Re: [RFC] KVM: mm: fd-based approach for supporting KVM guest private memory

[David Hildenbrand]

On 01.09.21 18:31, James Bottomley wrote:
> On Wed, 2021-09-01 at 18:22 +0200, David Hildenbrand wrote:
> > On 01.09.21 18:18, James Bottomley wrote:
> > > On Wed, 2021-09-01 at 08:54 -0700, Andy Lutomirski wrote:
> > > [...]
> > > > If you want to swap a page on TDX, you can't.  Sorry, go directly
> > > > to jail, do not collect $200.
> > >
> > > Actually, even on SEV-ES you can't either.  You can read the
> > > encrypted page and write it out if you want, but unless you swap it
> > > back to the exact same physical memory location, the encryption key
> > > won't work.  Since we don't guarantee this for swap, I think swap
> > > won't actually work for any confidential computing environment.
> > >
> > > > So I think there are literally zero code paths that currently
> > > > call try_to_unmap() that will actually work like that on TDX.  If
> > > > we run out of memory on a TDX host, we can kill the guest
> > > > completely and reclaim all of its memory (which probably also
> > > > involves killing QEMU or whatever other user program is in
> > > > charge), but that's really our only option.
> > >
> > > I think our only option for swap is guest co-operation.  We're
> > > going to have to inflate a balloon or something in the guest and
> > > have the guest driver do some type of bounce of the page, where it
> > > becomes an unencrypted page in the guest (so the host can read it
> > > without the physical address keying of the encryption getting in
> > > the way) but actually encrypted with a swap transfer key known only
> > > to the guest.  I assume we can use the page acceptance
> > > infrastructure currently being discussed elsewhere to do swap back
> > > in as well ... the host provides the guest with the encrypted swap
> > > page and the guest has to decrypt it and place it in encrypted
> > > guest memory.
> >
> > Ballooning is indeed *the* mechanism to avoid swapping in the
> > hypervisor  and much rather let the guest swap. Shame it requires
> > trusting a guest, which we, in general, can't. Not to mention other
> > issues we already do have with ballooning (latency, broken auto-
> > ballooning, over-inflating, ...).
>
>
> Well not necessarily, but it depends how clever we want to get.  If you
> look over on the OVMF/edk2 list, there's a proposal to do guest
> migration via a mirror VM that invokes a co-routine embedded in the
> OVMF binary:

Yes, I heard of that. "Interesting" design.

> https://patchew.org/EDK2/20210818212048.162626-1-tobin@xxxxxxxxxxxxx/
>
> This gives us a page encryption mechanism that's provided by the host
> but accepted via the guest using attestation, meaning we have a
> mutually trusted piece of code that can use to extract encrypted pages.
> It does seem it could be enhanced to do swapping for us as well if
> that's a road we want to go down?

Right, but that's than no longer ballooning, unless I am missing 
something important. You'd ask the guest to export/import, and you can 
trust it. But do we want to call something like that out of random 
kernel context when swapping/writeback, ...? Hard to tell. Feels like it 
won't win in a beauty contest.

--
Thanks,

David / dhildenb