diff options
Diffstat (limited to 'drivers/nvme')
| -rw-r--r-- | drivers/nvme/host/core.c | 105 | ||||
| -rw-r--r-- | drivers/nvme/host/ioctl.c | 21 | ||||
| -rw-r--r-- | drivers/nvme/host/multipath.c | 10 | ||||
| -rw-r--r-- | drivers/nvme/host/nvme.h | 3 | ||||
| -rw-r--r-- | drivers/nvme/host/pci.c | 6 | ||||
| -rw-r--r-- | drivers/nvme/target/nvmet.h | 2 |
6 files changed, 79 insertions, 68 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 92697f98c601..7493e5aa984c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -386,7 +386,7 @@ static void nvme_log_err_passthru(struct request *req) nr->cmd->common.cdw12, nr->cmd->common.cdw13, nr->cmd->common.cdw14, - nr->cmd->common.cdw14); + nr->cmd->common.cdw15); } enum nvme_disposition { @@ -2015,21 +2015,41 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl, } -static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns, - struct nvme_id_ns *id, struct queue_limits *lim, - u32 bs, u32 atomic_bs) +static u32 nvme_configure_atomic_write(struct nvme_ns *ns, + struct nvme_id_ns *id, struct queue_limits *lim, u32 bs) { - unsigned int boundary = 0; + u32 atomic_bs, boundary = 0; - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) { - if (le16_to_cpu(id->nabspf)) + /* + * We do not support an offset for the atomic boundaries. + */ + if (id->nabo) + return bs; + + if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) { + /* + * Use the per-namespace atomic write unit when available. + */ + atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; + if (id->nabspf) boundary = (le16_to_cpu(id->nabspf) + 1) * bs; + } else { + /* + * Use the controller wide atomic write unit. This sucks + * because the limit is defined in terms of logical blocks while + * namespaces can have different formats, and because there is + * no clear language in the specification prohibiting different + * values for different controllers in the subsystem. + */ + atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; } + lim->atomic_write_hw_max = atomic_bs; lim->atomic_write_hw_boundary = boundary; lim->atomic_write_hw_unit_min = bs; lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs); lim->features |= BLK_FEAT_ATOMIC_WRITES; + return atomic_bs; } static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl) @@ -2067,34 +2087,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, valid = false; } - atomic_bs = phys_bs = bs; - if (id->nabo == 0) { - /* - * Bit 1 indicates whether NAWUPF is defined for this namespace - * and whether it should be used instead of AWUPF. If NAWUPF == - * 0 then AWUPF must be used instead. - */ - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) - atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; - else - atomic_bs = (1 + ns->ctrl->awupf) * bs; - - /* - * Set subsystem atomic bs. - */ - if (ns->ctrl->subsys->atomic_bs) { - if (atomic_bs != ns->ctrl->subsys->atomic_bs) { - dev_err_ratelimited(ns->ctrl->device, - "%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n", - ns->disk ? ns->disk->disk_name : "?", - ns->ctrl->subsys->atomic_bs, - atomic_bs); - } - } else - ns->ctrl->subsys->atomic_bs = atomic_bs; - - nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs); - } + phys_bs = bs; + atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs); if (id->nsfeat & NVME_NS_FEAT_IO_OPT) { /* NPWG = Namespace Preferred Write Granularity */ @@ -2382,16 +2376,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (!nvme_update_disk_info(ns, id, &lim)) capacity = 0; - /* - * Validate the max atomic write size fits within the subsystem's - * atomic write capabilities. - */ - if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) { - blk_mq_unfreeze_queue(ns->disk->queue, memflags); - ret = -ENXIO; - goto out; - } - nvme_config_discard(ns, &lim); if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && ns->head->ids.csi == NVME_CSI_ZNS) @@ -3215,6 +3199,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) memcpy(subsys->model, id->mn, sizeof(subsys->model)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; + subsys->awupf = le16_to_cpu(id->awupf); /* Versions prior to 1.4 don't necessarily report a valid type */ if (id->cntrltype == NVME_CTRL_DISC || @@ -3552,6 +3537,15 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret) goto out_free; } + + if (le16_to_cpu(id->awupf) != ctrl->subsys->awupf) { + dev_err_ratelimited(ctrl->device, + "inconsistent AWUPF, controller not added (%u/%u).\n", + le16_to_cpu(id->awupf), ctrl->subsys->awupf); + ret = -EINVAL; + goto out_free; + } + memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); @@ -3647,7 +3641,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) dev_pm_qos_expose_latency_tolerance(ctrl->device); else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - ctrl->awupf = le16_to_cpu(id->awupf); out_free: kfree(id); return ret; @@ -4036,6 +4029,10 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) list_add_tail_rcu(&ns->siblings, &head->list); ns->head = head; mutex_unlock(&ctrl->subsys->lock); + +#ifdef CONFIG_NVME_MULTIPATH + cancel_delayed_work(&head->remove_work); +#endif return 0; out_put_ns_head: @@ -4089,6 +4086,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) struct nvme_ns *ns; struct