Merge tag 'for-linus-20180623' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

- Further timeout fixes. We aren't quite there yet, so expect another
round of fixes for that to completely close some of the IRQ vs
completion races. (Christoph/Bart)

- Set of NVMe fixes from the usual suspects, mostly error handling

- Two off-by-one fixes (Dan)

- Another bdi race fix (Jan)

- Fix nbd reconfigure with NBD_DISCONNECT_ON_CLOSE (Doron)

* tag 'for-linus-20180623' of git://git.kernel.dk/linux-block:
blk-mq: Fix timeout handling in case the timeout handler returns BLK_EH_DONE
bdi: Fix another oops in wb_workfn()
lightnvm: Remove depends on HAS_DMA in case of platform dependency
nvme-pci: limit max IO size and segments to avoid high order allocations
nvme-pci: move nvme_kill_queues to nvme_remove_dead_ctrl
nvme-fc: release io queues to allow fast fail
nbd: Add the nbd NBD_DISCONNECT_ON_CLOSE config flag.
block: sed-opal: Fix a couple off by one bugs
blk-mq-debugfs: Off by one in blk_mq_rq_state_name()
nvmet: reset keep alive timer in controller enable
nvme-rdma: don't override opts->queue_size
nvme-rdma: Fix command completion race at error recovery
nvme-rdma: fix possible free of a non-allocated async event buffer
nvme-rdma: fix possible double free condition when failing to create a controller
Revert "block: Add warning for bi_next not NULL in bio_endio()"
block: fix timeout changes for legacy request drivers

block/bio.c

···
 	if (!bio_integrity_endio(bio))
 		return;
 
-	if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL"))
-		bio->bi_next = NULL;
-
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that

block/blk-core.c

···
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	/*
-	 * XXX this code looks suspicious - it's not consistent with advancing
-	 * req->bio in caller
-	 */
 	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
 		bio_endio(bio);
 }
···
 		struct bio *bio = req->bio;
 		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_iter.bi_size) {
+		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
-			bio->bi_next = NULL;
-		}
 
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);

block/blk-mq-debugfs.c

···
 
 static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state)
 {
-	if (WARN_ON_ONCE((unsigned int)rq_state >
+	if (WARN_ON_ONCE((unsigned int)rq_state >=
 			 ARRAY_SIZE(blk_mq_rq_state_name_array)))
 		return "(?)";
 	return blk_mq_rq_state_name_array[rq_state];

block/blk-mq.c

···
 		WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
 	}
 
-	req->rq_flags &= ~RQF_TIMED_OUT;
 	blk_add_timer(req);
 }
 

block/blk-softirq.c

···
 
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(__blk_complete_request);
 
 /**
  * blk_complete_request - end I/O on a request

block/blk-timeout.c

···
 	if (!req->timeout)
 		req->timeout = q->rq_timeout;
 
+	req->rq_flags &= ~RQF_TIMED_OUT;
 	blk_rq_set_deadline(req, jiffies + req->timeout);
 
 	/*

block/sed-opal.c

···
 		return 0;
 	}
 
-	if (n > resp->num) {
+	if (n >= resp->num) {
 		pr_debug("Response has %d tokens. Can't access %d\n",
 			 resp->num, n);
 		return 0;
···
 		return 0;
 	}
 
-	if (n > resp->num) {
+	if (n >= resp->num) {
 		pr_debug("Response has %d tokens. Can't access %d\n",
 			 resp->num, n);
 		return 0;

drivers/block/nbd.c

···
 #define NBD_HAS_CONFIG_REF		4
 #define NBD_BOUND			5
 #define NBD_DESTROY_ON_DISCONNECT	6
+#define NBD_DISCONNECT_ON_CLOSE 	7
 
 struct nbd_config {
 	u32 flags;
···
 static void nbd_connect_reply(struct genl_info *info, int index);
 static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
 static void nbd_dead_link_work(struct work_struct *work);
+static void nbd_disconnect_and_put(struct nbd_device *nbd);
 
