Merge branch 'nvme-4.19' of git://git.infradead.org/nvme into for-4.19/block2

Pull NVMe changes from Christoph:

"This contains the support for TP4004, Asymmetric Namespace Access,
 which makes NVMe multipathing usable in practice."

* 'nvme-4.19' of git://git.infradead.org/nvme:
  nvmet: use Retain Async Event bit to clear AEN
  nvmet: support configuring ANA groups
  nvmet: add minimal ANA support
  nvmet: track and limit the number of namespaces per subsystem
  nvmet: keep a port pointer in nvmet_ctrl
  nvme: add ANA support
  nvme: remove nvme_req_needs_failover
  nvme: simplify the API for getting log pages
  nvme.h: add ANA definitions
  nvme.h: add support for the log specific field
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/nvme/host/core.c

@@ -252,7 +252,8 @@ void nvme_complete_rq(struct request *req)
 	trace_nvme_complete_rq(req);
 
 	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if (nvme_req_needs_failover(req, status)) {
+		if ((req->cmd_flags & REQ_NVME_MPATH) &&
+		    blk_path_error(status)) {
 			nvme_failover_req(req);
 			return;
 		}
@@ -1067,7 +1068,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 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)
 {
@@ -2281,21 +2282,16 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	return ret;
 }
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		     u8 log_page, void *log,
-		     size_t size, u64 offset)
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
 	unsigned long dwlen = size / 4 - 1;
 
 	c.get_log_page.opcode = nvme_admin_get_log_page;
-
-	if (ns)
-		c.get_log_page.nsid = cpu_to_le32(ns->head->ns_id);
-	else
-		c.get_log_page.nsid = cpu_to_le32(NVME_NSID_ALL);
-
+	c.get_log_page.nsid = cpu_to_le32(nsid);
 	c.get_log_page.lid = log_page;
+	c.get_log_page.lsp = lsp;
 	c.get_log_page.numdl = cpu_to_le16(dwlen & ((1 << 16) - 1));
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
@@ -2304,12 +2300,6 @@ int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_log(struct nvme_ctrl *ctrl, u8 log_page, void *log,
-			size_t size)
-{
-	return nvme_get_log_ext(ctrl, NULL, log_page, log, size, 0);
-}
-
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 {
 	int ret;
@@ -2320,8 +2310,8 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 	if (!ctrl->effects)
 		return 0;
 
-	ret = nvme_get_log(ctrl, NVME_LOG_CMD_EFFECTS, ctrl->effects,
-					sizeof(*ctrl->effects));
+	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
+			ctrl->effects, sizeof(*ctrl->effects), 0);
 	if (ret) {
 		kfree(ctrl->effects);
 		ctrl->effects = NULL;
@@ -2412,6 +2402,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	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 */
@@ -2471,8 +2462,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		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)
@@ -2691,6 +2686,10 @@ static struct attribute *nvme_ns_id_attrs[] = {
 	&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,
 };
 
@@ -2713,6 +2712,14 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 		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;
 }
 
@@ -3086,8 +3093,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	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))
@@ -3097,8 +3102,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		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);
@@ -3240,7 +3247,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
+			log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -3357,9 +3365,9 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_LOG_FW_SLOT, log, sizeof(*log)))
-		dev_warn(ctrl->device,
-				"Get FW SLOT INFO log error\n");
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log,
+			sizeof(*log), 0))
+		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
 
@@ -3405,6 +3413,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	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);
 	}
@@ -3437,6 +3452,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 
 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);
@@ -3474,6 +3490,7 @@ static void nvme_free_ctrl(struct device *dev)
 
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 	kfree(ctrl->effects);
+	nvme_mpath_uninit(ctrl);
 
 	if (subsys) {
 		mutex_lock(&subsys->lock);

drivers/nvme/host/lightnvm.c

@@ -604,8 +604,9 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	while (left) {
 		len = min_t(unsigned int, left, max_len);
 
-		ret = nvme_get_log_ext(ctrl, ns, NVME_NVM_LOG_REPORT_CHUNK,
-				dev_meta, len, offset);
+		ret = nvme_get_log(ctrl, ns->head->ns_id,
+				NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
+				offset);
 		if (ret) {
 			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
 			break;

drivers/nvme/host/multipath.c

 /*
- * 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,
@@ -20,6 +20,11 @@ module_param(multipath, bool, 0444);
 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
@@ -45,6 +50,7 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 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);
@@ -52,15 +58,35 @@ void nvme_failover_req(struct request *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);
-}
+	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;
+	}
 
