@@ -453,6 +453,8 @@ struct kvm_vcpu_stat {
u32 hypercalls;
u32 irq_injections;
u32 nmi_injections;
+ u32 tsc_overshoot;
+ u32 tsc_ahead;
};
struct kvm_x86_ops {
@@ -134,6 +134,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
{ "irq_injections", VCPU_STAT(irq_injections) },
{ "nmi_injections", VCPU_STAT(nmi_injections) },
+ { "tsc_overshoot", VCPU_STAT(tsc_overshoot) },
+ { "tsc_ahead", VCPU_STAT(tsc_ahead) },
{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
@@ -849,35 +851,80 @@ static int kvm_recompute_guest_time(struct kvm_vcpu *v)
struct kvm_vcpu_arch *vcpu = &v->arch;
void *shared_kaddr;
unsigned long this_tsc_khz;
+ s64 kernel_ns, delta;
+ u64 tsc_timestamp;
+ bool upscale;
if ((!vcpu->time_page))
return 0;
- this_tsc_khz = get_cpu_var(cpu_tsc_khz);
- put_cpu_var(cpu_tsc_khz);
+ /*
+ * The protection we require is simple: we must not be preempted from
+ * the CPU between our read of the TSC khz and our read of the TSC.
+ * Interrupt protection is not strictly required, but it does result in
+ * greater accuracy for the TSC / kernel_ns measurement.
+ */
+ local_irq_save(flags);
+ this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+ kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
+ ktime_get_ts(&ts);
+ monotonic_to_bootbased(&ts);
+ kernel_ns = timespec_to_ns(&ts);
+ local_irq_restore(flags);
+
if (unlikely(this_tsc_khz == 0)) {
kvm_request_guest_time_update(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.
+ */
+ delta = native_read_tsc() - vcpu->hv_clock.tsc_timestamp;
+ delta = pvclock_scale_delta(delta, vcpu->hv_clock.tsc_to_system_mul,
+ vcpu->hv_clock.tsc_shift);
+ delta += vcpu->hv_clock.system_time;
+
if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
+ upscale = this_tsc_khz > vcpu->hw_tsc_khz;
kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz,
&vcpu->hv_clock.tsc_shift,
&vcpu->hv_clock.tsc_to_system_mul);
vcpu->hw_tsc_khz = this_tsc_khz;
}
- /* 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);
- ktime_get_ts(&ts);
- monotonic_to_bootbased(&ts);
- local_irq_restore(flags);
+ if (delta > kernel_ns) {
+ s64 overshoot = delta - kernel_ns;
+ ++v->stat.tsc_ahead;
+ if (upscale)
+ overshoot = overshoot * 9 / 10;
+ if (overshoot > 1000ULL * this_tsc_khz / HZ) {
+ ++v->stat.tsc_overshoot;
+ }
+ kernel_ns = delta;
+ }
/* With all the info we got, fill in the values */
-
- vcpu->hv_clock.system_time = ts.tv_nsec +
- (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;
+ vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
+ vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
/*
* The interface expects us to write an even number signaling that the