Bug 102228 - [drm] GPU HANG: ecode 6:0:0x6770706f, in kwin_x11 [2345], reason: Hang on render ring, action: reset
Summary: [drm] GPU HANG: ecode 6:0:0x6770706f, in kwin_x11 [2345], reason: Hang on ren...
Status: CLOSED FIXED
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
Hardware: x86-64 (AMD64) Linux (All)
: medium critical
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2017-08-15 06:33 UTC by Andrew
Modified: 2018-02-13 16:37 UTC (History)
1 user (show)

See Also:
i915 platform: SNB
i915 features: GPU hang


Attachments
GPU dump and kernel messages (158.47 KB, application/gzip)
2017-08-15 06:33 UTC, Andrew
no flags Details

Description Andrew 2017-08-15 06:33:33 UTC
Created attachment 133522 [details]
GPU dump and kernel messages

Hi. Please delete this if it is duplicated. I can't tell if it is, so I have filed a new bug as instructed by my dmesg messages.

While running a copy operation and the steam client under OpenSUSE 42.3, the system will freeze/hang. Sometimes it will recover enough for me to save the kernel logs and GPU error dump attached. Most of the time, it is a hard crash (power cycle required to recover)

Kernel: 4.4.79-4-default
Mesa info:
Vendor: Intel Open Source Technology Center (0x8086)
    Device: Mesa DRI Intel(R) Sandybridge Mobile  (0x116)
    Version: 17.0.5
    Accelerated: yes
And with DRI_PRIME=1:
    Vendor: X.Org (0x1002)
    Device: AMD TURKS (DRM 2.49.0 / 4.4.79-4-default, LLVM 3.8.0) (0x6741)
    Version: 17.0.5
    Accelerated: yes


Hardware: Dell Vostro 3550 Laptop, with Radeon/Intel graphics (open source drivers). 

If there is more information required, I can try to produce it, but my time is somewhat limited.
Comment 1 Chris Wilson 2017-08-15 11:02:56 UTC
Hmm, the set of active buffers is suspicious enough to suggest that this is bug 99671. All we can suggest at the moment is getting the latest kernel (4.12) and mesa (17.2) and crossing your fingers.
Comment 2 Andrew 2017-08-15 11:41:18 UTC
(In reply to Chris Wilson from comment #1)
> Hmm, the set of active buffers is suspicious enough to suggest that this is
> bug 99671. All we can suggest at the moment is getting the latest kernel
> (4.12) and mesa (17.2) and crossing your fingers.

I just realised that part of my problem is my hard disk appears to be unreliable(never buy a sshd), which muddies the waters unfortunately. 

I have a replacement, so I will try again tonight. I'll also see if I can update to the latest kernel and mesa. 

Thanks
Comment 3 Andrew 2017-08-17 06:07:27 UTC
(In reply to Chris Wilson from comment #1)
> Hmm, the set of active buffers is suspicious enough to suggest that this is
> bug 99671. All we can suggest at the moment is getting the latest kernel
> (4.12) and mesa (17.2) and crossing your fingers.

Hi 

I retested on kernel 4.4.79-4-default with a new hard disk, and the issue was still present.

I then updated to 4.12, and it seems that this (without the mesa update) resolves this issue. I didn't do the mesa update because Kernel 4.12 broke my touchpad, and I spent quite a while trying to fix that before getting around to trying to do the update. 

I think this can be marked resolved?

Thank you for your assistance.
Comment 4 Jari Tahvanainen 2017-08-18 12:37:11 UTC
Verified by Reporter - see previous comment.
Comment 5 Elizabeth 2018-02-13 16:37:24 UTC
Closing old verified.


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.