From: Wanpeng Li <wanpengli@xxxxxxxxxxx>
Let's treat lapic_timer_advance_ns automatic tuning logic as hypervisor
overhead, move it before wait_lapic_expire instead of between wait_lapic_expire
and the world switch, the wait duration should be calculated by the
up-to-date guest_tsc after the overhead of automatic tuning logic. This
patch reduces ~30+ cycles for kvm-unit-tests/tscdeadline-latency when testing
busy waits.
Signed-off-by: Wanpeng Li <wanpengli@xxxxxxxxxxx>
---
v3 -> v4:
* consider automatic tuning is disabled and timer did not arrive early
* add a code comment
arch/x86/kvm/lapic.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c0ebef560bd1..5d91f2367c31 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1598,11 +1598,19 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline;
+ if (lapic_timer_advance_dynamic) {
+ adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
+ /*
+ * If the timer fired early, reread the TSC to account for the
+ * overhead of the above adjustment to avoid waiting longer
+ * than is necessary.
+ */
+ if (guest_tsc < tsc_deadline)
+ guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+ }
+
if (guest_tsc < tsc_deadline)
__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
-
- if (lapic_timer_advance_dynamic)
- adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
}
void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
--
2.25.1
