Merge tag 'nvme-5.18-2022-03-29' of git://git.infradead.org/nvme into for-5.18/drivers

Pull NVMe fixes from Christoph:

"- fix multipath hang when disk goes live over reconnect (Anton Eidelman)
 - fix RCU hole that allowed for endless looping in multipath round robin
   (Chris Leech)
 - remove redundant assignment after left shift (Colin Ian King)
 - add quirks for Samsung X5 SSDs (Monish Kumar R)
 - fix the read-only state for zoned namespaces with unsupposed features
   (Pankaj Raghav)
 - use a private workqueue instead of the system workqueue in nvmet
   (Sagi Grimberg)
 - allow duplicate NSIDs for private namespaces (Sungup Moon)
 - expose use_threaded_interrupts read-only in sysfs (Xin Hao)"

* tag 'nvme-5.18-2022-03-29' of git://git.infradead.org/nvme:
  nvme-multipath: fix hang when disk goes live over reconnect
  nvme: fix RCU hole that allowed for endless looping in multipath round robin
  nvme: allow duplicate NSIDs for private namespaces
  nvmet: remove redundant assignment after left shift
  nvmet: use a private workqueue instead of the system workqueue
  nvme-pci: add quirks for Samsung X5 SSDs
  nvme-pci: expose use_threaded_interrupts read-only in sysfs
  nvme: fix the read-only state for zoned namespaces with unsupposed features

Author: axboe

drivers/nvme/host/core.c

@@ -1867,9 +1867,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	nvme_config_discard(disk, ns);
 	blk_queue_max_write_zeroes_sectors(disk->queue,
 					   ns->ctrl->max_zeroes_sectors);
-
-	set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) ||
-		test_bit(NVME_NS_FORCE_RO, &ns->flags));
 }
 
 static inline bool nvme_first_scan(struct gendisk *disk)
@@ -1930,6 +1927,8 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 			goto out_unfreeze;
 	}
 
+	set_disk_ro(ns->disk, (id->nsattr & NVME_NS_ATTR_RO) ||
+		test_bit(NVME_NS_FORCE_RO, &ns->flags));
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
@@ -1942,6 +1941,9 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 	if (nvme_ns_head_multipath(ns->head)) {
 		blk_mq_freeze_queue(ns->head->disk->queue);
 		nvme_update_disk_info(ns->head->disk, ns, id);
+		set_disk_ro(ns->head->disk,
+			    (id->nsattr & NVME_NS_ATTR_RO) ||
+				    test_bit(NVME_NS_FORCE_RO, &ns->flags));
 		nvme_mpath_revalidate_paths(ns);
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
@@ -3625,15 +3627,20 @@ static const struct attribute_group *nvme_dev_attr_groups[] = {
 	NULL,
 };
 
-static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
+static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl,
 		unsigned nsid)
 {
 	struct nvme_ns_head *h;
 
-	lockdep_assert_held(&subsys->lock);
+	lockdep_assert_held(&ctrl->subsys->lock);
 
-	list_for_each_entry(h, &subsys->nsheads, entry) {
-		if (h->ns_id != nsid)
+	list_for_each_entry(h, &ctrl->subsys->nsheads, entry) {
+		/*
+		 * Private namespaces can share NSIDs under some conditions.
+		 * In that case we can't use the same ns_head for namespaces
+		 * with the same NSID.
+		 */
+		if (h->ns_id != nsid || !nvme_is_unique_nsid(ctrl, h))
 			continue;
 		if (!list_empty(&h->list) && nvme_tryget_ns_head(h))
 			return h;
@@ -3827,7 +3834,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 	}
 
 	mutex_lock(&ctrl->subsys->lock);
-	head = nvme_find_ns_head(ctrl->subsys, nsid);
+	head = nvme_find_ns_head(ctrl, nsid);
 	if (!head) {
 		ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, ids);
 		if (ret) {
@@ -4024,6 +4031,16 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	set_capacity(ns->disk, 0);
 	nvme_fault_inject_fini(&ns->fault_inject);
 
+	/*
+	 * Ensure that !NVME_NS_READY is seen by other threads to prevent
+	 * this ns going back into current_path.
+	 */
+	synchronize_srcu(&ns->head->srcu);
+
+	/* wait for concurrent submissions */
+	if (nvme_mpath_clear_current_path(ns))
+		synchronize_srcu(&ns->head->srcu);
+
 	mutex_lock(&ns->ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
 	if (list_empty(&ns->head->list)) {
@@ -4035,10 +4052,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	/* guarantee not available in head->list */
 	synchronize_rcu();
 
