[6.7.0-0.rc1] RX 7900 XTX: amdgpu: [gfxhub] page fault
I see a similar bug at #2943, but creating a new one since I don't see the issue on the kernel version here's reporting on. It's perfectly fine on the Fedora 39 stable kernel (6.5.11).
Brief summary of the problem:
I don't actually see any problems on screen. I only noticed the issue when I went to check dmesg errors. I can consistently reproduce this every boot on Fedora Rawhide which is currently using Linux 6.7.0 RC1.
amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0)
amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x000080885bcb6000 from client 10
amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00041D52
amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: SDMA1 (0xe)
amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0
amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x1
amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x5
amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x1
amdgpu 0000:03:00.0: amdgpu: RW: 0x1
Hardware description:
- CPU: AMD Ryzen 9 7950X
- GPU: AMD Radeon RX 7900 XTX
- Motherboard: ASRock X670E Taichi
- System Memory: F5-6400J3239F48GX2-TZ5RK
- Display(s): ASUS ROG PG279QM
- Type of Display Connection: DP
System information:
- Distro name and Version: Fedora Rawhide
- Kernel version: 6.7.0-0.rc1.20231117git7475e51b8796.19.fc40.x86_64
- Custom kernel: N/A
- AMD official driver version: N/A
How to reproduce the issue:
Boot up, check dmesg.
Logs
- Full dmesg: dmesg.log
- Errors only: dmesg-err.log