diff options
| author | Chao Yu <chao2.yu@samsung.com> | 2015-07-16 18:19:02 +0800 |
|---|---|---|
| committer | Jaegeuk Kim <jaegeuk@kernel.org> | 2015-08-05 08:08:09 -0700 |
| commit | 55f57d2c4259a9a4048cf4629a2c6ba53729188d (patch) | |
| tree | 00308a663bd758c81f7c9bcc90d66b8dc7f52f0d /fs/f2fs/inode.c | |
| parent | ecbaa4068f88f96a8ffde37d532e618508394b53 (diff) | |
| download | linux-55f57d2c4259a9a4048cf4629a2c6ba53729188d.tar.gz linux-55f57d2c4259a9a4048cf4629a2c6ba53729188d.tar.bz2 linux-55f57d2c4259a9a4048cf4629a2c6ba53729188d.zip | |
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>
Diffstat (limited to 'fs/f2fs/inode.c')
| -rw-r--r-- | fs/f2fs/inode.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 5b7547f0bdea..cc4f1082419a 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -343,7 +343,7 @@ void f2fs_evict_inode(struct inode *inode) i_size_write(inode, 0); if (F2FS_HAS_BLOCKS(inode)) - f2fs_truncate(inode); + f2fs_truncate(inode, true); f2fs_lock_op(sbi); remove_inode_page(inode); @@ -385,7 +385,7 @@ void handle_failed_inode(struct inode *inode) i_size_write(inode, 0); if (F2FS_HAS_BLOCKS(inode)) - f2fs_truncate(inode); + f2fs_truncate(inode, false); remove_inode_page(inode); |