tear down connections that have no (initial) udp connectivity

Prior to the introduction of gossip, a tcp connection would not see
regular communication until it had been marked as 'established',
because the topology communication scheme would periodically send
'FetchAll' only after that. So in the absence of udp connectivity we'd
time out. The timeout could of course occur for other reasons, namely
disrupted tcp connectivity, but the combination of a timeout and 'not
established' pointed to a lack of udp connectivity as a likely
cause. So that's what we checked for.

In the new gossip-based topology communication, however, gossip (of
anything, not just topology) occurs as soon as we have tcp
connectivity. Therefore we will no longer encounter a timeout when
just udp connectivity is disrupted. Which makes our check invalid.

So instead we introduce a one-shot timer, created on handshake
completion and cancelled when we mark the connection as
'established'. When the timer fires, and the connection still hasn't
been established, we shut down the connection with an error indicating
lack of udp connectivity.

router/connection.go

@@ -38,26 +38,27 @@ type RemoteConnection struct {
 type LocalConnection struct {
 	sync.RWMutex
 	RemoteConnection
-	TCPConn           *net.TCPConn
-	tcpSender         TCPSender
-	remoteUDPAddr     *net.UDPAddr
-	established       bool
-	receivedHeartbeat bool
-	stackFrag         bool
-	effectivePMTU     int
-	SessionKey        *[32]byte
-	heartbeatFrame    *ForwardedFrame
-	heartbeat         *time.Ticker
-	fragTest          *time.Ticker
-	forwardChan       chan<- *ForwardedFrame
-	forwardChanDF     chan<- *ForwardedFrame
-	stopForward       chan<- interface{}
-	stopForwardDF     chan<- interface{}
-	verifyPMTU        chan<- int
-	Decryptor         Decryptor
-	Router            *Router
-	uid               uint64
-	queryChan         chan<- *ConnectionInteraction
+	TCPConn            *net.TCPConn
+	tcpSender          TCPSender
+	remoteUDPAddr      *net.UDPAddr
+	established        bool
+	receivedHeartbeat  bool
+	stackFrag          bool
+	effectivePMTU      int
+	SessionKey         *[32]byte
+	establishedTimeout *time.Timer
+	heartbeatFrame     *ForwardedFrame
+	heartbeat          *time.Ticker
+	fragTest           *time.Ticker
+	forwardChan        chan<- *ForwardedFrame
+	forwardChanDF      chan<- *ForwardedFrame
+	stopForward        chan<- interface{}
+	stopForwardDF      chan<- interface{}
+	verifyPMTU         chan<- int
+	Decryptor          Decryptor
+	Router             *Router
+	uid                uint64
+	queryChan          chan<- *ConnectionInteraction
 }
 
 type ConnectionInteraction struct {
@@ -253,10 +254,9 @@ func (conn *LocalConnection) run(queryChan <-chan *ConnectionInteraction, accept
 		}
 	}
 
-	err := conn.queryLoop(queryChan)
-	if netErr, ok := err.(net.Error); ok && netErr.Timeout() && !conn.established {
-		conn.log("connection shutting down due to timeout; possibly caused by blocked UDP connectivity")
-	} else if err != nil {
+	conn.establishedTimeout = time.NewTimer(EstablishedTimeout)
+
+	if err := conn.queryLoop(queryChan); err != nil {
 		conn.log("connection shutting down due to error:", err)
 	} else {
 		conn.log("connection shutting down")
@@ -278,10 +278,15 @@ func (conn *LocalConnection) queryLoop(queryChan <-chan *ConnectionInteraction)
 			case CReceivedHeartbeat:
 				err = conn.handleReceivedHeartbeat(query.payload.(*net.UDPAddr))
 			case CSetEstablished:
+				conn.establishedTimeout.Stop()
 				err = conn.handleSetEstablished()
 			case CSendProtocolMsg:
 				err = conn.handleSendProtocolMsg(query.payload.(ProtocolMsg))
 			}
+		case <-conn.establishedTimeout.C:
+			if !conn.established {
+				err = fmt.Errorf("failed to establish UDP connectivity")
+			}
 		case <-tickerChan(conn.heartbeat):
 			conn.Forward(true, conn.heartbeatFrame, nil)
 		case <-tickerChan(conn.fragTest):
@@ -368,6 +373,10 @@ func (conn *LocalConnection) handleShutdown() {
 		conn.Router.Ourself.DeleteConnection(conn)
 	}
 
+	if conn.establishedTimeout != nil {
+		conn.establishedTimeout.Stop()
+	}
+
 	stopTicker(conn.heartbeat)
 	stopTicker(conn.fragTest)
 

router/consts.go

@@ -19,6 +19,7 @@ const (
 	FastHeartbeat      = 500 * time.Millisecond
 	SlowHeartbeat      = 10 * time.Second
 	FragTestInterval   = 5 * time.Minute
+	EstablishedTimeout = 30 * time.Second
 	ReadTimeout        = 1 * time.Minute
 	PMTUVerifyAttempts = 8
 	PMTUVerifyTimeout  = 10 * time.Millisecond // gets doubled with every attempt