Difference between revisions of "PCI Passthrough"

From Proxmox VE
Jump to navigation Jump to search
(fix)
(43 intermediate revisions by 4 users not shown)
Line 1: Line 1:
 
== Introduction ==
 
== Introduction ==
  
−
PCI passthrough allows you to use a physical PCI device (graphic card, network card) inside a VM (KVM virtualization only)  
+
PCI passthrough allows you to use a physical PCI device (graphics card, network card) inside a VM (KVM virtualization only).
−
If you "PCI passthrough" a device, the device is not available in the host anymore.
+
If you "PCI passthrough" a device, the device is not available to the host anymore.
  
 
'''Note:'''  
 
'''Note:'''  
  
−
PCI passthrough is a experimental features in Proxmox VE
+
PCI passthrough is an experimental feature in Proxmox VE
  
 
== Intel CPU ==
 
== Intel CPU ==
Line 18: Line 18:
 
</source> then <source lang="bash">
 
</source> then <source lang="bash">
 
# update-grub
 
# update-grub
−
# reboot
 
 
</source>  
 
</source>  
  
 
<br>  
 
<br>  
  
−
Then run "dmesg | grep -e DMAR -e IOMMU" from the command line. &nbsp;If there is no output, then something is wrong.  
+
Then run "dmesg | grep -e DMAR -e IOMMU" from the command line. &nbsp;If there is no output, then something is wrong.
  
 
== AMD CPU ==
 
== AMD CPU ==
Line 37: Line 36:
 
</source> To: <source lang="bash">
 
</source> To: <source lang="bash">
 
GRUB_CMDLINE_LINUX_DEFAULT="quiet amd_iommu=on"  
 
GRUB_CMDLINE_LINUX_DEFAULT="quiet amd_iommu=on"  
−
</source> Then: <source lang="bash">
+
 
−
# update-grub
 
−
# echo "options kvm allow_unsafe_assigned_interrupts=1" > /etc/modprobe.d/kvm_iommu_map_guest.conf
 
−
# reboot
 
 
</source>  
 
</source>  
  
−
== Determine your PCI card address, and configure your VM ==
 
−
 
−
Locate your card using "lspci". &nbsp;The address should be in the form of: 04:00.0
 
  
−
Manually edit the node.conf file. &nbsp;It can be located at:&nbsp;/etc/pve/qemu-server/vmid.conf.
+
==Required modules ==
 +
add to /etc/modules
  
−
Add this line to the end of the file:
 
 
<pre>
 
<pre>
−
hostpci0: 04:00.0
+
vfio
 +
vfio_iommu_type1
 +
vfio_pci
 +
vfio_virqfd
 
</pre>
 
</pre>
  
−
If you have a multi-function device (like a vga card with embedded audio chipset),
+
== IOMMU interrupt remapping ==
 +
it will not be possible to use PCI passthrough without interrupt remapping.
 +
 
 +
Device assignment will fail with a 'Failed to assign device "[device name]" : Operation not permitted' error for users of KVM, and a 'Interrupt Remapping hardware not found, passing devices to unprivileged domains is insecure.
  
−
you can pass both with removing the ".0" in pci address.
+
Systems which don't support interrupt remapping:
  
−
<pre>
 
−
hostpci0: 04:00
 
−
</pre>
 
  
−
== PCI EXPRESS PASSTHROUGH ==
+
* All systems using an AMD processor and chipset that have AMD I/O Virtualization (AMD-Vi) support. Such hardware has interrupt remapping support; however, the software support is not yet available upstream.
  
−
<pre>
+
* All systems using an Intel processor and chipset that have support for Intel Virtualization Technology for Directed I/O (VT-d), but do not have support for interrupt remapping. Interrupt remapping support is provided in newer processors and chipsets. To identify if your system has support for interrupt remapping:
−
/etc/pve/qemuserver/<vmid>.cfg
 
−
</pre>
 
  
−
simple pci-express passthrough
+
1) Run the "dmesg | grep ecap" command.
−
<pre>
 
−
machine: q35
 
−
hostpci0: 04:00.0,pcie=1
 
−
</pre>
 
  
−
== GPU PASSTHROUGH ==
+
2) On the IOMMU lines, the hexadecimal value after "ecap" indicates whether interrupt remapping is supported. If the last character of this value is an 8, 9, a, b, c, d, e, or an f, interrupt remapping is supported. For example, "ecap 1000" indicates there is no interrupt remapping support. "ecap 10207f" indicates interrupt remapping support, as the last character is an "f".
  
