[PATCH v6 10/18] nvme-tcp: Use CCR to recover controller that hits an error

[Daniel Wagner]

On Sun, Sep 20, 2026 at 11:28:08AM -0700, Mohamed Khalfella wrote:
> @@ -2731,13 +2755,15 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
>  	struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req);
>  	struct nvme_command *cmd = &pdu->cmd;
>  	int qid = nvme_tcp_queue_id(req->queue);
> +	enum nvme_ctrl_state state;
>  
>  	dev_warn(ctrl->device,
>  		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
>  		 rq->tag, nvme_cid(rq), pdu->hdr.type, cmd->common.opcode,
>  		 nvme_fabrics_opcode_str(qid, cmd), qid);
>  
> -	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
> +	state = nvme_ctrl_state(ctrl);
> +	if (state != NVME_CTRL_LIVE && state != NVME_CTRL_FENCING) {
>  		/*
>  		 * If we are resetting, connecting or deleting we should
>  		 * complete immediately because we may block controller

The documentation should be updated, maybe something like:

          state = nvme_ctrl_state(ctrl);
          if (state != NVME_CTRL_LIVE && state != NVME_CTRL_FENCING) {
                  /*
                   * If fencing has finished or 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.
                   */
                  nvme_tcp_complete_timed_out(rq);
                  return BLK_EH_DONE;
          }

          /*
           * LIVE state should trigger the normal error recovery which will
           * handle completing this request. In FENCING state the request
           * must not be completed before fencing has finished, so just
           * rearm the timer and let the error recovery pick it up.
           */
          nvme_tcp_error_recovery(ctrl);
          return BLK_EH_RESET_TIMER;