Arch Linux

sanne2

Member

Registered: 2024-06-05

Posts: 8

AMD GPU MES errors and page faults on Arch Linux when use darktable

Hello,
I'm experiencing AMD GPU driver issues on Arch Linux with my AMD graphics card. The system shows MES errors and page faults in the kernel logs.

System Information:
Kernel: 6.12.59-1-lts
CPU and GPU: AMD Ryzen 7 7840HS w/ Radeon 780M Graphics
Driver: amdgpu

error log:

~ ❯ sudo journalctl -b 0 -k -p err -r                                                                                                         ✘ INT 7s 00:38:14
Dec 13 00:37:45 primary-pc kernel: [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
Dec 13 00:37:45 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
Dec 13 00:37:43 primary-pc kernel: [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
Dec 13 00:37:43 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
Dec 13 00:37:40 primary-pc kernel: [drm:amdgpu_device_ip_suspend_phase2 [amdgpu]] *ERROR* suspend of IP block <mes_v11_0> failed -110
Dec 13 00:37:40 primary-pc kernel: [drm:amdgpu_mes_suspend [amdgpu]] *ERROR* failed to suspend all gangs
Dec 13 00:37:40 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: MES failed to respond to msg=SUSPEND
Dec 13 00:37:37 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: Failed to evict process queues
Dec 13 00:37:37 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: Failed to evict queue 1
Dec 13 00:37:37 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: MES might be in unrecoverable state, issue a GPU reset
Dec 13 00:37:37 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: failed to remove hardware queue from MES, doorbell=0x1002
Dec 13 00:37:37 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu:          RW: 0x0
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu:          MAPPING_ERROR: 0x0
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu:          PERMISSION_FAULTS: 0xb
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu:          WALKER_ERROR: 0x0
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu:          MORE_FAULTS: 0x0
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu:          Faulty UTCL2 client ID: SQC (inst) (0x9)
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x008012B0
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu:   in page starting at address 0x0000000000000000 from client 10
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu:  in process darktable pid 205695 thread worker 1 pid 205774)
Dec 13 00:37:35 primary-pc kernel: amdgpu 0000:c5:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:88 vmid:8 pasid:32798)

Last edited by sanne2 (2025-12-12 16:47:20)

Lone_Wolf

Administrator

From: Netherlands, Europe

Registered: 2005-10-04

Posts: 14,795

Re: AMD GPU MES errors and page faults on Arch Linux when use darktable

GCVM_L2_PROTECTION_FAULT_STATUS:0x008012B0

That's a nasty one to troubleshoot .

Does the stock linux kernel (6.17.9 currently) also have the issue ?

---

Disliking systemd intensely, but not satisfied with alternatives so focusing on taming systemd.

clean chroot building not flexible enough ?
Try clean chroot manager by graysky