KVM: x86: workaround SuSE's 2.6.16 pvclock vs masterclock issue
SuSE's 2.6.16 kernel fails to boot if the delta between tsc_timestamp
and rdtsc is larger than a given threshold:
* If we get more than the below threshold into the future, we rerequest
* the real time from the host again which has only little offset then
* that we need to adjust using the TSC.
*
* For now that threshold is 1/5th of a jiffie. That should be good
* enough accuracy for completely broken systems, but also give us swing
* to not call out to the host all the time.
*/
#define PVCLOCK_DELTA_MAX ((1000000000ULL / HZ) / 5)
Disable masterclock support (which increases said delta) in case the
boot vcpu does not use MSR_KVM_SYSTEM_TIME_NEW.
Upstreams kernels which support pvclock vsyscalls (and therefore make
use of PVCLOCK_STABLE_BIT) use MSR_KVM_SYSTEM_TIME_NEW.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index dcb996b..917672f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1542,7 +1542,8 @@
&ka->master_cycle_now);
ka->use_master_clock = host_tsc_clocksource && vcpus_matched
- && !backwards_tsc_observed;
+ && !backwards_tsc_observed
+ && !ka->boot_vcpu_runs_old_kvmclock;
if (ka->use_master_clock)
atomic_set(&kvm_guest_has_master_clock, 1);
@@ -2174,8 +2175,20 @@
case MSR_KVM_SYSTEM_TIME_NEW:
case MSR_KVM_SYSTEM_TIME: {
u64 gpa_offset;
+ struct kvm_arch *ka = &vcpu->kvm->arch;
+
kvmclock_reset(vcpu);
+ if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) {
+ bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
+
+ if (ka->boot_vcpu_runs_old_kvmclock != tmp)
+ set_bit(KVM_REQ_MASTERCLOCK_UPDATE,
+ &vcpu->requests);
+
+ ka->boot_vcpu_runs_old_kvmclock = tmp;
+ }
+
vcpu->arch.time = data;
kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);