1 files changed, 161 insertions, 62 deletions

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0a88d7bdc5e3..48e7a8906d01 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -17,6 +17,7 @@ MODULE_PARM_DESC(multipath,
 static const char *nvme_iopolicy_names[] = {
 	[NVME_IOPOLICY_NUMA]	= "numa",
 	[NVME_IOPOLICY_RR]	= "round-robin",
+	[NVME_IOPOLICY_QD]      = "queue-depth",
 };
 
 static int iopolicy = NVME_IOPOLICY_NUMA;
@@ -29,6 +30,8 @@ static int nvme_set_iopolicy(const char *val, const struct kernel_param *kp)
 		iopolicy = NVME_IOPOLICY_NUMA;
 	else if (!strncmp(val, "round-robin", 11))
 		iopolicy = NVME_IOPOLICY_RR;
+	else if (!strncmp(val, "queue-depth", 11))
+		iopolicy = NVME_IOPOLICY_QD;
 	else
 		return -EINVAL;
 
@@ -43,7 +46,7 @@ static int nvme_get_iopolicy(char *buf, const struct kernel_param *kp)
 module_param_call(iopolicy, nvme_set_iopolicy, nvme_get_iopolicy,
 	&iopolicy, 0644);
 MODULE_PARM_DESC(iopolicy,
-	"Default multipath I/O policy; 'numa' (default) or 'round-robin'");
+	"Default multipath I/O policy; 'numa' (default), 'round-robin' or 'queue-depth'");
 
 void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
 {
@@ -83,7 +86,7 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
-	u16 status = nvme_req(req)->status & 0x7ff;
+	u16 status = nvme_req(req)->status & NVME_SCT_SC_MASK;
 	unsigned long flags;
 	struct bio *bio;
 
@@ -118,7 +121,8 @@ void nvme_failover_req(struct request *req)
 	blk_steal_bios(&ns->head->requeue_list, req);
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
 
-	blk_mq_end_request(req, 0);
+	nvme_req(req)->status = 0;
+	nvme_end_req(req);
 	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
@@ -127,6 +131,11 @@ void nvme_mpath_start_request(struct request *rq)
 	struct nvme_ns *ns = rq->q->queuedata;
 	struct gendisk *disk = ns->head->disk;
 
+	if (READ_ONCE(ns->head->subsys->iopolicy) == NVME_IOPOLICY_QD) {
+		atomic_inc(&ns->ctrl->nr_active);
+		nvme_req(rq)->flags |= NVME_MPATH_CNT_ACTIVE;
+	}
+
 	if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq))
 		return;
 
@@ -140,6 +149,9 @@ void nvme_mpath_end_request(struct request *rq)
 {
 	struct nvme_ns *ns = rq->q->queuedata;
 
+	if (nvme_req(rq)->flags & NVME_MPATH_CNT_ACTIVE)
+		atomic_dec_if_positive(&ns->ctrl->nr_active);
+
 	if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
 		return;
 	bdev_end_io_acct(ns->head->disk->part0, req_op(rq),
@@ -150,16 +162,17 @@ void nvme_mpath_end_request(struct request *rq)
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		if (!ns->head->disk)
 			continue;
 		kblockd_schedule_work(&ns->head->requeue_work);
-		if (ctrl->state == NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 			disk_uevent(ns->head->disk, KOBJ_CHANGE);
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 
 static const char *nvme_ana_state_names[] = {
@@ -193,13 +206,14 @@ out:
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		nvme_mpath_clear_current_path(ns);
 		kblockd_schedule_work(&ns->head->requeue_work);
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 
 void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
@@ -223,13 +237,14 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(ns->ctrl);
+
 	/*
 	 * We don't treat NVME_CTRL_DELETING as a disabled path as I/O should
 	 * still be able to complete assuming that the controller is connected.
 	 * Otherwise it will fail immediately and return to the requeue list.
 	 */
-	if (ns->ctrl->state != NVME_CTRL_LIVE &&
-	    ns->ctrl->state != NVME_CTRL_DELETING)
+	if (state != NVME_CTRL_LIVE && state != NVME_CTRL_DELETING)
 		return true;
 	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
 	    !test_bit(NVME_NS_READY, &ns->flags))
@@ -246,7 +261,8 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
 		if (nvme_path_is_disabled(ns))
 			continue;
 
-		if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
+		if (ns->ctrl->numa_node != NUMA_NO_NODE &&
+		    READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
 			distance = node_distance(node, ns->ctrl->numa_node);
 		else
 			distance = LOCAL_DISTANCE;
@@ -286,10 +302,15 @@ static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head,
 	return list_first_or_null_rcu(&head->list, struct nvme_ns, siblings);
 }
 
-static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
-		int node, struct nvme_ns *old)
+static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns, *found = NULL;
+	int node = numa_node_id();
+	struct nvme_ns *old = srcu_dereference(head->current_path[node],
+					       &head->srcu);
+
+	if (unlikely(!old))
+		return __nvme_find_path(head, node);
 
 	if (list_is_singular(&head->list)) {
 		if (nvme_path_is_disabled(old))
@@ -329,13 +350,49 @@ out:
 	return found;
 }
 
