From owner-freebsd-amd64@FreeBSD.ORG Sat Oct 7 21:43:39 2006 Return-Path: X-Original-To: freebsd-amd64@FreeBSD.org Delivered-To: freebsd-amd64@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 50BC116A407 for ; Sat, 7 Oct 2006 21:43:39 +0000 (UTC) (envelope-from jmg@hydrogen.funkthat.com) Received: from hydrogen.funkthat.com (gate.funkthat.com [69.17.45.168]) by mx1.FreeBSD.org (Postfix) with ESMTP id F086B43D4C for ; Sat, 7 Oct 2006 21:43:36 +0000 (GMT) (envelope-from jmg@hydrogen.funkthat.com) Received: from hydrogen.funkthat.com (y1ek7oa0ttp6hth3@localhost.funkthat.com [127.0.0.1]) by hydrogen.funkthat.com (8.13.6/8.13.3) with ESMTP id k97Lha2F051438 for ; Sat, 7 Oct 2006 14:43:36 -0700 (PDT) (envelope-from jmg@hydrogen.funkthat.com) Received: (from jmg@localhost) by hydrogen.funkthat.com (8.13.6/8.13.3/Submit) id k97LhanZ051437 for freebsd-amd64@FreeBSD.org; Sat, 7 Oct 2006 14:43:36 -0700 (PDT) (envelope-from jmg) Date: Sat, 7 Oct 2006 14:43:36 -0700 From: John-Mark Gurney To: freebsd-amd64@FreeBSD.org Message-ID: <20061007214336.GJ793@funkthat.com> Mail-Followup-To: freebsd-amd64@FreeBSD.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.2.1i X-Operating-System: FreeBSD 5.4-RELEASE-p6 i386 X-PGP-Fingerprint: B7 EC EF F8 AE ED A7 31 96 7A 22 B3 D8 56 36 F4 X-Files: The truth is out there X-URL: http://resnet.uoregon.edu/~gurney_j/ X-Resume: http://resnet.uoregon.edu/~gurney_j/resume.html Cc: Subject: amd64 agp driver bug? X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: John-Mark Gurney List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 07 Oct 2006 21:43:39 -0000 I was looking at the agp driver and the BIOS and Kernel Developer's Guide, and noticed that it appears we program the page register incorrectly... Currently we do, in sys/pci/agp_amd64.c: sc->gatt->ag_virtual[offset >> AGP_PAGE_SHIFT] = physical; but according to Table 38 in the guide, it looks like it should be: sc->gatt->ag_virtual[offset >> AGP_PAGE_SHIFT] = (physical & 0xfffff000) | ((physical >> 28) & 0xff0) | 1; To support physical addresses above 4G... Has anyone used AGP w/ >4GB of memmory? I'm also puzzled by the fact that the guide says to set bit 0, but we don't do that... -- John-Mark Gurney Voice: +1 415 225 5579 "All that I will do, has been done, All that I have, has not."