ocfs2: do not set OCFS2_LOCK_UPCONVERT_FINISHING if nonblocking lock can not be granted at once

ocfs2_readpages() use nonblocking flag to avoid page lock inversion.  It
will trigger cluster hang because that flag OCFS2_LOCK_UPCONVERT_FINISHING
is not cleared if nonblocking lock cannot be granted at once.  The flag
would prevent dc thread from downconverting.  So other nodes cannot
acheive this lockres for ever.

So we should not set OCFS2_LOCK_UPCONVERT_FINISHING when receiving ast if
nonblocking lock had already returned.

Signed-off-by: joyce.xue <xuejiufei@huawei.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/ocfs2/ocfs2.h

@@ -144,6 +144,12 @@ enum ocfs2_unlock_action {
 						     * before the upconvert
 						     * has completed */
 
+#define OCFS2_LOCK_NONBLOCK_FINISHED (0x00001000) /* NONBLOCK cluster
+						   * lock has already
+						   * returned, do not block
+						   * dc thread from
+						   * downconverting */
+
 struct ocfs2_lock_res_ops;
 
 typedef void (*ocfs2_lock_callback)(int status, unsigned long data);