Do not warn about local address failures on every update

localAddrs runs inside every SendUpdate, which fires on lighthouse.interval
and again on every network change via RebindUDPServer. Logging the failure
there meant a persistent failure warned every interval for the life of the
process, once per failing interface.

collectLocalAddrs now returns its failures instead of logging them, which
keeps it stateless and lets the tests assert on errors rather than log
output. The lighthouse holds the previous error and warns only when it
changes, demoting repeats to Debug, matching how handshake_manager handles
repeated send failures.

Makefile

@@ -222,11 +222,14 @@ test-cov-html:
 	go test -coverprofile=coverage.out
 	go tool cover -html=coverage.out
 
+# The package builds only compile. The final line links an android binary so a linker-only failure,
+# such as the //go:linkname reference anet makes, cannot pass CI.
 build-test-mobile:
 	GOARCH=amd64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
 	GOARCH=arm64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
 	GOARCH=amd64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
 	GOARCH=arm64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
+	GOARCH=arm64 GOOS=android go build -ldflags=-checklinkname=0 -o /dev/null ${NEBULA_CMD_PATH}
 
 bench:
 	go test -bench=.

connection_manager.go

@@ -105,17 +105,11 @@ func (cm *connectionManager) getInactivityTimeout() time.Duration {
 }
 
 func (cm *connectionManager) In(h *HostInfo) {
-	h.markIn()
+	h.in.Store(true)
 }
 
-// OutRelay records relayed traffic, leaving the rebind epoch for the direct path to this host to consume
+func (cm *connectionManager) Out(h *HostInfo) {
-func (cm *connectionManager) OutRelay(h *HostInfo) {
+	h.out.Store(true)
-	h.markOutOnly()
-}
-
-// Out records outbound traffic and reports whether we rebound since this tunnel last sent
-func (cm *connectionManager) Out(h *HostInfo) bool {
-	return h.markOut(cm.intf.rebindEpoch.Load())
 }
 
 func (cm *connectionManager) RelayUsed(localIndex uint32) {
@@ -134,7 +128,8 @@ func (cm *connectionManager) RelayUsed(localIndex uint32) {
 // getAndResetTrafficCheck returns if there was any inbound or outbound traffic within the last tick and
 // resets the state for this local index
 func (cm *connectionManager) getAndResetTrafficCheck(h *HostInfo, now time.Time) (bool, bool) {
-	in, out := h.takeTraffic()
+	in := h.in.Swap(false)
+	out := h.out.Swap(false)
 	if in || out {
 		h.lastUsed = now
 	}
@@ -345,7 +340,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
 				"tunnelCheck", m{"state": "alive", "method": "passive"},
 			)
 		}
-		hostinfo.setPendingDeletion(false)
+		hostinfo.pendingDeletion.Store(false)
 
 		if mainHostInfo {
 			decision = tryRehandshake
@@ -368,7 +363,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
 		return decision, hostinfo, primary
 	}
 
-	if hostinfo.isPendingDeletion() {
+	if hostinfo.pendingDeletion.Load() {
 		// We have already sent a test packet and nothing was returned, this hostinfo is dead
 		hostinfo.logger(cm.l).Info("Tunnel status",
 			"tunnelCheck", m{"state": "dead", "method": "active"},
@@ -419,7 +414,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
 		}
 	}
 
-	hostinfo.setPendingDeletion(true)
+	hostinfo.pendingDeletion.Store(true)
 	cm.trafficTimer.Add(hostinfo.localIndexId, cm.pendingDeletionInterval)
 	return decision, hostinfo, nil
 }

connection_manager_test.go

@@ -86,25 +86,25 @@ func Test_NewConnectionManagerTest(t *testing.T) {
 	// We saw traffic out to vpnIp
 	nc.Out(hostinfo)
 	nc.In(hostinfo)
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
-	assert.True(t, hostinfo.sentSinceCheck())
+	assert.True(t, hostinfo.out.Load())
-	assert.True(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.True(t, hostinfo.in.Load())
 
