From owner-freebsd-alpha Sun Jul 9 14:33:34 2000 Delivered-To: freebsd-alpha@freebsd.org Received: from pluto.plutotech.com (mail.plutotech.com [206.168.67.137]) by hub.freebsd.org (Postfix) with ESMTP id C69B437B669 for ; Sun, 9 Jul 2000 14:33:31 -0700 (PDT) (envelope-from gibbs@plutotech.com) Received: from caspian.plutotech.com (root@mail.plutotech.com [206.168.67.137]) by pluto.plutotech.com (8.9.2/8.9.1) with ESMTP id PAA27142; Sun, 9 Jul 2000 15:33:29 -0600 (MDT) (envelope-from gibbs@plutotech.com) Message-Id: <200007092133.PAA27142@pluto.plutotech.com> X-Mailer: exmh version 2.1.1 10/15/1999 To: mjacob@feral.com Cc: "Justin T. Gibbs" , alpha@freebsd.org Subject: Re: AHC_ALLOW_MEMIO in 4.1 && 5.0 for alpha? In-Reply-To: Your message of "Sat, 08 Jul 2000 17:36:15 PDT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 09 Jul 2000 15:34:07 -0600 From: "Justin T. Gibbs" Sender: owner-freebsd-alpha@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >Justin- things work a lot better on alphas when they use mem space in >preference to I/O space- in particular I just got bit by a 3940 not working >(past the bridge) in I/O space. > >Do you mind if I we set this option into the GENERIC for alpha? As far as I'm concerned, the "allow memio" options in drivers are a hack that was supposed to be temporary. Memory mapped I/O should always be preferred and the allocation fail if the path to the device cannot support it. Unfortunately we don't have that mechanism yet. In the mean time, I'll let others dictate the default policy for which type of access method is attempted first. -- Justin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message