diff options
Diffstat (limited to 'drivers/nvme')
| -rw-r--r-- | drivers/nvme/host/core.c | 18 | ||||
| -rw-r--r-- | drivers/nvme/host/fc.c | 75 | ||||
| -rw-r--r-- | drivers/nvme/host/nvme.h | 3 | ||||
| -rw-r--r-- | drivers/nvme/host/rdma.c | 2 | ||||
| -rw-r--r-- | drivers/nvme/target/rdma.c | 3 |
5 files changed, 85 insertions, 16 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 559d567693b8..962012135b62 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -831,6 +831,8 @@ static int nvme_submit_user_cmd(struct request_queue *q, static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) { struct nvme_ctrl *ctrl = rq->end_io_data; + unsigned long flags; + bool startka = false; blk_mq_free_request(rq); @@ -841,7 +843,13 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) return; } - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + spin_lock_irqsave(&ctrl->lock, flags); + if (ctrl->state == NVME_CTRL_LIVE || + ctrl->state == NVME_CTRL_CONNECTING) + startka = true; + spin_unlock_irqrestore(&ctrl->lock, flags); + if (startka) + schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); } static int nvme_keep_alive(struct nvme_ctrl *ctrl) @@ -3314,6 +3322,9 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) struct nvme_ns *ns, *next; LIST_HEAD(ns_list); + /* prevent racing with ns scanning */ + flush_work(&ctrl->scan_work); + /* * The dead states indicates the controller was not gracefully * disconnected. In that case, we won't be able to flush any data while @@ -3476,7 +3487,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl) nvme_mpath_stop(ctrl); nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); - flush_work(&ctrl->scan_work); cancel_work_sync(&ctrl->fw_act_work); if (ctrl->ops->stop_ctrl) ctrl->ops->stop_ctrl(ctrl); @@ -3585,7 +3595,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, return 0; out_free_name: - kfree_const(dev->kobj.name); + kfree_const(ctrl->device->kobj.name); out_release_instance: ida_simple_remove(&nvme_instance_ida, ctrl->instance); out: @@ -3607,7 +3617,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) down_read(&ctrl->namespaces_rwsem); /* Forcibly unquiesce queues to avoid blocking dispatch */ - if (ctrl->admin_q) + if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q)) blk_mq_unquiesce_queue(ctrl->admin_q); list_for_each_entry(ns, &ctrl->namespaces, list) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 0b70c8bab045..feb86b59170e 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -152,6 +152,7 @@ struct nvme_fc_ctrl { bool ioq_live; bool assoc_active; + atomic_t err_work_active; u64 association_id; struct list_head ctrl_list; /* rport->ctrl_list */ @@ -160,6 +161,7 @@ struct nvme_fc_ctrl { struct blk_mq_tag_set tag_set; struct delayed_work connect_work; + struct work_struct err_work; struct kref ref; u32 flags; @@ -1531,6 +1533,10 @@ nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl) struct nvme_fc_fcp_op *aen_op = ctrl->aen_ops; int i; + /* ensure we've initialized the ops once */ + if (!(aen_op->flags & FCOP_FLAGS_AEN)) + return; + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) __nvme_fc_abort_op(ctrl, aen_op); } @@ -1746,12 +1752,12 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq, struct nvme_fc_queue *queue = &ctrl->queues[queue_idx]; int res; - nvme_req(rq)->ctrl = &ctrl->ctrl; res = __nvme_fc_init_request(ctrl, queue, &op->op, rq, queue->rqcnt++); if (res) return res; op->op.fcp_req.first_sgl = &op->sgl[0]; op->op.fcp_req.private = &op->priv[0]; + nvme_req(rq)->ctrl = &ctrl->ctrl; return res; } @@ -2049,7 +2055,25 @@ nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl) static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) { - /* only proceed if in LIVE state - e.g. on first error */ + int active; + + /* + * if an error (io timeout, etc) while (re)connecting, + * it's an error on creating the new association. + * Start the error recovery thread if it hasn't already + * been started. It is expected there could be multiple + * ios hitting this path before things are cleaned up. + */ + if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) { + active = atomic_xchg(&ctrl->err_work_active, 1); + if (!active && !schedule_work(&ctrl->err_work)) { + atomic_set(&ctrl->err_work_active, 0); + WARN_ON(1); + } + return; + } + + /* Otherwise, only proceed if in LIVE state - e.g. on first error */ if (ctrl->ctrl.state != NVME_CTRL_LIVE) return; @@ -2814,6 +2838,7 