-bool nvme_req_needs_failover(struct request *req, blk_status_t error)
-{
-	if (!(req->cmd_flags & REQ_NVME_MPATH))
-		return false;
-	return blk_path_error(error);
+	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
@@ -75,25 +101,51 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 	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;
 }
@@ -142,7 +194,7 @@ static bool nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc)
 
 	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;
@@ -176,6 +228,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	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);
@@ -220,29 +273,232 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	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);
@@ -250,3 +506,52 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	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);
+}
+

drivers/nvme/host/nvme.h

@@ -183,6 +183,7 @@ struct nvme_ctrl {
 	u16 oacs;
 	u16 nssa;
 	u16 nr_streams;
+	u32 max_namespaces;
 	atomic_t abort_limit;
 	u8 vwc;
 	u32 vs;
@@ -205,6 +206,19 @@ struct nvme_ctrl {
 	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;
@@ -269,6 +283,7 @@ struct nvme_ns_head {
 	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;
@@ -295,6 +310,10 @@ struct nvme_ns {
 	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;
@@ -307,8 +326,9 @@ struct nvme_ns {
 	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
@@ -436,21 +456,24 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		u8 log_page, void *log, size_t size, u64 offset);
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset);
 
 extern const struct attribute_group nvme_ns_id_attr_group;
 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);
-bool nvme_req_needs_failover(struct request *req, blk_status_t error);
 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)
 {
@@ -469,7 +492,14 @@ static inline void nvme_mpath_check_last_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.
@@ -483,11 +513,6 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 static inline void nvme_failover_req(struct request *req)
 {
 }
-static inline bool nvme_req_needs_failover(struct request *req,
-					   blk_status_t error)
-{
-	return false;
-}
 static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 }
@@ -496,7 +521,8 @@ static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,
 {
 	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)
@@ -508,6 +534,17 @@ static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 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

drivers/nvme/target/admin-cmd.c

@@ -19,6 +19,19 @@
 #include <asm/unaligned.h>
 #include "nvmet.h"
 
+/*
+ * This helper allows us to clear the AEN based on the RAE bit,
+ * Please use this helper when processing the log pages which are
+ * associated with the AEN.
+ */
+static inline void nvmet_clear_aen(struct nvmet_req *req, u32 aen_bit)
+{
+	int rae = le32_to_cpu(req->cmd->common.cdw10[0]) & 1 << 15;
+
+	if (!rae)
+		clear_bit(aen_bit, &req->sq->ctrl->aen_masked);
+}
+
 u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 {
 	u32 len = le16_to_cpu(cmd->get_log_page.numdu);
@@ -176,12 +189,76 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 	if (!status)
 		status = nvmet_zero_sgl(req, len, req->data_len - len);
 	ctrl->nr_changed_ns = 0;
-	clear_bit(NVME_AEN_CFG_NS_ATTR, &ctrl->aen_masked);
+	nvmet_clear_aen(req, NVME_AEN_CFG_NS_ATTR);
 	mutex_unlock(&ctrl->lock);
 out:
 	nvmet_req_complete(req, status);
 }
 
+static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
+		struct nvme_ana_group_desc *desc)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvmet_ns *ns;
+	u32 count = 0;
+
+	if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+			if (ns->anagrpid == grpid)
+				desc->nsids[count++] = cpu_to_le32(ns->nsid);
+		rcu_read_unlock();
+	}
+
+	desc->grpid = cpu_to_le32(grpid);
+	desc->nnsids = cpu_to_le32(count);
+	desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	desc->state = req->port->ana_state[grpid];
+	memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
+	return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
+}
+
+static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
+{
+	struct nvme_ana_rsp_hdr hdr = { 0, };
+	struct nvme_ana_group_desc *desc;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr); /* start beyond hdr */
+	size_t len;
+	u32 grpid;
+	u16 ngrps = 0;
+	u16 status;
+
+	status = NVME_SC_INTERNAL;
+	desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
+			NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
+	if (!desc)
+		goto out;
+
+	down_read(&nvmet_ana_sem);
+	for (grpid = 1; grpid <= NVMET_MAX_ANAGRPS; grpid++) {
+		if (!nvmet_ana_group_enabled[grpid])
+			continue;
+		len = nvmet_format_ana_group(req, grpid, desc);
+		status = nvmet_copy_to_sgl(req, offset, desc, len);
+		if (status)
+			break;
+		offset += len;
+		ngrps++;
+	}
+
+	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	hdr.ngrps = cpu_to_le16(ngrps);
+	nvmet_clear_aen(req, NVME_AEN_CFG_ANA_CHANGE);
+	up_read(&nvmet_ana_sem);
+
+	kfree(desc);
+
+	/* copy the header last once we know the number of groups */
+	status = nvmet_copy_to_sgl(req, 0, &hdr, sizeof(hdr));
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -213,8 +290,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	 * the safest is to leave it as zeroes.
 	 */
 
