EXPORT_SYMBOL_GPL(nvme_set_queue_count);
#define NVME_AEN_SUPPORTED \
- (NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT)
+ (NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | NVME_AEN_CFG_ANA_CHANGE)
static void nvme_enable_aen(struct nvme_ctrl *ctrl)
{
- u32 result;
+ u32 supported = ctrl->oaes & NVME_AEN_SUPPORTED, result;
int status;
- status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
- ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+ status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported, NULL,
+ 0, &result);
if (status)
dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
- ctrl->oaes & NVME_AEN_SUPPORTED);
+ supported);
}
static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
nvme_set_queue_limits(ctrl, ctrl->admin_q);
ctrl->sgls = le32_to_cpu(id->sgls);
ctrl->kas = le16_to_cpu(id->kas);
+ ctrl->max_namespaces = le32_to_cpu(id->mnan);
if (id->rtd3e) {
/* us -> s */
ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
}
+ ret = nvme_mpath_init(ctrl, id);
kfree(id);
+ if (ret < 0)
+ return ret;
+
if (ctrl->apst_enabled && !prev_apst_enabled)
dev_pm_qos_expose_latency_tolerance(ctrl->device);
else if (!ctrl->apst_enabled && prev_apst_enabled)
&dev_attr_nguid.attr,
&dev_attr_eui.attr,
&dev_attr_nsid.attr,
+#ifdef CONFIG_NVME_MULTIPATH
+ &dev_attr_ana_grpid.attr,
+ &dev_attr_ana_state.attr,
+#endif
NULL,
};
if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
return 0;
}
+#ifdef CONFIG_NVME_MULTIPATH
+ if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
+ if (dev_to_disk(dev)->fops != &nvme_fops) /* per-path attr */
+ return 0;
+ if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
+ return 0;
+ }
+#endif
return a->mode;
}
nvme_get_ctrl(ctrl);
- kfree(id);
-
device_add_disk(ctrl->device, ns->disk);
if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
&nvme_ns_id_attr_group))
pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
ns->disk->disk_name);
- nvme_mpath_add_disk(ns->head);
+ nvme_mpath_add_disk(ns, id);
nvme_fault_inject_init(ns);
+ kfree(id);
+
return;
out_unlink_ns:
mutex_lock(&ctrl->subsys->lock);
case NVME_AER_NOTICE_FW_ACT_STARTING:
queue_work(nvme_wq, &ctrl->fw_act_work);
break;
+#ifdef CONFIG_NVME_MULTIPATH
+ case NVME_AER_NOTICE_ANA:
+ if (!ctrl->ana_log_buf)
+ break;
+ queue_work(nvme_wq, &ctrl->ana_work);
+ break;
+#endif
default:
dev_warn(ctrl->device, "async event result %08x\n", result);
}
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);
ida_simple_remove(&nvme_instance_ida, ctrl->instance);
kfree(ctrl->effects);
+ nvme_mpath_uninit(ctrl);
if (subsys) {
mutex_lock(&subsys->lock);
/*
- * Copyright (c) 2017 Christoph Hellwig.
+ * Copyright (c) 2017-2018 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,
MODULE_PARM_DESC(multipath,
"turn on native support for multiple controllers per subsystem");
+inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+ return multipath && (ctrl->subsys->cmic & (1 << 3));
+}
+
/*
* If multipathing is enabled we need to always use the subsystem instance
* number for numbering our devices to avoid conflicts between subsystems that
void nvme_failover_req(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
+ u16 status = nvme_req(req)->status;
unsigned long flags;
spin_lock_irqsave(&ns->head->requeue_lock, flags);
spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
blk_mq_end_request(req, 0);
- nvme_reset_ctrl(ns->ctrl);
+ switch (status & 0x7ff) {
+ case NVME_SC_ANA_TRANSITION:
+ case NVME_SC_ANA_INACCESSIBLE:
+ case NVME_SC_ANA_PERSISTENT_LOSS:
+ /*
+ * If we got back an ANA error we know the controller is alive,
+ * but not ready to serve this namespaces. The spec suggests
+ * we should update our general state here, but due to the fact
+ * that the admin and I/O queues are not serialized that is
+ * fundamentally racy. So instead just clear the current path,
+ * mark the the path as pending and kick of a re-read of the ANA
+ * log page ASAP.
+ */
+ nvme_mpath_clear_current_path(ns);
+ if (ns->ctrl->ana_log_buf) {
+ set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+ queue_work(nvme_wq, &ns->ctrl->ana_work);
+ }
+ break;
+ default:
+ /*
+ * Reset the controller for any non-ANA error as we don't know
+ * what caused the error.
