From: Knut Omang <knut.omang@oracle.com>
To: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>,
"Michael S. Tsirkin" <mst@redhat.com>
Cc: Stefan Hajnoczi <stefanha@gmail.com>,
Elijah Shakkour <elijahs@mellanox.com>,
"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
Tal Attaly <talat@mellanox.com>
Subject: Re: [Qemu-devel] Question: SRIOV support over Win Hyper-V VM running in QEMU process on Linux host
Date: Thu, 26 Jul 2018 19:25:46 +0200 [thread overview]
Message-ID: <1532625946.2458.187.camel@oracle.com> (raw)
In-Reply-To: <9e3bedbf-e6a7-61ae-babd-79a9ec13da24@gmail.com>
On Thu, 2018-07-26 at 20:05 +0300, Marcel Apfelbaum wrote:
>
> On 07/26/2018 07:42 PM, Knut Omang wrote:
> > On Thu, 2018-07-26 at 19:41 +0300, Michael S. Tsirkin wrote:
> > > On Thu, Jul 26, 2018 at 06:38:32PM +0200, Knut Omang wrote:
> > > > On Thu, 2018-07-26 at 18:51 +0300, Marcel Apfelbaum wrote:
> > > > > Hi
> > > > >
> > > > > On 07/26/2018 05:52 PM, Stefan Hajnoczi wrote:
> > > > > > On Thu, Jul 12, 2018 at 07:33:14AM +0000, Elijah Shakkour wrote:
> > > > > > > Hey,
> > > > > > >
> > > > > > > Our team is adding a NIC functional emulation to QEMU.
> > > > > > > One of the features we are adding to this NIC is SRIOV.
> > > > > > >
> > > > > > > Here is the error message I get when checking SRIOV support
> > > > > > > of our
> > > > > > > emulated NIC on Win2016 server (the hyper-v VM).
> > > > > > > "
> > > > > > > SR-IOV cannot be used on this system as the PCI Express hardware
> > > > > > > does
> > > > > > > not
> > > > > > > support Access Control Services (ACS) at any root port.
> > > > >
> > > > > QEMU's emulated PCI Express Root Ports do not support ACS yet, however
> > > > > I
> > > > > am not sure ACS is a prerequisite
> > > > > for SR-IOV. We would need ARI support for allowing more than 8VFs, but
> > > > > QEMU doesn't support that either (yet).
> > > > >
> > > > > Knut Omag has some working patches, he successfully implemented SR-IOV
> > > > > with QEMU, see:
> > > > > https://github.com/knuto/qemu/tree/sriov_patches_v7
> > > > >
> > > > > The code was not merged since we need at least a device with SR-IOV
> > > > > support to justify the addition.
> > > >
> > > > FYI, I recently rebased these to latest master but just didn't get to
> > > > push
> > > > them
> > > > out. I did just now - they are available here:
> > > >
> > > > https://github.com/knuto/qemu/tree/sriov_patches_v8
> > > >
> > > > As far as I know ARI support with my patch set works just fine - I have
> > > > tested
> > > > it with lots of VFs.
> > > >
> > > > One of the patches in the series (pci: Make use of the devfn property
> > > > when
> > > > registering new devices) is necessary to make ARI work as it should with
> > > > SR/IOV.
> > > >
> > > > For the hardware model I developed the SR/IOV patches for, I also added
> > > > enough
> > > > ACS support in the root port (PCIe capability helper patch + usage in
> > > > ioh3420) to make VFIO "happy". I haven't submitted them because they
> > > > are "questionable" since they likely do not reflect the actual features
> > > > of
> > > > the
> > > > ioh3420.
> > >
> > > In that the actual ioh3420 doesn't support ACS?
> >
> > yes.. I don't have one so I don't know but that was my assumption..
>
> Hi Knut,
>
> We have now a generic PCIe Root Port we can add whatever we want to it.
> See please hw/pci-bridge/gen_pcie_root_port.c.
