From mboxrd@z Thu Jan 1 00:00:00 1970 From: Benjamin Herrenschmidt Subject: Re: [PATCH] drm/radeon: Disable writeback by default on ppc Date: Fri, 08 Nov 2013 09:29:16 +1100 Message-ID: <1383863356.4776.202.camel@pasglop> References: <1371477978-25440-1-git-send-email-ajax@redhat.com> <1371485240.13840.78.camel@localhost> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from gate.crashing.org (gate.crashing.org [63.228.1.57]) by gabe.freedesktop.org (Postfix) with ESMTP id 4EA63113136 for ; Thu, 7 Nov 2013 15:25:36 -0800 (PST) In-Reply-To: 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: Alex Deucher Cc: dri-devel@lists.freedesktop.org, Jerome Glisse , Thadeu Lima de Souza Cascardo , Brian King List-Id: dri-devel@lists.freedesktop.org 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). 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.