Warning: UPDATING these packages broke my pci passthrough.

I have to second this observation.
In my case it is a RTX 4060 Ti which should be passed through to a Linux VM.
It also currently refuses to start
Code: 
root@pve-win11:~# pveversion -v
proxmox-ve: 8.3.0 (running kernel: 6.8.12-1-pve)
pve-manager: 8.3.2 (running version: 8.3.2/3e76eec21c4a14a7)
proxmox-kernel-helper: 8.1.0
proxmox-kernel-6.8: 6.8.12-5
proxmox-kernel-6.8.12-5-pve-signed: 6.8.12-5
proxmox-kernel-6.8.12-4-pve-signed: 6.8.12-4
proxmox-kernel-6.8.12-1-pve-signed: 6.8.12-1
proxmox-kernel-6.5.13-6-pve-signed: 6.5.13-6
proxmox-kernel-6.5: 6.5.13-6
proxmox-kernel-6.5.11-8-pve-signed: 6.5.11-8
amd64-microcode: 3.20240820.1~deb12u1
ceph: 18.2.4-pve3
ceph-fuse: 18.2.4-pve3
corosync: 3.1.7-pve3
criu: 3.17.1-2+deb12u1
glusterfs-client: 10.3-5
ifupdown2: 3.2.0-1+pmx11
ksm-control-daemon: 1.5-1
libjs-extjs: 7.0.0-5
libknet1: 1.28-pve1
libproxmox-acme-perl: 1.5.1
libproxmox-backup-qemu0: 1.4.1
libproxmox-rs-perl: 0.3.4
libpve-access-control: 8.2.0
libpve-apiclient-perl: 3.3.2
libpve-cluster-api-perl: 8.0.10
libpve-cluster-perl: 8.0.10
libpve-common-perl: 8.2.9
libpve-guest-common-perl: 5.1.6
libpve-http-server-perl: 5.1.2
libpve-network-perl: 0.10.0
libpve-rs-perl: 0.9.1
libpve-storage-perl: 8.3.3
libspice-server1: 0.15.1-1
lvm2: 2.03.16-2
lxc-pve: 6.0.0-1
lxcfs: 6.0.0-pve2
novnc-pve: 1.5.0-1
proxmox-backup-client: 3.3.2-1
proxmox-backup-file-restore: 3.3.2-2
proxmox-firewall: 0.6.0
proxmox-kernel-helper: 8.1.0
proxmox-mail-forward: 0.3.1
proxmox-mini-journalreader: 1.4.0
proxmox-offline-mirror-helper: 0.6.7
proxmox-widget-toolkit: 4.3.3
pve-cluster: 8.0.10
pve-container: 5.2.3
pve-docs: 8.3.1
pve-edk2-firmware: 4.2023.08-4
pve-esxi-import-tools: 0.7.2
pve-firewall: 5.1.0
pve-firmware: 3.14-2
pve-ha-manager: 4.0.6
pve-i18n: 3.3.2
pve-qemu-kvm: 9.0.2-4
pve-xtermjs: 5.3.0-3
qemu-server: 8.3.3
smartmontools: 7.3-pve1
spiceterm: 3.3.0
swtpm: 0.8.0+pve1
vncterm: 1.8.0
zfsutils-linux: 2.2.6-pve1

