diff options
Diffstat (limited to 'drivers/nvme/host/fc.c')
| -rw-r--r-- | drivers/nvme/host/fc.c | 793 |
1 files changed, 592 insertions, 201 deletions
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index be49d0f793816..7ab0be55c7d06 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -30,27 +30,19 @@ /* *************************** Data Structures/Defines ****************** */ -/* - * We handle AEN commands ourselves and don't even let the - * block layer know about them. - */ -#define NVME_FC_NR_AEN_COMMANDS 1 -#define NVME_FC_AQ_BLKMQ_DEPTH \ - (NVME_AQ_DEPTH - NVME_FC_NR_AEN_COMMANDS) -#define AEN_CMDID_BASE (NVME_FC_AQ_BLKMQ_DEPTH + 1) - enum nvme_fc_queue_flags { NVME_FC_Q_CONNECTED = (1 << 0), }; #define NVMEFC_QUEUE_DELAY 3 /* ms units */ +#define NVME_FC_DEFAULT_DEV_LOSS_TMO 60 /* seconds */ + struct nvme_fc_queue { struct nvme_fc_ctrl *ctrl; struct device *dev; struct blk_mq_hw_ctx *hctx; void *lldd_handle; - int queue_size; size_t cmnd_capsule_len; u32 qnum; u32 rqcnt; @@ -124,6 +116,7 @@ struct nvme_fc_lport { struct device *dev; /* physical device for dma */ struct nvme_fc_port_template *ops; struct kref ref; + atomic_t act_rport_cnt; } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ struct nvme_fc_rport { @@ -136,6 +129,8 @@ struct nvme_fc_rport { struct nvme_fc_lport *lport; spinlock_t lock; struct kref ref; + atomic_t act_ctrl_cnt; + unsigned long dev_loss_end; } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ enum nvme_fcctrl_flags { @@ -150,6 +145,7 @@ struct nvme_fc_ctrl { struct nvme_fc_rport *rport; u32 cnum; + bool assoc_active; u64 association_id; struct list_head ctrl_list; /* rport->ctrl_list */ @@ -157,7 +153,6 @@ struct nvme_fc_ctrl { struct blk_mq_tag_set admin_tag_set; struct blk_mq_tag_set tag_set; - struct work_struct delete_work; struct delayed_work connect_work; struct kref ref; @@ -165,7 +160,7 @@ struct nvme_fc_ctrl { u32 iocnt; wait_queue_head_t ioabort_wait; - struct nvme_fc_fcp_op aen_ops[NVME_FC_NR_AEN_COMMANDS]; + struct nvme_fc_fcp_op aen_ops[NVME_NR_AEN_COMMANDS]; struct nvme_ctrl ctrl; }; @@ -213,10 +208,16 @@ static DEFINE_IDA(nvme_fc_ctrl_cnt); +/* + * These items are short-term. They will eventually be moved into + * a generic FC class. See comments in module init. + */ +static struct class *fc_class; +static struct device *fc_udev_device; + /* *********************** FC-NVME Port Management ************************ */ -static int __nvme_fc_del_ctrl(struct nvme_fc_ctrl *); static void __nvme_fc_delete_hw_queue(struct nvme_fc_ctrl *, struct nvme_fc_queue *, unsigned int); @@ -235,9 +236,6 @@ nvme_fc_free_lport(struct kref *ref) list_del(&lport->port_list); spin_unlock_irqrestore(&nvme_fc_lock, flags); - /* let the LLDD know we've finished tearing it down */ - lport->ops->localport_delete(&lport->localport); - ida_simple_remove(&nvme_fc_local_port_cnt, lport->localport.port_num); ida_destroy(&lport->endp_cnt); @@ -260,7 +258,9 @@ nvme_fc_lport_get(struct nvme_fc_lport *lport) static struct nvme_fc_lport * -nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo) +nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo, + struct nvme_fc_port_template *ops, + struct device *dev) { struct nvme_fc_lport *lport; unsigned long flags; @@ -272,6 +272,11 @@ nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo) lport->localport.port_name != pinfo->port_name) continue; + if (lport->dev != dev) { + lport = ERR_PTR(-EXDEV); + goto out_done; + } + if (lport->localport.port_state != FC_OBJSTATE_DELETED) { lport = ERR_PTR(-EEXIST); goto out_done; @@ -288,6 +293,7 @@ nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo) /* resume the lport */ + lport->ops = ops; lport->localport.port_role = pinfo->port_role; lport->localport.port_id = pinfo->port_id; lport->localport.port_state = FC_OBJSTATE_ONLINE; @@ -348,7 +354,7 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, * expired, we can simply re-enable the localport. Remoteports * and controller reconnections should resume naturally. */ - newrec = nvme_fc_attach_to_unreg_lport(pinfo); + newrec = nvme_fc_attach_to_unreg_lport(pinfo, template, dev); /* found an lport, but something about its state is bad */ if (IS_ERR(newrec)) { @@ -384,6 +390,7 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, INIT_LIST_HEAD(&newrec->port_list); INIT_LIST_HEAD(&newrec->endp_list); kref_init(&newrec->ref); + atomic_set(&newrec->act_rport_cnt, 