−
* MD RADEON 5xxx, 6xxx, 7xxx and NVIDIA GEFORCE 7, 8, 4xx, 5xx, 6xx, 7xx have been reported working.
+
Interrupt remapping will only be enabled if every IOMMU supports it.
−
* Maybe you'll need to load some specific options in grub.cfg or other tuning values,
 
−
* Here a good forum thread of archlinux: https://bbs.archlinux.org/viewtopic.php?id=162768
 
  
−
They are 4 configuration possible:
+
Alternatively, run the following script to determine if your system has interrupt remapping support:
  
−
=== GPU Seabios PCI PASSTHROUGH ===
 
 
<pre>
 
<pre>
−
hostpci0: 04:00.0,x-vga=on
+
#!/bin/sh
−
</pre>
+
if [ $(dmesg | grep ecap | wc -l) -eq 0 ]; then
−
 
+
  echo "No interrupt remapping support found"
 +
  exit 1
 +
fi
  
−
=== GPU Seabios PCI EXPRESS PASSTHROUGH ===
+
for i in $(dmesg | grep ecap | awk '{print $NF}'); do
−
<pre>
+
  if [ $(( (0x$i & 0xf) >> 3 )) -ne 1 ]; then
−
machine: q35
+
    echo "Interrupt remapping not supported"
−
hostpci0: 04:00.0,pcie=1,x-vga=on
+
    exit 1
 +
  fi
 +
done
 
</pre>
 
</pre>
  
 +
If your system doesn't support interrupt remapping,
  
−
=== GPU OVMF PCI  PASSTHROUGH  ===
+
you can allow unsafe interrupts with:
−
 
 
−
OVMF replace bios by UEFI boot.
 
−
You need to install your guest OS with uefi support,
 
−
 
 
−
and you need to your graphic card have a uefi bootable rom
 
−
 
 
−
This is the recommended mode
 
  
 
<pre>
 
<pre>
−
bios: ovmf
+
echo "options vfio_iommu_type1 allow_unsafe_interrupts=1" > /etc/modprobe.d/iommu_unsafe_interrupts.conf
−
scsihw: virtio-scsi-pci
 
−
bootdisk: scsi0
 
−
scsi0: .....
 
−
hostpci0: 04:00.0,x-vga=on
 
 
</pre>
 
</pre>
  
−
=== GPU OVMF PCI EXPRESS PASSTHROUGH ===
+
== Verify IOMMU isolation==
−
 
 
−
<pre>
 
−
bios: ovmf
 
−
scsihw: virtio-scsi-pci
 
−
bootdisk: scsi0
 
−
scsi0: .....
 
−
machine: q35
 
−
hostpci0: 04:00.0,pcie=1,x-vga=on
 
−
</pre>
 
−
 
 
−
 
 
−
== Verify IOMMU ==
 
  
 
To have pci passthrough working fine, you need dedicated iommu group for
 
To have pci passthrough working fine, you need dedicated iommu group for
Line 191: Line 160:
  
 
2) add "pcie_acs_override=downstream" to grub options, which can help on some setup with bad ACS implementation.
 
