1 files changed, 75 insertions, 41 deletions

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 3968f89f7855..811f7b96b551 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -156,13 +156,12 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
-	mutex_lock(&ctrl->scan_lock);
 	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		if (nvme_mpath_clear_current_path(ns))
-			kblockd_schedule_work(&ns->head->requeue_work);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		nvme_mpath_clear_current_path(ns);
+		kblockd_schedule_work(&ns->head->requeue_work);
+	}
 	up_read(&ctrl->namespaces_rwsem);
-	mutex_unlock(&ctrl->scan_lock);
 }
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
@@ -233,7 +232,7 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 	}
 
 	for (ns = nvme_next_ns(head, old);
-	     ns != old;
+	     ns && ns != old;
 	     ns = nvme_next_ns(head, ns)) {
 		if (nvme_path_is_disabled(ns))
 			continue;
@@ -330,7 +329,7 @@ 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 = generic_make_request(bio);
 	} else if (nvme_available_path(head)) {
 		dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
 
@@ -459,8 +458,14 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
 
 	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);
+		u32 nr_nsids;
+		size_t nsid_buf_size;
+
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
+			return -EINVAL;
+
+		nr_nsids = le32_to_cpu(desc->nnsids);
+		nsid_buf_size = nr_nsids * sizeof(__le32);
 
 		if (WARN_ON_ONCE(desc->grpid == 0))
 			return -EINVAL;
@@ -480,8 +485,6 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
 			return error;
 
 		offset += nsid_buf_size;
-		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
-			return -EINVAL;
 	}
 
 	return 0;
@@ -498,8 +501,17 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	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() will trigger I/O to the multipath path device
+	 * and in turn to this path device.  However we cannot accept this I/O
+	 * if the controller is not live.  This may deadlock if called from
+	 * nvme_mpath_init_identify() and the ctrl will never complete
+	 * initialization, preventing I/O from completing.  For this case we
+	 * will reprocess the ANA log page in nvme_mpath_update() once the
+	 * controller is ready.
+	 */
+	if (nvme_state_is_live(ns->ana_state) &&
+	    ns->ctrl->state == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
 }
 
@@ -522,14 +534,17 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		unsigned nsid = le32_to_cpu(desc->nsids[n]);
-
+		unsigned nsid;
+again:
+		nsid = le32_to_cpu(desc->nsids[n]);
 		if (ns->head->ns_id < nsid)
 			continue;
 		if (ns->head->ns_id == nsid)
 			nvme_update_ns_ana_state(desc, ns);
 		if (++n == nr_nsids)
 			break;
+		if (ns->head->ns_id > nsid)
+			goto again;
 	}
 	up_read(&ctrl->namespaces_rwsem);
 	return 0;
@@ -580,6 +595,18 @@ static void nvme_ana_work(struct work_struct *work)
 	nvme_read_ana_log(ctrl);
 }
 
+void nvme_mpath_update(struct nvme_ctrl *ctrl)
+{
+	u32 nr_change_groups = 0;
+
+	if (!ctrl->ana_log_buf)
+		return;
+
+	mutex_lock(&ctrl->ana_lock);
+	nvme_parse_ana_log(ctrl, &nr_change_groups, nvme_update_ana_state);
+	mutex_unlock(&ctrl->ana_lock);
+}
+
 static void nvme_anatt_timeout(struct timer_list *t)
 {
 	struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
@@ -677,6 +704,10 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 		if (desc.state) {
 			/* found the group desc: update */
 			nvme_update_ns_ana_state(&desc, ns);
+		} else {
+			/* group desc not found: trigger a re-read */
+			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+			queue_work(nvme_wq, &ns->ctrl->ana_work);
 		}
 	} else {
 		ns->ana_state = NVME_ANA_OPTIMIZED; 
@@ -714,9 +745,18 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	put_disk(head->disk);
 }
 
-int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl)
 {
-	int error;
+	mutex_init(&ctrl->ana_lock);
+	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
+	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+}
+
+int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	size_t max_transfer_size = ctrl->max_hw_sectors << SECTOR_SHIFT;
+	size_t ana_log_size;
+	int error = 0;
 
 	/* check if multipath is enabled and we have the capability */
 	if (!multipath || !ctrl->subsys || !(ctrl->subsys->cmic & (1 << 3)))
@@ -727,37 +767,31 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	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);
-	ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
-
-	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
+	ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
+		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc) +
+		ctrl->max_namespaces * sizeof(__le32);
+	if (ana_log_size > max_transfer_size) {
 		dev_err(ctrl->device,
-			"ANA log page size (%zd) larger than MDTS (%d).\n",
-			ctrl->ana_log_size,
-			ctrl->max_hw_sectors << SECTOR_SHIFT);
+			"ANA log page size (%zd) larger than MDTS (%zd).\n",
+			ana_log_size, max_transfer_size);
 		dev_err(ctrl->device, "disabling ANA support.\n");
-		return 0;
+		goto out_uninit;
 	}
-
-	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
-	kfree(ctrl->ana_log_buf);
-	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
-	if (!ctrl->ana_log_buf) {
-		error = -ENOMEM;
-		goto out;
+	if (ana_log_size > ctrl->ana_log_size) {
+		nvme_mpath_stop(ctrl);
+		kfree(ctrl->ana_log_buf);
+		ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL);
+		if (!ctrl->ana_log_buf)
+			return -ENOMEM;
 	}
-
+	ctrl->ana_log_size = ana_log_size;
 	error = nvme_read_ana_log(ctrl);
 	if (error)
-		goto out_free_ana_log_buf;
+		goto out_uninit;
 	return 0;
-out_free_ana_log_buf:
-	kfree(ctrl->ana_log_buf);
-	ctrl->ana_log_buf = NULL;
-out:
+
+out_uninit:
+	nvme_mpath_uninit(ctrl);
 	return error;
 }