[amdgpu][renoir][ryzen5800H] amdgpu ring vcn_dec timeout when playing 2 VA-API streams
System information
- OS: Arch Linux
- GPU: 05:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Cezanne [1002:1638] (rev c5)
- Kernel version: 5.14.3-arch1-1
- Mesa version: Mesa 21.2.1
- Xserver version (if applicable): /
- Desktop manager and compositor: sway
Lenovo IdeaPad 5 Pro Gen 6 Notebook with Ryzen 5800H CPU.
Describe the issue
When watching 2 videos in parallel i.e. watching 2 Twitch streams using FireFox with VA-API enabled or via mpv with "--hwdec=vaapi" the amdgpu driver crashes after a couple of seconds playing. The kernel recovers from the crash, one video will continue playing, the other one is still broken.
Watching a single video with VA-API works.
Regression
Since it is a new notebook I don't know if it ever worked.
Log files as attachment
dmesg of the issue (full dmesg attached):
[ 104.649648] [drm:amdgpu_dm_atomic_commit_tail [amdgpu]] *ERROR* Waiting for fences timed out!
[ 109.769438] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring vcn_dec timeout, signaled seq=4195, emitted seq=4197
[ 109.769429] [drm:amdgpu_dm_atomic_commit_tail [amdgpu]] *ERROR* Waiting for fences timed out!
[ 109.769781] [drm:amdgpu_job_timedout [amdgpu]] *ERROR* Process information: process mpv pid 1655 thread mpv:cs0 pid 1671
[ 109.770062] amdgpu 0000:05:00.0: amdgpu: GPU reset begin!
[ 110.065171] [drm] Register(0) [mmUVD_POWER_STATUS] failed to reach value 0x00000001 != 0x00000002
[ 110.257322] [drm] Register(0) [mmUVD_RBC_RB_RPTR] failed to reach value 0x000001a0 != 0x00000180
[ 110.449827] [drm] Register(0) [mmUVD_POWER_STATUS] failed to reach value 0x00000001 != 0x00000002
[ 110.458451] [drm] free PSP TMR buffer
[ 110.486808] amdgpu 0000:05:00.0: amdgpu: MODE2 reset
[ 110.487284] amdgpu 0000:05:00.0: amdgpu: GPU reset succeeded, trying to resume
[ 110.487458] [drm] PCIE GART of 1024M enabled.
[ 110.487462] [drm] PTB located at 0x000000F400900000
[ 110.487933] [drm] PSP is resuming...
[ 110.507984] [drm] reserve 0x400000 from 0xf47f800000 for PSP TMR
[ 110.589931] amdgpu 0000:05:00.0: amdgpu: RAS: optional ras ta ucode is not available
[ 110.598557] amdgpu 0000:05:00.0: amdgpu: RAP: optional rap ta ucode is not available
[ 110.598560] amdgpu 0000:05:00.0: amdgpu: SECUREDISPLAY: securedisplay ta ucode is not available
[ 110.598563] amdgpu 0000:05:00.0: amdgpu: SMU is resuming...
[ 110.600595] amdgpu 0000:05:00.0: amdgpu: SMU is resumed successfully!
[ 110.791991] [drm] kiq ring mec 2 pipe 1 q 0
[ 110.792541] [drm] DMUB hardware initialized: version=0x01010019
[ 110.959413] [drm] VCN decode and encode initialized successfully(under DPG Mode).
[ 110.959471] [drm] JPEG decode initialized successfully.
[ 110.959478] amdgpu 0000:05:00.0: amdgpu: ring gfx uses VM inv eng 0 on hub 0
[ 110.959483] amdgpu 0000:05:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[ 110.959484] amdgpu 0000:05:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[ 110.959485] amdgpu 0000:05:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 5 on hub 0
[ 110.959486] amdgpu 0000:05:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 6 on hub 0
[ 110.959488] amdgpu 0000:05:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 7 on hub 0
[ 110.959489] amdgpu 0000:05:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 8 on hub 0
[ 110.959490] amdgpu 0000:05:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 9 on hub 0
[ 110.959491] amdgpu 0000:05:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 10 on hub 0
[ 110.959494] amdgpu 0000:05:00.0: amdgpu: ring kiq_2.1.0 uses VM inv eng 11 on hub 0
[ 110.959495] amdgpu 0000:05:00.0: amdgpu: ring sdma0 uses VM inv eng 0 on hub 1
[ 110.959496] amdgpu 0000:05:00.0: amdgpu: ring vcn_dec uses VM inv eng 1 on hub 1
[ 110.959497] amdgpu 0000:05:00.0: amdgpu: ring vcn_enc0 uses VM inv eng 4 on hub 1
[ 110.959498] amdgpu 0000:05:00.0: amdgpu: ring vcn_enc1 uses VM inv eng 5 on hub 1
[ 110.959499] amdgpu 0000:05:00.0: amdgpu: ring jpeg_dec uses VM inv eng 6 on hub 1
[ 110.962160] amdgpu 0000:05:00.0: amdgpu: recover vram bo from shadow start
[ 110.962163] amdgpu 0000:05:00.0: amdgpu: recover vram bo from shadow done
[ 110.962197] [drm] Skip scheduling IBs!
[ 110.962198] [drm] Skip scheduling IBs!
[ 110.962243] [drm] Skip scheduling IBs!
[ 110.962259] amdgpu 0000:05:00.0: amdgpu: GPU reset(1) succeeded!
[ 110.962500] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.963056] [drm] Skip scheduling IBs!
[ 110.966885] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.973422] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.974081] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.981674] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.982045] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.982280] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.982450] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.982642] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 110.983019] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[ 253.629325] kauditd_printk_skb: 160 callbacks suppressed