Code: 
root@pve-win11:~# qm showcmd 110
/usr/bin/kvm -id 110 -name 'ollama,debug-threads=on' -no-shutdown -chardev 'socket,id=qmp,path=/var/run/qemu-server/110.qmp,server=on,wait=off' -mon 'chardev=qmp,mode=control' -chardev 'socket,id=qmp-event,path=/var/run/qmeventd.sock,reconnect=5' -mon 'chardev=qmp-event,mode=control' -pidfile /var/run/qemu-server/110.pid -daemonize -smbios 'type=1,uuid=32225e3d-397e-475d-b7a7-6ce4308df946' -drive 'if=pflash,unit=0,format=raw,readonly=on,file=/usr/share/pve-edk2-firmware//OVMF_CODE_4M.secboot.fd' -drive 'if=pflash,unit=1,id=drive-efidisk0,format=raw,file=/dev/zvol/rpool/data/vm-110-disk-1,size=540672' -smp '4,sockets=1,cores=4,maxcpus=4' -nodefaults -boot 'menu=on,strict=on,reboot-timeout=1000,splash=/usr/share/qemu-server/bootsplash.jpg' -vnc 'unix:/var/run/qemu-server/110.vnc,password=on' -cpu qemu64,+abm,+aes,+avx,+avx2,+avx512bw,+avx512cd,+avx512dq,+avx512f,+avx512vl,+bmi1,+bmi2,enforce,+f16c,+fma,+kvm_pv_eoi,+kvm_pv_unhalt,+movbe,+pni,+popcnt,+sse4.1,+sse4.2,+ssse3,+xsave -m 16382 -object 'iothread,id=iothread-virtioscsi0' -readconfig /usr/share/qemu-server/pve-q35-4.0.cfg -device 'vmgenid,guid=355d72bb-8c8b-4ba0-9749-701600ecbb7a' -device 'usb-tablet,id=tablet,bus=ehci.0,port=1' -device 'vfio-pci,host=0000:01:00.0,id=hostpci0.0,bus=ich9-pcie-port-1,addr=0x0.0,multifunction=on' -device 'vfio-pci,host=0000:01:00.1,id=hostpci0.1,bus=ich9-pcie-port-1,addr=0x0.1' -device 'VGA,id=vga,bus=pcie.0,addr=0x1' -chardev 'socket,path=/var/run/qemu-server/110.qga,server=on,wait=off,id=qga0' -device 'virtio-serial,id=qga0,bus=pci.0,addr=0x8' -device 'virtserialport,chardev=qga0,name=org.qemu.guest_agent.0' -iscsi 'initiator-name=iqn.1993-08.org.debian:01:2bf63bb7ad9' -drive 'if=none,id=drive-ide2,media=cdrom,aio=io_uring' -device 'ide-cd,bus=ide.1,unit=0,drive=drive-ide2,id=ide2,bootindex=101' -device 'virtio-scsi-pci,id=virtioscsi0,bus=pci.3,addr=0x1,iothread=iothread-virtioscsi0' -drive 'file=/dev/zvol/rpool/data/vm-110-disk-0,if=none,id=drive-scsi0,discard=on,format=raw,cache=none,aio=io_uring,detect-zeroes=unmap' -device 'scsi-hd,bus=virtioscsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0,id=scsi0,bootindex=100' -netdev 'type=tap,id=net0,ifname=tap110i0,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=BC:24:11:EC:31:38,netdev=net0,bus=pci.0,addr=0x12,id=net0,rx_queue_size=1024,tx_queue_size=256,bootindex=102' -machine 'type=q35+pve0'

Start error message
Code: 
error writing '1' to '/sys/bus/pci/devices/0000:01:00.0/reset': Inappropriate ioctl for device
failed to reset PCI device '0000:01:00.0', but trying to continue as not all devices need a reset
kvm: ../hw/pci/pci.c:1633: pci_irq_handler: Assertion `0 <= irq_num && irq_num < PCI_NUM_PINS' failed.
TASK ERROR: start failed: QEMU exited with code 1

journalctl
Code: 
Jan 15 16:06:28 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 16:06:28 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 16:06:28 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 16:06:28 pve-win11 kernel: vfio-pci 0000:01:00.1: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 16:06:28 pve-win11 kernel: vfio-pci 0000:01:00.1: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 16:06:28 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible

Jan 15 15:58:11 pve-win11 pvestatd[1639]: VM 110 qmp command failed - VM 110 not running
Jan 15 15:58:47 pve-win11 systemd-logind[1181]: New session 4621 of user root.
Jan 15 15:58:11 pve-win11 pvedaemon[2669381]: <root@pam> end task UPID:pve-win11:002F7714:52E3B19F:6787CC72:qmstart:110:root@pam: start failed: QEMU exited with code 1
Jan 15 15:58:47 pve-win11 systemd[1]: Starting user-runtime-dir@0.service - User Runtime Directory /run/user/0...
Jan 15 15:58:11 pve-win11 pvedaemon[3110676]: start failed: QEMU exited with code 1
Jan 15 15:58:47 pve-win11 systemd[1]: Created slice user-0.slice - User Slice of UID 0.
Jan 15 15:58:10 pve-win11 pvedaemon[3107237]: VM 110 qmp command failed - VM 110 not running
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.1: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 65535ms after bus reset; giving up
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 32767ms after bus reset; waiting
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 16383ms after bus reset; waiting
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 8191ms after bus reset; waiting
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 4095ms after bus reset; waiting
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 2047ms after bus reset; waiting
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 1023ms after bus reset; waiting
Jan 15 15:59:24 pve-win11 kernel: pcieport 0000:00:01.1: retraining failed
Jan 15 15:59:24 pve-win11 kernel: pcieport 0000:00:01.1: broken device, retraining non-functional downstream link at 2.5GT/s
Jan 15 15:59:24 pve-win11 kernel: pcieport 0000:00:01.1: retraining failed
Jan 15 15:59:24 pve-win11 kernel: pcieport 0000:00:01.1: broken device, retraining non-functional downstream link at 2.5GT/s
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.1: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:59:24 pve-win11 kernel: fwbr110i0: port 2(tap110i0) entered disabled state
Jan 15 15:59:24 pve-win11 kernel: tap110i0 (unregistering): left allmulticast mode
Jan 15 15:59:24 pve-win11 kernel: fwbr110i0: port 2(tap110i0) entered disabled state
Jan 15 15:59:24 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.1: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible


