nvme fixes for Linux 6.9

- Atomic queue limits fixes (Christoph)
  - Fabrics fixes (Hannes, Daniel)
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE3Fbyvv+648XNRdHTPe3zGtjzRgkFAmYOzugACgkQPe3zGtjz
 RglXXw/+NxnIgIP14ZZ0rrg6PoAR7U7RigMvfsqo0oQVK8c889TnzjaTbdJ2dmaV
 7Vo3BfX7Uf7o0e98OwE04CfXNs3VZKd6Q9NCbc4kpNwa5fGSwNx6PcCnYQzPuwZd
 6Irboiozzaq46YTkOWWiGYhAxs22PDOnruX7aPGCwZiGHNAKAnuXfPOL5Oq0G2jX
 1GbEXfgLHQ/bTGNE3Qx1UjaTSbc6sFIKYg1NuWtGGu4HaR5AkGqhR4vuLsBic1cv
 xiwDVTaFTzyXXWq6Hjwti/q7y/OGOaGdP6dHbASCGMmZJfrayZkzEwTejHblS5gp
 h/u2fRBcGCpJ2+nExnUSztrcyfbqnG5MPT4X62eU6KNKjvyo2hXAs4lF2Dl+Ho61
 gzCtyHNPsR1cDU7Y2EPlN0d4ZezZ4DqBQT+1xx60O7/JGyYvyQ36cvRPNKE6Nsc0
 siWLAWPFVPV6RU9trDFAeINLB50fOmHJQR5yWHMs29RLde/LmY9/WeP4Ka/FCbbl
 7qVehD4yqJTTvEZgluD1PvOVaJCPXPKwNhQTatqV8m1PiekFEuA3K5OGZid/VcT9
 RkIQH8HRyACxrcP+oVYXrdiCIqVpE3akT0HXVcmE0Rx1A/vM52qnDS0CZhJFg1SQ
 OKdPGSIfKxFxkCXzl1d2Gx1iIOAeTUhNcNXlSZzEVwa9XSvB0fs=
 =ZgYG
 -----END PGP SIGNATURE-----

Merge tag 'nvme-6.9-2024-04-04' of git://git.infradead.org/nvme into block-6.9

Pull NVMe fixes from Keith:

"nvme fixes for Linux 6.9

 - Atomic queue limits fixes (Christoph)
 - Fabrics fixes (Hannes, Daniel)"

* tag 'nvme-6.9-2024-04-04' of git://git.infradead.org/nvme:
  nvme-fc: rename free_ctrl callback to match name pattern
  nvmet-fc: move RCU read lock to nvmet_fc_assoc_exists
  nvmet: implement unique discovery NQN
  nvme: don't create a multipath node for zero capacity devices
  nvme: split nvme_update_zone_info
  nvme-multipath: don't inherit LBA-related fields for the multipath node

drivers/nvme/host/core.c

@@ -2076,6 +2076,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT;
 	struct queue_limits lim;
 	struct nvme_id_ns_nvm *nvm = NULL;
+	struct nvme_zone_info zi = {};
 	struct nvme_id_ns *id;
 	sector_t capacity;
 	unsigned lbaf;
@@ -2088,9 +2089,10 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (id->ncap == 0) {
 		/* namespace not allocated or attached */
 		info->is_removed = true;
-		ret = -ENODEV;
+		ret = -ENXIO;
 		goto out;
 	}
+	lbaf = nvme_lbaf_index(id->flbas);
 
 	if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) {
 		ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm);
@@ -2098,8 +2100,14 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 			goto out;
 	}
 
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+	    ns->head->ids.csi == NVME_CSI_ZNS) {
+		ret = nvme_query_zone_info(ns, lbaf, &zi);
+		if (ret < 0)
+			goto out;
+	}
+
 	blk_mq_freeze_queue(ns->disk->queue);
-	lbaf = nvme_lbaf_index(id->flbas);
 	ns->head->lba_shift = id->lbaf[lbaf].ds;
 	ns->head->nuse = le64_to_cpu(id->nuse);
 	capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze));
@@ -2112,13 +2120,8 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		capacity = 0;
 	nvme_config_discard(ns, &lim);
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-	    ns->head->ids.csi == NVME_CSI_ZNS) {
-		ret = nvme_update_zone_info(ns, lbaf, &lim);
-		if (ret) {
-			blk_mq_unfreeze_queue(ns->disk->queue);
-			goto out;
-		}
-	}
+	    ns->head->ids.csi == NVME_CSI_ZNS)
+		nvme_update_zone_info(ns, &lim, &zi);
 	ret = queue_limits_commit_update(ns->disk->queue, &lim);
 	if (ret) {
 		blk_mq_unfreeze_queue(ns->disk->queue);
@@ -2201,6 +2204,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 	}
 
