Merge tag 'for-linus-20180302' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A collection of fixes for this series. This is a little larger than
  usual at this time, but that's mainly because I was out on vacation
  last week. Nothing in here is major in any way, it's just two weeks of
  fixes. This contains:

   - NVMe pull from Keith, with a set of fixes from the usual suspects.

   - mq-deadline zone unlock fix from Damien, fixing an issue with the
     SMR zone locking added for 4.16.

   - two bcache fixes sent in by Michael, with changes from Coly and
     Tang.

   - comment typo fix from Eric for blktrace.

   - return-value error handling fix for nbd, from Gustavo.

   - fix a direct-io case where we don't defer to a completion handler,
     making us sleep from IRQ device completion. From Jan.

   - a small series from Jan fixing up holes around handling of bdev
     references.

   - small set of regression fixes from Jiufei, mostly fixing problems
     around the gendisk pointer -> partition index change.

   - regression fix from Ming, fixing a boundary issue with the discard
     page cache invalidation.

   - two-patch series from Ming, fixing both a core blk-mq-sched and
     kyber issue around token freeing on a requeue condition"

* tag 'for-linus-20180302' of git://git.kernel.dk/linux-block: (24 commits)
  block: fix a typo
  block: display the correct diskname for bio
  block: fix the count of PGPGOUT for WRITE_SAME
  mq-deadline: Make sure to always unlock zones
  nvmet: fix PSDT field check in command format
  nvme-multipath: fix sysfs dangerously created links
  nbd: fix return value in error handling path
  bcache: fix kcrashes with fio in RAID5 backend dev
  bcache: correct flash only vols (check all uuids)
  blktrace_api.h: fix comment for struct blk_user_trace_setup
  blockdev: Avoid two active bdev inodes for one device
  genhd: Fix BUG in blkdev_open()
  genhd: Fix use after free in __blkdev_get()
  genhd: Add helper put_disk_and_module()
  genhd: Rename get_disk() to get_disk_and_module()
  genhd: Fix leaked module reference for NVME devices
  direct-io: Fix sleep in atomic due to sync AIO
  nvme-pci: Fix nvme queue cleanup if IRQ setup fails
  block: kyber: fix domain token leak during requeue
  blk-mq: don't call io sched's .requeue_request when requeueing rq to ->dispatch
  ...

block/blk-cgroup.c

@@ -812,7 +812,6 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	struct gendisk *disk;
 	struct request_queue *q;
 	struct blkcg_gq *blkg;
-	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;
@@ -904,9 +903,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	spin_unlock_irq(q->queue_lock);
 	rcu_read_unlock();
 fail:
-	owner = disk->fops->owner;
-	put_disk(disk);
-	module_put(owner);
+	put_disk_and_module(disk);
 	/*
 	 * If queue was bypassing, we should retry.  Do so after a
 	 * short msleep().  It isn't strictly necessary but queue
@@ -931,13 +928,9 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
-	struct module *owner;
-
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
-	owner = ctx->disk->fops->owner;
-	put_disk(ctx->disk);
-	module_put(owner);
+	put_disk_and_module(ctx->disk);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 

block/blk-core.c

@@ -2434,7 +2434,7 @@ blk_qc_t submit_bio(struct bio *bio)
 		unsigned int count;
 
 		if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
-			count = queue_logical_block_size(bio->bi_disk->queue);
+			count = queue_logical_block_size(bio->bi_disk->queue) >> 9;
 		else
 			count = bio_sectors(bio);
 

block/blk-mq.c

@@ -712,7 +712,6 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 	trace_block_rq_requeue(q, rq);
 	wbt_requeue(q->rq_wb, &rq->issue_stat);
-	blk_mq_sched_requeue_request(rq);
 
 	if (blk_mq_rq_state(rq) != MQ_RQ_IDLE) {
 		blk_mq_rq_update_state(rq, MQ_RQ_IDLE);
@@ -725,6 +724,9 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
 {
 	__blk_mq_requeue_request(rq);
 
+	/* this request will be re-inserted to io scheduler queue */
+	blk_mq_sched_requeue_request(rq);
+
 	BUG_ON(blk_queued_rq(rq));
 	blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
 }

block/genhd.c

@@ -547,7 +547,7 @@ static int exact_lock(dev_t devt, void *data)
 {
 	struct gendisk *p = data;
 
