blk-mq: don't insert passthrough request into sw queue

In case of real io scheduler, q->elevator is set, so blk_mq_run_hw_queue()
may just check if scheduler queue has request to dispatch, see
__blk_mq_sched_dispatch_requests(). Then IO hang may be caused because
all passthorugh requests may stay in sw queue.

And any passthrough request should have been inserted to hctx->dispatch
always.

Reported-by: Guangwu Zhang <guazhang@redhat.com>
Fixes: d97217e7f024 ("blk-mq: don't queue plugged passthrough requests into scheduler")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230621132208.1142318-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 16c524e37123315610af5094baf5c2f53ed601e7..720b5061ffe880496d7a0264904459ec920291b2 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2728,7 +2728,12 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 
        percpu_ref_get(&this_hctx->queue->q_usage_counter);
        /* passthrough requests should never be issued to the I/O scheduler */
-       if (this_hctx->queue->elevator && !is_passthrough) {
+       if (is_passthrough) {
+               spin_lock(&this_hctx->lock);
+               list_splice_tail_init(&list, &this_hctx->dispatch);
+               spin_unlock(&this_hctx->lock);
+               blk_mq_run_hw_queue(this_hctx, from_sched);
+       } else if (this_hctx->queue->elevator) {
                this_hctx->queue->elevator->type->ops.insert_requests(this_hctx,
                                &list, 0);
                blk_mq_run_hw_queue(this_hctx, from_sched);