 static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 {
···
 static void nbd_release(struct gendisk *disk, fmode_t mode)
 {
 	struct nbd_device *nbd = disk->private_data;
+	struct block_device *bdev = bdget_disk(disk, 0);
+
+	if (test_bit(NBD_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
+			bdev->bd_openers == 0)
+		nbd_disconnect_and_put(nbd);
+
 	nbd_config_put(nbd);
 	nbd_put(nbd);
 }
···
 				&config->runtime_flags);
 			put_dev = true;
 		}
+		if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+			set_bit(NBD_DISCONNECT_ON_CLOSE,
+				&config->runtime_flags);
+		}
 	}
 
 	if (info->attrs[NBD_ATTR_SOCKETS]) {
···
 	return ret;
 }
 
+static void nbd_disconnect_and_put(struct nbd_device *nbd)
+{
+	mutex_lock(&nbd->config_lock);
+	nbd_disconnect(nbd);
+	nbd_clear_sock(nbd);
+	mutex_unlock(&nbd->config_lock);
+	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+			       &nbd->config->runtime_flags))
+		nbd_config_put(nbd);
+}
+
 static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nbd_device *nbd;
···
 		nbd_put(nbd);
 		return 0;
 	}
-	mutex_lock(&nbd->config_lock);
-	nbd_disconnect(nbd);
-	nbd_clear_sock(nbd);
-	mutex_unlock(&nbd->config_lock);
-	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
-			       &nbd->config->runtime_flags))
-		nbd_config_put(nbd);
+	nbd_disconnect_and_put(nbd);
 	nbd_config_put(nbd);
 	nbd_put(nbd);
 	return 0;
···
 	struct nbd_device *nbd = NULL;
 	struct nbd_config *config;
 	int index;
-	int ret = -EINVAL;
+	int ret = 0;
 	bool put_dev = false;
 
 	if (!netlink_capable(skb, CAP_SYS_ADMIN))
···
 	    !nbd->task_recv) {
 		dev_err(nbd_to_dev(nbd),
 			"not configured, cannot reconfigure\n");
+		ret = -EINVAL;
 		goto out;
 	}
 
···
 			if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT,
 					       &config->runtime_flags))
 				refcount_inc(&nbd->refs);
+		}
+
+		if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+			set_bit(NBD_DISCONNECT_ON_CLOSE,
+					&config->runtime_flags);
+		} else {
+			clear_bit(NBD_DISCONNECT_ON_CLOSE,
+					&config->runtime_flags);
 		}
 	}
 

drivers/block/null_blk.c

···
 static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
 {
 	pr_info("null: rq %p timed out\n", rq);
-	blk_mq_complete_request(rq);
+	__blk_complete_request(rq);
 	return BLK_EH_DONE;
 }
 

drivers/lightnvm/Kconfig

···
 
 menuconfig NVM
 	bool "Open-Channel SSD target support"
-	depends on BLOCK && HAS_DMA && PCI
+	depends on BLOCK && PCI
 	select BLK_DEV_NVME
 	help
 	  Say Y here to get to enable Open-channel SSDs.

drivers/nvme/host/core.c

···
 		u32 max_segments =
 			(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
 
+		max_segments = min_not_zero(max_segments, ctrl->max_segments);
 		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
 		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
 	}

drivers/nvme/host/fc.c

···
 	/* re-enable the admin_q so anything new can fast fail */
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 
+	/* resume the io queues so that things will fast fail */
+	nvme_start_queues(&ctrl->ctrl);
+
 	nvme_fc_ctlr_inactive_on_rport(ctrl);
 }
 
···
 	 * waiting for io to terminate
 	 */
 	nvme_fc_delete_association(ctrl);
-
-	/* resume the io queues so that things will fast fail */
-	nvme_start_queues(nctrl);
 }
 
 static void

drivers/nvme/host/nvme.h

···
 	u64 cap;
 	u32 page_size;
 	u32 max_hw_sectors;
+	u32 max_segments;
 	u16 oncs;
 	u16 oacs;
 	u16 nssa;

drivers/nvme/host/pci.c

···
 
 #define SGES_PER_PAGE	(PAGE_SIZE / sizeof(struct nvme_sgl_desc))
 
+/*
+ * These can be higher, but we need to ensure that any command doesn't
+ * require an sg allocation that needs more than a page of data.
+ */
+#define NVME_MAX_KB_SZ	4096
+#define NVME_MAX_SEGS	127
+
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0);
 
