blk-mq: fix for flush deadlock

The flush state machine takes in a struct request, which then is
submitted multiple times to the underling driver.  The old block code
requeses the same request for each of those, so it does not have an
issue with tapping into the request pool.  The new one on the other hand
allocates a new request for each of the actualy steps of the flush
sequence. If have already allocated all of the tags for IO, we will
fail allocating the flush request.

Set aside a reserved request just for flushes.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 12 insertions, 2 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index ac804c635040..2dc8de86d0d2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -210,14 +210,15 @@ static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 	return rq;
 }
 
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp)
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
+		gfp_t gfp, bool reserved)
 {
 	struct request *rq;
 
 	if (blk_mq_queue_enter(q))
 		return NULL;
 
-	rq = blk_mq_alloc_request_pinned(q, rw, gfp, false);
+	rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved);
 	blk_mq_put_ctx(rq->mq_ctx);
 	return rq;
 }
@@ -1327,6 +1328,15 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 		reg->queue_depth = BLK_MQ_MAX_DEPTH;
 	}
 
+	/*
+	 * Set aside a tag for flush requests.  It will only be used while
+	 * another flush request is in progress but outside the driver.
+	 *
+	 * TODO: only allocate if flushes are supported
+	 */
+	reg->queue_depth++;
+	reg->reserved_tags++;
+
 	if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN))
 		return ERR_PTR(-EINVAL);