1 files changed, 55 insertions, 81 deletions

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 324bf35ec..128e7df5b 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))
@@ -426,7 +428,7 @@ 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)
@@ -1863,9 +1865,11 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 		rbd_osd_read_callback(obj_request);
 		break;
 	case CEPH_OSD_OP_SETALLOCHINT:
-		rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE);
+		rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE ||
+			   osd_req->r_ops[1].op == CEPH_OSD_OP_WRITEFULL);
 		/* fall through */
 	case CEPH_OSD_OP_WRITE:
+	case CEPH_OSD_OP_WRITEFULL:
 		rbd_osd_write_callback(obj_request);
 		break;
 	case CEPH_OSD_OP_STAT:
@@ -2401,7 +2405,10 @@ static void rbd_img_obj_request_fill(struct rbd_obj_request *obj_request,
 				opcode = CEPH_OSD_OP_ZERO;
 		}
 	} else if (op_type == OBJ_OP_WRITE) {
-		opcode = CEPH_OSD_OP_WRITE;
+		if (!offset && length == object_size)
+			opcode = CEPH_OSD_OP_WRITEFULL;
+		else
+			opcode = CEPH_OSD_OP_WRITE;
 		osd_req_op_alloc_hint_init(osd_request, num_ops,
 					object_size, object_size);
 		num_ops++;
@@ -3474,52 +3481,6 @@ static int rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_MQ_RQ_QUEUE_OK;
 }
 
-/*
- * a queue callback. Makes sure that we don't create a bio that spans across
- * multiple osd objects. One exception would be with a single page bios,
- * which we handle later at bio_chain_clone_range()
- */
-static int rbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
-			  struct bio_vec *bvec)
-{
-	struct rbd_device *rbd_dev = q->queuedata;
-	sector_t sector_offset;
-	sector_t sectors_per_obj;
-	sector_t obj_sector_offset;
-	int ret;
-
-	/*
-	 * Find how far into its rbd object the partition-relative
-	 * bio start sector is to offset relative to the enclosing
-	 * device.
-	 */
-	sector_offset = get_start_sect(bmd->bi_bdev) + bmd->bi_sector;
-	sectors_per_obj = 1 << (rbd_dev->header.obj_order - SECTOR_SHIFT);
-	obj_sector_offset = sector_offset & (sectors_per_obj - 1);
-
-	/*
-	 * Compute the number of bytes from that offset to the end
-	 * of the object.  Account for what's already used by the bio.
-	 */
-	ret = (int) (sectors_per_obj - obj_sector_offset) << SECTOR_SHIFT;
-	if (ret > bmd->bi_size)
-		ret -= bmd->bi_size;
-	else
-		ret = 0;
-
-	/*
-	 * Don't send back more than was asked for.  And if the bio
-	 * was empty, let the whole thing through because:  "Note
-	 * that a block device *must* allow a single page to be
-	 * added to an empty bio."
-	 */
-	rbd_assert(bvec->bv_len <= PAGE_SIZE);
-	if (ret > (int) bvec->bv_len || !bmd->bi_size)
-		ret = (int) bvec->bv_len;
-
-	return ret;
-}
-
 static void rbd_free_disk(struct rbd_device *rbd_dev)
 {
 	struct gendisk *disk = rbd_dev->disk;
@@ -3806,6 +3767,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	/* set io sizes to object size */
 	segment_size = rbd_obj_bytes(&rbd_dev->header);
 	blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+	q->limits.max_sectors = queue_max_hw_sectors(q);
 	blk_queue_max_segments(q, segment_size / SECTOR_SIZE);
 	blk_queue_max_segment_size(q, segment_size);
 	blk_queue_io_min(q, segment_size);
@@ -3815,10 +3777,12 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	q->limits.discard_granularity = segment_size;
 	q->limits.discard_alignment = segment_size;
-	q->limits.max_discard_sectors = segment_size / SECTOR_SIZE;
+	blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
 	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;
@@ -4720,7 +4684,10 @@ static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev)
 	}
 
 	ret = rbd_dev_v2_snap_context(rbd_dev);
-	dout("rbd_dev_v2_snap_context returned %d\n", ret);
+	if (ret && first_time) {
+		kfree(rbd_dev->header.object_prefix);
+		rbd_dev->header.object_prefix = NULL;
+	}
 
 	return ret;
 }
@@ -5169,44 +5136,51 @@ 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, NULL);
-	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,
+				NULL);
+	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;
 }
 
@@ -5324,7 +5298,7 @@ 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;
 
@@ -5342,7 +5316,7 @@ 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)
@@ -5363,7 +5337,7 @@ 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);
@@ -5385,12 +5359,12 @@ 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;
 
@@ -5401,7 +5375,7 @@ 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);
@@ -5464,7 +5438,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	spec = NULL;		/* rbd_dev now owns this */
 	rbd_opts = 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;