···
 	u32 cmbloc;
 	struct nvme_ctrl ctrl;
 	struct completion ioq_wait;
+
+	mempool_t *iod_mempool;
 
 	/* shadow doorbell buffer support: */
 	u32 *dbbuf_dbs;
···
 	iod->use_sgl = nvme_pci_use_sgls(dev, rq);
 
 	if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
-		size_t alloc_size = nvme_pci_iod_alloc_size(dev, size, nseg,
-				iod->use_sgl);
-
-		iod->sg = kmalloc(alloc_size, GFP_ATOMIC);
+		iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
 		if (!iod->sg)
 			return BLK_STS_RESOURCE;
 	} else {
···
 	}
 
 	if (iod->sg != iod->inline_sg)
-		kfree(iod->sg);
+		mempool_free(iod->sg, dev->iod_mempool);
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
···
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
 	free_opal_dev(dev->ctrl.opal_dev);
+	mempool_destroy(dev->iod_mempool);
 	kfree(dev);
 }
 
···
 
 	nvme_get_ctrl(&dev->ctrl);
 	nvme_dev_disable(dev, false);
+	nvme_kill_queues(&dev->ctrl);
 	if (!queue_work(nvme_wq, &dev->remove_work))
 		nvme_put_ctrl(&dev->ctrl);
 }
···
 	result = nvme_alloc_admin_tags(dev);
 	if (result)
 		goto out;
+
+	/*
+	 * Limit the max command size to prevent iod->sg allocations going
+	 * over a single page.
+	 */
+	dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
+	dev->ctrl.max_segments = NVME_MAX_SEGS;
 
 	result = nvme_init_identify(&dev->ctrl);
 	if (result)
···
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
-	nvme_kill_queues(&dev->ctrl);
 	if (pci_get_drvdata(pdev))
 		device_release_driver(&pdev->dev);
 	nvme_put_ctrl(&dev->ctrl);
···
 	int node, result = -ENOMEM;
 	struct nvme_dev *dev;
 	unsigned long quirks = id->driver_data;
+	size_t alloc_size;
 
 	node = dev_to_node(&pdev->dev);
 	if (node == NUMA_NO_NODE)
···
 			quirks);
 	if (result)
 		goto release_pools;
+
+	/*
+	 * Double check that our mempool alloc size will cover the biggest
+	 * command we support.
+	 */
+	alloc_size = nvme_pci_iod_alloc_size(dev, NVME_MAX_KB_SZ,
+						NVME_MAX_SEGS, true);
+	WARN_ON_ONCE(alloc_size > PAGE_SIZE);
+
+	dev->iod_mempool = mempool_create_node(1, mempool_kmalloc,
+						mempool_kfree,
+						(void *) alloc_size,
+						GFP_KERNEL, node);
+	if (!dev->iod_mempool) {
+		result = -ENOMEM;
+		goto release_pools;
+	}
 
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 

drivers/nvme/host/rdma.c

···
 	if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
 		return;
 
-	if (nvme_rdma_queue_idx(queue) == 0) {
-		nvme_rdma_free_qe(queue->device->dev,
-			&queue->ctrl->async_event_sqe,
-			sizeof(struct nvme_command), DMA_TO_DEVICE);
-	}
-
 	nvme_rdma_destroy_queue_ib(queue);
 	rdma_destroy_id(queue->cm_id);
 }
···
 		set = &ctrl->tag_set;
 		memset(set, 0, sizeof(*set));
 		set->ops = &nvme_rdma_mq_ops;
-		set->queue_depth = nctrl->opts->queue_size;
+		set->queue_depth = nctrl->sqsize + 1;
 		set->reserved_tags = 1; /* fabric connect */
 		set->numa_node = NUMA_NO_NODE;
 		set->flags = BLK_MQ_F_SHOULD_MERGE;
···
 static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (remove) {
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
 		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
 	}
+	nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+		sizeof(struct nvme_command), DMA_TO_DEVICE);
 	nvme_rdma_free_queue(&ctrl->queues[0]);
 }
 
···
 
 	ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev);
 
