[vfio-users] vfio help needed (nvidia GTX 750 Ti persistent code 43)

Mogliii mogliii at gmx.net
Fri Sep 18 00:39:23 UTC 2015


On 9/17/2015 9:59 PM, Alex Williamson wrote:
> On Wed, Sep 16, 2015 at 5:39 PM, Mogliii <mogliii at gmx.net
> <mailto:mogliii at gmx.net>> wrote:
>
>     Hello,
>
>     Thank you for all the valuable input. However, the problem is not
>     yet resolved.
>
>     I specifically forced all the hyperv and clock options off so the
>     nvidia driver hopefully does not recognize its in a vm. However, I
>     get the same problem. Once the system recognized the graphics card
>     and wants to activate the driver, the screen goes black and I have
>     a loss of signal.
>
>     My qemu command is (added newlines for better readability)
>     # ps aux | grep kvm
>
>     /usr/bin/qemu-system-x86_64 -name win81 -S
>     -machine pc-i440fx-utopic,accel=kvm,usb=off
>     -cpu host,kvm=off -bios /usr/share/ovmf/OVMF-pure-efi_win81.fd
>     -m 4096 -realtime mlock=off -smp 2,sockets=2,cores=1,threads=1
>     -uuid redacted -nographic -no-user-config -nodefaults
>     -chardev
>     socket,id=charmonitor,path=/var/lib/libvirt/qemu/win81.monitor,server,nowait
>
>     -mon chardev=charmonitor,id=monitor,mode=control
>     -rtc base=localtime,driftfix=slew -global
>     kvm-pit.lost_tick_policy=discard
>     -no-hpet -no-shutdown -global PIIX4_PM.disable_s3=1 -global
>     PIIX4_PM.disable_s4=1
>     -boot strict=on -device ich9-usb-ehci1,id=usb,bus=pci.0,addr=0x6.0x7
>     -device
>     ich9-usb-uhci1,masterbus=usb.0,firstport=0,bus=pci.0,multifunction=on,addr=0x6
>
>     -device
>     ich9-usb-uhci2,masterbus=usb.0,firstport=2,bus=pci.0,addr=0x6.0x1
>     -device
>     ich9-usb-uhci3,masterbus=usb.0,firstport=4,bus=pci.0,addr=0x6.0x2
>     -device virtio-serial-pci,id=virtio-serial0,bus=pci.0,addr=0x5
>     -drive
>     file=/dev/main/Win7xen,if=none,id=drive-virtio-disk0,format=raw,cache=none,aio=native
>     -device
>     virtio-blk-pci,scsi=off,bus=pci.0,addr=0x8,drive=drive-virtio-disk0,id=virtio-disk0,bootindex=1
>
>     -netdev tap,fd=24,id=hostnet0,vhost=on,vhostfd=25
>     -device
>     virtio-net-pci,netdev=hostnet0,id=net0,mac=52:54:00:ab:b6:10,bus=pci.0,addr=0x4
>
>     -device usb-host,hostbus=1,hostaddr=2,id=hostdev0
>     -device usb-host,hostbus=5,hostaddr=2,id=hostdev1
>     -device usb-host,hostbus=5,hostaddr=3,id=hostdev2
>     -device vfio-pci,host=01:00.0,id=hostdev3,bus=pci.0,addr=0x3
>     -device vfio-pci,host=01:00.1,id=hostdev4,bus=pci.0,addr=0x9
>      -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x7 -msg
>     timestamp=on
>
>     I can also confirm that the vfio-pci bind script is not necessary,
>     and that removing "allow_unsafe_interrupts" did not change anything.
>
>     I might later try switching the graphics card to bios mode.
>
>
> Have you looked for errors in dmesg or the libvirt log file for the
> domain yet?  Users with APUs generally get IOMMU faults unless they
> disable hugepage support in vfio,
>  vfio_iommu_type1.disable_hugepages=1.  I thought we had enough people
> using APU systems to not completely give up on the platform.
Dear Alex,

Below are outputs for dmesg | grep iommu and
/var/log/libvirt/qemu/win81.log. Actually now the VM restarts by itself.
The INVALID_DEVICE_REQUEST might be a problem. I found something about
it here:
https://bbs.archlinux.org/viewtopic.php?pid=1519198#p1519198

and further:
""So, the only way to run vfio-pci stable on AMD APU-based Athlon CPUs
or APUs is OVMF.
UPD:
Just checked AMD's revision guide on fam15h mod30h-3fh - they've deleted
a lot of bugs, but the IOMMU ones are still present. Still not quite
sure what do they mean.
""
But I am using OVMF. How to get the version of the bytecode of the APU?
Does it get updated through linux or would I have to run windows in bare
metal on that machine? Do I need a newer kernel that has patches to work
around know bugs of the APU?

