1 files changed, 161 insertions, 158 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7e3893d06bab..e26b085a007a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -384,6 +384,8 @@ static inline void nvme_end_req(struct request *req)
 		nvme_log_error(req);
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
+	if (req->cmd_flags & REQ_NVME_MPATH)
+		nvme_mpath_end_request(req);
 	blk_mq_end_request(req, status);
 }
 
@@ -851,8 +853,11 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 	cmnd->write_zeroes.length =
 		cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 
+	if (!(req->cmd_flags & REQ_NOUNMAP) && (ns->features & NVME_NS_DEAC))
+		cmnd->write_zeroes.control |= cpu_to_le16(NVME_WZ_DEAC);
+
 	if (nvme_ns_has_pi(ns)) {
-		cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT);
+		cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT);
 
 		switch (ns->pi_type) {
 		case NVME_NS_DPS_PI_TYPE1:
@@ -1118,11 +1123,12 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
 		nvme_unfreeze(ctrl);
 		nvme_mpath_unfreeze(ctrl->subsys);
 		mutex_unlock(&ctrl->subsys->lock);
-		nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
 		mutex_unlock(&ctrl->scan_lock);
 	}
-	if (effects & NVME_CMD_EFFECTS_CCC)
-		nvme_init_ctrl_finish(ctrl);
+	if (effects & NVME_CMD_EFFECTS_CCC) {
+		dev_info(ctrl->device,
+"controller capabilities changed, reset may be required to take effect.\n");
+	}
 	if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) {
 		nvme_queue_scan(ctrl);
 		flush_work(&ctrl->scan_work);
@@ -2003,6 +2009,14 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		}
 	}
 
+	/*
+	 * Only set the DEAC bit if the device guarantees that reads from
+	 * deallocated data return zeroes.  While the DEAC bit does not
+	 * require that, it must be a no-op if reads from deallocated data
+	 * do not return zeroes.
+	 */
+	if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
+		ns->features |= NVME_NS_DEAC;
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
@@ -2179,7 +2193,7 @@ const struct pr_ops nvme_pr_ops = {
 };
 
 #ifdef CONFIG_BLK_SED_OPAL
-int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
+static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 		bool send)
 {
 	struct nvme_ctrl *ctrl = data;
@@ -2196,7 +2210,23 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
 			NVME_QID_ANY, 1, 0);
 }
-EXPORT_SYMBOL_GPL(nvme_sec_submit);
+
+static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended)
+{
+	if (ctrl->oacs & NVME_CTRL_OACS_SEC_SUPP) {
+		if (!ctrl->opal_dev)
+			ctrl->opal_dev = init_opal_dev(ctrl, &nvme_sec_submit);
+		else if (was_suspended)
+			opal_unlock_from_suspend(ctrl->opal_dev);
+	} else {
+		free_opal_dev(ctrl->opal_dev);
+		ctrl->opal_dev = NULL;
+	}
+}
+#else
+static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended)
+{
+}
 #endif /* CONFIG_BLK_SED_OPAL */
 
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -2221,16 +2251,17 @@ static const struct block_device_operations nvme_bdev_ops = {
 	.pr_ops		= &nvme_pr_ops,
 };
 
-static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 timeout, bool enabled)
+static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 mask, u32 val,
+		u32 timeout, const char *op)
 {
-	unsigned long timeout_jiffies = ((timeout + 1) * HZ / 2) + jiffies;
-	u32 csts, bit = enabled ? NVME_CSTS_RDY : 0;
+	unsigned long timeout_jiffies = jiffies + timeout * HZ;
+	u32 csts;
 	int ret;
 
 	while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
 		if (csts == ~0)
 			return -ENODEV;
-		if ((csts & NVME_CSTS_RDY) == bit)
+		if ((csts & mask) == val)
 			break;
 
 		usleep_range(1000, 2000);
@@ -2239,7 +2270,7 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 timeout, bool enabled)
 		if (time_after(jiffies, timeout_jiffies)) {
 			dev_err(ctrl->device,
 				"Device not ready; aborting %s, CSTS=0x%x\n",
-				enabled ? "initialisation" : "reset", csts);
+				op, csts);
 			return -ENODEV;
 		}
 	}
@@ -2247,27 +2278,29 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 timeout, bool enabled)
 	return ret;
 }
 