 	// Do a traffic check tick, should not be pending deletion but should not have any in/out packets recorded
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 
 	// Do another traffic check tick, this host should be pending deletion now
 	nc.Out(hostinfo)
-	assert.True(t, hostinfo.sentSinceCheck())
+	assert.True(t, hostinfo.out.Load())
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.True(t, hostinfo.isPendingDeletion())
+	assert.True(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 
@@ -168,33 +168,33 @@ func Test_NewConnectionManagerTest2(t *testing.T) {
 	// We saw traffic out to vpnIp
 	nc.Out(hostinfo)
 	nc.In(hostinfo)
-	assert.True(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.True(t, hostinfo.in.Load())
-	assert.True(t, hostinfo.sentSinceCheck())
+	assert.True(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 
 	// Do a traffic check tick, should not be pending deletion but should not have any in/out packets recorded
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 
 	// Do another traffic check tick, this host should be pending deletion now
 	nc.Out(hostinfo)
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.True(t, hostinfo.isPendingDeletion())
+	assert.True(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 
 	// We saw traffic, should no longer be pending deletion
 	nc.In(hostinfo)
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 }
@@ -253,31 +253,31 @@ func Test_NewConnectionManager_DisconnectInactive(t *testing.T) {
 	// Do a traffic check tick, in and out should be cleared but should not be pending deletion
 	nc.Out(hostinfo)
 	nc.In(hostinfo)
-	assert.True(t, hostinfo.sentSinceCheck())
+	assert.True(t, hostinfo.out.Load())
-	assert.True(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.True(t, hostinfo.in.Load())
 
 	now := time.Now()
 	decision, _, _ := nc.makeTrafficDecision(hostinfo.localIndexId, now)
 	assert.Equal(t, tryRehandshake, decision)
 	assert.Equal(t, now, hostinfo.lastUsed)
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 
 	decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Second*5))
 	assert.Equal(t, doNothing, decision)
 	assert.Equal(t, now, hostinfo.lastUsed)
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 
 	// Do another traffic check tick, should still not be pending deletion
 	decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Second*10))
 	assert.Equal(t, doNothing, decision)
 	assert.Equal(t, now, hostinfo.lastUsed)
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 
@@ -285,9 +285,9 @@ func Test_NewConnectionManager_DisconnectInactive(t *testing.T) {
 	decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Minute*10))
 	assert.Equal(t, closeTunnel, decision)
 	assert.Equal(t, now, hostinfo.lastUsed)
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.out.Load())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.in.Load())
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 }

control.go

@@ -212,7 +212,7 @@ func (c *Control) RebindUDPServer() {
 	c.f.lightHouse.SendUpdate()
 
 	// Let the main interface know that we rebound so that underlying tunnels know to trigger punches from their remotes
-	c.f.rebindEpoch.Add(1)
+	c.f.rebindCount++
 }
 
 // ListHostmapHosts returns details about the actual or pending (handshaking) hostmap by vpn ip

control_tester.go

@@ -123,16 +123,6 @@ func (c *Control) SetLocalAddrsFn(fn func(*LocalAllowList) []netip.Addr) {
 	c.f.lightHouse.localAddrsFn = fn
 }
 
-// GetRebindEpochFor returns the rebind epoch a tunnel last sent under, so a test can tell whether a send
-// consumed the epoch edge without having to infer it from lighthouse traffic.
-func (c *Control) GetRebindEpochFor(vpnAddr netip.Addr) (uint32, bool) {
-	h := c.f.hostMap.QueryVpnAddr(vpnAddr)
-	if h == nil {
-		return 0, false
-	}
-	return h.state.Load() >> stateEpochShift, true
-}
-
 func (c *Control) KillPendingTunnel(vpnIp netip.Addr) bool {
 	hostinfo := c.f.handshakeManager.QueryVpnAddr(vpnIp)
 	if hostinfo == nil {