2) add "pcie_acs_override=downstream" to grub options, which can help on some setup with bad ACS implementation.
−
 
−
3) you can also try to add this option
 
−
<pre>
 
−
echo "options vfio_iommu_type1 allow_unsafe_interrupts=1" > /etc/modprobe.d/iommu_unsafe_interrupts.conf
 
−
</pre>
 
  
  
Line 204: Line 168:
 
http://vfio.blogspot.be/2014/08/iommu-groups-inside-and-out.html
 
http://vfio.blogspot.be/2014/08/iommu-groups-inside-and-out.html
  
−
== Verify Operation ==
 
  
−
Start the VM from the UI.
+
== Determine your PCI card address, and configure your VM ==
 +
 
 +
Locate your card using "lspci". &nbsp;The address should be in the form of: 01:00.0
 +
 
 +
Manually edit the node.conf file. &nbsp;It can be located at:&nbsp;/etc/pve/qemu-server/vmid.conf.
 +
 
 +
Add this line to the end of the file:
 +
<pre>
 +
hostpci0: 01:00.0
 +
</pre>
 +
 
 +
If you have a multi-function device  (like a vga card with embedded audio chipset),
 +
 
 +
you can pass all functions manually with
 +
 
 +
<pre>
 +
hostpci0: 01:00.0;01:00.1
 +
</pre>
 +
 
 +
or
 +
 
 +
to pass all functions automatically
  
−
Enter the qm monitor. &nbsp;"qm monitor vmnumber"
+
<pre>
 +
hostpci0: 01:00
 +
</pre>
  
−
Verify that your card is listed here: "info pci"
+
== PCI EXPRESS PASSTHROUGH ==
  
−
Then install drivers on your guest OS. &nbsp;
+
<pre>
 +
/etc/pve/qemu-server/<vmid>.conf
 +
</pre>
  
−
NOTE: Card support might be limited to 2 or 3 devices.
+
simple pci-express passthrough
 +
<pre>
 +
machine: q35
 +
hostpci0: 01:00.0,pcie=1
 +
</pre>
  
−
NOTE: This process will remove the card from the proxmox host OS. &nbsp;
+
== GPU PASSTHROUGH ==
  
−
Editorial Note:  Using PCI passthrough to present drives direct to a ZFS (FreeNAS, Openfiler, OmniOS) virtual machine is OK for testing, but '''not recommended''' for production use. Specific FreeNAS warnings can be found here: http://forums.freenas.org/threads/absolutely-must-virtualize-freenas-a-guide-to-not-completely-losing-your-data.12714/
+
* MD RADEON 5xxx, 6xxx, 7xxx and NVIDIA GEFORCE 7, 8, 4xx, 5xx, 6xx, 7xx have been reported working.
 +
* Maybe you'll need to load some specific options in grub.cfg or other tuning values,
 +
* Here a good forum thread of archlinux: https://bbs.archlinux.org/viewtopic.php?id=162768
  
 +
For GPU, it's good that host don't try to use the GPU, and avoids issues with the host driver unbinding and re-binding to the device.
  
−
== WORKING NVIDIA SETUP ==
+
First, find the device and vendor id of your vga card
  
−
I've been able to get this working with an NVIDIA GTX 750 Ti card using driver version 344.75 (newer versions inconsistently cause Code 43 Errors) by using the following setup:
+
<pre>
 +
$ lspci -n -s 01:00
 +
01:00.0 0300: 10de:1381 (rev a2)
 +
01:00.1 0403: 10de:0fbc (rev a1)
 +
</pre>
  
−
Install <tt>pve-kernel-3.10.0-5-pve</tt> with:
+
The Vendor:Device IDs for my GPU and audio functions are therefore 10de:1381, 10de:0fbc.
  
 +
Then, create a file
 
<pre>
 
<pre>
−
Add to /etc/modules:
+
echo "options vfio-pci ids=10de:1381,10de:0fbc" > /etc/modprobe.d/vfio.conf
−
pci_stub
 
−
vfio
 
−
vfio_iommu_type1
 
−
vfio_pci
 
−
kvm
 
−
kvm_intel
 
 
</pre>
 
</pre>
  
−
Add the following options to <tt>/etc/default/grub</tt> on the GRUB_CMDLINE_LINUX_DEFAULT line:
+
Then blacklist drivers
 +
 
 
<pre>
 
<pre>
−
intel_iommu=on vfio_iommu_type1.allow_unsafe_interrupts=1 rootdelay=10 scsi_mod.scan=sync
+
echo "blacklist radeon" >> /etc/modprobe.d/blacklist.conf
 +
echo "blacklist nouveau" >> /etc/modprobe.d/blacklist.conf
 +
echo "blacklist nvidia" >> /etc/modprobe.d/blacklist.conf
 
</pre>
 
</pre>
 +
For VM configuration, They are 4 configuration possible:
 +
 +
=== GPU OVMF PCI  PASSTHROUGH  (recommended) ===
 +
 +
OVMF replace bios by UEFI boot.
 +
You need to install your guest OS with uefi support,  (for windows, try win >=8)
  
 +
using OVMF, you can also add disable_vga=1 to vfio-pci module, which try to to opt-out devices from vga arbitration if possible.
 
