Kernel time, which advances in discrete steps may progress much slower
than TSC. As a result, when kvmclock is adjusted to a new base, the
apparent time to the guest, which runs at a much higher, nsec scaled
rate based on the current TSC, may have already been observed to have
a larger value (kernel_ns + scaled tsc) than the value to which we are
setting it (kernel_ns + 0).
We must instead compute the clock as potentially observed by the guest
for kernel_ns to make sure it does not go backwards.
Signed-off-by: Zachary Amsden<zamsden@xxxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 4 ++
arch/x86/kvm/x86.c | 79 +++++++++++++++++++++++++++++++++------
2 files changed, 71 insertions(+), 12 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1afecd7..7ec2472 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -338,6 +338,8 @@ 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;
@@ -455,6 +457,8 @@ struct kvm_vcpu_stat {
u32 hypercalls;
u32 irq_injections;
u32 nmi_injections;
+ u32 tsc_overshoot;
+ u32 tsc_ahead;
};
struct kvm_x86_ops {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 52d7d34..703ea43 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -138,6 +138,8 @@ 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) },
@@ -927,33 +929,84 @@ 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, max_kernel_ns;
+ u64 tsc_timestamp;
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.
+ */
+ max_kernel_ns = 0;
+ if (vcpu->hv_clock.tsc_timestamp) {
+ max_kernel_ns = vcpu->last_guest_tsc -
