Messages in this thread Patch in this message | | | From | Jaegeuk Kim <> | Subject | [PATCH 04/09] f2fs: fix race conditon on truncation with inline_data | Date | Sun, 19 Oct 2014 22:18:27 -0700 |
| |
Let's consider the following scenario.
blkaddr[0] inline_data i_size i_blocks writepage truncate NEW X 4096 2 dirty page #0 NEW X 0 change i_size NEW X 0 2 f2fs_write_inline_data NEW X 0 2 get_dnode_of_data NEW X 0 2 truncate_data_blocks_range NULL O 0 1 memcpy(inline_data) NULL O 0 1 f2fs_put_dnode NULL O 0 1 f2fs_truncate NULL O 0 1 get_dnode_of_data NULL O 0 1 *invalid block addr*
This patch adds checking inline_data flag during f2fs_truncate not to refer corrupted block indices.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> --- fs/f2fs/file.c | 6 ++++++ 1 file changed, 6 insertions(+)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 8e68bb6..543d8c6 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -473,6 +473,12 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) return err; } + /* writepage can convert inline_data under get_donde_of_data */ + if (f2fs_has_inline_data(inode)) { + f2fs_put_dnode(&dn); + goto done; + } + count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); count -= dn.ofs_in_node; -- 2.1.1
| |