diff options
Diffstat (limited to 'drivers/nvme/host')
| -rw-r--r-- | drivers/nvme/host/core.c | 8 | ||||
| -rw-r--r-- | drivers/nvme/host/multipath.c | 3 | ||||
| -rw-r--r-- | drivers/nvme/host/nvme.h | 1 | ||||
| -rw-r--r-- | drivers/nvme/host/pci.c | 147 | ||||
| -rw-r--r-- | drivers/nvme/host/rdma.c | 64 | ||||
| -rw-r--r-- | drivers/nvme/host/tcp.c | 19 |
6 files changed, 119 insertions, 123 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 150e49723c15..6a9dd68c0f4f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1253,6 +1253,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, * effects say only one namespace is affected. */ if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { + mutex_lock(&ctrl->scan_lock); nvme_start_freeze(ctrl); nvme_wait_freeze(ctrl); } @@ -1281,8 +1282,10 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) */ if (effects & NVME_CMD_EFFECTS_LBCC) nvme_update_formats(ctrl); - if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) + if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { nvme_unfreeze(ctrl); + mutex_unlock(&ctrl->scan_lock); + } if (effects & NVME_CMD_EFFECTS_CCC) nvme_init_identify(ctrl); if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) @@ -3401,6 +3404,7 @@ static void nvme_scan_work(struct work_struct *work) if (nvme_identify_ctrl(ctrl, &id)) return; + mutex_lock(&ctrl->scan_lock); nn = le32_to_cpu(id->nn); if (ctrl->vs >= NVME_VS(1, 1, 0) && !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) { @@ -3409,6 +3413,7 @@ static void nvme_scan_work(struct work_struct *work) } nvme_scan_ns_sequential(ctrl, nn); out_free_id: + mutex_unlock(&ctrl->scan_lock); kfree(id); down_write(&ctrl->namespaces_rwsem); list_sort(NULL, &ctrl->namespaces, ns_cmp); @@ -3652,6 +3657,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->state = NVME_CTRL_NEW; spin_lock_init(&ctrl->lock); + mutex_init(&ctrl->scan_lock); INIT_LIST_HEAD(&ctrl->namespaces); init_rwsem(&ctrl->namespaces_rwsem); ctrl->dev = dev; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index df4b3a6db51b..b9fff3b8ed1b 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -545,8 +545,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0); ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) + ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc); - if (!(ctrl->anacap & (1 << 6))) - ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32); + ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32); if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) { dev_err(ctrl->device, diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index ab961bdeea89..c4a1bb41abf0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -154,6 +154,7 @@ struct nvme_ctrl { enum nvme_ctrl_state state; bool identified; spinlock_t lock; + struct mutex scan_lock; const struct nvme_ctrl_ops *ops; struct request_queue *admin_q; struct request_queue *connect_q; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9bc585415d9b..e905861186e3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2041,53 +2041,52 @@ static int nvme_setup_host_mem(struct nvme_dev *dev) return ret; } -/* irq_queues covers admin queue */ -static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues) +/* + * nirqs is the number of interrupts available for write and read + * queues. The core already reserved an interrupt for the admin queue. + */ +static void nvme_calc_irq_sets(struct irq_affinity *affd, unsigned int nrirqs) { - unsigned int this_w_queues = write_queues; - - WARN_ON(!irq_queues); - - /* - * Setup read/write queue split, assign admin queue one independent - * irq vector if irq_queues is > 1. - */ - if (irq_queues <= 2) { - dev->io_queues[HCTX_TYPE_DEFAULT] = 1; - dev->io_queues[HCTX_TYPE_READ] = 0; - return; - } - - /* - * If 'write_queues' is set, ensure it leaves room for at least - * one read queue and one admin queue - */ - if (this_w_queues >= irq_queues) - this_w_queues = irq_queues - 2; + struct nvme_dev *dev = affd->priv; + unsigned int nr_read_queues; /* - * If 'write_queues' is set to zero, reads and writes will share - * a queue set. + * If there is no interupt available for queues, ensure that + * the default queue is set to 1. The affinity set size is + * also set to one, but the irq core ignores it for this case. + * + * If only one interrupt is available or 'write_queue' == 0, combine + * write and read queues. + * + * If 'write_queues' > 0, ensure it leaves room for at least one read + * queue. */ - if (!this_w_queues) { - dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues - 1; - dev->io_queues[HCTX_TYPE_READ] = 0; + if (!nrirqs) { + nrirqs = 1; + nr_read_queues = 0; + } else if (nrirqs == 1 || !write_queues) { + nr_read_queues = 0; + } else if (write_queues >= nrirqs) { + nr_read_queues = 1; } else { - dev->io_queues[HCTX_TYPE_DEFAULT] = this_w_queues; - dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues - 1; + nr_read_queues = nrirqs - write_queues; } + + dev->io_queues[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues; + affd->set_size[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues; + dev->io_queues[HCTX_TYPE_READ] = nr_read_queues; + affd->set_size[HCTX_TYPE_READ] = nr_read_queues; + affd->nr_sets = nr_read_queues ? 