blk-mq: fix potential race in queue restart and driver tag allocation

Once we mark the queue as needing a restart, re-check if we can
get a driver tag. This fixes a theoretical issue where the needed
IO completes _after_ blk_mq_get_driver_tag() fails, but before we
manage to set the restart bit.

Signed-off-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Tested-by: Hannes Reinecke <hare@suse.com>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1f948d5c2715bb666016078b9626d8ce0483e575..fd80101c7591a2ae4642e2ce6f1dd979de3a3d91 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -928,8 +928,16 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
                if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
                        if (!queued && reorder_tags_to_front(list))
                                continue;
+
+                       /*
+                        * We failed getting a driver tag. Mark the queue(s)
+                        * as needing a restart. Retry getting a tag again,
+                        * in case the needed IO completed right before we
+                        * marked the queue as needing a restart.
+                        */
                        blk_mq_sched_mark_restart(hctx);
-                       break;
+                       if (!blk_mq_get_driver_tag(rq, &hctx, false))
+                               break;
                }
                list_del_init(&rq->queuelist);