Ok, I see! - I wasn't aware of that. I was thinking more in terms of just
emulating a slightly newer Intel root port but never got around to that.
> So your patches add both ARI and ACS support, nice!
> Maybe it worth merging at least these features.
I'll have a look at the generic root port, it is probably a natural extension
for v9 of the sriov patch set :-)
Thanks,
Knut
>
> Thanks,
> Marcel
>
> >
> > Knut
> >
> > > > I can make those available if interesting.
> > > >
> > > > Thanks,
> > > > Knut
> > > >
> > > > > > > Contact your system vendor for further information.
> > > > > > > "
> > > > > >
> > > > > > I'm not sure what the status of emulated SR-IOV is so I have CCed
> > > > > > Michael Tsirkin and Marcel Apfelbaum, the PCI maintainers in QEMU.
> > > > >
> > > > > Thanks,
> > > > > Marcel
> > > > >
> > > > > > > Could you please advise about what could be the issue here?
> > > > > > >
> > > > > > > BTW: I use same configuration (VM XML file attached) when running
> > > > > > > linux VM
> > > > > > > (RH7.2) image (instead of Win Hyper-V) over the same host and
> > > > > > > SRIOV is
> > > > > > > working for me there.
> > > > > > >
> > > > > > > Here the XML file I use to define the VM (our emulated NIC is
> > > > > > > added at
> > > > > > > the
> > > > > > > end of XML):
> > > > > > > "
> > > > > > > <domain type='kvm' xmlns:qemu='http://libvirt.org/schemas/domain/q
> > > > > > > emu/
> > > > > > > 1.0'
> > > > > > > > ;
> > > > > > >
> > > > > > > <name>nst105</name>
> > > > > > > <uuid>0249a525-2ee2-432b-a1f5-a6db83b089a3</uuid>
> > > > > > > <memory unit='KiB'>8388608</memory>
> > > > > > > <currentMemory unit='KiB'>8388608</currentMemory>
> > > > > > > <vcpu placement='static'>8</vcpu>
> > > > > > > <resource>
> > > > > > > <partition>/machine</partition>
> > > > > > > </resource>
> > > > > > > <os>
> > > > > > > <type arch='x86_64' machine='pc-q35-2.11'>hvm</type>
> > > > > > > </os>
> > > > > > > <features>
> > > > > > > <acpi/>
> > > > > > > <apic/>
> > > > > > > <hyperv>
> > > > > > > <relaxed state='on'/>
> > > > > > > <vapic state='on'/>
> > > > > > > <spinlocks state='on' retries='8191'/>
> > > > > > > </hyperv>
> > > > > > > </features>
> > > > > > > <cpu mode='custom' match='exact' check='none'>
> > > > > > > <model fallback='forbid'>SandyBridge</model>
> > > > > > > <feature policy='require' name='hypervisor'/>
> > > > > > > <feature policy='require' name='vmx'/>
> > > > > > > </cpu>
> > > > > > > <clock offset='localtime'>
> > > > > > > <timer name='rtc' tickpolicy='catchup'/>
> > > > > > > <timer name='pit' tickpolicy='delay'/>
> > > > > > > <timer name='hpet' present='no'/>
> > > > > > > <timer name='hypervclock' present='yes'/>
> > > > > > > </clock>
> > > > > > > <on_poweroff>destroy</on_poweroff>
> > > > > > > <on_reboot>restart</on_reboot>
> > > > > > > <on_crash>destroy</on_crash>
> > > > > > > <pm>
> > > > > > > <suspend-to-mem enabled='no'/>
> > > > > > > <suspend-to-disk enabled='no'/>
> > > > > > > </pm>
> > > > > > > <devices>
> > > > > > > <emulator>/opt/qemu/bin/qemu-system-x86_64</emulator>
> > > > > > > <disk type='file' device='disk'>
> > > > > > > <driver name='qemu' type='qcow2'/>
> > > > > > > <source file='/images/nst105.qcow2'/>
> > > > > > > <target dev='sda' bus='sata'/>
> > > > > > > <boot order='2'/>
> > > > > > > <address type='drive' controller='0' bus='0' target='0'
