[libvirt] [RFC v2] libvirt vGPU QEMU integration

[Alex Williamson]

On Mon, 19 Sep 2016 23:50:56 +0200
Paolo Bonzini <pbonzini at redhat.com> wrote:

> On 19/09/2016 23:36, Alex Williamson wrote:
> > On Tue, 20 Sep 2016 02:05:52 +0530
> > Kirti Wankhede <kwankhede at nvidia.com> wrote:  
> >> 'fb_length':
> >>     Read-only file. Mandatory.
> >>     Returns <number>{K,M,G}, size of framebuffer.  
> > 
> > This can't be mandatory, it's only relevant to vGPU devices, vGPUs are
> > just one user of mediated devices. [...]
> >   
> >> 'params'
> >>     Write-Only file. Optional.
> >>     String input. Libvirt would pass the string given in XML file to
> >> this file and then create mdev device. Set empty string to clear params.
> >> For example, set parameter 'frame_rate_limiter=0' to disable frame rate
> >> limiter for performance benchmarking, then create device of type 11. The
> >> device created would have that parameter set by vendor driver.  
> > 
> > Might as well just call it "magic", there's absolutely no ability to
> > introspect what parameters are allowed or even valid here.  Can all
> > parameters be changed dynamically?  Do parameter changes apply to
> > existing devices or only future devices?  This is a poorly specified
> > interface.  I'd prefer this be done via module options on the vendor
> > driver.  
> 
> Or additional files in the mdev's sysfs directory?

Sure, the vendor driver could certainly support that, it'd be vendor
specific of course.
 
> >> The parent device would look like:
> >>
> >>    <device>
> >>      <name>pci_0000_86_00_0</name>
> >>      <capability type='pci'>
> >>        <domain>0</domain>
> >>        <bus>134</bus>
> >>        <slot>0</slot>
> >>        <function>0</function>  
> > 
> > This is the parent device address?  
> 
> (Since this is taken from an email of mine, this is libvirt's XML
> interpretation of the udev database and the contents of sysfs.  Try
> "virsh nodedev-dumpxml pci_0000_00_02_0" for an example that is
> unrelated to mdev).
> 
> >> 2. Create/destroy mediated device
> >>
> >> With above example, vGPU device XML would look like:
> >>
> >>    <device>
> >>      <name>my-vgpu</name>
> >>      <parent>pci_0000_86_00_0</parent>
> >>      <capability type='mdev'>
> >>        <type id='11'/>
> >>        <group>1</group>
> >>        <params>'frame_rate_limiter=0'</params>
> >>      </capability>
> >>    </device>
> >>
> >> 'type id' is mandatory.  
> > 
> > I was under the impression that the vendor supplied "name" was the one
> > unique identifier.  We're certainly not going to create a registrar to
> > hand out type ids to each vendor, so what makes type id unique?  
> 
> Why does it have to be unique?  It's just parroting what libvirt said in
> the <capability type='mdev'> block of the parent's nodedev-dumpxml.
> 
> (Though I guess going by name could be useful as well.  Perhaps both
> could be allowed).

Do we not want to be able to migrate a VM to another host and have the
XML mean something?  Off-line or on-line, mdev device may support
migration.  Thanks,

Alex