ublk: properly serialize all FETCH_REQs

Most uring_cmds issued against ublk character devices are serialized
because each command affects only one queue, and there is an early check
which only allows a single task (the queue's ubq_daemon) to issue
uring_cmds against that queue. However, this mechanism does not work for
FETCH_REQs, since they are expected before ubq_daemon is set. Since
FETCH_REQs are only used at initialization and not in the fast path,
serialize them using the per-ublk-device mutex. This fixes a number of
data races that were previously possible if a badly behaved ublk server
decided to issue multiple FETCH_REQs against the same qid/tag
concurrently.

Reported-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250416035444.99569-2-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/block/ublk_drv.c

@@ -1832,8 +1832,8 @@ static void ublk_nosrv_work(struct work_struct *work)
 
 /* device can only be started after all IOs are ready */
 static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
+	__must_hold(&ub->mutex)
 {
-	mutex_lock(&ub->mutex);
 	ubq->nr_io_ready++;
 	if (ublk_queue_ready(ubq)) {
 		ubq->ubq_daemon = current;
@@ -1845,7 +1845,6 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
 	}
 	if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues)
 		complete_all(&ub->completion);
-	mutex_unlock(&ub->mutex);
 }
 
 static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id,
@@ -1929,6 +1928,52 @@ static int ublk_unregister_io_buf(struct io_uring_cmd *cmd,
 	return io_buffer_unregister_bvec(cmd, index, issue_flags);
 }
 
+static int ublk_fetch(struct io_uring_cmd *cmd, struct ublk_queue *ubq,
+		      struct ublk_io *io, __u64 buf_addr)
+{
+	struct ublk_device *ub = ubq->dev;
+	int ret = 0;
+
+	/*
+	 * When handling FETCH command for setting up ublk uring queue,
+	 * ub->mutex is the innermost lock, and we won't block for handling
+	 * FETCH, so it is fine even for IO_URING_F_NONBLOCK.
+	 */
+	mutex_lock(&ub->mutex);
+	/* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
+	if (ublk_queue_ready(ubq)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* allow each command to be FETCHed at most once */
+	if (io->flags & UBLK_IO_FLAG_ACTIVE) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV);
+
+	if (ublk_need_map_io(ubq)) {
+		/*
+		 * FETCH_RQ has to provide IO buffer if NEED GET
+		 * DATA is not enabled
+		 */
+		if (!buf_addr && !ublk_need_get_data(ubq))
+			goto out;
+	} else if (buf_addr) {
+		/* User copy requires addr to be unset */
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ublk_fill_io_cmd(io, cmd, buf_addr);
+	ublk_mark_io_ready(ub, ubq);
+out:
+	mutex_unlock(&ub->mutex);
+	return ret;
+}
+
 static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			       unsigned int issue_flags,
 			       const struct ublksrv_io_cmd *ub_cmd)
@@ -1985,33 +2030,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	case UBLK_IO_UNREGISTER_IO_BUF:
 		return ublk_unregister_io_buf(cmd, ub_cmd->addr, issue_flags);
 	case UBLK_IO_FETCH_REQ:
-		/* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
+		ret = ublk_fetch(cmd, ubq, io, ub_cmd->addr);
-		if (ublk_queue_ready(ubq)) {
+		if (ret)
-			ret = -EBUSY;
 			goto out;
-		}
-		/*
-		 * The io is being handled by server, so COMMIT_RQ is expected
-		 * instead of FETCH_REQ
-		 */
-		if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)
-			goto out;
-
-		if (ublk_need_map_io(ubq)) {
-			/*
-			 * FETCH_RQ has to provide IO buffer if NEED GET
-			 * DATA is not enabled
-			 */
-			if (!ub_cmd->addr && !ublk_need_get_data(ubq))
-				goto out;
-		} else if (ub_cmd->addr) {
-			/* User copy requires addr to be unset */
-			ret = -EINVAL;
-			goto out;
-		}
-
-		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
-		ublk_mark_io_ready(ub, ubq);
 		break;
 	case UBLK_IO_COMMIT_AND_FETCH_REQ:
 		req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);