e2e/rebind_test.go

@@ -223,57 +223,3 @@ func TestRebindAdvertisesNewAddressAfterMove(t *testing.T) {
 	lhControl.Stop()
 	myControl.Stop()
 }
-
-// A relayed send records traffic but must not consume the rebind epoch. If it does, the next direct send to the
-// relay host sees the epoch already current and never requeries, so the far side is never told to punch at our
-// new address. This pins the SendVia call site, which the unit tests cannot reach.
-func TestRebindRequeriesAfterRelayedSend(t *testing.T) {
-	t.Parallel()
-	ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
-
-	// No lighthouse on purpose: it would hand out a direct address for them and nothing would relay.
-	myControl, myVpnIpNet, _, _ := newSimpleServer(cert.Version2, ca, caKey, "me", "10.128.0.1/24", m{"relay": m{"use_relays": true}})
-	relayControl, relayVpnIpNet, relayUdpAddr, _ := newSimpleServer(cert.Version2, ca, caKey, "relay", "10.128.0.128/24", m{"relay": m{"am_relay": true}})
-	theirControl, theirVpnIpNet, theirUdpAddr, _ := newSimpleServer(cert.Version2, ca, caKey, "them", "10.128.0.2/24", m{"relay": m{"use_relays": true}})
-
-	myControl.InjectLightHouseAddr(relayVpnIpNet[0].Addr(), relayUdpAddr)
-	myControl.InjectRelays(theirVpnIpNet[0].Addr(), []netip.Addr{relayVpnIpNet[0].Addr()})
-	relayControl.InjectLightHouseAddr(theirVpnIpNet[0].Addr(), theirUdpAddr)
-
-	r := router.NewR(t, myControl, relayControl, theirControl)
-	defer r.RenderFlow()
-
-	myControl.Start()
-	relayControl.Start()
-	theirControl.Start()
-
-	myControl.InjectTunPacket(BuildTunUDPPacket(theirVpnIpNet[0].Addr(), 80, myVpnIpNet[0].Addr(), 80, []byte("establish")))
-	r.RouteForAllUntilTxTun(theirControl)
-	r.RouteFor(time.Millisecond * 500)
-
-	hi := myControl.GetHostInfoByVpnAddr(theirVpnIpNet[0].Addr(), false)
-	require.NotNil(t, hi, "expected a tunnel to them")
-	require.NotEmpty(t, hi.CurrentRelaysToMe, "them must be reachable only via the relay for this test to mean anything")
-	// sendNoMetrics only reaches SendVia when there is no direct remote, so pin that too. Without this the test
-	// keeps passing while quietly sending direct and never exercising the relay path.
-	require.False(t, hi.CurrentRemote.IsValid(), "them must have no direct remote, otherwise SendVia is never called")
-
-	before, ok := myControl.GetRebindEpochFor(relayVpnIpNet[0].Addr())
-	require.True(t, ok, "expected a tunnel to the relay")
-
-	myControl.RebindUDPServer()
-
-	// Traffic to them goes through SendVia on the relay tunnel. That must record traffic without consuming the
-	// relay tunnel's own epoch edge, which belongs to the direct path.
-	myControl.InjectTunPacket(BuildTunUDPPacket(theirVpnIpNet[0].Addr(), 80, myVpnIpNet[0].Addr(), 80, []byte("relayed")))
-	r.RouteForAllUntilTxTun(theirControl)
-
-	after, ok := myControl.GetRebindEpochFor(relayVpnIpNet[0].Addr())
-	require.True(t, ok)
-	assert.Equal(t, before, after,
-		"a relayed send consumed the relay tunnel's rebind epoch, so the next direct send will not requery")
-
-	myControl.Stop()
-	relayControl.Stop()
-	theirControl.Stop()
-}

go.mod

@@ -22,6 +22,7 @@ require (
 	github.com/stefanberger/go-pkcs11uri v0.0.0-20230803200340-78284954bff6
 	github.com/stretchr/testify v1.11.1
 	github.com/vishvananda/netlink v1.3.1
+	github.com/wlynxg/anet v0.0.5
 	go.uber.org/goleak v1.3.0
 	go.yaml.in/yaml/v3 v3.0.4
 	golang.org/x/crypto v0.54.0

go.sum

@@ -149,6 +149,8 @@ github.com/vishvananda/netlink v1.3.1 h1:3AEMt62VKqz90r0tmNhog0r/PpWKmrEShJU0wJW
 github.com/vishvananda/netlink v1.3.1/go.mod h1:ARtKouGSTGchR8aMwmkzC0qiNPrrWO5JS/XMVl45+b4=
 github.com/vishvananda/netns v0.0.5 h1:DfiHV+j8bA32MFM7bfEunvT8IAqQ/NzSJHtcmW5zdEY=
 github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
+github.com/wlynxg/anet v0.0.5 h1:J3VJGi1gvo0JwZ/P1/Yc/8p63SoW98B5dHkYDmpgvvU=
+github.com/wlynxg/anet v0.0.5/go.mod h1:eay5PRQr7fIVAMbTbchTnO9gG65Hg/uYGdc7mguHxoA=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=

hostmap.go

@@ -238,26 +238,18 @@ const (
 )
 
 type HostInfo struct {
-	// The first cache line is everything the packet paths touch.
-
 	remote          atomic.Pointer[netip.AddrPort]
+	remotes         *RemoteList
+	promoteCounter  atomic.Uint32
 	ConnectionState *ConnectionState
-
+	remoteIndexId   uint32
-	// Traffic bits, pendingDeletion, and the rebind epoch we last sent under
+	localIndexId    uint32
-	state atomic.Uint32
-
-	promoteCounter atomic.Uint32
-	remoteIndexId  uint32
-	localIndexId   uint32
-	remotes        *RemoteList
 
