3 files changed, 50 insertions, 34 deletions

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 683dff272562..04c0e8f3183c 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -590,6 +590,7 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 	struct nvme_iod *iod = ctx;
 	struct request *req = iod_get_private(iod);
 	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+	bool requeue = false;
 
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
 
@@ -598,12 +599,13 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 		    && (jiffies - req->start_time) < req->timeout) {
 			unsigned long flags;
 
+			requeue = true;
 			blk_mq_requeue_request(req);
 			spin_lock_irqsave(req->q->queue_lock, flags);
 			if (!blk_queue_stopped(req->q))
 				blk_mq_kick_requeue_list(req->q);
 			spin_unlock_irqrestore(req->q->queue_lock, flags);
-			return;
+			goto release_iod;
 		}
 		req->errors = nvme_error_status(status);
 	} else
@@ -613,7 +615,7 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 		dev_warn(&nvmeq->dev->pci_dev->dev,
 			"completing aborted command with status:%04x\n",
 			status);
-
+ release_iod:
 	if (iod->nents) {
 		dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->sg, iod->nents,
 			rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
@@ -626,7 +628,8 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 	}
 	nvme_free_iod(nvmeq->dev, iod);
 
-	blk_mq_complete_request(req);
+	if (likely(!requeue))
+		blk_mq_complete_request(req);
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index fe8f1e4b4c7c..09138ceba046 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -96,6 +96,8 @@ static int atomic_dec_return_safe(atomic_t *v)
 #define RBD_MINORS_PER_MAJOR		256
 #define RBD_SINGLE_MAJOR_PART_SHIFT	4
 
+#define RBD_MAX_PARENT_CHAIN_LEN	16
+
 #define RBD_SNAP_DEV_NAME_PREFIX	"snap_"
 #define RBD_MAX_SNAP_NAME_LEN	\
 			(NAME_MAX - (sizeof (RBD_SNAP_DEV_NAME_PREFIX) - 1))
@@ -425,7 +427,7 @@ static ssize_t rbd_add_single_major(struct bus_type *bus, const char *buf,
 				    size_t count);
 static ssize_t rbd_remove_single_major(struct bus_type *bus, const char *buf,
 				       size_t count);
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping);
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth);
 static void rbd_spec_put(struct rbd_spec *spec);
 
 static int rbd_dev_id_to_minor(int dev_id)
@@ -3415,6 +3417,7 @@ static void rbd_queue_workfn(struct work_struct *work)
 		goto err_rq;
 	}
 	img_request->rq = rq;
+	snapc = NULL; /* img_request consumes a ref */
 
 	if (op_type == OBJ_OP_DISCARD)
 		result = rbd_img_request_fill(img_request, OBJ_REQUEST_NODATA,
@@ -3797,6 +3800,9 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	q->limits.discard_zeroes_data = 1;
 
 	blk_queue_merge_bvec(q, rbd_merge_bvec);
+	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
+		q->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
+
 	disk->queue = q;
 
 	q->queuedata = rbd_dev;
@@ -5142,44 +5148,50 @@ out_err:
 	return ret;
 }
 
-static int rbd_dev_probe_parent(struct rbd_device *rbd_dev)
+/*
+ * @depth is rbd_dev_image_probe() -> rbd_dev_probe_parent() ->
+ * rbd_dev_image_probe() recursion depth, which means it's also the
+ * length of the already discovered part of the parent chain.
+ */
+static int rbd_dev_probe_parent(struct rbd_device *rbd_dev, int depth)
 {
 	struct rbd_device *parent = NULL;
-	struct rbd_spec *parent_spec;
-	struct rbd_client *rbdc;
 	int ret;
 
 	if (!rbd_dev->parent_spec)
 		return 0;
-	/*
-	 * We need to pass a reference to the client and the parent
-	 * spec when creating the parent rbd_dev.  Images related by
-	 * parent/child relationships always share both.
-	 */
-	parent_spec = rbd_spec_get(rbd_dev->parent_spec);
-	rbdc = __rbd_get_client(rbd_dev->rbd_client);
 
