AMD-Vi: Completion-Wait loop timed out

May 31, 2018

Something to do with the GPU passthrough. Probably need to downgrade the kernel.

[18195.106858] pcieport 0000:00:03.1: PCIe Bus Error: severity=Uncorrected (Non-Fatal), type=Transaction Layer, id=0019(Receiver ID)
[18195.106861] pcieport 0000:00:03.1:   device [1022:1453] error status/mask=00200000/04400000
[18195.106863] pcieport 0000:00:03.1:    [21] ACS Violation          (First)
[18195.106866] pcieport 0000:00:03.1: broadcast error_detected message
[18195.552816] pcieport 0000:00:03.1: broadcast mmio_enabled message
[18195.552819] pcieport 0000:00:03.1: broadcast resume message
[18195.552821] pcieport 0000:00:03.1: AER: Device recovery successful
[18195.682608] AMD-Vi: Completion-Wait loop timed out
[18195.812147] AMD-Vi: Completion-Wait loop timed out
[18195.941794] AMD-Vi: Completion-Wait loop timed out
[18196.071513] AMD-Vi: Completion-Wait loop timed out
[18196.105323] AMD-Vi: Event logged [
[18196.105325] IOTLB_INV_TIMEOUT device=22:00.0 address=0x000000043e979780]

22 is the video card I think. A more appropriate title would be “IOTLB_INV_TIMEOUT”.

There were some warnings when compiling the kernel I’m using. Possibly related to the patches Manjaro uses.

Downgraded the kernel, got to reboot now.