DCMUB Error on BIOS 3.05 + Kernel 6.13.1 hit a very nasty AMDGPU bug on Framework Laptop 13 (AMD Ryzen 7 7840U)

Framework Laptop 13 Linux
1

Hi all,

I have 64GB of RAM official from Framework, and 4GB are allocated to the AMDGPU (UMA optimized options in BIOS, I don’t remember the exact name anymore).

USB-C dock : Thinkpad USB-C dock gen 2 with one screen 1920x1080@60hz using HDMI plugged in.

So I was just browsing the web with about 30 tabs open, and the laptop just froze a few times and the gpu did recover at first, but then I tried to fullscreen a video and it completely froze, no GPU recovery, seemed to have been tried after that.

image
image1446×692 209 KB

As you can see the input apparently was very slow.
image
image1269×340 272 KB

I also saw these lines :

kwin_wayland_drm: Pageflip timed out! This is a kernel bug

And have more logs on my phone as some were not written due to me hard shutting down the laptop as I had no ssh session running and keyboard was unresponsive, I will enable sysrq keys and hope I can reproduce it next time.

I tried to switch tty and it did work I saw a lot of drm errors (flip_done timed out and (CRTC:79:crtc-01/CONNECTOR:93eDP-1/PLANE:50:plane-3: commit wait timed_out) but the keyboard wasn’t working nor was an external USB one, it isn’t that it wasn’t working but basically the laptop was extremely slow, like if I type one key, 10 minutes later the letter appears.

Unplugging or replugging the USB-C dock did not change anything during the issue.

I’m very concerned about this issue cause reproducing it, I have no clue how to do that.

Tagging :

  • @Mario_Limonciello if you know if there is any firmware bump in the firmware provided in the next BIOS release please feel free to let us know, or if there is already a similar bug that has been reported upstream.
  • @Kieran_Levin : Please let us know any news on the BIOS release 3.0.7, I won’t be testing the Beta however.
  • @Matt_Hartley : Could Framework work more closely with AMD on squashing those very edge cases ? Is there something we as users could do to help better pin those issues (given that reproducibility is very hard) ?

Currently I have rebooted on 6.13.4 #1-NixOS SMP PREEMPT_DYNAMIC Fri Feb 21 13:11:21 UTC 2025 x86_64 GNU/Linux
Linux firmware : /nix/store/n58qg129fcnbp52gwblp2rg00p1v0z3x-linux-firmware-20250211-zstd

May be related to : NixOS AMD Framework 13th AMD Ryzen 7 7840U/64GB Framework DDR5 RAM/UMA settings gamer on kernels 6.11.X have random heavy lags related to AMDGPU or possibly firmware

Kind regards,
Lahfa Samy

2

Reproduced a less annoying issue (it did recover, and not freeze) :

  • This happened when I was on the tab : listenonrepeat.com (YouTube video embedded playing) with Firefox 135.01 with Kernel 6.13.4
  • Uptime doesn’t seem to matter.
  • KDE Plasma 6.2.5 (Wayland + XWayland)

image
image1326×651 152 KB

[11493.749110] amdgpu 0000:c1:00.0: amdgpu: Dumping IP State
[11493.751769] amdgpu 0000:c1:00.0: amdgpu: Dumping IP State Completed
[11493.761816] amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 timeout, signaled seq=2246503, emitted seq=2246505
[11493.761819] amdgpu 0000:c1:00.0: amdgpu: Process information: process .firefox-wrappe pid 3642 thread .firefox-w:cs0 pid 3730
[11493.761822] amdgpu 0000:c1:00.0: amdgpu: Starting gfx_0.0.0 ring reset
[11495.765672] amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=RESET
[11495.765679] [drm:amdgpu_mes_reset_legacy_queue [amdgpu]] *ERROR* failed to reset legacy queue
[11495.765852] amdgpu 0000:c1:00.0: amdgpu: Ring gfx_0.0.0 reset failure
[11495.765854] amdgpu 0000:c1:00.0: amdgpu: GPU reset begin!
[11495.766076] Bluetooth: hci0: ACL packet for unknown connection handle 3837
[11497.977385] amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
[11497.977401] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[11498.246347] [drm:gfx_v11_0_hw_fini [amdgpu]] *ERROR* failed to halt cp gfx
[11498.248326] amdgpu 0000:c1:00.0: amdgpu: MODE2 reset
[11498.285771] amdgpu 0000:c1:00.0: amdgpu: GPU reset succeeded, trying to resume
[11498.286476] [drm] PCIE GART of 512M enabled (table at 0x00000080FFD00000).
[11498.286560] amdgpu 0000:c1:00.0: amdgpu: SMU is resuming...
[11498.289240] amdgpu 0000:c1:00.0: amdgpu: SMU is resumed successfully!
[11498.296513] [drm] DMUB hardware initialized: version=0x08004B01
[11498.957456] amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[11498.957464] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[11498.957466] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[11498.957469] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
[11498.957470] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
[11498.957472] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
[11498.957473] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
[11498.957474] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
[11498.957476] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
[11498.957478] amdgpu 0000:c1:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
[11498.957480] amdgpu 0000:c1:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
[11498.957481] amdgpu 0000:c1:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
[11498.957483] amdgpu 0000:c1:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
[11498.959553] amdgpu 0000:c1:00.0: amdgpu: GPU reset(2) succeeded!
[11499.028123] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!

