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
  ...

8 files changed, 67 insertions, 23 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4117524ca45b..c2033a232a44 100644
--- a/block/blk-cgroup.c
+++ b/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 @@ fail_unlock:
 	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);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 2d1a7bbe0634..6d82c4f7fadd 100644
--- a/block/blk-core.c
+++ b/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);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 357492712b0e..16e83e6df404 100644
--- a/block/blk-mq.c
+++ b/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);
 }
diff --git a/block/genhd.c b/block/genhd.c
index 88a53c188cb7..9656f9e9f99e 100644
--- a/block/genhd.c
+++ b/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";
diff --git a/block/ioctl.c b/block/ioctl.c
index 1668506d8ed8..3884d810efd2 100644
--- a/block/ioctl.c
+++ b/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);
 }
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index f95c60774ce8..0d6d25e32e1f 100644
--- a/block/kyber-iosched.c
+++ b/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,
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index c56f211c8440..8ec0ba9f5386 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -536,12 +536,21 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 }
 
 /*
+ * 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,
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 91622db9aedf..08dabcd8b6ae 100644
--- a/block/partition-generic.c
+++ b/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