Merge branch 'nvme-5.2' of git://git.infradead.org/nvme into for-5.2/block-post

Pull NVMe fixes from Christoph

* 'nvme-5.2' of git://git.infradead.org/nvme:
  nvme: validate cntlid during controller initialisation
  nvme: change locking for the per-subsystem controller list
  nvme: trace all async notice events
  nvme: fix typos in nvme status code values
  nvme-fabrics: remove unused argument
  nvme-multipath: avoid crash on invalid subsystem cntlid enumeration
  nvme-fc: use separate work queue to avoid warning
  nvme-rdma: remove redundant reference between ib_device and tagset
  nvme-pci: mark expected switch fall-through
  nvme-pci: add known admin effects to augument admin effects log page
  nvme-pci: init shadow doorbell after each reset

drivers/nvme/host/core.c

@@ -1257,10 +1257,9 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		return 0;
 	}
 
+	effects |= nvme_known_admin_effects(opcode);
 	if (ctrl->effects)
 		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
-	else
-		effects = nvme_known_admin_effects(opcode);
 
 	/*
 	 * For simplicity, IO to all namespaces is quiesced even if the command
@@ -2342,20 +2341,35 @@ static const struct attribute_group *nvme_subsys_attrs_groups[] = {
 	NULL,
 };
 
-static int nvme_active_ctrls(struct nvme_subsystem *subsys)
+static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
+		struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 {
-	int count = 0;
-	struct nvme_ctrl *ctrl;
+	struct nvme_ctrl *tmp;
+
+	lockdep_assert_held(&nvme_subsystems_lock);
+
+	list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) {
+		if (ctrl->state == NVME_CTRL_DELETING ||
+		    ctrl->state == NVME_CTRL_DEAD)
+			continue;
 
-	mutex_lock(&subsys->lock);
-	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
-		if (ctrl->state != NVME_CTRL_DELETING &&
-		    ctrl->state != NVME_CTRL_DEAD)
-			count++;
+		if (tmp->cntlid == ctrl->cntlid) {
+			dev_err(ctrl->device,
+				"Duplicate cntlid %u with %s, rejecting\n",
+				ctrl->cntlid, dev_name(tmp->device));
+			return false;
 		}
-	mutex_unlock(&subsys->lock);
 
-	return count;
+		if ((id->cmic & (1 << 1)) ||
+		    (ctrl->opts && ctrl->opts->discovery_nqn))
+			continue;
+
+		dev_err(ctrl->device,
+			"Subsystem does not support multiple controllers\n");
+		return false;
+	}
+
+	return true;
 }
 
 static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
@@ -2395,22 +2409,13 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	mutex_lock(&nvme_subsystems_lock);
 	found = __nvme_find_get_subsystem(subsys->subnqn);
 	if (found) {
-		/*
-		 * Verify that the subsystem actually supports multiple
-		 * controllers, else bail out.
-		 */
-		if (!(ctrl->opts && ctrl->opts->discovery_nqn) &&
-		    nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
-			dev_err(ctrl->device,
-				"ignoring ctrl due to duplicate subnqn (%s).\n",
-				found->subnqn);
-			nvme_put_subsystem(found);
-			ret = -EINVAL;
-			goto out_unlock;
-		}
-
 		__nvme_release_subsystem(subsys);
 		subsys = found;
+
+		if (!nvme_validate_cntlid(subsys, ctrl, id)) {
+			ret = -EINVAL;
+			goto out_put_subsystem;
+		}
 	} else {
 		ret = device_add(&subsys->dev);
 		if (ret) {
@@ -2422,23 +2427,20 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		list_add_tail(&subsys->entry, &nvme_subsystems);
 	}
 
-	ctrl->subsys = subsys;
-	mutex_unlock(&nvme_subsystems_lock);
-
 	if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
 			dev_name(ctrl->device))) {
 		dev_err(ctrl->device,
 			"failed to create sysfs link from subsystem.\n");
-		/* the transport driver will eventually put the subsystem */
-		return -EINVAL;
+		goto out_put_subsystem;
 	}
 
-	mutex_lock(&subsys->lock);
+	ctrl->subsys = subsys;
 	list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
-	mutex_unlock(&subsys->lock);
-
+	mutex_unlock(&nvme_subsystems_lock);
 	return 0;
 
+out_put_subsystem:
+	nvme_put_subsystem(subsys);
 out_unlock:
 	mutex_unlock(&nvme_subsystems_lock);
 	put_device(&subsys->dev);
@@ -3605,19 +3607,18 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 {
 	u32 aer_notice_type = (result & 0xff00) >> 8;
 