EDIT (02/03/2025) :

  • Added KDE Plasma version
  • Added observation of slow down in Firefox during sweeping (hover across multiples YouTubes tabs fast)
  • Not able to reproduce yet.

I believe the firefox preview of pinned YouTube tabs (sweeping the cursor) across multiples tabs very fast (this slows down the laptop quite a bit, as if it is struggling a lot to render frame per seconds but only for the Firefox window, but it doesn’t trigger the issue), I haven’t been able to reproduce it yet.

Without the preview sweeping across the tab does not cause slow down (the tab are highlighted and there is no slow down).

I noticed a slow down I can reproduce only happens in Firefox (playing a video or not), the other windows are refreshing properly.

I can’t reproduce on non-pinned tabs but I haven’t tried to unpin the YouTube tabs and attempt to reproduce the slow down, no message is shown in dmesg, I’ll try and launch Firefox from cmdline and see if there is anything, I have no clue also on how to investigate Firefox crash dumps but I have some.

I’ll have to check if I have the same behavior under Chromium based browser with YouTube tabs and the tab preview feature, hovering the cursor over multiples tabs sweeping across them.

EDIT (08/03/2025) :

Reproduced part of the issue but the gpu did recover (the screen flickered, went black during recovery) but I’m still on 6.13.4 with amdgpu.debugmask=0x10 :

[601581.219983] amdgpu 0000:c1:00.0: amdgpu: Dumping IP State
[601581.223062] amdgpu 0000:c1:00.0: amdgpu: Dumping IP State Completed
[601581.233116] amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 timeout, signaled seq=46796963, emitted seq=46796965
[601581.233122] amdgpu 0000:c1:00.0: amdgpu: Process information: process .firefox-wrappe pid 3642 thread .firefox-w:cs0 pid 3730
[601581.233125] amdgpu 0000:c1:00.0: amdgpu: Starting gfx_0.0.0 ring reset
[601583.236959] amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=RESET
[601583.236967] [drm:amdgpu_mes_reset_legacy_queue [amdgpu]] *ERROR* failed to reset legacy queue
[601583.237166] amdgpu 0000:c1:00.0: amdgpu: Ring gfx_0.0.0 reset failure
[601583.237169] amdgpu 0000:c1:00.0: amdgpu: GPU reset begin!
[601585.288389] amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
[601585.288411] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[601585.551134] [drm:gfx_v11_0_hw_fini [amdgpu]] *ERROR* failed to halt cp gfx
[601585.553124] amdgpu 0000:c1:00.0: amdgpu: MODE2 reset
[601585.591467] amdgpu 0000:c1:00.0: amdgpu: GPU reset succeeded, trying to resume
[601585.592291] [drm] PCIE GART of 512M enabled (table at 0x00000080FFD00000).
[601585.592364] amdgpu 0000:c1:00.0: amdgpu: SMU is resuming...
[601585.595072] amdgpu 0000:c1:00.0: amdgpu: SMU is resumed successfully!
[601585.601315] [drm] DMUB hardware initialized: version=0x08004B01
[601585.921724] amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[601585.921730] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[601585.921732] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[601585.921734] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
[601585.921735] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
[601585.921737] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
[601585.921738] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
[601585.921740] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
[601585.921741] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
[601585.921743] amdgpu 0000:c1:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
[601585.921744] amdgpu 0000:c1:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
[601585.921746] amdgpu 0000:c1:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
[601585.921748] amdgpu 0000:c1:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
[601585.923402] amdgpu 0000:c1:00.0: amdgpu: GPU reset(6) succeeded!
[601585.950777] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!

Once I reboot with amdgpu.debugmask=0x12, I’ll see if I can reproduce at some point.