-	if (!get_disk(p))
+	if (!get_disk_and_module(p))
 		return -1;
 	return 0;
 }
@@ -717,6 +717,11 @@ void del_gendisk(struct gendisk *disk)
 	blk_integrity_del(disk);
 	disk_del_events(disk);
 
+	/*
+	 * Block lookups of the disk until all bdevs are unhashed and the
+	 * disk is marked as dead (GENHD_FL_UP cleared).
+	 */
+	down_write(&disk->lookup_sem);
 	/* invalidate stuff */
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
@@ -731,6 +736,7 @@ void del_gendisk(struct gendisk *disk)
 	bdev_unhash_inode(disk_devt(disk));
 	set_capacity(disk, 0);
 	disk->flags &= ~GENHD_FL_UP;
+	up_write(&disk->lookup_sem);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN))
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -809,16 +815,28 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 
 		spin_lock_bh(&ext_devt_lock);
 		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		if (part && get_disk(part_to_disk(part))) {
+		if (part && get_disk_and_module(part_to_disk(part))) {
 			*partno = part->partno;
 			disk = part_to_disk(part);
 		}
 		spin_unlock_bh(&ext_devt_lock);
 	}
 
-	if (disk && unlikely(disk->flags & GENHD_FL_HIDDEN)) {
-		put_disk(disk);
+	if (!disk)
+		return NULL;
+
+	/*
+	 * Synchronize with del_gendisk() to not return disk that is being
+	 * destroyed.
+	 */
+	down_read(&disk->lookup_sem);
+	if (unlikely((disk->flags & GENHD_FL_HIDDEN) ||
+		     !(disk->flags & GENHD_FL_UP))) {
+		up_read(&disk->lookup_sem);
+		put_disk_and_module(disk);
 		disk = NULL;
+	} else {
+		up_read(&disk->lookup_sem);
 	}
 	return disk;
 }
@@ -1418,6 +1436,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 			kfree(disk);
 			return NULL;
 		}
+		init_rwsem(&disk->lookup_sem);
 		disk->node_id = node_id;
 		if (disk_expand_part_tbl(disk, 0)) {
 			free_part_stats(&disk->part0);
@@ -1453,7 +1472,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 }
 EXPORT_SYMBOL(__alloc_disk_node);
 
-struct kobject *get_disk(struct gendisk *disk)
+struct kobject *get_disk_and_module(struct gendisk *disk)
 {
 	struct module *owner;
 	struct kobject *kobj;
@@ -1471,17 +1490,30 @@ struct kobject *get_disk(struct gendisk *disk)
 	return kobj;
 
 }
-
-EXPORT_SYMBOL(get_disk);
+EXPORT_SYMBOL(get_disk_and_module);
 
 void put_disk(struct gendisk *disk)
 {
 	if (disk)
 		kobject_put(&disk_to_dev(disk)->kobj);
 }
-
 EXPORT_SYMBOL(put_disk);
 
+/*
+ * This is a counterpart of get_disk_and_module() and thus also of
+ * get_gendisk().
+ */
+void put_disk_and_module(struct gendisk *disk)
+{
+	if (disk) {
+		struct module *owner = disk->fops->owner;
+
+		put_disk(disk);
+		module_put(owner);
+	}
+}
+EXPORT_SYMBOL(put_disk_and_module);
+
 static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 {
 	char event[] = "DISK_RO=1";

block/ioctl.c

@@ -225,7 +225,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 
 	if (start + len > i_size_read(bdev->bd_inode))
 		return -EINVAL;
-	truncate_inode_pages_range(mapping, start, start + len);
+	truncate_inode_pages_range(mapping, start, start + len - 1);
 	return blkdev_issue_discard(bdev, start >> 9, len >> 9,
 				    GFP_KERNEL, flags);
 }

block/kyber-iosched.c

@@ -833,6 +833,7 @@ static struct elevator_type kyber_sched = {
 		.limit_depth = kyber_limit_depth,
 		.prepare_request = kyber_prepare_request,
 		.finish_request = kyber_finish_request,
+		.requeue_request = kyber_finish_request,
 		.completed_request = kyber_completed_request,
 		.dispatch_request = kyber_dispatch_request,
 		.has_work = kyber_has_work,

block/mq-deadline.c

@@ -535,13 +535,22 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 	spin_unlock(&dd->lock);
 }
 
+/*
+ * Nothing to do here. This is defined only to ensure that .finish_request
+ * method is called upon request completion.
+ */
+static void dd_prepare_request(struct request *rq, struct bio *bio)
+{
+}
+
 /*
  * For zoned block devices, write unlock the target zone of
  * completed write requests. Do this while holding the zone lock
  * spinlock so that the zone is never unlocked while deadline_fifo_request()
- * while deadline_next_request() are executing.
+ * or deadline_next_request() are executing. This function is called for
+ * all requests, whether or not these requests complete successfully.
  */
-static void dd_completed_request(struct request *rq)
+static void dd_finish_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
@@ -756,7 +765,8 @@ static struct elevator_type mq_deadline = {
 	.ops.mq = {
 		.insert_requests	= dd_insert_requests,
 		.dispatch_request	= dd_dispatch_request,
-		.completed_request	= dd_completed_request,
+		.prepare_request	= dd_prepare_request,
+		.finish_request		= dd_finish_request,
 		.next_request		= elv_rb_latter_request,
 		.former_request		= elv_rb_former_request,
 		.bio_merge		= dd_bio_merge,

block/partition-generic.c

@@ -51,6 +51,12 @@ const char *bdevname(struct block_device *bdev, char *buf)
 
 EXPORT_SYMBOL(bdevname);
 
+const char *bio_devname(struct bio *bio, char *buf)
+{
+	return disk_name(bio->bi_disk, bio->bi_partno, buf);
+}
+EXPORT_SYMBOL(bio_devname);
+
 /*
  * There's very little reason to use this, you should really
  * have a struct block_device just about everywhere and use

drivers/block/amiflop.c

@@ -1758,7 +1758,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data)
 	if (unit[drive].type->code == FD_NODRIVE)
 		return NULL;
 	*part = 0;
-	return get_disk(unit[drive].gendisk);
+	return get_disk_and_module(unit[drive].gendisk);
 }
 
 static int __init amiga_floppy_probe(struct platform_device *pdev)

drivers/block/ataflop.c

@@ -1917,7 +1917,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data)
 	if (drive >= FD_MAX_UNITS || type > NUM_DISK_MINORS)
 		return NULL;
 	*part = 0;
-	return get_disk(unit[drive].disk);
+	return get_disk_and_module(unit[drive].disk);
 }
 
 static int __init atari_floppy_init (void)

drivers/block/brd.c

@@ -456,7 +456,7 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 
 	mutex_lock(&brd_devices_mutex);
 	brd = brd_init_one(MINOR(dev) / max_part, &new);
-	kobj = brd ? get_disk(brd->brd_disk) : NULL;
+	kobj = brd ? get_disk_and_module(brd->brd_disk) : NULL;
 	mutex_unlock(&brd_devices_mutex);
 
 	if (new)

drivers/block/floppy.c

@@ -4505,7 +4505,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data)
 	if (((*part >> 2) & 0x1f) >= ARRAY_SIZE(floppy_type))
 		return NULL;
 	*part = 0;
-	return get_disk(disks[drive]);
+	return get_disk_and_module(disks[drive]);
 }
 
 static int __init do_floppy_init(void)

drivers/block/loop.c

@@ -1922,7 +1922,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
 	if (err < 0)
 		kobj = NULL;
 	else
-		kobj = get_disk(lo->lo_disk);
+		kobj = get_disk_and_module(lo->lo_disk);
 	mutex_unlock(&loop_index_mutex);
 
 	*part = 0;

drivers/block/nbd.c

@@ -1591,7 +1591,7 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 			if (new_index < 0) {
 				mutex_unlock(&nbd_index_mutex);
 				printk(KERN_ERR "nbd: failed to add new device\n");
-				return ret;
+				return new_index;
 			}
 			nbd = idr_find(&nbd_index_idr, new_index);
 		}

drivers/block/pktcdvd.c

@@ -1122,7 +1122,7 @@ static int pkt_start_recovery(struct packet_data *pkt)
 	pkt->sector = new_sector;
 
 	bio_reset(pkt->bio);
-	bio_set_set(pkt->bio, pd->bdev);
+	bio_set_dev(pkt->bio, pd->bdev);
 	bio_set_op_attrs(pkt->bio, REQ_OP_WRITE, 0);
 	pkt->bio->bi_iter.bi_sector = new_sector;
 	pkt->bio->bi_iter.bi_size = pkt->frames * CD_FRAMESIZE;

drivers/block/swim.c

@@ -799,7 +799,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data)
 		return NULL;
 
