Bug 102465

Summary: [SKL] GPU hang (render ring)
Product: DRI Reporter: sean.stanko
Component: DRM/IntelAssignee: Intel GFX Bugs mailing list <intel-gfx-bugs>
Status: RESOLVED DUPLICATE QA Contact: Intel GFX Bugs mailing list <intel-gfx-bugs>
Severity: blocker    
Priority: medium CC: intel-gfx-bugs
Version: unspecified   
Hardware: x86-64 (AMD64)   
OS: Linux (All)   
Whiteboard:
i915 platform: SKL i915 features: GPU hang
Attachments:
Description Flags
GPU error
none
GPU error (2)
none
dmesg none

Description sean.stanko 2017-08-29 01:03:25 UTC
System is a second generation Intel computestick running Ubuntu 16.04 and kernel version 4.10.0-33-generic. C-states have been disabled. "timed out waiting for forcewake ack request" is spammed, then GPU hangs while in a ROS gscam process.

See attached files for dmesg log and error log.
Comment 1 sean.stanko 2017-08-29 01:05:25 UTC
Created attachment 133858 [details]
GPU error
Comment 2 sean.stanko 2017-08-29 01:27:21 UTC
Created attachment 133859 [details]
GPU error (2)
Comment 3 sean.stanko 2017-08-29 01:28:38 UTC
Created attachment 133860 [details]
dmesg
Comment 4 Chris Wilson 2017-08-29 11:44:42 UTC
Hmm, the video decoder is active at the time of the hang, so the forcewake errors may well be due to an invalid batch. It then screws up the gpu such that recovery is then impossible. Since the GPU is dead, the error state is devoid of register information, definitely an interesting side-effect! The second hang also points the finger at libva.

It's worth just sticking on drm-tip [https://cgit.freedesktop.org/drm-tip] just to see if anything changes.
Comment 5 sean.stanko 2017-09-01 21:20:04 UTC
Update, from my end:

Due to some software dependencies on our system, I'm hesitant to change the kernel version.

I've done some research on the problem and found the Arch Linux community has reported 1915 issues with Skylake processors (https://wiki.archlinux.org/index.php/intel_graphics#Skylake_support). While this is a Debian/Ubuntu system, I tried their recommendation of setting i915.enable_rc6=0 in my grub configuration, which appears to resolve/suppress the GPU hangs,
Comment 6 Jani Saarinen 2018-03-29 07:11:22 UTC
First of all. Sorry about spam.
This is mass update for our bugs. 

Sorry if you feel this annoying but with this trying to understand if bug still valid or not.
If bug investigation still in progress, please ignore this and I apologize!

If you think this is not anymore valid, please comment to the bug that can be closed.
If you haven't tested with our latest pre-upstream tree(drm-tip), can you do that also to see if issue is valid there still and if you cannot see issue there, please comment to the bug.
Comment 7 Jani Saarinen 2018-04-25 06:59:06 UTC
Closing, please re-open is issue still exists.
Comment 8 Chris Wilson 2019-04-01 09:08:25 UTC
Forward dup to retain some history.

*** This bug has been marked as a duplicate of bug 110297 ***

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.