-/*
- * If the device has been passed off to us in an enabled state, just clear
- * the enabled bit.  The spec says we should set the 'shutdown notification
- * bits', but doing so may cause the device to complete commands to the
- * admin queue ... and we don't know what memory that might be pointing at!
- */
-int nvme_disable_ctrl(struct nvme_ctrl *ctrl)
+int nvme_disable_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
 {
 	int ret;
 
 	ctrl->ctrl_config &= ~NVME_CC_SHN_MASK;
-	ctrl->ctrl_config &= ~NVME_CC_ENABLE;
+	if (shutdown)
+		ctrl->ctrl_config |= NVME_CC_SHN_NORMAL;
+	else
+		ctrl->ctrl_config &= ~NVME_CC_ENABLE;
 
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)
 		return ret;
 
+	if (shutdown) {
+		return nvme_wait_ready(ctrl, NVME_CSTS_SHST_MASK,
+				       NVME_CSTS_SHST_CMPLT,
+				       ctrl->shutdown_timeout, "shutdown");
+	}
 	if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
 		msleep(NVME_QUIRK_DELAY_AMOUNT);
-
-	return nvme_wait_ready(ctrl, NVME_CAP_TIMEOUT(ctrl->cap), false);
+	return nvme_wait_ready(ctrl, NVME_CSTS_RDY, 0,
+			       (NVME_CAP_TIMEOUT(ctrl->cap) + 1) / 2, "reset");
 }
 EXPORT_SYMBOL_GPL(nvme_disable_ctrl);
 
@@ -2332,41 +2365,11 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)
 		return ret;
-	return nvme_wait_ready(ctrl, timeout, true);
+	return nvme_wait_ready(ctrl, NVME_CSTS_RDY, NVME_CSTS_RDY,
+			       (timeout + 1) / 2, "initialisation");
 }
 EXPORT_SYMBOL_GPL(nvme_enable_ctrl);
 
-int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
-{
-	unsigned long timeout = jiffies + (ctrl->shutdown_timeout * HZ);
-	u32 csts;
-	int ret;
-
-	ctrl->ctrl_config &= ~NVME_CC_SHN_MASK;
-	ctrl->ctrl_config |= NVME_CC_SHN_NORMAL;
-
-	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
-	if (ret)
-		return ret;
-
-	while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
-		if ((csts & NVME_CSTS_SHST_MASK) == NVME_CSTS_SHST_CMPLT)
-			break;
-
-		msleep(100);
-		if (fatal_signal_pending(current))
-			return -EINTR;
-		if (time_after(jiffies, timeout)) {
-			dev_err(ctrl->device,
-				"Device shutdown incomplete; abort shutdown\n");
-			return -ENODEV;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl);
-
 static int nvme_configure_timestamp(struct nvme_ctrl *ctrl)
 {
 	__le64 ts;
@@ -3049,7 +3052,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 
 	id = kzalloc(sizeof(*id), GFP_KERNEL);
 	if (!id)
-		return 0;
+		return -ENOMEM;
 
 	c.identify.opcode = nvme_admin_identify;
 	c.identify.cns = NVME_ID_CNS_CS_CTRL;
@@ -3229,7 +3232,7 @@ out_free:
  * register in our nvme_ctrl structure.  This should be called as soon as
  * the admin queue is fully up and running.
  */
-int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl)
+int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl, bool was_suspended)
 {
 	int ret;
 
@@ -3260,6 +3263,8 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl)
 	if (ret < 0)
 		return ret;
 
+	nvme_configure_opal(ctrl, was_suspended);
+
 	if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) {
 		/*
 		 * Do not return errors unless we are in a controller reset,
@@ -3745,15 +3750,19 @@ static ssize_t nvme_ctrl_dhchap_secret_store(struct device *dev,
 	memcpy(dhchap_secret, buf, count);
 	nvme_auth_stop(ctrl);
 	if (strcmp(dhchap_secret, opts->dhchap_secret)) {
+		struct nvme_dhchap_key *key, *host_key;
 		int ret;
 