gendisk *disk; int node = ctrl->numa_node; + bool last_path = false; ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); if (!ns) @@ -4181,9 +4179,22 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) out_unlink_ns: mutex_lock(&ctrl->subsys->lock); list_del_rcu(&ns->siblings); - if (list_empty(&ns->head->list)) + if (list_empty(&ns->head->list)) { list_del_init(&ns->head->entry); + /* + * If multipath is not configured, we still create a namespace + * head (nshead), but head->disk is not initialized in that + * case. As a result, only a single reference to nshead is held + * (via kref_init()) when it is created. Therefore, ensure that + * we do not release the reference to nshead twice if head->disk + * is not present. + */ + if (ns->head->disk) + last_path = true; + } mutex_unlock(&ctrl->subsys->lock); + if (last_path) + nvme_put_ns_head(ns->head); nvme_put_ns_head(ns->head); out_cleanup_disk: put_disk(disk); diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 0b50da2f1175..6b3ac8ae3f34 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -429,21 +429,14 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, pdu->result = le64_to_cpu(nvme_req(req)->result.u64); /* - * For iopoll, complete it directly. Note that using the uring_cmd - * helper for this is safe only because we check blk_rq_is_poll(). - * As that returns false if we're NOT on a polled queue, then it's - * safe to use the polled completion helper. - * - * Otherwise, move the completion to task work. + * IOPOLL could potentially complete this request directly, but + * if multiple rings are polling on the same queue, then it's possible + * for one ring to find completions for another ring. Punting the + * completion via task_work will always direct it to the right + * location, rather than potentially complete requests for ringA + * under iopoll invocations from ringB. */ - if (blk_rq_is_poll(req)) { - if (pdu->bio) - blk_rq_unmap_user(pdu->bio); - io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status); - } else { - io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); - } - + io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); return RQ_END_IO_FREE; } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index e040e467f9fa..3da980dc60d9 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -690,8 +690,8 @@ static void nvme_remove_head(struct nvme_ns_head *head) nvme_cdev_del(&head->cdev, &head->cdev_device); synchronize_srcu(&head->srcu); del_gendisk(head->disk); - nvme_put_ns_head(head); } + nvme_put_ns_head(head); } static void nvme_remove_head_work(struct work_struct *work) @@ -1200,7 +1200,8 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head) */ srcu_idx = srcu_read_lock(&head->srcu); - list_for_each_entry_rcu(ns, &head->list, siblings) { + list_for_each_entry_srcu(ns, &head->list, siblings, + srcu_read_lock_held(&head->srcu)) { /* * Ensure that ns path disk node is already added otherwise we * may get invalid kobj name for target @@ -1291,6 +1292,9 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) { bool remove = false; + if (!head->disk) + return; + mutex_lock(&head->subsys->lock); /* * We are called when all paths have been removed, and at that point @@ -1311,7 +1315,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) */ if (!try_module_get(THIS_MODULE)) goto out; - queue_delayed_work(nvme_wq, &head->remove_work, + mod_delayed_work(nvme_wq, &head->remove_work, head->delayed_removal_secs * HZ); } else { list_del_init(&head->entry); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index a468cdc5b5cb..7df2ea21851f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -410,7 +410,6 @@ struct nvme_ctrl { enum nvme_ctrl_type cntrltype; enum nvme_dctype dctype; - u16 awupf; /* 0's based value. */ }; static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) @@ -443,11 +442,11 @@ struct nvme_subsystem { u8 cmic; enum nvme_subsys_type subtype; u16 vendor_id; + u16 awupf; /* 0's based value. */ struct ida ns_ida; #ifdef CONFIG_NVME_MULTIPATH enum nvme_iopolicy iopolicy; #endif - u32 atomic_bs; }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 8ff12e415cb5..320aaa41ec39 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2101,8 +2101,6 @@ static void nvme_map_cmb(struct nvme_dev *dev) if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) == (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) pci_p2pmem_publish(pdev, true); - - nvme_update_attrs(dev); } static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits) @@ -3010,6 +3008,8 @@ static void nvme_reset_work(struct work_struct *work) if (result < 0) goto out; + nvme_update_attrs(dev); + result = nvme_setup_io_queues(dev); if (result) goto out; @@ -3343,6 +3343,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (result < 0) goto out_disable; + nvme_update_attrs(dev); + result = nvme_setup_io_queues(dev); if (result) goto out_disable; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index df69a9dee71c..51df72f5e89b 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -867,6 +867,8 @@ static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio) { if (bio != &req->b.inline_bio) bio_put(bio); + else + bio_uninit(bio); } #ifdef CONFIG_NVME_TARGET_TCP_TLS |