<pre>
 
<pre>
−
Run: update-grub
+
echo "options vfio-pci ids=10de:1381,10de:0fbc disable_vga=1" > /etc/modprobe.d/vfio.conf
 
</pre>
 
</pre>
 +
 +
and you need to your graphic card have a uefi bootable rom
 +
http://vfio.blogspot.fr/2014/08/does-my-graphics-card-rom-support-efi.html
  
 
<pre>
 
<pre>
−
Add the following to <tt>/etc/initramfs-tools/modules</tt> (find the PCI stub IDs for your card by running <tt>lspci -nn | grep NVIDIA</tt>):
+
bios: ovmf
−
pci_stub ids=10de:0f02,10de:0bea
+
scsihw: virtio-scsi-pci
 +
bootdisk: scsi0
 +
scsi0: .....
 +
hostpci0: 01:00,x-vga=on
 
</pre>
 
</pre>
 +
 +
=== GPU OVMF PCI EXPRESS PASSTHROUGH ===
 +
OVMF replace bios by UEFI boot.
 +
 +
You need to install your guest OS with uefi support,  (for windows, try win >=8)
 +
 +
and you need to your graphic card have a uefi bootable rom
 +
http://vfio.blogspot.fr/2014/08/does-my-graphics-card-rom-support-efi.html
  
 
<pre>
 
<pre>
−
Run: update-initramfs -u and then reboot into the new kernel.
+
bios: ovmf
 +
scsihw: virtio-scsi-pci
 +
bootdisk: scsi0
 +
scsi0: .....
 +
machine: q35
 +
hostpci0: 01:00,pcie=1,x-vga=on
 
</pre>
 
</pre>
  
−
Boot into the VM using the Proxmox web interface, and install the OS (I had better luck with Windows 8.1 - can't remember specifics though).
+
=== GPU Seabios PCI PASSTHROUGH ===
 +
<pre>
 +
hostpci0: 01:00,x-vga=on
 +
</pre>
  
−
Add the following options to <tt>/etc/pve/host/qemu-server/vmid.conf</tt> (get the PCI address from <tt>lspci</tt> command, and I added the USB device address for my Avocent KVM DSRIQ USB module, you can do the same for a physical keyboard and mouse):
+
=== GPU Seabios PCI EXPRESS PASSTHROUGH ===
 
<pre>
 
<pre>
−
hostpci0: 05:00,x-vga=on,pcie=1
 
 
machine: q35
 
machine: q35
−
usb0: host=0624:0307
+
hostpci0: 01:00,pcie=1,x-vga=on
 +
</pre>
 +
 
 +
=== How to known if card is UEFI (ovmf) compatible ===
 +
 
 +
Get and compile the software "rom-parser"
 +
<pre>
 +
$ git clone https://github.com/awilliam/rom-parser
 +
$ cd rom-parser
 +
$ make
 