-		ret = nvme_auth_generate_key(dhchap_secret, &ctrl->host_key);
+		ret = nvme_auth_generate_key(dhchap_secret, &key);
 		if (ret)
 			return ret;
 		kfree(opts->dhchap_secret);
 		opts->dhchap_secret = dhchap_secret;
-		/* Key has changed; re-authentication with new key */
-		nvme_auth_reset(ctrl);
+		host_key = ctrl->host_key;
+		mutex_lock(&ctrl->dhchap_auth_mutex);
+		ctrl->host_key = key;
+		mutex_unlock(&ctrl->dhchap_auth_mutex);
+		nvme_auth_free_key(host_key);
 	}
 	/* Start re-authentication */
 	dev_info(ctrl->device, "re-authenticating controller\n");
@@ -3795,15 +3804,19 @@ static ssize_t nvme_ctrl_dhchap_ctrl_secret_store(struct device *dev,
 	memcpy(dhchap_secret, buf, count);
 	nvme_auth_stop(ctrl);
 	if (strcmp(dhchap_secret, opts->dhchap_ctrl_secret)) {
+		struct nvme_dhchap_key *key, *ctrl_key;
 		int ret;
 
-		ret = nvme_auth_generate_key(dhchap_secret, &ctrl->ctrl_key);
+		ret = nvme_auth_generate_key(dhchap_secret, &key);
 		if (ret)
 			return ret;
 		kfree(opts->dhchap_ctrl_secret);
 		opts->dhchap_ctrl_secret = dhchap_secret;
-		/* Key has changed; re-authentication with new key */
-		nvme_auth_reset(ctrl);
+		ctrl_key = ctrl->ctrl_key;
+		mutex_lock(&ctrl->dhchap_auth_mutex);
+		ctrl->ctrl_key = key;
+		mutex_unlock(&ctrl->dhchap_auth_mutex);
+		nvme_auth_free_key(ctrl_key);
 	}
 	/* Start re-authentication */
 	dev_info(ctrl->device, "re-authenticating controller\n");
@@ -3875,10 +3888,11 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-static const struct attribute_group nvme_dev_attrs_group = {
+const struct attribute_group nvme_dev_attrs_group = {
 	.attrs		= nvme_dev_attrs,
 	.is_visible	= nvme_dev_attrs_are_visible,
 };
+EXPORT_SYMBOL_GPL(nvme_dev_attrs_group);
 
 static const struct attribute_group *nvme_dev_attr_groups[] = {
 	&nvme_dev_attrs_group,
@@ -4333,10 +4347,6 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info)
 {
 	int ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
 
-	if (test_bit(NVME_NS_DEAD, &ns->flags))
-		goto out;
-
-	ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
 	if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) {
 		dev_err(ns->ctrl->device,
 			"identifiers changed for nsid %d\n", ns->head->ns_id);
@@ -4407,7 +4417,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 
 	down_write(&ctrl->namespaces_rwsem);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags))
+		if (ns->head->ns_id > nsid)
 			list_move_tail(&ns->list, &rm_list);
 	}
 	up_write(&ctrl->namespaces_rwsem);
@@ -4424,9 +4434,6 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
 	u32 prev = 0;
 	int ret = 0, i;
 
-	if (nvme_ctrl_limited_cns(ctrl))
-		return -EOPNOTSUPP;
-
 	ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
 	if (!ns_list)
 		return -ENOMEM;
@@ -4534,8 +4541,18 @@ static void nvme_scan_work(struct work_struct *work)
 	}
 
 	mutex_lock(&ctrl->scan_lock);
-	if (nvme_scan_ns_list(ctrl) != 0)
+	if (nvme_ctrl_limited_cns(ctrl)) {
 		nvme_scan_ns_sequential(ctrl);
+	} else {
+		/*
+		 * Fall back to sequential scan if DNR is set to handle broken
+		 * devices which should support Identify NS List (as per the VS
+		 * they report) but don't actually support it.
+		 */
+		ret = nvme_scan_ns_list(ctrl);
+		if (ret > 0 && ret & NVME_SC_DNR)
+			nvme_scan_ns_sequential(ctrl);
+	}
 	mutex_unlock(&ctrl->scan_lock);
 }
 
