Quoting r. Roland Dreier <[EMAIL PROTECTED]>: > Subject: Re: [PATCH] mthca: memfree completion with error workaround > > This makes me sad. We're adding considerable code to the CQ polling > fast path
It might not be too bad - there's a single additional test on fastpath, and I am guessing both wqe_index and rq.max should be in registers already. Once wqe_index is out of rq.max range we are on slow path. > I wish there were a better way. We can make it a compile-time option, so that users can disable it once there's a firmware that does not need this code. -- MST _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
