Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Mon, 26 Jun 2023 13:42:32 -0700
In-Reply-To: <CALMp9eRvUky-jcrkJ75N5-kvWWxVMNaf95XpyGTa_k49n48g9A@mail.gmail.com>
Mime-Version: 1.0
References: <20230605004334.1930091-1-mizhang@google.com> <CALMp9eSQgcKd=SN4q2QRYbveKoayKzuYEQPM0Xu+FgQ_Mja8-g@mail.gmail.com>
 <CAL715WJowYL=W40SWmtPoz1F9WVBFDG7TQwbsV2Bwf9-cS77=Q@mail.gmail.com>
 <ZH4ofuj0qvKNO9Bz@google.com> <CAL715WKtsC=93Nqr7QJZxspWzF04_CLqN3FUxUaqTHWFRUrwBA@mail.gmail.com>
 <ZH+8GafaNLYPvTJI@google.com> <CAL715WJ1rHS9ORR2ttyAw+idqbaLnOhLveUhW8f4tB9o+ZsuiQ@mail.gmail.com>
 <ZH/PKMmWWgJQdcJQ@google.com> <CAL715W+KSgNMk+kTt3=B-CgxTkToH6xmvHWvVmm3V+hir-jE=g@mail.gmail.com>
 <CALMp9eRvUky-jcrkJ75N5-kvWWxVMNaf95XpyGTa_k49n48g9A@mail.gmail.com>
Message-ID: <ZJn4OFrQfTYpoIYE@google.com>
Subject: Re: [PATCH] KVM: x86/mmu: Remove KVM MMU write lock when accessing indirect_shadow_pages
From:   Sean Christopherson <seanjc@google.com>
To:     Jim Mattson <jmattson@google.com>
Cc:     Mingwei Zhang <mizhang@google.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org, Ben Gardon <bgardon@google.com>
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Mon, Jun 26, 2023, Jim Mattson wrote:
> On Thu, Jun 15, 2023 at 4:58=E2=80=AFPM Mingwei Zhang <mizhang@google.com=
> wrote:
> >
> > On Tue, Jun 6, 2023 at 5:28=E2=80=AFPM Sean Christopherson <seanjc@goog=
le.com> wrote:
> > >
> > > On Tue, Jun 06, 2023, Mingwei Zhang wrote:
> > > > > > Hmm. I agree with both points above, but below, the change seem=
s too
> > > > > > heavyweight. smp_wb() is a mfence(), i.e., serializing all
> > > > > > loads/stores before the instruction. Doing that for every shado=
w page
> > > > > > creation and destruction seems a lot.
> > > > >
> > > > > No, the smp_*b() variants are just compiler barriers on x86.
> > > >
> > > > hmm, it is a "lock addl" now for smp_mb(). Check this: 450cbdd0125c
> > > > ("locking/x86: Use LOCK ADD for smp_mb() instead of MFENCE")
> > > >
> > > > So this means smp_mb() is not a free lunch and we need to be a litt=
le
> > > > bit careful.
> > >
> > > Oh, those sneaky macros.  x86 #defines __smp_mb(), not the outer help=
er.  I'll
> > > take a closer look before posting to see if there's a way to avoid th=
e runtime
> > > barrier.
> >
> > Checked again, I think using smp_wmb() and smp_rmb() should be fine as
> > those are just compiler barriers. We don't need a full barrier here.
>=20
> That seems adequate.

Strictly speaking, no, because neither FNAME(fetch) nor kvm_mmu_pte_write()=
 are
pure readers or writers.  FNAME(fetch) reads guest memory (guest PTEs) and =
writes
indirect_shadow_pages.   kvm_mmu_pte_write() writes guest memory (guest PTE=
s) and
reads indirect_shadow_pages (it later writes indirect_shadow_pages too, but=
 that
write isn't relevant to the ordering we care about here).