Messages in this thread Patch in this message | | | From | Zachary Amsden <> | Subject | [PATCH 08/18] Fix deep C-state TSC desynchronization | Date | Mon, 12 Jul 2010 16:08:02 -1000 |
| |
When CPUs with unstable TSCs enter deep C-state, TSC may stop running. This causes us to require resynchronization. Since we can't tell when this may potentially happen, we assume the worst by forcing re-compensation for it at every point the VCPU task is descheduled.
Signed-off-by: Zachary Amsden <zamsden@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 9e71222..0ad6419 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1872,7 +1872,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_x86_ops->vcpu_load(vcpu, cpu); - if (unlikely(vcpu->cpu != cpu)) { + if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { /* Make sure TSC doesn't go backwards */ s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : native_read_tsc() - vcpu->arch.last_host_tsc; -- 1.7.1
| |