Jan 15 15:57:06 pve-win11 pvestatd[1639]: VM 110 qmp command failed - VM 110 qmp command 'query-proxmox-support' failed - got timeout
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 65535ms after FLR; giving up
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 32767ms after FLR; waiting
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 16383ms after FLR; waiting
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 8191ms after FLR; waiting
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 4095ms after FLR; waiting
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 2047ms after FLR; waiting
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 1023ms after FLR; waiting
Jan 15 15:58:10 pve-win11 kernel: pcieport 0000:00:01.1: retraining failed
Jan 15 15:58:10 pve-win11 kernel: pcieport 0000:00:01.1: broken device, retraining non-functional downstream link at 2.5GT/s
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: timed out waiting for pending transaction; performing function level reset anyway
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:58:10 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:57:00 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:56:57 pve-win11 kernel: fwbr110i0: port 2(tap110i0) entered forwarding state
Jan 15 15:56:57 pve-win11 kernel: fwbr110i0: port 2(tap110i0) entered blocking state
Jan 15 15:56:57 pve-win11 kernel: tap110i0: entered allmulticast mode
Jan 15 15:56:57 pve-win11 kernel: fwbr110i0: port 2(tap110i0) entered disabled state
Jan 15 15:56:57 pve-win11 kernel: fwbr110i0: port 2(tap110i0) entered blocking state
Jan 15 15:56:57 pve-win11 kernel: fwbr110i0: port 1(fwln110i0) entered forwarding state
Jan 15 15:56:57 pve-win11 kernel: fwbr110i0: port 1(fwln110i0) entered blocking state
Jan 15 15:56:57 pve-win11 kernel: fwln110i0: entered promiscuous mode
Jan 15 15:56:57 pve-win11 kernel: fwln110i0: entered allmulticast mode
Jan 15 15:56:57 pve-win11 kernel: fwbr110i0: port 1(fwln110i0) entered disabled state
Jan 15 15:56:57 pve-win11 kernel: fwbr110i0: port 1(fwln110i0) entered blocking state
Jan 15 15:56:57 pve-win11 kernel: vmbr0: port 3(fwpr110p0) entered forwarding state
Jan 15 15:56:57 pve-win11 kernel: vmbr0: port 3(fwpr110p0) entered blocking state
Jan 15 15:56:57 pve-win11 kernel: fwpr110p0: entered promiscuous mode
Jan 15 15:56:57 pve-win11 kernel: fwpr110p0: entered allmulticast mode
Jan 15 15:56:57 pve-win11 kernel: vmbr0: port 3(fwpr110p0) entered disabled state
Jan 15 15:56:57 pve-win11 kernel: vmbr0: port 3(fwpr110p0) entered blocking state
Jan 15 15:56:57 pve-win11 kernel: tap110i0: entered promiscuous mode
Jan 15 15:56:57 pve-win11 systemd[1]: Started 110.scope.
Jan 15 15:56:57 pve-win11 pvedaemon[3110676]: failed to reset PCI device '0000:01:00.0', but trying to continue as not all devices need a reset
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:56:57 pve-win11 pvedaemon[3110676]: error writing '1' to '/sys/bus/pci/devices/0000:01:00.0/reset': Inappropriate ioctl for device
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 65535ms after FLR; giving up
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 32767ms after FLR; waiting
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 16383ms after FLR; waiting
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 8191ms after FLR; waiting
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 4095ms after FLR; waiting
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 2047ms after FLR; waiting
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: not ready 1023ms after FLR; waiting
Jan 15 15:56:57 pve-win11 kernel: pcieport 0000:00:01.1: retraining failed
Jan 15 15:56:57 pve-win11 kernel: pcieport 0000:00:01.1: broken device, retraining non-functional downstream link at 2.5GT/s
Jan 15 15:56:57 pve-win11 kernel: vfio-pci 0000:01:00.0: timed out waiting for pending transaction; performing function level reset anyway
Jan 15 15:55:46 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:55:46 pve-win11 kernel: vfio-pci 0000:01:00.0: Unable to change power state from D3cold to D0, device inaccessible
Jan 15 15:55:46 pve-win11 pvedaemon[3110676]: start VM 110: UPID:pve-win11:002F7714:52E3B19F:6787CC72:qmstart:110:root@pam:
Jan 15 15:55:46 pve-win11 pvedaemon[2669381]: <root@pam> starting task UPID:pve-win11:002F7714:52E3B19F:6787CC72:qmstart:110:root@pam:

