<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"><!-- P {margin-top:0;margin-bottom:0;} --></style>
</head>
<body dir="ltr">
<div id="divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Helvetica,sans-serif;" dir="ltr">
<p style="margin-top:0;margin-bottom:0">We haven't had a chance to look yet.</p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">Alex<br>
</p>
</div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> Luís Mendes <luis.p.mendes@gmail.com><br>
<b>Sent:</b> Wednesday, February 7, 2018 10:50:48 AM<br>
<b>To:</b> Koenig, Christian<br>
<b>Cc:</b> Alex Deucher; Deucher, Alexander; Zhou, David(ChunMing); Michel Dänzer; amd-gfx@lists.freedesktop.org<br>
<b>Subject:</b> Re: Deadlocks with multiple applications on AMD RX 460 and RX 550 - Update 2</font>
<div> </div>
</div>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText">Hi Christian, Alexander,<br>
<br>
Kmemleak reported leaked data structures and the GPU hung a bit after.<br>
Could this be caused from DC?<br>
Info in attachments.<br>
<br>
<br>
I'm not sure if my previous email got overlooked, or if simply, there<br>
are no suggestions at this moment. Sorry for kind of re-sending the<br>
email.<br>
<br>
<br>
Regards,<br>
Luís<br>
<br>
On Mon, Feb 5, 2018 at 12:40 PM, Luís Mendes <luis.p.mendes@gmail.com> wrote:<br>
> Hi everyone,<br>
><br>
> I have some updates. I left the system idle most of the time during<br>
> the weekend and from time to time I played a video on youtube and<br>
> turned off the screen. Yesterday night I did the same and today<br>
> morning I checked the system and it got hung up during the night. This<br>
> time it took a lot longer to hang, but I think it was related to a<br>
> Flash animation add that was only present on the youtube page the last<br>
> time I switched off the screen. The amdgpu always seem to hang when<br>
> that flash animation is present, from all the crash attempts I have<br>
> made.<br>
> There is a memory leak according to kmemleak which I attach along with<br>
> the crash dmesg log.<br>
><br>
> The kernel and patches are the same as on my previous email. I ended<br>
> up not changing either the mesa version, nor the kernel version and<br>
> patches.<br>
><br>
> Regards,<br>
> Luís<br>
><br>
><br>
> On Fri, Feb 2, 2018 at 6:46 PM, Luís Mendes <luis.p.mendes@gmail.com> wrote:<br>
>> Hi Christian, Alexander,<br>
>><br>
>> I have enabled kmemleak, but memleak didn't detect anything special,<br>
>> in fact this time, I don't know why, I didn't get any allocation<br>
>> failure at all, but the GPU did hang after around 4h 6m of uptime with<br>
>> Xorg.<br>
>> The log can be found in attachment. I will try again to see if the<br>
>> allocation failure reappears, or if it has become less apparent due to<br>
>> kmemleak scans.<br>
>><br>
>> The kernel stack trace is similar to the GPU hangs I was getting on<br>
>> earlier kernel versions with Kodi, or Firefox when watching videos<br>
>> with either one, but if I left Xorg idle, it would remain up and<br>
>> available without hanging for more than one day.<br>
>> This stack trace also looks quite similar to what Daniel Andersson<br>
>> reported in "[BUG] Intermittent hang/deadlock when opening browser tab<br>
>> with Vega gpu", looks like another demonstration of the same bug on<br>
>> different architectures.<br>
>><br>
>> Regards,<br>
>> Luís<br>
>><br>
>> On Fri, Feb 2, 2018 at 7:48 AM, Christian König<br>
>> <ckoenig.leichtzumerken@gmail.com> wrote:<br>
>>> Hi Luis,<br>
>>><br>
>>> please enable kmemleak in your build and watch out for any suspicious<br>
