From owner-freebsd-hackers Wed Sep 6 13:42:11 1995 Return-Path: hackers-owner Received: (from majordom@localhost) by freefall.freebsd.org (8.6.11/8.6.6) id NAA22664 for hackers-outgoing; Wed, 6 Sep 1995 13:42:11 -0700 Received: from localhost.cdrom.com (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.6.11/8.6.6) with SMTP id NAA22654 ; Wed, 6 Sep 1995 13:42:09 -0700 Message-Id: <199509062042.NAA22654@freefall.freebsd.org> X-Authentication-Warning: freefall.freebsd.org: Host localhost.cdrom.com didn't use HELO protocol To: Terry Lambert cc: hackers@freefall.freebsd.org Subject: Re: Cyrix cache enable patches? In-reply-to: Your message of "Wed, 06 Sep 1995 12:54:58 PDT." <199509061954.MAA00541@phaeton.artisoft.com> Date: Wed, 06 Sep 1995 13:42:08 -0700 From: "Justin T. Gibbs" Sender: hackers-owner@FreeBSD.org Precedence: bulk >> >> Did anyone look at integrating these patches? I think this was for a different chip, but even if this is the case, then the work should be done and the code that was submitted shouldn't just fall through the cracks. We've needed detection of crappy processors from various vendors for some time... >Cyrix doesn't honor the non-cacheable bit. > >It would be silly to integrate patches to turn it on without integrating >detect as a global setting and doing a BINVD when a read is issued to >get around it not honoring the non-cacheable bit. > >You *aren't* going to get a cache update, since the motherboard chipset >doesn't notify the chip of a bus mastering DMA causing a cache invalidation >to be necessary (no pin on the chip for it). > > > Terry Lambert > terry@lambert.org >--- >Any opinions in this posting are my own and not those of my present >or previous employers. -- Justin T. Gibbs =========================================== Software Developer - Walnut Creek CDROM FreeBSD: Turning PCs into workstations ===========================================