virtio_blk: fix race between start and stop queue

commit aa0818c6ee8d8e4772725a43550823347bc1ad30 upstream.

When there isn't enough vring descriptor for adding to vq,
blk-mq will be put as stopped state until some of pending
descriptors are completed & freed.

Unfortunately, the vq's interrupt may come just before
blk-mq's BLK_MQ_S_STOPPED flag is set, so the blk-mq will
still be kept as stopped even though lots of descriptors
are completed and freed in the interrupt handler. The worst
case is that all pending descriptors are freed in the
interrupt handler, and the queue is kept as stopped forever.

This patch fixes the problem by starting/stopping blk-mq
with holding vq_lock.

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index b1cb3f4c4db45543c653fd86ce28e75b67522430..6c911c86fb5a404ad1cd2fb990f3d18f49bbea28 100644 (file)
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -144,11 +144,11 @@ static void virtblk_done(struct virtqueue *vq)
                if (unlikely(virtqueue_is_broken(vq)))
                        break;
        } while (!virtqueue_enable_cb(vq));
-       spin_unlock_irqrestore(&vblk->vq_lock, flags);
 
        /* In case queue is stopped waiting for more buffers. */
        if (req_done)
                blk_mq_start_stopped_hw_queues(vblk->disk->queue);
+       spin_unlock_irqrestore(&vblk->vq_lock, flags);
 }
 
 static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
@@ -200,8 +200,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
        spin_lock_irqsave(&vblk->vq_lock, flags);
        if (__virtblk_add_req(vblk->vq, vbr, vbr->sg, num) < 0) {
                virtqueue_kick(vblk->vq);
-               spin_unlock_irqrestore(&vblk->vq_lock, flags);
                blk_mq_stop_hw_queue(hctx);
+               spin_unlock_irqrestore(&vblk->vq_lock, flags);
                return BLK_MQ_RQ_QUEUE_BUSY;
        }