diff options
| author | Chao Yu <chao2.yu@samsung.com> | 2014-03-29 15:30:40 +0800 |
|---|---|---|
| committer | Ziyan <jaraidaniel@gmail.com> | 2015-05-02 14:36:41 +0200 |
| commit | 34fa2015dd0fa2ce092d6004bb3c702aac2ee44c (patch) | |
| tree | e1c0db59f6f2fd9201d051e8825d708d6ee796c4 /fs | |
| parent | b52876502c6e24b0e260af45afda818275e44394 (diff) | |
| download | kernel_samsung_tuna-34fa2015dd0fa2ce092d6004bb3c702aac2ee44c.zip kernel_samsung_tuna-34fa2015dd0fa2ce092d6004bb3c702aac2ee44c.tar.gz kernel_samsung_tuna-34fa2015dd0fa2ce092d6004bb3c702aac2ee44c.tar.bz2 | |
f2fs: fix error path when fail to read inline data
We should unlock page in ->readpage() path and also should unlock & release page
in error path of ->write_begin() to avoid deadlock or memory leak.
So let's add release code to fix the problem when we fail to read inline data.
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Diffstat (limited to 'fs')
| -rw-r--r-- | fs/f2fs/data.c | 14 | ||||
| -rw-r--r-- | fs/f2fs/inline.c | 4 |
2 files changed, 13 insertions, 5 deletions
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ea58787..f451e71 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -947,13 +947,19 @@ inline_data: if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); } else { - if (f2fs_has_inline_data(inode)) + if (f2fs_has_inline_data(inode)) { err = f2fs_read_inline_data(inode, page); - else + if (err) { + page_cache_release(page); + return err; + } + } else { err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, READ_SYNC); - if (err) - return err; + if (err) + return err; + } + lock_page(page); if (unlikely(!PageUptodate(page))) { f2fs_put_page(page, 1); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 31ee5b1..383db1f 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -45,8 +45,10 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) } ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) + if (IS_ERR(ipage)) { + unlock_page(page); return PTR_ERR(ipage); + } zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); |