System:
AMD Ryzen 7700X
MSI MAG B650 Tomahawk
 
Edit: Problem solved - different reason.

Today I encountered the same problem! My server ran for a week, with a Ubuntu 24 VM running + passed through AMD Radeon Pro WX4100, which worked on several different OS's without a problem (Also after VM reboots, etc.) Today I rebootet the host and no VM can access the GPU anymore.
I tried with and without attached ROM file, several host-reboots. Nothing.

Code: 
error writing '1' to '/sys/bus/pci/devices/0000:03:00.0/reset': Inappropriate ioctl for device
failed to reset PCI device '0000:03:00.0', but trying to continue as not all devices need a reset
kvm: vfio: Cannot reset device 0000:00:14.0, no available reset mechanism.
kvm: vfio: Cannot reset device 0000:00:14.0, no available reset mechanism.
TASK OK

Apologies! In my case the VM didn't start because I had forgotten to load keys for ZFS volumes that the VM needed, bringing my attention to the PCI reset error. What bothers me is that there is no error, indicating the actual reason why the VM can't start, pointing me in the completely wrong direction...

Code: 
# pveversion -v
proxmox-ve: 8.3.0 (running kernel: 6.8.12-5-pve)
pve-manager: 8.3.2 (running version: 8.3.2/3e76eec21c4a14a7)
proxmox-kernel-helper: 8.1.0
proxmox-kernel-6.8: 6.8.12-5
proxmox-kernel-6.8.12-5-pve-signed: 6.8.12-5
proxmox-kernel-6.8.12-4-pve-signed: 6.8.12-4
ceph-fuse: 17.2.7-pve3
corosync: 3.1.7-pve3
criu: 3.17.1-2+deb12u1
dnsmasq: 2.90-4~deb12u1
glusterfs-client: 10.3-5
ifupdown2: 3.2.0-1+pmx11
ksm-control-daemon: 1.5-1
libjs-extjs: 7.0.0-5
libknet1: 1.28-pve1
libproxmox-acme-perl: 1.5.1
libproxmox-backup-qemu0: 1.4.1
libproxmox-rs-perl: 0.3.4
libpve-access-control: 8.2.0
libpve-apiclient-perl: 3.3.2
libpve-cluster-api-perl: 8.0.10
libpve-cluster-perl: 8.0.10
libpve-common-perl: 8.2.9
libpve-guest-common-perl: 5.1.6
libpve-http-server-perl: 5.1.2
libpve-network-perl: 0.10.0
libpve-rs-perl: 0.9.1
libpve-storage-perl: 8.3.3
libspice-server1: 0.15.1-1
lvm2: 2.03.16-2
lxc-pve: 6.0.0-1
lxcfs: 6.0.0-pve2
novnc-pve: 1.5.0-1
proxmox-backup-client: 3.3.2-1
proxmox-backup-file-restore: 3.3.2-2
proxmox-firewall: 0.6.0
proxmox-kernel-helper: 8.1.0
proxmox-mail-forward: 0.3.1
proxmox-mini-journalreader: 1.4.0
proxmox-offline-mirror-helper: 0.6.7
proxmox-widget-toolkit: 4.3.3
pve-cluster: 8.0.10
pve-container: 5.2.3
pve-docs: 8.3.1
pve-edk2-firmware: 4.2023.08-4
pve-esxi-import-tools: 0.7.2
pve-firewall: 5.1.0
pve-firmware: 3.14-2
pve-ha-manager: 4.0.6
pve-i18n: 3.3.2
pve-qemu-kvm: 9.0.2-4
pve-xtermjs: 5.3.0-3
qemu-server: 8.3.3
smartmontools: 7.3-pve1
spiceterm: 3.3.0
swtpm: 0.8.0+pve1
vncterm: 1.8.0
zfsutils-linux: 2.2.6-pve1
 