0); newrec->ops = template; newrec->dev = dev; ida_init(&newrec->endp_cnt); @@ -446,12 +453,177 @@ nvme_fc_unregister_localport(struct nvme_fc_local_port *portptr) spin_unlock_irqrestore(&nvme_fc_lock, flags); + if (atomic_read(&lport->act_rport_cnt) == 0) + lport->ops->localport_delete(&lport->localport); + nvme_fc_lport_put(lport); return 0; } EXPORT_SYMBOL_GPL(nvme_fc_unregister_localport); +/* + * TRADDR strings, per FC-NVME are fixed format: + * "nn-0x<16hexdigits>:pn-0x<16hexdigits>" - 43 characters + * udev event will only differ by prefix of what field is + * being specified: + * "NVMEFC_HOST_TRADDR=" or "NVMEFC_TRADDR=" - 19 max characters + * 19 + 43 + null_fudge = 64 characters + */ +#define FCNVME_TRADDR_LENGTH 64 + +static void +nvme_fc_signal_discovery_scan(struct nvme_fc_lport *lport, + struct nvme_fc_rport *rport) +{ + char hostaddr[FCNVME_TRADDR_LENGTH]; /* NVMEFC_HOST_TRADDR=...*/ + char tgtaddr[FCNVME_TRADDR_LENGTH]; /* NVMEFC_TRADDR=...*/ + char *envp[4] = { "FC_EVENT=nvmediscovery", hostaddr, tgtaddr, NULL }; + + if (!(rport->remoteport.port_role & FC_PORT_ROLE_NVME_DISCOVERY)) + return; + + snprintf(hostaddr, sizeof(hostaddr), + "NVMEFC_HOST_TRADDR=nn-0x%016llx:pn-0x%016llx", + lport->localport.node_name, lport->localport.port_name); + snprintf(tgtaddr, sizeof(tgtaddr), + "NVMEFC_TRADDR=nn-0x%016llx:pn-0x%016llx", + rport->remoteport.node_name, rport->remoteport.port_name); + kobject_uevent_env(&fc_udev_device->kobj, KOBJ_CHANGE, envp); +} + +static void +nvme_fc_free_rport(struct kref *ref) +{ + struct nvme_fc_rport *rport = + container_of(ref, struct nvme_fc_rport, ref); + struct nvme_fc_lport *lport = + localport_to_lport(rport->remoteport.localport); + unsigned long flags; + + WARN_ON(rport->remoteport.port_state != FC_OBJSTATE_DELETED); + WARN_ON(!list_empty(&rport->ctrl_list)); + + /* remove from lport list */ + spin_lock_irqsave(&nvme_fc_lock, flags); + list_del(&rport->endp_list); + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + ida_simple_remove(&lport->endp_cnt, rport->remoteport.port_num); + + kfree(rport); + + nvme_fc_lport_put(lport); +} + +static void +nvme_fc_rport_put(struct nvme_fc_rport *rport) +{ + kref_put(&rport->ref, nvme_fc_free_rport); +} + +static int +nvme_fc_rport_get(struct nvme_fc_rport *rport) +{ + return kref_get_unless_zero(&rport->ref); +} + +static void +nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl) +{ + switch (ctrl->ctrl.state) { + case NVME_CTRL_NEW: + case NVME_CTRL_RECONNECTING: + /* + * As all reconnects were suppressed, schedule a + * connect. + */ + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: connectivity re-established. " + "Attempting reconnect\n", ctrl->cnum); + + queue_delayed_work(nvme_wq, &ctrl->connect_work, 0); + break; + + case NVME_CTRL_RESETTING: + /* + * Controller is already in the process of terminating the + * association. No need to do anything further. The reconnect + * step will naturally occur after the reset completes. + */ + break; + + default: + /* no action to take - let it delete */ + break; + } +} + +static struct nvme_fc_rport * +nvme_fc_attach_to_suspended_rport(struct nvme_fc_lport *lport, + struct nvme_fc_port_info *pinfo) +{ + struct nvme_fc_rport *rport; + struct nvme_fc_ctrl *ctrl; + unsigned long flags; + + spin_lock_irqsave(&nvme_fc_lock, flags); + + list_for_each_entry(rport, &lport->endp_list, endp_list) { + if (rport->remoteport.node_name != pinfo->node_name || + rport->remoteport.port_name != pinfo->port_name) + continue; + + if (!nvme_fc_rport_get(rport)) { + rport = ERR_PTR(-ENOLCK); + goto out_done; + } + + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + spin_lock_irqsave(&rport->lock, flags); + + /* has it been unregistered */ + if (rport->remoteport.port_state != FC_OBJSTATE_DELETED) { + /* means lldd called us twice */ + spin_unlock_irqrestore(&rport->lock, flags); + nvme_fc_rport_put(rport); + return ERR_PTR(-ESTALE); + } + + rport->remoteport.port_state = FC_OBJSTATE_ONLINE; + rport->dev_loss_end = 0; + + /* + * kick off a reconnect attempt on all associations to the + * remote port. A successful reconnects will resume i/o. + */ + list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) + nvme_fc_resume_controller(ctrl); + + spin_unlock_irqrestore(&rport->lock, flags); + + return