 	*part = 0;
-	return get_disk(swd->unit[drive].disk);
+	return get_disk_and_module(swd->unit[drive].disk);
 }
 
 static int swim_add_floppy(struct swim_priv *swd, enum drive_location location)

drivers/block/z2ram.c

@@ -332,7 +332,7 @@ static const struct block_device_operations z2_fops =
 static struct kobject *z2_find(dev_t dev, int *part, void *data)
 {
 	*part = 0;
-	return get_disk(z2ram_gendisk);
+	return get_disk_and_module(z2ram_gendisk);
 }
 
 static struct request_queue *z2_queue;

drivers/ide/ide-probe.c

@@ -928,7 +928,7 @@ static int exact_lock(dev_t dev, void *data)
 {
 	struct gendisk *p = data;
 
-	if (!get_disk(p))
+	if (!get_disk_and_module(p))
 		return -1;
 	return 0;
 }

drivers/md/bcache/request.c

@@ -659,11 +659,11 @@ static void do_bio_hook(struct search *s, struct bio *orig_bio)
 static void search_free(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
-	bio_complete(s);
 
 	if (s->iop.bio)
 		bio_put(s->iop.bio);
 
+	bio_complete(s);
 	closure_debug_destroy(cl);
 	mempool_free(s, s->d->c->search);
 }

drivers/md/bcache/super.c

@@ -1274,7 +1274,7 @@ static int flash_devs_run(struct cache_set *c)
 	struct uuid_entry *u;
 
 	for (u = c->uuids;
-	     u < c->uuids + c->devices_max_used && !ret;
+	     u < c->uuids + c->nr_uuids && !ret;
 	     u++)
 		if (UUID_FLASH_ONLY(u))
 			ret = flash_dev_run(c, u);

drivers/nvme/host/core.c

@@ -2844,7 +2844,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 }
 
 static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
-		struct nvme_id_ns *id, bool *new)
+		struct nvme_id_ns *id)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	bool is_shared = id->nmic & (1 << 0);
@@ -2860,8 +2860,6 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 			ret = PTR_ERR(head);
 			goto out_unlock;
 		}
-
-		*new = true;
 	} else {
 		struct nvme_ns_ids ids;
 
@@ -2873,8 +2871,6 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 			ret = -EINVAL;
 			goto out_unlock;
 		}
-
-		*new = false;
 	}
 
 	list_add_tail(&ns->siblings, &head->list);
@@ -2945,7 +2941,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	struct nvme_id_ns *id;
 	char disk_name[DISK_NAME_LEN];
 	int node = dev_to_node(ctrl->dev), flags = GENHD_FL_EXT_DEVT;
-	bool new = true;
 
 	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
@@ -2971,7 +2966,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	if (id->ncap == 0)
 		goto out_free_id;
 
-	if (nvme_init_ns_head(ns, nsid, id, &new))
+	if (nvme_init_ns_head(ns, nsid, id))
 		goto out_free_id;
 	nvme_setup_streams_ns(ctrl, ns);
 	
@@ -3037,8 +3032,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
 			ns->disk->disk_name);
 
-	if (new)
-		nvme_mpath_add_disk(ns->head);
+	nvme_mpath_add_disk(ns->head);
 	nvme_mpath_add_disk_links(ns);
 	return;
  out_unlink_ns:

drivers/nvme/host/fabrics.c

@@ -493,7 +493,7 @@ EXPORT_SYMBOL_GPL(nvmf_should_reconnect);
  */
 int nvmf_register_transport(struct nvmf_transport_ops *ops)
 {
-	if (!ops->create_ctrl || !ops->module)
+	if (!ops->create_ctrl)
 		return -EINVAL;
 
 	down_write(&nvmf_transports_rwsem);

drivers/nvme/host/multipath.c

@@ -198,11 +198,16 @@ void nvme_mpath_add_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	device_add_disk(&head->subsys->dev, head->disk);
-	if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
-			&nvme_ns_id_attr_group))
-		pr_warn("%s: failed to create sysfs group for identification\n",
-			head->disk->disk_name);
+
+	mutex_lock(&head->subsys->lock);
+	if (!(head->disk->flags & GENHD_FL_UP)) {
+		device_add_disk(&head->subsys->dev, head->disk);
+		if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
+				&nvme_ns_id_attr_group))
+			pr_warn("%s: failed to create sysfs group for identification\n",
+				head->disk->disk_name);
+	}
+	mutex_unlock(&head->subsys->lock);
 }
 
 void nvme_mpath_add_disk_links(struct nvme_ns *ns)

drivers/nvme/host/pci.c

@@ -1459,7 +1459,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	nvmeq->cq_vector = qid - 1;
 	result = adapter_alloc_cq(dev, qid, nvmeq);
 	if (result < 0)
-		return result;
+		goto release_vector;
 
