diff options
-rw-r--r-- | drivers/nvme/host/Kconfig | 9 | ||||
-rw-r--r-- | drivers/nvme/host/Makefile | 1 | ||||
-rw-r--r-- | drivers/nvme/host/core.c | 147 | ||||
-rw-r--r-- | drivers/nvme/host/multipath.c | 255 | ||||
-rw-r--r-- | drivers/nvme/host/nvme.h | 57 |
5 files changed, 455 insertions, 14 deletions
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 46d6cb1e03bd..b979cf3bce65 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -13,6 +13,15 @@ config BLK_DEV_NVME To compile this driver as a module, choose M here: the module will be called nvme. +config NVME_MULTIPATH + bool "NVMe multipath support" + depends on NVME_CORE + ---help--- + This option enables support for multipath access to NVMe + subsystems. If this option is enabled only a single + /dev/nvmeXnY device will show up for each NVMe namespaces, + even if it is accessible through multiple controllers. + config NVME_FABRICS tristate diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index cc0aacb4c8b4..b856f2f549cd 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_NVME_RDMA) += nvme-rdma.o obj-$(CONFIG_NVME_FC) += nvme-fc.o nvme-core-y := core.o +nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o nvme-core-$(CONFIG_NVM) += lightnvm.o nvme-y += pci.o diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 13676f6cd4f6..59f80a613fd8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -185,17 +185,22 @@ static inline bool nvme_req_needs_retry(struct request *req) return false; if (nvme_req(req)->retries >= nvme_max_retries) return false; - if (blk_queue_dying(req->q)) - return false; return true; } void nvme_complete_rq(struct request *req) { if (unlikely(nvme_req(req)->status && nvme_req_needs_retry(req))) { - nvme_req(req)->retries++; - blk_mq_requeue_request(req, true); - return; + if (nvme_req_needs_failover(req)) { + nvme_failover_req(req); + return; + } + + if (!blk_queue_dying(req->q)) { + nvme_req(req)->retries++; + blk_mq_requeue_request(req, true); + return; + } } blk_mq_end_request(req, nvme_error_status(req)); @@ -286,7 +291,8 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, ctrl->state = new_state; spin_unlock_irqrestore(&ctrl->lock, flags); - + if (changed && ctrl->state == NVME_CTRL_LIVE) + nvme_kick_requeue_lists(ctrl); return changed; } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); @@ -296,6 +302,7 @@ static void nvme_free_ns_head(struct kref *ref) struct nvme_ns_head *head = container_of(ref, struct nvme_ns_head, ref); + nvme_mpath_remove_disk(head); ida_simple_remove(&head->subsys->ns_ida, head->instance); list_del_init(&head->entry); cleanup_srcu_struct(&head->srcu); @@ -1138,11 +1145,33 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return status; } -static int nvme_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) +/* + * Issue ioctl requests on the first available path. Note that unlike normal + * block layer requests we will not retry failed request on another controller. + */ +static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk, + struct nvme_ns_head **head, int *srcu_idx) { - struct nvme_ns *ns = bdev->bd_disk->private_data; +#ifdef CONFIG_NVME_MULTIPATH + if (disk->fops == &nvme_ns_head_ops) { + *head = disk->private_data; + *srcu_idx = srcu_read_lock(&(*head)->srcu); + return nvme_find_path(*head); + } +#endif + *head = NULL; + *srcu_idx = -1; + return disk->private_data; +} + +static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx) +{ + if (head) + srcu_read_unlock(&head->srcu, idx); +} +static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned cmd, unsigned long arg) +{ switch (cmd) { case NVME_IOCTL_ID: force_successful_syscall_return(); @@ -1165,10 +1194,31 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, } } +static int nvme_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + struct nvme_ns_head *head = NULL; + struct nvme_ns *ns; + int srcu_idx, ret; + + ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx); + if (unlikely(!ns)) + ret = -EWOULDBLOCK; + else + ret = nvme_ns_ioctl(ns, cmd, arg); + nvme_put_ns_from_disk(head, srcu_idx); + return ret; +} + static int nvme_open(struct block_device *bdev, fmode_t mode) { struct nvme_ns *ns = bdev->bd_disk->private_data; +#ifdef CONFIG_NVME_MULTIPATH + /* should never be called due to GENHD_FL_HIDDEN */ + if (WARN_ON_ONCE(ns->head->disk)) + return -ENXIO; +#endif if (!kref_get_unless_zero(&ns->kref)) return -ENXIO; return 0; @@ -1329,6 +1379,10 