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) { struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); + cancel_work_sync(&ctrl->err_work); cancel_delayed_work_sync(&ctrl->connect_work); /* * kill the association on the link side. this will block @@ -2866,23 +2891,30 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) } static void -nvme_fc_reset_ctrl_work(struct work_struct *work) +__nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl) { - struct nvme_fc_ctrl *ctrl = - container_of(work, struct nvme_fc_ctrl, ctrl.reset_work); - int ret; - - nvme_stop_ctrl(&ctrl->ctrl); + nvme_stop_keep_alive(&ctrl->ctrl); /* will block will waiting for io to terminate */ nvme_fc_delete_association(ctrl); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { + if (ctrl->ctrl.state != NVME_CTRL_CONNECTING && + !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) dev_err(ctrl->ctrl.device, "NVME-FC{%d}: error_recovery: Couldn't change state " "to CONNECTING\n", ctrl->cnum); - return; - } +} + +static void +nvme_fc_reset_ctrl_work(struct work_struct *work) +{ + struct nvme_fc_ctrl *ctrl = + container_of(work, struct nvme_fc_ctrl, ctrl.reset_work); + int ret; + + __nvme_fc_terminate_io(ctrl); + + nvme_stop_ctrl(&ctrl->ctrl); if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE) ret = nvme_fc_create_association(ctrl); @@ -2897,6 +2929,24 @@ nvme_fc_reset_ctrl_work(struct work_struct *work) ctrl->cnum); } +static void +nvme_fc_connect_err_work(struct work_struct *work) +{ + struct nvme_fc_ctrl *ctrl = + container_of(work, struct nvme_fc_ctrl, err_work); + + __nvme_fc_terminate_io(ctrl); + + atomic_set(&ctrl->err_work_active, 0); + + /* + * Rescheduling the connection after recovering + * from the io error is left to the reconnect work + * item, which is what should have stalled waiting on + * the io that had the error that scheduled this work. + */ +} + static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { .name = "fc", .module = THIS_MODULE, @@ -3007,6 +3057,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->cnum = idx; ctrl->ioq_live = false; ctrl->assoc_active = false; + atomic_set(&ctrl->err_work_active, 0); init_waitqueue_head(&ctrl->ioabort_wait); get_device(ctrl->dev); @@ -3014,6 +3065,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work); INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work); + INIT_WORK(&ctrl->err_work, nvme_fc_connect_err_work); spin_lock_init(&ctrl->lock); /* io queue count */ @@ -3103,6 +3155,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, fail_ctrl: nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING); cancel_work_sync(&ctrl->ctrl.reset_work); + cancel_work_sync(&ctrl->err_work); cancel_delayed_work_sync(&ctrl->connect_work); ctrl->ctrl.opts = NULL; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index cee79cb388af..081cbdcce880 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -531,6 +531,9 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) static inline int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { + if (ctrl->subsys->cmic & (1 << 3)) + dev_warn(ctrl->device, +"Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n"); return 0; } static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index d181cafedc58..ab6ec7295bf9 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -184,6 +184,7 @@ static int nvme_rdma_alloc_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe, qe->dma = ib_dma_map_single(ibdev, qe->data, capsule_size, dir); if (ib_dma_mapping_error(ibdev, qe->dma)) { kfree(qe->data); + qe->data = NULL; return -ENOMEM; } @@ -823,6 +824,7 @@ out_free_tagset: out_free_async_qe: nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe, sizeof(struct nvme_command), DMA_TO_DEVICE); + ctrl->async_event_sqe.data = NULL; out_free_queue: nvme_rdma_free_queue(&ctrl->queues[0]); return error; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 3f7971d3706d..583086dd9cb9 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -529,6 +529,7 @@ static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc) { struct nvmet_rdma_rsp *rsp = container_of(wc->wr_cqe, struct nvmet_rdma_rsp, send_cqe); + struct nvmet_rdma_queue *queue = cq->cq_context; nvmet_rdma_release_rsp(rsp); @@ -536,7 +537,7 @@ static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc) wc->status != IB_WC_WR_FLUSH_ERR)) { pr_err("SEND for CQE 0x%p failed with status %s (%d).\n", wc->wr_cqe, ib_wc_status_msg(wc->status), wc->status); - nvmet_rdma_error_comp(rsp->queue); + nvmet_rdma_error_comp(queue); } } |