From: Glauber Costa <glommer@parallels.com>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: <mingo@kernel.org>, <kvm@vger.kernel.org>, <johnstul@us.ibm.com>,
<jeremy@goop.org>
Subject: Re: [patch 18/18] KVM: x86: update pvclock area conditionally, on cpu migration
Date: Tue, 20 Nov 2012 13:01:12 +0400 [thread overview]
Message-ID: <50AB46D8.5010400@parallels.com> (raw)
In-Reply-To: <20121119215959.499058001@redhat.com>
On 11/20/2012 01:58 AM, Marcelo Tosatti wrote:
> As requested by Glauber, do not update kvmclock area on vcpu->pcpu
> migration, in case the host has stable TSC.
>
> This is to reduce cacheline bouncing.
>
> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
>
> Index: vsyscall/arch/x86/kvm/x86.c
> ===================================================================
> --- vsyscall.orig/arch/x86/kvm/x86.c
> +++ vsyscall/arch/x86/kvm/x86.c
> @@ -2615,7 +2615,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu
> kvm_x86_ops->write_tsc_offset(vcpu, offset);
> vcpu->arch.tsc_catchup = 1;
> }
> - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
> + /*
> + * On a host with synchronized TSC, there is no need to update
> + * kvmclock on vcpu->cpu migration
> + */
> + if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1)
> + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
> if (vcpu->cpu != cpu)
> kvm_migrate_timers(vcpu);
> vcpu->cpu = cpu;
Ok. Since you are only touching the one in kvm_arch_vcpu_load() and
leaving the others untouched, it looks correct.
Acked-by: Glauber Costa <glommer@parallels.com>
next prev parent reply other threads:[~2012-11-20 9:01 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-15 0:08 [patch 00/18] pvclock vsyscall support + KVM hypervisor support (v4) Marcelo Tosatti
2012-11-15 0:08 ` [patch 01/18] KVM: x86: retain pvclock guest stopped bit in guest memory Marcelo Tosatti
2012-11-15 0:08 ` [patch 02/18] x86: kvmclock: allocate pvclock shared memory area Marcelo Tosatti
2012-11-15 17:05 ` Glauber Costa
2012-11-16 2:07 ` [patch 02/18] x86: kvmclock: allocate pvclock shared memory area (v2) Marcelo Tosatti
2012-11-16 7:06 ` Glauber Costa
2012-11-15 0:08 ` [patch 03/18] x86: pvclock: make sure rdtsc doesnt speculate out of region Marcelo Tosatti
2012-11-15 0:08 ` [patch 04/18] x86: pvclock: remove pvclock_shadow_time Marcelo Tosatti
2012-11-15 0:08 ` [patch 05/18] x86: pvclock: create helper for pvclock data retrieval Marcelo Tosatti
2012-11-15 12:27 ` Glauber Costa
2012-11-15 0:08 ` [patch 06/18] x86: pvclock: introduce helper to read flags Marcelo Tosatti
2012-11-15 12:28 ` Glauber Costa
2012-11-15 0:08 ` [patch 07/18] x86: pvclock: add note about rdtsc barriers Marcelo Tosatti
2012-11-15 12:30 ` Glauber Costa
2012-11-16 2:05 ` [patch 07/18] x86: pvclock: add note about rdtsc barriers (v2) Marcelo Tosatti
2012-11-15 0:08 ` [patch 08/18] sched: add notifier for cross-cpu migrations Marcelo Tosatti
2012-11-15 7:01 ` Gleb Natapov
2012-11-15 0:08 ` [patch 09/18] x86: pvclock: generic pvclock vsyscall initialization Marcelo Tosatti
2012-11-15 0:08 ` [patch 10/18] x86: kvm guest: pvclock vsyscall support Marcelo Tosatti
