Bug 109756 - GPU hang ecode 9:1:0xef35fff4
Summary: GPU hang ecode 9:1:0xef35fff4
Status: RESOLVED MOVED
Alias: None
Product: xorg
Classification: Unclassified
Component: Driver/intel (show other bugs)
Version: unspecified
Hardware: x86-64 (AMD64) other
: medium normal
Assignee: Chris Wilson
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2019-02-24 01:22 UTC by Jiacheng Ma
Modified: 2019-11-27 13:50 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:


Attachments
the crash dump (43.36 KB, text/plain)
2019-02-24 01:22 UTC, Jiacheng Ma
no flags Details
attachment-14292-0.html (2.31 KB, text/html)
2019-02-25 14:54 UTC, Jiacheng Ma
no flags Details
attachment-4155-0.html (1.91 KB, text/html)
2019-02-25 17:48 UTC, Jiacheng Ma
no flags Details

Description Jiacheng Ma 2019-02-24 01:22:11 UTC
Created attachment 143446 [details]
the crash dump

GPU hang on Kaby Lake GT3e with ecode 9:1:0xef35fff4 while running a TK application (synopsys vcs-mx).
The operating system is Archlinux with kernel 4.20.11-arch2-1-ARCH. The desktop is Gnome 3.30.2.

Attached is the crash dump.
Comment 1 Chris Wilson 2019-02-24 09:21:43 UTC
We overran the batch:

  batch: [0x00000000_0d436000, 0x00000000_0d446000]
  BBADDR: 0x00000000_0d446019


In the middle of a bunch of single lined mixed XY_SRC_COPY_BLT, so spans.
Comment 2 Paul 2019-02-25 10:29:59 UTC
Hi Jiacheng Ma,
Thanks for the report. Could you please provide answers on questions below?
1. Provide please version of mesa on your machine
2. Does the hang reproduce stable or it was just once? 
3. Also, apitrace with hang would be helpful, if it is possible
https://github.com/apitrace/apitrace
Thanks!
Comment 3 Jiacheng Ma 2019-02-25 14:54:22 UTC
Created attachment 143459 [details]
attachment-14292-0.html

Hi,

1. The mesa version is mesa-18.3.3-2.
2. The hang can reproduce stable
3. Cannot reproduce the bug with apitrace. With apitrace the bug is less
frequent. The only time it crashes crash the whole system and I cannot find
the log. Sorry about that.

Thanks and regards,
Jiacheng

On Mon, Feb 25, 2019 at 5:30 AM <bugzilla-daemon@freedesktop.org> wrote:

> *Comment # 2 <https://bugs.freedesktop.org/show_bug.cgi?id=109756#c2> on
> bug 109756 <https://bugs.freedesktop.org/show_bug.cgi?id=109756> from Paul
> <qamonstergl@gmail.com> *
>
> Hi Jiacheng Ma,
> Thanks for the report. Could you please provide answers on questions below?
> 1. Provide please version of mesa on your machine
> 2. Does the hang reproduce stable or it was just once?
> 3. Also, apitrace with hang would be helpful, if it is possiblehttps://github.com/apitrace/apitrace
> Thanks!
>
> ------------------------------
> You are receiving this mail because:
>
>    - You reported the bug.
>
>
Comment 4 Sergii Romantsov 2019-02-25 15:04:26 UTC
Hello, Jiacheng.
Paul asked you to 'trace' your application 'synopsys vcs-mx' with apitrace.
Was you able to do it?
Actually we don't need a log file, but just a trace (it should stay even due crash)
Comment 5 Jiacheng Ma 2019-02-25 17:48:40 UTC
Created attachment 143463 [details]
attachment-4155-0.html

Hi,

I tried again. It seems like the trace tool does not work for the program
and there is no trace file no matter whether GPU crashes or not. But I
found that it can run without problem with Gnome over Wayland.

Best,
Jiacheng Ma

On Mon, Feb 25, 2019 at 10:04 AM <bugzilla-daemon@freedesktop.org> wrote:

> *Comment # 4 <https://bugs.freedesktop.org/show_bug.cgi?id=109756#c4> on
> bug 109756 <https://bugs.freedesktop.org/show_bug.cgi?id=109756> from
> Sergii Romantsov <sergii.romantsov@gmail.com> *
>
> Hello, Jiacheng.
> Paul asked you to 'trace' your application 'synopsys vcs-mx' with apitrace.
> Was you able to do it?
> Actually we don't need a log file, but just a trace (it should stay even due
> crash)
>
> ------------------------------
> You are receiving this mail because:
>
>    - You reported the bug.
>
>
Comment 6 Martin Peres 2019-11-27 13:50:06 UTC
-- GitLab Migration Automatic Message --

This bug has been migrated to freedesktop.org's GitLab instance and has been closed from further activity.

You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.freedesktop.org/xorg/driver/xf86-video-intel/issues/160.


Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.