rport; + } + + rport = NULL; + +out_done: + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + return rport; +} + +static inline void +__nvme_fc_set_dev_loss_tmo(struct nvme_fc_rport *rport, + struct nvme_fc_port_info *pinfo) +{ + if (pinfo->dev_loss_tmo) + rport->remoteport.dev_loss_tmo = pinfo->dev_loss_tmo; + else + rport->remoteport.dev_loss_tmo = NVME_FC_DEFAULT_DEV_LOSS_TMO; +} + /** * nvme_fc_register_remoteport - transport entry point called by an * LLDD to register the existence of a NVME @@ -478,28 +650,52 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, unsigned long flags; int ret, idx; + if (!nvme_fc_lport_get(lport)) { + ret = -ESHUTDOWN; + goto out_reghost_failed; + } + + /* + * look to see if there is already a remoteport that is waiting + * for a reconnect (within dev_loss_tmo) with the same WWN's. + * If so, transition to it and reconnect. + */ + newrec = nvme_fc_attach_to_suspended_rport(lport, pinfo); + + /* found an rport, but something about its state is bad */ + if (IS_ERR(newrec)) { + ret = PTR_ERR(newrec); + goto out_lport_put; + + /* found existing rport, which was resumed */ + } else if (newrec) { + nvme_fc_lport_put(lport); + __nvme_fc_set_dev_loss_tmo(newrec, pinfo); + nvme_fc_signal_discovery_scan(lport, newrec); + *portptr = &newrec->remoteport; + return 0; + } + + /* nothing found - allocate a new remoteport struct */ + newrec = kmalloc((sizeof(*newrec) + lport->ops->remote_priv_sz), GFP_KERNEL); if (!newrec) { ret = -ENOMEM; - goto out_reghost_failed; - } - - if (!nvme_fc_lport_get(lport)) { - ret = -ESHUTDOWN; - goto out_kfree_rport; + goto out_lport_put; } idx = ida_simple_get(&lport->endp_cnt, 0, 0, GFP_KERNEL); if (idx < 0) { ret = -ENOSPC; - goto out_lport_put; + goto out_kfree_rport; } INIT_LIST_HEAD(&newrec->endp_list); INIT_LIST_HEAD(&newrec->ctrl_list); INIT_LIST_HEAD(&newrec->ls_req_list); kref_init(&newrec->ref); + atomic_set(&newrec->act_ctrl_cnt, 0); spin_lock_init(&newrec->lock); newrec->remoteport.localport = &lport->localport; newrec->dev = lport->dev; @@ -511,63 +707,27 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, newrec->remoteport.port_id = pinfo->port_id; newrec->remoteport.port_state = FC_OBJSTATE_ONLINE; newrec->remoteport.port_num = idx; + __nvme_fc_set_dev_loss_tmo(newrec, pinfo); spin_lock_irqsave(&nvme_fc_lock, flags); list_add_tail(&newrec->endp_list, &lport->endp_list); spin_unlock_irqrestore(&nvme_fc_lock, flags); + nvme_fc_signal_discovery_scan(lport, newrec); + *portptr = &newrec->remoteport; return 0; -out_lport_put: - nvme_fc_lport_put(lport); out_kfree_rport: kfree(newrec); +out_lport_put: + nvme_fc_lport_put(lport); out_reghost_failed: *portptr = NULL; return ret; } EXPORT_SYMBOL_GPL(nvme_fc_register_remoteport); -static void -nvme_fc_free_rport(struct kref *ref) -{ - struct nvme_fc_rport *rport = - container_of(ref, struct nvme_fc_rport, ref); - struct nvme_fc_lport *lport = - localport_to_lport(rport->remoteport.localport); - unsigned long flags; - - WARN_ON(rport->remoteport.port_state != FC_OBJSTATE_DELETED); - WARN_ON(!list_empty(&rport->ctrl_list)); - - /* remove from lport list */ - spin_lock_irqsave(&nvme_fc_lock, flags); - list_del(&rport->endp_list); - spin_unlock_irqrestore(&nvme_fc_lock, flags); - - /* let the LLDD know we've finished tearing it down */ - lport->ops->remoteport_delete(&rport->remoteport); - - ida_simple_remove(&lport->endp_cnt, rport->remoteport.port_num); - - kfree(rport); - - nvme_fc_lport_put(lport); -} - -static void -nvme_fc_rport_put(struct nvme_fc_rport *rport) -{ - kref_put(&rport->ref, nvme_fc_free_rport); -} - -static int -nvme_fc_rport_get(struct nvme_fc_rport *rport) -{ - return kref_get_unless_zero(&rport->ref); -} - static int nvme_fc_abort_lsops(struct nvme_fc_rport *rport) { @@ -592,6 +752,58 @@ restart: return 0; } +static void +nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl) +{ + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: controller connectivity lost. Awaiting " + "Reconnect", ctrl->cnum); + + switch (ctrl->ctrl.state) { + case NVME_CTRL_NEW: + case NVME_CTRL_LIVE: + /* + * Schedule a controller reset. The reset will terminate the + * association and schedule the reconnect timer. Reconnects + * will be attempted until either the ctlr_loss_tmo + * (max_retries * connect_delay) expires or the remoteport's + * dev_loss_tmo expires. + */ + if (nvme_reset_ctrl(&ctrl->ctrl)) { + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: Couldn't schedule reset. " + "Deleting controller.