-	/* we support multiple ports and multiples hosts: */
-	id->cmic = (1 << 0) | (1 << 1);
+	/* we support multiple ports, multiples hosts and ANA: */
+	id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
 
 	/* no limit on data transfer sizes for now */
 	id->mdts = 0;
@@ -252,6 +329,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
 
 	id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
+	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
 			NVME_CTRL_ONCS_WRITE_ZEROES);
 
@@ -281,6 +359,11 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 
 	id->msdbd = ctrl->ops->msdbd;
 
+	id->anacap = (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4);
+	id->anatt = 10; /* random value */
+	id->anagrpmax = cpu_to_le32(NVMET_MAX_ANAGRPS);
+	id->nanagrpid = cpu_to_le32(NVMET_MAX_ANAGRPS);
+
 	/*
 	 * Meh, we don't really support any power state.  Fake up the same
 	 * values that qemu does.
@@ -322,8 +405,15 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * nuse = ncap = nsze isn't always true, but we have no way to find
 	 * that out from the underlying device.
 	 */
-	id->ncap = id->nuse = id->nsze =
-		cpu_to_le64(ns->size >> ns->blksize_shift);
+	id->ncap = id->nsze = cpu_to_le64(ns->size >> ns->blksize_shift);
+	switch (req->port->ana_state[ns->anagrpid]) {
+	case NVME_ANA_INACCESSIBLE:
+	case NVME_ANA_PERSISTENT_LOSS:
+		break;
+	default:
+		id->nuse = id->nsze;
+		break;
+        }
 
 	/*
 	 * We just provide a single LBA format that matches what the
@@ -337,6 +427,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * controllers, but also with any other user of the block device.
 	 */
 	id->nmic = (1 << 0);
+	id->anagrpid = cpu_to_le32(ns->anagrpid);
 
 	memcpy(&id->nguid, &ns->nguid, sizeof(id->nguid));
 
@@ -619,6 +710,9 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		case NVME_LOG_CMD_EFFECTS:
 			req->execute = nvmet_execute_get_log_cmd_effects_ns;
 			return 0;
+		case NVME_LOG_ANA:
+			req->execute = nvmet_execute_get_log_page_ana;
+			return 0;
 		}
 		break;
 	case nvme_admin_identify:

drivers/nvme/target/configfs.c

@@ -411,6 +411,39 @@ static ssize_t nvmet_ns_device_nguid_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_ns_, device_nguid);
 
+static ssize_t nvmet_ns_ana_grpid_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%u\n", to_nvmet_ns(item)->anagrpid);
+}
+
+static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	u32 oldgrpid, newgrpid;
+	int ret;
+
+	ret = kstrtou32(page, 0, &newgrpid);
+	if (ret)
+		return ret;
+
+	if (newgrpid < 1 || newgrpid > NVMET_MAX_ANAGRPS)
+		return -EINVAL;
+
+	down_write(&nvmet_ana_sem);
+	oldgrpid = ns->anagrpid;
+	nvmet_ana_group_enabled[newgrpid]++;
+	ns->anagrpid = newgrpid;
+	nvmet_ana_group_enabled[oldgrpid]--;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_send_ana_event(ns->subsys, NULL);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, ana_grpid);
+
 static ssize_t nvmet_ns_enable_show(struct config_item *item, char *page)
 {
 	return sprintf(page, "%d\n", to_nvmet_ns(item)->enabled);
@@ -468,6 +501,7 @@ static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_device_path,
 	&nvmet_ns_attr_device_nguid,
 	&nvmet_ns_attr_device_uuid,
+	&nvmet_ns_attr_ana_grpid,
 	&nvmet_ns_attr_enable,
 	&nvmet_ns_attr_buffered_io,
 	NULL,
@@ -916,6 +950,134 @@ static const struct config_item_type nvmet_referrals_type = {
 	.ct_group_ops	= &nvmet_referral_group_ops,
 };
 
