[Ocfs2-devel] [patch 08/11] ocfs2: should call ocfs2_journal_access_di() before ocfs2_delete_entry() in ocfs2_orphan_del()

[Younger Liu]

On 2014/2/7 7:28, Mark Fasheh wrote:
> On Fri, Jan 24, 2014 at 12:47:07PM -0800, akpm at linux-foundation.org wrote:
>> From: Younger Liu <younger.liu at huawei.com>
>> Subject: ocfs2: should call ocfs2_journal_access_di() before ocfs2_delete_entry() in ocfs2_orphan_del()
>>
>> While deleting a file into orphan dir in ocfs2_orphan_del(), it calls
>> ocfs2_delete_entry() before ocfs2_journal_access_di().  If
>> ocfs2_delete_entry() succeeded and ocfs2_journal_access_di() failed, there
>> would be a inconsistency: the file is deleted from orphan dir, but orphan
>> dir dinode is not updated.
>>
>> So we need to call ocfs2_journal_access_di() before ocfs2_orphan_del().
> 
> I am confused by this. Re-reading the code in fs/ocfs2/dir.c,
> __ocfs2_delete_entry() takes great pains to mark the buffer head as part of
> the journal:
> 
> 	ocfs2_journal_access_func access = ocfs2_journal_access_db;
> 
> 	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
> 		access = ocfs2_journal_access_di;
> 
> <snip>
> 
> 			status = access(handle, INODE_CACHE(dir), bh,
> 					OCFS2_JOURNAL_ACCESS_WRITE);
> 
> 
> Am I missing something here?
> 	--Mark
Hi Mark
   I am sorry to reply so late.
   I can understand your meaning, But if OCFS2_I(dir) is not inline
data, access = ocfs2_journal_access_db.
   Moreover, logically speaking, ocfs2_journal_access_di() should not
been called after ocfs2_delete_entry(). Otherwise, there is a potential
risk for inconsistency.

     --Younger
> 
> --
> Mark Fasheh
> 
> _______________________________________________
> Ocfs2-devel mailing list
> Ocfs2-devel at oss.oracle.com
> https://oss.oracle.com/mailman/listinfo/ocfs2-devel
>