2 : 1; } static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) { struct pci_dev *pdev = to_pci_dev(dev->dev); - int irq_sets[2]; struct irq_affinity affd = { - .pre_vectors = 1, - .nr_sets = ARRAY_SIZE(irq_sets), - .sets = irq_sets, + .pre_vectors = 1, + .calc_sets = nvme_calc_irq_sets, + .priv = dev, }; - int result = 0; unsigned int irq_queues, this_p_queues; /* @@ -2103,51 +2102,12 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) } dev->io_queues[HCTX_TYPE_POLL] = this_p_queues; - /* - * For irq sets, we have to ask for minvec == maxvec. This passes - * any reduction back to us, so we can adjust our queue counts and - * IRQ vector needs. - */ - do { - nvme_calc_io_queues(dev, irq_queues); - irq_sets[0] = dev->io_queues[HCTX_TYPE_DEFAULT]; - irq_sets[1] = dev->io_queues[HCTX_TYPE_READ]; - if (!irq_sets[1]) - affd.nr_sets = 1; - - /* - * If we got a failure and we're down to asking for just - * 1 + 1 queues, just ask for a single vector. We'll share - * that between the single IO queue and the admin queue. - * Otherwise, we assign one independent vector to admin queue. - */ - if (irq_queues > 1) - irq_queues = irq_sets[0] + irq_sets[1] + 1; + /* Initialize for the single interrupt case */ + dev->io_queues[HCTX_TYPE_DEFAULT] = 1; + dev->io_queues[HCTX_TYPE_READ] = 0; - result = pci_alloc_irq_vectors_affinity(pdev, irq_queues, - irq_queues, - PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd); - - /* - * Need to reduce our vec counts. If we get ENOSPC, the - * platform should support mulitple vecs, we just need - * to decrease our ask. If we get EINVAL, the platform - * likely does not. Back down to ask for just one vector. - */ - if (result == -ENOSPC) { - irq_queues--; - if (!irq_queues) - return result; - continue; - } else if (result == -EINVAL) { - irq_queues = 1; - continue; - } else if (result <= 0) - return -EIO; - break; - } while (1); - - return result; + return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues, + PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd); } static void nvme_disable_io_queues(struct nvme_dev *dev) @@ -2557,27 +2517,18 @@ static void nvme_reset_work(struct work_struct *work) if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) nvme_dev_disable(dev, false); - /* - * Introduce CONNECTING state from nvme-fc/rdma transports to mark the - * initializing procedure here. - */ - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { - dev_warn(dev->ctrl.device, - "failed to mark controller CONNECTING\n"); - goto out; - } - + mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); if (result) - goto out; + goto out_unlock; result = nvme_pci_configure_admin_queue(dev); if (result) - goto out; + goto out_unlock; result = nvme_alloc_admin_tags(dev); if (result) - goto out; + goto out_unlock; /* * Limit the max command size to prevent iod->sg allocations going @@ -2585,6 +2536,17 @@ static void nvme_reset_work(struct work_struct *work) */ dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1; dev->ctrl.max_segments = NVME_MAX_SEGS; + mutex_unlock(&dev->shutdown_lock); + + /* + * Introduce CONNECTING state from nvme-fc/rdma transports to mark the + * initializing procedure here. + */ + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { + dev_warn(dev->ctrl.device, + "failed to mark controller CONNECTING\n"); + goto out; + } result = nvme_init_identify(&dev->ctrl); if (result) @@ -2649,6 +2611,8 @@ static void nvme_reset_work(struct work_struct *work) nvme_start_ctrl(&dev->ctrl); return; + out_unlock: + mutex_unlock(&dev->shutdown_lock); out: nvme_remove_dead_ctrl(dev, result); } @@ -3020,6 +2984,7 @@ static struct pci_driver nvme_driver = { static int __init nvme_init(void) { + BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2); return pci_register_driver(&nvme_driver); } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 0a2fd2949ad7..52abc3a6de12 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -119,6 +119,7 @@ struct nvme_rdma_ctrl { struct nvme_ctrl ctrl; bool use_inline_data; + u32 io_queues[HCTX_MAX_TYPES]; }; static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl) @@ -165,8 +166,8 @@ static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue) static bool nvme_rdma_poll_queue(struct nvme_rdma_queue *queue) { return nvme_rdma_queue_idx(queue) > - queue->ctrl->ctrl.opts->nr_io_queues + - queue->ctrl->ctrl.opts->nr_write_queues; + queue->ctrl->io_queues[HCTX_TYPE_DEFAULT] + + queue->ctrl->io_queues[HCTX_TYPE_READ]; } static inline size_t nvme_rdma_inline_data_size(struct nvme_rdma_queue *queue) @@ -661,8 +662,21 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) nr_io_queues = min_t(unsigned int, nr_io_queues, ibdev->num_comp_vectors); - nr_io_queues += min(opts->nr_write_queues, num_online_cpus()); - nr_io_queues += min(opts->nr_poll_queues, num_online_cpus()); + if (opts->nr_write_queues) { + ctrl->io_queues[HCTX_TYPE_DEFAULT] = + min(opts->nr_write_queues, nr_io_queues); + nr_io_queues += ctrl->io_queues[HCTX_TYPE_DEFAULT]; + } else { + ctrl->io_queues[HCTX_TYPE_DEFAULT] = nr_io_queues; + } + + ctrl->io_queues[HCTX_TYPE_READ] = nr_io_queues; + + if (opts->nr_poll_queues) { + ctrl->io_queues[HCTX_TYPE_POLL] = + min(opts->nr_poll_queues, num_online_cpus()); + nr_io_queues += ctrl->io_queues[HCTX_TYPE_POLL]; + } ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); if (ret) @@ -1689,18 +1703,28 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq, bool reserved) { 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; - dev_warn(req->queue->ctrl->ctrl.device, - "I/O %d QID %d timeout, reset controller\n", - rq->tag, nvme_rdma_queue_idx(req->queue)); + dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n", + rq->tag, nvme_rdma_queue_idx(queue)); - /* queue error recovery */ - nvme_rdma_error_recovery(req->queue->ctrl); + 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. + */ + flush_work(&ctrl->err_work); + nvme_rdma_teardown_io_queues(ctrl, false); + nvme_rdma_teardown_admin_queue(ctrl, false); + return BLK_EH_DONE; + } - /* fail with DNR on cmd timeout */ - nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR; + dev_warn(ctrl->ctrl.device, "starting error recovery\n"); + nvme_rdma_error_recovery(ctrl); - return BLK_EH_DONE; + return BLK_EH_RESET_TIMER; } static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, @@ -1779,17 +1803,15 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) struct nvme_rdma_ctrl *ctrl = set->driver_data; set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = ctrl->ctrl.opts->nr_io_queues; + set->map[HCTX_TYPE_DEFAULT].nr_queues = + ctrl->io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_READ].nr_queues = ctrl->io_queues[HCTX_TYPE_READ]; if (ctrl->ctrl.opts->nr_write_queues) { /* separate read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->ctrl.opts->nr_write_queues; set->map[HCTX_TYPE_READ].queue_offset = - ctrl->ctrl.opts->nr_write_queues; + ctrl->io_queues[HCTX_TYPE_DEFAULT]; } else { /* mixed read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->ctrl.opts->nr_io_queues; set->map[HCTX_TYPE_READ].queue_offset = 0; } blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT], @@ -1799,12 +1821,12 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) if (ctrl->ctrl.opts->nr_poll_queues) { set->map[HCTX_TYPE_POLL].nr_queues = - ctrl->ctrl.opts->nr_poll_queues; + ctrl->io_queues[HCTX_TYPE_POLL]; set->map[HCTX_TYPE_POLL].queue_offset = - ctrl->ctrl.opts->nr_io_queues; + ctrl->io_queues[HCTX_TYPE_DEFAULT]; if (ctrl->ctrl.opts->nr_write_queues) set->map[HCTX_TYPE_POLL].queue_offset += - ctrl->ctrl.opts->nr_write_queues; + ctrl->io_queues[HCTX_TYPE_READ]; blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); } return 0; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 265a0543b381..5f0a00425242 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1948,20 +1948,23 @@ nvme_tcp_timeout(struct request *rq, bool reserved) struct nvme_tcp_ctrl *ctrl = req->queue->ctrl; struct nvme_tcp_cmd_pdu *pdu = req->pdu; - dev_dbg(ctrl->ctrl.device, + dev_warn(ctrl->ctrl.device, "queue %d: timeout request %#x type %d\n", - nvme_tcp_queue_id(req->queue), rq->tag, - pdu->hdr.type); + nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type); if (ctrl->ctrl.state != NVME_CTRL_LIVE) { - union nvme_result res = {}; - - nvme_req(rq)->flags |= NVME_REQ_CANCELLED; - nvme_end_request(rq, cpu_to_le16(NVME_SC_ABORT_REQ), res); + /* + * 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. + */ + flush_work(&ctrl->err_work); + nvme_tcp_teardown_io_queues(&ctrl->ctrl, false); + nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false); return BLK_EH_DONE; } - /* queue error recovery */ + dev_warn(ctrl->ctrl.device, "starting error recovery\n"); nvme_tcp_error_recovery(&ctrl->ctrl); return BLK_EH_RESET_TIMER; |