 	if (!ret && nvme_ns_head_multipath(ns->head)) {
+		struct queue_limits *ns_lim = &ns->disk->queue->limits;
 		struct queue_limits lim;
 
 		blk_mq_freeze_queue(ns->head->disk->queue);
@@ -2212,7 +2216,26 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
 		nvme_mpath_revalidate_paths(ns);
 
+		/*
+		 * queue_limits mixes values that are the hardware limitations
+		 * for bio splitting with what is the device configuration.
+		 *
+		 * For NVMe the device configuration can change after e.g. a
+		 * Format command, and we really want to pick up the new format
+		 * value here.  But we must still stack the queue limits to the
+		 * least common denominator for multipathing to split the bios
+		 * properly.
+		 *
+		 * To work around this, we explicitly set the device
+		 * configuration to those that we just queried, but only stack
+		 * the splitting limits in to make sure we still obey possibly
+		 * lower limitations of other controllers.
+		 */
 		lim = queue_limits_start_update(ns->head->disk->queue);
+		lim.logical_block_size = ns_lim->logical_block_size;
+		lim.physical_block_size = ns_lim->physical_block_size;
+		lim.io_min = ns_lim->io_min;
+		lim.io_opt = ns_lim->io_opt;
 		queue_limits_stack_bdev(&lim, ns->disk->part0, 0,
 					ns->head->disk->disk_name);
 		ret = queue_limits_commit_update(ns->head->disk->queue, &lim);

drivers/nvme/host/fc.c

@@ -2428,7 +2428,7 @@ nvme_fc_ctrl_get(struct nvme_fc_ctrl *ctrl)
  * controller. Called after last nvme_put_ctrl() call
  */
 static void
-nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl)
+nvme_fc_free_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 
@@ -3384,7 +3384,7 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
-	.free_ctrl		= nvme_fc_nvme_ctrl_freed,
+	.free_ctrl		= nvme_fc_free_ctrl,
 	.submit_async_event	= nvme_fc_submit_async_event,
 	.delete_ctrl		= nvme_fc_delete_ctrl,
 	.get_address		= nvmf_get_address,

drivers/nvme/host/nvme.h

@@ -1036,10 +1036,18 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
+struct nvme_zone_info {
+	u64 zone_size;
+	unsigned int max_open_zones;
+	unsigned int max_active_zones;
+};
+
 int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
-		struct queue_limits *lim);
+int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf,
+		struct nvme_zone_info *zi);
+void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
+		struct nvme_zone_info *zi);
 #ifdef CONFIG_BLK_DEV_ZONED
 blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
 				       struct nvme_command *cmnd,

drivers/nvme/host/zns.c

@@ -35,8 +35,8 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 	return 0;
 }
 
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
-		struct queue_limits *lim)
+int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf,
+		struct nvme_zone_info *zi)
 {
 	struct nvme_effects_log *log = ns->head->effects;
 	struct nvme_command c = { };
@@ -89,27 +89,34 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
 		goto free_data;
 	}
 
-	ns->head->zsze =
-		nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze));
-	if (!is_power_of_2(ns->head->zsze)) {
+	zi->zone_size = le64_to_cpu(id->lbafe[lbaf].zsze);
+	if (!is_power_of_2(zi->zone_size)) {
 		dev_warn(ns->ctrl->device,
-			"invalid zone size:%llu for namespace:%u\n",
-			ns->head->zsze, ns->head->ns_id);
+			"invalid zone size: %llu for namespace: %u\n",
+			zi->zone_size, ns->head->ns_id);
 		status = -ENODEV;
 		goto free_data;
 	}
+	zi->max_open_zones = le32_to_cpu(id->mor) + 1;
+	zi->max_active_zones = le32_to_cpu(id->mar) + 1;
 
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
-	lim->zoned = 1;
-	lim->max_open_zones = le32_to_cpu(id->mor) + 1;
-	lim->max_active_zones = le32_to_cpu(id->mar) + 1;
-	lim->chunk_sectors = ns->head->zsze;
-	lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
 free_data:
 	kfree(id);
 	return status;
 }
 