Anyway, I ordered the Z87 Extrexeme6 and a i5-4460. I need to see
successful passthrough to believe in this technology^^ Maybe I will
regain motivation to try again with the APU.


=================

dmesg
[    0.000000] Kernel command line:
BOOT_IMAGE=/vmlinuz-3.19.0-28-generic root=/dev/mapper/main-root ro
rootflags=subvol=@ quiet splash nomdmonddf nomdmonisw amd_iommu=on
iommu=pt vfio_iommu_type1.disable_hugepages=1
pci-stub.ids=10de:0fbc,10de:1380 vt.handoff=7
[    0.986796] perf: amd_iommu: Detected. (2 banks, 4 counters/bank)
[...]
[  324.248382] AMD-Vi: Event logged [INVALID_DEVICE_REQUEST
device=00:00.1 address=0x000000fdf8040020 flags=0x0a00]



/var/log/libvirt/qemu/win81.log

2015-09-17 23:58:35.148+0000: starting up
LC_ALL=C
PATH=/usr/local/sbin:/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin
QEMU_AUDIO_DRV=none /usr/bin/qemu-system-x86_64 -name win81 -S -machine
pc-i440fx-utopic,accel=kvm,usb=off -cpu host,kvm=off -bios
/usr/share/ovmf/OVMF-pure-efi_win81.fd -m 4096 -realtime mlock=off -smp
2,sockets=2,cores=1,threads=1 -uuid b9934413-4497-4405-bfec-2767990989ff
-nographic -no-user-config -nodefaults -chardev
socket,id=charmonitor,path=/var/lib/libvirt/qemu/win81.monitor,server,nowait
-mon chardev=charmonitor,id=monitor,mode=control -rtc
base=localtime,driftfix=slew -global kvm-pit.lost_tick_policy=discard
-no-hpet -no-shutdown -global PIIX4_PM.disable_s3=1 -global
PIIX4_PM.disable_s4=1 -boot strict=on -device
ich9-usb-ehci1,id=usb,bus=pci.0,addr=0x6.0x7 -device
ich9-usb-uhci1,masterbus=usb.0,firstport=0,bus=pci.0,multifunction=on,addr=0x6
-device
ich9-usb-uhci2,masterbus=usb.0,firstport=2,bus=pci.0,addr=0x6.0x1
-device
ich9-usb-uhci3,masterbus=usb.0,firstport=4,bus=pci.0,addr=0x6.0x2
-device virtio-serial-pci,id=virtio-serial0,bus=pci.0,addr=0x5 -drive
file=/dev/main/Win7xen,if=none,id=drive-virtio-disk0,format=raw,cache=none,aio=native
-device
virtio-blk-pci,scsi=off,bus=pci.0,addr=0x8,drive=drive-virtio-disk0,id=virtio-disk0,bootindex=1
-netdev tap,fd=24,id=hostnet0,vhost=on,vhostfd=25 -device
virtio-net-pci,netdev=hostnet0,id=net0,mac=52:54:00:ab:b6:10,bus=pci.0,addr=0x4
-device usb-host,hostbus=1,hostaddr=2,id=hostdev0 -device
usb-host,hostbus=5,hostaddr=2,id=hostdev1 -device
usb-host,hostbus=5,hostaddr=3,id=hostdev2 -device
vfio-pci,host=01:00.0,id=hostdev3,bus=pci.0,addr=0x3 -device
vfio-pci,host=01:00.1,id=hostdev4,bus=pci.0,addr=0x2 -device
virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x7 -msg timestamp=on
Domain id=2 is tainted: high-privileges
Domain id=2 is tainted: host-cpu
qemu: terminating on signal 15 from pid 2745
2015-09-18 00:00:14.694+0000: shutting down

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listman.redhat.com/archives/vfio-users/attachments/20150918/0b92c727/attachment.htm>


More information about the vfio-users mailing list