1 files changed, 33 insertions, 16 deletions

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index b164c662fed3..4e73da2c45bb 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1101,6 +1101,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
 		return;
 
+	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
 	queue_work(nvme_reset_wq, &ctrl->err_work);
 }
 
@@ -1704,6 +1705,22 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	return 0;
 }
 
+static void nvme_rdma_complete_timed_out(struct request *rq)
+{
+	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;
+
+	/* fence other contexts that may complete the command */
+	mutex_lock(&ctrl->teardown_lock);
+	nvme_rdma_stop_queue(queue);
+	if (!blk_mq_request_completed(rq)) {
+		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
+		blk_mq_complete_request(rq);
+	}
+	mutex_unlock(&ctrl->teardown_lock);
+}
+
 static enum blk_eh_timer_return
 nvme_rdma_timeout(struct request *rq, bool reserved)
 {
@@ -1714,29 +1731,29 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
 		 rq->tag, nvme_rdma_queue_idx(queue));
 
-	/*
-	 * Restart the timer if a controller reset is already scheduled. Any
-	 * timed out commands would be handled before entering the connecting
-	 * state.
-	 */
-	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
-		return BLK_EH_RESET_TIMER;
-
 	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.
+		 * If we are resetting, connecting or deleting we should
+		 * complete immediately because we may block controller
+		 * teardown or setup sequence
+		 * - ctrl disable/shutdown fabrics requests
+		 * - connect requests
+		 * - initialization admin requests
+		 * - I/O requests that entered after unquiescing and
+		 *   the controller stopped responding
+		 *
+		 * All other requests should be cancelled by the error
+		 * recovery work, so it's fine that we fail it here.
 		 */
-		flush_work(&ctrl->err_work);
-		nvme_rdma_teardown_io_queues(ctrl, false);
-		nvme_rdma_teardown_admin_queue(ctrl, false);
+		nvme_rdma_complete_timed_out(rq);
 		return BLK_EH_DONE;
 	}
 
-	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
+	/*
+	 * LIVE state should trigger the normal error recovery which will
+	 * handle completing this request.
+	 */
 	nvme_rdma_error_recovery(ctrl);
-
 	return BLK_EH_RESET_TIMER;
 }