From owner-freebsd-alpha Thu Jul 20 15:18:38 2000 Delivered-To: freebsd-alpha@freebsd.org Received: from implode.root.com (root.com [209.102.106.178]) by hub.freebsd.org (Postfix) with ESMTP id 772B137C1C6; Thu, 20 Jul 2000 15:18:24 -0700 (PDT) (envelope-from dg@implode.root.com) Received: from implode.root.com (localhost [127.0.0.1]) by implode.root.com (8.8.8/8.8.5) with ESMTP id PAA07882; Thu, 20 Jul 2000 15:05:27 -0700 (PDT) Message-Id: <200007202205.PAA07882@implode.root.com> To: Mike Smith Cc: =?ISO-8859-1?Q?G=E9rard_Roudier?= , freebsd-alpha@FreeBSD.ORG Subject: Re: fxp0 hangs on a PC164 using STABLE In-reply-to: Your message of "Thu, 20 Jul 2000 15:00:59 PDT." <200007202201.PAA00657@mass.osd.bsdi.com> From: David Greenman Reply-To: dg@root.com Date: Thu, 20 Jul 2000 15:05:27 -0700 Sender: owner-freebsd-alpha@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >> As a result ( applying to my opinion ;-) ), when a PCI device and its >> software driver communicates through the main memory, it is _very_ likely >> memory barrier to be needed in some places so that program-expected >> ordering as seen from the system BUS will happen. > >I am inclined to agree with you that there are probably cases in the fxp >driver where the author has made assumptions regarding the x86 normal >behaviour of retiring writes in program order, however that's not the >issue that this change is trying to address. That is correct. The author assumed that writes would be retired in order and without any special memory barriers or other synchronization. -DG David Greenman Co-founder, The FreeBSD Project - http://www.freebsd.org Manufacturer of high-performance Internet servers - http://www.terasolutions.com Pave the road of life with opportunities. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message