Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932183AbaKSP3u (ORCPT ); Wed, 19 Nov 2014 10:29:50 -0500 Received: from mout1.fh-giessen.de ([212.201.18.42]:50108 "EHLO mout1.fh-giessen.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932126AbaKSP3r (ORCPT ); Wed, 19 Nov 2014 10:29:47 -0500 X-Greylist: delayed 644 seconds by postgrey-1.27 at vger.kernel.org; Wed, 19 Nov 2014 10:29:47 EST Message-ID: <546CB4E2.3010707@mni.thm.de> Date: Wed, 19 Nov 2014 16:18:58 +0100 From: Tobias Klausmann User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:36.0) Gecko/20100101 Thunderbird/36.0a1 MIME-Version: 1.0 To: Maarten Lankhorst , Michael Marineau , dri-devel@lists.freedesktop.org CC: linux-kernel@vger.kernel.org, Ben Skeggs , David Airlie Subject: Re: 3.18-rc regression: drm/nouveau: use shared fences for readable objects References: <546C5085.1020300@canonical.com> In-Reply-To: <546C5085.1020300@canonical.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 19.11.2014 09:10, Maarten Lankhorst wrote: > Hey, > > On 19-11-14 07:43, Michael Marineau wrote: >> On 3.18-rc kernel's I have been intermittently experiencing GPU >> lockups shortly after startup, accompanied with one or both of the >> following errors: >> >> nouveau E[ PFIFO][0000:01:00.0] read fault at 0x000734a000 [PTE] >> from PBDMA0/HOST_CPU on channel 0x007faa3000 [unknown] >> nouveau E[ DRM] GPU lockup - switching to software fbcon >> >> I was able to trace the issue with bisect to commit >> 809e9447b92ffe1346b2d6ec390e212d5307f61c "drm/nouveau: use shared >> fences for readable objects". The lockups appear to have cleared up >> since reverting that and a few related followup commits: >> >> 809e9447: "drm/nouveau: use shared fences for readable objects" >> 055dffdf: "drm/nouveau: bump driver patchlevel to 1.2.1" >> e3be4c23: "drm/nouveau: specify if interruptible wait is desired in >> nouveau_fence_sync" >> 15a996bb: "drm/nouveau: assign fence_chan->name correctly" > Weird. I'm not sure yet what causes it. > > http://cgit.freedesktop.org/~mlankhorst/linux/commit/?h=fixed-fences-for-bisect&id=86be4f216bbb9ea3339843a5658d4c21162c7ee2 > > On the EDITED patch from fixed-fences-for-bisect, can you do the following: > > In nouveau/nv84_fence.c function nv84_fence_context_new, remove > > fctx->base.sequence = nv84_fence_read(chan); > > and add back > > nouveau_bo_wr32(priv->bo, chan->chid * 16/4, 0x00000000); > > If that fails you should compile your kernel with trace events, to get some debugging info from the fences. I'll post debugging info if this does not fix it. > > ~Maarten Hey, as mentioned in IRC the new fencing hangs my GPU for a while as well (nve7). Bisected back to 86be4f216bbb9ea3339843a5658d4c21162c7ee2 , EDITED from the fixed-fences-for-bisect branch mentioned above. Original bisect on linus brach brought me to: 29ba89b2371d466ca68973525816cf10debc2655 drm/nouveau: rework to new fence interface Michael if you are going to bisect the "fixed-fences-for-bisect" branch, maybe take a closer look if you come anywhere near that commit, if that does or does not trigger the GPU hangs for you! Tobias -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/