@@ -4565,8 +4582,10 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	 * removing the namespaces' disks; fail all the queues now to avoid
 	 * potentially having to clean up the failed sync later.
 	 */
-	if (ctrl->state == NVME_CTRL_DEAD)
-		nvme_kill_queues(ctrl);
+	if (ctrl->state == NVME_CTRL_DEAD) {
+		nvme_mark_namespaces_dead(ctrl);
+		nvme_unquiesce_io_queues(ctrl);
+	}
 
 	/* this is a no-op when called from the controller reset handler */
 	nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
@@ -4692,7 +4711,7 @@ static void nvme_fw_act_work(struct work_struct *work)
 		fw_act_timeout = jiffies +
 				msecs_to_jiffies(admin_timeout * 1000);
 
-	nvme_stop_queues(ctrl);
+	nvme_quiesce_io_queues(ctrl);
 	while (nvme_ctrl_pp_status(ctrl)) {
 		if (time_after(jiffies, fw_act_timeout)) {
 			dev_warn(ctrl->device,
@@ -4706,7 +4725,7 @@ static void nvme_fw_act_work(struct work_struct *work)
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
 		return;
 
-	nvme_start_queues(ctrl);
+	nvme_unquiesce_io_queues(ctrl);
 	/* read FW slot information to clear the AER */
 	nvme_get_fw_slot_info(ctrl);
 
@@ -4811,8 +4830,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 
 int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
-		const struct blk_mq_ops *ops, unsigned int flags,
-		unsigned int cmd_size)
+		const struct blk_mq_ops *ops, unsigned int cmd_size)
 {
 	int ret;
 
@@ -4822,7 +4840,9 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	if (ctrl->ops->flags & NVME_F_FABRICS)
 		set->reserved_tags = NVMF_RESERVED_TAGS;
 	set->numa_node = ctrl->numa_node;
-	set->flags = flags;
+	set->flags = BLK_MQ_F_NO_SCHED;
+	if (ctrl->ops->flags & NVME_F_BLOCKING)
+		set->flags |= BLK_MQ_F_BLOCKING;
 	set->cmd_size = cmd_size;
 	set->driver_data = ctrl;
 	set->nr_hw_queues = 1;
@@ -4850,6 +4870,7 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 
 out_cleanup_admin_q:
 	blk_mq_destroy_queue(ctrl->admin_q);
+	blk_put_queue(ctrl->admin_q);
 out_free_tagset:
 	blk_mq_free_tag_set(ctrl->admin_tagset);
 	return ret;
@@ -4859,14 +4880,17 @@ EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set);
 void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl)
 {
 	blk_mq_destroy_queue(ctrl->admin_q);
-	if (ctrl->ops->flags & NVME_F_FABRICS)
+	blk_put_queue(ctrl->admin_q);
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		blk_mq_destroy_queue(ctrl->fabrics_q);
+		blk_put_queue(ctrl->fabrics_q);
+	}
 	blk_mq_free_tag_set(ctrl->admin_tagset);
 }
 EXPORT_SYMBOL_GPL(nvme_remove_admin_tag_set);
 
 int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
-		const struct blk_mq_ops *ops, unsigned int flags,
+		const struct blk_mq_ops *ops, unsigned int nr_maps,
 		unsigned int cmd_size)
 {
 	int ret;
@@ -4874,15 +4898,23 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	memset(set, 0, sizeof(*set));
 	set->ops = ops;
 	set->queue_depth = ctrl->sqsize + 1;
-	set->reserved_tags = NVMF_RESERVED_TAGS;
+	/*
+	 * Some Apple controllers requires tags to be unique across admin and
+	 * the (only) I/O queue, so reserve the first 32 tags of the I/O queue.
+	 */
+	if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS)
+		set->reserved_tags = NVME_AQ_DEPTH;
+	else if (ctrl->ops->flags & NVME_F_FABRICS)
+		set->reserved_tags = NVMF_RESERVED_TAGS;
 	set->numa_node = ctrl->numa_node;
-	set->flags = flags;
+	set->flags = BLK_MQ_F_SHOULD_MERGE;
+	if (ctrl->ops->flags & NVME_F_BLOCKING)
+		set->flags |= BLK_MQ_F_BLOCKING;
 	set->cmd_size = cmd_size,
 	set->driver_data = ctrl;
 	set->nr_hw_queues = ctrl->queue_count - 1;
 	set->timeout = NVME_IO_TIMEOUT;
-	if (ops->map_queues)
-		set->nr_maps = ctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2;
+	set->nr_maps = nr_maps;
 	ret = blk_mq_alloc_tag_set(set);
 	if (ret)
 		return ret;
@@ -4893,6 +4925,8 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 			ret = PTR_ERR(ctrl->connect_q);
 			goto out_free_tag_set;
 		}
+		blk_queue_flag_set(QUEUE_FLAG_SKIP_TAGSET_QUIESCE,
+				   ctrl->connect_q);
 	}
 
