KVM: Use eoi to track RTC interrupt delivery status

Current interrupt coalescing logci which only used by RTC has conflict
with Posted Interrupt.
This patch introduces a new mechinism to use eoi to track interrupt:
When delivering an interrupt to vcpu, the pending_eoi set to number of
vcpu that received the interrupt. And decrease it when each vcpu writing
eoi. No subsequent RTC interrupt can deliver to vcpu until all vcpus
write eoi.

Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

virt/kvm/ioapic.c

@@ -147,6 +147,22 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
 	    __rtc_irq_eoi_tracking_restore_one(vcpu);
 }
 
+static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
+{
+	if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map))
+		--ioapic->rtc_status.pending_eoi;
+
+	WARN_ON(ioapic->rtc_status.pending_eoi < 0);
+}
+
+static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
+{
+	if (ioapic->rtc_status.pending_eoi > 0)
+		return true; /* coalesced */
+
+	return false;
+}
+
 static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx,
 		bool line_status)
 {
@@ -260,6 +276,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status)
 {
 	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
 	struct kvm_lapic_irq irqe;
+	int ret;
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
 		     "vector=%x trig_mode=%x\n",
@@ -275,7 +292,15 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status)
 	irqe.level = 1;
 	irqe.shorthand = 0;
 
-	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
+	if (irq == RTC_GSI && line_status) {
+		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
+		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
+				ioapic->rtc_status.dest_map);
+		ioapic->rtc_status.pending_eoi = ret;
+	} else
+		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
+
+	return ret;
 }
 
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
@@ -299,13 +324,20 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 		ret = 1;
 	} else {
 		int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
+
+		if (irq == RTC_GSI && line_status &&
+			rtc_irq_check_coalesced(ioapic)) {
+			ret = 0; /* coalesced */
+			goto out;
+		}
 		ioapic->irr |= mask;
 		if ((edge && old_irr != ioapic->irr) ||
 		    (!edge && !entry.fields.remote_irr))
 			ret = ioapic_service(ioapic, irq, line_status);
 		else
 			ret = 0; /* report coalesced interrupt */
 	}
+out:
 	trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
 	spin_unlock(&ioapic->lock);
 
@@ -333,6 +365,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 		if (ent->fields.vector != vector)
 			continue;
 
+		if (i == RTC_GSI)
+			rtc_irq_eoi(ioapic, vcpu);
 		/*
 		 * We are dropping lock while calling ack notifiers because ack
 		 * notifier callbacks for assigned devices call into IOAPIC