AMD 8700G [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx_0.0.0 timeout

Brief summary of the problem:

100% occurrences when playing 3D games (using "Wine" or native Linux games) after some seconds or minutes. Tested with ~10 games. No occurrences when playing 2D content (Like old consoles emulation). The screen freezes and sometimes the application crashes. The system is still up and running.

Hardware description:

• CPU: AMD Ryzen 7 8700G w/ Radeon 780M Graphics
• GPU: Advanced Micro Devices, Inc. [AMD/ATI] Phoenix [1002:15bf] (rev 06)
• System Memory: 32GB (Note: I tested with multiple DDR5 kits, from 8GB 5600 to 32GB 7200, with or without EXPO/XMP profiles enabled)
• Display(s): 3840x2160@60Hz
• Type of Display Connection: HDMI

System information:

• Distro name and Version: Batocera 39 2024/02/09 22:37
• Kernel version: Linux 6.7.2 #1 SMP PREEMPT_DYNAMIC Fri Feb 9 10:46:05 Europe 2024 x86_64 GNU/Linux
• Custom kernel: N/A
• AMD official driver version: N/A
• Linux-firmware version: 20240115

How to reproduce the issue:

• Run any 3D game and wait.

Log files (for system lockups / game freezes / crashes)

Dmesg log when crashing:

[ 2054.100213] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx_0.0.0 timeout, signaled seq=290341, emitted seq=290343
[ 2054.100374] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* Process information: process X pid 2314 thread X:cs0 pid 2416
[ 2054.100505] amdgpu 0000:11:00.0: amdgpu: GPU reset begin!
[ 2054.269299] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2054.269438] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2054.396749] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2054.396880] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2054.524197] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2054.524299] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2054.651616] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2054.651717] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2054.779040] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2054.779141] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2054.906480] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2054.906580] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2055.033914] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2055.034030] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2055.161355] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2055.161456] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2055.288788] [drm:mes_v11_0_submit_pkt_and_poll_completion.constprop.0 [amdgpu]] *ERROR* MES failed to response msg=3
[ 2055.288888] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[ 2055.488467] [drm:gfx_v11_0_hw_fini [amdgpu]] *ERROR* failed to halt cp gfx
[ 2055.489756] amdgpu 0000:11:00.0: amdgpu: MODE2 reset
[ 2055.525694] amdgpu 0000:11:00.0: amdgpu: GPU reset succeeded, trying to resume
[ 2055.526082] [drm] PCIE GART of 512M enabled (table at 0x000000801FD00000).
[ 2055.526157] amdgpu 0000:11:00.0: amdgpu: SMU is resuming...
[ 2055.528319] amdgpu 0000:11:00.0: amdgpu: SMU is resumed successfully!
[ 2055.530224] [drm] DMUB hardware initialized: version=0x08003000
[ 2055.725083] [drm] kiq ring mec 3 pipe 1 q 0
[ 2055.727196] [drm] VCN decode and encode initialized successfully(under DPG Mode).
[ 2055.727392] amdgpu 0000:11:00.0: [drm:jpeg_v4_0_hw_init [amdgpu]] JPEG decode initialized successfully.
[ 2055.727786] amdgpu 0000:11:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[ 2055.727787] amdgpu 0000:11:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[ 2055.727788] amdgpu 0000:11:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[ 2055.727788] amdgpu 0000:11:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
[ 2055.727789] amdgpu 0000:11:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
[ 2055.727789] amdgpu 0000:11:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
[ 2055.727789] amdgpu 0000:11:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
[ 2055.727790] amdgpu 0000:11:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
[ 2055.727790] amdgpu 0000:11:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
[ 2055.727790] amdgpu 0000:11:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
[ 2055.727791] amdgpu 0000:11:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
[ 2055.727792] amdgpu 0000:11:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
[ 2055.727792] amdgpu 0000:11:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
[ 2055.729792] amdgpu 0000:11:00.0: amdgpu: recover vram bo from shadow start
[ 2055.729793] amdgpu 0000:11:00.0: amdgpu: recover vram bo from shadow done
[ 2055.729800] amdgpu 0000:11:00.0: amdgpu: GPU reset(6) succeeded!
[ 2055.729820] [drm] Skip scheduling IBs!
[ 2055.729823] [drm] Skip scheduling IBs!
[ 2055.729825] [drm] Skip scheduling IBs!
[ 2055.729826] [drm] Skip scheduling IBs!
[ 2055.729827] [drm] Skip scheduling IBs!
[ 2055.729828] [drm] Skip scheduling IBs!
[ 2055.729829] [drm] Skip scheduling IBs!
[ 2055.729830] [drm] Skip scheduling IBs!
[ 2055.729830] [drm] Skip scheduling IBs!
[ 2055.729831] [drm] Skip scheduling IBs!
[ 2055.729832] [drm] Skip scheduling IBs!
[ 2055.729833] [drm] Skip scheduling IBs!
[ 2055.729834] [drm] Skip scheduling IBs!
[ 2055.729835] [drm] Skip scheduling IBs!
[ 2055.729836] [drm] Skip scheduling IBs!
[ 2055.729837] [drm] Skip scheduling IBs!
[ 2055.729838] [drm] Skip scheduling IBs!
[ 2055.729839] [drm] Skip scheduling IBs!
[ 2055.741627] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!

Full Dmesg log: ## Attached files:dmesg.7z