PCIe passed through to Docker giving multiple errors

[BurningSky]

I have a mPCIe Coral TPU connected to a PCIe to mPCIe adaptor which is then passed through to Frigate Docker which seems to be working but today I got a notification that my syslog is filling up and I've had a look and see this error relating to the Coral device but I don't know what could be causing this error? The Docker container is running in priviledged mode and passed through via /dev/apex_0

 

Nov  5 08:46:19 Ragon kernel: pcieport 0000:00:01.3: AER: Multiple Corrected error received: 0000:25:00.0
Nov  5 08:46:19 Ragon kernel: apex 0000:25:00.0: PCIe Bus Error: severity=Corrected, type=Physical Layer, (Receiver ID)
Nov  5 08:46:19 Ragon kernel: apex 0000:25:00.0:   device [1ac1:089a] error status/mask=00000041/00006000
Nov  5 08:46:19 Ragon kernel: apex 0000:25:00.0:    [ 0] RxErr                 
Nov  5 08:46:19 Ragon kernel: apex 0000:25:00.0:    [ 6] BadTLP    

 

ragon-diagnostics-20231105-0852.zip

[BurningSky]

After doing some digging I've added pcie_aspm=off to my syslinux config so I will see if that resolves the issue.