+	trace_nvme_async_event(ctrl, aer_notice_type);
+
 	switch (aer_notice_type) {
 	case NVME_AER_NOTICE_NS_CHANGED:
-		trace_nvme_async_event(ctrl, aer_notice_type);
 		set_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events);
 		nvme_queue_scan(ctrl);
 		break;
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
-		trace_nvme_async_event(ctrl, aer_notice_type);
 		queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
 #ifdef CONFIG_NVME_MULTIPATH
 	case NVME_AER_NOTICE_ANA:
-		trace_nvme_async_event(ctrl, aer_notice_type);
 		if (!ctrl->ana_log_buf)
 			break;
 		queue_work(nvme_wq, &ctrl->ana_work);
@@ -3696,10 +3697,10 @@ static void nvme_free_ctrl(struct device *dev)
 	__free_page(ctrl->discard_page);
 
 	if (subsys) {
-		mutex_lock(&subsys->lock);
+		mutex_lock(&nvme_subsystems_lock);
 		list_del(&ctrl->subsys_entry);
-		mutex_unlock(&subsys->lock);
 		sysfs_remove_link(&subsys->dev.kobj, dev_name(ctrl->device));
+		mutex_unlock(&nvme_subsystems_lock);
 	}
 
 	ctrl->ops->free_ctrl(ctrl);

drivers/nvme/host/fabrics.c

@@ -978,7 +978,7 @@ EXPORT_SYMBOL_GPL(nvmf_free_options);
 				 NVMF_OPT_DISABLE_SQFLOW)
 
 static struct nvme_ctrl *
-nvmf_create_ctrl(struct device *dev, const char *buf, size_t count)
+nvmf_create_ctrl(struct device *dev, const char *buf)
 {
 	struct nvmf_ctrl_options *opts;
 	struct nvmf_transport_ops *ops;
@@ -1073,7 +1073,7 @@ static ssize_t nvmf_dev_write(struct file *file, const char __user *ubuf,
 		goto out_unlock;
 	}
 
-	ctrl = nvmf_create_ctrl(nvmf_device, buf, count);
+	ctrl = nvmf_create_ctrl(nvmf_device, buf);
 	if (IS_ERR(ctrl)) {
 		ret = PTR_ERR(ctrl);
 		goto out_unlock;

drivers/nvme/host/fc.c

@@ -202,7 +202,7 @@ static LIST_HEAD(nvme_fc_lport_list);
 static DEFINE_IDA(nvme_fc_local_port_cnt);
 static DEFINE_IDA(nvme_fc_ctrl_cnt);
 
-
+static struct workqueue_struct *nvme_fc_wq;
 
 /*
  * These items are short-term. They will eventually be moved into
@@ -2054,7 +2054,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	 */
 	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
 		active = atomic_xchg(&ctrl->err_work_active, 1);
-		if (!active && !schedule_work(&ctrl->err_work)) {
+		if (!active && !queue_work(nvme_fc_wq, &ctrl->err_work)) {
 			atomic_set(&ctrl->err_work_active, 0);
 			WARN_ON(1);
 		}
@@ -3399,6 +3399,10 @@ static int __init nvme_fc_init_module(void)
 {
 	int ret;
 
+	nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0);
+	if (!nvme_fc_wq)
+		return -ENOMEM;
+
 	/*
 	 * NOTE:
 	 * It is expected that in the future the kernel will combine
@@ -3416,7 +3420,7 @@ static int __init nvme_fc_init_module(void)
 	ret = class_register(&fc_class);
 	if (ret) {
 		pr_err("couldn't register class fc\n");
-		return ret;
+		goto out_destroy_wq;
 	}
 
 	/*
@@ -3440,6 +3444,9 @@ static int __init nvme_fc_init_module(void)
 	device_destroy(&fc_class, MKDEV(0, 0));
 out_destroy_class:
 	class_unregister(&fc_class);
+out_destroy_wq:
+	destroy_workqueue(nvme_fc_wq);
+
 	return ret;
 }
 