Last edited:
I am having similar problems. Rebooting my Windows 11 VM(120) w RX560 PCIe Passthrough causes my Host to reboot on:
Code: 
pcieport 0000:00:03.1: AER: Correctable error message received from 0000:00:03.1
pcieport 0000:00:03.1: PCIe Bus Error: severity=Correctable, type=Transaction Layer, (Receiver ID)
pcieport 0000:00:03.1:   device [1022:1483] error status/mask=00002000/00004000
pcieport 0000:00:03.1:    [13] NonFatalErr

The VM had no issue until I added an m.2 NVME drive and reinstalled/upgraded from Proxmox 8.2 to 8.3.3.
apt update && apt install libpve-common-perl qemu-server
Hit:1 http://deb.debian.org/debian bookworm InRelease
Hit:2 http://security.debian.org/debian-security bookworm-security InRelease
Hit:3 http://deb.debian.org/debian bookworm-updates InRelease
Hit:4 http://download.proxmox.com/debian/pve bookworm InRelease
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
All packages are up to date.
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
libpve-common-perl is already the newest version (8.2.9).
qemu-server is already the newest version (8.3.7).

ASRock X570 Taichi
Ryzen 5950x
Kingston KSM32ED8/16HD-DDR4-16 GB (x2) & KSM26ED8/16ME-DDR4-16 GB (x2)
MSI Radeon RX 560 4GT LP OC GPU
Hauppauge 1229 WinTV-HVR-2255 LSI SAS9207-8e 8-Port External HBA Lenovo SA120
LSI SAS9207-8e 8-Port External HBA to Lenovo SA120

Thanks!

