Binge watching youtube videos on chromium caused the GPU to crash
System information
System: Host: naomi-pc Kernel: 5.9.2-artix1-1 x86_64 bits: 64 compiler: gcc v: 10.2.0 Desktop: KDE Plasma 5.20.2
tk: Qt 5.15.1 wm: kwin_x11 dm: SDDM Distro: Artix Linux
CPU: Info: 8-Core model: AMD Ryzen 7 3800XT bits: 64 type: MT MCP arch: Zen 2 L2 cache: 4096 KiB
flags: avx avx2 lm nx pae sse sse2 sse3 sse4_1 sse4_2 sse4a ssse3 svm bogomips: 124843
Speed: 2798 MHz min/max: 2200/3900 MHz boost: enabled Core speeds (MHz): 1: 2799 2: 1866 3: 1913 4: 2069 5: 2194
6: 2193 7: 2192 8: 2193 9: 1866 10: 1866 11: 2201 12: 2198 13: 2197 14: 2199 15: 2695 16: 2070
Graphics: Device-1: Advanced Micro Devices [AMD/ATI] Ellesmere [Radeon RX 470/480/570/570X/580/580X/590]
vendor: Sapphire Limited Nitro+ driver: amdgpu v: kernel bus ID: 0c:00.0 chip ID: 1002:67df
Display: x11 server: X.org 1.20.9 compositor: kwin_x11 driver: modesetting alternate: ati,fbdev,vesa
resolution: <xdpyinfo missing>
OpenGL: renderer: Radeon RX 580 Series (POLARIS10 DRM 3.39.0 5.9.2-artix1-1-amd-i2c LLVM 10.0.1) v: 4.6 Mesa 20.2.0
direct render: Yes
Not cited in inxi, I am running a Samsung 22" TV monitor, 1920x1080 @ 60Hz over HDMI.
Describe the issue
I was watching youtube videos on my computer while not doing anything else. To be more exact, I left youtube videos on just for the music and I was doing entirely other stuff. When I came back to my computer, I saw that the GPU had crashed and it was impossible for me to get in the virtual terminals (I took the log from an SSH session). I had to reboot the computer to "restore" it in working conditions. Any GUI dependent program had become unresponsive to any kind of POSIX signals (excluding SIGKILL for obvious reasons). This usually means that I need to force reboot the system.
Regression
It used to work fine, though I don't really have a way to do regression testing right now. I first experienced it roughly a month ago. Since then it sometimes happens, and it other times does not.
Log files as attachment
[ 8224.020742] [drm:amdgpu_dm_atomic_commit_tail [amdgpu]] *ERROR* Waiting for fences timed out!
[ 8229.460604] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout, signaled seq=24015, emitted seq=24017
[ 8229.460692] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* Process information: process pid 0 thread pid 0
[ 8229.460696] amdgpu 0000:01:00.0: GPU reset begin!
[ 8229.470508] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, signaled seq=1085726, emitted seq=1085728
[ 8229.470567] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* Process information: process chromium pid 3209 thread chromium pid 3209
[ 8229.470569] amdgpu 0000:01:00.0: GPU reset begin!
[ 8229.470570] [drm] Bailing on TDR for s_job:1077f1, as another already in progress
[ 8229.892060] amdgpu 0000:01:00.0: GPU pci config reset
[ 8230.018265] amdgpu 0000:01:00.0: GPU reset succeeded, trying to resume
[ 8230.018636] [drm] PCIE GART of 256M enabled (table at 0x000000F4007E9000).
[ 8230.018646] [drm] VRAM is lost due to GPU reset!
[ 8230.115614] [drm] UVD and UVD ENC initialized successfully.
[ 8230.226600] [drm] VCE initialized successfully.
[ 8230.230988] [drm] recover vram bo from shadow start
[ 8230.234532] [drm] recover vram bo from shadow done
[ 8230.234535] [drm] Skip scheduling IBs!
[ 8230.234560] [drm] Skip scheduling IBs!
[ 8230.234561] [drm] Skip scheduling IBs!
[ 8230.234563] [drm] Skip scheduling IBs!
[ 8230.234569] [drm] Skip scheduling IBs!
[ 8230.234574] [drm] Skip scheduling IBs!
[ 8230.234578] amdgpu 0000:01:00.0: GPU reset(2) succeeded!
[ 8230.234581] [drm] Skip scheduling IBs!
[ 8230.234590] [drm] Skip scheduling IBs!
[ 8230.234591] [drm] Skip scheduling IBs!
[ 8230.234593] [drm] Skip scheduling IBs!
[ 8230.234594] [drm] Skip scheduling IBs!
[ 8230.234596] [drm] Skip scheduling IBs!
[ 8230.234598] [drm] Skip scheduling IBs!
