list_for_each_entry_safe(unbound, tmp,
-				 &group->unbound_list, unbound_next) {
-		list_del(&unbound->unbound_next);
-		kfree(unbound);
-	}
 
 	mutex_destroy(&group->device_lock);
-	mutex_destroy(&group->unbound_lock);
 	iommu_group_put(group->iommu_group);
 	ida_free(&vfio.group_ida, MINOR(group->dev.devt));
 	kfree(group);
@@ -381,8 +363,6 @@ static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
 	refcount_set(&group->users, 1);
 	INIT_LIST_HEAD(&group->device_list);
 	mutex_init(&group->device_lock);
-	INIT_LIST_HEAD(&group->unbound_list);
-	mutex_init(&group->unbound_lock);
 	init_waitqueue_head(&group->container_q);
 	group->iommu_group = iommu_group;
 	/* put in vfio_group_release() */
@@ -412,13 +392,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 		goto err_put;
 	}
 
-	group->nb.notifier_call = vfio_iommu_group_notifier;
-	err = iommu_group_register_notifier(iommu_group, &group->nb);
-	if (err) {
-		ret = ERR_PTR(err);
-		goto err_put;
-	}
-
 	mutex_lock(&vfio.group_lock);
 
 	/* Did we race creating this group? */
@@ -439,7 +412,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 
 err_unlock:
 	mutex_unlock(&vfio.group_lock);
-	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
 err_put:
 	put_device(&group->dev);
 	return ret;
@@ -464,7 +436,6 @@ static void vfio_group_put(struct vfio_group *group)
 	cdev_device_del(&group->cdev, &group->dev);
 	mutex_unlock(&vfio.group_lock);
 
-	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
 	put_device(&group->dev);
 }
 
@@ -505,175 +476,6 @@ static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
 }
 
 /*
- * Some drivers, like pci-stub, are only used to prevent other drivers from
- * claiming a device and are therefore perfectly legitimate for a user owned
- * group.  The pci-stub driver has no dependencies on DMA or the IOVA mapping
- * of the device, but it does prevent the user from having direct access to
- * the device, which is useful in some circumstances.
- *
- * We also assume that we can include PCI interconnect devices, ie. bridges.
- * IOMMU grouping on PCI necessitates that if we lack isolation on a bridge
- * then all of the downstream devices will be part of the same IOMMU group as
- * the bridge.  Thus, if placing the bridge into the user owned IOVA space
- * breaks anything, it only does so for user owned devices downstream.  Note
- * that error notification via MSI can be affected for platforms that handle
- * MSI within the same IOVA space as DMA.
- */
-static const char * const vfio_driver_allowed[] = { "pci-stub" };
-
-static bool vfio_dev_driver_allowed(struct device *dev,
-				    struct device_driver *drv)
-{
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-
-		if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
-			return true;
-	}
-
-	return match_string(vfio_driver_allowed,
-			    ARRAY_SIZE(vfio_driver_allowed),
-			    drv->name) >= 0;
-}
-
-/*
- * A vfio group is viable for use by userspace if all devices are in
- * one of the following states:
- *  - driver-less
- *  - bound to a vfio driver
- *  - bound to an otherwise allowed driver
- *  - a PCI interconnect device
- *
- * We use two methods to determine whether a device is bound to a vfio
- * driver.  The first is to test whether the device exists in the vfio
- * group.  The second is to test if the device exists on the group
- * unbound_list, indicating it's in the middle of transitioning from
- * a vfio driver to driver-less.
- */
-static int vfio_dev_viable(struct device *dev, void *data)
-{
-	struct vfio_group *group = data;
-	struct vfio_device *device;
-	struct device_driver *drv = READ_ONCE(dev->driver);
-	struct vfio_unbound_dev *unbound;
-	int ret = -EINVAL;
-
-	mutex_lock(&group->unbound_lock);
-	list_for_each_entry(unbound, &group->unbound_list, unbound_next) {
-		if (dev == unbound->dev) {
-			ret = 0;
-			break;
-		}
-	}
-	mutex_unlock(&group->unbound_lock);
-
-	if (!ret || !drv || vfio_dev_driver_allowed(dev, drv))
-		return 0;
-
-	device = vfio_group_get_device(group, dev);
-	if (device) {
-		vfio_device_put(device);
-		return 0;
-	}
-
-	return ret;
-}
-
-/*
- * Async device support
- */
-static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
-{
-	struct vfio_device *device;
-
-	/* Do we already know about it?  We shouldn't */
-	device = vfio_group_get_device(group, dev);
-	if (WARN_ON_ONCE(device)) {
-		vfio_device_put(device);
-		return 0;
-	}
-
-	/* Nothing to do for idle groups */
-	if (!atomic_read(&group->container_users))
-		return 0;
-
-	/* TODO Prevent device auto probing */
-	dev_WARN(dev, "Device added to live group %d!\n",
-		 iommu_group_id(group->iommu_group));
-
-	return 0;
-}
-
-static int vfio_group_nb_verify(struct vfio_group *group, struct device *dev)
-{
-	/* We don't care what happens when the group isn't in use */
-	if (!atomic_read(&group->container_users))
-		return 0;
-
-	return vfio_dev_viable(dev, group);
-}
-
-static int vfio_iommu_group_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data)
-{
-	struct vfio_group *group = container_of(nb, struct vfio_group, nb);
-	struct device *dev = data;
-	struct vfio_unbound_dev *unbound;
-
-	switch (action) {
-	case IOMMU_GROUP_NOTIFY_ADD_DEVICE:
-		vfio_group_nb_add_dev(group, dev);
-		break;
-	case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
-		/*
-		 * Nothing to do here.  If the device is in use, then the
-		 * vfio sub-driver should block the remove callback until
-		 * it is unused.  If the device is unused or attached to a
-		 * stub driver, then it should be released and we don't
-		 * care that it will be going away.
-		 */
-		break;
-	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
-		dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
-			iommu_group_id(group->iommu_group));
-		break;
-	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
-		dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
-			iommu_group_id(group->iommu_group), dev->driver->name);
-		BUG_ON(vfio_group_nb_verify(group, dev));
-		break;
-	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
-		dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
-			__func__, iommu_group_id(group->iommu_group),
-			dev->driver->name);
-		break;
-	case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
-		dev_dbg(dev, "%s: group %d unbound from driver\n", __func__,
-			iommu_group_id(group->iommu_group));
-		/*
-		 * XXX An unbound device in a live group is ok, but we'd
-		 * really like to avoid the above BUG_ON by preventing other
-		 * drivers from binding to it.  Once that occurs, we have to
-		 * stop the system to maintain isolation.  At a minimum, we'd
-		 * want a toggle to disable driver auto probe for this device.
-		 */
-
-		mutex_lock(&group->unbound_lock);
-		list_for_each_entry(unbound,
-				    &group->unbound_list, unbound_next) {
-			if (dev == unbound->dev) {
-				list_del(&unbound->unbound_next);
-				kfree(unbound);
-				break;
-			}
-		}
-		mutex_unlock(&group->unbound_lock);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-/*
  * VFIO driver API
  */
 void vfio_init_group_dev(struct vfio_device *device, struct device *dev,
@@ -850,29 +652,10 @@ static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
 void vfio_unregister_group_dev(struct vfio_device *device)
 {
 	struct vfio_group *group = device->group;
-	struct vfio_unbound_dev *unbound;
 	unsigned int i = 0;
 	bool interrupted = false;
 	long rc;
 
