korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-24 20:54:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

f2fs: fix deadlock to grab 0'th data page

Browse Source 
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>
This commit is contained in:
Jaegeuk Kim 2014-11-11 11:01:01 -08:00
parent 57e2a2c0a6
commit 764d2c8040
1 changed files with 3 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
fs/f2fs/file.c
View File

@ -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;