From: Ralf Baechle <ralf@linux-mips.org>

wake_up's implementation does an implicit memory barrier and I think that's
the only sane semantics as the caller shouldn't have to worry.  So this
write memory barrier is useless.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Cc: David Chinner <dgc@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---

 fs/xfs/linux-2.6/xfs_super.c |    1 -
 1 file changed, 1 deletion(-)

diff -puN fs/xfs/linux-2.6/xfs_super.c~xfs-remove-useless-wmb-memory-barrier fs/xfs/linux-2.6/xfs_super.c
--- a/fs/xfs/linux-2.6/xfs_super.c~xfs-remove-useless-wmb-memory-barrier
+++ a/fs/xfs/linux-2.6/xfs_super.c
@@ -553,7 +553,6 @@ vfs_sync_worker(
 		error = bhv_vfs_sync(vfsp, SYNC_FSDATA | SYNC_BDFLUSH | \
 					SYNC_ATTR | SYNC_REFCACHE, NULL);
 	vfsp->vfs_sync_seq++;
-	wmb();
 	wake_up(&vfsp->vfs_wait_single_sync_task);
 }
 
_