[Intel-gfx] [PATCH v12 24/24] docs: vfio: Add vfio device cdev description

[Alex Williamson]

On Tue, 13 Jun 2023 12:01:51 +0000
"Liu, Yi L" <yi.l.liu at intel.com> wrote:

> > From: Alex Williamson <alex.williamson at redhat.com>
> > Sent: Tuesday, June 13, 2023 7:06 AM
> > 
> > On Fri,  2 Jun 2023 05:16:53 -0700
> > Yi Liu <yi.l.liu at intel.com> wrote:
> >   
> > > This gives notes for userspace applications on device cdev usage.
> > >
> > > Reviewed-by: Kevin Tian <kevin.tian at intel.com>
> > > Signed-off-by: Yi Liu <yi.l.liu at intel.com>
> > > ---
> > >  Documentation/driver-api/vfio.rst | 132 ++++++++++++++++++++++++++++++
> > >  1 file changed, 132 insertions(+)
> > >
> > > diff --git a/Documentation/driver-api/vfio.rst b/Documentation/driver-api/vfio.rst
> > > index 363e12c90b87..f00c9b86bda0 100644
> > > --- a/Documentation/driver-api/vfio.rst
> > > +++ b/Documentation/driver-api/vfio.rst
> > > @@ -239,6 +239,130 @@ group and can access them as follows::
> > >  	/* Gratuitous device reset and go... */
> > >  	ioctl(device, VFIO_DEVICE_RESET);
> > >
> > > +IOMMUFD and vfio_iommu_type1
> > > +----------------------------
> > > +
> > > +IOMMUFD is the new user API to manage I/O page tables from userspace.
> > > +It intends to be the portal of delivering advanced userspace DMA
> > > +features (nested translation [5]_, PASID [6]_, etc.) while also providing
> > > +a backwards compatibility interface for existing VFIO_TYPE1v2_IOMMU use
> > > +cases.  Eventually the vfio_iommu_type1 driver, as well as the legacy
> > > +vfio container and group model is intended to be deprecated.
> > > +
> > > +The IOMMUFD backwards compatibility interface can be enabled two ways.
> > > +In the first method, the kernel can be configured with
> > > +CONFIG_IOMMUFD_VFIO_CONTAINER, in which case the IOMMUFD subsystem
> > > +transparently provides the entire infrastructure for the VFIO
> > > +container and IOMMU backend interfaces.  The compatibility mode can
> > > +also be accessed if the VFIO container interface, ie. /dev/vfio/vfio is
> > > +simply symlink'd to /dev/iommu.  Note that at the time of writing, the
> > > +compatibility mode is not entirely feature complete relative to
> > > +VFIO_TYPE1v2_IOMMU (ex. DMA mapping MMIO) and does not attempt to
> > > +provide compatibility to the VFIO_SPAPR_TCE_IOMMU interface.  Therefore
> > > +it is not generally advisable at this time to switch from native VFIO
> > > +implementations to the IOMMUFD compatibility interfaces.
> > > +
> > > +Long term, VFIO users should migrate to device access through the cdev
> > > +interface described below, and native access through the IOMMUFD
> > > +provided interfaces.
> > > +
> > > +VFIO Device cdev
> > > +----------------
> > > +
> > > +Traditionally user acquires a device fd via VFIO_GROUP_GET_DEVICE_FD
> > > +in a VFIO group.
> > > +
> > > +With CONFIG_VFIO_DEVICE_CDEV=y the user can now acquire a device fd
> > > +by directly opening a character device /dev/vfio/devices/vfioX where
> > > +"X" is the number allocated uniquely by VFIO for registered devices.
> > > +cdev interface does not support noiommu, so user should use the legacy
> > > +group interface if noiommu is needed.
> > > +
> > > +The cdev only works with IOMMUFD.  Both VFIO drivers and applications
> > > +must adapt to the new cdev security model which requires using
> > > +VFIO_DEVICE_BIND_IOMMUFD to claim DMA ownership before starting to
> > > +actually use the device.  Once BIND succeeds then a VFIO device can
> > > +be fully accessed by the user.
> > > +
> > > +VFIO device cdev doesn't rely on VFIO group/container/iommu drivers.
> > > +Hence those modules can be fully compiled out in an environment
> > > +where no legacy VFIO application exists.
> > > +
> > > +So far SPAPR does not support IOMMUFD yet.  So it cannot support device
> > > +cdev neither.  
> > 
> > s/neither/either/  
> 
> Got it.
> 
> > 
> > Unless I missed it, we've not described that vfio device cdev access is
> > still bound by IOMMU group semantics, ie. there can be one DMA owner
> > for the group.  That's a pretty common failure point for multi-function
> > consumer device use cases, so the why, where, and how it fails should
> > be well covered.  
> 
> Yes. this needs to be documented. How about below words:
> 
> vfio device cdev access is still bound by IOMMU group semantics, ie. there
> can be only one DMA owner for the group.  Devices belonging to the same
> group can not be bound to multiple iommufd_ctx.

... or shared between native kernel and vfio drivers.


>  The users that try to bind
> such device to different iommufd shall be failed in VFIO_DEVICE_BIND_IOMMUFD
> which is the start point to get full access for the device.

"A violation of this ownership requirement will fail at the
VFIO_DEVICE_BIND_IOMMUFD ioctl, which gates full device access."

Thanks,
Alex