+static struct {
+	enum nvme_ana_state	state;
+	const char		*name;
+} nvmet_ana_state_names[] = {
+	{ NVME_ANA_OPTIMIZED,		"optimized" },
+	{ NVME_ANA_NONOPTIMIZED,	"non-optimized" },
+	{ NVME_ANA_INACCESSIBLE,	"inaccessible" },
+	{ NVME_ANA_PERSISTENT_LOSS,	"persistent-loss" },
+	{ NVME_ANA_CHANGE,		"change" },
+};
+
+static ssize_t nvmet_ana_group_ana_state_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	enum nvme_ana_state state = grp->port->ana_state[grp->grpid];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (state != nvmet_ana_state_names[i].state)
+			continue;
+		return sprintf(page, "%s\n", nvmet_ana_state_names[i].name);
+	}
+
+	return sprintf(page, "\n");
+}
+
+static ssize_t nvmet_ana_group_ana_state_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (sysfs_streq(page, nvmet_ana_state_names[i].name))
+			goto found;
+	}
+
+	pr_err("Invalid value '%s' for ana_state\n", page);
+	return -EINVAL;
+
+found:
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = nvmet_ana_state_names[i].state;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ana_group_, ana_state);
+
+static struct configfs_attribute *nvmet_ana_group_attrs[] = {
+	&nvmet_ana_group_attr_ana_state,
+	NULL,
+};
+
+static void nvmet_ana_group_release(struct config_item *item)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+
+	if (grp == &grp->port->ana_default_group)
+		return;
+
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = NVME_ANA_INACCESSIBLE;
+	nvmet_ana_group_enabled[grp->grpid]--;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	kfree(grp);
+}
+
+static struct configfs_item_operations nvmet_ana_group_item_ops = {
+	.release		= nvmet_ana_group_release,
+};
+
+static const struct config_item_type nvmet_ana_group_type = {
+	.ct_item_ops		= &nvmet_ana_group_item_ops,
+	.ct_attrs		= nvmet_ana_group_attrs,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_ana_groups_make_group(
+		struct config_group *group, const char *name)
+{
+	struct nvmet_port *port = ana_groups_to_port(&group->cg_item);
+	struct nvmet_ana_group *grp;
+	u32 grpid;
+	int ret;
+
+	ret = kstrtou32(name, 0, &grpid);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	if (grpid <= 1 || grpid > NVMET_MAX_ANAGRPS)
+		goto out;
+
+	ret = -ENOMEM;
+	grp = kzalloc(sizeof(*grp), GFP_KERNEL);
+	if (!grp)
+		goto out;
+	grp->port = port;
+	grp->grpid = grpid;
+
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[grpid]++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+
+	config_group_init_type_name(&grp->group, name, &nvmet_ana_group_type);
+	return &grp->group;
+out:
+	return ERR_PTR(ret);
+}
+
+static struct configfs_group_operations nvmet_ana_groups_group_ops = {
+	.make_group		= nvmet_ana_groups_make_group,
+};
+
+static const struct config_item_type nvmet_ana_groups_type = {
+	.ct_group_ops		= &nvmet_ana_groups_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
 /*
  * Ports definitions.
  */
@@ -923,6 +1085,7 @@ static void nvmet_port_release(struct config_item *item)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
 
+	kfree(port->ana_state);
 	kfree(port);
 }
 
@@ -951,6 +1114,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 {
 	struct nvmet_port *port;
 	u16 portid;
+	u32 i;
 
 	if (kstrtou16(name, 0, &portid))
 		return ERR_PTR(-EINVAL);
@@ -959,6 +1123,20 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	if (!port)
 		return ERR_PTR(-ENOMEM);
 
+	port->ana_state = kcalloc(NVMET_MAX_ANAGRPS + 1,
+			sizeof(*port->ana_state), GFP_KERNEL);
+	if (!port->ana_state) {
+		kfree(port);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 1; i <= NVMET_MAX_ANAGRPS; i++) {
+		if (i == NVMET_DEFAULT_ANA_GRPID)
+			port->ana_state[1] = NVME_ANA_OPTIMIZED;
+		else
+			port->ana_state[i] = NVME_ANA_INACCESSIBLE;
+	}
+
 	INIT_LIST_HEAD(&port->entry);
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
@@ -975,6 +1153,18 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 			"referrals", &nvmet_referrals_type);
 	configfs_add_default_group(&port->referrals_group, &port->group);
 