</pre>
 
</pre>
  
 +
Then dump the rom of you vga card
 +
<pre>
 +
 +
# cd /sys/bus/pci/devices/0000:01:00.0/
 +
# echo 1 > rom
 +
# cat rom > /tmp/image.rom
 +
# echo 0 > rom
 +
</pre>
 +
 +
and test it with
 +
<pre>
 +
./rom-parser /tmp/image.rom
 +
 +
Valid ROM signature found @0h, PCIR offset 190h
 +
PCIR: type 0, vendor: 10de, device: 1280, class: 030000
 +
PCIR: revision 0, vendor revision: 1
 +
Valid ROM signature found @f400h, PCIR offset 1ch
 +
PCIR: type 3, vendor: 10de, device: 1280, class: 030000
 +
PCIR: revision 3, vendor revision: 0
 +
  EFI: Signature Valid
 +
Last image
 +
</pre>
 +
 +
To be UEFI compatible, you need a "type 3" in the result.
 +
 +
=== Nvidia tips ===
 +
 +
Some applications like geforce experience, Passmark Performance Test and SiSoftware Sandra crash can crash the vm.
 +
you need to add:
 +
<pre>
 +
echo "options kvm ignore_msrs=1" > /etc/modprobe.d/kvm.conf
 +
</pre>
 +
 +
User have reported that Nvidia Kepler K80 need this in vmid.conf
 +
<pre>
 +
args: -machine pc,max-ram-below-4g=1G
 +
</pre>
 +
 +
 +
=== romfile ===
 +
http://lime-technology.com/forum/index.php?topic=43644.msg482110#msg482110
 +
 +
Some motherboard can't gpu passthrough on the first pci slot by default because its vbios is shadowed during bootup.  So we need to capture its bios when its working "normally" then when we move the card to slot 1 we can start the vm using the dumped vbios.
 +
 +
to dump the bios
 +
 +
<pre>
 +
cd /sys/bus/pci/devices/0000:01:00.0/
 +
echo 1 > rom
 +
cat rom > /usr/share/kvm/vbios.bin
 +
echo 0 > rom
 +
</pre>
 +
 +
then you can pass the vbios file (must be located in /usr/share/kvm/) with
 +
<pre>
 +
hostpci0: 01:00,x-vga=on,romfile=vbios.bin
 +
</pre>
 +
 +
(romfile option is available in proxmox since january 2017)
 +
 +
=== BAR 3: can't reserve [mem] error ===
 +
 +
If you have this error when try to use the card used by the host
 +
 +
<pre>
 +
vfio-pci 0000:04:00.0: BAR 3: can't reserve [mem 0xca000000-0xcbffffff 64bit]
 +
</pre>
 +
 +
you can try to add to grub kernel option:
 +
<pre>
 +
video=efifb:off
 +
</pre>
 +
 +
==  Troubleshooting ==
 +
 +
=== SPICE ===
 +
 +
Spice may give trouble when passing through a GPU as it presents a "virtual" PCI graphic card to the guest and some drivers have problems with that even when both cards show up.
 +
It's always worth a try to disable SPICE and check again if something fails.
 +
 +
== Verify Operation ==
 +
 +
Start the VM from the UI.
 +
 +
Enter the qm monitor. &nbsp;"qm monitor vmnumber"
 +
 +
Verify that your card is listed here: "info pci"
 +
 +
Then install drivers on your guest OS. &nbsp;
 +
 +
NOTE: Card support might be limited to 2 or 3 devices.
 +
 +
NOTE: This process will remove the card from the proxmox host OS. &nbsp;
 +
 +
Editorial Note:  Using PCI passthrough to present drives direct to a ZFS (FreeNAS, Openfiler, OmniOS) virtual machine is OK for testing, but '''not recommended''' for production use.  Specific FreeNAS warnings can be found here:  http://forums.freenas.org/threads/absolutely-must-virtualize-freenas-a-guide-to-not-completely-losing-your-data.12714/
 +
 +
 +
== USB PASSTHROUGH ==
 +
if you need to passthrough usb devices (keyboard,mouse),
 +
please follow this wiki:
 +
 +
https://pve.proxmox.com/wiki/USB_physical_port_mapping
 
[[Category:HOWTO]]
 
[[Category:HOWTO]]

Revision as of 14:46, 9 January 2017

Introduction

PCI passthrough allows you to use a physical PCI device (graphics card, network card) inside a VM (KVM virtualization only). If you "PCI passthrough" a device, the device is not available to the host anymore.

Note:

PCI passthrough is an experimental feature in Proxmox VE

Intel CPU


edit: 

#vi /etc/default/grub

change 

GRUB_CMDLINE_LINUX_DEFAULT="quiet"

to 

GRUB_CMDLINE_LINUX_DEFAULT="quiet intel_iommu=on"

then 

# update-grub


Then run "dmesg | grep -e DMAR -e IOMMU" from the command line.  If there is no output, then something is wrong.

