Commit 70f437fb authored by Keith Busch's avatar Keith Busch Committed by Christoph Hellwig
Browse files

nvme-tcp: fix io_work priority inversion 



Dispatching requests inline with the .queue_rq() call may block while
holding the send_mutex. If the tcp io_work also happens to schedule, it
may see the req_list is non-empty, leaving "pending" true and remaining
in TASK_RUNNING. Since io_work is of higher scheduling priority, the
.queue_rq task may not get a chance to run, blocking forward progress
and leading to io timeouts.

Instead of checking for pending requests within io_work, let the queueing
restart io_work outside the send_mutex lock if there is more work to be
done.

Fixes: a0fdd141 ("nvme-tcp: rerun io_work if req_list is not empty")
Reported-by: default avatarSamuel Jones <sjones@kalrayinc.com>
Signed-off-by: default avatarKeith Busch <kbusch@kernel.org>
Reviewed-by: default avatarSagi Grimberg <sagi@grimberg.me>
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
parent 9817d763

drivers/nvme/host/tcp.c

+10 −10
Original line number Diff line number Diff line
@@ -274,6 +274,12 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue) 
	} while (ret > 0);

}



static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)

{

	return !list_empty(&queue->send_list) ||

		!llist_empty(&queue->req_list) || queue->more_requests;

}



static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,

		bool sync, bool last)

{
@@ -294,9 +300,10 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, 
		nvme_tcp_send_all(queue);

		queue->more_requests = false;

		mutex_unlock(&queue->send_mutex);

	} else if (last) {

		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);

	}



	if (last && nvme_tcp_queue_more(queue))

		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);

}



static void nvme_tcp_process_req_list(struct nvme_tcp_queue *queue)
@@ -906,12 +913,6 @@ static void nvme_tcp_state_change(struct sock *sk) 
	read_unlock_bh(&sk->sk_callback_lock);

}



static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)

{

	return !list_empty(&queue->send_list) ||

		!llist_empty(&queue->req_list) || queue->more_requests;

}



static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue)

{

	queue->request = NULL;
@@ -1145,8 +1146,7 @@ static void nvme_tcp_io_work(struct work_struct *w) 
				pending = true;

			else if (unlikely(result < 0))

				break;

		} else

			pending = !llist_empty(&queue->req_list);

		}



		result = nvme_tcp_try_recv(queue);

		if (result > 0)