\n", + ctrl->cnum); + nvme_delete_ctrl(&ctrl->ctrl); + } + break; + + case NVME_CTRL_RECONNECTING: + /* + * The association has already been terminated and the + * controller is attempting reconnects. No need to do anything + * futher. Reconnects will be attempted until either the + * ctlr_loss_tmo (max_retries * connect_delay) expires or the + * remoteport's dev_loss_tmo expires. + */ + break; + + case NVME_CTRL_RESETTING: + /* + * Controller is already in the process of terminating the + * association. No need to do anything further. The reconnect + * step will kick in naturally after the association is + * terminated. + */ + break; + + case NVME_CTRL_DELETING: + default: + /* no action to take - let it delete */ + break; + } +} + /** * nvme_fc_unregister_remoteport - transport entry point called by an * LLDD to deregister/remove a previously @@ -621,19 +833,78 @@ nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *portptr) } portptr->port_state = FC_OBJSTATE_DELETED; - /* tear down all associations to the remote port */ - list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) - __nvme_fc_del_ctrl(ctrl); + rport->dev_loss_end = jiffies + (portptr->dev_loss_tmo * HZ); + + list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) { + /* if dev_loss_tmo==0, dev loss is immediate */ + if (!portptr->dev_loss_tmo) { + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: controller connectivity lost. " + "Deleting controller.\n", + ctrl->cnum); + nvme_delete_ctrl(&ctrl->ctrl); + } else + nvme_fc_ctrl_connectivity_loss(ctrl); + } spin_unlock_irqrestore(&rport->lock, flags); nvme_fc_abort_lsops(rport); + if (atomic_read(&rport->act_ctrl_cnt) == 0) + rport->lport->ops->remoteport_delete(portptr); + + /* + * release the reference, which will allow, if all controllers + * go away, which should only occur after dev_loss_tmo occurs, + * for the rport to be torn down. + */ nvme_fc_rport_put(rport); + return 0; } EXPORT_SYMBOL_GPL(nvme_fc_unregister_remoteport); +/** + * nvme_fc_rescan_remoteport - transport entry point called by an + * LLDD to request a nvme device rescan. + * @remoteport: pointer to the (registered) remote port that is to be + * rescanned. + * + * Returns: N/A + */ +void +nvme_fc_rescan_remoteport(struct nvme_fc_remote_port *remoteport) +{ + struct nvme_fc_rport *rport = remoteport_to_rport(remoteport); + + nvme_fc_signal_discovery_scan(rport->lport, rport); +} +EXPORT_SYMBOL_GPL(nvme_fc_rescan_remoteport); + +int +nvme_fc_set_remoteport_devloss(struct nvme_fc_remote_port *portptr, + u32 dev_loss_tmo) +{ + struct nvme_fc_rport *rport = remoteport_to_rport(portptr); + unsigned long flags; + + spin_lock_irqsave(&rport->lock, flags); + + if (portptr->port_state != FC_OBJSTATE_ONLINE) { + spin_unlock_irqrestore(&rport->lock, flags); + return -EINVAL; + } + + /* a dev_loss_tmo of 0 (immediate) is allowed to be set */ + rport->remoteport.dev_loss_tmo = dev_loss_tmo; + + spin_unlock_irqrestore(&rport->lock, flags); + + return 0; +} +EXPORT_SYMBOL_GPL(nvme_fc_set_remoteport_devloss); + /* *********************** FC-NVME DMA Handling **************************** */ @@ -723,7 +994,6 @@ fc_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, dma_unmap_sg(dev, sg, nents, dir); } - /* *********************** FC-NVME LS Handling **************************** */ static void nvme_fc_ctrl_put(struct nvme_fc_ctrl *); @@ -1266,7 +1536,7 @@ nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl) unsigned long flags; int i, ret; - for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) { + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) { if (atomic_read(&aen_op->state) != FCPOP_STATE_ACTIVE) continue; @@ -1331,7 +1601,7 @@ 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: @@ -1373,8 +1643,9 @@ 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); @@ -1438,23 +1709,27 @@ 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) @@ -1531,7 +1806,7 @@ nvme_fc_init_aen_ops(struct nvme_fc_ctrl *ctrl) int i, ret; aen_op = ctrl->aen_ops; - for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) { + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) { private = kzalloc(ctrl->lport->ops->fcprqst_priv_sz, GFP_KERNEL); if (!private) @@ -1541,7 +1816,7 @@ nvme_fc_init_aen_ops(struct nvme_fc_ctrl *ctrl) sqe = &cmdiu->sqe; ret = __nvme_fc_init_request(ctrl, &ctrl->queues[0], aen_op, (struct request *)NULL, - (AEN_CMDID_BASE + i)); + (NVME_AQ_BLK_MQ_DEPTH + i)); if (ret) { kfree(private); return ret; @@ -1554,7 +1829,7 @@ nvme_fc_init_aen_ops(struct nvme_fc_ctrl *ctrl) memset(sqe, 0, sizeof(*sqe)); sqe->common.opcode = nvme_admin_async_event; /* Note: core layer may overwrite the sqe.command_id value */ - sqe->common.command_id = AEN_CMDID_BASE + i; + sqe->common.command_id = NVME_AQ_BLK_MQ_DEPTH + i; } return 0; } @@ -1566,7 +1841,7 @@ nvme_fc_term_aen_ops(struct nvme_fc_ctrl *ctrl) int i; aen_op = ctrl->aen_ops; - for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) { + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) { if (!aen_op->fcp_req.private) continue; @@ -1610,7 +1885,7 @@ nvme_fc_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, } static void -nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx, size_t queue_size) +nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx) { struct nvme_fc_queue *queue; @@ -1626,8 +1901,6 @@ nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx, size_t queue_size) else queue->cmnd_capsule_len = sizeof(struct nvme_command); - queue->queue_size = queue_size; - /* * Considered whether we should allocate buffers for all SQEs * and CQEs and dma map them - mapping their respective entries @@ -1751,7 +2024,7 @@ nvme_fc_init_io_queues(struct nvme_fc_ctrl *ctrl) int i; for (i = 1; i < ctrl->ctrl.queue_count; i++) - nvme_fc_init_queue(ctrl, i, ctrl->ctrl.sqsize); + nvme_fc_init_queue(ctrl, i); } static void @@ -1825,13 +2098,6 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: resetting controller\n", ctrl->cnum); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { - dev_err(ctrl->ctrl.device, - "NVME-FC{%d}: error_recovery: Couldn't change state " - "to RECONNECTING\n", ctrl->cnum); - return; - } - nvme_reset_ctrl(&ctrl->ctrl); } @@ -1842,13 +2108,14 @@ nvme_fc_timeout(struct request *rq, bool reserved) struct nvme_fc_ctrl *ctrl = op->ctrl; int ret; - if (reserved) + if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE || + atomic_read(&op->state) == FCPOP_STATE_ABORTED) return BLK_EH_RESET_TIMER; ret = __nvme_fc_abort_op(ctrl, op); if (ret) - /* io wasn't active to abort consider it done */ - return BLK_EH_HANDLED; + /* io wasn't active to abort */ + return BLK_EH_NOT_HANDLED; /* * we can't individually ABTS an io without affecting the queue, @@ -1859,7 +2126,12 @@ nvme_fc_timeout(struct request *rq, bool reserved) */ nvme_fc_error_recovery(ctrl, "io timeout error"); - return BLK_EH_HANDLED; + /* + * the io abort has been initiated. Have the reset timer + * restarted and the abort completion will complete the io + * shortly. Avoids a synchronous wait while the abort finishes. + */ + return BLK_EH_RESET_TIMER; } static int @@ -2110,7 +2382,7 @@ nvme_fc_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag) } static void -nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx) +nvme_fc_submit_async_event(struct nvme_ctrl *arg) { struct nvme_fc_ctrl *ctrl = to_fc_ctrl(arg); struct nvme_fc_fcp_op *aen_op; @@ -2118,9 +2390,6 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx) bool terminating = false; blk_status_t ret; - if (aer_idx > NVME_FC_NR_AEN_COMMANDS) - return; - spin_lock_irqsave(&ctrl->lock, flags); if (ctrl->flags & FCCTRL_TERMIO) terminating = true; @@ -2129,13 +2398,13 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx) if (terminating) return; - aen_op = &ctrl->aen_ops[aer_idx]; + aen_op = &ctrl->aen_ops[0]; ret = nvme_fc_start_fcp_op(ctrl, aen_op->queue, aen_op, 0, NVMEFC_FCP_NODATA); if (ret) dev_err(ctrl->ctrl.device, - "failed async event work [%d]\n", aer_idx); + "failed async event work\n"); } static void @@ -2337,7 +2606,7 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl) nvme_fc_init_io_queues(ctrl); - ret = blk_mq_reinit_tagset(&ctrl->tag_set, nvme_fc_reinit_request); + ret = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.tagset); if (ret) goto out_free_io_queues; @@ -2360,6 +2629,61 @@ out_free_io_queues: return ret; } +static void +nvme_fc_rport_active_on_lport(struct nvme_fc_rport *rport) +{ + struct nvme_fc_lport *lport = rport->lport; + + atomic_inc(&lport->act_rport_cnt); +} + +static void +nvme_fc_rport_inactive_on_lport(struct nvme_fc_rport *rport) +{ + struct nvme_fc_lport *lport = rport->lport; + u32 cnt; + + cnt = atomic_dec_return(&lport->act_rport_cnt); + if (cnt == 0 && lport->localport.port_state == FC_OBJSTATE_DELETED) + lport->ops->localport_delete(&lport->localport); +} + +static int +nvme_fc_ctlr_active_on_rport(struct nvme_fc_ctrl *ctrl) +{ + struct nvme_fc_rport *rport = ctrl->rport; + u32 cnt; + + if (ctrl->assoc_active) + return 1; + + ctrl->assoc_active = true; + cnt = atomic_inc_return(&rport->act_ctrl_cnt); + if (cnt == 1) + nvme_fc_rport_active_on_lport(rport); + + return 0; +} + +static int +nvme_fc_ctlr_inactive_on_rport(struct nvme_fc_ctrl *ctrl) +{ + struct nvme_fc_rport *rport = ctrl->rport; + struct nvme_fc_lport *lport = rport->lport; + u32 cnt; + + /* ctrl->assoc_active=false will be set independently */ + + cnt = atomic_dec_return(&rport->act_ctrl_cnt); + if (cnt == 0) { + if (rport->remoteport.port_state == FC_OBJSTATE_DELETED) + lport->ops->remoteport_delete(&rport->remoteport); + nvme_fc_rport_inactive_on_lport(rport); + } + + return 0; +} + /* * This routine restarts the controller on the host side, and * on the link side, recreates the controller association. @@ -2368,26 +2692,31 @@ static int nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) { struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; - u32 segs; int ret; bool changed; ++ctrl->ctrl.nr_reconnects; + if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE) + return -ENODEV; + + if (nvme_fc_ctlr_active_on_rport(ctrl)) + return -ENOTUNIQ; + /* * Create the admin queue */ - nvme_fc_init_queue(ctrl, 0, NVME_FC_AQ_BLKMQ_DEPTH); + nvme_fc_init_queue(ctrl, 0); ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0, - NVME_FC_AQ_BLKMQ_DEPTH); + NVME_AQ_BLK_MQ_DEPTH); if (ret) goto out_free_queue; ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0], - NVME_FC_AQ_BLKMQ_DEPTH, - (NVME_FC_AQ_BLKMQ_DEPTH / 4)); + NVME_AQ_BLK_MQ_DEPTH, + (NVME_AQ_BLK_MQ_DEPTH / 4)); if (ret) goto out_delete_hw_queue; @@ -2419,9 +2748,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (ret) goto out_disconnect_admin_queue; - segs = min_t(u32, NVME_FC_MAX_SEGMENTS, - ctrl->lport->ops->max_sgl_segments); - ctrl->ctrl.max_hw_sectors = (segs - 1) << (PAGE_SHIFT - 9); + ctrl->ctrl.max_hw_sectors = + (ctrl->lport->ops->max_sgl_segments - 1) << (PAGE_SHIFT - 9); ret = nvme_init_identify(&ctrl->ctrl); if (ret) @@ -2465,11 +2793,11 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - WARN_ON_ONCE(!changed); ctrl->ctrl.nr_reconnects = 0; - nvme_start_ctrl(&ctrl->ctrl); + if (changed) + nvme_start_ctrl(&ctrl->ctrl); return 0; /* Success */ @@ -2482,6 +2810,8 @@ out_delete_hw_queue: __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0); out_free_queue: nvme_fc_free_queue(&ctrl->queues[0]); + ctrl->assoc_active = false; + nvme_fc_ctlr_inactive_on_rport(ctrl); return ret; } @@ -2497,6 +2827,10 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) { unsigned long flags; + if (!ctrl->assoc_active) + return; + ctrl->assoc_active = false; + spin_lock_irqsave(&ctrl->lock, flags); ctrl->flags |= FCCTRL_TERMIO; ctrl->iocnt = 0; @@ -2537,7 +2871,8 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) * use blk_mq_tagset_busy_itr() and the transport routine to * terminate the exchanges. */ - blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + if (ctrl->ctrl.state != NVME_CTRL_NEW) + blk_mq_quiesce_queue(ctrl->ctrl.admin_q); blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_fc_terminate_exchange, &ctrl->ctrl); @@ -2568,102 +2903,64 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0); nvme_fc_free_queue(&ctrl->queues[0]); + + nvme_fc_ctlr_inactive_on_rport(ctrl); } static void -nvme_fc_delete_ctrl_work(struct work_struct *work) +nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) { - struct nvme_fc_ctrl *ctrl = - container_of(work, struct nvme_fc_ctrl, delete_work); + struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); - cancel_work_sync(&ctrl->ctrl.reset_work); cancel_delayed_work_sync(&ctrl->connect_work); - nvme_stop_ctrl(&ctrl->ctrl); - nvme_remove_namespaces(&ctrl->ctrl); /* * kill the association on the link side. this will block * waiting for io to terminate */ nvme_fc_delete_association(ctrl); - - /* - * tear down the controller - * After the last reference on the nvme ctrl is removed, - * the transport nvme_fc_nvme_ctrl_freed() callback will be - * invoked. From there, the transport will tear down it's - * logical queues and association. - */ - nvme_uninit_ctrl(&ctrl->ctrl); - - nvme_put_ctrl(&ctrl->ctrl); -} - -static bool -__nvme_fc_schedule_delete_work(struct nvme_fc_ctrl *ctrl) -{ - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) - return true; - - if (!queue_work(nvme_wq, &ctrl->delete_work)) - return true; - - return false; -} - -static int -__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl) -{ - return __nvme_fc_schedule_delete_work(ctrl) ? -EBUSY : 0; -} - -/* - * Request from nvme core layer to delete the controller - */ -static int -nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl) -{ - struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); - int ret; - - if (!kref_get_unless_zero(&ctrl->ctrl.kref)) - return -EBUSY; - - ret = __nvme_fc_del_ctrl(ctrl); - - if (!ret) - flush_workqueue(nvme_wq); - - nvme_put_ctrl(&ctrl->ctrl); - - return ret; } static void nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) { - /* If we are resetting/deleting then do nothing */ - if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) { - WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW || - ctrl->ctrl.state == NVME_CTRL_LIVE); - return; - } + struct nvme_fc_rport *rport = ctrl->rport; + struct nvme_fc_remote_port *portptr = &rport->remoteport; + unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ; + bool recon = true; - dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n", - ctrl->cnum, status); + if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) + return; - if (nvmf_should_reconnect(&ctrl->ctrl)) { + if (portptr->port_state == FC_OBJSTATE_ONLINE) dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: Reconnect attempt in %d seconds.\n", - ctrl->cnum, ctrl->ctrl.opts->reconnect_delay); - queue_delayed_work(nvme_wq, &ctrl->connect_work, - ctrl->ctrl.opts->reconnect_delay * HZ); + "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n", + ctrl->cnum, status); + else if (time_after_eq(jiffies, rport->dev_loss_end)) + recon = false; + + if (recon && nvmf_should_reconnect(&ctrl->ctrl)) { + if (portptr->port_state == FC_OBJSTATE_ONLINE) + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: Reconnect attempt in %ld " + "seconds\n", + ctrl->cnum, recon_delay / HZ); + else if (time_after(jiffies + recon_delay, rport->dev_loss_end)) + recon_delay = rport->dev_loss_end - jiffies; + + queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay); } else { - dev_warn(ctrl->ctrl.device, + if (portptr->port_state == FC_OBJSTATE_ONLINE) + dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: Max reconnect attempts (%d) " "reached. Removing controller\n", ctrl->cnum, ctrl->ctrl.nr_reconnects); - WARN_ON(__nvme_fc_schedule_delete_work(ctrl)); + else + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: dev_loss_tmo (%d) expired " + "while waiting for remoteport connectivity. " + "Removing controller\n", ctrl->cnum, + portptr->dev_loss_tmo); + WARN_ON(nvme_delete_ctrl(&ctrl->ctrl)); } } @@ -2675,15 +2972,28 @@ nvme_fc_reset_ctrl_work(struct work_struct *work) int ret; nvme_stop_ctrl(&ctrl->ctrl); + /* will block will waiting for io to terminate */ nvme_fc_delete_association(ctrl); - ret = nvme_fc_create_association(ctrl); + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { + dev_err(ctrl->ctrl.device, + "NVME-FC{%d}: error_recovery: Couldn't change state " + "to RECONNECTING\n", ctrl->cnum); + return; + } + + if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE) + ret = nvme_fc_create_association(ctrl); + else + ret = -ENOTCONN; + if (ret) nvme_fc_reconnect_or_delete(ctrl, ret); else dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: controller reset complete\n", ctrl->cnum); + "NVME-FC{%d}: controller reset complete\n", + ctrl->cnum); } static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { @@ -2695,8 +3005,9 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { .reg_write32 = nvmf_reg_write32, .free_ctrl = nvme_fc_nvme_ctrl_freed, .submit_async_event = nvme_fc_submit_async_event, - .delete_ctrl = nvme_fc_del_nvme_ctrl, + .delete_ctrl = nvme_fc_delete_ctrl, .get_address = nvmf_get_address, + .reinit_request = nvme_fc_reinit_request, }; static void @@ -2728,6 +3039,33 @@ static const struct blk_mq_ops nvme_fc_admin_mq_ops = { }; +/* + * Fails a controller request if it matches an existing controller + * (association) with the same tuple: + * <Host NQN, Host ID, local FC port, remote FC port, SUBSYS NQN> + * + * The ports don't need to be compared as they are intrinsically + * already matched by the port pointers supplied. + */ +static bool +nvme_fc_existing_controller(struct nvme_fc_rport *rport, + struct nvmf_ctrl_options *opts) +{ + struct nvme_fc_ctrl *ctrl; + unsigned long flags; + bool found = false; + + spin_lock_irqsave(&rport->lock, flags); + list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) { + found = nvmf_ctlr_matches_baseopts(&ctrl->ctrl, opts); + if (found) + break; + } + spin_unlock_irqrestore(&rport->lock, flags); + + return found; +} + static struct nvme_ctrl * nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, struct nvme_fc_lport *lport, struct nvme_fc_rport *rport) @@ -2742,6 +3080,12 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto out_fail; } + if (!opts->duplicate_connect && + nvme_fc_existing_controller(rport, opts)) { + ret = -EALREADY; + goto out_fail; + } + ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); if (!ctrl) { ret = -ENOMEM; @@ -2760,12 +3104,12 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->rport = rport; ctrl->dev = lport->dev; ctrl->cnum = idx; + ctrl->assoc_active = false; init_waitqueue_head(&ctrl->ioabort_wait); get_device(ctrl->dev); kref_init(&ctrl->ref); - INIT_WORK(&ctrl->delete_work, nvme_fc_delete_ctrl_work); INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work); INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work); spin_lock_init(&ctrl->lock); @@ -2787,7 +3131,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops; - ctrl->admin_tag_set.queue_depth = NVME_FC_AQ_BLKMQ_DEPTH; + ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */ ctrl->admin_tag_set.numa_node = NUMA_NO_NODE; ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) + @@ -2797,6 +3141,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->admin_tag_set.driver_data = ctrl; ctrl->admin_tag_set.nr_hw_queues = 1; ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT; + ctrl->admin_tag_set.flags = BLK_MQ_F_NO_SCHED; ret = blk_mq_alloc_tag_set(&ctrl->admin_tag_set); if (ret) @@ -2878,7 +3223,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, return ERR_PTR(ret); } - kref_get(&ctrl->ctrl.kref); + nvme_get_ctrl(&ctrl->ctrl); dev_info(ctrl->ctrl.device, "NVME-FC{%d}: new ctrl: NQN \"%s\"\n", @@ -3026,7 +3371,50 @@ static struct nvmf_transport_ops nvme_fc_transport = { static int __init nvme_fc_init_module(void) { - return nvmf_register_transport(&nvme_fc_transport); + int ret; + + /* + * NOTE: + * It is expected that in the future the kernel will combine + * the FC-isms that are currently under scsi and now being + * added to by NVME into a new standalone FC class. The SCSI + * and NVME protocols and their devices would be under this + * new FC class. + * + * As we need something to post FC-specific udev events to, + * specifically for nvme probe events, start by creating the + * new device class. When the new standalone FC class is + * put in place, this code will move to a more generic + * location for the class. + */ + fc_class = class_create(THIS_MODULE, "fc"); + if (IS_ERR(fc_class)) { + pr_err("couldn't register class fc\n"); + return PTR_ERR(fc_class); + } + + /* + * Create a device for the FC-centric udev events + */ + fc_udev_device = device_create(fc_class, NULL, MKDEV(0, 0), NULL, + "fc_udev_device"); + if (IS_ERR(fc_udev_device)) { + pr_err("couldn't create fc_udev device!\n"); + ret = PTR_ERR(fc_udev_device); + goto out_destroy_class; + } + + ret = nvmf_register_transport(&nvme_fc_transport); + if (ret) + goto out_destroy_device; + + return 0; + +out_destroy_device: + device_destroy(fc_class, MKDEV(0, 0)); +out_destroy_class: + class_destroy(fc_class); + return ret; } static void __exit nvme_fc_exit_module(void) @@ -3039,6 +3427,9 @@ static void __exit nvme_fc_exit_module(void) ida_destroy(&nvme_fc_local_port_cnt); ida_destroy(&nvme_fc_ctrl_cnt); + + device_destroy(fc_class, MKDEV(0, 0)); + class_destroy(fc_class); } module_init(nvme_fc_init_module); |