Commit 764d2c80 authored Nov 11, 2014 by Jaegeuk Kim

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>

parent 57e2a2c0

fs/f2fs/file.c

+3 −5

Original line number	Diff line number	Diff line
		@@ -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;

Admin message