From owner-freebsd-bugs Thu Apr 17 19:05:08 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id TAA24321 for bugs-outgoing; Thu, 17 Apr 1997 19:05:08 -0700 (PDT) Received: from gneiss.eps.nagoya-u.ac.jp (gneiss.eps.nagoya-u.ac.jp [133.6.57.99]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id TAA24311 for ; Thu, 17 Apr 1997 19:05:00 -0700 (PDT) Received: from marble.eps.nagoya-u.ac.jp (localhost [127.0.0.1]) by gneiss.eps.nagoya-u.ac.jp (8.8.5/3.4W4) with ESMTP id LAA03835; Fri, 18 Apr 1997 11:04:08 +0900 (JST) Message-Id: <199704180204.LAA03835@gneiss.eps.nagoya-u.ac.jp> To: rb@gid.co.uk Cc: freebsd-bugs@freefall.freebsd.org Subject: Re: kern/3292: Cyrix 486 performance problem In-Reply-To: Your message of "Thu, 17 Apr 1997 15:40:02 -0700 (PDT)" References: <199704172240.PAA11576@freefall.freebsd.org> X-Mailer: Mew version 1.69 on Emacs 19.28.1 / Mule 2.3 X-PGP-Fingerprint: 03 72 85 36 62 46 23 03 52 B1 10 22 44 10 0D 9E Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Date: Fri, 18 Apr 1997 11:04:07 +0900 From: KATO Takenori Sender: owner-bugs@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk To determine cache disable/enable by default is to determine support all/not-all Cx486 box. If CPU cache is enabled by default, FreeBSD cannot boot on old Cyrix-unaware motherboards. Because Cyrix sold 486SLC/DLC series as `up-grade products', I considered that FreeBSD should support old motherboard users and disable CPU cache by default in initcpu.c. If we change the code to enable CPU cache by default, we should chose one of the followings: (1) Give up supporting old motherboards. (2) Implement cache flush code as PC-98 tree dose (c.f. DMA code in /sys/pc98/pc98/pc98.c). I prefer (2) to (1). I think such old-motherboards doesn't have PCI bus, so we should change only DAM code in /sys/i386/isa/isa.c and some code in identcpu.c. (If other source than isa.c has its own DMA routine, we should look for it and change it.) > You're right, this CPU needs options CYRIX_CACHE_WORKS. I've never heard of > cache problems with Cyrix 486DX; except perhaps when using them on old > Cyrix-unaware motherboards, and then they often won't run period. I have a > machine around with a (similar IIRC) TI486DX2/80, guess I'd better check > that too. > On a 486DX2/80 with the cache disabled you'd need over 3 hours to build a > kernel to fix it. On the evidence so far I'd say the cache should be > enabled by default for Cx486; I appreciate there are other gotchas with > Cx586 and Cx686. ---- KATO Takenori Dept. Earth Planet. Sci., Nagoya Univ., Nagoya, 464-01, Japan PGP public key: finger kato@eclogite.eps.nagoya-u.ac.jp ------------------- Powered by FreeBSD(98) -------------------