[PATCH RFC V2 2/2] KVM: x86: Support using the VMX preemption timer for APIC Timer periodic/oneshot mode

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

Most windows guests still utilize APIC Timer periodic/oneshot mode 
instead of tsc-deadline mode, and the APIC Timer periodic/oneshot 
mode are still emulated by high overhead hrtimer on host. This patch 
converts the expected expire time of the periodic/oneshot mode to
guest deadline tsc in order to leverage VMX preemption timer logic 
for APIC Timer tsc-deadline mode.

Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Cc: Yunhong Jiang <yunhong.jiang@xxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
 arch/x86/kvm/lapic.c | 103 +++++++++++++++++++++++++++++++++++----------------
 arch/x86/kvm/lapic.h |   1 +
 2 files changed, 73 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dad743e..f5a03ae 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1101,7 +1101,14 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 		apic->lapic_timer.period == 0)
 		return 0;
 
-	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
+	if (kvm_lapic_hv_timer_in_use(apic->vcpu)) {
+		ktime_t now;
+
+		now = apic->lapic_timer.timer.base->get_time();
+		remaining = ktime_sub(apic->lapic_timer.expired_period, now);
+	} else
+		remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
+
 	if (ktime_to_ns(remaining) < 0)
 		remaining = ktime_set(0, 0);
 
@@ -1353,8 +1360,6 @@ static void start_sw_period(struct kvm_lapic *apic)
 
 	/* lapic timer in oneshot or periodic mode */
 	now = apic->lapic_timer.timer.base->get_time();
-	apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT)
-		    * APIC_BUS_CYCLE_NS * apic->divide_count;
 
 	if (!apic->lapic_timer.period)
 		return;
@@ -1377,7 +1382,7 @@ static void start_sw_period(struct kvm_lapic *apic)
 	}
 
 	hrtimer_start(&apic->lapic_timer.timer,
-		      ktime_add_ns(now, apic->lapic_timer.period),
+		      apic->lapic_timer.expired_period,
 		      HRTIMER_MODE_ABS_PINNED);
 
 	apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
@@ -1400,52 +1405,71 @@ bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
 
-static void cancel_hv_tscdeadline(struct kvm_lapic *apic)
+static void cancel_hv_timer(struct kvm_lapic *apic)
 {
 	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
 	apic->lapic_timer.hv_timer_in_use = false;
 }
 
-void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-
-	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
-	WARN_ON(swait_active(&vcpu->wq));
-	cancel_hv_tscdeadline(apic);
-	apic_timer_expired(apic);
-}
-EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
-
-static bool start_hv_tscdeadline(struct kvm_lapic *apic)
+static bool start_hv_timer(struct kvm_lapic *apic)
 {
 	u64 tscdeadline = apic->lapic_timer.tscdeadline;
 
-	if (atomic_read(&apic->lapic_timer.pending) ||
+	if ((atomic_read(&apic->lapic_timer.pending) &&
+		!apic_lvtt_period(apic)) ||
 		kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) {
 		if (apic->lapic_timer.hv_timer_in_use)
-			cancel_hv_tscdeadline(apic);
+			cancel_hv_timer(apic);
 	} else {
 		apic->lapic_timer.hv_timer_in_use = true;
 		hrtimer_cancel(&apic->lapic_timer.timer);
 
 		/* In case the sw timer triggered in the window */
-		if (atomic_read(&apic->lapic_timer.pending))
-			cancel_hv_tscdeadline(apic);
+		if (atomic_read(&apic->lapic_timer.pending) &&
+			!apic_lvtt_period(apic))
+			cancel_hv_timer(apic);
 	}
 	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id,
 			apic->lapic_timer.hv_timer_in_use);
 	return apic->lapic_timer.hv_timer_in_use;
 }
 
+void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+	WARN_ON(swait_active(&vcpu->wq));
+	cancel_hv_timer(apic);
+	apic_timer_expired(apic);
+
+	if (apic_lvtt_period(apic)) {
+		ktime_t now;
+		u64 tscl = rdtsc();
+
+		apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT)
+			* APIC_BUS_CYCLE_NS * apic->divide_count;
+
+		if (!apic->lapic_timer.period)
+			return;
+
+		apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
+			nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+		now = apic->lapic_timer.timer.base->get_time();
+		apic->lapic_timer.expired_period = ktime_add_ns(now, apic->lapic_timer.period);
+
+		start_hv_timer(apic);
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
+
 void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	WARN_ON(apic->lapic_timer.hv_timer_in_use);
 
-	if (apic_lvtt_tscdeadline(apic))
-		start_hv_tscdeadline(apic);
+	start_hv_timer(apic);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer);
 
@@ -1457,12 +1481,15 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
 	if (!apic->lapic_timer.hv_timer_in_use)
 		return;
 
-	cancel_hv_tscdeadline(apic);
+	cancel_hv_timer(apic);
 
 	if (atomic_read(&apic->lapic_timer.pending))
 		return;
 
-	start_sw_tscdeadline(apic);
+	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
+		start_sw_period(apic);
+	else if (apic_lvtt_tscdeadline(apic))
+		start_sw_tscdeadline(apic);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
 
@@ -1470,10 +1497,25 @@ static void start_apic_timer(struct kvm_lapic *apic)
 {
 	atomic_set(&apic->lapic_timer.pending, 0);
 
-	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
-		start_sw_period(apic);
-	else if (apic_lvtt_tscdeadline(apic)) {
-		if (!(kvm_x86_ops->set_hv_timer && start_hv_tscdeadline(apic)))
+	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
+		ktime_t now;
+		u64 tscl = rdtsc();
+
+		apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT)
+			* APIC_BUS_CYCLE_NS * apic->divide_count;
+
+		if (!apic->lapic_timer.period)
+			return;
+
+		apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
+			nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+		now = apic->lapic_timer.timer.base->get_time();
+		apic->lapic_timer.expired_period = ktime_add_ns(now, apic->lapic_timer.period);
+
+		if (!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic)))
+			start_sw_period(apic);
+	} else if (apic_lvtt_tscdeadline(apic)) {
+		if (!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic)))
 			start_sw_tscdeadline(apic);
 	}
 }
@@ -1711,8 +1753,7 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
-			apic_lvtt_period(apic))
+	if (!lapic_in_kernel(vcpu))
 		return 0;
 
 	return apic->lapic_timer.tscdeadline;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index f60d01c..fea7602 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -15,6 +15,7 @@
 struct kvm_timer {
 	struct hrtimer timer;
 	s64 period; 				/* unit: ns */
+	ktime_t expired_period;
 	u32 timer_mode;
 	u32 timer_mode_mask;
 	u64 tscdeadline;
-- 
1.9.1