| From e3c02baed2cd408d4b18679ba63eb74144699637 Mon Sep 17 00:00:00 2001 |
| From: Anton Eidelman <anton@lightbitslabs.com> |
| Date: Mon, 10 Feb 2020 10:37:18 -0800 |
| Subject: [PATCH] nvme/tcp: fix bug on double requeue when send fails |
| |
| commit 2d570a7c0251c594489a2c16b82b14ae30345c03 upstream. |
| |
| When nvme_tcp_io_work() fails to send to socket due to |
| connection close/reset, error_recovery work is triggered |
| from nvme_tcp_state_change() socket callback. |
| This cancels all the active requests in the tagset, |
| which requeues them. |
| |
| The failed request, however, was ended and thus requeued |
| individually as well unless send returned -EPIPE. |
| Another return code to be treated the same way is -ECONNRESET. |
| |
| Double requeue caused BUG_ON(blk_queued_rq(rq)) |
| in blk_mq_requeue_request() from either the individual requeue |
| of the failed request or the bulk requeue from |
| blk_mq_tagset_busy_iter(, nvme_cancel_request, ); |
| |
| Signed-off-by: Anton Eidelman <anton@lightbitslabs.com> |
| Reviewed-by: Sagi Grimberg <sagi@grimberg.me> |
| Signed-off-by: Keith Busch <kbusch@kernel.org> |
| Signed-off-by: Jens Axboe <axboe@kernel.dk> |
| Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> |
| |
| diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c |
| index bdadb27b28bb..94d64de6f8af 100644 |
| --- a/drivers/nvme/host/tcp.c |
| +++ b/drivers/nvme/host/tcp.c |
| @@ -1051,7 +1051,12 @@ static void nvme_tcp_io_work(struct work_struct *w) |
| } else if (unlikely(result < 0)) { |
| dev_err(queue->ctrl->ctrl.device, |
| "failed to send request %d\n", result); |
| - if (result != -EPIPE) |
| + |
| + /* |
| + * Fail the request unless peer closed the connection, |
| + * in which case error recovery flow will complete all. |
| + */ |
| + if ((result != -EPIPE) && (result != -ECONNRESET)) |
| nvme_tcp_fail_request(queue->request); |
| nvme_tcp_done_send_req(queue); |
| return; |
| -- |
| 2.7.4 |
| |