Cancel the context when Main hands back no Control (#1889)

The goroutines Main starts stop only when its context does, and only a caller
holding the Control can arrange that. Cancelling solely on error left a config
test, which returns no Control and no error, with the lighthouse query worker
and a hostname resolver per dns named static host running for the life of the
process. Every embedder that validates a config in process rather than by
exec'ing pays for that on each config load, dnclient and the apple clients
included.

Co-authored-by: Nate Brown <nbrown.us@gmail.com>

main.go

@@ -32,9 +32,12 @@ const _ = noiseutil.RejectHeadroom - 4*maxRoutines
 
 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

@@ -1,12 +1,21 @@
 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/slackhq/nebula/util"
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"go.uber.org/goleak"
 )
 
 func TestParseCpuAffinity(t *testing.T) {
@@ -49,3 +58,68 @@ func TestParseCpuAffinity(t *testing.T) {
 		assert.Nil(t, parseCpuAffinity(newConfig([]any{1 << 20}), l, 1))
 	}
 }
+
+// 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")
+}