[PATCH 2/3] f2fs: fix deadlock to grab 0'th data page

[Jaegeuk Kim]

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@xxxxxxxxxx>
---
 fs/f2fs/file.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 54722a0..edc3ce8 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;
-- 
2.1.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/