AMD CPU

Edit: 

# vi /etc/default/grub

Change: 

GRUB_CMDLINE_LINUX_DEFAULT="quiet"

To: 

GRUB_CMDLINE_LINUX_DEFAULT="quiet amd_iommu=on"


Required modules

add to /etc/modules 

vfio
vfio_iommu_type1
vfio_pci
vfio_virqfd

IOMMU interrupt remapping

it will not be possible to use PCI passthrough without interrupt remapping.

Device assignment will fail with a 'Failed to assign device "[device name]" : Operation not permitted' error for users of KVM, and a 'Interrupt Remapping hardware not found, passing devices to unprivileged domains is insecure.

Systems which don't support interrupt remapping:


  • All systems using an AMD processor and chipset that have AMD I/O Virtualization (AMD-Vi) support. Such hardware has interrupt remapping support; however, the software support is not yet available upstream.
  • All systems using an Intel processor and chipset that have support for Intel Virtualization Technology for Directed I/O (VT-d), but do not have support for interrupt remapping. Interrupt remapping support is provided in newer processors and chipsets. To identify if your system has support for interrupt remapping:

1) Run the "dmesg | grep ecap" command.

2) On the IOMMU lines, the hexadecimal value after "ecap" indicates whether interrupt remapping is supported. If the last character of this value is an 8, 9, a, b, c, d, e, or an f, interrupt remapping is supported. For example, "ecap 1000" indicates there is no interrupt remapping support. "ecap 10207f" indicates interrupt remapping support, as the last character is an "f".

Interrupt remapping will only be enabled if every IOMMU supports it.

Alternatively, run the following script to determine if your system has interrupt remapping support: 

#!/bin/sh
if [ $(dmesg | grep ecap | wc -l) -eq 0 ]; then
  echo "No interrupt remapping support found"
  exit 1
fi

for i in $(dmesg | grep ecap | awk '{print $NF}'); do
  if [ $(( (0x$i & 0xf) >> 3 )) -ne 1 ]; then
    echo "Interrupt remapping not supported"
    exit 1
  fi
done

If your system doesn't support interrupt remapping,

you can allow unsafe interrupts with: 

echo "options vfio_iommu_type1 allow_unsafe_interrupts=1" > /etc/modprobe.d/iommu_unsafe_interrupts.conf

Verify IOMMU isolation

To have pci passthrough working fine, you need dedicated iommu group for your pci devices

You should have something like 

# find /sys/kernel/iommu_groups/ -type l
/sys/kernel/iommu_groups/0/devices/0000:00:00.0
/sys/kernel/iommu_groups/1/devices/0000:00:01.0
/sys/kernel/iommu_groups/1/devices/0000:01:00.0
/sys/kernel/iommu_groups/1/devices/0000:01:00.1
/sys/kernel/iommu_groups/2/devices/0000:00:02.0
/sys/kernel/iommu_groups/3/devices/0000:00:16.0
/sys/kernel/iommu_groups/4/devices/0000:00:1a.0
/sys/kernel/iommu_groups/5/devices/0000:00:1b.0
/sys/kernel/iommu_groups/6/devices/0000:00:1c.0
/sys/kernel/iommu_groups/7/devices/0000:00:1c.5
/sys/kernel/iommu_groups/8/devices/0000:00:1c.6
/sys/kernel/iommu_groups/9/devices/0000:00:1c.7
/sys/kernel/iommu_groups/9/devices/0000:05:00.0
/sys/kernel/iommu_groups/10/devices/0000:00:1d.0
/sys/kernel/iommu_groups/11/devices/0000:00:1f.0
/sys/kernel/iommu_groups/11/devices/0000:00:1f.2
/sys/kernel/iommu_groups/11/devices/0000:00:1f.3
/sys/kernel/iommu_groups/12/devices/0000:02:00.0
/sys/kernel/iommu_groups/12/devices/0000:02:00.1
/sys/kernel/iommu_groups/13/devices/0000:03:00.0
/sys/kernel/iommu_groups/14/devices/0000:04:00.0


To have separate iommu, your processor need to have support for a feature called ACS (Access Control Services).