2012-11-15 0:08 ` [patch 11/18] x86: vdso: pvclock gettime support Marcelo Tosatti
2012-11-15 0:08 ` [patch 12/18] KVM: x86: pass host_tsc to read_l1_tsc Marcelo Tosatti
2012-11-15 0:08 ` [patch 13/18] time: export time information for KVM pvclock Marcelo Tosatti
2012-11-15 1:38 ` John Stultz
2012-11-15 0:08 ` [patch 14/18] KVM: x86: notifier for clocksource changes Marcelo Tosatti
2012-11-15 0:08 ` [patch 15/18] KVM: x86: implement PVCLOCK_TSC_STABLE_BIT pvclock flag Marcelo Tosatti
2012-11-15 0:08 ` [patch 16/18] KVM: x86: add kvm_arch_vcpu_postcreate callback, move TSC initialization Marcelo Tosatti
2012-11-15 0:08 ` [patch 17/18] KVM: x86: require matched TSC offsets for master clock Marcelo Tosatti
2012-11-15 0:08 ` [patch 18/18] KVM: x86: update pvclock area conditionally, on cpu migration Marcelo Tosatti
2012-11-15 12:34 ` Glauber Costa
2012-11-19 21:57 ` [patch 00/18] pvclock vsyscall support + KVM hypervisor support (v5) Marcelo Tosatti
2012-11-19 21:57 ` [patch 01/18] KVM: x86: retain pvclock guest stopped bit in guest memory Marcelo Tosatti
2012-11-19 21:58 ` [patch 02/18] x86: kvmclock: allocate pvclock shared memory area Marcelo Tosatti
2012-11-19 21:58 ` [patch 03/18] x86: pvclock: make sure rdtsc doesnt speculate out of region Marcelo Tosatti
2012-11-19 21:58 ` [patch 04/18] x86: pvclock: remove pvclock_shadow_time Marcelo Tosatti
2012-11-19 21:58 ` [patch 05/18] x86: pvclock: create helper for pvclock data retrieval Marcelo Tosatti
2012-11-19 21:58 ` [patch 06/18] x86: pvclock: introduce helper to read flags Marcelo Tosatti
2012-11-19 21:58 ` [patch 07/18] x86: pvclock: add note about rdtsc barriers Marcelo Tosatti
2012-11-19 21:58 ` [patch 08/18] sched: add notifier for cross-cpu migrations Marcelo Tosatti
2012-11-19 21:58 ` [patch 09/18] x86: pvclock: generic pvclock vsyscall initialization Marcelo Tosatti
2012-11-19 21:58 ` [patch 11/18] x86: vdso: pvclock gettime support Marcelo Tosatti
2012-11-19 21:58 ` [patch 12/18] KVM: x86: pass host_tsc to read_l1_tsc Marcelo Tosatti
2012-11-19 21:58 ` [patch 13/18] time: export time information for KVM pvclock Marcelo Tosatti
2012-11-19 21:58 ` [patch 14/18] KVM: x86: notifier for clocksource changes Marcelo Tosatti
2012-11-19 21:58 ` [patch 15/18] KVM: x86: implement PVCLOCK_TSC_STABLE_BIT pvclock flag Marcelo Tosatti
2012-11-19 21:58 ` [patch 16/18] KVM: x86: add kvm_arch_vcpu_postcreate callback, move TSC initialization Marcelo Tosatti
2012-11-19 21:58 ` [patch 17/18] KVM: x86: require matched TSC offsets for master clock Marcelo Tosatti
2012-11-19 21:58 ` [patch 18/18] KVM: x86: update pvclock area conditionally, on cpu migration Marcelo Tosatti
2012-11-20 9:01 ` Glauber Costa [this message]
2012-11-20 9:03 ` [patch 00/18] pvclock vsyscall support + KVM hypervisor support (v5) Glauber Costa
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=50AB46D8.5010400@parallels.com \
--to=glommer@parallels.com \
--cc=jeremy@goop.org \
--cc=johnstul@us.ibm.com \
--cc=kvm@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=mtosatti@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).