> > > > > > > unit='0'/>
> > > > > > > </disk>
> > > > > > > <controller type='usb' index='0' model='ich9-ehci1'>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x1d'
> > > > > > > function='0x7'/>
> > > > > > > </controller>
> > > > > > > <controller type='usb' index='0' model='ich9-uhci1'>
> > > > > > > <master startport='0'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x1d'
> > > > > > > function='0x0' multifunction='on'/>
> > > > > > > </controller>
> > > > > > > <controller type='usb' index='0' model='ich9-uhci2'>
> > > > > > > <master startport='2'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x1d'
> > > > > > > function='0x1'/>
> > > > > > > </controller>
> > > > > > > <controller type='usb' index='0' model='ich9-uhci3'>
> > > > > > > <master startport='4'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x1d'
> > > > > > > function='0x2'/>
> > > > > > > </controller>
> > > > > > > <controller type='sata' index='0'>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x1f'
> > > > > > > function='0x2'/>
> > > > > > > </controller>
> > > > > > > <controller type='pci' index='0' model='pcie-root'/>
> > > > > > > <controller type='pci' index='1' model='pcie-root-port'>
> > > > > > > <model name='pcie-root-port'/>
> > > > > > > <target chassis='1' port='0x10'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x02'
> > > > > > > function='0x0' multifunction='on'/>
> > > > > > > </controller>
> > > > > > > <controller type='pci' index='2' model='pcie-root-port'>
> > > > > > > <model name='pcie-root-port'/>
> > > > > > > <target chassis='2' port='0x11'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x02'
> > > > > > > function='0x1'/>
> > > > > > > </controller>
> > > > > > > <controller type='pci' index='3' model='pcie-root-port'>
> > > > > > > <model name='pcie-root-port'/>
> > > > > > > <target chassis='3' port='0x12'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x02'
> > > > > > > function='0x2'/>
> > > > > > > </controller>
> > > > > > > <controller type='pci' index='4' model='dmi-to-pci-bridge'>
> > > > > > > <model name='i82801b11-bridge'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x1e'
> > > > > > > function='0x0'/>
> > > > > > > </controller>
> > > > > > > <controller type='pci' index='5' model='pci-bridge'>
> > > > > > > <model name='pci-bridge'/>
> > > > > > > <target chassisNr='5'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x04' slot='0x00'
> > > > > > > function='0x0'/>
> > > > > > > </controller>
> > > > > > > <interface type='bridge'>
> > > > > > > <mac address='00:50:56:1b:dd:6f'/>
> > > > > > > <source bridge='br0'/>
> > > > > > > <model type='virtio'/>
> > > > > > > <boot order='1'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x01' slot='0x00'
> > > > > > > function='0x0'/>
> > > > > > > </interface>
> > > > > > > <serial type='pty'>
> > > > > > > <target port='0'/>
> > > > > > > </serial>
> > > > > > > <console type='pty'>
> > > > > > > <target type='serial' port='0'/>
> > > > > > > </console>
> > > > > > > <input type='tablet' bus='usb'>
> > > > > > > <address type='usb' bus='0' port='1'/>
> > > > > > > </input>
> > > > > > > <input type='mouse' bus='ps2'/>
> > > > > > > <input type='keyboard' bus='ps2'/>
> > > > > > > <graphics type='vnc' port='-1' autoport='yes'
> > > > > > > listen='127.0.0.1'
