From 1f1a4f89562d3b33b6ca4fc8a4f3bd4cd35ab4ea Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Sun, 13 Nov 2022 13:24:23 +0200 Subject: nvme-tcp: stop auth work after tearing down queues in error recovery when starting error recovery there might be a authentication work running, and it involves I/O commands. Given the controller is tearing down there is no chance for the I/O to complete other than timing out which may unnecessarily take a full io timeout. So first tear down the queues, fail/cancel all inflight I/O (including potentially authentication) and only then stop authentication. This ensures that failover is not stalled due to blocked authentication I/O. Signed-off-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/nvme/host/tcp.c') diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 4f8584657bb7..3fedddf0aedc 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2119,7 +2119,6 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) struct nvme_tcp_ctrl, err_work); struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl; - nvme_auth_stop(ctrl); nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); nvme_tcp_teardown_io_queues(ctrl, false); @@ -2127,6 +2126,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) nvme_start_queues(ctrl); nvme_tcp_teardown_admin_queue(ctrl, false); nvme_start_admin_queue(ctrl); + nvme_auth_stop(ctrl); if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) { /* state change failure is ok if we started ctrl delete */ -- cgit v1.2.3