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
  ...

1 files changed, 40 insertions, 8 deletions

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";