All Xeon processor support them (E3,E5) excluding Xeon E3-1200

For intel Core , it's different, only some processors support ACS 

Haswell-E (LGA2011-v3)
i7-5960X (8-core, 3/3.5GHz)
i7-5930K (6-core, 3.2/3.8GHz)
i7-5820K (6-core, 3.3/3.6GHz)

Ivy Bridge-E (LGA2011)
i7-4960X (6-core, 3.6/4GHz)
i7-4930K (6-core, 3.4/3.6GHz)
i7-4820K (4-core, 3.7/3.9GHz)

Sandy Bridge-E (LGA2011)
i7-3960X (6-core, 3.3/3.9GHz)
i7-3970X (6-core, 3.5/4GHz)
i7-3930K (6-core, 3.2/3.8GHz)
i7-3820 (4-core, 3.6/3.8GHz)

UPDATE ME : AMD processors ?

If you don't have dedicated iommu, your can try :


1) move the card to another pci slot

2) add "pcie_acs_override=downstream" to grub options, which can help on some setup with bad ACS implementation.


More infos :

http://vfio.blogspot.be/2015/10/intel-processors-with-acs-support.html

http://vfio.blogspot.be/2014/08/iommu-groups-inside-and-out.html


Determine your PCI card address, and configure your VM

Locate your card using "lspci".  The address should be in the form of: 01:00.0

Manually edit the node.conf file.  It can be located at: /etc/pve/qemu-server/vmid.conf.

Add this line to the end of the file: 

hostpci0: 01:00.0

If you have a multi-function device (like a vga card with embedded audio chipset),

you can pass all functions manually with 

hostpci0: 01:00.0;01:00.1

or

to pass all functions automatically 

hostpci0: 01:00

PCI EXPRESS PASSTHROUGH

/etc/pve/qemu-server/<vmid>.conf

simple pci-express passthrough 

machine: q35
hostpci0: 01:00.0,pcie=1

GPU PASSTHROUGH

  • MD RADEON 5xxx, 6xxx, 7xxx and NVIDIA GEFORCE 7, 8, 4xx, 5xx, 6xx, 7xx have been reported working.
  • Maybe you'll need to load some specific options in grub.cfg or other tuning values,
  • Here a good forum thread of archlinux: https://bbs.archlinux.org/viewtopic.php?id=162768

For GPU, it's good that host don't try to use the GPU, and avoids issues with the host driver unbinding and re-binding to the device.

First, find the device and vendor id of your vga card 

$ lspci -n -s 01:00
01:00.0 0300: 10de:1381 (rev a2)
01:00.1 0403: 10de:0fbc (rev a1)

The Vendor:Device IDs for my GPU and audio functions are therefore 10de:1381, 10de:0fbc.

Then, create a file 

echo "options vfio-pci ids=10de:1381,10de:0fbc" > /etc/modprobe.d/vfio.conf

Then blacklist drivers 

echo "blacklist radeon" >> /etc/modprobe.d/blacklist.conf 
echo "blacklist nouveau" >> /etc/modprobe.d/blacklist.conf 
echo "blacklist nvidia" >> /etc/modprobe.d/blacklist.conf

For VM configuration, They are 4 configuration possible:

GPU OVMF PCI PASSTHROUGH (recommended)

OVMF replace bios by UEFI boot. You need to install your guest OS with uefi support, (for windows, try win >=8)

using OVMF, you can also add disable_vga=1 to vfio-pci module, which try to to opt-out devices from vga arbitration if possible. 

echo "options vfio-pci ids=10de:1381,10de:0fbc disable_vga=1" > /etc/modprobe.d/vfio.conf

and you need to your graphic card have a uefi bootable rom http://vfio.blogspot.fr/2014/08/does-my-graphics-card-rom-support-efi.html 

bios: ovmf
scsihw: virtio-scsi-pci
bootdisk: scsi0
scsi0: .....
hostpci0: 01:00,x-vga=on

GPU OVMF PCI EXPRESS PASSTHROUGH

OVMF replace bios by UEFI boot.

