[Intel-gfx] [PATCH v15 00/26] Add vfio_device cdev for iommufd support

Alex Williamson alex.williamson at redhat.com
Mon Jul 24 19:09:22 UTC 2023


On Tue, 18 Jul 2023 13:57:46 -0300
Jason Gunthorpe <jgg at nvidia.com> wrote:

> On Tue, Jul 18, 2023 at 06:55:25AM -0700, Yi Liu wrote:
> > Existing VFIO provides group-centric user APIs for userspace. Userspace
> > opens the /dev/vfio/$group_id first before getting device fd and hence
> > getting access to device. This is not the desired model for iommufd. Per
> > the conclusion of community discussion[1], iommufd provides device-centric
> > kAPIs and requires its consumer (like VFIO) to be device-centric user
> > APIs. Such user APIs are used to associate device with iommufd and also
> > the I/O address spaces managed by the iommufd.
> > 
> > This series first introduces a per device file structure to be prepared
> > for further enhancement and refactors the kvm-vfio code to be prepared
> > for accepting device file from userspace. After this, adds a mechanism for
> > blocking device access before iommufd bind. Then refactors the vfio to be
> > able to handle cdev paths (e.g. iommufd binding, no-iommufd, [de]attach ioas).
> > This refactor includes making the device_open exclusive between the group
> > and the cdev path, only allow single device open in cdev path; vfio-iommufd
> > code is also refactored to support cdev. e.g. split the vfio_iommufd_bind()
> > into two steps. Eventually, adds the cdev support for vfio device and the
> > new ioctls, then makes group infrastructure optional as it is not needed
> > when vfio device cdev is compiled.
> > 
> > This series is based on some preparation works done to vfio emulated devices[2]
> > and vfio pci hot reset enhancements[3]. Per discussion[4], this series does not
> > support cdev for physical devices that do not have IOMMU. Such devices only
> > have group-centric user APIs.
> > 
> > This series is a prerequisite for iommu nesting for vfio device[5] [6].
> > 
> > The complete code can be found in below branch, simple tests done to the
> > legacy group path and the cdev path. QEMU changes are in upstreaming[7]
> > and the complete code can be found at[8]
> > 
> > https://github.com/yiliu1765/iommufd/tree/vfio_device_cdev_v15
> > (config CONFIG_IOMMUFD=y CONFIG_VFIO_DEVICE_CDEV=y)  
> 
> Alex, if you are still good with this lets make this into a shared
> branch, do you want to do it or would you like a PR from me?

Sorry, was out much of last week.  Yes, my intent would be to put this
both in a shared branch and my next branch for v6.6.  Given this is
mostly vfio, it seems like it'd make sense for me to provide that
branch but I may not get to it until tomorrow.  Thanks,

Alex



More information about the Intel-gfx mailing list