Bug#758460: xserver-xorg-video-nouveau: Crash and freeze with GeForce 6150SE.
2015-05-05 19:43 GMT+02:00 Martin-Éric Racine <martin-eric.racine@iki.fi>:
> 2015-05-05 19:38 GMT+03:00 Agustin Martin <agmartin@debian.org>:
>> On Mon, May 04, 2015 at 12:49:52PM +0200, Agustin Martin wrote:
>>> Hi,
>>>
>>> Just to confirm a similar problem in a GeForce 6150SE graphics engine,
>>>
>>> 00:0d.0 VGA compatible controller: NVIDIA Corporation C61 [GeForce 6150SE nForce 430] (rev a2)
>>>
>>> Similar messages in syslog,
>>>
>>> [ 711.849697] nouveau E[ PBUS][0000:00:0d.0] MMIO write of 0x00870001 FAULT at 0x00b010
>>>
>>> and random freeze. Last seen thing is some sort of zig-zag random pattern
>>> apparently with colors used at that time. Nothing but hard reboot helps
>>> once the system is frozen, not even Magic SysRq. No relevant info seems
>>> to appear in syslog.
>>>
>>> An important info is that this does not happen if I reboot with old
>>> 3.2.04-amd64 (3.2.65-1+deb7u2) wheezy kernel. So this seems to be a problem
>>> with the nouveau kernel module.
[...]
>> http://cgit.freedesktop.org/~darktama/nouveau/commit/?id=b7387454bda64a16350fabee4d81bec3b8de8fa2
>>
>> applied, but I then noticed that it is already in jessie's kernel.
>>
>>
>> drm/nv4c/mc: disable msi
>>
>> commit 4761703bd04bbdf56396d264903cc5a1fdcb3c01 upstream.
>>
>> Martin-Éric, has jessie's kernel fixed the problem in your box?
>
> Agustin,
>
> There's two NVDIA boxes involved (IIRC, I filed separate bugs reports).
>
> Neither box works with the Nouveau X.org driver in Jessie. In both
> cases, I've had to remove xserver-xorg-video-nouveau and let Xserver
> use the generic modeline driver.
Hi,
Just to add that this freeze no longer appears with jessie's kernel if
I pass nouveau.noaccel=1 as a kernel boot parameter (as suggested in
#776838) or if I put
options nouveau noaccel=1
in my /etc/modprobe.d/local-video.conf. No intense graphics use is
done in this box, so I did not notice a performance loss.
--
Agustin
Reply to: