Let the darwin tun adopt an fd the host already configured

main.go

@@ -22,9 +22,12 @@ type m = map[string]any
 
 func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, deviceFactory overlay.DeviceFactory) (retcon *Control, reterr error) {
 	ctx, cancel := context.WithCancel(context.Background())
-	// Automatically cancel the context if Main returns an error, to signal all created goroutines to quit.
+	// The goroutines started below stop only when this context does, and only a caller holding the
+	// Control can arrange that. Cancel whenever we are not handing one back, which covers an error
+	// and a config test alike: a config test used to leave the lighthouse query worker, and a
+	// hostname resolver per dns named static host, running for the life of the process.
 	defer func() {
-		if reterr != nil {
+		if retcon == nil {
 			cancel()
 		}
 	}()

main_test.go

@@ -0,0 +1,82 @@
+package nebula
+
+import (
+	"fmt"
+	"net/netip"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/slackhq/nebula/cert"
+	cert_test "github.com/slackhq/nebula/cert_test"
+	"github.com/slackhq/nebula/config"
+	"github.com/slackhq/nebula/test"
+	"github.com/stretchr/testify/require"
+	"go.uber.org/goleak"
+)
+
+// TestMain_ConfigTestReleasesItsGoroutines pins the rule that Main only leaves goroutines running
+// when it hands back a Control to stop them with.
+//
+// A config test gets no Control, so anything it started had nothing to stop it: the lighthouse
+// query worker, and a hostname resolver per dns named static host, ran for the life of the
+// process. That matters to every embedder that validates a config in process rather than by
+// exec'ing, dnclient and the apple clients included, because they do it on each config load and
+// the leak accumulates.
+func TestMain_ConfigTestReleasesItsGoroutines(t *testing.T) {
+	defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
+
+	l := test.NewLogger()
+	dir := t.TempDir()
+
+	before := time.Now().Add(-time.Hour)
+	after := time.Now().Add(time.Hour)
+	ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, before, after, nil, nil, nil)
+	networks := []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}
+	_, _, keyPEM, certPEM := cert_test.NewTestCert(
+		cert.Version2, cert.Curve_CURVE25519, ca, caKey, "config-test", before, after, networks, nil, nil)
+
+	caPath := filepath.Join(dir, "ca.pem")
+	certPath := filepath.Join(dir, "cert.pem")
+	keyPath := filepath.Join(dir, "key.pem")
+	require.NoError(t, os.WriteFile(caPath, caPEM, 0o600))
+	require.NoError(t, os.WriteFile(certPath, certPEM, 0o600))
+	require.NoError(t, os.WriteFile(keyPath, keyPEM, 0o600))
+
+	// A static host by address, not by name: the query worker is the goroutine under test and a
+	// hostname would drag a real dns lookup into a unit test.
+	configBody := fmt.Sprintf(`
+pki:
+  ca: %s
+  cert: %s
+  key: %s
+static_host_map:
+  "10.0.0.2": ["192.0.2.1:4242"]
+lighthouse:
+  hosts:
+    - "10.0.0.2"
+listen:
+  host: 127.0.0.1
+  port: 0
+tun:
+  disabled: true
+firewall:
+  outbound:
+    - port: any
+      proto: any
+      host: any
+  inbound:
+    - port: any
+      proto: any
+      host: any
+`, caPath, certPath, keyPath)
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(configBody), 0o600))
+
+	c := config.NewC(l)
+	require.NoError(t, c.Load(dir))
+
+	ctrl, err := Main(c, true, "config-test", l, nil)
+	require.NoError(t, err)
+	require.Nil(t, ctrl, "a config test hands back nothing to stop, so it must stop itself")
+}

overlay/tun_darwin.go

@@ -30,7 +30,10 @@ type tun struct {
 	Routes      atomic.Pointer[[]Route]
 	routeTree   atomic.Pointer[bart.Table[routing.Gateways]]
 	linkAddr    *netroute.LinkAddr
-	l           *slog.Logger
+	// hostOwned means the fd arrived from the OS, which has already configured addressing, mtu
+	// and routes for it. NEPacketTunnelProvider on darwin does this.
+	hostOwned bool
+	l         *slog.Logger
 }
 
 type ifReq struct {
@@ -150,8 +153,48 @@ func (t *tun) deviceBytes() (o [16]byte) {
 	return
 }
 
-func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
+// newTunFromFd adopts a utun the host already created and configured, which is how a darwin
-	return nil, fmt.Errorf("newTunFromFd not supported in Darwin")
+// network extension is handed its device. Everything about moving packets is shared with newTun,
+// only the setup differs: the host owns addressing and routing here.
+func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip.Prefix) (*tun, error) {
+	if err := unix.SetNonblock(deviceFd, true); err != nil {
+		// We own the fd from the moment it is handed to us
+		_ = unix.Close(deviceFd)
+		return nil, fmt.Errorf("failed to set the tun fd to non-blocking mode: %w", err)
+	}
+
+	file := os.NewFile(uintptr(deviceFd), "/dev/tun")
+	t := &tun{
+		f:           file,
+		Device:      utunNameFromFd(deviceFd),
+		vpnNetworks: vpnNetworks,
+		DefaultMTU:  c.GetInt("tun.mtu", DefaultMTU),
+		hostOwned:   true,
+		l:           l,
+	}
+
+	if err := t.reload(c, true); err != nil {
+		_ = file.Close()
+		return nil, err
+	}
+
+	c.RegisterReloadCallback(func(c *config.C) {
+		if err := t.reload(c, false); err != nil {
+			util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
+		}
+	})
+
+	return t, nil
+}
+
+// utunNameFromFd asks the socket what interface it is, for logs. A blank name is not worth
+// failing a tunnel over, so an error just leaves it empty.
+func utunNameFromFd(fd int) string {
+	name, err := unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
+	if err != nil {
+		return ""
+	}
+	return name
 }
 
 func (t *tun) Close() error {
@@ -162,6 +205,12 @@ func (t *tun) Close() error {
 }
 
 func (t *tun) Activate() error {
+	// The host handed us a configured device. Its addresses, mtu and routes come from the network
+	// settings it applied, and a sandboxed extension cannot change them anyway.
+	if t.hostOwned {
+		return nil
+	}
+
 	devName := t.deviceBytes()
 
 	s, err := unix.Socket(
@@ -375,6 +424,11 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
 }
 
 func (t *tun) addRoutes(logErrors bool) error {
+	// The route tree is still ours, the system routing table is not
+	if t.hostOwned {
+		return nil
+	}
+
 	routes := *t.Routes.Load()
 
 	for _, r := range routes {
@@ -404,6 +458,10 @@ func (t *tun) addRoutes(logErrors bool) error {
 }
 
 func (t *tun) removeRoutes(routes []Route) error {
+	if t.hostOwned {
+		return nil
+	}
+
 	for _, r := range routes {
 		if !r.Install {
 			continue