[ 8230.234598] [drm] Skip scheduling IBs!
[ 8230.234601] [drm] Skip scheduling IBs!
[ 8230.234601] [drm] Skip scheduling IBs!
[ 8230.234603] [drm] Skip scheduling IBs!
[ 8230.234604] [drm] Skip scheduling IBs!
[ 8230.234605] [drm] Skip scheduling IBs!
[ 8230.234607] [drm] Skip scheduling IBs!
[ 8230.234608] [drm] Skip scheduling IBs!
[ 8230.234610] [drm] Skip scheduling IBs!
[ 8230.234612] [drm] Skip scheduling IBs!
[ 8230.234612] [drm] Skip scheduling IBs!
[ 8230.234615] [drm] Skip scheduling IBs!
[ 8230.234615] [drm] Skip scheduling IBs!
[ 8230.234618] [drm] Skip scheduling IBs!
[ 8230.234618] [drm] Skip scheduling IBs!
[ 8230.234620] [drm] Skip scheduling IBs!
[ 8230.234621] [drm] Skip scheduling IBs!
[ 8230.234622] [drm] Skip scheduling IBs!
[ 8230.234624] [drm] Skip scheduling IBs!
[ 8230.234625] [drm] Skip scheduling IBs!
[ 8230.234627] [drm] Skip scheduling IBs!
[ 8230.234628] [drm] Skip scheduling IBs!
[ 8230.234639] [drm] Skip scheduling IBs!
[ 8230.234646] [drm] Skip scheduling IBs!
[ 8230.234877] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 8240.340626] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8250.580451] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8260.820367] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8261.127283] GpuWatchdog[5282]: segfault at 0 ip 000055cff8b21c6e sp 00007fc42e35b380 error 6 in chromium[55cff4625000+798a000]
[ 8261.127293] Code: e8 56 6f ff 48 8b 7d b0 48 8d 45 c0 48 39 c7 74 05 e8 a6 75 ab fe 41 8b 84 24 e8 00 00 00 89 45 b0 48 8d 7d b0 e8 d2 b3 d2 fb <c7> 04 25 00 00 00 00 37 13 00 00 64 48 8b 04 25 28 00 00 00 48 3b
[ 8265.860197] [drm:amdgpu_dm_atomic_commit_tail [amdgpu]] *ERROR* Waiting for fences timed out!
[ 8271.700359] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8277.525520] GpuWatchdog[5303]: segfault at 0 ip 000055cff8b21c6e sp 00007fc42e35b380 error 6 in chromium[55cff4625000+798a000]
[ 8277.525528] Code: e8 56 6f ff 48 8b 7d b0 48 8d 45 c0 48 39 c7 74 05 e8 a6 75 ab fe 41 8b 84 24 e8 00 00 00 89 45 b0 48 8d 7d b0 e8 d2 b3 d2 fb <c7> 04 25 00 00 00 00 37 13 00 00 64 48 8b 04 25 28 00 00 00 48 3b
[ 8281.940369] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8292.180113] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8302.419868] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8312.235489] GpuWatchdog[5351]: segfault at 0 ip 000055cff8b21c6e sp 00007fc42e35b380 error 6 in chromium[55cff4625000+798a000]
[ 8312.235498] Code: e8 56 6f ff 48 8b 7d b0 48 8d 45 c0 48 39 c7 74 05 e8 a6 75 ab fe 41 8b 84 24 e8 00 00 00 89 45 b0 48 8d 7d b0 e8 d2 b3 d2 fb <c7> 04 25 00 00 00 00 37 13 00 00 64 48 8b 04 25 28 00 00 00 48 3b
[ 8312.660036] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8322.899594] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8333.139665] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8343.389528] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8343.674443] elogind-daemon[1291]: New session 4 of user naomi.
[ 8351.698996] Failed to expire sync object before unbinding TTM
[ 8353.619478] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8363.859346] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8374.099115] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8379.218655] Failed to expire sync object before unbinding TTM
[ 8384.339119] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8394.578474] Failed to expire sync object before unbinding TTM
[ 8394.578646] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout, but soft recovered
[ 8394.578700] Failed to expire sync object before unbinding TTM
Screenshots/video files (if applicable)
I couldn't take a photo out of the glitchiness because I thought of just taking logs and rebooting. Sorry :C
It is fairly similar to the photo posted on #3584 (maybe it is related to that issue as well?)
Any extra information would be greatly appreciated
It also happened randomly when I was playing Minecraft (1.16.3) vanilla, though I have no logs of that time (the symptom was the same one).
I can reproduce the crashing on purpose if I use Minecraft (1.16.3) with the shaders mod.
Playing games on Steam Proton generally works fine and does not crash my card, not even when the load is heavy.