-	/* wait for concurrent submissions */
-	if (nvme_mpath_clear_current_path(ns))
-		synchronize_srcu(&ns->head->srcu);
-
 	if (!nvme_ns_head_multipath(ns->head))
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
 	del_gendisk(ns->disk);
@@ -4509,6 +4522,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 	if (ctrl->queue_count > 1) {
 		nvme_queue_scan(ctrl);
 		nvme_start_queues(ctrl);
+		nvme_mpath_update(ctrl);
 	}
 
 	nvme_change_uevent(ctrl, "NVME_EVENT=connected");

drivers/nvme/host/multipath.c

@@ -482,10 +482,11 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 
 	/*
 	 * Add a multipath node if the subsystems supports multiple controllers.
-	 * We also do this for private namespaces as the namespace sharing data could
-	 * change after a rescan.
+	 * We also do this for private namespaces as the namespace sharing flag
+	 * could change after a rescan.
 	 */
-	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath)
+	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
+	    !nvme_is_unique_nsid(ctrl, head) || !multipath)
 		return 0;
 
 	head->disk = blk_alloc_disk(ctrl->numa_node);
@@ -612,8 +613,17 @@ 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);
 }
 
@@ -700,6 +710,18 @@ 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);

drivers/nvme/host/nvme.h

@@ -722,6 +722,25 @@ static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		return queue_live;
 	return __nvme_check_ready(ctrl, rq, queue_live);
 }
+
+/*
+ * NSID shall be unique for all shared namespaces, or if at least one of the
+ * following conditions is met:
+ *   1. Namespace Management is supported by the controller
+ *   2. ANA is supported by the controller
+ *   3. NVM Set are supported by the controller
+ *
+ * In other case, private namespace are not required to report a unique NSID.
+ */
+static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl,
+		struct nvme_ns_head *head)
+{
+	return head->shared ||
+		(ctrl->oacs & NVME_CTRL_OACS_NS_MNGT_SUPP) ||
+		(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA) ||
+		(ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS);
+}
+
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
@@ -781,6 +800,7 @@ 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_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
 void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl);
+void nvme_mpath_update(struct nvme_ctrl *ctrl);
 void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
@@ -852,6 +872,9 @@ static inline int nvme_mpath_init_identify(struct nvme_ctrl *ctrl,
 "Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n");
 	return 0;
 }
+static inline void nvme_mpath_update(struct nvme_ctrl *ctrl)
+{
+}
 static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 {
 }

drivers/nvme/host/pci.c

@@ -44,7 +44,7 @@
 #define NVME_MAX_SEGS	127
 
 static int use_threaded_interrupts;
-module_param(use_threaded_interrupts, int, 0);
+module_param(use_threaded_interrupts, int, 0444);
 
 static bool use_cmb_sqes = true;
 module_param(use_cmb_sqes, bool, 0444);
@@ -3466,7 +3466,10 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_128_BYTES_SQES |
 				NVME_QUIRK_SHARED_TAGS |
 				NVME_QUIRK_SKIP_CID_GEN },
-
+	{ PCI_DEVICE(0x144d, 0xa808),   /* Samsung X5 */
+		.driver_data =  NVME_QUIRK_DELAY_BEFORE_CHK_RDY|
+				NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ 0, }
 };

drivers/nvme/target/admin-cmd.c

@@ -988,7 +988,7 @@ void nvmet_execute_async_event(struct nvmet_req *req)
 	ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req;
 	mutex_unlock(&ctrl->lock);
 
-	schedule_work(&ctrl->async_event_work);
+	queue_work(nvmet_wq, &ctrl->async_event_work);
 }
 
 void nvmet_execute_keep_alive(struct nvmet_req *req)

drivers/nvme/target/configfs.c

@@ -1593,7 +1593,7 @@ static void nvmet_port_release(struct config_item *item)
 	struct nvmet_port *port = to_nvmet_port(item);
 
 	/* Let inflight controllers teardown complete */
-	flush_scheduled_work();
+	flush_workqueue(nvmet_wq);
 	list_del(&port->global_entry);
 
 	kfree(port->ana_state);

drivers/nvme/target/core.c

@@ -20,6 +20,9 @@ struct workqueue_struct *zbd_wq;
 static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
 static DEFINE_IDA(cntlid_ida);
 
