@@ -340,6 +340,8 @@ struct kvm_vcpu_arch {
struct page *time_page;
u64 last_host_tsc;
u64 last_host_ns;
+ u64 last_guest_tsc;
+ u64 last_kernel_ns;
bool nmi_pending;
bool nmi_injected;
@@ -974,14 +974,15 @@ static int kvm_write_guest_time(struct kvm_vcpu *v)
struct kvm_vcpu_arch *vcpu = &v->arch;
void *shared_kaddr;
unsigned long this_tsc_khz;
- s64 kernel_ns;
+ s64 kernel_ns, max_kernel_ns;
+ u64 tsc_timestamp;
if ((!vcpu->time_page))
return 0;
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp);
+ kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
kernel_ns = get_kernel_ns();
this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
local_irq_restore(flags);
@@ -991,13 +992,49 @@ static int kvm_write_guest_time(struct kvm_vcpu *v)
return 1;
}
+ /*
+ * Time as measured by the TSC may go backwards when resetting the base
+ * tsc_timestamp. The reason for this is that the TSC resolution is
+ * higher than the resolution of the other clock scales. Thus, many
+ * possible measurments of the TSC correspond to one measurement of any
+ * other clock, and so a spread of values is possible. This is not a
+ * problem for the computation of the nanosecond clock; with TSC rates
+ * around 1GHZ, there can only be a few cycles which correspond to one
+ * nanosecond value, and any path through this code will inevitably
+ * take longer than that. However, with the kernel_ns value itself,
+ * the precision may be much lower, down to HZ granularity. If the
+ * first sampling of TSC against kernel_ns ends in the low part of the
+ * range, and the second in the high end of the range, we can get:
+ *
+ * (TSC - offset_low) * S + kns_old > (TSC - offset_high) * S + kns_new
+ *
+ * As the sampling errors potentially range in the thousands of cycles,
+ * it is possible such a time value has already been observed by the
+ * guest. To protect against this, we must compute the system time as
+ * observed by the guest and ensure the new system time is greater.
+ */
+ max_kernel_ns = 0;
+ if (vcpu->hv_clock.tsc_timestamp && vcpu->last_guest_tsc) {
+ max_kernel_ns = vcpu->last_guest_tsc -
+ vcpu->hv_clock.tsc_timestamp;
+ max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
+ vcpu->hv_clock.tsc_to_system_mul,
+ vcpu->hv_clock.tsc_shift);
+ max_kernel_ns += vcpu->last_kernel_ns;
+ }
+
if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
kvm_set_time_scale(this_tsc_khz, &vcpu->hv_clock);
vcpu->hw_tsc_khz = this_tsc_khz;
}
+ if (max_kernel_ns > kernel_ns)
+ kernel_ns = max_kernel_ns;
+
/* With all the info we got, fill in the values */
+ 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->hv_clock.flags = 0;
/*
@@ -4918,6 +4955,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (hw_breakpoint_active())
hw_breakpoint_restore();
+ kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);
+
atomic_set(&vcpu->guest_mode, 0);
smp_wmb();
local_irq_enable();