umr top triggers "amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C"
Brief summary of the problem:
Yesterday I noticed that GUI apps and some CLI apps suddenly took pretty long time to open, and while an app was opening the cpu usage on the app's process was 100% (1 CPU core).
I don't know how that randomly happened, but I can reproduce it constantly by launching umr using sudo umr -t
The system is still kinda usable, but launching anything GPU related takes a loong time to start. For example simply launching glxgears
after triggering this bug takes about 2 minutes to actually open.
Hardware description:
- CPU: Ryzen 9 4900HS
- GPU: Vega 8 (Advanced Micro Devices, Inc. [AMD/ATI] Renoir [1002:1636] (rev c5))
- System Memory: 24GB
- Display(s): Internal Laptop display
- Type of Display Connection: eDP
- Laptop: ASUS Zephyrus G15 2020 (GA502IV) with the latest bios version
300
System information:
- Distro name and Version: Arch Linux
- Kernel version: 6.4.1-arch1-1-snipex (Same behavior on Linux 6.5-rc1)
- Custom kernel: 6.4.1-arch1-1-snipex is the Arch Linux's stock kernel + this patch
- AMD official driver version: amdgpu + mesa 23.1.3
- DE: KDE Plasma 5.27.6 (Wayland session)
How to reproduce the issue:
- Install umr-git from the AUR, my current version is commit 2847b9980edd0e99a37241031999d7a5abd19eee
- Launch umr top with
sudo umr -t
Attached files:
Log files (for system lockups / game freezes / crashes)
Sample:
[55204.366023] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
[55204.366041] amdgpu 0000:06:00.0: amdgpu: Failed to export SMU metrics table!
[55209.967084] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
[55209.967102] amdgpu 0000:06:00.0: amdgpu: Failed to export SMU metrics table!
[55215.585143] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
[55215.585161] amdgpu 0000:06:00.0: amdgpu: Failed to export SMU metrics table!
[55221.202035] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
[55221.202053] amdgpu 0000:06:00.0: amdgpu: Failed to export SMU metrics table!
[55226.761138] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
[55226.761156] amdgpu 0000:06:00.0: amdgpu: Failed to export SMU metrics table!
[55232.390437] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
[55232.390456] amdgpu 0000:06:00.0: amdgpu: Failed to export SMU metrics table!
[55238.004440] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
[55238.004464] amdgpu 0000:06:00.0: amdgpu: Attempt to get max GX frequency from SMC Failed !
[55243.526148] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
[55243.526165] amdgpu 0000:06:00.0: amdgpu: Attempt to get min GX frequency from SMC Failed !
[55249.135657] amdgpu 0000:06:00.0: amdgpu: SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x0000001C SMN_C2PMSG_82:0x00000007
dmesg: amdgpu-hang_2023-07-16