From mboxrd@z Thu Jan 1 00:00:00 1970 From: Kleber Sacilotto de Souza Subject: Re: [PATCH] drm/radeon: Disable writeback by default on ppc Date: Fri, 08 Nov 2013 11:43:25 -0200 Message-ID: <527CEA7D.4060704@linux.vnet.ibm.com> References: <1371477978-25440-1-git-send-email-ajax@redhat.com> <1371485240.13840.78.camel@localhost> <1383863356.4776.202.camel@pasglop> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; Format="flowed" Content-Transfer-Encoding: 7bit Return-path: Received: from e24smtp05.br.ibm.com (e24smtp05.br.ibm.com [32.104.18.26]) by gabe.freedesktop.org (Postfix) with ESMTP id 9D14911373C for ; Fri, 8 Nov 2013 05:43:33 -0800 (PST) Received: from /spool/local by e24smtp05.br.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 8 Nov 2013 11:43:31 -0200 Received: from d24relay01.br.ibm.com (d24relay01.br.ibm.com [9.8.31.16]) by d24dlp02.br.ibm.com (Postfix) with ESMTP id 60FD11DC0063 for ; Fri, 8 Nov 2013 08:43:28 -0500 (EST) Received: from d24av05.br.ibm.com (d24av05.br.ibm.com [9.18.232.44]) by d24relay01.br.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id rA8DhUgv393380 for ; Fri, 8 Nov 2013 11:43:31 -0200 Received: from d24av05.br.ibm.com (d24av05 [127.0.0.1]) by d24av05.br.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id rA8DhQOo028020 for ; Fri, 8 Nov 2013 08:43:27 -0500 In-Reply-To: <1383863356.4776.202.camel@pasglop> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dri-devel-bounces@lists.freedesktop.org Errors-To: dri-devel-bounces@lists.freedesktop.org To: Benjamin Herrenschmidt Cc: dri-devel@lists.freedesktop.org, Brian King , Jerome Glisse , Thadeu Lima de Souza Cascardo List-Id: dri-devel@lists.freedesktop.org On 11/07/2013 08:29 PM, Benjamin Herrenschmidt wrote: > On Mon, 2013-06-17 at 18:57 -0400, Alex Deucher wrote: > >> Weird. I wonder if there is an issue with cache snoops on PPC. We >> currently use the gart in cached mode (GPU snoops CPU cache) with >> cached pages. I wonder if we need to use uncached pages on PPC. > > There is no such issue and no known bugs with DMA writes on those > PCIe host bridges (and they do get hammered pretty bad here). > > This needs further investigation by the lab/hw guys to find out what's > actually happening on the bus and the host bridge. > > Thadeu, Kleber: Jerome suggested writing a test case in userspace that > continuously writes to a spare scratch register (thus triggering the > corresponding writeback DMA) and checks the memory location to compare > the writeback value (using a debugfs file for example, or mmap). > I can look into that. Thanks, Kleber > Can you guys do something like that ? Then we need the analyzer on > and/or the lab guys to look at the fabric trace & PHB trace. > > Ben. > > -- Kleber Sacilotto de Souza IBM Linux Technology Center