I’m using Arch Linux (fully updated) with BIOS 20250902 and the linux-zen kernel on a Ryzen 7840 FW13 mainboard.
When under GPU load the laptop will often lockup or hard reboot. After a lockup the only thing i can do is hold the power button to force restart. After restarting the journal from the previous boot doesn’t show anything related (Usually the last line is something like wlan0: CTRL-EVENT-SIGNAL-CHANGE above=1 signal=-61 noise=9999 txrate=576400 since the WiFi driver spams that constantly)
These reboots happen occasionally when running games and extremely often with GPGPU loads (like Folding@Home and machine learning). Sometimes instead of instantly crashing slight graphical artifact shows up or the GPU resets with this in the log:
amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
amdgpu 0000:c1:00.0: amdgpu: failed to remove hardware queue from MES, doorbell=0x1004
amdgpu 0000:c1:00.0: amdgpu: MES might be in unrecoverable state, issue a GPU reset
amdgpu 0000:c1:00.0: amdgpu: Failed to evict queue 3
amdgpu 0000:c1:00.0: amdgpu: GPU reset begin!
amdgpu 0000:c1:00.0: amdgpu: Failed to evict queue 1
amdgpu 0000:c1:00.0: amdgpu: Failed to evict queue 0
amdgpu: Failed to quiesce KFD
amdgpu 0000:c1:00.0: amdgpu: Dumping IP State
amdgpu 0000:c1:00.0: amdgpu: Dumping IP State Completed
amdgpu: Freeing queue vital buffer 0x7f6194600000, queue evicted
amdgpu: Freeing queue vital buffer 0x7f6228c00000, queue evicted
amdgpu: Freeing queue vital buffer 0x7f6240400000, queue evicted
amdgpu: Freeing queue vital buffer 0x7f6241400000, queue evicted
amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
amdgpu 0000:c1:00.0: amdgpu: failed to unmap legacy queue
amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
kwin_wayland[1052]: Pageflip timed out! This is a bug in the amdgpu kernel driver
kwin_wayland[1052]: Please report this at https://gitlab.freedesktop.org/drm/amd/-/issues
kwin_wayland[1052]: With the output of 'sudo dmesg' and 'journalctl --user-unit plasma-kwin_wayland --boot 0'
amdgpu 0000:c1:00.0: amdgpu: failed to unmap legacy queue
amdgpu 0000:c1:00.0: amdgpu: MODE2 reset
amdgpu 0000:c1:00.0: amdgpu: GPU reset succeeded, trying to resume
amdgpu 0000:c1:00.0: amdgpu: [drm] AMDGPU device coredump file has been created
amdgpu 0000:c1:00.0: amdgpu: [drm] Check your /sys/class/drm/card1/device/devcoredump/data
amdgpu 0000:c1:00.0: amdgpu: SMU is resuming...
amdgpu 0000:c1:00.0: amdgpu: SMU is resumed successfully!
amdgpu 0000:c1:00.0: amdgpu: [drm] DMUB hardware initialized: version=0x08005400
kwin_wayland[1052]: Pageflip arrived after all, 1882ms after the commit
Is there any way to fix this in software, or is this a hardware issue that needs a mainboard replacement?
Thanks in advance