Quoting r. Roland Dreier <[EMAIL PROTECTED]>: > Subject: Re: [PATCH] roland-uverbs: possible race condition > > Since there seems to be no analogous statement about INTx messages in > the PCIe spec, there is no guarantee that an ISR will see all PMW > transactions issued prior to the INTx message. > > Thanks, > Roland
OK, so are we all in agreement now, that an empty eq, too, must be re-armed in memfree mode when working in regular interrupt mode? Please note how that has no extra cost, since as my patch that started this thread does, you can arm all eqs in one fell swoop, pre-computing the mask. -- MST - Michael S. Tsirkin _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