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
@@ -1473,9 +1473,12 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	return result;
 
  release_sq:
+	dev->online_queues--;
 	adapter_delete_sq(dev, qid);
  release_cq:
 	adapter_delete_cq(dev, qid);
+ release_vector:
+	nvmeq->cq_vector = -1;
 	return result;
 }
 

drivers/nvme/host/rdma.c

@@ -1051,7 +1051,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
 	struct nvme_rdma_device *dev = queue->device;
 	struct ib_device *ibdev = dev->dev;
 
-	if (!blk_rq_bytes(rq))
+	if (!blk_rq_payload_bytes(rq))
 		return;
 
 	if (req->mr) {
@@ -1166,7 +1166,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 
 	c->common.flags |= NVME_CMD_SGL_METABUF;
 
-	if (!blk_rq_bytes(rq))
+	if (!blk_rq_payload_bytes(rq))
 		return nvme_rdma_set_sg_null(c);
 
 	req->sg_table.sgl = req->first_sgl;

drivers/nvme/target/core.c

@@ -520,9 +520,12 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 		goto fail;
 	}
 
-	/* either variant of SGLs is fine, as we don't support metadata */
-	if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF &&
-		     (flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METASEG)) {
+	/*
+	 * For fabrics, PSDT field shall describe metadata pointer (MPTR) that
+	 * contains an address of a single contiguous physical buffer that is
+	 * byte aligned.
+	 */
+	if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) {
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		goto fail;
 	}

drivers/nvme/target/loop.c

@@ -184,7 +184,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		return BLK_STS_OK;
 	}
 
-	if (blk_rq_bytes(req)) {
+	if (blk_rq_payload_bytes(req)) {
 		iod->sg_table.sgl = iod->first_sgl;
 		if (sg_alloc_table_chained(&iod->sg_table,
 				blk_rq_nr_phys_segments(req),
@@ -193,7 +193,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 		iod->req.sg = iod->sg_table.sgl;
 		iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl);
-		iod->req.transfer_len = blk_rq_bytes(req);
+		iod->req.transfer_len = blk_rq_payload_bytes(req);
 	}
 
 	blk_mq_start_request(req);

fs/block_dev.c

@@ -1058,6 +1058,27 @@ static int bd_prepare_to_claim(struct block_device *bdev,
 	return 0;
 }
 
+static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno)
+{
+	struct gendisk *disk = get_gendisk(bdev->bd_dev, partno);
+
+	if (!disk)
+		return NULL;
+	/*
+	 * Now that we hold gendisk reference we make sure bdev we looked up is
+	 * not stale. If it is, it means device got removed and created before
+	 * we looked up gendisk and we fail open in such case. Associating
+	 * unhashed bdev with newly created gendisk could lead to two bdevs
+	 * (and thus two independent caches) being associated with one device
+	 * which is bad.
+	 */
+	if (inode_unhashed(bdev->bd_inode)) {
+		put_disk_and_module(disk);
+		return NULL;
+	}
+	return disk;
+}
+
 /**
  * bd_start_claiming - start claiming a block device
  * @bdev: block device of interest
@@ -1094,7 +1115,7 @@ static struct block_device *bd_start_claiming(struct block_device *bdev,
 	 * @bdev might not have been initialized properly yet, look up
 	 * and grab the outer block device the hard way.
 	 */
-	disk = get_gendisk(bdev->bd_dev, &partno);
+	disk = bdev_get_gendisk(bdev, &partno);
 	if (!disk)
 		return ERR_PTR(-ENXIO);
 
@@ -1111,8 +1132,7 @@ static struct block_device *bd_start_claiming(struct block_device *bdev,
 	else
 		whole = bdgrab(bdev);
 
-	module_put(disk->fops->owner);
-	put_disk(disk);
+	put_disk_and_module(disk);
 	if (!whole)
 		return ERR_PTR(-ENOMEM);
 
