>Quoting r. Zach Brown <[EMAIL PROTECTED]>: >> BC: >> >> query_idr.lock is taken with interrupts enabled and so is implicitly >> ordered before dev->_xmit_lock which is taken in interrupt context. >> >> ipoib_mcast_join_task() >> ipoib_mcast_join() >> ib_sa_mcmember_rec_query() >> send_mad() >> idr_pre_get(&query_idr) >> spin_lock(&idp->lock) > >Got to check, but if that's true we have a simple deadlock here: >ib_sa_mcmember_rec_query might get called from interrupt >context as well, deadlocking on idp->lock? > >Sean?
As a side note, I believe that this is the upstream code and does not include the latest multicast changes. I'm not sure if anything calls into the sa_query interfaces from interrupt context, but I doubt it. From my brief look at the initially reported issue, I can't determine if there's an actual problem without studying the ipoib code more. - Sean _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
