From 4c174e6366746ae8d49f9cc409f728eebb7a9ac9 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 8 Jan 2019 00:53:22 -0800 Subject: [PATCH] nvme-rdma: fix timeout handler Currently, we have several problems with the timeout handler: 1. If we timeout on the controller establishment flow, we will hang because we don't execute the error recovery (and we shouldn't because the create_ctrl flow needs to fail and cleanup on its own) 2. We might also hang if we get a disconnet on a queue while the controller is already deleting. This racy flow can cause the controller disable/shutdown admin command to hang. We cannot complete a timed out request from the timeout handler without mutual exclusion from the teardown flow (e.g. nvme_rdma_error_recovery_work). So we serialize it in the timeout handler and teardown io and admin queues to guarantee that no one races with us from completing the request. Reported-by: Jaesoo Lee Reviewed-by: Christoph Hellwig Signed-off-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/rdma.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 0a2fd2949ad7..4101961feb44 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1689,18 +1689,28 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq, bool reserved) { struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_rdma_queue *queue = req->queue; + struct nvme_rdma_ctrl *ctrl = queue->ctrl; - dev_warn(req->queue->ctrl->ctrl.device, - "I/O %d QID %d timeout, reset controller\n", - rq->tag, nvme_rdma_queue_idx(req->queue)); + dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n", + rq->tag, nvme_rdma_queue_idx(queue)); - /* queue error recovery */ - nvme_rdma_error_recovery(req->queue->ctrl); + if (ctrl->ctrl.state != NVME_CTRL_LIVE) { + /* + * Teardown immediately if controller times out while starting + * or we are already started error recovery. all outstanding + * requests are completed on shutdown, so we return BLK_EH_DONE. + */ + flush_work(&ctrl->err_work); + nvme_rdma_teardown_io_queues(ctrl, false); + nvme_rdma_teardown_admin_queue(ctrl, false); + return BLK_EH_DONE; + } - /* fail with DNR on cmd timeout */ - nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR; + dev_warn(ctrl->ctrl.device, "starting error recovery\n"); + nvme_rdma_error_recovery(ctrl); - return BLK_EH_DONE; + return BLK_EH_RESET_TIMER; } static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,