[SOLVED] In Proxmox VE 8.1.4 intel i226-v PCI passthrough VM cannot start. Attempted to add pcie_port_pm=off to Grub

[For_Pugss]

I followed some tutorials to set up passthrough for the network card and added the "pcie_port_pm=off" parameter in Grub, but still cannot start the VM.

GRUB_CMDLINE_LINUX_DEFAULT="quiet intel_iommu=on iommu=pt pcie_port_pm=off"

View through dmesg

[   29.317702] igc 0000:08:00.0 enp8s0: NIC Link is Up 1000 Mbps Full Duplex, Flow Control: RX/TX
[   29.318067] vmbr0: port 1(enp8s0) entered blocking state
[   29.318089] vmbr0: port 1(enp8s0) entered forwarding state
[   34.560328] bpfilter: Loaded bpfilter_umh pid 907
[   34.561859] Started bpfilter
[   44.857354] kvm[941]: memfd_create() called without MFD_EXEC or MFD_NOEXEC_SEAL set
[   66.021868] igc 0000:05:00.0 enp5s0: PHC removed
[   66.266695] vfio-pci 0000:05:00.0: Unable to change power state from D3hot to D0, device inaccessible
[   66.329059] vfio-pci 0000:05:00.0: Unable to change power state from D3cold to D0, device inaccessible
[   67.057435] vfio-pci 0000:05:00.0: timed out waiting for pending transaction; performing function level reset anyway
[   68.305406] pcieport 0000:00:1c.6: broken device, retraining non-functional downstream link at 2.5GT/s
[   69.305362] pcieport 0000:00:1c.6: retraining failed
[   69.305367] vfio-pci 0000:05:00.0: not ready 1023ms after FLR; waiting
[   70.353354] vfio-pci 0000:05:00.0: not ready 2047ms after FLR; waiting
[   72.657281] vfio-pci 0000:05:00.0: not ready 4095ms after FLR; waiting
[   77.009139] vfio-pci 0000:05:00.0: not ready 8191ms after FLR; waiting
[   85.456817] vfio-pci 0000:05:00.0: not ready 16383ms after FLR; waiting
[  103.888203] vfio-pci 0000:05:00.0: not ready 32767ms after FLR; waiting
[  138.702975] vfio-pci 0000:05:00.0: not ready 65535ms after FLR; giving up
[  139.742958] pcieport 0000:00:1c.6: broken device, retraining non-functional downstream link at 2.5GT/s
[  140.742906] pcieport 0000:00:1c.6: retraining failed
[  141.998878] pcieport 0000:00:1c.6: broken device, retraining non-functional downstream link at 2.5GT/s
[  143.006832] pcieport 0000:00:1c.6: retraining failed
[  143.006837] vfio-pci 0000:05:00.0: not ready 1023ms after bus reset; waiting
[  144.046788] vfio-pci 0000:05:00.0: not ready 2047ms after bus reset; waiting
[  146.126724] vfio-pci 0000:05:00.0: not ready 4095ms after bus reset; waiting
[  150.478595] vfio-pci 0000:05:00.0: not ready 8191ms after bus reset; waiting
[  158.926273] vfio-pci 0000:05:00.0: not ready 16383ms after bus reset; waiting
[  175.568540] vfio-pci 0000:05:00.0: not ready 32767ms after bus reset; waiting
[  210.383390] vfio-pci 0000:05:00.0: not ready 65535ms after bus reset; giving up
[  210.387140] vfio-pci 0000:05:00.0: Unable to change power state from D3cold to D0, device inaccessible
[  211.979150] tap100i0: entered promiscuous mode
[  212.016258] vmbr0: port 2(fwpr100p0) entered blocking state
[  212.016263] vmbr0: port 2(fwpr100p0) entered disabled state
[  212.016283] fwpr100p0: entered allmulticast mode
[  212.016349] fwpr100p0: entered promiscuous mode
[  212.016404] vmbr0: port 2(fwpr100p0) entered blocking state
[  212.016406] vmbr0: port 2(fwpr100p0) entered forwarding state
[  212.023614] fwbr100i0: port 1(fwln100i0) entered blocking state
[  212.023620] fwbr100i0: port 1(fwln100i0) entered disabled state
[  212.023638] fwln100i0: entered allmulticast mode
[  212.023675] fwln100i0: entered promiscuous mode
[  212.023707] fwbr100i0: port 1(fwln100i0) entered blocking state
[  212.023709] fwbr100i0: port 1(fwln100i0) entered forwarding state
[  212.030461] fwbr100i0: port 2(tap100i0) entered blocking state
[  212.030466] fwbr100i0: port 2(tap100i0) entered disabled state
[  212.030485] tap100i0: entered allmulticast mode
[  212.030542] fwbr100i0: port 2(tap100i0) entered blocking state
[  212.030545] fwbr100i0: port 2(tap100i0) entered forwarding state
[  212.713863] vfio-pci 0000:05:00.0: Unable to change power state from D3cold to D0, device inaccessible
[  212.713959] vfio-pci 0000:05:00.0: Unable to change power state from D3cold to D0, device inaccessible
[  212.714134] vfio-pci 0000:05:00.0: Unable to change power state from D3cold to D0, device inaccessible
[  213.455291] vfio-pci 0000:05:00.0: timed out waiting for pending transaction; performing function level reset anyway

 

[Graxo]

Hello,

Did you manage to find a solution for this?
Im having the same issues.

