[PATCH v4] KVM: LAPIC: Fix lapic timer injection delay

[Wanpeng Li <kernellwp@gmail.com>]

From: Wanpeng Li <wanpeng.li@hotmail.com>

If the TSC deadline timer is programmed really close to the deadline or 
even in the past, the computation in vmx_set_hv_timer will program the 
absolute target tsc value to vmcs preemption timer field w/ delta == 0, 
then plays a vmentry and an upcoming vmx preemption timer fire vmexit 
dance, the lapic timer injection is delayed due to this duration. Actually 
the lapic timer which is emulated by hrtimer can handle this correctly.

This patch fixes it by firing the lapic timer and injecting a timer interrupt 
immediately during the next vmentry if the TSC deadline timer is programmed
really close to the deadline or even in the past. This saves ~300 cycles on 
the tsc_deadline_timer test of apic.flat.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
 arch/x86/kvm/lapic.c | 33 ++++++++++++++++++++-------------
 arch/x86/kvm/vmx.c   |  6 +++++-
 2 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d24c874..40ad729 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1504,21 +1504,28 @@ static void cancel_hv_timer(struct kvm_lapic *apic)
 static bool start_hv_timer(struct kvm_lapic *apic)
 {
 	u64 tscdeadline = apic->lapic_timer.tscdeadline;
+	bool need_cancel = apic->lapic_timer.hv_timer_in_use;
+	if (!atomic_read(&apic->lapic_timer.pending) || apic_lvtt_period(apic)) {
+		int r = kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline);
+		if (r >= 0) {
+			need_cancel = false;
+			apic->lapic_timer.hv_timer_in_use = true;
+			hrtimer_cancel(&apic->lapic_timer.timer);
+
+			/* In case the sw timer triggered in the window */
+			if (!apic_lvtt_period(apic)) {
+				if (r || atomic_read(&apic->lapic_timer.pending)) {
+					need_cancel = true;
+					if (r)
+						apic_timer_expired(apic);
+				}
+			}
+		}
+	}
 
-	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_timer(apic);
-	} else {
-		apic->lapic_timer.hv_timer_in_use = true;
-		hrtimer_cancel(&apic->lapic_timer.timer);
+	if (need_cancel)
+		cancel_hv_timer(apic);
 
-		/* In case the sw timer triggered in the window */
-		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;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4263860..f8ccf8b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11158,7 +11158,11 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 	vmx->hv_deadline_tsc = tscl + delta_tsc;
 	vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
 			PIN_BASED_VMX_PREEMPTION_TIMER);
-	return 0;
+
+	if (delta_tsc == 0)
+		return 1;
+	else
+		return 0;
 }
 
 static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
-- 
2.7.4