From: Paolo Bonzini <pbonzini@redhat.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: mtosatti@redhat.com
Subject: [PATCH 2/4] KVM: x86: rewrite handling of scaled TSC for kvmclock
Date: Mon, 8 Feb 2016 16:18:29 +0100 [thread overview]
Message-ID: <1454944711-33022-3-git-send-email-pbonzini@redhat.com> (raw)
In-Reply-To: <1454944711-33022-1-git-send-email-pbonzini@redhat.com>
This is the same as before:
kvm_scale_tsc(tgt_tsc_khz)
= tgt_tsc_khz * ratio
= tgt_tsc_khz * user_tsc_khz / tsc_khz (see set_tsc_khz)
= user_tsc_khz (see kvm_guest_time_update)
= vcpu->arch.virtual_tsc_khz (see kvm_set_tsc_khz)
However, computing it through kvm_scale_tsc makes it possible
to include the NTP correction in tgt_tsc_khz, as done in the
next patch.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/x86.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1ca2b44f70bb..6db3c219795b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1713,7 +1713,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
- unsigned long flags, this_tsc_khz, tgt_tsc_khz;
+ unsigned long flags, tgt_tsc_khz;
struct kvm_vcpu_arch *vcpu = &v->arch;
struct kvm_arch *ka = &v->kvm->arch;
s64 kernel_ns;
@@ -1739,8 +1739,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
- if (unlikely(this_tsc_khz == 0)) {
+ tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
+ if (unlikely(tgt_tsc_khz == 0)) {
local_irq_restore(flags);
kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
return 1;
@@ -1775,13 +1775,14 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
if (!vcpu->pv_time_enabled)
return 0;
- if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
- tgt_tsc_khz = kvm_has_tsc_control ?
- vcpu->virtual_tsc_khz : this_tsc_khz;
+ if (kvm_has_tsc_control)
+ tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);
+
+ if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz,
&vcpu->hv_clock.tsc_shift,
&vcpu->hv_clock.tsc_to_system_mul);
- vcpu->hw_tsc_khz = this_tsc_khz;
+ vcpu->hw_tsc_khz = tgt_tsc_khz;
}
/* With all the info we got, fill in the values */
--
1.8.3.1
next prev parent reply other threads:[~2016-02-08 15:18 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-08 15:18 [PATCH 0/4] kvmclock: improve accuracy Paolo Bonzini
2016-02-08 15:18 ` [PATCH 1/4] KVM: x86: rename argument to kvm_set_tsc_khz Paolo Bonzini
2016-02-11 15:01 ` Marcelo Tosatti
2016-02-08 15:18 ` Paolo Bonzini [this message]
2016-02-11 15:23 ` [PATCH 2/4] KVM: x86: rewrite handling of scaled TSC for kvmclock Marcelo Tosatti
2016-02-08 15:18 ` [PATCH 3/4] KVM: x86: pass kvm_get_time_scale arguments in hertz Paolo Bonzini
2016-02-08 15:18 ` [PATCH 4/4] KVM: x86: track actual TSC frequency from the timekeeper struct Paolo Bonzini
2016-02-09 18:41 ` Owen Hofmann
2016-02-10 13:57 ` Paolo Bonzini
2016-02-16 13:48 ` Marcelo Tosatti
2016-02-16 14:25 ` Marcelo Tosatti
2016-02-16 16:59 ` Paolo Bonzini
2016-02-19 14:12 ` Marcelo Tosatti
2016-02-19 15:53 ` Paolo Bonzini
2016-02-16 14:00 ` [PATCH 0/4] kvmclock: improve accuracy Marcelo Tosatti
-- strict thread matches above, loose matches on Subject: below --
2016-01-28 14:04 [PATCH kvm-unit-tests] KVM: x86: add hyperv clock test case Paolo Bonzini
2016-01-28 14:04 ` Paolo Bonzini
2016-01-28 14:25 ` Andrey Smetanin
2016-01-28 14:50 ` Paolo Bonzini
2016-01-28 15:53 ` Paolo Bonzini
2016-01-28 18:45 ` Roman Kagan
2016-01-28 18:53 ` Roman Kagan
2016-01-28 21:28 ` Paolo Bonzini
2016-01-28 16:22 ` Roman Kagan
2016-02-03 16:37 ` Paolo Bonzini
2016-02-04 9:33 ` Roman Kagan
2016-02-04 10:13 ` Paolo Bonzini
2016-02-04 11:12 ` Roman Kagan
2016-04-21 17:01 ` Roman Kagan
2016-04-22 13:32 ` Roman Kagan
2016-04-22 18:08 ` Paolo Bonzini
2016-04-25 8:47 ` Roman Kagan
2016-04-26 10:34 ` Roman Kagan
2016-05-25 18:33 ` Roman Kagan
2016-05-26 14:47 ` Roman Kagan
2016-05-29 22:34 ` Marcelo Tosatti
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=1454944711-33022-3-git-send-email-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.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).