Kind regrads,
Graxo

 

[Taomyn]

The thread says solved but I see no solution - I'm having the same issue since upgrading my BIOS for the PKFail fix. The NICs all function as standard ports in Promox, but if I try to pass any of them through to a VM I get:

Sep 09 18:46:54 ned pvedaemon[1186]: <root@pam> starting task UPID:ned:00000681:000023F2:66DF267E:qmstart:100:root@pam:
Sep 09 18:46:54 ned kernel: VFIO - User Level meta-driver version: 0.3
Sep 09 18:46:55 ned kernel: igc 0000:01:00.0 enp1s0: PHC removed
Sep 09 18:46:55 ned kernel: igc 0000:03:00.0 enp3s0: PHC removed
Sep 09 18:46:55 ned kernel: igc 0000:04:00.0 enp4s0: PHC removed
Sep 09 18:46:57 ned kernel: pcieport 0000:00:1c.6: broken device, retraining non-functional downstream link at 2.5GT/s
Sep 09 18:46:58 ned kernel: pcieport 0000:00:1c.6: retraining failed
Sep 09 18:46:59 ned kernel: pcieport 0000:00:1c.6: broken device, retraining non-functional downstream link at 2.5GT/s
Sep 09 18:47:00 ned kernel: pcieport 0000:00:1c.6: retraining failed
Sep 09 18:47:00 ned kernel: vfio-pci 0000:04:00.0: not ready 1023ms after resume; waiting
Sep 09 18:47:01 ned kernel: vfio-pci 0000:04:00.0: not ready 2047ms after resume; waiting
Sep 09 18:47:03 ned kernel: vfio-pci 0000:04:00.0: not ready 4095ms after resume; waiting
Sep 09 18:47:07 ned kernel: vfio-pci 0000:04:00.0: not ready 8191ms after resume; waiting
Sep 09 18:47:16 ned kernel: vfio-pci 0000:04:00.0: not ready 16383ms after resume; waiting

Proxmox v8.2.4 (6.8.12-1-pve)

 

[amartin90]

The thread says solved but I see no solution - I'm having the same issue since upgrading my BIOS for the PKFail fix. The NICs all function as standard ports in Promox, but if I try to pass any of them through to a VM I get:

Sep 09 18:46:54 ned pvedaemon[1186]: <root@pam> starting task UPID:ned:00000681:000023F2:66DF267E:qmstart:100:root@pam:
Sep 09 18:46:54 ned kernel: VFIO - User Level meta-driver version: 0.3
Sep 09 18:46:55 ned kernel: igc 0000:01:00.0 enp1s0: PHC removed
Sep 09 18:46:55 ned kernel: igc 0000:03:00.0 enp3s0: PHC removed
Sep 09 18:46:55 ned kernel: igc 0000:04:00.0 enp4s0: PHC removed
Sep 09 18:46:57 ned kernel: pcieport 0000:00:1c.6: broken device, retraining non-functional downstream link at 2.5GT/s
Sep 09 18:46:58 ned kernel: pcieport 0000:00:1c.6: retraining failed
Sep 09 18:46:59 ned kernel: pcieport 0000:00:1c.6: broken device, retraining non-functional downstream link at 2.5GT/s
Sep 09 18:47:00 ned kernel: pcieport 0000:00:1c.6: retraining failed
Sep 09 18:47:00 ned kernel: vfio-pci 0000:04:00.0: not ready 1023ms after resume; waiting
Sep 09 18:47:01 ned kernel: vfio-pci 0000:04:00.0: not ready 2047ms after resume; waiting
Sep 09 18:47:03 ned kernel: vfio-pci 0000:04:00.0: not ready 4095ms after resume; waiting
Sep 09 18:47:07 ned kernel: vfio-pci 0000:04:00.0: not ready 8191ms after resume; waiting
Sep 09 18:47:16 ned kernel: vfio-pci 0000:04:00.0: not ready 16383ms after resume; waiting

Proxmox v8.2.4 (6.8.12-1-pve)

Did you manage to solve?

 

[Taomyn]

Did you manage to solve?

No not yet - I have not found the time to retry it since it's my Internet connection which makes it more difficult to test things. I'm caught between trying to get it working again or just leaving it without pass-through as it's working pretty well.