-	ret = -ENOMEM;
-	parent = rbd_dev_create(rbdc, parent_spec);
-	if (!parent)
+	if (++depth > RBD_MAX_PARENT_CHAIN_LEN) {
+		pr_info("parent chain is too long (%d)\n", depth);
+		ret = -EINVAL;
 		goto out_err;
+	}
 
-	ret = rbd_dev_image_probe(parent, false);
+	parent = rbd_dev_create(rbd_dev->rbd_client, rbd_dev->parent_spec);
+	if (!parent) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	/*
+	 * Images related by parent/child relationships always share
+	 * rbd_client and spec/parent_spec, so bump their refcounts.
+	 */
+	__rbd_get_client(rbd_dev->rbd_client);
+	rbd_spec_get(rbd_dev->parent_spec);
+
+	ret = rbd_dev_image_probe(parent, depth);
 	if (ret < 0)
 		goto out_err;
+
 	rbd_dev->parent = parent;
 	atomic_set(&rbd_dev->parent_ref, 1);
-
 	return 0;
+
 out_err:
-	if (parent) {
-		rbd_dev_unparent(rbd_dev);
+	rbd_dev_unparent(rbd_dev);
+	if (parent)
 		rbd_dev_destroy(parent);
-	} else {
-		rbd_put_client(rbdc);
-		rbd_spec_put(parent_spec);
-	}
-
 	return ret;
 }
 
@@ -5297,7 +5309,7 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev)
  * parent), initiate a watch on its header object before using that
  * object to get detailed information about the rbd image.
  */
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
 {
 	int ret;
 
@@ -5315,7 +5327,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 	if (ret)
 		goto err_out_format;
 
-	if (mapping) {
+	if (!depth) {
 		ret = rbd_dev_header_watch_sync(rbd_dev);
 		if (ret) {
 			if (ret == -ENOENT)
@@ -5336,7 +5348,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 	 * Otherwise this is a parent image, identified by pool, image
 	 * and snap ids - need to fill in names for those ids.
 	 */
-	if (mapping)
+	if (!depth)
 		ret = rbd_spec_fill_snap_id(rbd_dev);
 	else
 		ret = rbd_spec_fill_names(rbd_dev);
@@ -5358,12 +5370,12 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 		 * Need to warn users if this image is the one being
 		 * mapped and has a parent.
 		 */
-		if (mapping && rbd_dev->parent_spec)
+		if (!depth && rbd_dev->parent_spec)
 			rbd_warn(rbd_dev,
 				 "WARNING: kernel layering is EXPERIMENTAL!");
 	}
 
-	ret = rbd_dev_probe_parent(rbd_dev);
+	ret = rbd_dev_probe_parent(rbd_dev, depth);
 	if (ret)
 		goto err_out_probe;
 
@@ -5374,7 +5386,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 err_out_probe:
 	rbd_dev_unprobe(rbd_dev);
 err_out_watch:
-	if (mapping)
+	if (!depth)
 		rbd_dev_header_unwatch_sync(rbd_dev);
 out_header_name:
 	kfree(rbd_dev->header_name);
@@ -5439,7 +5451,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	rbdc = NULL;		/* rbd_dev now owns this */
 	spec = NULL;		/* rbd_dev now owns this */
 
-	rc = rbd_dev_image_probe(rbd_dev, true);
+	rc = rbd_dev_image_probe(rbd_dev, 0);
 	if (rc < 0)
 		goto err_out_rbd_dev;
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 89c7371ab2dc..42ef86c409b6 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1925,7 +1925,8 @@ static void blkback_changed(struct xenbus_device *dev,
 			break;
 		/* Missed the backend's Closing state -- fallthrough */
 	case XenbusStateClosing:
-		blkfront_closing(info);
+		if (info)
+			blkfront_closing(info);
 		break;
 	}
 }