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->noiob) nvme_set_chunk_size(ns); nvme_update_disk_info(disk, ns, id); +#ifdef CONFIG_NVME_MULTIPATH + if (ns->head->disk) + nvme_update_disk_info(ns->head->disk, ns, id); +#endif } static int nvme_revalidate_disk(struct gendisk *disk) @@ -1388,8 +1442,10 @@ static char nvme_pr_type(enum pr_type type) static int nvme_pr_command(struct block_device *bdev, u32 cdw10, u64 key, u64 sa_key, u8 op) { - struct nvme_ns *ns = bdev->bd_disk->private_data; + struct nvme_ns_head *head = NULL; + struct nvme_ns *ns; struct nvme_command c; + int srcu_idx, ret; u8 data[16] = { 0, }; put_unaligned_le64(key, &data[0]); @@ -1397,10 +1453,16 @@ static int nvme_pr_command(struct block_device *bdev, u32 cdw10, memset(&c, 0, sizeof(c)); c.common.opcode = op; - c.common.nsid = cpu_to_le32(ns->head->ns_id); + c.common.nsid = cpu_to_le32(head->ns_id); c.common.cdw10[0] = cpu_to_le32(cdw10); - return nvme_submit_sync_cmd(ns->queue, &c, data, 16); + ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx); + if (unlikely(!ns)) + ret = -EWOULDBLOCK; + else + ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16); + nvme_put_ns_from_disk(head, srcu_idx); + return ret; } static int nvme_pr_register(struct block_device *bdev, u64 old, @@ -1490,6 +1552,32 @@ static const struct block_device_operations nvme_fops = { .pr_ops = &nvme_pr_ops, }; +#ifdef CONFIG_NVME_MULTIPATH +static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode) +{ + struct nvme_ns_head *head = bdev->bd_disk->private_data; + + if (!kref_get_unless_zero(&head->ref)) + return -ENXIO; + return 0; +} + +static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode) +{ + nvme_put_ns_head(disk->private_data); +} + +const struct block_device_operations nvme_ns_head_ops = { + .owner = THIS_MODULE, + .open = nvme_ns_head_open, + .release = nvme_ns_head_release, + .ioctl = nvme_ioctl, + .compat_ioctl = nvme_ioctl, + .getgeo = nvme_getgeo, + .pr_ops = &nvme_pr_ops, +}; +#endif /* CONFIG_NVME_MULTIPATH */ + static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled) { unsigned long timeout = @@ -2592,6 +2680,10 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, goto out_cleanup_srcu; } + ret = nvme_mpath_alloc_disk(ctrl, head); + if (ret) + goto out_cleanup_srcu; + list_add_tail(&head->entry, &ctrl->subsys->nsheads); return head; out_cleanup_srcu: @@ -2704,7 +2796,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) struct gendisk *disk; struct nvme_id_ns *id; char disk_name[DISK_NAME_LEN]; - int node = dev_to_node(ctrl->dev); + int node = dev_to_node(ctrl->dev), flags = GENHD_FL_EXT_DEVT; bool new = true; ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); @@ -2735,7 +2827,30 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (nvme_init_ns_head(ns, nsid, id, &new)) goto out_free_id; +#ifdef CONFIG_NVME_MULTIPATH + /* + * If multipathing is enabled we need to always use the subsystem + * instance number for numbering our devices to avoid conflicts + * between subsystems that have multiple controllers and thus use + * the multipath-aware subsystem node and those that have a single + * controller and use the controller node directly. + */ + if (ns->head->disk) { + sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance, + ctrl->cntlid, ns->head->instance); + flags = GENHD_FL_HIDDEN; + } else { + sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance, + ns->head->instance); + } +#else + /* + * But without the multipath code enabled, multiple controller per + * subsystems are visible as devices and thus we cannot use the + * subsystem instance. + */ sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance); +#endif if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) { if (nvme_nvm_register(ns, disk_name, node)) { @@ -2751,7 +2866,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) disk->fops = &nvme_fops; disk->private_data = ns; disk->queue = ns->queue; - disk->flags = GENHD_FL_EXT_DEVT; + disk->flags = flags; memcpy(disk->disk_name, disk_name, DISK_NAME_LEN); ns->disk = disk; @@ -2773,6 +2888,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (ns->ndev && nvme_nvm_register_sysfs(ns)) pr_warn("%s: failed to register lightnvm sysfs group for identification\n", ns->disk->disk_name); + + if (new) + nvme_mpath_add_disk(ns->head); return; out_unlink_ns: mutex_lock(&ctrl->subsys->lock); @@ -2805,6 +2923,7 @@ static void nvme_ns_remove(struct nvme_ns *ns) } mutex_lock(&ns->ctrl->subsys->lock); + nvme_mpath_clear_current_path(ns); if (head) list_del_rcu(&ns->siblings); mutex_unlock(&ns->ctrl->subsys->lock); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c new file mode 100644 index 000000000000..062754ebebfd --- /dev/null +++ b/drivers/nvme/host/multipath.c @@ -0,0 +1,255 @@ +/* + * Copyright (c) 2017 Christoph Hellwig. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/moduleparam.h> +#include "nvme.h" + +static bool multipath = true; +module_param(multipath, bool, 0644); +MODULE_PARM_DESC(multipath, + "turn on native support for multiple controllers per subsystem"); + +void nvme_failover_req(struct request *req) +{ + struct nvme_ns *ns = req->q->queuedata; + unsigned long flags; + + spin_lock_irqsave(&ns->head->requeue_lock, flags); + blk_steal_bios(&ns->head->requeue_list, req); + spin_unlock_irqrestore(&ns->head->requeue_lock, flags); + blk_mq_end_request(req, 0); + + nvme_reset_ctrl(ns->ctrl); + kblockd_schedule_work(&ns->head->requeue_work); +} + +bool nvme_req_needs_failover(struct request *req) +{ + if (!(req->cmd_flags & REQ_NVME_MPATH)) + return false; + + switch (nvme_req(req)->status & 0x7ff) { + /* + * Generic command status: + */ + case NVME_SC_INVALID_OPCODE: + case NVME_SC_INVALID_FIELD: + case NVME_SC_INVALID_NS: + case NVME_SC_LBA_RANGE: + case NVME_SC_CAP_EXCEEDED: + case NVME_SC_RESERVATION_CONFLICT: + return false; + + /* + * I/O command set specific error. Unfortunately these values are + * reused for fabrics commands, but those should never get here. + */ + case NVME_SC_BAD_ATTRIBUTES: + case NVME_SC_INVALID_PI: + case NVME_SC_READ_ONLY: + case NVME_SC_ONCS_NOT_SUPPORTED: + WARN_ON_ONCE(nvme_req(req)->cmd->common.opcode == + nvme_fabrics_command); + return false; + + /* + * Media and Data Integrity Errors: + */ + case NVME_SC_WRITE_FAULT: + case NVME_SC_READ_ERROR: + case NVME_SC_GUARD_CHECK: + case NVME_SC_APPTAG_CHECK: + case NVME_SC_REFTAG_CHECK: + case NVME_SC_COMPARE_FAILED: + case NVME_SC_ACCESS_DENIED: + case NVME_SC_UNWRITTEN_BLOCK: + return false; + } + + /* Everything else could be a path failure, so should be retried */ + return true; +} + +void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) +{ + struct nvme_ns *ns; + + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { + if (ns->head->disk) + kblockd_schedule_work(&ns->head->requeue_work); + } + mutex_unlock(&ctrl->namespaces_mutex); +} + +static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head) +{ + struct nvme_ns *ns; + + list_for_each_entry_rcu(ns, &head->list, siblings) { + if (ns->ctrl->state == NVME_CTRL_LIVE) { + rcu_assign_pointer(head->current_path, ns); + return ns; + } + } + + return NULL; +} + +inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head) +{ + struct nvme_ns *ns = srcu_dereference(head->current_path, &head->srcu); + + if (unlikely(!ns || ns->ctrl->state != NVME_CTRL_LIVE)) + ns = __nvme_find_path(head); + return ns; +} + +static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, + struct bio *bio) +{ + struct nvme_ns_head *head = q->queuedata; + struct device *dev = disk_to_dev(head->disk); + struct nvme_ns *ns; + blk_qc_t ret = BLK_QC_T_NONE; + int srcu_idx; + + srcu_idx = srcu_read_lock(&head->srcu); + ns = nvme_find_path(head); + if (likely(ns)) { + bio->bi_disk = ns->disk; + bio->bi_opf |= REQ_NVME_MPATH; + ret = direct_make_request(bio); + } else if (!list_empty_careful(&head->list)) { + dev_warn_ratelimited(dev, "no path available - requeing I/O\n"); + + spin_lock_irq(&head->requeue_lock); + bio_list_add(&head->requeue_list, bio); + spin_unlock_irq(&head->requeue_lock); + } else { + dev_warn_ratelimited(dev, "no path - failing I/O\n"); + + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); + } + + srcu_read_unlock(&head->srcu, srcu_idx); + return ret; +} + +static bool nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc) +{ + struct nvme_ns_head *head = q->queuedata; + struct nvme_ns *ns; + bool found = false; + int srcu_idx; + + srcu_idx = srcu_read_lock(&head->srcu); + ns = srcu_dereference(head->current_path, &head->srcu); + if (likely(ns && ns->ctrl->state == NVME_CTRL_LIVE)) + found = ns->queue->poll_fn(q, qc); + srcu_read_unlock(&head->srcu, srcu_idx); + return found; +} + +static void nvme_requeue_work(struct work_struct *work) +{ + struct nvme_ns_head *head = + container_of(work, struct nvme_ns_head, requeue_work); + struct bio *bio, *next; + + spin_lock_irq(&head->requeue_lock); + next = bio_list_get(&head->requeue_list); + spin_unlock_irq(&head->requeue_lock); + + while ((bio = next) != NULL) { + next = bio->bi_next; + bio->bi_next = NULL; + + /* + * Reset disk to the mpath node and resubmit to select a new + * path. + */ + bio->bi_disk = head->disk; + generic_make_request(bio); + } +} + +int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) +{ + struct request_queue *q; + bool vwc = false; + + bio_list_init(&head->requeue_list); + spin_lock_init(&head->requeue_lock); + INIT_WORK(&head->requeue_work, nvme_requeue_work); + + /* + * Add a multipath node if the subsystems supports multiple controllers. + * We also do this for private namespaces as the namespace sharing data could + * change after a rescan. + */ + if (!(ctrl->subsys->cmic & (1 << 1)) || !multipath) + return 0; + + q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE); + if (!q) + goto out; + q->queuedata = head; + blk_queue_make_request(q, nvme_ns_head_make_request); + q->poll_fn = nvme_ns_head_poll; + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); + /* set to a default value for 512 until disk is validated */ + blk_queue_logical_block_size(q, 512); + + /* we need to propagate up the VMC settings */ + if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) + vwc = true; + blk_queue_write_cache(q, vwc, vwc); + + head->disk = alloc_disk(0); + if (!head->disk) + goto out_cleanup_queue; + head->disk->fops = &nvme_ns_head_ops; + head->disk->private_data = head; + head->disk->queue = q; + head->disk->flags = GENHD_FL_EXT_DEVT; + sprintf(head->disk->disk_name, "nvme%dn%d", + ctrl->subsys->instance, head->instance); + return 0; + +out_cleanup_queue: + blk_cleanup_queue(q); +out: + return -ENOMEM; +} + +void nvme_mpath_add_disk(struct nvme_ns_head *head) +{ + if (!head->disk) + return; + device_add_disk(&head->subsys->dev, head->disk); +} + +void nvme_mpath_remove_disk(struct nvme_ns_head *head) +{ + if (!head->disk) + return; + del_gendisk(head->disk); + blk_set_queue_dying(head->disk->queue); + /* make sure all pending bios are cleaned up */ + kblockd_schedule_work(&head->requeue_work); + flush_work(&head->requeue_work); + blk_cleanup_queue(head->disk->queue); + put_disk(head->disk); +} diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 6e5004b00975..dd6ced664b45 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -95,6 +95,11 @@ struct nvme_request { u16 status; }; +/* + * Mark a bio as coming in through the mpath node. + */ +#define REQ_NVME_MPATH REQ_DRV + enum { NVME_REQ_CANCELLED = (1 << 0), }; @@ -235,6 +240,13 @@ struct nvme_ns_ids { * only ever has a single entry for private namespaces. */ struct nvme_ns_head { +#ifdef CONFIG_NVME_MULTIPATH + struct gendisk *disk; + struct nvme_ns __rcu *current_path; + struct bio_list requeue_list; + spinlock_t requeue_lock; + struct work_struct requeue_work; +#endif struct list_head list; struct srcu_struct srcu; struct nvme_subsystem *subsys; @@ -384,6 +396,51 @@ int nvme_reset_ctrl(struct nvme_ctrl *ctrl); int nvme_delete_ctrl(struct nvme_ctrl *ctrl); int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl); +extern const struct block_device_operations nvme_ns_head_ops; + +#ifdef CONFIG_NVME_MULTIPATH +void nvme_failover_req(struct request *req); +bool nvme_req_needs_failover(struct request *req); +void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); +int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); +void nvme_mpath_add_disk(struct nvme_ns_head *head); +void nvme_mpath_remove_disk(struct nvme_ns_head *head); + +static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) +{ + struct nvme_ns_head *head = ns->head; + + if (head && ns == srcu_dereference(head->current_path, &head->srcu)) + rcu_assign_pointer(head->current_path, NULL); +} +struct nvme_ns *nvme_find_path(struct nvme_ns_head *head); +#else +static inline void nvme_failover_req(struct request *req) +{ +} +static inline bool nvme_req_needs_failover(struct request *req) +{ + return false; +} +static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) +{ +} +static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, + struct nvme_ns_head *head) +{ + return 0; +} +static inline void nvme_mpath_add_disk(struct nvme_ns_head *head) +{ +} +static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) +{ +} +static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) +{ +} +#endif /* CONFIG_NVME_MULTIPATH */ + #ifdef CONFIG_NVM int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node); void nvme_nvm_unregister(struct nvme_ns *ns); |