+	config_group_init_type_name(&port->ana_groups_group,
+			"ana_groups", &nvmet_ana_groups_type);
+	configfs_add_default_group(&port->ana_groups_group, &port->group);
+
+	port->ana_default_group.port = port;
+	port->ana_default_group.grpid = NVMET_DEFAULT_ANA_GRPID;
+	config_group_init_type_name(&port->ana_default_group.group,
+			__stringify(NVMET_DEFAULT_ANA_GRPID),
+			&nvmet_ana_group_type);
+	configfs_add_default_group(&port->ana_default_group.group,
+			&port->ana_groups_group);
+
 	return &port->group;
 }
 

drivers/nvme/target/core.c

@@ -40,6 +40,10 @@ static DEFINE_IDA(cntlid_ida);
  */
 DECLARE_RWSEM(nvmet_config_sem);
 
+u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+u64 nvmet_ana_chgcnt;
+DECLARE_RWSEM(nvmet_ana_sem);
+
 static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 		const char *subsysnqn);
 
@@ -190,6 +194,33 @@ static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 	}
 }
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port)
+{
+	struct nvmet_ctrl *ctrl;
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		if (port && ctrl->port != port)
+			continue;
+		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_ANA_CHANGE))
+			continue;
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
+	}
+	mutex_unlock(&subsys->lock);
+}
+
+void nvmet_port_send_ana_event(struct nvmet_port *port)
+{
+	struct nvmet_subsys_link *p;
+
+	down_read(&nvmet_config_sem);
+	list_for_each_entry(p, &port->subsystems, entry)
+		nvmet_send_ana_event(p->subsys, port);
+	up_read(&nvmet_config_sem);
+}
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
 {
 	int ret = 0;
@@ -337,9 +368,13 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&subsys->lock);
+	ret = -EMFILE;
+	if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
+		goto out_unlock;
+	ret = 0;
 	if (ns->enabled)
 		goto out_unlock;
 
@@ -374,6 +409,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 
 		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
 	}
+	subsys->nr_namespaces++;
 
 	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
@@ -414,6 +450,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
+	subsys->nr_namespaces--;
 	nvmet_ns_changed(subsys, ns->nsid);
 	nvmet_ns_dev_disable(ns);
 out_unlock:
@@ -424,6 +461,10 @@ void nvmet_ns_free(struct nvmet_ns *ns)
 {
 	nvmet_ns_disable(ns);
 
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[ns->anagrpid]--;
+	up_write(&nvmet_ana_sem);
+
 	kfree(ns->device_path);
 	kfree(ns);
 }
@@ -441,6 +482,12 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 
 	ns->nsid = nsid;
 	ns->subsys = subsys;
+
+	down_write(&nvmet_ana_sem);
+	ns->anagrpid = NVMET_DEFAULT_ANA_GRPID;
+	nvmet_ana_group_enabled[ns->anagrpid]++;
+	up_write(&nvmet_ana_sem);
+
 	uuid_gen(&ns->uuid);
 	ns->buffered_io = false;
 
@@ -548,6 +595,20 @@ int nvmet_sq_init(struct nvmet_sq *sq)
 }
 EXPORT_SYMBOL_GPL(nvmet_sq_init);
 
+static inline u16 nvmet_check_ana_state(struct nvmet_port *port,
+		struct nvmet_ns *ns)
+{
+	enum nvme_ana_state state = port->ana_state[ns->anagrpid];
+
+	if (unlikely(state == NVME_ANA_INACCESSIBLE))
+		return NVME_SC_ANA_INACCESSIBLE;
+	if (unlikely(state == NVME_ANA_PERSISTENT_LOSS))
+		return NVME_SC_ANA_PERSISTENT_LOSS;
+	if (unlikely(state == NVME_ANA_CHANGE))
+		return NVME_SC_ANA_TRANSITION;
+	return 0;
+}
+
 static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
@@ -560,6 +621,9 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
 	if (unlikely(!req->ns))
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+	ret = nvmet_check_ana_state(req->port, req->ns);
+	if (unlikely(ret))
+		return ret;
 
 	if (req->ns->file)
 		return nvmet_file_parse_io_cmd(req);
@@ -876,6 +940,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	nvmet_init_cap(ctrl);
 
