On Mon, Jun 20, 2011 at 02:32:03PM -0700, Joel Becker wrote:

	Are we guaranteed that all allocation changes are locked out by
i_dio_count>0?  I don't think we are.  The ocfs2 code very strongly
assumes the state of a file's allocation when it holds i_alloc_sem.  I
feel like we lose that here. 

You aren't, neither with the old i_alloc_sem code, nor with the 1:1
replacement using i_dio_count.

Do a quick grep who gets i_alloc_sem exclusively (down_write): it's
really just the truncate code, and it's cut & paste duplicates in ntfs
and reiserfs.