[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [RFC PATCH] vfio: Add sysfsdev property for pci & platf
From: |
Alex Williamson |
Subject: |
Re: [Qemu-devel] [RFC PATCH] vfio: Add sysfsdev property for pci & platform |
Date: |
Thu, 21 Jan 2016 08:14:54 -0700 |
On Thu, 2016-01-21 at 07:51 +0000, Tian, Kevin wrote:
> > From: Alex Williamson [mailto:address@hidden
> > Sent: Thursday, January 21, 2016 2:07 AM
> >
> > vfio-pci currently requires a host= parameter, which comes in the
> > form of a PCI address in [domain:] notation. We
> > expect to find a matching entry in sysfs for that under
> > /sys/bus/pci/devices/. vfio-platform takes a similar approach, but
> > defines the host= parameter to be a string, which can be matched
> > directly under /sys/bus/platform/devices/. On the PCI side, we have
> > some interest in using vfio to expose vGPU devices. These are not
> > actual discrete PCI devices, so they don't have a compatible host PCI
> > bus address or a device link where QEMU wants to look for it. There's
> > also really no requirement that vfio can only be used to expose
> > physical devices, a new vfio bus and iommu driver could expose a
> > completely emulated device. To fit within the vfio framework, it
> > would need a kernel struct device and associated IOMMU group, but
> > those are easy constraints to manage.
> >
> > To support such devices, which would include vGPUs, that honor the
> > VFIO PCI programming API, but are not necessarily backed by a unique
> > PCI address, add support for specifying any device in sysfs. The
> > vfio API already has support for probing the device type to ensure
> > compatibility with either vfio-pci or vfio-platform.
> >
> > With this, a vfio-pci device could either be specified as:
> >
> > -device vfio-pci,host=02:00.0
> >
> > or
> >
> > -device vfio-pci,sysfsdev=/sys/devices/pci0000:00/0000:00:1c.0/0000:02:00.0
> >
> > or even
> >
> > -device vfio-pci,sysfsdev=/sys/bus/pci/devices/0000:02:00.0
> >
> > When vGPU support comes along, this might look something more like:
> >
> > -device
> > vfio-pci,sysfsdev=/sys/devices/virtual/intel-vgpu/address@hidden:00:02.0
> >
> > NB - This is only a made up example path, but it should be noted that
> > the device namespace is global for vfio, a virtual device cannot
> > overlap with existing namespaces and should not create a name prone to
> > conflict, such as a simple instance number.
> >
>
> Thanks Alex! It's a good improvement to support coming vgpu feature.
> Just curious. Does the virtual device name has to include a BDF format
> or it can be random strings (e.g. just "vgpu0")? In the latter case, then
> overlapping chance would be small.
Hi Kevin,
Yeah, looking at the vfio code again (vfio_device_get_from_name), as
long as the name is unique within the IOMMU group, I think we'll be
fine. I expect that vGPUs will create singleton groups, so the
namespace constraints I mention above are maybe not a concern. For
vendors that can support multiple GPUs, each with vGPUs, userspace will
probably want some way to determine the source of a vGPU for load
balancing and locality purpose, but that's better handled through
parent/child device links in sysfs rather than embedding it in the
device name. Thanks,
Alex