+	ctrl->port = req->port;
+
 	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
 	INIT_LIST_HEAD(&ctrl->async_events);
 
@@ -1115,12 +1181,15 @@ static int __init nvmet_init(void)
 {
 	int error;
 
+	nvmet_ana_group_enabled[NVMET_DEFAULT_ANA_GRPID] = 1;
+
 	buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq",
 			WQ_MEM_RECLAIM, 0);
 	if (!buffered_io_wq) {
 		error = -ENOMEM;
 		goto out;
 	}
+
 	error = nvmet_init_discovery();
 	if (error)
 		goto out;

drivers/nvme/target/nvmet.h

@@ -30,12 +30,11 @@
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
 
-
 /*
  * Supported optional AENs:
  */
 #define NVMET_AEN_CFG_OPTIONAL \
-	NVME_AEN_CFG_NS_ATTR
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_ANA_CHANGE)
 
 /*
  * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
@@ -64,6 +63,7 @@ struct nvmet_ns {
 	loff_t			size;
 	u8			nguid[16];
 	uuid_t			uuid;
+	u32			anagrpid;
 
 	bool			buffered_io;
 	bool			enabled;
@@ -98,6 +98,18 @@ struct nvmet_sq {
 	struct completion	confirm_done;
 };
 
+struct nvmet_ana_group {
+	struct config_group	group;
+	struct nvmet_port	*port;
+	u32			grpid;
+};
+
+static inline struct nvmet_ana_group *to_ana_group(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_ana_group,
+			group);
+}
+
 /**
  * struct nvmet_port -	Common structure to keep port
  *				information for the target.
@@ -115,6 +127,9 @@ struct nvmet_port {
 	struct list_head		subsystems;
 	struct config_group		referrals_group;
 	struct list_head		referrals;
+	struct config_group		ana_groups_group;
+	struct nvmet_ana_group		ana_default_group;
+	enum nvme_ana_state		*ana_state;
 	void				*priv;
 	bool				enabled;
 	int				inline_data_size;
@@ -126,6 +141,13 @@ static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
 			group);
 }
 
+static inline struct nvmet_port *ana_groups_to_port(
+		struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_port,
+			ana_groups_group);
+}
+
 struct nvmet_ctrl {
 	struct nvmet_subsys	*subsys;
 	struct nvmet_cq		**cqs;
@@ -140,6 +162,8 @@ struct nvmet_ctrl {
 	u16			cntlid;
 	u32			kato;
 
+	struct nvmet_port	*port;
+
 	u32			aen_enabled;
 	unsigned long		aen_masked;
 	struct nvmet_req	*async_event_cmds[NVMET_ASYNC_EVENTS];
@@ -168,6 +192,7 @@ struct nvmet_subsys {
 	struct kref		ref;
 
 	struct list_head	namespaces;
+	unsigned int		nr_namespaces;
 	unsigned int		max_nsid;
 
 	struct list_head	ctrls;
@@ -340,6 +365,10 @@ void nvmet_ns_disable(struct nvmet_ns *ns);
 struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid);
 void nvmet_ns_free(struct nvmet_ns *ns);
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port);
+void nvmet_port_send_ana_event(struct nvmet_port *port);
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops);
 void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops);
 
@@ -360,6 +389,22 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 #define NVMET_QUEUE_SIZE	1024
 #define NVMET_NR_QUEUES		128
 #define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
+
+/*
+ * Nice round number that makes a list of nsids fit into a page.
+ * Should become tunable at some point in the future.
+ */
+#define NVMET_MAX_NAMESPACES	1024
+
+/*
+ * 0 is not a valid ANA group ID, so we start numbering at 1.
+ *
+ * ANA Group 1 exists without manual intervention, has namespaces assigned to it
+ * by default, and is available in an optimized state through all ports.
+ */
+#define NVMET_MAX_ANAGRPS	128
+#define NVMET_DEFAULT_ANA_GRPID	1
+
 #define NVMET_KAS		10
 #define NVMET_DISC_KATO		120
 
