Re: Unmapping KVM Guest Memory from Host Kernel

From: Fuad Tabba <tabba@google.com>
To: "Manwaring, Derek" <derekmn@amazon.com>
Cc: David Woodhouse <dwmw2@infradead.org>,
	David Matlack <dmatlack@google.com>,
	 Brendan Jackman <jackmanb@google.com>,
	"qperret@google.com" <qperret@google.com>,
	 "jason.cj.chen@intel.com" <jason.cj.chen@intel.com>,
	"Gowans, James" <jgowans@amazon.com>,
	 "seanjc@google.com" <seanjc@google.com>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	 "Roy, Patrick" <roypat@amazon.co.uk>,
	 "chao.p.peng@linux.intel.com" <chao.p.peng@linux.intel.com>,
	"rppt@kernel.org" <rppt@kernel.org>,
	 "pbonzini@redhat.com" <pbonzini@redhat.com>,
	"Kalyazin, Nikita" <kalyazin@amazon.co.uk>,
	 "lstoakes@gmail.com" <lstoakes@gmail.com>,
	"Liam.Howlett@oracle.com" <Liam.Howlett@oracle.com>,
	 "linux-mm@kvack.org" <linux-mm@kvack.org>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	 "kirill.shutemov@linux.intel.com"
	<kirill.shutemov@linux.intel.com>,
	"vbabka@suse.cz" <vbabka@suse.cz>,
	 "mst@redhat.com" <mst@redhat.com>,
	"somlo@cmu.edu" <somlo@cmu.edu>, "Graf (AWS),
	Alexander" <graf@amazon.de>,
	 "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	 "linux-coco@lists.linux.dev" <linux-coco@lists.linux.dev>,
	 "kvmarm@lists.linux.dev" <kvmarm@lists.linux.dev>,
	 "kvmarm@lists.cs.columbia.edu" <kvmarm@lists.cs.columbia.edu>
Subject: Re: Unmapping KVM Guest Memory from Host Kernel
Date: Mon, 11 Mar 2024 09:26:12 +0000	[thread overview]
Message-ID: <CA+EHjTxpBM6LyqGfE_y--Uy1oR4oP7Ozcp3mBwFvAijOZe0i+Q@mail.gmail.com> (raw)
In-Reply-To: <335E21FA-7F1E-4540-8A70-01A63D8C72FA@amazon.com>

Hi,

On Fri, Mar 8, 2024 at 9:05 PM Manwaring, Derek <derekmn@amazon.com> wrote:
>
> On 2024-03-08 at 10:46-0700, David Woodhouse wrote:
> > On Fri, 2024-03-08 at 09:35 -0800, David Matlack wrote:
> > > I think what James is looking for (and what we are also interested
> > > in), is _eliminating_ the ability to access guest memory from the
> > > direct map entirely. And in general, eliminate the ability to access
> > > guest memory in as many ways as possible.
> >
> > Well, pKVM does that...
>
> Yes we've been looking at pKVM and it accomplishes a lot of what we're trying
> to do. Our initial inclination is that we want to stick with VHE for the lower
> overhead. We also want flexibility across server parts, so we would need to
> get pKVM working on Intel & AMD if we went this route.
>
> Certainly there are advantages of pKVM on the perf side like the in-place
> memory sharing rather than copying as well as on the security side by simply
> reducing the TCB. I'd be interested to hear others' thoughts on pKVM vs
> memfd_secret or general ASI.

The work we've done for pKVM is still an RFC [*], but there is nothing
in it that limits it to nVHE (at least not intentionally). It should
work with VHE and hVHE as well. On respinning the patch series [*], we
plan on adding support for normal VMs to use guest_memfd() as well in
arm64, mainly for testing, and to make it easier for others to base
their work on it.

Cheers,
/fuad

[*] https://lore.kernel.org/all/20240222161047.402609-1-tabba@google.com
>
> Derek
>