Created attachment 120687 [details] Output of cat /sys/class/drm/card0/error I bought the game "Never Alone" on Steam and started playing. It worked for a minute and then hung, eventually closing the game. Looking through dmesg I found a notice that suggested to report this here. CPU is i7-6700hq, Kernel 4.4.0-rc6, Xorg driver xf86-video-intel 1:2.99.917+519+g8229390-1, Arch Linux. If you need more information, I'd be happy to come up with it :)
There were workaround for SKL and improvements pushed in kernel and Mesa that will benefit to your system, so please re-test with latest kernel & Mesa to see if this issue is still occurring (you may also collect and attach logs collected thanks to apitrace: http://apitrace.github.io/) Kernel: 4.4.0-rc6-mainline Platform: SKL - i7-6700h Mesa: [Please confirm your mesa version] In the meantime, assigning to Mesa product. From this error dump, hung is happening in render ring batch with active head at 0xf8026324, with 0x78260000 (3DSTATE_BINDING_TABLE_POINTERS_VS) as IPEHR. Batch extract (around 0xf8026324): 0xf8026318: 0x00000000: MI_NOOP 0xf802631c: 0x78260000: 3DSTATE_BINDING_TABLE_POINTERS_VS 0xf8026320: 0x00000000: dword 1 0xf8026324: 0x782a0000: 3DSTATE_BINDING_TABLE_POINTERS_PS 0xf8026328: 0x00007a60: dword 1 0xf802632c: 0x782f0000: 3DSTATE_SAMPLER_STATE_POINTERS_PS 0xf8026330: 0x00007a40: dword 1 Bad length 9 in 3DSTATE_VS, expected 6-6 0xf8026334: 0x78100007: 3DSTATE_VS 0xf8026338: 0x00099c00: kernel pointer 0xf802633c: 0x00000000: SPF=0, VME=0, Sampler Count 0, Binding table count 0 0xf8026340: 0x00010000: scratch offset 0xf8026344: 0x00000000: Dispatch GRF start 0, VUE read length 0, VUE read offset 0 0xf8026348: 0x00000000: Max Threads 1, Vertex Cache enable, VS func disable
Please test a new version of Mesa (12 or 13) and mark as REOPENED if you can reproduce and RESOLVED/* if you cannot reproduce. If you can reproduce, please capture and upload an apitrace (https://github.com/apitrace/apitrace) so that we can easily reproduce as well.
The GPU hangs still happen as of today. ➜ ~ uname -a Linux revolution 4.8.6-1-ARCH #1 SMP PREEMPT Mon Oct 31 18:51:30 CET 2016 x86_64 GNU/Linux ➜ ~ pacman -Qi mesa | grep Version Version : 13.0.0-1 I made an apitrace, it's a mere 2GB however, will try to upload as an attachment now ;-)
Upload is too big... You can download the trace here: http://schrodt.org/Never_Alone.x64.trace.bz2 (2.1GB) Uploading now, ETA 30min.
Reproduced this hang with mesa master commit 3ff9f8c on SKL, kernel 4.7.10-100.fc23.x86_64. Attached apitrace is too big. I'll try to trim it down to a reasonable size where I can do an aubdump.
Hello. Thanks for apitrace. I found out that I can reproduce this issue on: Manjaro OpenGL version string: 3.0 Mesa 13.0.0 (git-df1b0a5a86) SKL _______ [864073.199929] [drm] GPU HANG: ecode 9:0:0x84df7cfc, in glretrace [13985], reason: Hang on rcs0, action: reset [864073.199938] i915 0000:00:02.0: Resetting rcs0 after gpu hang [864077.242807] asynchronous wait on fence i915:Xorg[1782]/0:481d9 timed out [864081.296258] i915 0000:00:02.0: Resetting rcs0 after gpu hang [864089.189584] i915 0000:00:02.0: Resetting rcs0 after gpu hang [864097.082928] i915 0000:00:02.0: Resetting rcs0 after gpu hang [864100.282801] asynchronous wait on fence i915:Xorg[1782]/0:481e1 timed out [864105.189590] i915 0000:00:02.0: Resetting rcs0 after gpu hang ______________________ But issue is not actual on mesa 18.1.0 (from manjaro repo). So issue can be closed as fixed somewhere between.
resolving, see comment #6
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.