@@ -373,6 +418,10 @@ extern struct nvmet_subsys *nvmet_disc_subsys;
 extern u64 nvmet_genctr;
 extern struct rw_semaphore nvmet_config_sem;
 
+extern u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+extern u64 nvmet_ana_chgcnt;
+extern struct rw_semaphore nvmet_ana_sem;
+
 bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
 		const char *hostnqn);
 

include/linux/nvme.h

@@ -242,7 +242,12 @@ struct nvme_id_ctrl {
 	__le32			sanicap;
 	__le32			hmminds;
 	__le16			hmmaxd;
-	__u8			rsvd338[174];
+	__u8			rsvd338[4];
+	__u8			anatt;
+	__u8			anacap;
+	__le32			anagrpmax;
+	__le32			nanagrpid;
+	__u8			rsvd352[160];
 	__u8			sqes;
 	__u8			cqes;
 	__le16			maxcmd;
@@ -258,7 +263,8 @@ struct nvme_id_ctrl {
 	__le16			acwu;
 	__u8			rsvd534[2];
 	__le32			sgls;
-	__u8			rsvd540[228];
+	__le32			mnan;
+	__u8			rsvd544[224];
 	char			subnqn[256];
 	__u8			rsvd1024[768];
 	__le32			ioccsz;
@@ -312,7 +318,9 @@ struct nvme_id_ns {
 	__le16			nabspf;
 	__le16			noiob;
 	__u8			nvmcap[16];
-	__u8			rsvd64[40];
+	__u8			rsvd64[28];
+	__le32			anagrpid;
+	__u8			rsvd96[8];
 	__u8			nguid[16];
 	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];
@@ -425,6 +433,32 @@ struct nvme_effects_log {
 	__u8   resv[2048];
 };
 
+enum nvme_ana_state {
+	NVME_ANA_OPTIMIZED		= 0x01,
+	NVME_ANA_NONOPTIMIZED		= 0x02,
+	NVME_ANA_INACCESSIBLE		= 0x03,
+	NVME_ANA_PERSISTENT_LOSS	= 0x04,
+	NVME_ANA_CHANGE			= 0x0f,
+};
+
+struct nvme_ana_group_desc {
+	__le32	grpid;
+	__le32	nnsids;
+	__le64	chgcnt;
+	__u8	state;
+	__u8	rsvd17[7];
+	__le32	nsids[];
+};
+
+/* flag for the log specific field of the ANA log */
+#define NVME_ANA_LOG_RGO	(1 << 0)
+
+struct nvme_ana_rsp_hdr {
+	__le64	chgcnt;
+	__le16	ngrps;
+	__le16	rsvd10[3];
+};
+
 enum {
 	NVME_SMART_CRIT_SPARE		= 1 << 0,
 	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
@@ -444,11 +478,13 @@ enum {
 enum {
 	NVME_AER_NOTICE_NS_CHANGED	= 0x00,
 	NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
+	NVME_AER_NOTICE_ANA		= 0x03,
 };
 
 enum {
 	NVME_AEN_CFG_NS_ATTR		= 1 << 8,
 	NVME_AEN_CFG_FW_ACT		= 1 << 9,
+	NVME_AEN_CFG_ANA_CHANGE		= 1 << 11,
 };
 
 struct nvme_lba_range_type {
@@ -763,6 +799,7 @@ enum {
 	NVME_LOG_FW_SLOT	= 0x03,
 	NVME_LOG_CHANGED_NS	= 0x04,
 	NVME_LOG_CMD_EFFECTS	= 0x05,
+	NVME_LOG_ANA		= 0x0c,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
@@ -885,7 +922,7 @@ struct nvme_get_log_page_command {
 	__u64			rsvd2[2];
 	union nvme_data_ptr	dptr;
 	__u8			lid;
-	__u8			rsvd10;
+	__u8			lsp; /* upper 4 bits reserved */
 	__le16			numdl;
 	__le16			numdu;
 	__u16			rsvd11;
@@ -1185,6 +1222,13 @@ enum {
 	NVME_SC_ACCESS_DENIED		= 0x286,
 	NVME_SC_UNWRITTEN_BLOCK		= 0x287,
 
+	/*
+	 * Path-related Errors:
+	 */
+	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
+	NVME_SC_ANA_INACCESSIBLE	= 0x302,
+	NVME_SC_ANA_TRANSITION		= 0x303,
+
 	NVME_SC_DNR			= 0x4000,
 };