+	error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+	if (error)
+		goto out_free_queue;
+
 	if (new) {
 		ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
 		if (IS_ERR(ctrl->ctrl.admin_tagset)) {
 			error = PTR_ERR(ctrl->ctrl.admin_tagset);
-			goto out_free_queue;
+			goto out_free_async_qe;
 		}
 
 		ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
···
 	if (error)
 		goto out_stop_queue;
 
-	error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
-			&ctrl->async_event_sqe, sizeof(struct nvme_command),
-			DMA_TO_DEVICE);
-	if (error)
-		goto out_stop_queue;
-
 	return 0;
 
 out_stop_queue:
···
 out_free_tagset:
 	if (new)
 		nvme_rdma_free_tagset(&ctrl->ctrl, 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);
 out_free_queue:
 	nvme_rdma_free_queue(&ctrl->queues[0]);
 	return error;
···
 static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	nvme_rdma_stop_io_queues(ctrl);
 	if (remove) {
 		blk_cleanup_queue(ctrl->ctrl.connect_q);
 		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
···
 	list_del(&ctrl->list);
 	mutex_unlock(&nvme_rdma_ctrl_mutex);
 
-	kfree(ctrl->queues);
 	nvmf_free_options(nctrl->opts);
 free_ctrl:
+	kfree(ctrl->queues);
 	kfree(ctrl);
 }
 
···
 	return;
 
 destroy_admin:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	nvme_rdma_destroy_admin_queue(ctrl, false);
 requeue:
 	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
···
 
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_stop_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
 		blk_mq_tagset_busy_iter(&ctrl->tag_set,
 					nvme_cancel_request, &ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, false);
 	}
 
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
 	nvme_rdma_destroy_admin_queue(ctrl, false);
···
 {
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_stop_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
 		blk_mq_tagset_busy_iter(&ctrl->tag_set,
 					nvme_cancel_request, &ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, shutdown);
···
 		nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
 
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
···
 		goto out_free_ctrl;
 	}
 
-	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
-				0 /* no quirks, we're perfect! */);
-	if (ret)
-		goto out_free_ctrl;
-
 	INIT_DELAYED_WORK(&ctrl->reconnect_work,
 			nvme_rdma_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
···
 	ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues),
 				GFP_KERNEL);
 	if (!ctrl->queues)
-		goto out_uninit_ctrl;
+		goto out_free_ctrl;
+
+	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
+				0 /* no quirks, we're perfect! */);
+	if (ret)
+		goto out_kfree_queues;
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
 	WARN_ON_ONCE(!changed);
 
 	ret = nvme_rdma_configure_admin_queue(ctrl, true);
 	if (ret)
-		goto out_kfree_queues;
+		goto out_uninit_ctrl;
 
 	/* sanity check icdoff */
 	if (ctrl->ctrl.icdoff) {
···
 		goto out_remove_admin_queue;
 	}
 
-	if (opts->queue_size > ctrl->ctrl.maxcmd) {
-		/* warn if maxcmd is lower than queue_size */
-		dev_warn(ctrl->ctrl.device,
-			"queue_size %zu > ctrl maxcmd %u, clamping down\n",
-			opts->queue_size, ctrl->ctrl.maxcmd);
-		opts->queue_size = ctrl->ctrl.maxcmd;
-	}
-
+	/* only warn if argument is too large here, will clamp later */
 	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
-		/* warn if sqsize is lower than queue_size */
 		dev_warn(ctrl->ctrl.device,
 			"queue_size %zu > ctrl sqsize %u, clamping down\n",
 			opts->queue_size, ctrl->ctrl.sqsize + 1);
-		opts->queue_size = ctrl->ctrl.sqsize + 1;
+	}
+
+	/* warn if maxcmd is lower than sqsize+1 */
+	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+		dev_warn(ctrl->ctrl.device,
+			"sqsize %u > ctrl maxcmd %u, clamping down\n",
+			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
 	}
 
 	if (opts->nr_io_queues) {
···
 	return &ctrl->ctrl;
 
 out_remove_admin_queue:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	nvme_rdma_destroy_admin_queue(ctrl, true);
-out_kfree_queues:
-	kfree(ctrl->queues);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);
+out_kfree_queues:
+	kfree(ctrl->queues);
 out_free_ctrl:
 	kfree(ctrl);
 	return ERR_PTR(ret);

