From owner-freebsd-x11@FreeBSD.ORG Thu Dec 17 14:38:34 2009 Return-Path: Delivered-To: freebsd-x11@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 79CEA106566C; Thu, 17 Dec 2009 14:38:34 +0000 (UTC) (envelope-from greg@rowes.org) Received: from cdptpa-omtalb.mail.rr.com (cdptpa-omtalb.mail.rr.com [75.180.132.121]) by mx1.freebsd.org (Postfix) with ESMTP id E2ED38FC08; Thu, 17 Dec 2009 14:38:33 +0000 (UTC) X-Authority-Analysis: v=1.0 c=1 a=vnbMBT4Wuw8A:10 a=6I5d2MoRAAAA:8 a=mXSImjQWwTpfCR563qcA:9 a=LPoyJNHV6M6FaGhitzoA:7 a=ZpsJQYTLhlhaNqityqvtiG-jxI4A:4 a=SV7veod9ZcQA:10 X-Cloudmark-Score: 0 X-Originating-IP: 24.173.162.118 Received: from [24.173.162.118] ([24.173.162.118:50198] helo=mudjinshores.rowes.org) by cdptpa-oedge04.mail.rr.com (envelope-from ) (ecelerity 2.2.2.39 r()) with ESMTP id 72/21-01550-8624A2B4; Thu, 17 Dec 2009 14:38:33 +0000 Received: from GregPC (nevisvista.rowes.org [192.168.1.71]) by mudjinshores.rowes.org (8.14.1/8.14.1) with ESMTP id nBHEcKEt045459; Thu, 17 Dec 2009 09:38:20 -0500 (EST) (envelope-from greg@rowes.org) From: "Greg Rowe" To: "'Robert Noland'" References: <200912071550.56061.greg@rowes.org> <1261004962.26065.29.camel@balrog.2hip.net> In-Reply-To: <1261004962.26065.29.camel@balrog.2hip.net> Date: Thu, 17 Dec 2009 09:37:39 -0500 Message-ID: <6D9629ACBA89464799BD1DD1C50CBA10@GregPC> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook 11 Thread-Index: Acp+pNZi3xQw9ES/TGK5BGWFlvUyMgAgSVIA X-MimeOLE: Produced By Microsoft MimeOLE V6.0.6002.18005 X-Rowes.org-MailScanner-Information: Please contact Greg for more information X-Rowes.org-MailScanner: Found to be clean X-Rowes.org-MailScanner-From: greg@rowes.org X-Spam-Status: No Cc: freebsd-x11@FreeBSD.org Subject: RE: Radeon HD4850 DRI Issues X-BeenThere: freebsd-x11@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: greg@rowes.org List-Id: X11 on FreeBSD -- maintaining and support List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 17 Dec 2009 14:38:34 -0000 Thanks Robert, My system is available for any testing you may need as you work on a fix. I can wipe it and get to any software level you need. Greg > Ok, I've found the issue now... It is a somewhat invasive solution > though, so it will take me a little time. > > Basically, the issue is this. We create a list of maps either in the > kernel or via userland requesting them to be added. Each map has an > offset associated with it for mmap. Mostly the offsets are all kernel > virtual addresses, but a few (register and framebuffer maps) are > physical addresses. On i386, when we allocate scatter gather memory for > the GART aperture (32Mb on radeon) it is being allocated at the end of > the kva space. I have gone back and looked at all of the reports of > this that I have and the framebuffer is always at 0xe0000000. When the > kva returned by bus_dma overlaps with the physical address of the > framebuffer, we match the incorrect map when mmap is called and > therefore we are actually mapping the ring buffer inside of the > framebuffer, rather that out of the scatter gather memory where it > belongs. > > I have never seen this issue on amd64. On i386 when the framebuffer is > located lower than 0xe0000000 things mostly work as well. I have to > overhaul the way that we handle mmap offsets to get this sorted out and > possibly make a couple of changes to libdrm, which is shared code. > > robert. > > > Thanks, > > Greg > > > > _______________________________________________ > > freebsd-x11@freebsd.org mailing list > > http://lists.freebsd.org/mailman/listinfo/freebsd-x11 > > To unsubscribe, send any mail to "freebsd-x11-unsubscribe@freebsd.org" > -- > Robert Noland > FreeBSD >