Yes, I think this is correct. I guess we never got in trouble because qp->refcount was always 0 by the time we reached the wait_event(). Good catch.
- R. _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
