blockdev: Fix livelocks on loop device
bd_set_size() updates also block device's block size. This is somewhat
unexpected from its name and at this point, only blkdev_open() uses this
functionality. Furthermore, this can result in changing block size under
a filesystem mounted on a loop device which leads to livelocks inside
__getblk_gfp() like:
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 10863 Comm: syz-executor0 Not tainted 4.18.0-rc5+ #151
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google
01/01/2011
RIP: 0010:__sanitizer_cov_trace_pc+0x3f/0x50 kernel/kcov.c:106
...
Call Trace:
init_page_buffers+0x3e2/0x530 fs/buffer.c:904
grow_dev_page fs/buffer.c:947 [inline]
grow_buffers fs/buffer.c:1009 [inline]
__getblk_slow fs/buffer.c:1036 [inline]
__getblk_gfp+0x906/0xb10 fs/buffer.c:1313
__bread_gfp+0x2d/0x310 fs/buffer.c:1347
sb_bread include/linux/buffer_head.h:307 [inline]
fat12_ent_bread+0x14e/0x3d0 fs/fat/fatent.c:75
fat_ent_read_block fs/fat/fatent.c:441 [inline]
fat_alloc_clusters+0x8ce/0x16e0 fs/fat/fatent.c:489
fat_add_cluster+0x7a/0x150 fs/fat/inode.c:101
__fat_get_block fs/fat/inode.c:148 [inline]
...
Trivial reproducer for the problem looks like:
truncate -s 1G /tmp/image
losetup /dev/loop0 /tmp/image
mkfs.ext4 -b 1024 /dev/loop0
mount -t ext4 /dev/loop0 /mnt
losetup -c /dev/loop0
l /mnt
Fix the problem by moving initialization of a block device block size
into a separate function and call it when needed.
Thanks to Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> for help with
debugging the problem.
Reported-by: syzbot+9933e4476f365f5d5a1b@syzkaller.appspotmail.com
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c546cdc..58a4c12 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -104,6 +104,20 @@ void invalidate_bdev(struct block_device *bdev)
}
EXPORT_SYMBOL(invalidate_bdev);
+static void set_init_blocksize(struct block_device *bdev)
+{
+ unsigned bsize = bdev_logical_block_size(bdev);
+ loff_t size = i_size_read(bdev->bd_inode);
+
+ while (bsize < PAGE_SIZE) {
+ if (size & bsize)
+ break;
+ bsize <<= 1;
+ }
+ bdev->bd_block_size = bsize;
+ bdev->bd_inode->i_blkbits = blksize_bits(bsize);
+}
+
int set_blocksize(struct block_device *bdev, int size)
{
/* Size must be a power of two, and between 512 and PAGE_SIZE */
@@ -1431,18 +1445,9 @@ EXPORT_SYMBOL(check_disk_change);
void bd_set_size(struct block_device *bdev, loff_t size)
{
- unsigned bsize = bdev_logical_block_size(bdev);
-
inode_lock(bdev->bd_inode);
i_size_write(bdev->bd_inode, size);
inode_unlock(bdev->bd_inode);
- while (bsize < PAGE_SIZE) {
- if (size & bsize)
- break;
- bsize <<= 1;
- }
- bdev->bd_block_size = bsize;
- bdev->bd_inode->i_blkbits = blksize_bits(bsize);
}
EXPORT_SYMBOL(bd_set_size);
@@ -1519,8 +1524,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
}
}
- if (!ret)
+ if (!ret) {
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+ set_init_blocksize(bdev);
+ }
/*
* If the device is invalidated, rescan partition
@@ -1555,6 +1562,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
goto out_clear;
}
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+ set_init_blocksize(bdev);
}
if (bdev->bd_bdi == &noop_backing_dev_info)