+ */
+ nvme_reset_ctrl(ns->ctrl);
+ break;
+ }
+
kblockd_schedule_work(&ns->head->requeue_work);
}
up_read(&ctrl->namespaces_rwsem);
}
+static const char *nvme_ana_state_names[] = {
+ [0] = "invalid state",
+ [NVME_ANA_OPTIMIZED] = "optimized",
+ [NVME_ANA_NONOPTIMIZED] = "non-optimized",
+ [NVME_ANA_INACCESSIBLE] = "inaccessible",
+ [NVME_ANA_PERSISTENT_LOSS] = "persistent-loss",
+ [NVME_ANA_CHANGE] = "change",
+};
+
static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head)
{
- struct nvme_ns *ns;
+ struct nvme_ns *ns, *fallback = NULL;
list_for_each_entry_rcu(ns, &head->list, siblings) {
- if (ns->ctrl->state == NVME_CTRL_LIVE) {
+ if (ns->ctrl->state != NVME_CTRL_LIVE ||
+ test_bit(NVME_NS_ANA_PENDING, &ns->flags))
+ continue;
+ switch (ns->ana_state) {
+ case NVME_ANA_OPTIMIZED:
rcu_assign_pointer(head->current_path, ns);
return ns;
+ case NVME_ANA_NONOPTIMIZED:
+ fallback = ns;
+ break;
+ default:
+ break;
}
}
- return NULL;
+ if (fallback)
+ rcu_assign_pointer(head->current_path, fallback);
+ return fallback;
+}
+
+static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
+{
+ return ns->ctrl->state == NVME_CTRL_LIVE &&
+ ns->ana_state == NVME_ANA_OPTIMIZED;
}
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))
+ if (unlikely(!ns || !nvme_path_is_optimized(ns)))
ns = __nvme_find_path(head);
return ns;
}
srcu_idx = srcu_read_lock(&head->srcu);
ns = srcu_dereference(head->current_path, &head->srcu);
- if (likely(ns && ns->ctrl->state == NVME_CTRL_LIVE))
+ if (likely(ns && nvme_path_is_optimized(ns)))
found = ns->queue->poll_fn(q, qc);
srcu_read_unlock(&head->srcu, srcu_idx);
return found;
struct request_queue *q;
bool vwc = false;
+ mutex_init(&head->lock);
bio_list_init(&head->requeue_list);
spin_lock_init(&head->requeue_lock);
INIT_WORK(&head->requeue_work, nvme_requeue_work);
return -ENOMEM;
}
-void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static void nvme_mpath_set_live(struct nvme_ns *ns)
{
+ struct nvme_ns_head *head = ns->head;
+
+ lockdep_assert_held(&ns->head->lock);
+
if (!head->disk)
return;
- mutex_lock(&head->subsys->lock);
if (!(head->disk->flags & GENHD_FL_UP)) {
device_add_disk(&head->subsys->dev, head->disk);
if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
&nvme_ns_id_attr_group))
- pr_warn("%s: failed to create sysfs group for identification\n",
- head->disk->disk_name);
+ dev_warn(&head->subsys->dev,
+ "failed to create id group.\n");
+ }
+
+ kblockd_schedule_work(&ns->head->requeue_work);
+}
+
+static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
+ int (*cb)(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *,
+ void *))
+{
+ void *base = ctrl->ana_log_buf;
+ size_t offset = sizeof(struct nvme_ana_rsp_hdr);
+ int error, i;
+
+ lockdep_assert_held(&ctrl->ana_lock);
+
+ for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) {
+ struct nvme_ana_group_desc *desc = base + offset;
+ u32 nr_nsids = le32_to_cpu(desc->nnsids);
+ size_t nsid_buf_size = nr_nsids * sizeof(__le32);
+
+ if (WARN_ON_ONCE(desc->grpid == 0))
+ return -EINVAL;
+ if (WARN_ON_ONCE(le32_to_cpu(desc->grpid) > ctrl->anagrpmax))
+ return -EINVAL;
+ if (WARN_ON_ONCE(desc->state == 0))
+ return -EINVAL;
+ if (WARN_ON_ONCE(desc->state > NVME_ANA_CHANGE))
+ return -EINVAL;
+
+ offset += sizeof(*desc);
+ if (WARN_ON_ONCE(offset > ctrl->ana_log_size - nsid_buf_size))
+ return -EINVAL;
+
+ error = cb(ctrl, desc, data);
+ if (error)
+ return error;
+
+ offset += nsid_buf_size;
+ if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static inline bool nvme_state_is_live(enum nvme_ana_state state)
+{
+ return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
+}
+
+static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
+ struct nvme_ns *ns)
+{
+ enum nvme_ana_state old;
+
+ mutex_lock(&ns->head->lock);
+ old = ns->ana_state;
+ ns->ana_grpid = le32_to_cpu(desc->grpid);
+ ns->ana_state = desc->state;
+ clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
+
+ if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old))
+ nvme_mpath_set_live(ns);
+ mutex_unlock(&ns->head->lock);
+}
+
+static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
+ struct nvme_ana_group_desc *desc, void *data)
+{
+ u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
+ unsigned *nr_change_groups = data;
+ struct nvme_ns *ns;
+
+ dev_info(ctrl->device, "ANA group %d: %s.\n",
+ le32_to_cpu(desc->grpid),
+ nvme_ana_state_names[desc->state]);
+
+ if (desc->state == NVME_ANA_CHANGE)
+ (*nr_change_groups)++;
+
+ if (!nr_nsids)
+ return 0;
+
+ down_write(&ctrl->namespaces_rwsem);
+ list_for_each_entry(ns, &ctrl->namespaces, list) {
+ if (ns->head->ns_id != le32_to_cpu(desc->nsids[n]))
+ continue;
+ nvme_update_ns_ana_state(desc, ns);
+ if (++n == nr_nsids)
+ break;
+ }
+ up_write(&ctrl->namespaces_rwsem);
+ WARN_ON_ONCE(n < nr_nsids);
+ return 0;
+}
+
+static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only)
+{
+ u32 nr_change_groups = 0;
+ int error;
+
+ mutex_lock(&ctrl->ana_lock);
+ error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA,
+ groups_only ? NVME_ANA_LOG_RGO : 0,
+ ctrl->ana_log_buf, ctrl->ana_log_size, 0);
+ if (error) {
+ dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
+ goto out_unlock;
+ }
+
+ error = nvme_parse_ana_log(ctrl, &nr_change_groups,
+ nvme_update_ana_state);
+ if (error)
+ goto out_unlock;
+
+ /*
+ * In theory we should have an ANATT timer per group as they might enter
+ * the change state at different times. But that is a lot of overhead
+ * just to protect against a target that keeps entering new changes
+ * states while never finishing previous ones. But we'll still
+ * eventually time out once all groups are in change state, so this
+ * isn't a big deal.
+ *
+ * We also double the ANATT value to provide some slack for transports
+ * or AEN processing overhead.
+ */
+ if (nr_change_groups)
+ mod_timer(&ctrl->anatt_timer, ctrl->anatt * HZ * 2 + jiffies);
+ else
+ del_timer_sync(&ctrl->anatt_timer);
+out_unlock:
+ mutex_unlock(&ctrl->ana_lock);
+ return error;
+}
+
+static void nvme_ana_work(struct work_struct *work)
+{
+ struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
+
+ nvme_read_ana_log(ctrl, false);
+}
+
+static void nvme_anatt_timeout(struct timer_list *t)
+{
+ struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
+
+ dev_info(ctrl->device, "ANATT timeout, resetting controller.\n");
+ nvme_reset_ctrl(ctrl);
+}
+
+void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+ if (!nvme_ctrl_use_ana(ctrl))
+ return;
+ del_timer_sync(&ctrl->anatt_timer);
+ cancel_work_sync(&ctrl->ana_work);
+}
+
+static ssize_t ana_grpid_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", nvme_get_ns_from_dev(dev)->ana_grpid);
+}
+DEVICE_ATTR_RO(ana_grpid);
+
+static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+
+ return sprintf(buf, "%s\n", nvme_ana_state_names[ns->ana_state]);
+}
+DEVICE_ATTR_RO(ana_state);
+
+static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
+ struct nvme_ana_group_desc *desc, void *data)
+{
+ struct nvme_ns *ns = data;
+
+ if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
+ nvme_update_ns_ana_state(desc, ns);
+ return -ENXIO; /* just break out of the loop */
+ }
+
+ return 0;
+}
+
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+ if (nvme_ctrl_use_ana(ns->ctrl)) {
+ mutex_lock(&ns->ctrl->ana_lock);
+ ns->ana_grpid = le32_to_cpu(id->anagrpid);
+ nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
+ mutex_unlock(&ns->ctrl->ana_lock);
+ } else {
+ mutex_lock(&ns->head->lock);
+ ns->ana_state = NVME_ANA_OPTIMIZED;
+ nvme_mpath_set_live(ns);
+ mutex_unlock(&ns->head->lock);
}
- mutex_unlock(&head->subsys->lock);
}
void nvme_mpath_remove_disk(struct nvme_ns_head *head)
{
if (!head->disk)
return;
- sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
- &nvme_ns_id_attr_group);
