radeon: RX7800XT: amdgpu: [mmhub] page fault in dmesg when launching sunshine
System information
- OS:
Exherbo Linux
- GPU:
2f:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Navi 32 [Radeon RX 7700 XT / 7800 XT] [1002:747e] (rev c8)
- Kernel version:
Linux exherbo 6.8.9 #1 SMP PREEMPT_DYNAMIC Thu May 2 20:57:44 CEST 2024 x86_64 GNU/Linux
- Mesa version:
OpenGL version string: 4.6 (Compatibility Profile) Mesa 24.1.0-rc2
- Xserver version:
21.1.13 (but running a wayland session)
- Desktop manager and compositor:
KDE Plasma 6.0.4 / kwin_wayland (6.0.4.1)
If applicable
- DXVK version: -
- Wine/Proton version: -
Describe the issue
Upon launching Sunshine (https://github.com/LizardByte/Sunshine) version 0.23.1
via:
$ systemctl start --user sunshine.service
I recently get the following dmesg amdgpu output/error:
[ 33.878141] input: Logitech Wireless Mouse PID:4038 as /devices/virtual/input/input19
[ 33.878280] input: Mouse passthrough as /devices/virtual/input/input20
[ 33.878612] input: Keyboard passthrough as /devices/virtual/input/input21
[ 34.372876] amdgpu 0000:2f:00.0: amdgpu: [mmhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0)
[ 34.372884] amdgpu 0000:2f:00.0: amdgpu: in page starting at address 0x0000800100747000 from client 18
[ 34.372887] amdgpu 0000:2f:00.0: amdgpu: MMVM_L2_PROTECTION_FAULT_STATUS:0x00042D52
[ 34.372889] amdgpu 0000:2f:00.0: amdgpu: Faulty UTCL2 client ID: VCNU1 (0x16)
[ 34.372892] amdgpu 0000:2f:00.0: amdgpu: MORE_FAULTS: 0x0
[ 34.372894] amdgpu 0000:2f:00.0: amdgpu: WALKER_ERROR: 0x1
[ 34.372896] amdgpu 0000:2f:00.0: amdgpu: PERMISSION_FAULTS: 0x5
[ 34.372898] amdgpu 0000:2f:00.0: amdgpu: MAPPING_ERROR: 0x1
[ 34.372900] amdgpu 0000:2f:00.0: amdgpu: RW: 0x1
[ 34.441368] amdgpu 0000:2f:00.0: amdgpu: [mmhub] page fault (src_id:0 ring:169 vmid:0 pasid:0, for process pid 0 thread pid 0)
[ 34.441374] amdgpu 0000:2f:00.0: amdgpu: in page starting at address 0x0000800100767000 from client 18
[ 34.441377] amdgpu 0000:2f:00.0: amdgpu: MMVM_L2_PROTECTION_FAULT_STATUS:0x00042752
[ 34.441379] amdgpu 0000:2f:00.0: amdgpu: Faulty UTCL2 client ID: VCNU0 (0x13)
[ 34.441381] amdgpu 0000:2f:00.0: amdgpu: MORE_FAULTS: 0x0
[ 34.441383] amdgpu 0000:2f:00.0: amdgpu: WALKER_ERROR: 0x1
[ 34.441385] amdgpu 0000:2f:00.0: amdgpu: PERMISSION_FAULTS: 0x5
[ 34.441387] amdgpu 0000:2f:00.0: amdgpu: MAPPING_ERROR: 0x1
[ 34.441389] amdgpu 0000:2f:00.0: amdgpu: RW: 0x1
Regression
Pretty sure I didn't see it before, but I can't tell exactly when it started as I do not check dmesg output very often.
Log files as attachment
Screenshots/video files (if applicable)
Any extra information would be greatly appreciated
- kernel 6.8.9
- linux-firmware 20240410
- libdrm 2.4.120
- mesa 24.1.0-rc2
- xf86-video-amdgpu 23.0.0
Edited by Timo Gurr