cmd/containerboot,kube: enable autoadvertisement of Tailscale services on containerboot (#18527)

* cmd/containerboot,kube/services: support the ability to automatically advertise services on startup

Updates #17769

Signed-off-by: chaosinthecrd <tom@tmlabs.co.uk>

* cmd/containerboot: don't assume we want to use kube state store if in kubernetes

Fixes #8188

Signed-off-by: chaosinthecrd <tom@tmlabs.co.uk>

---------

Signed-off-by: chaosinthecrd <tom@tmlabs.co.uk>

kube/localclient/fake-client.go

@@ -12,6 +12,29 @@ import (
 
 type FakeLocalClient struct {
 	FakeIPNBusWatcher
+	SetServeCalled bool
+	EditPrefsCalls []*ipn.MaskedPrefs
+	GetPrefsResult *ipn.Prefs
+}
+
+func (m *FakeLocalClient) SetServeConfig(ctx context.Context, cfg *ipn.ServeConfig) error {
+	m.SetServeCalled = true
+	return nil
+}
+
+func (m *FakeLocalClient) EditPrefs(ctx context.Context, mp *ipn.MaskedPrefs) (*ipn.Prefs, error) {
+	m.EditPrefsCalls = append(m.EditPrefsCalls, mp)
+	if m.GetPrefsResult == nil {
+		return &ipn.Prefs{}, nil
+	}
+	return m.GetPrefsResult, nil
+}
+
+func (m *FakeLocalClient) GetPrefs(ctx context.Context) (*ipn.Prefs, error) {
+	if m.GetPrefsResult == nil {
+		return &ipn.Prefs{}, nil
+	}
+	return m.GetPrefsResult, nil
 }
 
 func (f *FakeLocalClient) WatchIPNBus(ctx context.Context, mask ipn.NotifyWatchOpt) (IPNBusWatcher, error) {

kube/localclient/local-client.go

@@ -17,6 +17,8 @@ import (
 // for easier testing.
 type LocalClient interface {
 	WatchIPNBus(ctx context.Context, mask ipn.NotifyWatchOpt) (IPNBusWatcher, error)
+	SetServeConfig(context.Context, *ipn.ServeConfig) error
+	EditPrefs(ctx context.Context, mp *ipn.MaskedPrefs) (*ipn.Prefs, error)
 	CertIssuer
 }
 
@@ -40,6 +42,14 @@ type localClient struct {
 	lc *local.Client
 }
 
+func (lc *localClient) SetServeConfig(ctx context.Context, config *ipn.ServeConfig) error {
+	return lc.lc.SetServeConfig(ctx, config)
+}
+
+func (lc *localClient) EditPrefs(ctx context.Context, mp *ipn.MaskedPrefs) (*ipn.Prefs, error) {
+	return lc.lc.EditPrefs(ctx, mp)
+}
+
 func (lc *localClient) WatchIPNBus(ctx context.Context, mask ipn.NotifyWatchOpt) (IPNBusWatcher, error) {
 	return lc.lc.WatchIPNBus(ctx, mask)
 }

kube/services/services.go

@@ -12,9 +12,46 @@ import (
 
 	"tailscale.com/client/local"
 	"tailscale.com/ipn"
+	"tailscale.com/kube/localclient"
 	"tailscale.com/types/logger"
 )
 
+// EnsureServicesAdvertised is a function that gets called on containerboot
+// startup and ensures that Services get advertised if they exist.
+func EnsureServicesAdvertised(ctx context.Context, services []string, lc localclient.LocalClient, logf logger.Logf) error {
+	if _, err := lc.EditPrefs(ctx, &ipn.MaskedPrefs{
+		AdvertiseServicesSet: true,
+		Prefs: ipn.Prefs{
+			AdvertiseServices: services,
+		},
+	}); err != nil {
+		// EditPrefs only returns an error if it fails _set_ its local prefs.
+		// If it fails to _persist_ the prefs in state, we don't get an error
+		// and we continue waiting below, as control will failover as usual.
+		return fmt.Errorf("error setting prefs AdvertiseServices: %w", err)
+	}
+
+	// Services use the same (failover XOR regional routing) mechanism that
+	// HA subnet routers use. Unfortunately we don't yet get a reliable signal
+	// from control that it's responded to our unadvertisement, so the best we
+	// can do is wait for 20 seconds, where 15s is the approximate maximum time
+	// it should take for control to choose a new primary, and 5s is for buffer.
+	//
+	// Note: There is no guarantee that clients have been _informed_ of the new
+	// primary no matter how long we wait. We would need a mechanism to await
+	// netmap updates for peers to know for sure.
+	//
+	// See https://tailscale.com/kb/1115/high-availability for more details.
+	// TODO(tomhjp): Wait for a netmap update instead of sleeping when control
+	// supports that.
+	select {
+	case <-ctx.Done():
+		return nil
+	case <-time.After(20 * time.Second):
+		return nil
+	}
+}
+
 // EnsureServicesNotAdvertised is a function that gets called on containerboot
 // or k8s-proxy termination and ensures that any currently advertised Services
 // get unadvertised to give clients time to switch to another node before this