Once BIOS release 3.07 is stable, I’ll also have to try and reproduce any issues with amdgpu.debugmask=0x12,amdgpu.debugmask=0x10 and without I guess.

3

Have you tried adding amdgpu.dcdebugmask=0x10 as a kernel parameter? I’ve needed this basically for every kernel since I think something in 6.10 or 6.11 to stop completely randomly occurring errors slowing the laptop input to a crawl until either reboot or force AMD GPU reset.

E: some bug reports that have been filed on the PSR thing:

1 Like
4

I’ve actually had more luck with amdgpu.dcdebugmask=0x12 (2+ weeks without the bug happening right now), if I recall correctly, I tried just 0x10 first and something was still broken.

PS. Just to demystify the number a little, it comes from this struct in the kernel code and is a hex sum. 0x12 disables memory stutter mode and PSR, 0x10 disables just PSR.

1 Like
5

I do have the kernel parameter, to be more precise here is my kernel cmdline : amdgpu.dcdebugmask=0x10 amd_pstate=active rtc_cmos.use_acpi_alarm=1 loglevel=4

And I did have it on kernel 6.13.1 when I triggered the issue.

I’ll try to reproduce the issue with amdgpu.dcdebugmask=0x12

6

Have you been able to reproduce the issue since?

PS. Looking over your kernel parameters, I think the rtc_cmos one is no longer necessary on newer kernels (I haven’t been using it for a while with no issues, but I can’t find a source for this right now).

1 Like
7

I haven’t rebooted with amdgpu.dcdebugmask=0x12 but will do so soon and and will comment if I reproduce any issues I’ve had.

I will also remove that rtos parameter.

1 Like
8

Hey @efindus

I was able to reproduce with amdgpu.dcdebugmask=0x12 the MES issue :

[1067406.235675] amdgpu 0000:c1:00.0: amdgpu: Dumping IP State
[1067406.238089] amdgpu 0000:c1:00.0: amdgpu: Dumping IP State Completed
[1067406.248202] amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 timeout, signaled seq=101872134, emitted seq=101872136
[1067406.248212] amdgpu 0000:c1:00.0: amdgpu: Process information: process .firefox-wrappe pid 3631 thread .firefox-w:cs0 pid 3957
[1067406.248216] amdgpu 0000:c1:00.0: amdgpu: Starting gfx_0.0.0 ring reset
[1067408.252057] amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=RESET
[1067408.252069] [drm:amdgpu_mes_reset_legacy_queue [amdgpu]] *ERROR* failed to reset legacy queue
[1067408.252527] amdgpu 0000:c1:00.0: amdgpu: Ring gfx_0.0.0 reset failure
[1067408.252532] amdgpu 0000:c1:00.0: amdgpu: GPU reset begin!
[1067410.475096] amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
[1067410.475109] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[1067410.681771] [drm:gfx_v11_0_hw_fini [amdgpu]] *ERROR* failed to halt cp gfx
[1067410.683674] amdgpu 0000:c1:00.0: amdgpu: MODE2 reset
[1067410.728232] amdgpu 0000:c1:00.0: amdgpu: GPU reset succeeded, trying to resume
[1067410.728618] [drm] PCIE GART of 512M enabled (table at 0x00000080FFD00000).
[1067410.728643] amdgpu 0000:c1:00.0: amdgpu: SMU is resuming...
[1067410.728936] amdgpu 0000:c1:00.0: amdgpu: SMU is resumed successfully!
[1067410.738243] [drm] DMUB hardware initialized: version=0x08004D00
[1067411.422627] amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[1067411.422639] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[1067411.422643] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[1067411.422646] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
[1067411.422649] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
[1067411.422652] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
[1067411.422655] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
[1067411.422658] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
[1067411.422661] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
[1067411.422664] amdgpu 0000:c1:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
[1067411.422667] amdgpu 0000:c1:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
[1067411.422670] amdgpu 0000:c1:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
[1067411.422673] amdgpu 0000:c1:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
[1067411.424948] amdgpu 0000:c1:00.0: amdgpu: GPU reset(2) succeeded!
[1067411.479232] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!
[1067615.641387] amdgpu 0000:c1:00.0: amdgpu: Dumping IP State
[1067615.644236] amdgpu 0000:c1:00.0: amdgpu: Dumping IP State Completed
[1067615.654262] amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 timeout, signaled seq=101973553, emitted seq=101973555
[1067615.654272] amdgpu 0000:c1:00.0: amdgpu: Process information: process .firefox-wrappe pid 3631 thread .firefox-w:cs0 pid 3957
[1067615.654278] amdgpu 0000:c1:00.0: amdgpu: Starting gfx_0.0.0 ring reset
[1067617.658116] amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=RESET
[1067617.658128] [drm:amdgpu_mes_reset_legacy_queue [amdgpu]] *ERROR* failed to reset legacy queue
[1067617.658621] amdgpu 0000:c1:00.0: amdgpu: Ring gfx_0.0.0 reset failure
[1067617.658626] amdgpu 0000:c1:00.0: amdgpu: GPU reset begin!
[1067619.888808] amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=REMOVE_QUEUE
[1067619.888820] [drm:amdgpu_mes_unmap_legacy_queue [amdgpu]] *ERROR* failed to unmap legacy queue
[1067620.098275] [drm:gfx_v11_0_hw_fini [amdgpu]] *ERROR* failed to halt cp gfx
[1067620.107770] amdgpu 0000:c1:00.0: amdgpu: MODE2 reset
[1067620.147468] amdgpu 0000:c1:00.0: amdgpu: GPU reset succeeded, trying to resume
[1067620.148613] [drm] PCIE GART of 512M enabled (table at 0x00000080FFD00000).
[1067620.148662] amdgpu 0000:c1:00.0: amdgpu: SMU is resuming...
[1067620.150481] amdgpu 0000:c1:00.0: amdgpu: SMU is resumed successfully!
[1067620.157176] [drm] DMUB hardware initialized: version=0x08004D00
[1067620.846328] amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[1067620.846339] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[1067620.846343] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[1067620.846346] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
[1067620.846349] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
[1067620.846352] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
[1067620.846354] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
[1067620.846357] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
[1067620.846360] amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
[1067620.846363] amdgpu 0000:c1:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
[1067620.846366] amdgpu 0000:c1:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
[1067620.846369] amdgpu 0000:c1:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
[1067620.846372] amdgpu 0000:c1:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
[1067620.848664] amdgpu 0000:c1:00.0: amdgpu: GPU reset(4) succeeded!
[1067620.900897] [drm:amdgpu_cs_ioctl [amdgpu]] *ERROR* Failed to initialize parser -125!

