From: Maxim Levitsky <mlevitsk@redhat.com>
To: Thomas Gleixner <tglx@linutronix.de>, Oliver Upton <oupton@google.com>
Cc: kvm list <kvm@vger.kernel.org>, "H. Peter Anvin" <hpa@zytor.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Jonathan Corbet <corbet@lwn.net>,
Jim Mattson <jmattson@google.com>,
Wanpeng Li <wanpengli@tencent.com>,
"open list:KERNEL SELFTEST FRAMEWORK"
<linux-kselftest@vger.kernel.org>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Marcelo Tosatti <mtosatti@redhat.com>,
Sean Christopherson <sean.j.christopherson@intel.com>,
open list <linux-kernel@vger.kernel.org>,
Ingo Molnar <mingo@redhat.com>,
"maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)"
<x86@kernel.org>, Joerg Roedel <joro@8bytes.org>,
Borislav Petkov <bp@alien8.de>, Shuah Khan <shuah@kernel.org>,
Andrew Jones <drjones@redhat.com>,
"open list:DOCUMENTATION" <linux-doc@vger.kernel.org>
Subject: Re: [PATCH v2 1/3] KVM: x86: implement KVM_{GET|SET}_TSC_STATE
Date: Tue, 08 Dec 2020 19:08:00 +0200 [thread overview]
Message-ID: <047afdde655350a6701803aa8ae739a8bd1c1c14.camel@redhat.com> (raw)
In-Reply-To: <87lfe82quh.fsf@nanos.tec.linutronix.de>
On Tue, 2020-12-08 at 17:40 +0100, Thomas Gleixner wrote:
> On Tue, Dec 08 2020 at 13:13, Maxim Levitsky wrote:
> > On Mon, 2020-12-07 at 11:29 -0600, Oliver Upton wrote:
> > > How would a VMM maintain the phase relationship between guest TSCs
> > > using these ioctls?
> >
> > By using the nanosecond timestamp.
> >
> > While I did made it optional in the V2 it was done for the sole sake of being
> > able to set TSC on (re)boot to 0 from qemu, and for cases when qemu migrates
> > from a VM where the feature is not enabled.
> > In this case the tsc is set to the given value exactly, just like you
> > can do today with KVM_SET_MSRS.
> > In all other cases the nanosecond timestamp will be given.
> >
> > When the userspace uses the nanosecond timestamp, the phase relationship
> > would not only be maintained but be exact, even if TSC reads were not
> > synchronized and even if their restore on the target wasn't synchronized as well.
> >
> > Here is an example:
> >
> > Let's assume that TSC on source/target is synchronized, and that the guest TSC
> > is synchronized as well.
> >
> > Let's call the guest TSC frequency F (guest TSC increments by F each second)
> >
> > We do KVM_GET_TSC_STATE on vcpu0 and receive (t0,tsc0).
> > We do KVM_GET_TSC_STATE on vcpu1 after 1 second passed (exaggerated)
> > and receive (t0 + 1s, tsc0 + F)
>
> Why?
>
> You freeeze the VM and store the realtime timestamp of doing that. At
> that point assuming a full sync host system the only interesting thing
> to store is the guest offset which is the same on all vCPUs and it is
> known already.
>
> So on restore the only thing which needs to be adjusted is the guest
> wide offset.
>
> newoffset = oldoffset + (now - tfreeze)
>
> Then set newoffset for all vCPUs. Anything else is complexity for no
> value and bound to fall apart in hard to debug ways.
>
> The offset is still the same for all vCPUs whether you can restore them
> in the same nanosecond or whether you need 3 minutes for each one. It
> does not matter because when you restore vCPU1 3 minutes after vCPU0
> then TSC has advanced 3 minutes as well. It's still correct from the
> guest POV.
>
> Even if you support TSCADJUST and let the guest write to it does not
> change the per guest offset at all. TSCADJUST is per [v]CPU and adds on
> top:
>
> tscvcpu = tsc_host + guest_offset + TSC_ADJUST
>
> Scaling is just orthogonal and does not change any of this.
I agree with this, and I think that this is what we will end up doing.
Paulo, what do you think about this?
