From 0a02e39fd1eb2ceb3dd0dc765cb2de4d09697a14 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 19 Oct 2017 16:11:38 -0700 Subject: nvme-fc: correct io termination handling The io completion handling for i/o's that are failing due to to a transport error or association termination had issues, causing io failures (DNR set so retries didn't kick in) or long stalls. Change the io completion handler for the following items: When an io has been completed due to a transport abort (based on an exchange error) or when marked as aborted as part of an association termination (FCOP_FLAGS_TERMIO), set the NVME completion status to NVME_SC_ABORTED. By default, do not set DNR on the status so that a retry can be attempted after association recreate. In cases where an io is failed (non-successful nvme status including aborted), if the controller is being deleted (blk_queue_dying) or the io was part of the ios used for association creation (ctrl state is NEW or RECONNECTING), then additionally set the DNR bit so the io will not be retried. If the failed io was part of association creation, the failure will tear down the partially completioned association and typically restart a new reconnect attempt (another create association later). Rearranged code flow to remove a largely unneeded local variable. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 0d0e898912ad..e1a7e5cdfcf4 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1387,7 +1387,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) struct nvme_command *sqe = &op->cmd_iu.sqe; __le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1); union nvme_result result; - bool complete_rq, terminate_assoc = true; + bool terminate_assoc = true; /* * WARNING: @@ -1429,8 +1429,9 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) fc_dma_sync_single_for_cpu(ctrl->lport->dev, op->fcp_req.rspdma, sizeof(op->rsp_iu), DMA_FROM_DEVICE); - if (atomic_read(&op->state) == FCPOP_STATE_ABORTED) - status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1); + if (atomic_read(&op->state) == FCPOP_STATE_ABORTED || + op->flags & FCOP_FLAGS_TERMIO) + status = cpu_to_le16(NVME_SC_ABORT_REQ << 1); else if (freq->status) status = cpu_to_le16(NVME_SC_INTERNAL << 1); @@ -1494,23 +1495,27 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) done: if (op->flags & FCOP_FLAGS_AEN) { nvme_complete_async_event(&queue->ctrl->ctrl, status, &result); - complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op); + __nvme_fc_fcpop_chk_teardowns(ctrl, op); atomic_set(&op->state, FCPOP_STATE_IDLE); op->flags = FCOP_FLAGS_AEN; /* clear other flags */ nvme_fc_ctrl_put(ctrl); goto check_error; } - complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op); - if (!complete_rq) { - if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) { - status = cpu_to_le16(NVME_SC_ABORT_REQ << 1); - if (blk_queue_dying(rq->q)) - status |= cpu_to_le16(NVME_SC_DNR << 1); - } - nvme_end_request(rq, status, result); - } else + /* + * Force failures of commands if we're killing the controller + * or have an error on a command used to create an new association + */ + if (status && + (blk_queue_dying(rq->q) || + ctrl->ctrl.state == NVME_CTRL_NEW || + ctrl->ctrl.state == NVME_CTRL_RECONNECTING)) + status |= cpu_to_le16(NVME_SC_DNR << 1); + + if (__nvme_fc_fcpop_chk_teardowns(ctrl, op)) __nvme_fc_final_op_cleanup(rq); + else + nvme_end_request(rq, status, result); check_error: if (terminate_assoc) -- cgit