Sophie

Sophie

distrib > Scientific%20Linux > 5x > x86_64 > by-pkgid > 3160499aacb81f6735941eb4c372d87a > files > 335

kvm-83-164.el5_5.30.src.rpm

From 99472fadb42f136c40baca313e54dd29222438e8 Mon Sep 17 00:00:00 2001
From: Chris Wright <chrisw@redhat.com>
Date: Thu, 5 Mar 2009 16:50:35 -0800
Subject: [PATCH] Disable kvmclock by default

* Dor Laor (dlaor@redhat.com) wrote:
> Who like to own the kvmclock fix or disabling of it?

Let's disable it, and fix in the background.  I wonder if we should
backport 40fb17152c50a69dc304dd632131c2f41281ce44, and key off of
X86_FEATURE_NONSTOP_TSC instead of X86_FEATURE_CONSTANT_TSC.

Hmm, looking at it, I'm using mwait

[ehabkost: This is a workaround for the kvmclock issues, not a definite fix]

RH-Upstream-status: not-applicable
Bugzilla: 469425 488543
Acked-by: Eduardo Habkost <ehabkost@redhat.com>
Acked-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/x86.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ebfaa3b..4c64655 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -997,7 +997,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = iommu_found();
 		break;
 	case KVM_CAP_CLOCKSOURCE:
-		r = force_kvmclock || boot_cpu_has(X86_FEATURE_CONSTANT_TSC);
+		r = force_kvmclock;
 		break;
 	default:
 		r = 0;
-- 
1.6.1