Received-SPF: pass (google.com: domain of linux-kernel+bounces-54113-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Date: Mon, 5 Feb 2024 16:12:27 -0800
In-Reply-To: <CANaxB-yAJf4wFyRgkc+XzAdkC9JUKtx-BoZ=eCV7jRSagjsv0g@mail.gmail.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240205173124.366901-1-avagin@google.com> <ZcErs9rPqT09nNge@google.com>
 <CANaxB-yAJf4wFyRgkc+XzAdkC9JUKtx-BoZ=eCV7jRSagjsv0g@mail.gmail.com>
Message-ID: <ZcF5a72HihKkLGVx@google.com>
Subject: Re: [PATCH] kvm/x86: add capability to disable the write-track mechanism
From: Sean Christopherson <seanjc@google.com>
To: Andrei Vagin <avagin@gmail.com>
Cc: Andrei Vagin <avagin@google.com>, Paolo Bonzini <pbonzini@redhat.com>, linux-kernel@vger.kernel.org, 
	x86@kernel.org, kvm@vger.kernel.org, Zhenyu Wang <zhenyuw@linux.intel.com>, 
	Zhi Wang <zhi.a.wang@intel.com>
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: quoted-printable

On Mon, Feb 05, 2024, Andrei Vagin wrote:
> On Mon, Feb 5, 2024 at 10:41=E2=80=AFAM Sean Christopherson <seanjc@googl=
e.com> wrote:
> >
> > On Mon, Feb 05, 2024, Andrei Vagin wrote:
> > > The write-track is used externally only by the gpu/drm/i915 driver.
> > > Currently, it is always enabled, if a kernel has been compiled with t=
his
> > > driver.
> > >
> > > Enabling the write-track mechanism adds a two-byte overhead per page =
across
> > > all memory slots. It isn't significant for regular VMs. However in gV=
isor,
> > > where the entire process virtual address space is mapped into the VM,=
 even
> > > with a 39-bit address space, the overhead amounts to 256MB.
> > >
> > > This change introduces the new KVM_CAP_PAGE_WRITE_TRACKING capability=
,
> > > allowing users to enable/disable the write-track mechanism. It is ena=
bled
> > > by default for backward compatibility.
> >
> > I would much prefer to allocate the write-tracking metadata on-demand i=
n
> > kvm_page_track_register_notifier(), i.e. do the same as mmu_first_shado=
w_root_alloc(),
> > except for just gfn_write_track.
> >
> > The only potential hiccup would be if taking slots_arch_lock would dead=
lock, but
> > it should be impossible for slots_arch_lock to be taken in any other pa=
th that
> > involves VFIO and/or KVMGT *and* can be coincident.  Except for kvm_arc=
h_destroy_vm()
> > (which deletes KVM's internal memslots), slots_arch_lock is taken only =
through
> > KVM ioctls(), and the caller of kvm_page_track_register_notifier() *mus=
t* hold
> > a reference to the VM.
> >
> > That way there's no need for new uAPI and no need for userspace changes=
.
>=20
> I think it is a good idea, I don't know why I didn't consider it.

Because you wanted to make me look smart ;-)