Best regards,
Maxim Levitsky
>
> Thanks,
>
> tglx
>
next prev parent reply other threads:[~2020-12-08 17:09 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-03 17:11 [PATCH v2 0/3] RFC: Precise TSC migration Maxim Levitsky
2020-12-03 17:11 ` [PATCH v2 1/3] KVM: x86: implement KVM_{GET|SET}_TSC_STATE Maxim Levitsky
2020-12-06 16:19 ` Thomas Gleixner
2020-12-07 12:16 ` Maxim Levitsky
2020-12-07 13:16 ` Vitaly Kuznetsov
2020-12-07 17:41 ` Thomas Gleixner
2020-12-08 9:48 ` Peter Zijlstra
2020-12-10 11:42 ` Paolo Bonzini
2020-12-10 12:14 ` Peter Zijlstra
2020-12-10 12:22 ` Paolo Bonzini
2020-12-10 13:01 ` Peter Zijlstra
2020-12-10 20:20 ` Thomas Gleixner
2020-12-07 16:38 ` Thomas Gleixner
2020-12-07 16:53 ` Andy Lutomirski
2020-12-07 17:00 ` Maxim Levitsky
2020-12-07 18:04 ` Andy Lutomirski
2020-12-07 23:11 ` Marcelo Tosatti
2020-12-08 17:43 ` Andy Lutomirski
2020-12-08 19:24 ` Thomas Gleixner
2020-12-08 20:32 ` Andy Lutomirski
2020-12-09 0:19 ` Thomas Gleixner
2020-12-09 4:08 ` Andy Lutomirski
2020-12-09 10:14 ` Thomas Gleixner
2020-12-10 23:42 ` Andy Lutomirski
2020-12-08 11:24 ` Maxim Levitsky
2020-12-08 9:35 ` Peter Zijlstra
2020-12-07 23:34 ` Marcelo Tosatti
2020-12-07 17:29 ` Oliver Upton
2020-12-08 11:13 ` Maxim Levitsky
2020-12-08 15:57 ` Oliver Upton
2020-12-08 15:58 ` Oliver Upton
2020-12-08 17:10 ` Maxim Levitsky
2020-12-08 16:40 ` Thomas Gleixner
2020-12-08 17:08 ` Maxim Levitsky [this message]
2020-12-10 11:48 ` Paolo Bonzini
2020-12-10 14:25 ` Maxim Levitsky
2020-12-07 23:29 ` Marcelo Tosatti
2020-12-08 14:50 ` Maxim Levitsky
2020-12-08 16:02 ` Thomas Gleixner
2020-12-08 16:25 ` Maxim Levitsky
2020-12-08 17:33 ` Andy Lutomirski
2020-12-08 21:25 ` Thomas Gleixner
2020-12-08 18:12 ` Marcelo Tosatti
2020-12-08 21:35 ` Thomas Gleixner
2020-12-08 21:20 ` Thomas Gleixner
2020-12-10 11:48 ` Paolo Bonzini
2020-12-10 14:52 ` Maxim Levitsky
2020-12-10 15:16 ` Andy Lutomirski
2020-12-10 17:59 ` Oliver Upton
2020-12-10 18:05 ` Paolo Bonzini
2020-12-10 18:13 ` Oliver Upton
2020-12-10 21:25 ` Thomas Gleixner
2020-12-10 22:01 ` Andy Lutomirski
2020-12-10 22:28 ` Thomas Gleixner
2020-12-10 23:19 ` Andy Lutomirski
2020-12-11 0:03 ` Thomas Gleixner
2020-12-08 18:11 ` Marcelo Tosatti
2020-12-08 21:33 ` Thomas Gleixner
2020-12-09 16:34 ` Marcelo Tosatti
2020-12-09 20:58 ` Thomas Gleixner
2020-12-10 15:26 ` Marcelo Tosatti
2020-12-10 21:48 ` Thomas Gleixner
2020-12-11 0:27 ` Marcelo Tosatti
2020-12-11 13:30 ` Thomas Gleixner
2020-12-11 14:18 ` Marcelo Tosatti
2020-12-11 21:04 ` Thomas Gleixner
2020-12-11 21:59 ` Paolo Bonzini
2020-12-12 13:03 ` Thomas Gleixner
2020-12-15 10:59 ` Marcelo Tosatti
2020-12-15 16:55 ` Andy Lutomirski
2020-12-15 22:34 ` Thomas Gleixner
2020-12-11 13:37 ` Paolo Bonzini
2020-12-08 17:35 ` Marcelo Tosatti
2020-12-03 17:11 ` [PATCH v2 2/3] KVM: x86: introduce KVM_X86_QUIRK_TSC_HOST_ACCESS Maxim Levitsky
2020-12-03 17:11 ` [PATCH v2 3/3] kvm/selftests: update tsc_msrs_test to cover KVM_X86_QUIRK_TSC_HOST_ACCESS Maxim Levitsky
2020-12-07 23:16 ` [PATCH v2 0/3] RFC: Precise TSC migration Marcelo Tosatti
2020-12-10 11:48 ` Paolo Bonzini
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=047afdde655350a6701803aa8ae739a8bd1c1c14.camel@redhat.com \
--to=mlevitsk@redhat.com \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=drjones@redhat.com \
--cc=hpa@zytor.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=mtosatti@redhat.com \
--cc=oupton@google.com \
--cc=pbonzini@redhat.com \
--cc=sean.j.christopherson@intel.com \
--cc=shuah@kernel.org \
--cc=tglx@linutronix.de \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=x86@kernel.org \
/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).