KVM: LAPIC: Tune lapic_timer_advance_ns automatically

In cloud environment, lapic_timer_advance_ns is needed to be tuned for every CPU
generations, and every host kernel versions(the kvm-unit-tests/tscdeadline_latency.flat
is 5700 cycles for upstream kernel and 9600 cycles for our 3.10 product kernel,
both preemption_timer=N, Skylake server).

This patch adds the capability to automatically tune lapic_timer_advance_ns
step by step, the initial value is 1000ns as 'commit d0659d946be0 ("KVM: x86:
add option to advance tscdeadline hrtimer expiration")' recommended, it will be
reduced when it is too early, and increased when it is too late. The guest_tsc
and tsc_deadline are hard to equal, so we assume we are done when the delta
is within a small scope e.g. 100 cycles. This patch reduces latency
(kvm-unit-tests/tscdeadline_latency, busy waits, preemption_timer enabled)
from ~2600 cyles to ~1200 cyles on our Skylake server.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 25 insertions, 2 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index fbb0e6df121b..91ffb63397f5 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -70,6 +70,11 @@
 #define APIC_BROADCAST			0xFF
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
+static bool lapic_timer_advance_adjust_done = false;
+#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
+/* step-by-step approximation to mitigate fluctuation */
+#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
+
 static inline int apic_test_vector(int vec, void *bitmap)
 {
 	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -1472,7 +1477,7 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
 void wait_lapic_expire(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	u64 guest_tsc, tsc_deadline;
+	u64 guest_tsc, tsc_deadline, ns;
 
 	if (!lapic_in_kernel(vcpu))
 		return;
@@ -1492,6 +1497,24 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 	if (guest_tsc < tsc_deadline)
 		__delay(min(tsc_deadline - guest_tsc,
 			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+
+	if (!lapic_timer_advance_adjust_done) {
+		/* too early */
+		if (guest_tsc < tsc_deadline) {
+			ns = (tsc_deadline - guest_tsc) * 1000000ULL;
+			do_div(ns, vcpu->arch.virtual_tsc_khz);
+			lapic_timer_advance_ns -= min((unsigned int)ns,
+				lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+		} else {
+		/* too late */
+			ns = (guest_tsc - tsc_deadline) * 1000000ULL;
+			do_div(ns, vcpu->arch.virtual_tsc_khz);
+			lapic_timer_advance_ns += min((unsigned int)ns,
+				lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+		}
+		if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
+			lapic_timer_advance_adjust_done = true;
+	}
 }
 
 static void start_sw_tscdeadline(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ca717737347e..1f3f95557703 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,7 +136,7 @@ static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
 /* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 0;
+unsigned int __read_mostly lapic_timer_advance_ns = 1000;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
 EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);