diff options
| author | Jaegeuk Kim | 2014-11-11 11:01:01 -0800 |
|---|---|---|
| committer | Jaegeuk Kim | 2014-11-11 14:15:48 -0800 |
| commit | 764d2c80401fcc7ee15933d604c6a783d5addc40 (patch) | |
| tree | 4f2c237c79c273d32326cd72dcad2801009f702a | |
| parent | 57e2a2c0a698406e6206ab707bd7c3dcf248c738 (diff) | |
f2fs: fix deadlock to grab 0'th data page
The scenario is like this.
One trhead triggers:
f2fs_write_data_pages
lock_page
f2fs_write_data_page
f2fs_lock_op <- wait
The other thread triggers:
f2fs_truncate
truncate_blocks
f2fs_lock_op
truncate_partial_data_page
lock_page <- wait for locking the page
This patch resolves this bug by relocating truncate_partial_data_page.
This function is just to truncate user data page and not related to FS
consistency as well.
And, we don't need to call truncate_inline_data. Rather than that,
f2fs_write_data_page will finally update inline_data later.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
| -rw-r--r-- | fs/f2fs/file.c | 8 |
1 files changed, 3 insertions, 5 deletions
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 54722a0a5be5..edc3ce867e9c 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -477,8 +477,6 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) } if (f2fs_has_inline_data(inode)) { - truncate_inline_data(ipage, from); - update_inode(inode, ipage); f2fs_put_page(ipage, 1); goto out; } @@ -504,13 +502,13 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) f2fs_put_dnode(&dn); free_next: err = truncate_inode_blocks(inode, free_from); +out: + if (lock) + f2fs_unlock_op(sbi); /* lastly zero out the first data page */ if (!err) err = truncate_partial_data_page(inode, from); -out: - if (lock) - f2fs_unlock_op(sbi); trace_f2fs_truncate_blocks_exit(inode, err); return err; |