@@ -1407,10 +1427,10 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	struct gendisk *disk;
-	struct module *owner;
 	int ret;
 	int partno;
 	int perm = 0;
+	bool first_open = false;
 
 	if (mode & FMODE_READ)
 		perm |= MAY_READ;
@@ -1430,14 +1450,14 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
  restart:
 
 	ret = -ENXIO;
-	disk = get_gendisk(bdev->bd_dev, &partno);
+	disk = bdev_get_gendisk(bdev, &partno);
 	if (!disk)
 		goto out;
-	owner = disk->fops->owner;
 
 	disk_block_events(disk);
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (!bdev->bd_openers) {
+		first_open = true;
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
@@ -1463,8 +1483,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 					bdev->bd_queue = NULL;
 					mutex_unlock(&bdev->bd_mutex);
 					disk_unblock_events(disk);
-					put_disk(disk);
-					module_put(owner);
+					put_disk_and_module(disk);
 					goto restart;
 				}
 			}
@@ -1524,15 +1543,15 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (ret)
 				goto out_unlock_bdev;
 		}
-		/* only one opener holds refs to the module and disk */
-		put_disk(disk);
-		module_put(owner);
 	}
 	bdev->bd_openers++;
 	if (for_part)
 		bdev->bd_part_count++;
 	mutex_unlock(&bdev->bd_mutex);
 	disk_unblock_events(disk);
+	/* only one opener holds refs to the module and disk */
+	if (!first_open)
+		put_disk_and_module(disk);
 	return 0;
 
  out_clear:
@@ -1546,8 +1565,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
  out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
 	disk_unblock_events(disk);
-	put_disk(disk);
-	module_put(owner);
+	put_disk_and_module(disk);
  out:
 	bdput(bdev);
 
@@ -1770,8 +1788,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 			disk->fops->release(disk, mode);
 	}
 	if (!bdev->bd_openers) {
-		struct module *owner = disk->fops->owner;
-
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
 		bdev->bd_disk = NULL;
@@ -1779,8 +1795,7 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 			victim = bdev->bd_contains;
 		bdev->bd_contains = NULL;
 
-		put_disk(disk);
-		module_put(owner);
+		put_disk_and_module(disk);
 	}
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);

fs/direct-io.c

@@ -1274,8 +1274,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	 */
 	if (dio->is_async && iov_iter_rw(iter) == WRITE) {
 		retval = 0;
-		if ((iocb->ki_filp->f_flags & O_DSYNC) ||
-		    IS_SYNC(iocb->ki_filp->f_mapping->host))
+		if (iocb->ki_flags & IOCB_DSYNC)
 			retval = dio_set_defer_completion(dio);
 		else if (!dio->inode->i_sb->s_dio_done_wq) {
 			/*

include/linux/bio.h

@@ -511,6 +511,7 @@ void zero_fill_bio(struct bio *bio);
 extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
 extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
+extern const char *bio_devname(struct bio *bio, char *buffer);
 
 #define bio_set_dev(bio, bdev) 			\
 do {						\
@@ -529,9 +530,6 @@ do {						\
 #define bio_dev(bio) \
 	disk_devt((bio)->bi_disk)
 
-#define bio_devname(bio, buf) \
-	__bdevname(bio_dev(bio), (buf))
-
 #ifdef CONFIG_BLK_CGROUP
 int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
 void bio_disassociate_task(struct bio *bio);

include/linux/genhd.h

@@ -198,6 +198,7 @@ struct gendisk {
 	void *private_data;
 
 	int flags;
+	struct rw_semaphore lookup_sem;
 	struct kobject *slave_dir;
 
 	struct timer_rand_state *random;
@@ -600,8 +601,9 @@ extern void delete_partition(struct gendisk *, int);
 extern void printk_all_partitions(void);
 
 extern struct gendisk *__alloc_disk_node(int minors, int node_id);
-extern struct kobject *get_disk(struct gendisk *disk);
+extern struct kobject *get_disk_and_module(struct gendisk *disk);
 extern void put_disk(struct gendisk *disk);
+extern void put_disk_and_module(struct gendisk *disk);
 extern void blk_register_region(dev_t devt, unsigned long range,
 			struct module *module,
 			struct kobject *(*probe)(dev_t, int *, void *),

include/uapi/linux/blktrace_api.h

@@ -131,7 +131,7 @@ enum {
 #define BLKTRACE_BDEV_SIZE	32
 
 /*
- * User setup structure passed with BLKTRACESTART
+ * User setup structure passed with BLKTRACESETUP
  */
 struct blk_user_trace_setup {
 	char name[BLKTRACE_BDEV_SIZE];	/* output */