From mboxrd@z Thu Jan 1 00:00:00 1970 From: Vitaly Kuznetsov Subject: Re: [PATCH v6 06/13] KVM: nVMX: optimize prepare_vmcs02{,_full} for Enlightened VMCS case Date: Thu, 18 Oct 2018 13:14:38 +0200 Message-ID: <87sh13qzfl.fsf@vitty.brq.redhat.com> References: <20181016165011.6607-1-vkuznets@redhat.com> <20181016165011.6607-7-vkuznets@redhat.com> <2064be05-4286-e3d5-cd22-13fd957b7003@redhat.com> <8736t4sk8w.fsf@vitty.brq.redhat.com> <0ff3acb0-1d20-cbb0-5f40-887d9db93d9e@redhat.com> <173cc977-58fd-9431-6199-c2eb8e898f7c@redhat.com> Mime-Version: 1.0 Content-Type: text/plain Cc: Radim =?utf-8?B?S3LEjW3DocWZ?= , Roman Kagan , "K. Y. Srinivasan" , Haiyang Zhang , Stephen Hemminger , "Michael Kelley \(EOSG\)" , LKML , Liran Alon , kvm list To: Paolo Bonzini , Jim Mattson Return-path: In-Reply-To: <173cc977-58fd-9431-6199-c2eb8e898f7c@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org Paolo Bonzini writes: > On 17/10/2018 19:08, Jim Mattson wrote: >> I believe that ESXi reads GUEST_CS_AR_BYTES on every VM-exit to >> determine code size. > > Which makes me wonder, maybe we should add GUEST_SS_AR_BYTES which is > where the CPL lives. But then your tests from last year didn't find it. > Hyper-V does read GUEST_SS_AR_BYTES. Way less frequent than GUEST_CS_AR_BYTES but still. Based on that my suggestion would be to shadow GUEST_SS_AR_BYTES, keep GUEST_SS_AR_BYTES and unshadow the rest (GUEST_ES_BASE, GUEST_CS_SELECTOR, GUEST_CS_LIMIT, GUEST_CS_BASE). I can do this as a separate patch as I see this series is already in kvm/queue. -- Vitaly