My motherboard is MAXSON MS-MoDT 12450H ITX WIFI
When I pass through the onboard SATA controller of the motherboard, the virtual machine startup task log throws the error message:
"kvm: -device vfio-pci,host=0000:00:17.0,id=hostpci1,bus=ich9-pcie-port-2,addr=0x0: 0000:00:17.0 BAR 1: failed to create dma-buf: PCI BAR IOMMU mappings may fail: Invalid argument kvm: -device vfio-pci,host=0000:00:17.0,id=hostpci1,bus=ich9-pcie-port-2,addr=0x0: 0000:00:17.0 BAR 5: failed to create dma-buf: PCI BAR IOMMU mappings may fail: Invalid argument kvm: vfio: Cannot reset device 0000:00:17.0, no available reset mechanism. kvm: vfio: Cannot reset device 0000:00:17.0, no available reset mechanism."
I confirm that this SATA controller is isolated in its own separate IOMMU group.
The JMB585 SATA controller connected to the M.2 slot on my motherboard passes through normally without any errors.
Although error messages appear during startup, I can boot the virtual machine normally and access the hard drives connected to the onboard SATA controller without issues. However, the VM occasionally shuts down unexpectedly for unknown reasons, and I suspect this startup error may be the cause.When my virtual machine shuts down for unknown reasons, attempting to restart this VM may cause all virtual machines on the entire PVE node to stop functioning properly—both this problematic VM and other previously normally running VMs.
If there is no way to resolve this issue, I may have to consider not passing through the onboard SATA controller.
When I pass through the onboard SATA controller of the motherboard, the virtual machine startup task log throws the error message:
"kvm: -device vfio-pci,host=0000:00:17.0,id=hostpci1,bus=ich9-pcie-port-2,addr=0x0: 0000:00:17.0 BAR 1: failed to create dma-buf: PCI BAR IOMMU mappings may fail: Invalid argument kvm: -device vfio-pci,host=0000:00:17.0,id=hostpci1,bus=ich9-pcie-port-2,addr=0x0: 0000:00:17.0 BAR 5: failed to create dma-buf: PCI BAR IOMMU mappings may fail: Invalid argument kvm: vfio: Cannot reset device 0000:00:17.0, no available reset mechanism. kvm: vfio: Cannot reset device 0000:00:17.0, no available reset mechanism."
I confirm that this SATA controller is isolated in its own separate IOMMU group.
The JMB585 SATA controller connected to the M.2 slot on my motherboard passes through normally without any errors.
Although error messages appear during startup, I can boot the virtual machine normally and access the hard drives connected to the onboard SATA controller without issues. However, the VM occasionally shuts down unexpectedly for unknown reasons, and I suspect this startup error may be the cause.When my virtual machine shuts down for unknown reasons, attempting to restart this VM may cause all virtual machines on the entire PVE node to stop functioning properly—both this problematic VM and other previously normally running VMs.
If there is no way to resolve this issue, I may have to consider not passing through the onboard SATA controller.