[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#758460: xserver-xorg-video-nouveau: Crash and freeze with GeForce 6150SE.



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.
> 
> Noticed that something similar has been reported in
> http://bugs.debian.org/758460 for a GeForce 6150LE. Not merging both bug
> reports in case they are different issues for different chip variants, but
> cc'ing. Following advice there I tried with kernel boot parameter
> "nouveau.config=NvMSI=0" in the command line and with
> 
> options nouveau NvMSI=0
> 
> in a /etc/modprobe.d/local-video.conf file (also built a new initramfs in
> case this is needed), problem is still here, no luck.

Hi,

I was thinking about building a kernel with patch mentioned in
http://bugs.debian.org/758460 

 http://cgit.freedesktop.org/~darktama/nouveau/commit/?id=b7387454bda64a16350fabee4d81bec3b8de8fa2

applied, but I then noticed that it is already in jessie's kernel.

Searching kernel changelogs, I found this in

https://www.kernel.org/pub/linux/kernel/v3.x/ChangeLog-3.18.4

commit 715f7c8214c7822833af757109022006c3f01d6a
Author: Ilia Mirkin <imirkin@alum.mit.edu>
Date:   Tue Dec 16 13:55:38 2014 -0500

    drm/nv4c/mc: disable msi
    
    commit 4761703bd04bbdf56396d264903cc5a1fdcb3c01 upstream.
    
    Several users have, over time, reported issues with MSI on these IGPs.
    They're old, rarely available, and MSI doesn't provide such huge
    advantages on them. Just disable.
    
    Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87361
    Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=74492
    Fixes: fa8c9ac72fe ("drm/nv4c/mc: nv4x igp's have a different msi rearm
    register")
    Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
    Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
    Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

also in https://www.kernel.org/pub/linux/kernel/v3.0/ChangeLog-3.14.30 (LTS?)

Now it is clear why setting NvMSI=0 did not make any difference in the box
with the GeForce 6150SE where I hit the bug (Did not try with noaccel).

Martin-Éric, has jessie's kernel fixed the problem in your box?

-- 
Agustin


Reply to: