linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: Jim Mattson <jmattson@google.com>
Cc: "Vitaly Kuznetsov" <vkuznets@redhat.com>,
	"Radim Krčmář" <rkrcmar@redhat.com>,
	"Roman Kagan" <rkagan@virtuozzo.com>,
	"K. Y. Srinivasan" <kys@microsoft.com>,
	"Haiyang Zhang" <haiyangz@microsoft.com>,
	"Stephen Hemminger" <sthemmin@microsoft.com>,
	"Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>,
	LKML <linux-kernel@vger.kernel.org>,
	"Liran Alon" <liran.alon@oracle.com>,
	"kvm list" <kvm@vger.kernel.org>
Subject: Re: [PATCH v6 06/13] KVM: nVMX: optimize prepare_vmcs02{,_full} for Enlightened VMCS case
Date: Wed, 17 Oct 2018 19:17:32 +0200	[thread overview]
Message-ID: <173cc977-58fd-9431-6199-c2eb8e898f7c@redhat.com> (raw)
In-Reply-To: <CALMp9eTtSuguXb=gCWKL9ZKWy5kUve0SNY1Toduf8x2Qn=1s9Q@mail.gmail.com>

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.

Paolo

> On Wed, Oct 17, 2018 at 10:02 AM, Paolo Bonzini <pbonzini@redhat.com> wrote:
>> On 17/10/2018 16:47, Vitaly Kuznetsov wrote:
>>>>> +   if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
>>>>> +                      HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
>>>>> +           vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
>>>>> +           vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
>>>>> +           vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
>>>>> +           vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
>>>>> +           vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
>>>>> +   }
>>>> For what it's worth, I suspect that these can be moved to
>>>> prepare_vmcs02_full.  The initial implementation of shadow VMCS did not
>>>> expose "unrestricted guest" to the L1 hypervisor, and emulation does a
>>>> lot of accesses to CS (of course).  Not sure how ES base ended up in
>>>> there and not DS base, though...
>>> I tried unshadowing all these fields and at least Hyper-V on KVM
>>> (without using eVMCS of course) experiences a 1200-1300 cpu cycles
>>> regression during tight cpuid loop test. I checked and this happens
>>> because it likes vmreading GUEST_CS_AR_BYTES a lot.
>>
>> Go figure. :)  Liran, do you happen to know if ESX does something
>> similar with CS descriptor cache fields?
>>
>> Paolo


  reply	other threads:[~2018-10-17 17:17 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-16 16:49 [PATCH v6 00/13] KVM: nVMX: Enlightened VMCS for Hyper-V on KVM Vitaly Kuznetsov
2018-10-16 16:49 ` [PATCH v6 01/13] KVM: hyperv: define VP assist page helpers Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 02/13] KVM: VMX: refactor evmcs_sanitize_exec_ctrls() Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 03/13] KVM: nVMX: add KVM_CAP_HYPERV_ENLIGHTENED_VMCS capability Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 04/13] KVM: nVMX: add enlightened VMCS state Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 05/13] KVM: nVMX: implement enlightened VMPTRLD and VMCLEAR Vitaly Kuznetsov
2018-12-12 23:19   ` Jim Mattson
2018-12-13 10:26     ` Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 06/13] KVM: nVMX: optimize prepare_vmcs02{,_full} for Enlightened VMCS case Vitaly Kuznetsov
2018-10-16 21:55   ` Paolo Bonzini
2018-10-17 14:47     ` Vitaly Kuznetsov
2018-10-17 17:02       ` Paolo Bonzini
2018-10-17 17:08         ` Jim Mattson
2018-10-17 17:17           ` Paolo Bonzini [this message]
2018-10-18 11:14             ` Vitaly Kuznetsov
2018-10-18 12:42               ` Paolo Bonzini
2018-10-16 16:50 ` [PATCH v6 07/13] x86/kvm/hyperv: don't clear VP assist pages on init Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 08/13] x86/kvm/lapic: preserve gfn_to_hva_cache len on cache reinit Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 09/13] x86/kvm/nVMX: allow bare VMXON state migration Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 10/13] KVM: selftests: state_test: test bare VMXON migration Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 11/13] x86/kvm/nVMX: nested state migration for Enlightened VMCS Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 12/13] tools/headers: update kvm.h Vitaly Kuznetsov
2018-10-16 16:50 ` [PATCH v6 13/13] KVM: selftests: add Enlightened VMCS test Vitaly Kuznetsov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=173cc977-58fd-9431-6199-c2eb8e898f7c@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=Michael.H.Kelley@microsoft.com \
    --cc=haiyangz@microsoft.com \
    --cc=jmattson@google.com \
    --cc=kvm@vger.kernel.org \
    --cc=kys@microsoft.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=liran.alon@oracle.com \
    --cc=rkagan@virtuozzo.com \
    --cc=rkrcmar@redhat.com \
    --cc=sthemmin@microsoft.com \
    --cc=vkuznets@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).