1 files changed, 70 insertions, 38 deletions

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index da78e499947a..3ded54d2c9c6 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -167,9 +167,18 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
-	return ns->ctrl->state != NVME_CTRL_LIVE ||
-		test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
-		test_bit(NVME_NS_REMOVING, &ns->flags);
+	/*
+	 * 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)
+		return true;
+	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
+	    test_bit(NVME_NS_REMOVING, &ns->flags))
+		return true;
+	return false;
 }
 
 static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
@@ -246,6 +255,12 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 			fallback = ns;
 	}
 
+	/* No optimized path found, re-check the current path */
+	if (!nvme_path_is_disabled(old) &&
+	    old->ana_state == NVME_ANA_OPTIMIZED) {
+		found = old;
+		goto out;
+	}
 	if (!fallback)
 		return NULL;
 	found = fallback;
@@ -266,10 +281,13 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 	struct nvme_ns *ns;
 
 	ns = srcu_dereference(head->current_path[node], &head->srcu);
-	if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR && ns)
-		ns = nvme_round_robin_path(head, node, ns);
-	if (unlikely(!ns || !nvme_path_is_optimized(ns)))
-		ns = __nvme_find_path(head, node);
+	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;
 }
 
@@ -291,8 +309,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	return false;
 }
 
-static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
-		struct bio *bio)
+blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 {
 	struct nvme_ns_head *head = bio->bi_disk->private_data;
 	struct device *dev = disk_to_dev(head->disk);
@@ -301,12 +318,11 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 	int srcu_idx;
 
 	/*
-	 * The namespace might be going away and the bio might
-	 * be moved to a different queue via blk_steal_bios(),
-	 * so we need to use the bio_split pool from the original
-	 * queue to allocate the bvecs from.
+	 * The namespace might be going away and the bio might be moved to a
+	 * different queue via blk_steal_bios(), so we need to use the bio_split
+	 * pool from the original queue to allocate the bvecs from.
 	 */
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);
@@ -316,7 +332,7 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 		trace_block_bio_remap(bio->bi_disk->queue, bio,
 				      disk_devt(ns->head->disk),
 				      bio->bi_iter.bi_sector);
-		ret = direct_make_request(bio);
+		ret = submit_bio_noacct(bio);
 	} else if (nvme_available_path(head)) {
 		dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
 
@@ -353,7 +369,7 @@ static void nvme_requeue_work(struct work_struct *work)
 		 * path.
 		 */
 		bio->bi_disk = head->disk;
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	}
 }
 
@@ -375,7 +391,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath)
 		return 0;
 
-	q = blk_alloc_queue(nvme_ns_head_make_request, ctrl->numa_node);
+	q = blk_alloc_queue(ctrl->numa_node);
 	if (!q)
 		goto out;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
@@ -409,15 +425,14 @@ 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;
 
-	if (!(head->disk->flags & GENHD_FL_UP))
+	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
 		device_add_disk(&head->subsys->dev, head->disk,
 				nvme_ns_id_attr_groups);
 
+	mutex_lock(&head->lock);
 	if (nvme_path_is_optimized(ns)) {
 		int node, srcu_idx;
 
@@ -426,9 +441,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 			__nvme_find_path(head, node);
 		srcu_read_unlock(&head->srcu, srcu_idx);
 	}
+	mutex_unlock(&head->lock);
 
-	synchronize_srcu(&ns->head->srcu);
-	kblockd_schedule_work(&ns->head->requeue_work);
+	synchronize_srcu(&head->srcu);
+	kblockd_schedule_work(&head->requeue_work);
 }
 
 static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
@@ -483,14 +499,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state)
 static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 		struct nvme_ns *ns)
 {
-	mutex_lock(&ns->head->lock);
 	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_mpath_set_live(ns);
-	mutex_unlock(&ns->head->lock);
 }
 
 static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
@@ -531,7 +545,7 @@ static int nvme_read_ana_log(struct nvme_ctrl *ctrl)
 	int error;
 
 	mutex_lock(&ctrl->ana_lock);
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0,
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0, NVME_CSI_NVM,
 			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
 	if (error) {
 		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
@@ -567,6 +581,9 @@ 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)
+		return;
+
 	nvme_read_ana_log(ctrl);
 }
 
@@ -640,38 +657,45 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
 }
 DEVICE_ATTR_RO(ana_state);
 
-static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
+static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl,
 		struct nvme_ana_group_desc *desc, void *data)
 {
-	struct nvme_ns *ns = data;
+	struct nvme_ana_group_desc *dst = 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 */
-	}
+	if (desc->grpid != dst->grpid)
+		return 0;
 
-	return 0;
+	*dst = *desc;
+	return -ENXIO; /* just break out of the loop */
 }
 
 void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	if (nvme_ctrl_use_ana(ns->ctrl)) {
+		struct nvme_ana_group_desc desc = {
+			.grpid = id->anagrpid,
+			.state = 0,
+		};
+
 		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);
+		nvme_parse_ana_log(ns->ctrl, &desc, nvme_lookup_ana_group_desc);
 		mutex_unlock(&ns->ctrl->ana_lock);
+		if (desc.state) {
+			/* found the group desc: update */
+			nvme_update_ns_ana_state(&desc, ns);
+		}
 	} else {
-		mutex_lock(&ns->head->lock);
 		ns->ana_state = NVME_ANA_OPTIMIZED; 
 		nvme_mpath_set_live(ns);
-		mutex_unlock(&ns->head->lock);
 	}
 
 	if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {
-		struct backing_dev_info *info =
-					ns->head->disk->queue->backing_dev_info;
+		struct gendisk *disk = ns->head->disk;
 
-		info->capabilities |= BDI_CAP_STABLE_WRITES;
+		if (disk)
+			disk->queue->backing_dev_info->capabilities |=
+					BDI_CAP_STABLE_WRITES;
 	}
 }
 
@@ -686,6 +710,14 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	kblockd_schedule_work(&head->requeue_work);
 	flush_work(&head->requeue_work);
 	blk_cleanup_queue(head->disk->queue);
+	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
+		/*
+		 * if device_add_disk wasn't called, prevent
+		 * disk release to put a bogus reference on the
+		 * request queue
+		 */
+		head->disk->queue = NULL;
+	}
 	put_disk(head->disk);
 }