Re: [PATCH v6 3/3] mm/gup: disallow FOLL_LONGTERM GUP-fast writing to file-backed mappings

[Jason Gunthorpe <jgg@nvidia.com>]

On Tue, May 02, 2023 at 01:59:09PM -0400, Matthew Rosato wrote:

> >> I'd really be happy to learn how a better approach would look like that does
> >> not use longterm pinnings.
> > 
> > Sounds like the FW sadly needs pinnings. This is why I said it looks
> > like DMA. If possible it would be better to get the pinning through
> > VFIO, eg as a mdev
> 
> Hrm, these are today handled as a vfio-pci device (e.g. no mdev) so that would be a pretty significant change.

I was thinking more of having your vIRQ controller as a vfio-mdev, so
qemu would have to open the irq controller as well as the kvm and the
PCI device

> > Otherwise, it would have been cleaner if this was divorced from KVM
> > and took in a direct user pointer, then maybe you could make the
> > argument is its own thing with its own lifetime rules. (then you are
> > kind of making your own mdev)
> 
> Problem there is that firmware needs both the location (where to
> indicate the event) and the identity of the KVM instance (what guest
> to ship the GISA alert to) so I don't think we can completely
> divorce them.

I should have said "kvm page table", being in the KVM ioctls is sort
of OK - but I'm really skeptical that KVM is a good place to put HW
device wrappers.

> > Or, perhaps, this is really part of some radical "irqfd" that we've
> > been on and off talking about specifically to get this area of
> > interrupt bypass uAPI'd properly..
> 
> I investigated that at one point and could not seem to get it to
> fit; I'll have another look there.

It is a long journey, but other arches have problems here too

Jason