Re: crash during resume of PCIe bridge in v5.17 (v5.16 works)

[Bert Karwatzki]

There are exitining news here:
I tested older linux versions with this script

#!/bin/bash
for i in {0..20000}
do
	echo $i
	evolution &
	sleep 5
	killall evolution
	sleep 5
done

with the following results:
Version v5.17, v6.1 and v6.8 show more or less the same
behaviour as v6.12+, i.e. repreated resumes crash after a 
while (sometimes the discrete GPU is lost without a crash)

Version v5.15 shows a different behaviour:
5.15.0-stable-dirty			booted 14:28, 16.1.2026 error 14:52 (25min, 142 resumes)
[ 1453.515962] [  T18093] amdgpu 0000:03:00.0: amdgpu: Failed to setup smc hw!
[ 1453.515978] [  T18093] [drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block <smu> failed -62
[ 1453.516046] [  T18093] amdgpu 0000:03:00.0: amdgpu: amdgpu_device_ip_resume failed (-62). (-ETIME!)
5.15.0-stable-dirty			booted 17:09, 16.1.2026 error 20:18 (3h, 1102 resumes)
[11337.547257] [ T157373] amdgpu 0000:03:00.0: amdgpu: Failed to setup smc hw!
[11337.547273] [ T157373] [drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block <smu> failed -62
[11337.547358] [ T157373] amdgpu 0000:03:00.0: amdgpu: amdgpu_device_ip_resume failed (-62).
5.15.0-stable-dirty			booted 20:51, 16.1.2026 error 21:20 (30min, 164 resumes)
[ 1698.065653] [  T22129] amdgpu 0000:03:00.0: amdgpu: Failed to setup smc hw!
[ 1698.065665] [  T22129] [drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block <smu> failed -62
[ 1698.065734] [  T22129] amdgpu 0000:03:00.0: amdgpu: amdgpu_device_ip_resume failed (-62).
5.15.0-stable-dirty			booted 21:25, 16.1.2026 error 21:41 (10min, 91 resumes)
[  965.908197] [   T3843] amdgpu 0000:03:00.0: amdgpu: Failed to setup smc hw!
[  965.908212] [   T3843] [drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block <smu> failed -62
[  965.908284] [   T3843] amdgpu 0000:03:00.0: amdgpu: amdgpu_device_ip_resume failed (-62).
5.15.0-stable-dirty			booted 21:46, 16.1.2026 error 1:43 17.1.2026 (4h, 1411 resumes)
[14220.044577] [ T203585] amdgpu 0000:03:00.0: amdgpu: Failed to setup smc hw!
[14220.044593] [ T203585] [drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block <smu> failed -62
[14220.044662] [ T203585] amdgpu 0000:03:00.0: amdgpu: amdgpu_device_ip_resume failed (-62).

In all 5 tests the resume failed, but with an error message not seen before, also no crash occured.

And most importantly v5.16 did not crash at all, and also did not show any GPU suspend/resume related error
despite being tested for 36h and 11644 resumes:
Testing (dirty because of -Wno-error=use-after-free and -Wno-error=format-truncation compile fix)
5.16.0-stable-dirty			booted 2:09, 17.1.2026 14:20, 18.1.2026 no error (neither crash or loss of device)
					(36h, 11644 resumes)

So the whole issue seems to be a pure software issue after all (not just an issue related to
probably broken hardware). I'm currently bisecting this between v5.16 and v5.17, but getting a
result can take 2 weeks given the length of the testruns.

The first step of the bisection is already finished and GOOD:
Testing (dirty because of -Wno-error=use-after-free and -Wno-error=format-truncation compile fix)
5.16.0-bisect-07203-g22ef12195e13-dirty booted 14:27, 18.1.2026 no error 1:57 (35.5h, 12508 resumes)

Bert Karwatzki