drivers/nvme/target/core.c

···
 	}
 
 	ctrl->csts = NVME_CSTS_RDY;
+
+	/*
+	 * Controllers that are not yet enabled should not really enforce the
+	 * keep alive timeout, but we still want to track a timeout and cleanup
+	 * in case a host died before it enabled the controller.  Hence, simply
+	 * reset the keep alive timer when the controller is enabled.
+	 */
+	mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)

drivers/scsi/scsi_transport_fc.c

···
 
 	/* the blk_end_sync_io() doesn't check the error */
 	if (inflight)
-		blk_mq_complete_request(req);
+		__blk_complete_request(req);
 	return BLK_EH_DONE;
 }
 

include/linux/backing-dev-defs.h

···
  */
 enum wb_state {
 	WB_registered,		/* bdi_register() was done */
-	WB_shutting_down,	/* wb_shutdown() in progress */
 	WB_writeback_running,	/* Writeback is in progress */
 	WB_has_dirty_io,	/* Dirty inodes on ->b_{dirty|io|more_io} */
 	WB_start_all,		/* nr_pages == 0 (all) work pending */
···
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
 	struct rb_root cgwb_congested_tree; /* their congested states */
+	struct mutex cgwb_release_mutex;  /* protect shutdown of wb structs */
 #else
 	struct bdi_writeback_congested *wb_congested;
 #endif

include/uapi/linux/nbd.h

···
 /* These are client behavior specific flags. */
 #define NBD_CFLAG_DESTROY_ON_DISCONNECT	(1 << 0) /* delete the nbd device on
 						    disconnect. */
+#define NBD_CFLAG_DISCONNECT_ON_CLOSE (1 << 1) /* disconnect the nbd device on
+						*  close by last opener.
+						*/
 
 /* userspace doesn't need the nbd_device structure */
 

mm/backing-dev.c

···
 	spin_lock_bh(&wb->work_lock);
 	if (!test_and_clear_bit(WB_registered, &wb->state)) {
 		spin_unlock_bh(&wb->work_lock);
-		/*
-		 * Wait for wb shutdown to finish if someone else is just
-		 * running wb_shutdown(). Otherwise we could proceed to wb /
-		 * bdi destruction before wb_shutdown() is finished.
-		 */
-		wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE);
 		return;
 	}
-	set_bit(WB_shutting_down, &wb->state);
 	spin_unlock_bh(&wb->work_lock);
 
 	cgwb_remove_from_bdi_list(wb);
···
 	mod_delayed_work(bdi_wq, &wb->dwork, 0);
 	flush_delayed_work(&wb->dwork);
 	WARN_ON(!list_empty(&wb->work_list));
-	/*
-	 * Make sure bit gets cleared after shutdown is finished. Matches with
-	 * the barrier provided by test_and_clear_bit() above.
-	 */
-	smp_wmb();
-	clear_and_wake_up_bit(WB_shutting_down, &wb->state);
 }
 
 static void wb_exit(struct bdi_writeback *wb)
···
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
 						release_work);
 
+	mutex_lock(&wb->bdi->cgwb_release_mutex);
 	wb_shutdown(wb);
 
 	css_put(wb->memcg_css);
 	css_put(wb->blkcg_css);
+	mutex_unlock(&wb->bdi->cgwb_release_mutex);
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 	percpu_ref_exit(&wb->refcnt);
···
 
 	INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
 	bdi->cgwb_congested_tree = RB_ROOT;
+	mutex_init(&bdi->cgwb_release_mutex);
 
 	ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
 	if (!ret) {
···
 	spin_lock_irq(&cgwb_lock);
 	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
 		cgwb_kill(*slot);
+	spin_unlock_irq(&cgwb_lock);
 
+	mutex_lock(&bdi->cgwb_release_mutex);
+	spin_lock_irq(&cgwb_lock);
 	while (!list_empty(&bdi->wb_list)) {
 		wb = list_first_entry(&bdi->wb_list, struct bdi_writeback,
 				      bdi_node);
···
 		spin_lock_irq(&cgwb_lock);
 	}
 	spin_unlock_irq(&cgwb_lock);
+	mutex_unlock(&bdi->cgwb_release_mutex);
 }
 
 /**