diff options
| author | Zachary Amsden <zamsden@redhat.com> | 2011-05-04 09:31:29 -0300 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@suse.de> | 2011-05-09 15:55:42 -0700 |
| commit | f413fc28a1db54519b75f731a6e57d1ef0269d78 (patch) | |
| tree | 7ee28526ce50141217b8dc820f15625164d245d5 | |
| parent | ad2088cabe0fd7f633f38ba106025d33ed9a2105 (diff) | |
KVM: x86: Fix kvmclock bug
(backported from commit 28e4639adf0c9f26f6bb56149b7ab547bf33bb95)
If preempted after kvmclock values are updated, but before hardware
virtualization is entered, the last tsc time as read by the guest is
never set. It underflows the next time kvmclock is updated if there
has not yet been a successful entry / exit into hardware virt.
Fix this by simply setting last_tsc to the newly read tsc value so
that any computed nsec advance of kvmclock is nulled.
Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
BugLink: http://bugs.launchpad.net/bugs/714335
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Reviewed-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
| -rw-r--r-- | arch/x86/kvm/x86.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8a10f27233a..df1cefb9457 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -694,6 +694,7 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_kernel_ns = kernel_ns; + vcpu->last_guest_tsc = tsc_timestamp; /* * The interface expects us to write an even number signaling that the |