f2fs: fix double lock in handle_failed_inode
In handle_failed_inode, there is a potential deadlock which can happen
in below call path:
- f2fs_create
- f2fs_lock_op down_read(cp_rwsem)
- f2fs_add_link
- __f2fs_add_link
- init_inode_metadata
- f2fs_init_security failed
- truncate_blocks failed
- handle_failed_inode
- f2fs_truncate
- truncate_blocks(..,true)
- write_checkpoint
- block_operations
- f2fs_lock_all down_write(cp_rwsem)
- f2fs_lock_op down_read(cp_rwsem)
So in this path, we pass parameter to f2fs_truncate to make sure
cp_rwsem in truncate_blocks will not be locked again.
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 0083b85..12eb69d 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -467,7 +467,7 @@
i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
- f2fs_truncate(inode);
+ f2fs_truncate(inode, true);
sb_end_intwrite(inode->i_sb);