Bug 2449155

Summary: Request backport: amdgpu: rework how we handle TLB fences (Fixes MES deadlocks on Strix Point)
Product: [Fedora] Fedora Reporter: Kingsley Bawuah <paralysis_roaming858>
Component: kernelAssignee: Justin M. Forbes <jforbes>
Status: CLOSED ERRATA QA Contact: Fedora Extras Quality Assurance <extras-qa>
Severity: urgent Docs Contact:
Priority: unspecified    
Version: 43CC: acaringi, adscvr, airlied, hans, hpa, jforbes, kernel-maint, lakhsa, linville, masami256, mchehab, nickolasjcarr, ptalbert, steved, suraj.ghimire7
Target Milestone: ---Keywords: Regression, Triaged
Target Release: ---   
Hardware: x86_64   
OS: Linux   
URL: https://community.frame.work/t/amd-gpu-mes-timeouts-causing-system-hangs-on-framework-laptop-13-amd-ai-300-series/71364/87
Whiteboard:
Fixed In Version: kernel-6.19.10-300.fc44 kernel-6.19.10-200.fc43 kernel-6.19.10-100.fc42 Doc Type: ---
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2026-03-31 00:17:37 UTC Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Attachments:
Description Flags
The output of journalctl -b -1 -k > dmesg.txt none

Description Kingsley Bawuah 2026-03-19 18:37:48 UTC 
1. Please describe the problem:

Hard system lockup on Framework 13 (AMD Ryzen AI 300 series / Strix Point). The mouse cursor remains moveable (hardware plane), but the UI is frozen and does not process input. Logs confirm a Micro-Engine Scheduler (MES) deadlock.

Technical Root Cause: Race condition in command submission and unnecessary TLB fence attachments on GFX1150 IP blocks.
Upstream Fix: [PATCH] drm/amdgpu: rework how we handle TLB fences (Commit: 69c5fbd2ce33614918e77c865f3f04494192780e)
Upstream Tracker: https://gitlab.freedesktop.org/drm/amd/-/issues/4749
2. What is the Version-Release number of the kernel:

6.19.8-200.fc43.x86_64
3. Did it work previously in Fedora?

No. This appears to be a day-one stability issue for the Ryzen AI 300 series (Strix Point) on the 6.19 kernel series.
4. Can you reproduce this issue?

Yes. It occurs randomly during standard desktop usage (GNOME Wayland), often triggered by hardware-accelerated tasks or waking from sleep.
Steps: Use the system normally with multiple windows open; the UI eventually stops responding while the mouse continues to track.
5. Does this problem occur with the latest Rawhide kernel?

Unknown / Not tested to avoid further system instability. (Note: Mario Limonciello noted the fix is heading into the 7.0-rc pull request this week, so Rawhide likely doesn't have it yet unless explicitly patched).
6. Are you running any modules that not shipped with directly Fedora's kernel?:

No.
7. Please attach the kernel logs.

Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: SMU is resuming...
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: SMU is resumed successfully!
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: [drm] Applying panel backlight quirk, min_brightness: 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring jpeg_dec_0 uses VM inv eng 1 on hub 8
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
Mar 19 13:04:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: ring vpe uses VM inv eng 4 on hub 8
Mar 19 13:11:03 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:03 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:06 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:06 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:09 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:09 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:12 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:12 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:15 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:15 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:18 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:21 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:21 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:24 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:24 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:27 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:27 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:28 framework kernel: amdgpu 0000:c1:00.0: amdgpu: VM memory stats for proc epiphany(5177) task epiphany(5177) is non-zero when fini
Mar 19 13:11:29 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:29 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:32 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:32 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:35 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:35 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:37 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:37 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:40 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:40 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:45 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES failed to respond to msg=MISC (WAIT_REG_MEM)
Mar 19 13:11:45 framework kernel: amdgpu 0000:c1:00.0: amdgpu: failed to reg_write_reg_wait
Mar 19 13:11:45 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES ring buffer is full.
Mar 19 13:11:48 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES ring buffer is full.
Mar 19 13:11:50 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES ring buffer is full.
Mar 19 13:11:53 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES ring buffer is full.
Mar 19 13:11:55 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES ring buffer is full.
Mar 19 13:11:58 framework kernel: amdgpu 0000:c1:00.0: amdgpu: MES ring buffer is full.