+void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
+		struct nvme_zone_info *zi)
+{
+	lim->zoned = 1;
+	lim->max_open_zones = zi->max_open_zones;
+	lim->max_active_zones = zi->max_active_zones;
+	lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
+	lim->chunk_sectors = ns->head->zsze =
+		nvme_lba_to_sect(ns->head, zi->zone_size);
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
+}
+
 static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 					  unsigned int nr_zones, size_t *buflen)
 {

drivers/nvme/target/configfs.c

@@ -1613,6 +1613,11 @@ static struct config_group *nvmet_subsys_make(struct config_group *group,
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (sysfs_streq(name, nvmet_disc_subsys->subsysnqn)) {
+		pr_err("can't create subsystem using unique discovery NQN\n");
+		return ERR_PTR(-EINVAL);
+	}
+
 	subsys = nvmet_subsys_alloc(name, NVME_NQN_NVME);
 	if (IS_ERR(subsys))
 		return ERR_CAST(subsys);
@@ -2159,7 +2164,49 @@ static const struct config_item_type nvmet_hosts_type = {
 
 static struct config_group nvmet_hosts_group;
 
+static ssize_t nvmet_root_discovery_nqn_show(struct config_item *item,
+					     char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%s\n", nvmet_disc_subsys->subsysnqn);
+}
+
+static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct list_head *entry;
+	size_t len;
+
+	len = strcspn(page, "\n");
+	if (!len || len > NVMF_NQN_FIELD_LEN - 1)
+		return -EINVAL;
+
+	down_write(&nvmet_config_sem);
+	list_for_each(entry, &nvmet_subsystems_group.cg_children) {
+		struct config_item *item =
+			container_of(entry, struct config_item, ci_entry);
+
+		if (!strncmp(config_item_name(item), page, len)) {
+			pr_err("duplicate NQN %s\n", config_item_name(item));
+			up_write(&nvmet_config_sem);
+			return -EINVAL;
+		}
+	}
+	memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN);
+	memcpy(nvmet_disc_subsys->subsysnqn, page, len);
+	up_write(&nvmet_config_sem);
+
+	return len;
+}
+
+CONFIGFS_ATTR(nvmet_root_, discovery_nqn);
+
+static struct configfs_attribute *nvmet_root_attrs[] = {
+	&nvmet_root_attr_discovery_nqn,
+	NULL,
+};
+
 static const struct config_item_type nvmet_root_type = {
+	.ct_attrs		= nvmet_root_attrs,
 	.ct_owner		= THIS_MODULE,
 };
 

drivers/nvme/target/core.c

@@ -1541,6 +1541,13 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 	}
 
 	down_read(&nvmet_config_sem);
+	if (!strncmp(nvmet_disc_subsys->subsysnqn, subsysnqn,
+				NVMF_NQN_SIZE)) {
+		if (kref_get_unless_zero(&nvmet_disc_subsys->ref)) {
+			up_read(&nvmet_config_sem);
+			return nvmet_disc_subsys;
+		}
+	}
 	list_for_each_entry(p, &port->subsystems, entry) {
 		if (!strncmp(p->subsys->subsysnqn, subsysnqn,
 				NVMF_NQN_SIZE)) {

drivers/nvme/target/fc.c

@@ -1115,16 +1115,21 @@ nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
 }
 
 static bool
-nvmet_fc_assoc_exits(struct nvmet_fc_tgtport *tgtport, u64 association_id)
+nvmet_fc_assoc_exists(struct nvmet_fc_tgtport *tgtport, u64 association_id)
 {
 	struct nvmet_fc_tgt_assoc *a;
+	bool found = false;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(a, &tgtport->assoc_list, a_list) {
-		if (association_id == a->association_id)
-			return true;
+		if (association_id == a->association_id) {
+			found = true;
+			break;
+		}
 	}
+	rcu_read_unlock();
 
-	return false;
+	return found;
 }
 
 static struct nvmet_fc_tgt_assoc *
@@ -1164,13 +1169,11 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 		ran = ran << BYTES_FOR_QID_SHIFT;
 
 		spin_lock_irqsave(&tgtport->lock, flags);
-		rcu_read_lock();
-		if (!nvmet_fc_assoc_exits(tgtport, ran)) {
+		if (!nvmet_fc_assoc_exists(tgtport, ran)) {
 			assoc->association_id = ran;
 			list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list);
 			done = true;
 		}
-		rcu_read_unlock();
 		spin_unlock_irqrestore(&tgtport->lock, flags);
 	} while (!done);