Additional information :

  • Firefox black screen or cursors leaves afterimages (after GPU reset recovers and then the afterimages of the cursor stops at some point/the window properly starts to render again)
  • /nix/store/70r77bb25qmfrjn7mwnzd4mzzp303ld7-mesa-24.2.8
  • /nix/store/ijaj1g829viydqk8lyajczak554h6zr0-linux-firmware-20250311-zstd
  • /nix/store/vwqkb8xx9vjg1jycp6k5732aw2ip9vbr-firefox-136.0.3
  • proc/cmdline: initrd=\EFI\nixos\d14nn2i3skrl1m1lksz8vjfka9cnz2lh-initrd-linux-6.13.7-initrd.efi init=/nix/store/6arhxi68iiy118rd4b4pflmbj4a45rgd-nixos-system-Hostname-24.11.715908.7105ae395770/init amdgpu.dcdebugmask=0x12 amd_pstate=active loglevel=4
  • Linux 6.13.7 #1-NixOS SMP PREEMPT_DYNAMIC Thu Mar 13 12:08:08 UTC 2025 x86_64 GNU/Linux

I’m just noting the Nix store path to see if they are rebuild (change in a dependency or a patch could be backported for instance) later.

9

That is very curious… I guess one more datapoint but it doesn’t solve your problem. I haven’t gotten one of these myself since setting the parameter. Right now I’m on 17 days of uptime so it shouldn’t be that either. The only meaningful difference I can spot between our setups is that I am currently on 25.0.1 of mesa.

My versions for the record:

  • linux-firmware-20250311.b69d4b74-2
  • mesa-1:25.0.1-2
  • firefox-developer-edition-137.0b5-1
  • kwin-6.3.3.1-1
  • Linux 6.13.6-arch1-1 #1 SMP PREEMPT_DYNAMIC Fri, 07 Mar 2025 20:19:00 +0000 x86_64 GNU/Linux

I’m also using Firefox Developer Edition but if anything that would be more unstable. Aside from Firefox video playback the other most consistent source of crashes for me has been playing Cyberpunk 2077 when my RAM wasn’t all basically free. I have since played with no issues for over 30h even when starting it when my ram usage was 24/32GB (I have additionally 16GB of swap).

10

I’ll bump to (most likely) mesa 25.0.3 the 31 May 2025, I’ll try to reproduce any of the issues but I think it’s most likely a mesa bug if you can’t reproduce it on your side.

I don’t think it’s something specific to Firefox.