-	/*
-	 * When the device is removed from the group, the group suddenly
-	 * becomes non-viable; the device has a driver (until the unbind
-	 * completes), but it's not present in the group.  This is bad news
-	 * for any external users that need to re-acquire a group reference
-	 * in order to match and release their existing reference.  To
-	 * solve this, we track such devices on the unbound_list to bridge
-	 * the gap until they're fully unbound.
-	 */
-	unbound = kzalloc(sizeof(*unbound), GFP_KERNEL);
-	if (unbound) {
-		unbound->dev = device->dev;
-		mutex_lock(&group->unbound_lock);
-		list_add(&unbound->unbound_next, &group->unbound_list);
-		mutex_unlock(&group->unbound_lock);
-	}
-	WARN_ON(!unbound);
-
 	vfio_device_put(device);
 	rc = try_wait_for_completion(&device->comp);
 	while (rc <= 0) {
@@ -1159,6 +942,8 @@ static void __vfio_group_unset_container(struct vfio_group *group)
 		driver->ops->detach_group(container->iommu_data,
 					  group->iommu_group);
 
+	iommu_group_release_dma_owner(group->iommu_group);
+
 	group->container = NULL;
 	wake_up(&group->container_q);
 	list_del(&group->container_next);
@@ -1243,13 +1028,19 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 		goto unlock_out;
 	}
 
+	ret = iommu_group_claim_dma_owner(group->iommu_group, f.file);
+	if (ret)
+		goto unlock_out;
+
 	driver = container->iommu_driver;
 	if (driver) {
 		ret = driver->ops->attach_group(container->iommu_data,
 						group->iommu_group,
 						group->type);
-		if (ret)
+		if (ret) {
+			iommu_group_release_dma_owner(group->iommu_group);
 			goto unlock_out;
+		}
 	}
 
 	group->container = container;
@@ -1266,12 +1057,6 @@ unlock_out:
 	return ret;
 }
 
-static bool vfio_group_viable(struct vfio_group *group)
-{
-	return (iommu_group_for_each_dev(group->iommu_group,
-					 group, vfio_dev_viable) == 0);
-}
-
 static int vfio_group_add_container_user(struct vfio_group *group)
 {
 	if (!atomic_inc_not_zero(&group->container_users))
@@ -1281,7 +1066,7 @@ static int vfio_group_add_container_user(struct vfio_group *group)
 		atomic_dec(&group->container_users);
 		return -EPERM;
 	}
-	if (!group->container->iommu_driver || !vfio_group_viable(group)) {
+	if (!group->container->iommu_driver) {
 		atomic_dec(&group->container_users);
 		return -EINVAL;
 	}
@@ -1305,7 +1090,7 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 	int ret = 0;
 
 	if (0 == atomic_read(&group->container_users) ||
-	    !group->container->iommu_driver || !vfio_group_viable(group))
+	    !group->container->iommu_driver)
 		return -EINVAL;
 
 	if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO))
@@ -1397,11 +1182,11 @@ static long vfio_group_fops_unl_ioctl(struct file *filep,
 
 		status.flags = 0;
 
-		if (vfio_group_viable(group))
-			status.flags |= VFIO_GROUP_FLAGS_VIABLE;
-
 		if (group->container)
-			status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET;
+			status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET |
+					VFIO_GROUP_FLAGS_VIABLE;
+		else if (!iommu_group_dma_owner_claimed(group->iommu_group))
+			status.flags |= VFIO_GROUP_FLAGS_VIABLE;
 
 		if (copy_to_user((void __user *)arg, &status, minsz))
 			return -EFAULT;