+static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
+{
+	struct nvme_ns *best_opt = NULL, *best_nonopt = NULL, *ns;
+	unsigned int min_depth_opt = UINT_MAX, min_depth_nonopt = UINT_MAX;
+	unsigned int depth;
+
+	list_for_each_entry_rcu(ns, &head->list, siblings) {
+		if (nvme_path_is_disabled(ns))
+			continue;
+
+		depth = atomic_read(&ns->ctrl->nr_active);
+
+		switch (ns->ana_state) {
+		case NVME_ANA_OPTIMIZED:
+			if (depth < min_depth_opt) {
+				min_depth_opt = depth;
+				best_opt = ns;
+			}
+			break;
+		case NVME_ANA_NONOPTIMIZED:
+			if (depth < min_depth_nonopt) {
+				min_depth_nonopt = depth;
+				best_nonopt = ns;
+			}
+			break;
+		default:
+			break;
+		}
+
+		if (min_depth_opt == 0)
+			return best_opt;
+	}
+
+	return best_opt ? best_opt : best_nonopt;
+}
+
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
-	return ns->ctrl->state == NVME_CTRL_LIVE &&
+	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
 		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
-inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
+static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head)
 {
 	int node = numa_node_id();
 	struct nvme_ns *ns;
@@ -343,22 +400,34 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 	ns = srcu_dereference(head->current_path[node], &head->srcu);
 	if (unlikely(!ns))
 		return __nvme_find_path(head, node);
-
-	if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR)
-		return nvme_round_robin_path(head, node, ns);
 	if (unlikely(!nvme_path_is_optimized(ns)))
 		return __nvme_find_path(head, node);
 	return ns;
 }
 
+inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
+{
+	switch (READ_ONCE(head->subsys->iopolicy)) {
+	case NVME_IOPOLICY_QD:
+		return nvme_queue_depth_path(head);
+	case NVME_IOPOLICY_RR:
+		return nvme_round_robin_path(head);
+	default:
+		return nvme_numa_path(head);
+	}
+}
+
 static bool nvme_available_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns;
 
+	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
+		return NULL;
+
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
 		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
 			continue;
-		switch (ns->ctrl->state) {
+		switch (nvme_ctrl_state(ns->ctrl)) {
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
@@ -422,6 +491,21 @@ static void nvme_ns_head_release(struct gendisk *disk)
 	nvme_put_ns_head(disk->private_data);
 }
 
+static int nvme_ns_head_get_unique_id(struct gendisk *disk, u8 id[16],
+		enum blk_unique_id type)
+{
+	struct nvme_ns_head *head = disk->private_data;
+	struct nvme_ns *ns;
+	int srcu_idx, ret = -EWOULDBLOCK;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (ns)
+		ret = nvme_ns_get_unique_id(ns, id, type);
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+
 #ifdef CONFIG_BLK_DEV_ZONED
 static int nvme_ns_head_report_zones(struct gendisk *disk, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data)
@@ -449,6 +533,7 @@ const struct block_device_operations nvme_ns_head_ops = {
 	.ioctl		= nvme_ns_head_ioctl,
 	.compat_ioctl	= blkdev_compat_ptr_ioctl,
 	.getgeo		= nvme_getgeo,
+	.get_unique_id	= nvme_ns_head_get_unique_id,
 	.report_zones	= nvme_ns_head_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
@@ -515,7 +600,7 @@ static void nvme_requeue_work(struct work_struct *work)
 
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 {
-	bool vwc = false;
+	struct queue_limits lim;
 
 	mutex_init(&head->lock);
 	bio_list_init(&head->requeue_list);
@@ -531,36 +616,21 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	    !nvme_is_unique_nsid(ctrl, head) || !multipath)
 		return 0;
 
-	head->disk = blk_alloc_disk(ctrl->numa_node);
-	if (!head->disk)
-		return -ENOMEM;
+	blk_set_stacking_limits(&lim);
+	lim.dma_alignment = 3;
+	lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
+	if (head->ids.csi == NVME_CSI_ZNS)
+		lim.features |= BLK_FEAT_ZONED;
+	else
+		lim.max_zone_append_sectors = 0;
+
+	head->disk = blk_alloc_disk(&lim, ctrl->numa_node);
+	if (IS_ERR(head->disk))
+		return PTR_ERR(head->disk);
 	head->disk->fops = &nvme_ns_head_ops;
 	head->disk->private_data = head;
 	sprintf(head->disk->disk_name, "nvme%dn%d",
 			ctrl->subsys->instance, head->instance);
-
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_IO_STAT, head->disk->queue);
-	/*
-	 * This assumes all controllers that refer to a namespace either
-	 * support poll queues or not.  That is not a strict guarantee,
-	 * but if the assumption is wrong the effect is only suboptimal
-	 * performance but not correctness problem.
-	 */
-	if (ctrl->tagset->nr_maps > HCTX_TYPE_POLL &&
-	    ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
-		blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
-
-	/* set to a default value of 512 until the disk is validated */
-	blk_queue_logical_block_size(head->disk->queue, 512);
-	blk_set_stacking_limits(&head->disk->queue->limits);
-	blk_queue_dma_alignment(head->disk->queue, 3);
-
-	/* we need to propagate up the VMC settings */
-	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
-		vwc = true;
-	blk_queue_write_cache(head->disk->queue, vwc, vwc);
 	return 0;
 }
 