>>> messages in the system log.<br>
>>><br>
>>> Regards,<br>
>>> Christian.<br>
>>><br>
>>><br>
>>> Am 02.02.2018 um 00:03 schrieb Luís Mendes:<br>
>>>><br>
>>>> Hi Alexander,<br>
>>>><br>
>>>> I didn't notice improvements on this issue with that particular patch<br>
>>>> applied. It still ends up failing to allocate kernel memory after a<br>
>>>> few hours of uptime with Xorg.<br>
>>>><br>
>>>> I will try to upgrade to mesa 18.0.0-rc3 and to amd-staging-drm-next<br>
>>>> head, to see if the issue still occurs with those versions.<br>
>>>><br>
>>>> If you have additional suggestions I'll be happy to try them.<br>
>>>><br>
>>>> Regards,<br>
>>>> Luís Mendes<br>
>>>><br>
>>>> On Thu, Feb 1, 2018 at 2:30 AM, Alex Deucher <alexdeucher@gmail.com><br>
>>>> wrote:<br>
>>>>><br>
>>>>> On Wed, Jan 31, 2018 at 6:57 PM, Luís Mendes <luis.p.mendes@gmail.com><br>
>>>>> wrote:<br>
>>>>>><br>
>>>>>> Hi everyone,<br>
>>>>>><br>
>>>>>> I am getting a new issue with amdgpu with RX460, that is, now I can<br>
>>>>>> play any videos with Kodi or play web videos with firefox and run<br>
>>>>>> OpenGL applications without running into any issues, however after<br>
>>>>>> some uptime with XOrg even when almost inactive I get a kmalloc<br>
>>>>>> allocation failure, normally followed by a GPU hang a while after the<br>
>>>>>> the allocation failure.<br>
>>>>>> I had a terminal window under Ubuntu Mate 17.10 and I was compiling<br>
>>>>>> code when I got the kernel messages that can be found in attachment.<br>
>>>>>><br>
>>>>>> I am using the kernel as identified on my previous email, which can be<br>
>>>>>> found below.<br>
>>>>><br>
>>>>> does this patch help?<br>
>>>>> <a href="https://patchwork.freedesktop.org/patch/198258/">https://patchwork.freedesktop.org/patch/198258/</a><br>
>>>>><br>
>>>>> Alex<br>
>>>>><br>
>>>>>> Regards,<br>
>>>>>> Luís Mendes<br>
>>>>>><br>
>>>>>> On Wed, Jan 31, 2018 at 12:47 PM, Luís Mendes <luis.p.mendes@gmail.com><br>
>>>>>> wrote:<br>
>>>>>>><br>
>>>>>>> Hi Alexander,<br>
>>>>>>><br>
>>>>>>> I've cherry picked the patch you pointed out into kernel from<br>
>>>>>>> amd-drm-next-4.17-wip at commit<br>
>>>>>>> 9ab2894122275a6d636bb2654a157e88a0f7b9e2 ( drm/amdgpu: set<br>
>>>>>>> DRIVER_ATOMIC flag early) and tested it on ARMv7l and the problem has<br>
>>>>>>> gone indeed.<br>
>>>>>>><br>
>>>>>>><br>
>>>>>>> Working great on ARMv7l with AMD RX460.<br>
>>>>>>><br>
>>>>>>> Thanks,<br>
>>>>>>> Luís Mendes<br>
>>>>>>><br>
>>>>>>><br>
>>>>>>> On Tue, Jan 30, 2018 at 6:44 PM, Deucher, Alexander<br>
>>>>>>> <Alexander.Deucher@amd.com> wrote:<br>
>>>>>>>><br>
>>>>>>>> Fixed with this patch:<br>
>>>>>>>><br>
>>>>>>>><br>
>>>>>>>> <a href="https://lists.freedesktop.org/archives/amd-gfx/2018-January/018472.html">
https://lists.freedesktop.org/archives/amd-gfx/2018-January/018472.html</a><br>
>>>>>>>><br>
>>>>>>>><br>
>>>>>>>> Alex<br>
>>>>>><br>
>>>>>> <><br>
>>>>>>>><br>
>>>>>>>> __________________<br>
>>>>>><br>
>>>>>> _______________________________________________<br>
>>>>>> amd-gfx mailing list<br>
>>>>>> amd-gfx@lists.freedesktop.org<br>
>>>>>> <a href="https://lists.freedesktop.org/mailman/listinfo/amd-gfx">https://lists.freedesktop.org/mailman/listinfo/amd-gfx</a><br>
>>>>>><br>
>>>> _______________________________________________<br>
>>>> amd-gfx mailing list<br>
>>>> amd-gfx@lists.freedesktop.org<br>
>>>> <a href="https://lists.freedesktop.org/mailman/listinfo/amd-gfx">https://lists.freedesktop.org/mailman/listinfo/amd-gfx</a><br>
>>><br>
>>><br>
</div>
</span></font></div>
</body>
</html>