 	ctrl->tagset = set;
@@ -4906,8 +4940,10 @@ EXPORT_SYMBOL_GPL(nvme_alloc_io_tag_set);
 
 void nvme_remove_io_tag_set(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->ops->flags & NVME_F_FABRICS)
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		blk_mq_destroy_queue(ctrl->connect_q);
+		blk_put_queue(ctrl->connect_q);
+	}
 	blk_mq_free_tag_set(ctrl->tagset);
 }
 EXPORT_SYMBOL_GPL(nvme_remove_io_tag_set);
@@ -4943,7 +4979,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 
 	if (ctrl->queue_count > 1) {
 		nvme_queue_scan(ctrl);
-		nvme_start_queues(ctrl);
+		nvme_unquiesce_io_queues(ctrl);
 		nvme_mpath_update(ctrl);
 	}
 
@@ -4988,6 +5024,7 @@ static void nvme_free_ctrl(struct device *dev)
 	nvme_auth_stop(ctrl);
 	nvme_auth_free(ctrl);
 	__free_page(ctrl->discard_page);
+	free_opal_dev(ctrl->opal_dev);
 
 	if (subsys) {
 		mutex_lock(&nvme_subsystems_lock);
@@ -5053,7 +5090,10 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 			ctrl->instance);
 	ctrl->device->class = nvme_class;
 	ctrl->device->parent = ctrl->dev;
-	ctrl->device->groups = nvme_dev_attr_groups;
+	if (ops->dev_attr_groups)
+		ctrl->device->groups = ops->dev_attr_groups;
+	else
+		ctrl->device->groups = nvme_dev_attr_groups;
 	ctrl->device->release = nvme_free_ctrl;
 	dev_set_drvdata(ctrl->device, ctrl);
 	ret = dev_set_name(ctrl->device, "nvme%d", ctrl->instance);
@@ -5077,9 +5117,13 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 
 	nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device));
 	nvme_mpath_init_ctrl(ctrl);
-	nvme_auth_init_ctrl(ctrl);
+	ret = nvme_auth_init_ctrl(ctrl);
+	if (ret)
+		goto out_free_cdev;
 
 	return 0;
+out_free_cdev:
+	cdev_device_del(&ctrl->cdev, ctrl->device);
 out_free_name:
 	nvme_put_ctrl(ctrl);
 	kfree_const(ctrl->device->kobj.name);
@@ -5092,62 +5136,17 @@ out:
 }
 EXPORT_SYMBOL_GPL(nvme_init_ctrl);
 
-static void nvme_start_ns_queue(struct nvme_ns *ns)
-{
-	if (test_and_clear_bit(NVME_NS_STOPPED, &ns->flags))
-		blk_mq_unquiesce_queue(ns->queue);
-}
-
-static void nvme_stop_ns_queue(struct nvme_ns *ns)
-{
-	if (!test_and_set_bit(NVME_NS_STOPPED, &ns->flags))
-		blk_mq_quiesce_queue(ns->queue);
-	else
-		blk_mq_wait_quiesce_done(ns->queue);
-}
-
-/*
- * Prepare a queue for teardown.
- *
- * This must forcibly unquiesce queues to avoid blocking dispatch, and only set
- * the capacity to 0 after that to avoid blocking dispatchers that may be
- * holding bd_butex.  This will end buffered writers dirtying pages that can't
- * be synced.
- */
-static void nvme_set_queue_dying(struct nvme_ns *ns)
-{
-	if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
-		return;
-
-	blk_mark_disk_dead(ns->disk);
-	nvme_start_ns_queue(ns);
-
-	set_capacity_and_notify(ns->disk, 0);
-}
-
-/**
- * nvme_kill_queues(): Ends all namespace queues
- * @ctrl: the dead controller that needs to end
- *
- * Call this function when the driver determines it is unable to get the
- * controller in a state capable of servicing IO.
- */
-void nvme_kill_queues(struct nvme_ctrl *ctrl)
+/* let I/O to all namespaces fail in preparation for surprise removal */
+void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
 	down_read(&ctrl->namespaces_rwsem);
-
-	/* Forcibly unquiesce queues to avoid blocking dispatch */
-	if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q))
-		nvme_start_admin_queue(ctrl);
-
 	list_for_each_entry(ns, &ctrl->namespaces, list)
-		nvme_set_queue_dying(ns);
-
+		blk_mark_disk_dead(ns->disk);
 	up_read(&ctrl->namespaces_rwsem);
 }
-EXPORT_SYMBOL_GPL(nvme_kill_queues);
+EXPORT_SYMBOL_GPL(nvme_mark_namespaces_dead);
 
