kvm: use insert sort in kvm_io_bus_register_dev function

The loading time of a VM is quite significant with a CPU usage
reaching 100% when loading a VM that its virtio devices use a
large amount of virt-queues (e.g. a virtio-serial device with
max_ports=511). Most of the time is spend in re-sorting the
kvm_io_bus kvm_io_range array when a new eventfd is registered.

The patch replaces the existing method with an insert sort.
Reviewed-by: NMarcel Apfelbaum <marcel@redhat.com>
Reviewed-by: NUri Lublin <ulublin@redhat.com>
Signed-off-by: NGal Hammer <ghammer@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

virt/kvm/kvm_main.c

@@ -3398,21 +3398,6 @@ static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
 	return kvm_io_bus_cmp(p1, p2);
 }
 
-static int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
-			  gpa_t addr, int len)
-{
-	bus->range[bus->dev_count++] = (struct kvm_io_range) {
-		.addr = addr,
-		.len = len,
-		.dev = dev,
-	};
-
-	sort(bus->range, bus->dev_count, sizeof(struct kvm_io_range),
-		kvm_io_bus_sort_cmp, NULL);
-
-	return 0;
-}
-
 static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
 			     gpa_t addr, int len)
 {
@@ -3553,7 +3538,9 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)
 {
+	int i;
 	struct kvm_io_bus *new_bus, *bus;
+	struct kvm_io_range range;
 
 	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
@@ -3567,9 +3554,22 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			  sizeof(struct kvm_io_range)), GFP_KERNEL);
 	if (!new_bus)
 		return -ENOMEM;
-	memcpy(new_bus, bus, sizeof(*bus) + (bus->dev_count *
-	       sizeof(struct kvm_io_range)));
-	kvm_io_bus_insert_dev(new_bus, dev, addr, len);
+
+	range = (struct kvm_io_range) {
+		.addr = addr,
+		.len = len,
+		.dev = dev,
+	};
+
+	for (i = 0; i < bus->dev_count; i++)
+		if (kvm_io_bus_cmp(&bus->range[i], &range) > 0)
+			break;
+
+	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
+	new_bus->dev_count++;
+	new_bus->range[i] = range;
+	memcpy(new_bus->range + i + 1, bus->range + i,
+		(bus->dev_count - i) * sizeof(struct kvm_io_range));
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);