[skl] GPU HANG: ecode 9:1:85dffffb in Xorg
I have not yet found a way to consistently provoke the hang. So far it always happened during compilation tasks, thus, heavy CPU load.
It happens in about 1 out of 10 cases and it usually happens about 1 minute into the compilation.
CPU temps are normal (~60C).
This has started happening after updating to kernel 5.9, but this was not the only update.
If there is more info needed let me know.
- Distro: Manjaro
- Arch: x86_64
- Kernel: 5.9.3-1-MANJARO
- Machine: Lenovo ThinkPad P50 (20EN0006GE)
- CPU: i7-6820HQ
- Display: internal + DP connected to VGA adapter
From the journal:
kernel: i915 0000:00:02.0: [drm] Resetting rcs0 for preemption time out
kernel: i915 0000:00:02.0: [drm] Xorg[997] context reset due to GPU hang
kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 9:1:85dffffb, in Xorg [997]
kernel: GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
kernel: Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.
kernel: Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.
kernel: drm/i915 developers can then reassign to the right component if it's not a kernel issue.
kernel: The GPU crash dump is required to analyze GPU hangs, so please always attach it.
kernel: GPU crash dump saved to /sys/class/drm/card0/error
crash dump: gpu_dump