From 56c0908c855afbb2bdda17c15d2879949a091ad3 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 26 Feb 2018 13:01:41 +0100 Subject: genhd: Fix BUG in blkdev_open() When two blkdev_open() calls for a partition race with device removal and recreation, we can hit BUG_ON(!bd_may_claim(bdev, whole, holder)) in blkdev_open(). The race can happen as follows: CPU0 CPU1 CPU2 del_gendisk() bdev_unhash_inode(part1); blkdev_open(part1, O_EXCL) blkdev_open(part1, O_EXCL) bdev = bd_acquire() bdev = bd_acquire() blkdev_get(bdev) bd_start_claiming(bdev) - finds old inode 'whole' bd_prepare_to_claim() -> 0 bdev_unhash_inode(whole); blkdev_get(bdev); bd_start_claiming(bdev) - finds new inode 'whole' bd_prepare_to_claim() - this also succeeds as we have different 'whole' here... - bad things happen now as we have two exclusive openers of the same bdev The problem here is that block device opens can see various intermediate states while gendisk is shutting down and then being recreated. We fix the problem by introducing new lookup_sem in gendisk that synchronizes gendisk deletion with get_gendisk() and furthermore by making sure that get_gendisk() does not return gendisk that is being (or has been) deleted. This makes sure that once we ever manage to look up newly created bdev inode, we are also guaranteed that following get_gendisk() will either return failure (and we fail open) or it returns gendisk for the new device and following bdget_disk() will return new bdev inode (i.e., blkdev_open() follows the path as if it is completely run after new device is created). Reported-and-analyzed-by: Hou Tao Tested-by: Hou Tao Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- block/genhd.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'block/genhd.c') diff --git a/block/genhd.c b/block/genhd.c index 4c05904345916..9656f9e9f99e2 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -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"); @@ -816,9 +822,21 @@ struct gendisk *get_gendisk(dev_t devt, int *partno) spin_unlock_bh(&ext_devt_lock); } - if (disk && unlikely(disk->flags & GENHD_FL_HIDDEN)) { + 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); -- cgit v1.2.3