proxmox-ve: 8.3.0 (running kernel: 6.8.12-8-pve)
pve-manager: 8.3.3 (running version: 8.3.3/f157a38b211595d6)
proxmox-kernel-helper: 8.1.0
proxmox-kernel-6.8: 6.8.12-8
proxmox-kernel-6.8.12-8-pve-signed: 6.8.12-8
proxmox-kernel-6.8.12-4-pve-signed: 6.8.12-4
ceph-fuse: 17.2.7-pve3
corosync: 3.1.7-pve3
criu: 3.17.1-2+deb12u1
glusterfs-client: 10.3-5
ifupdown2: 3.2.0-1+pmx11
ksm-control-daemon: 1.5-1
libjs-extjs: 7.0.0-5
libknet1: 1.28-pve1
libproxmox-acme-perl: 1.5.1
libproxmox-backup-qemu0: 1.5.1
libproxmox-rs-perl: 0.3.4
libpve-access-control: 8.2.0
libpve-apiclient-perl: 3.3.2
libpve-cluster-api-perl: 8.0.10
libpve-cluster-perl: 8.0.10
libpve-common-perl: 8.2.9
libpve-guest-common-perl: 5.1.6
libpve-http-server-perl: 5.2.0
libpve-network-perl: 0.10.0
libpve-rs-perl: 0.9.1
libpve-storage-perl: 8.3.3
libspice-server1: 0.15.1-1
lvm2: 2.03.16-2
lxc-pve: 6.0.0-1
lxcfs: 6.0.0-pve2
novnc-pve: 1.5.0-1
proxmox-backup-client: 3.3.2-1
proxmox-backup-file-restore: 3.3.2-2
proxmox-firewall: 0.6.0
proxmox-kernel-helper: 8.1.0
proxmox-mail-forward: 0.3.1
proxmox-mini-journalreader: 1.4.0
proxmox-offline-mirror-helper: 0.6.7
proxmox-widget-toolkit: 4.3.4
pve-cluster: 8.0.10
pve-container: 5.2.3
pve-docs: 8.3.1
pve-edk2-firmware: 4.2023.08-4
pve-esxi-import-tools: 0.7.2
pve-firewall: 5.1.0
pve-firmware: 3.14-3
pve-ha-manager: 4.0.6
pve-i18n: 3.3.3
pve-qemu-kvm: 9.0.2-5
pve-xtermjs: 5.3.0-3
qemu-server: 8.3.7
smartmontools: 7.3-pve1
spiceterm: 3.3.0
swtpm: 0.8.0+pve1
vncterm: 1.8.0
zfsutils-linux: 2.2.7-pve1
NAME FSUSE% SIZE LABEL FSTYPE MODEL
sda 1T WDC WD1001X06X-00SJVT0
└─sda1 1T Games ntfs
sdb 238.5G KINGSTON SVP100S2256G
└─sdb1 238.5G Win ntfs
sdc 238.5G KINGSTON SVP100S2256G
└─sdc1 62% 238.5G Nightly ext4
sdd 238.5G KINGSTON SVP100S2256G
sde 465.8G SAMSUNG HN-M500MBB
└─sde1 465.8G Security exfat
sdf 465.8G TOSHIBA MK5055GSX
└─sdf1 75% 465.8G Store ext4
sr0 1024M Optiarc BD ROM BC-5640H
nvme1n1 953.9G KXG60ZNV1T02 KIOXIA
└─nvme1n1p3 952.9G LVM2_member
├─pve--kioxia-swap 8G swap
├─pve--kioxia-root 96G ext4
├─pve--kioxia-data_tmeta 8.3G
│ └─pve--kioxia-data-tpool 816.2G
│ ├─pve--kioxia-data 816.2G
│ ├─pve--kioxia-vm--110--disk--0 21G
│ ├─pve--kioxia-vm--150--disk--0 20G
│ ├─pve--kioxia-vm--124--disk--0 4M
│ ├─pve--kioxia-vm--124--disk--1 65G
│ ├─pve--kioxia-vm--124--disk--2 4M
│ ├─pve--kioxia-vm--140--disk--0 32G
│ ├─pve--kioxia-vm--120--disk--1 65G
│ ├─pve--kioxia-vm--120--disk--2 4M
│ ├─pve--kioxia-vm--101--disk--0 8G ext4
│ ├─pve--kioxia-vm--160--disk--0 20G
│ └─pve--kioxia-vm--120--disk--0 4M
└─pve--kioxia-data_tdata 816.2G
└─pve--kioxia-data-tpool 816.2G
├─pve--kioxia-data 816.2G
├─pve--kioxia-vm--110--disk--0 21G
├─pve--kioxia-vm--150--disk--0 20G
├─pve--kioxia-vm--124--disk--0 4M
├─pve--kioxia-vm--124--disk--1 65G
├─pve--kioxia-vm--124--disk--2 4M
├─pve--kioxia-vm--140--disk--0 32G
├─pve--kioxia-vm--120--disk--1 65G
├─pve--kioxia-vm--120--disk--2 4M
├─pve--kioxia-vm--101--disk--0 8G ext4
├─pve--kioxia-vm--160--disk--0 20G
└─pve--kioxia-vm--120--disk--0 4M
nvme0n1 13.4G H10 HBRPEKNX0101AO NVMe INTEL 16GB
├─nvme0n1p1 1007K
├─nvme0n1p2 512M vfat
└─nvme0n1p3 12.9G LVM2_member
├─pve-swap 1G swap
└─pve-root 40% 11.9G ext4
00:00.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse Root Complex [1022:1480]
00:00.2 IOMMU [0806]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse IOMMU [1022:1481]
00:01.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse PCIe Dummy Host Bridge [1022:1482]
00:01.2 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse GPP Bridge [1022:1483]
00:01.3 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse GPP Bridge [1022:1483]
00:02.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse PCIe Dummy Host Bridge [1022:1482]
00:03.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse PCIe Dummy Host Bridge [1022:1482]
00:03.1 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse GPP Bridge [1022:1483]
00:03.2 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse GPP Bridge [1022:1483]