@@ -579,9 +649,9 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 	 */
 	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		rc = device_add_disk(&head->subsys->dev, head->disk,
-				     nvme_ns_id_attr_groups);
+				     nvme_ns_attr_groups);
 		if (rc) {
-			clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
+			clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags);
 			return;
 		}
 		nvme_add_ns_head_cdev(head);
@@ -592,7 +662,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 		int node, srcu_idx;
 
 		srcu_idx = srcu_read_lock(&head->srcu);
-		for_each_node(node)
+		for_each_online_node(node)
 			__nvme_find_path(head, node);
 		srcu_read_unlock(&head->srcu, srcu_idx);
 	}
@@ -667,7 +737,7 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	 * controller is ready.
 	 */
 	if (nvme_state_is_live(ns->ana_state) &&
-	    ns->ctrl->state == NVME_CTRL_LIVE)
+	    nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
 }
 
@@ -677,6 +747,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
 	unsigned *nr_change_groups = data;
 	struct nvme_ns *ns;
+	int srcu_idx;
 
 	dev_dbg(ctrl->device, "ANA group %d: %s.\n",
 			le32_to_cpu(desc->grpid),
@@ -688,8 +759,8 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	if (!nr_nsids)
 		return 0;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		unsigned nsid;
 again:
 		nsid = le32_to_cpu(desc->nsids[n]);
@@ -702,7 +773,7 @@ again:
 		if (ns->head->ns_id > nsid)
 			goto again;
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return 0;
 }
 
@@ -748,7 +819,7 @@ static void nvme_ana_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	nvme_read_ana_log(ctrl);
@@ -796,6 +867,29 @@ static ssize_t nvme_subsys_iopolicy_show(struct device *dev,
 			  nvme_iopolicy_names[READ_ONCE(subsys->iopolicy)]);
 }
 
+static void nvme_subsys_iopolicy_update(struct nvme_subsystem *subsys,
+		int iopolicy)
+{
+	struct nvme_ctrl *ctrl;
+	int old_iopolicy = READ_ONCE(subsys->iopolicy);
+
+	if (old_iopolicy == iopolicy)
+		return;
+
+	WRITE_ONCE(subsys->iopolicy, iopolicy);
+
+	/* iopolicy changes clear the mpath by design */
+	mutex_lock(&nvme_subsystems_lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		nvme_mpath_clear_ctrl_paths(ctrl);
+	mutex_unlock(&nvme_subsystems_lock);
+
+	pr_notice("subsysnqn %s iopolicy changed from %s to %s\n",
+			subsys->subnqn,
+			nvme_iopolicy_names[old_iopolicy],
+			nvme_iopolicy_names[iopolicy]);
+}
+
 static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
@@ -805,7 +899,7 @@ static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
 
 	for (i = 0; i < ARRAY_SIZE(nvme_iopolicy_names); i++) {
 		if (sysfs_streq(buf, nvme_iopolicy_names[i])) {
-			WRITE_ONCE(subsys->iopolicy, i);
+			nvme_subsys_iopolicy_update(subsys, i);
 			return count;
 		}
 	}
@@ -868,9 +962,6 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid)
 		nvme_mpath_set_live(ns);
 	}
 
-	if (blk_queue_stable_writes(ns->queue) && ns->head->disk)
-		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
-				   ns->head->disk->queue);
 #ifdef CONFIG_BLK_DEV_ZONED
 	if (blk_queue_is_zoned(ns->queue) && ns->head->disk)
 		ns->head->disk->nr_zones = ns->disk->nr_zones;
@@ -881,11 +972,16 @@ void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	kblockd_schedule_work(&head->requeue_work);
-	if (test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
+	if (test_and_clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		nvme_cdev_del(&head->cdev, &head->cdev_device);
 		del_gendisk(head->disk);
 	}
+	/*
+	 * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared
+	 * to allow multipath to fail all I/O.
+	 */
+	synchronize_srcu(&head->srcu);
+	kblockd_schedule_work(&head->requeue_work);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
@@ -916,6 +1012,9 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	    !(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA))
 		return 0;
 
+	/* initialize this in the identify path to cover controller resets */
+	atomic_set(&ctrl->nr_active, 0);
+
 	if (!ctrl->max_namespaces ||
 	    ctrl->max_namespaces > le32_to_cpu(id->nn)) {
 		dev_err(ctrl->device,