> > > > > > > keymap='en-us'>
> > > > > > > <listen type='address' address='127.0.0.1'/>
> > > > > > > </graphics>
> > > > > > > <video>
> > > > > > > <model type='vga' vram='16384' heads='1' primary='yes'/>
> > > > > > > <address type='pci' domain='0x0000' bus='0x00' slot='0x01'
> > > > > > > function='0x0'/>
> > > > > > > </video>
> > > > > > > <memballoon model='virtio'>
> > > > > > > <address type='pci' domain='0x0000' bus='0x02' slot='0x00'
> > > > > > > function='0x0'/>
> > > > > > > </memballoon>
> > > > > > > </devices>
> > > > > > > <seclabel type='none' model='none'/>
> > > > > > > <seclabel type='dynamic' model='dac' relabel='yes'/>
> > > > > > > <qemu:commandline>
> > > > > > > <qemu:arg value='-device'/>
> > > > > > > <qemu:arg value='pcie-root-port,pref64-
> > > > > > > reserve=500M,slot=0,id=pcie_port.1'/>
> > > > > > > <qemu:arg value='-netdev'/>
> > > > > > > <qemu:arg
> > > > > > > value='tap,id=tap5,ifname=tap5,script=no,downscript=no'/>
> > > > > > > <qemu:arg value='-device'/>
> > > > > > > <qemu:arg value='my_emu_nic,netdev=tap5,bus=pcie_port.1'/>
> > > > > > > </qemu:commandline>
> > > > > > > </domain>
> > > > > > > "
> > > > > > > ______________________
> > > > > > > General info:
> > > > > > > Host OS: RH7.0 (Kernel: 4.14.13)
> > > > > > > QEMU version: 2.11
> > > > > > > libvirt version: 3.2.0
> > > > > > > Running the following on the host shows that both nested and IOMMU
> > > > > > > are
> > > > > > > enabled:
> > > > > > > ~]#: cat /sys/module/kvm_intel/parameters/nested
> > > > > > > Y
> > > > > > > ~]# dmesg | grep -e DMAR -e IOMMU
> > > > > > > [ 0.000000] DMAR: IOMMU enabled
> > > > > > >
> > > > > > > Thanks,
> > > > > > > Elijah
> > > > > > >
>
>
next prev parent reply other threads:[~2018-07-26 17:30 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <DB5PR05MB11605C65D7D734C9354F0421D54F0@DB5PR05MB1160.eurprd05.prod.outlook.com>
[not found] ` <1407239306.11199051.1530240887935.JavaMail.zimbra@redhat.com>
[not found] ` <20180705194311-mutt-send-email-mst@kernel.org>
[not found] ` <DB5PR05MB1160D84E747DA480435B6605D5440@DB5PR05MB1160.eurprd05.prod.outlook.com>
[not found] ` <DB5PR05MB1160BB381473C723C8336EC2D55A0@DB5PR05MB1160.eurprd05.prod.outlook.com>
[not found] ` <AM5PR0501MB2499CB4F2D01BCDA47C0ACB6C95A0@AM5PR0501MB2499.eurprd05.prod.outlook.com>
2018-07-12 7:33 ` [Qemu-devel] Question: SRIOV support over Win Hyper-V VM running in QEMU process on Linux host Elijah Shakkour
2018-07-26 14:52 ` Stefan Hajnoczi
2018-07-26 15:51 ` Marcel Apfelbaum
2018-07-26 16:14 ` Michael S. Tsirkin
2018-07-26 16:34 ` Marcel Apfelbaum
2018-07-26 16:38 ` Michael S. Tsirkin
2018-07-26 16:42 ` Alex Williamson
2018-07-26 17:11 ` Michael S. Tsirkin
2018-07-26 17:22 ` Knut Omang
2018-07-26 17:22 ` Alex Williamson
2018-07-26 16:38 ` Knut Omang
2018-07-26 16:41 ` Michael S. Tsirkin
2018-07-26 16:42 ` Knut Omang
2018-07-26 17:05 ` Marcel Apfelbaum
2018-07-26 17:25 ` Knut Omang [this message]
2018-07-26 17:27 ` Knut Omang
2018-07-26 17:28 ` Michael S. Tsirkin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1532625946.2458.187.camel@oracle.com \
--to=knut.omang@oracle.com \
--cc=elijahs@mellanox.com \
--cc=marcel.apfelbaum@gmail.com \
--cc=mst@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@gmail.com \
--cc=talat@mellanox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.