00:04.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse PCIe Dummy Host Bridge [1022:1482]
00:05.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse PCIe Dummy Host Bridge [1022:1482]
00:07.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse PCIe Dummy Host Bridge [1022:1482]
00:07.1 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse Internal PCIe GPP Bridge 0 to bus[E:B] [1022:1484]
00:08.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse PCIe Dummy Host Bridge [1022:1482]
00:08.1 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse Internal PCIe GPP Bridge 0 to bus[E:B] [1022:1484]
00:14.0 SMBus [0c05]: Advanced Micro Devices, Inc. [AMD] FCH SMBus Controller [1022:790b] (rev 61)
00:14.3 ISA bridge [0601]: Advanced Micro Devices, Inc. [AMD] FCH LPC Bridge [1022:790e] (rev 51)
00:18.0 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Matisse/Vermeer Data Fabric: Device 18h; Function 0 [1022:1440]
00:18.1 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Matisse/Vermeer Data Fabric: Device 18h; Function 1 [1022:1441]
00:18.2 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Matisse/Vermeer Data Fabric: Device 18h; Function 2 [1022:1442]
00:18.3 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Matisse/Vermeer Data Fabric: Device 18h; Function 3 [1022:1443]
00:18.4 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Matisse/Vermeer Data Fabric: Device 18h; Function 4 [1022:1444]
00:18.5 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Matisse/Vermeer Data Fabric: Device 18h; Function 5 [1022:1445]
00:18.6 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Matisse/Vermeer Data Fabric: Device 18h; Function 6 [1022:1446]
00:18.7 Host bridge [0600]: Advanced Micro Devices, Inc. [AMD] Matisse/Vermeer Data Fabric: Device 18h; Function 7 [1022:1447]
01:00.0 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Matisse Switch Upstream [1022:57ad]
02:01.0 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Matisse PCIe GPP Bridge [1022:57a3]
02:02.0 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Matisse PCIe GPP Bridge [1022:57a3]
02:03.0 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Matisse PCIe GPP Bridge [1022:57a3]
02:08.0 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Matisse PCIe GPP Bridge [1022:57a4]
02:09.0 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Matisse PCIe GPP Bridge [1022:57a4]
02:0a.0 PCI bridge [0604]: Advanced Micro Devices, Inc. [AMD] Matisse PCIe GPP Bridge [1022:57a4]
03:00.0 Multimedia controller [0480]: Philips Semiconductors SAA7164 [1131:7164] (rev 81)
04:00.0 Non-Volatile memory controller [0108]: Intel Corporation Optane NVME SSD H10 with Solid State Storage [Teton Glacier] [8086:0975]
05:00.0 PCI bridge [0604]: ASMedia Technology Inc. ASM1184e 4-Port PCIe x1 Gen2 Packet Switch [1b21:1184]
06:01.0 PCI bridge [0604]: ASMedia Technology Inc. ASM1184e 4-Port PCIe x1 Gen2 Packet Switch [1b21:1184]
06:03.0 PCI bridge [0604]: ASMedia Technology Inc. ASM1184e 4-Port PCIe x1 Gen2 Packet Switch [1b21:1184]
06:05.0 PCI bridge [0604]: ASMedia Technology Inc. ASM1184e 4-Port PCIe x1 Gen2 Packet Switch [1b21:1184]
06:07.0 PCI bridge [0604]: ASMedia Technology Inc. ASM1184e 4-Port PCIe x1 Gen2 Packet Switch [1b21:1184]
07:00.0 Network controller [0280]: Intel Corporation Wi-Fi 6 AX200 [8086:2723] (rev 1a)
09:00.0 Ethernet controller [0200]: Intel Corporation I211 Gigabit Network Connection [8086:1539] (rev 03)
0b:00.0 Non-Essential Instrumentation [1300]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse Reserved SPP [1022:1485]
0b:00.1 USB controller [0c03]: Advanced Micro Devices, Inc. [AMD] Matisse USB 3.0 Host Controller [1022:149c]
0b:00.3 USB controller [0c03]: Advanced Micro Devices, Inc. [AMD] Matisse USB 3.0 Host Controller [1022:149c]
0c:00.0 SATA controller [0106]: Advanced Micro Devices, Inc. [AMD] FCH SATA Controller [AHCI mode] [1022:7901] (rev 51)