 void nvme_unfreeze(struct nvme_ctrl *ctrl)
 {
@@ -5197,43 +5196,41 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_freeze);
 
-void nvme_stop_queues(struct nvme_ctrl *ctrl)
+void nvme_quiesce_io_queues(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns;
-
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		nvme_stop_ns_queue(ns);
-	up_read(&ctrl->namespaces_rwsem);
+	if (!ctrl->tagset)
+		return;
+	if (!test_and_set_bit(NVME_CTRL_STOPPED, &ctrl->flags))
+		blk_mq_quiesce_tagset(ctrl->tagset);
+	else
+		blk_mq_wait_quiesce_done(ctrl->tagset);
 }
-EXPORT_SYMBOL_GPL(nvme_stop_queues);
+EXPORT_SYMBOL_GPL(nvme_quiesce_io_queues);
 
-void nvme_start_queues(struct nvme_ctrl *ctrl)
+void nvme_unquiesce_io_queues(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns;
-
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		nvme_start_ns_queue(ns);
-	up_read(&ctrl->namespaces_rwsem);
+	if (!ctrl->tagset)
+		return;
+	if (test_and_clear_bit(NVME_CTRL_STOPPED, &ctrl->flags))
+		blk_mq_unquiesce_tagset(ctrl->tagset);
 }
-EXPORT_SYMBOL_GPL(nvme_start_queues);
+EXPORT_SYMBOL_GPL(nvme_unquiesce_io_queues);
 
-void nvme_stop_admin_queue(struct nvme_ctrl *ctrl)
+void nvme_quiesce_admin_queue(struct nvme_ctrl *ctrl)
 {
 	if (!test_and_set_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags))
 		blk_mq_quiesce_queue(ctrl->admin_q);
 	else
-		blk_mq_wait_quiesce_done(ctrl->admin_q);
+		blk_mq_wait_quiesce_done(ctrl->admin_q->tag_set);
 }
-EXPORT_SYMBOL_GPL(nvme_stop_admin_queue);
+EXPORT_SYMBOL_GPL(nvme_quiesce_admin_queue);
 
-void nvme_start_admin_queue(struct nvme_ctrl *ctrl)
+void nvme_unquiesce_admin_queue(struct nvme_ctrl *ctrl)
 {
 	if (test_and_clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags))
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 }
-EXPORT_SYMBOL_GPL(nvme_start_admin_queue);
+EXPORT_SYMBOL_GPL(nvme_unquiesce_admin_queue);
 
 void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
 {
@@ -5344,8 +5341,13 @@ static int __init nvme_core_init(void)
 		goto unregister_generic_ns;
 	}
 
+	result = nvme_init_auth();
+	if (result)
+		goto destroy_ns_chr;
 	return 0;
 
+destroy_ns_chr:
+	class_destroy(nvme_ns_chr_class);
 unregister_generic_ns:
 	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
 destroy_subsys_class:
@@ -5366,6 +5368,7 @@ out:
 
 static void __exit nvme_core_exit(void)
 {
+	nvme_exit_auth();
 	class_destroy(nvme_ns_chr_class);
 	class_destroy(nvme_subsys_class);
 	class_destroy(nvme_class);