[PATCH v2 2/3] KVM: LAPIC: lapic timer interrupt is injected by posted interrupt

[Wanpeng Li <kernellwp@gmail.com>]

From: Wanpeng Li <wanpengli@tencent.com>

Dedicated instances are currently disturbed by unnecessary jitter due 
to the emulated lapic timers fire on the same pCPUs which vCPUs resident.
There is no hardware virtual timer on Intel for guest like ARM. Both 
programming timer in guest and the emulated timer fires incur vmexits.
This patch tries to avoid vmexit which is incurred by the emulated 
timer fires in dedicated instance scenario. 

When nohz_full is enabled in dedicated instances scenario, the emulated 
timers can be offload to the nearest busy housekeeping cpus since APICv 
is really common in recent years. The guest timer interrupt is injected 
by posted-interrupt which is delivered by housekeeping cpu once the emulated 
timer fires. 

3%~5% redis performance benefit can be observed on Skylake server.

Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
 arch/x86/kvm/lapic.c | 32 +++++++++++++++++++++++++-------
 arch/x86/kvm/x86.h   |  5 +++++
 2 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 09b7387..c08e5a8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -133,6 +133,12 @@ static inline bool posted_interrupt_inject_timer_enabled(struct kvm_vcpu *vcpu)
 		kvm_mwait_in_guest(vcpu->kvm);
 }
 
+static inline bool can_posted_interrupt_inject_timer(struct kvm_vcpu *vcpu)
+{
+	return posted_interrupt_inject_timer_enabled(vcpu) &&
+		!vcpu_halt_in_guest(vcpu);
+}
+
 static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 		u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) {
 	switch (map->mode) {
@@ -1441,6 +1447,19 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
 	}
 }
 
+static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic)
+{
+	struct kvm_timer *ktimer = &apic->lapic_timer;
+
+	kvm_apic_local_deliver(apic, APIC_LVTT);
+	if (apic_lvtt_tscdeadline(apic))
+		ktimer->tscdeadline = 0;
+	if (apic_lvtt_oneshot(apic)) {
+		ktimer->tscdeadline = 0;
+		ktimer->target_expiration = 0;
+	}
+}
+
 static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1450,6 +1469,11 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	if (atomic_read(&apic->lapic_timer.pending))
 		return;
 
+	if (unlikely(can_posted_interrupt_inject_timer(apic->vcpu))) {
+		kvm_apic_inject_pending_timer_irqs(apic);
+		return;
+	}
+
 	atomic_inc(&apic->lapic_timer.pending);
 	kvm_set_pending_timer(vcpu);
 
@@ -2386,13 +2410,7 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	if (atomic_read(&apic->lapic_timer.pending) > 0) {
-		kvm_apic_local_deliver(apic, APIC_LVTT);
-		if (apic_lvtt_tscdeadline(apic))
-			apic->lapic_timer.tscdeadline = 0;
-		if (apic_lvtt_oneshot(apic)) {
-			apic->lapic_timer.tscdeadline = 0;
-			apic->lapic_timer.target_expiration = 0;
-		}
+		kvm_apic_inject_pending_timer_irqs(apic);
 		atomic_set(&apic->lapic_timer.pending, 0);
 	}
 }
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index aa539d6..74c86cb 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -364,4 +364,9 @@ static inline bool kvm_pat_valid(u64 data)
 void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
 void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
 
+static inline bool vcpu_halt_in_guest(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.apf.halted;
+}
+
 #endif
-- 
2.7.4