0d:00.0 SATA controller [0106]: Advanced Micro Devices, Inc. [AMD] FCH SATA Controller [AHCI mode] [1022:7901] (rev 51)
0e:00.0 Non-Volatile memory controller [0108]: Toshiba Corporation XG6 NVMe SSD Controller [1179:011a]
0f:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Baffin [Radeon RX 550 640SP / RX 560/560X] [1002:67ff] (rev cf)
0f:00.1 Audio device [0403]: Advanced Micro Devices, Inc. [AMD/ATI] Baffin HDMI/DP Audio [Radeon RX 550 640SP / RX 560/560X] [1002:aae0]
10:00.0 Serial Attached SCSI controller [0107]: Broadcom / LSI SAS2308 PCI-Express Fusion-MPT SAS-2 [1000:0087] (rev 05)
11:00.0 Non-Essential Instrumentation [1300]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse PCIe Dummy Function [1022:148a]
12:00.0 Non-Essential Instrumentation [1300]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse Reserved SPP [1022:1485]
12:00.1 Encryption controller [1080]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse Cryptographic Coprocessor PSPCPP [1022:1486]
12:00.3 USB controller [0c03]: Advanced Micro Devices, Inc. [AMD] Matisse USB 3.0 Host Controller [1022:149c]
12:00.4 Audio device [0403]: Advanced Micro Devices, Inc. [AMD] Starship/Matisse HD Audio Controller [1022:1487]
#TaichiMedia Windows 11 Pro Version 23H2
agent: 1,fstrim_cloned_disks=1
args: -cpu host,+svm
audio0: device=ich9-intel-hda,driver=none
balloon: 0
bios: ovmf
boot: order=scsi0;ide0
cores: 12
cpu: host
efidisk0: kioxia:vm-120-disk-0,efitype=4m,pre-enrolled-keys=1,size=4M
hostpci0: 0000:0f:00,pcie=1,romfile=Polaris21.rom,x-vga=1
hostpci1: 0000:03:00,pcie=1
ide0: Store:iso/virtio-win-0.1.266.iso,media=cdrom,size=707456K
machine: pc-q35-9.0
memory: 16384
meta: creation-qemu=6.2.0,ctime=1651621342
name: TaichiMedia
net0: virtio=BC:24:11:06:EE:F5,bridge=vmbr0,firewall=1
numa: 1
onboot: 1
ostype: win11
sata0: /dev/disk/by-label/Win,backup=0,replicate=0,size=244197M
sata1: /dev/disk/by-label/Games,backup=0,replicate=0,size=1068342M
sata2: /dev/disk/by-label/Security,backup=0,replicate=0,size=476939M
scsi0: kioxia:vm-120-disk-1,cache=writeback,discard=on,iothread=1,size=65G,ssd=1
scsihw: virtio-scsi-single
smbios1: uuid=4f897015-58c9-4227-a45c-9dbffa649749
sockets: 1
startup: order=1
tablet: 1
tpmstate0: kioxia:vm-120-disk-2,size=4M,version=v2.0
usb1: host=046d:c52b
usb2: host=04da:3903
usb3: host=044f:0409
vga: vmware,memory=36
vmgenid: 6354cf20-6496-4bf7-9e82-707d4b661e30
GRUB_DEFAULT=0
GRUB_TIMEOUT=2
GRUB_DISTRIBUTOR=`lsb_release -i -s 2> /dev/null || echo Debian`
GRUB_CMDLINE_LINUX_DEFAULT="quiet initcall_blacklist=sysfb_init" # also tried with iommu=pt
GRUB_CMDLINE_LINUX=""
CPU Configuration > SVM Mode > Enabled
PCI Configuration > SR-IOV Support > Enabled
Onboard Devices Configuration > Restore on AC Power Loss > Power On
Storage Configuration > SATA Controllers(s) > AHCI
ACPI Configuration > PCIE Devices Power On > Enabled
AMD Overclocking > PBO2 > Auto
AMD CBS > NBIO Common Options
IOMMU Enabled
Enable AER Cap Enabled
ACS Enabled
PCIe ARI Support Disabled
vfio
vfio_iommu_type1
vfio_pci
vfio_virqfd
vhost-net
IOMMU Groups: https://pastebin.com/XtC2muTF
dmesg | grep AMD-Vi
[ 0.180891] AMD-Vi: Using global IVHD EFR:0x0, EFR2:0x0
[ 0.786620] pci 0000:00:00.2: AMD-Vi: IOMMU performance counters supported
[ 0.788553] AMD-Vi: Extended features (0x58f77ef22294a5a, 0x0): PPR NX GT IA PC GA_vAPIC
[ 0.788559] AMD-Vi: Interrupt remapping enabled

dmesg | grep -e DMAR -e IOMMU
[ 0.786620] pci 0000:00:00.2: AMD-Vi: IOMMU performance counters supported
[ 0.788889] perf/amd_iommu: Detected AMD IOMMU #0 (2 banks, 4 counters/bank).

dmesg | grep 'remapping'
[ 0.498855] x2apic: IRQ remapping doesn't support X2APIC mode
[ 0.788559] AMD-Vi: Interrupt remapping enabled
The following logs were captured from a fresh boot through crash. Only VM120, the problematic VM with GPU, was running:
demsg https://pastebin.com/jkafJvvX
journalctl -b -1 https://pastebin.com/4UUBZz3i
 
Last edited:
You must log in or register to reply here.
Top Bottom