Roland, I thought a bit more about ipoib_qprst_protect.patch: during ipoib_ib_dev_stop, what prevents us from seeing a stale value of tx_head? If this happens, we might think the queue is empty and tx_head == tx_tail, where it actually is not.
The patch under discussion is here: https://openib.org/svn/trunk/contrib/mellanox/denied/ipoib_qprst_protect.patch -- Michael S. Tsirkin Staff Engineer, Mellanox Technologies _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
