Received-SPF: pass (google.com: domain of linux-kernel+bounces-141665-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Precedence: bulk
MIME-Version: 1.0
References: <20240126085444.324918-1-xiong.y.zhang@linux.intel.com>
 <20240126085444.324918-29-xiong.y.zhang@linux.intel.com> <ZhhcAT7XiLHK3ZNQ@google.com>
In-Reply-To: <ZhhcAT7XiLHK3ZNQ@google.com>
From: Jim Mattson <jmattson@google.com>
Date: Thu, 11 Apr 2024 15:10:54 -0700
Message-ID: <CALMp9eTQr8ndf48uHHDem2ZkycdhAuVqz18+V1reEEfv0sx8qg@mail.gmail.com>
Subject: Re: [RFC PATCH 28/41] KVM: x86/pmu: Switch IA32_PERF_GLOBAL_CTRL at
 VM boundary
To: Sean Christopherson <seanjc@google.com>
Cc: Xiong Zhang <xiong.y.zhang@linux.intel.com>, pbonzini@redhat.com, 
	peterz@infradead.org, mizhang@google.com, kan.liang@intel.com, 
	zhenyuw@linux.intel.com, dapeng1.mi@linux.intel.com, kvm@vger.kernel.org, 
	linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org, 
	zhiyuan.lv@intel.com, eranian@google.com, irogers@google.com, 
	samantha.alt@intel.com, like.xu.linux@gmail.com, chao.gao@intel.com, 
	Xiong Zhang <xiong.y.zhang@intel.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Thu, Apr 11, 2024 at 2:54=E2=80=AFPM Sean Christopherson <seanjc@google.=
com> wrote:
>
> On Fri, Jan 26, 2024, Xiong Zhang wrote:
> > +static void save_perf_global_ctrl_in_passthrough_pmu(struct vcpu_vmx *=
vmx)
> > +{
> > +     struct kvm_pmu *pmu =3D vcpu_to_pmu(&vmx->vcpu);
> > +     int i;
> > +
> > +     if (vm_exit_controls_get(vmx) & VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTR=
L) {
> > +             pmu->global_ctrl =3D vmcs_read64(GUEST_IA32_PERF_GLOBAL_C=
TRL);
> > +     } else {
> > +             i =3D vmx_find_loadstore_msr_slot(&vmx->msr_autostore.gue=
st,
> > +                                             MSR_CORE_PERF_GLOBAL_CTRL=
);
> > +             if (i < 0)
> > +                     return;
> > +             pmu->global_ctrl =3D vmx->msr_autostore.guest.val[i].valu=
e;
>
> As before, NAK to using the MSR load/store lists unless there's a *really=
* good
> reason I'm missing.

The VM-exit control, "save IA32_PERF_GLOBAL_CTL," first appears in
Sapphire Rapids. I think that's a compelling reason.

> And we should consider adding VCPU_EXREG_GLOBAL_CTRL so that we can defer=
 the
> VMREAD until KVM actually tries to access the guest value.