AMDGPU RAS REBOOT BEHAVIOR FOR UNRECOVERABLE ERRORS(9)

💖 AMDGPU RAS Reboot Behavior for Unrecoverable Errors(9) 💖

okay bestie, this one's straight from the Kernel API Manual and it's giving "GPU error endgame" energy 😭✨

🌸 DESCRIPTION 🌸

Normally, when there's an uncorrectable error, the driver will reset the GPU to recover — that's the usual recovery slay 💅.

But in the event of a unrecoverable error, the driver provides an interface to reboot the system automatically in that event. Yep, it just reboots. No cap 🫶.

The following file in debugfs provides that interface:

/sys/kernel/debug/dri/[0/1/2...]/ras/auto_reboot

Usage:

echo true > .../ras/auto_reboot

🔥 SEE ALSO 🔥

• Kernel file ./drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
• AMDGPU RAS debugfs control interface(9)
• AMDGPU RAS debugfs EEPROM table reset interface(9)
• AMDGPU RAS sysfs Error Count Interface(9)
• amdgpu_ras_query_error_count_helper(9)
• amdgpu_ras_query_error_count(9)
• AMDGPU RAS sysfs gpu_vram_bad_pages Interface(9)

xoxo, the source/version is ./drivers/gpu/drm/amd/amdgpu, dated October 2026 🎀💜