KVM: x86: add option to advance tscdeadline hrtimer expiration

For the hrtimer which emulates the tscdeadline timer in the guest,
add an option to advance expiration, and busy spin on VM-entry waiting
for the actual expiration time to elapse.

This allows achieving low latencies in cyclictest (or any scenario
which requires strict timing regarding timer expiration).

Reduces average cyclictest latency from 12us to 8us
on Core i5 desktop.

Note: this option requires tuning to find the appropriate value
for a particular hardware/guest combination. One method is to measure the
average delay between apic_timer_fn and VM-entry.
Another method is to start with 1000ns, and increase the value
in say 500ns increments until avg cyclictest numbers stop decreasing.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/lapic.c

@@ -33,6 +33,7 @@
 #include <asm/page.h>
 #include <asm/current.h>
 #include <asm/apicdef.h>
+#include <asm/delay.h>
 #include <linux/atomic.h>
 #include <linux/jump_label.h>
 #include "kvm_cache_regs.h"
@@ -1073,6 +1074,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
 	wait_queue_head_t *q = &vcpu->wq;
+	struct kvm_timer *ktimer = &apic->lapic_timer;
 
 	/*
 	 * Note: KVM_REQ_PENDING_TIMER is implicitly checked in
@@ -1087,11 +1089,61 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 
 	if (waitqueue_active(q))
 		wake_up_interruptible(q);
+
+	if (apic_lvtt_tscdeadline(apic))
+		ktimer->expired_tscdeadline = ktimer->tscdeadline;
+}
+
+/*
+ * On APICv, this test will cause a busy wait
+ * during a higher-priority task.
+ */
+
+static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u32 reg = kvm_apic_get_reg(apic, APIC_LVTT);
+
+	if (kvm_apic_hw_enabled(apic)) {
+		int vec = reg & APIC_VECTOR_MASK;
+
+		if (kvm_x86_ops->test_posted_interrupt)
+			return kvm_x86_ops->test_posted_interrupt(vcpu, vec);
+		else {
+			if (apic_test_vector(vec, apic->regs + APIC_ISR))
+				return true;
+		}
+	}
+	return false;
+}
+
+void wait_lapic_expire(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u64 guest_tsc, tsc_deadline;
+
+	if (!kvm_vcpu_has_lapic(vcpu))
+		return;
+
+	if (apic->lapic_timer.expired_tscdeadline == 0)
+		return;
+
+	if (!lapic_timer_int_injected(vcpu))
+		return;
+
+	tsc_deadline = apic->lapic_timer.expired_tscdeadline;
+	apic->lapic_timer.expired_tscdeadline = 0;
+	guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+
+	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
+	if (guest_tsc < tsc_deadline)
+		__delay(tsc_deadline - guest_tsc);
 }
 
 static void start_apic_timer(struct kvm_lapic *apic)
 {
 	ktime_t now;
+
 	atomic_set(&apic->lapic_timer.pending, 0);
 
 	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
@@ -1137,6 +1189,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		/* lapic timer in tsc deadline mode */
 		u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
 		u64 ns = 0;
+		ktime_t expire;
 		struct kvm_vcpu *vcpu = apic->vcpu;
 		unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
 		unsigned long flags;
@@ -1151,8 +1204,10 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		if (likely(tscdeadline > guest_tsc)) {
 			ns = (tscdeadline - guest_tsc) * 1000000ULL;
 			do_div(ns, this_tsc_khz);
+			expire = ktime_add_ns(now, ns);
+			expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
 			hrtimer_start(&apic->lapic_timer.timer,
-				ktime_add_ns(now, ns), HRTIMER_MODE_ABS);
+				      expire, HRTIMER_MODE_ABS);
 		} else
 			apic_timer_expired(apic);
 

arch/x86/kvm/lapic.h

@@ -14,6 +14,7 @@ struct kvm_timer {
 	u32 timer_mode;
 	u32 timer_mode_mask;
 	u64 tscdeadline;
+	u64 expired_tscdeadline;
 	atomic_t pending;			/* accumulated triggered timers */
 };
 
@@ -170,4 +171,6 @@ static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
 
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
+void wait_lapic_expire(struct kvm_vcpu *vcpu);
+
 #endif

arch/x86/kvm/x86.c

@@ -108,6 +108,10 @@ EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);
 static u32 tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
+/* lapic timer advance (tscdeadline mode only) in nanoseconds */
+unsigned int lapic_timer_advance_ns = 0;
+module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+
 static bool backwards_tsc_observed = false;
 
 #define KVM_NR_SHARED_MSRS 16
@@ -6312,6 +6316,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
+	wait_lapic_expire(vcpu);
 	kvm_x86_ops->run(vcpu);
 
 	/*

arch/x86/kvm/x86.h

@@ -170,5 +170,7 @@ extern u64 kvm_supported_xcr0(void);
 
 extern unsigned int min_timer_period_us;
 
+extern unsigned int lapic_timer_advance_ns;
+
 extern struct static_key kvm_no_apic_vcpu;
 #endif