Unrecoverable GPU HANG

Dec 03 20:52:27 TY-T580 kernel: i915 0000:00:02.0: GPU HANG: ecode 9:1:0x00000000, hang on rcs0
Dec 03 20:52:27 TY-T580 kernel: GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
Dec 03 20:52:27 TY-T580 kernel: Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
Dec 03 20:52:27 TY-T580 kernel: drm/i915 developers can then reassign to the right component if it's not a kernel issue.
Dec 03 20:52:27 TY-T580 kernel: The GPU crash dump is required to analyze GPU hangs, so please always attach it.
Dec 03 20:52:27 TY-T580 kernel: GPU crash dump saved to /sys/class/drm/card0/error
Dec 03 20:52:27 TY-T580 kernel: i915 0000:00:02.0: Resetting rcs0 for hang on rcs0
Dec 03 20:53:01 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080
Dec 03 20:53:01 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080
Dec 03 20:53:01 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080
Dec 03 20:53:01 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080


These pipe A faults continued for more than 300,000 lines before I rebooted. During this time I couldn't see anything useful due to garbled screen output.

Dec 03 20:53:41 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080
Dec 03 20:53:41 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080
Dec 03 20:53:41 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080
Dec 03 20:53:41 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080
Dec 03 20:53:41 TY-T580 kernel: [drm:gen8_de_irq_handler [i915]] *ERROR* Fault errors on pipe A: 0x00000080

Since I'm looking at this after reboot, there is nothing in /sys/class/drm/card0/error