- del_gendisk(head->disk);
+ if (head->disk->flags & GENHD_FL_UP) {
+ sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
+ &nvme_ns_id_attr_group);
+ 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);
blk_cleanup_queue(head->disk->queue);
put_disk(head->disk);
}
+
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+ int error;
+
+ if (!nvme_ctrl_use_ana(ctrl))
+ return 0;
+
+ ctrl->anacap = id->anacap;
+ ctrl->anatt = id->anatt;
+ ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);
+ ctrl->anagrpmax = le32_to_cpu(id->anagrpmax);
+
+ mutex_init(&ctrl->ana_lock);
+ 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);
+
+ if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
+ dev_err(ctrl->device,
+ "ANA log page size (%zd) larger than MDTS (%d).\n",
+ ctrl->ana_log_size,
+ ctrl->max_hw_sectors << SECTOR_SHIFT);
+ dev_err(ctrl->device, "disabling ANA support.\n");
+ return 0;
+ }
+
+ INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+ ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
+ if (!ctrl->ana_log_buf)
+ goto out;
+
+ error = nvme_read_ana_log(ctrl, true);
+ if (error)
+ goto out_free_ana_log_buf;
+ return 0;
+out_free_ana_log_buf:
+ kfree(ctrl->ana_log_buf);
+out:
+ return -ENOMEM;
+}
+
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+ kfree(ctrl->ana_log_buf);
+}
+
u16 oacs;
u16 nssa;
u16 nr_streams;
+ u32 max_namespaces;
atomic_t abort_limit;
u8 vwc;
u32 vs;
struct work_struct fw_act_work;
unsigned long events;
+#ifdef CONFIG_NVME_MULTIPATH
+ /* asymmetric namespace access: */
+ u8 anacap;
+ u8 anatt;
+ u32 anagrpmax;
+ u32 nanagrpid;
+ struct mutex ana_lock;
+ struct nvme_ana_rsp_hdr *ana_log_buf;
+ size_t ana_log_size;
+ struct timer_list anatt_timer;
+ struct work_struct ana_work;
+#endif
+
/* Power saving configuration */
u64 ps_max_latency_us;
bool apst_enabled;
struct bio_list requeue_list;
spinlock_t requeue_lock;
struct work_struct requeue_work;
+ struct mutex lock;
#endif
struct list_head list;
struct srcu_struct srcu;
struct nvme_ctrl *ctrl;
struct request_queue *queue;
struct gendisk *disk;
+#ifdef CONFIG_NVME_MULTIPATH
+ enum nvme_ana_state ana_state;
+ u32 ana_grpid;
+#endif
struct list_head siblings;
struct nvm_dev *ndev;
struct kref kref;
bool ext;
u8 pi_type;
unsigned long flags;
-#define NVME_NS_REMOVING 0
-#define NVME_NS_DEAD 1
+#define NVME_NS_REMOVING 0
+#define NVME_NS_DEAD 1
+#define NVME_NS_ANA_PENDING 2
u16 noiob;
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
extern const struct block_device_operations nvme_ns_head_ops;
#ifdef CONFIG_NVME_MULTIPATH
+bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
struct nvme_ctrl *ctrl, int *flags);
void nvme_failover_req(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_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
void nvme_mpath_remove_disk(struct nvme_ns_head *head);
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
+void nvme_mpath_stop(struct nvme_ctrl *ctrl);
static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
{
kblockd_schedule_work(&head->requeue_work);
}
+extern struct device_attribute dev_attr_ana_grpid;
+extern struct device_attribute dev_attr_ana_state;
+
#else
+static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+ return false;
+}
/*
* Without the multipath code enabled, multiple controller per subsystems are
* visible as devices and thus we cannot use the subsystem instance.
{
return 0;
}
-static inline void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static inline void nvme_mpath_add_disk(struct nvme_ns *ns,
+ struct nvme_id_ns *id)
{
}
static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
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)
+{
+ return 0;
+}
+static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+}
+static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+}
#endif /* CONFIG_NVME_MULTIPATH */
#ifdef CONFIG_NVM
projects / users / hch / configfs.git / commitdiff