Reproducible: Always
Comment 1 Kingsley Bawuah 2026-03-19 18:59:09 UTC 
Created attachment 2134168 [details]
The output of journalctl -b -1 -k > dmesg.txt

This was retrieved after restarting my device
Comment 2 Fedora Update System 2026-03-26 01:53:22 UTC 
FEDORA-2026-d4572d6000 (kernel-6.19.10-200.fc43) has been submitted as an update to Fedora 43.
https://bodhi.fedoraproject.org/updates/FEDORA-2026-d4572d6000
Comment 3 Fedora Update System 2026-03-26 01:53:32 UTC 
FEDORA-2026-e976c4f5fa (kernel-6.19.10-300.fc44) has been submitted as an update to Fedora 44.
https://bodhi.fedoraproject.org/updates/FEDORA-2026-e976c4f5fa
Comment 4 Fedora Update System 2026-03-26 01:53:42 UTC 
FEDORA-2026-d85f7a71f0 (kernel-6.19.10-100.fc42) has been submitted as an update to Fedora 42.
https://bodhi.fedoraproject.org/updates/FEDORA-2026-d85f7a71f0
Comment 5 Fedora Update System 2026-03-27 01:40:03 UTC 
FEDORA-2026-e976c4f5fa has been pushed to the Fedora 44 testing repository.
Soon you'll be able to install the update with the following command:
`sudo dnf upgrade --enablerepo=updates-testing --refresh --advisory=FEDORA-2026-e976c4f5fa`
You can provide feedback for this update here: https://bodhi.fedoraproject.org/updates/FEDORA-2026-e976c4f5fa

See also https://fedoraproject.org/wiki/QA:Updates_Testing for more information on how to test updates.
Comment 6 Fedora Update System 2026-03-27 01:52:07 UTC 
FEDORA-2026-d4572d6000 has been pushed to the Fedora 43 testing repository.
Soon you'll be able to install the update with the following command:
`sudo dnf upgrade --enablerepo=updates-testing --refresh --advisory=FEDORA-2026-d4572d6000`
You can provide feedback for this update here: https://bodhi.fedoraproject.org/updates/FEDORA-2026-d4572d6000

See also https://fedoraproject.org/wiki/QA:Updates_Testing for more information on how to test updates.
Comment 7 Fedora Update System 2026-03-27 02:12:24 UTC 
FEDORA-2026-d85f7a71f0 has been pushed to the Fedora 42 testing repository.
Soon you'll be able to install the update with the following command:
`sudo dnf upgrade --enablerepo=updates-testing --refresh --advisory=FEDORA-2026-d85f7a71f0`
You can provide feedback for this update here: https://bodhi.fedoraproject.org/updates/FEDORA-2026-d85f7a71f0

See also https://fedoraproject.org/wiki/QA:Updates_Testing for more information on how to test updates.
Comment 8 Fedora Update System 2026-03-31 00:17:37 UTC 
FEDORA-2026-e976c4f5fa (kernel-6.19.10-300.fc44) has been pushed to the Fedora 44 stable repository.
If problem still persists, please make note of it in this bug report.
Comment 9 Fedora Update System 2026-03-31 00:54:13 UTC 
FEDORA-2026-d4572d6000 (kernel-6.19.10-200.fc43) has been pushed to the Fedora 43 stable repository.
If problem still persists, please make note of it in this bug report.
Comment 10 Fedora Update System 2026-03-31 01:09:12 UTC 
FEDORA-2026-d85f7a71f0 (kernel-6.19.10-100.fc42) has been pushed to the Fedora 42 stable repository.
If problem still persists, please make note of it in this bug report.