You need to install your guest OS with uefi support, (for windows, try win >=8)

and you need to your graphic card have a uefi bootable rom http://vfio.blogspot.fr/2014/08/does-my-graphics-card-rom-support-efi.html 

bios: ovmf
scsihw: virtio-scsi-pci
bootdisk: scsi0
scsi0: .....
machine: q35
hostpci0: 01:00,pcie=1,x-vga=on

GPU Seabios PCI PASSTHROUGH

hostpci0: 01:00,x-vga=on

GPU Seabios PCI EXPRESS PASSTHROUGH

machine: q35
hostpci0: 01:00,pcie=1,x-vga=on

How to known if card is UEFI (ovmf) compatible

Get and compile the software "rom-parser" 

$ git clone https://github.com/awilliam/rom-parser
$ cd rom-parser
$ make

Then dump the rom of you vga card 


# cd /sys/bus/pci/devices/0000:01:00.0/
# echo 1 > rom
# cat rom > /tmp/image.rom
# echo 0 > rom

and test it with 

./rom-parser /tmp/image.rom

Valid ROM signature found @0h, PCIR offset 190h
 PCIR: type 0, vendor: 10de, device: 1280, class: 030000
 PCIR: revision 0, vendor revision: 1
Valid ROM signature found @f400h, PCIR offset 1ch
 PCIR: type 3, vendor: 10de, device: 1280, class: 030000
 PCIR: revision 3, vendor revision: 0
  EFI: Signature Valid
 Last image

To be UEFI compatible, you need a "type 3" in the result.

Nvidia tips

Some applications like geforce experience, Passmark Performance Test and SiSoftware Sandra crash can crash the vm. you need to add: 

echo "options kvm ignore_msrs=1" > /etc/modprobe.d/kvm.conf

User have reported that Nvidia Kepler K80 need this in vmid.conf 

args: -machine pc,max-ram-below-4g=1G


romfile

http://lime-technology.com/forum/index.php?topic=43644.msg482110#msg482110

Some motherboard can't gpu passthrough on the first pci slot by default because its vbios is shadowed during bootup. So we need to capture its bios when its working "normally" then when we move the card to slot 1 we can start the vm using the dumped vbios.

to dump the bios 

cd /sys/bus/pci/devices/0000:01:00.0/
echo 1 > rom
cat rom > /usr/share/kvm/vbios.bin
echo 0 > rom

then you can pass the vbios file (must be located in /usr/share/kvm/) with 

hostpci0: 01:00,x-vga=on,romfile=vbios.bin

(romfile option is available in proxmox since january 2017)

BAR 3: can't reserve [mem] error

If you have this error when try to use the card used by the host 

vfio-pci 0000:04:00.0: BAR 3: can't reserve [mem 0xca000000-0xcbffffff 64bit]

you can try to add to grub kernel option: 

video=efifb:off

Troubleshooting

SPICE

Spice may give trouble when passing through a GPU as it presents a "virtual" PCI graphic card to the guest and some drivers have problems with that even when both cards show up. It's always worth a try to disable SPICE and check again if something fails.

Verify Operation

Start the VM from the UI.

Enter the qm monitor.  "qm monitor vmnumber"

Verify that your card is listed here: "info pci"

Then install drivers on your guest OS.  

NOTE: Card support might be limited to 2 or 3 devices.

NOTE: This process will remove the card from the proxmox host OS.  

Editorial Note: Using PCI passthrough to present drives direct to a ZFS (FreeNAS, Openfiler, OmniOS) virtual machine is OK for testing, but not recommended for production use. Specific FreeNAS warnings can be found here: http://forums.freenas.org/threads/absolutely-must-virtualize-freenas-a-guide-to-not-completely-losing-your-data.12714/


USB PASSTHROUGH

if you need to passthrough usb devices (keyboard,mouse), please follow this wiki:

https://pve.proxmox.com/wiki/USB_physical_port_mapping

Retrieved from "https://pve.proxmox.com/mediawiki/index.php?title=PCI_Passthrough&oldid=9629"