@@ -3456,6 +3463,7 @@ static void __exit nvme_fc_exit_module(void)
 
 	device_destroy(&fc_class, MKDEV(0, 0));
 	class_unregister(&fc_class);
+	destroy_workqueue(nvme_fc_wq);
 }
 
 module_init(nvme_fc_init_module);

drivers/nvme/host/multipath.c

@@ -31,7 +31,7 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 		sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
 	} else if (ns->head->disk) {
 		sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
-				ctrl->cntlid, ns->head->instance);
+				ctrl->instance, ns->head->instance);
 		*flags = GENHD_FL_HIDDEN;
 	} else {
 		sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,

drivers/nvme/host/pci.c

@@ -1296,6 +1296,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	switch (dev->ctrl.state) {
 	case NVME_CTRL_DELETING:
 		shutdown = true;
+		/* fall through */
 	case NVME_CTRL_CONNECTING:
 	case NVME_CTRL_RESETTING:
 		dev_warn_ratelimited(dev->ctrl.device,
@@ -2280,8 +2281,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 			return ret;
 		}
 		dev->ctrl.tagset = &dev->tagset;
-
-		nvme_dbbuf_set(dev);
 	} else {
 		blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
 
@@ -2289,6 +2288,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		nvme_free_queues(dev, dev->online_queues);
 	}
 
+	nvme_dbbuf_set(dev);
 	return 0;
 }
 

drivers/nvme/host/rdma.c

@@ -697,15 +697,6 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 	return ret;
 }
 
-static void nvme_rdma_free_tagset(struct nvme_ctrl *nctrl,
-		struct blk_mq_tag_set *set)
-{
-	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
-
-	blk_mq_free_tag_set(set);
-	nvme_rdma_dev_put(ctrl->device);
-}
-
 static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
 		bool admin)
 {
@@ -744,24 +735,9 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
 
 	ret = blk_mq_alloc_tag_set(set);
 	if (ret)
-		goto out;
-
-	/*
-	 * We need a reference on the device as long as the tag_set is alive,
-	 * as the MRs in the request structures need a valid ib_device.
-	 */
-	ret = nvme_rdma_dev_get(ctrl->device);
-	if (!ret) {
-		ret = -EINVAL;
-		goto out_free_tagset;
-	}
+		return ERR_PTR(ret);
 
 	return set;
-
-out_free_tagset:
-	blk_mq_free_tag_set(set);
-out:
-	return ERR_PTR(ret);
 }
 
 static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
@@ -769,7 +745,7 @@ static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
 {
 	if (remove) {
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
-		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
+		blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
 	}
 	if (ctrl->async_event_sqe.data) {
 		nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
@@ -847,7 +823,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
 out_free_tagset:
 	if (new)
-		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
+		blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
 out_free_async_qe:
 	nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
 		sizeof(struct nvme_command), DMA_TO_DEVICE);
@@ -862,7 +838,7 @@ static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl,
 {
 	if (remove) {
 		blk_cleanup_queue(ctrl->ctrl.connect_q);
-		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
+		blk_mq_free_tag_set(ctrl->ctrl.tagset);
 	}
 	nvme_rdma_free_io_queues(ctrl);
 }
@@ -903,7 +879,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 		blk_cleanup_queue(ctrl->ctrl.connect_q);
 out_free_tag_set:
 	if (new)
-		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
+		blk_mq_free_tag_set(ctrl->ctrl.tagset);
 out_free_io_queues:
 	nvme_rdma_free_io_queues(ctrl);
 	return ret;

drivers/nvme/host/trace.h

@@ -167,6 +167,7 @@ TRACE_EVENT(nvme_async_event,
 		aer_name(NVME_AER_NOTICE_NS_CHANGED),
 		aer_name(NVME_AER_NOTICE_ANA),
 		aer_name(NVME_AER_NOTICE_FW_ACT_STARTING),
+		aer_name(NVME_AER_NOTICE_DISC_CHANGED),
 		aer_name(NVME_AER_ERROR),
 		aer_name(NVME_AER_SMART),
 		aer_name(NVME_AER_CSS),

include/linux/nvme.h

@@ -1246,9 +1246,9 @@ enum {
 	NVME_SC_FW_NEEDS_SUBSYS_RESET	= 0x110,
 	NVME_SC_FW_NEEDS_RESET		= 0x111,
 	NVME_SC_FW_NEEDS_MAX_TIME	= 0x112,
-	NVME_SC_FW_ACIVATE_PROHIBITED	= 0x113,
+	NVME_SC_FW_ACTIVATE_PROHIBITED	= 0x113,
 	NVME_SC_OVERLAPPING_RANGE	= 0x114,
-	NVME_SC_NS_INSUFFICENT_CAP	= 0x115,
+	NVME_SC_NS_INSUFFICIENT_CAP	= 0x115,
 	NVME_SC_NS_ID_UNAVAILABLE	= 0x116,
 	NVME_SC_NS_ALREADY_ATTACHED	= 0x118,
 	NVME_SC_NS_IS_PRIVATE		= 0x119,