Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1476475

Re: [PATCH 3/4] KVM: x86: introduce get_kvmclock_ns

From Paolo Bonzini <pbonzini@redhat.com>
Newsgroups linux.kernel
Subject Re: [PATCH 3/4] KVM: x86: introduce get_kvmclock_ns
Date 2016-09-05 16:00 +0200
Message-ID <se2Bj-4t4-21@gated-at.bofh.it> (permalink)
References <scC6e-3Bv-17@gated-at.bofh.it> <scC6e-3Bv-19@gated-at.bofh.it> <se2Bj-4t4-23@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw



On 02/09/2016 17:24, Roman Kagan wrote:
> On Thu, Sep 01, 2016 at 05:26:14PM +0200, Paolo Bonzini wrote:
>> Introduce a function that reads the exact nanoseconds value that is
>> provided to the guest in kvmclock.  This crystallizes the notion of
>> kvmclock as a thin veneer over a stable TSC, that the guest will
>> (hopefully) convert with NTP.  In other words, kvmclock is *not* a
>> paravirtualized host-to-guest NTP.
> 
> It might also be worth documenting this approach in a comment somewhere
> around pvclock_gtod_notify / update_pvclock_gtod or friends.  And, if
> those could be simplified due to this change, it would be great, too.

Yes, Radim or I are going to look at it next...

Paolo

Back to linux.kernel | Previous | NextPrevious in thread | Find similar | Unroll thread


Thread

[PATCH 3/4] KVM: x86: introduce get_kvmclock_ns Paolo Bonzini <pbonzini@redhat.com> - 2016-09-01 17:30 +0200
  Re: [PATCH 3/4] KVM: x86: introduce get_kvmclock_ns Paolo Bonzini <pbonzini@redhat.com> - 2016-09-02 16:20 +0200
    Re: [PATCH 3/4] KVM: x86: introduce get_kvmclock_ns Paolo Bonzini <pbonzini@redhat.com> - 2016-09-02 18:40 +0200
      Re: [PATCH 3/4] KVM: x86: introduce get_kvmclock_ns Paolo Bonzini <pbonzini@redhat.com> - 2016-09-02 19:00 +0200
  Re: [PATCH 3/4] KVM: x86: introduce get_kvmclock_ns Paolo Bonzini <pbonzini@redhat.com> - 2016-09-05 16:00 +0200

csiph-web