Message-ID: <1514753618.20829.3.camel@gmx.de>
Subject: Re: nouveau. swiotlb: coherent allocation failed for device
 0000:01:00.0 size=2097152
From: Mike Galbraith <efault@gmx.de>
To: Ilia Mirkin <imirkin@alum.mit.edu>,
        Christian =?ISO-8859-1?Q?K=F6nig?= <christian.koenig@amd.com>
Cc: Michel =?ISO-8859-1?Q?D=E4nzer?= <michel@daenzer.net>,
        Tobias Klausmann <tobias.johannes.klausmann@mni.thm.de>,
        nouveau <nouveau@lists.freedesktop.org>,
        LKML <linux-kernel@vger.kernel.org>,
        dri-devel <dri-devel@lists.freedesktop.org>,
        Ben Skeggs <bskeggs@redhat.com>
Date: Sun, 31 Dec 2017 21:53:38 +0100
In-Reply-To: <CAKb7Uvgt+SOwf6i2kAzEz65VTGzP6vYb2nBD+78FnXLtMZfOvg@mail.gmail.com>
References: <1513620418.7113.51.camel@gmx.de>
         <a083d576-215f-eb76-278b-741fc65fb138@mni.thm.de>
         <f447948f-cfad-f4ea-4c41-54e42a733c16@daenzer.net>
         <a96f755f-a20b-a177-ead1-7b79acbb1250@daenzer.net>
         <e1b8dd62-4423-2b51-9634-e8938801b5d9@gmail.com>
         <CAKb7Uvgt+SOwf6i2kAzEz65VTGzP6vYb2nBD+78FnXLtMZfOvg@mail.gmail.com>
Content-Type: text/plain; charset="ISO-8859-15"
Mime-Version: 1.0
Content-Transfer-Encoding: 8BIT
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2296
Lines: 63

On Sun, 2017-12-31 at 13:27 -0500, Ilia Mirkin wrote:
> On Tue, Dec 19, 2017 at 8:45 AM, Christian K?nig
> <ckoenig.leichtzumerken@gmail.com> wrote:
> > Am 19.12.2017 um 11:39 schrieb Michel D?nzer:
> >>
> >> On 2017-12-19 11:37 AM, Michel D?nzer wrote:
> >>>
> >>> On 2017-12-18 08:01 PM, Tobias Klausmann wrote:
> >>>>
> >>>> On 12/18/17 7:06 PM, Mike Galbraith wrote:
> >>>>>
> >>>>> Greetings,
> >>>>>
> >>>>> Kernel bound workloads seem to trigger the below for whatever reason.
> >>>>>    I only see this when beating up NFS.  There was a kworker wakeup
> >>>>> latency issue, but with a bandaid applied to fix that up, I can still
> >>>>> trigger this.
> >>>>
> >>>>
> >>>> Hi,
> >>>>
> >>>> i have seen this one as well with my system, but i could not find an
> >>>> easy way to trigger it for bisecting purpose. If you can trigger it
> >>>> conveniently, a bisect would be nice!
> >>>
> >>> I'm seeing this (with the amdgpu and radeon drivers) when restic takes a
> >>> backup, creating memory pressure. I happen to have just finished
> >>> bisecting, the result is:
> >>>
> >>> 648bc3574716400acc06f99915815f80d9563783 is the first bad commit
> >>> commit 648bc3574716400acc06f99915815f80d9563783
> >>> Author: Christian K?nig <christian.koenig@amd.com>
> >>> Date:   Thu Jul 6 09:59:43 2017 +0200
> >>>
> >>>      drm/ttm: add transparent huge page support for DMA allocations v2
> >>>
> >>>      Try to allocate huge pages when it makes sense.
> >>>
> >>>      v2: fix comment and use ifdef
> >>>
> >>>
> >> BTW, I haven't noticed any bad effects other than the dmesg splats, so
> >> maybe it's just noise about transient failures for which there is a
> >> proper fallback in place.
> >
> >
> > Yeah, I think that is exactly what happens here.
> >
> > We try to allocate a huge page, but fail and so fall back to using multiple
> > 4k pages instead.
> >
> > Going to send out a patch to suppress the warning.
> 
> Hi Christian,
> 
> Did you ever send out such a patch? I didn't see one on the list, but
> perhaps I missed it. One definitely hasn't made it upstream yet. (I
> just hit the issue myself with Linus's tree from last night.)

Actually, that wants a bit more methinks, because while the stack dump
goes away, you still get spammed, it just comes in smaller chunks.

	-Mike