+struct workqueue_struct *nvmet_wq;
+EXPORT_SYMBOL_GPL(nvmet_wq);
+
 /*
  * This read/write semaphore is used to synchronize access to configuration
  * information on a target system that will result in discovery log page
@@ -205,7 +208,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 	list_add_tail(&aen->entry, &ctrl->async_events);
 	mutex_unlock(&ctrl->lock);
 
-	schedule_work(&ctrl->async_event_work);
+	queue_work(nvmet_wq, &ctrl->async_event_work);
 }
 
 static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
@@ -385,7 +388,7 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 	if (reset_tbkas) {
 		pr_debug("ctrl %d reschedule traffic based keep-alive timer\n",
 			ctrl->cntlid);
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvmet_wq, &ctrl->ka_work, ctrl->kato * HZ);
 		return;
 	}
 
@@ -403,7 +406,7 @@ void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
-	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+	queue_delayed_work(nvmet_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
@@ -1120,7 +1123,7 @@ static inline u8 nvmet_cc_iocqes(u32 cc)
 
 static inline bool nvmet_css_supported(u8 cc_css)
 {
-	switch (cc_css <<= NVME_CC_CSS_SHIFT) {
+	switch (cc_css << NVME_CC_CSS_SHIFT) {
 	case NVME_CC_CSS_NVM:
 	case NVME_CC_CSS_CSI:
 		return true;
@@ -1478,7 +1481,7 @@ void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl)
 	mutex_lock(&ctrl->lock);
 	if (!(ctrl->csts & NVME_CSTS_CFS)) {
 		ctrl->csts |= NVME_CSTS_CFS;
-		schedule_work(&ctrl->fatal_err_work);
+		queue_work(nvmet_wq, &ctrl->fatal_err_work);
 	}
 	mutex_unlock(&ctrl->lock);
 }
@@ -1620,9 +1623,15 @@ static int __init nvmet_init(void)
 		goto out_free_zbd_work_queue;
 	}
 
+	nvmet_wq = alloc_workqueue("nvmet-wq", WQ_MEM_RECLAIM, 0);
+	if (!nvmet_wq) {
+		error = -ENOMEM;
+		goto out_free_buffered_work_queue;
+	}
+
 	error = nvmet_init_discovery();
 	if (error)
-		goto out_free_work_queue;
+		goto out_free_nvmet_work_queue;
 
 	error = nvmet_init_configfs();
 	if (error)
@@ -1631,7 +1640,9 @@ static int __init nvmet_init(void)
 
 out_exit_discovery:
 	nvmet_exit_discovery();
-out_free_work_queue:
+out_free_nvmet_work_queue:
+	destroy_workqueue(nvmet_wq);
+out_free_buffered_work_queue:
 	destroy_workqueue(buffered_io_wq);
 out_free_zbd_work_queue:
 	destroy_workqueue(zbd_wq);
@@ -1643,6 +1654,7 @@ static void __exit nvmet_exit(void)
 	nvmet_exit_configfs();
 	nvmet_exit_discovery();
 	ida_destroy(&cntlid_ida);
+	destroy_workqueue(nvmet_wq);
 	destroy_workqueue(buffered_io_wq);
 	destroy_workqueue(zbd_wq);
 

drivers/nvme/target/fc.c

@@ -1491,7 +1491,7 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport)
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
-		if (!schedule_work(&assoc->del_work))
+		if (!queue_work(nvmet_wq, &assoc->del_work))
 			/* already deleting - release local reference */
 			nvmet_fc_tgt_a_put(assoc);
 	}
@@ -1546,7 +1546,7 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port,
 			continue;
 		assoc->hostport->invalid = 1;
 		noassoc = false;
-		if (!schedule_work(&assoc->del_work))
+		if (!queue_work(nvmet_wq, &assoc->del_work))
 			/* already deleting - release local reference */
 			nvmet_fc_tgt_a_put(assoc);
 	}
@@ -1592,7 +1592,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 		nvmet_fc_tgtport_put(tgtport);
 
 		if (found_ctrl) {
-			if (!schedule_work(&assoc->del_work))
+			if (!queue_work(nvmet_wq, &assoc->del_work))
 				/* already deleting - release local reference */
 				nvmet_fc_tgt_a_put(assoc);
 			return;
@@ -2060,7 +2060,7 @@ nvmet_fc_rcv_ls_req(struct nvmet_fc_target_port *target_port,
 	iod->rqstdatalen = lsreqbuf_len;
 	iod->hosthandle = hosthandle;
 
-	schedule_work(&iod->work);
+	queue_work(nvmet_wq, &iod->work);
 
 	return 0;
 }