 	// vpnAddrs is a list of vpn addresses assigned to this host that are within our own vpn networks
 	// The host may have other vpn addresses that are outside our
 	// vpn networks but were removed because they are not usable
 	vpnAddrs []netip.Addr
 
-	// Everything below is off the packet path: handshakes, relays, roaming and the connection manager.
-
 	// networks is a combination of specific vpn addresses (not prefixes!) and full unsafe networks assigned to this host.
 	networks   *bart.Table[NetworkType]
 	relayState RelayState
@@ -270,6 +262,11 @@ type HostInfo struct {
 	// This is used to limit lighthouse re-queries in chatty clients
 	nextLHQuery atomic.Int64
 
+	// lastRebindCount is the other side of Interface.rebindCount, if these values don't match then we need to ask LH
+	// for a punch from the remote end of this tunnel. The goal being to prime their conntrack for our traffic just like
+	// with a handshake
+	lastRebindCount int8
+
 	// lastHandshakeTime records the time the remote side told us about at the stage when the handshake was completed locally
 	// Stage 1 packet will contain it if I am a responder, stage 2 packet if I am an initiator
 	// This is used to avoid an attack where a handshake packet is replayed after some time
@@ -278,6 +275,9 @@ type HostInfo struct {
 	lastRoam       time.Time
 	lastRoamRemote netip.AddrPort
 
+	//TODO: in, out, and others might benefit from being an atomic.Int32. We could collapse connectionManager pendingDeletion, relayUsed, and in/out into this 1 thing
+	in, out, pendingDeletion atomic.Bool
+
 	// lastUsed tracks the last time ConnectionManager checked the tunnel and it was in use.
 	// This value will be behind against actual tunnel utilization in the hot path.
 	// This should only be used by the ConnectionManagers ticker routine.
@@ -658,7 +658,7 @@ func (hm *HostMap) unlockedAddHostInfo(hostinfo *HostInfo, f *Interface) {
 	hm.Indexes[hostinfo.localIndexId] = hostinfo
 	hm.RemoteIndexes[hostinfo.remoteIndexId] = hostinfo
 
-	hostinfo.markOut(f.rebindEpoch.Load())
+	hostinfo.out.Store(true)
 	if f.connectionManager != nil { // f.connectionManager is only nil in some unit tests
 		f.connectionManager.trafficTimer.Add(hostinfo.localIndexId, f.connectionManager.checkInterval)
 	}
@@ -759,68 +759,6 @@ func (i *HostInfo) TryPromoteBest(preferredRanges []netip.Prefix, ifce *Interfac
 	}
 }
 
-// Bits within HostInfo.state, everything above stateEpochShift is the epoch
-const (
-	stateIn uint32 = 1 << iota
-	stateOut
-	statePendingDeletion
-
-	stateFlags      = stateIn | stateOut | statePendingDeletion
-	stateEpochShift = 3
-)
-
-// markIn records inbound traffic
-func (i *HostInfo) markIn() {
-	if i.state.Load()&stateIn == 0 {
-		i.state.Or(stateIn)
-	}
-}
-
-// markOut records a send and reports whether the epoch moved, meaning we want a punch from the far side
-func (i *HostInfo) markOut(epoch uint32) bool {
-	e := epoch << stateEpochShift
-	for {
-		old := i.state.Load()
-		if old&stateOut != 0 && old&^stateFlags == e {
-			return false
-		}
-
-		if i.state.CompareAndSwap(old, old&stateFlags|stateOut|e) {
-			return old&^stateFlags != e
-		}
-	}
-}
-
-// markOutOnly records a send without consuming the rebind epoch, for paths that cannot act on a requery
-func (i *HostInfo) markOutOnly() {
-	if i.state.Load()&stateOut == 0 {
-		i.state.Or(stateOut)
-	}
-}
-
-// sentSinceCheck reports whether anything has been sent since the connection manager last looked
-func (i *HostInfo) sentSinceCheck() bool {
-	return i.state.Load()&stateOut != 0
-}
-
-// takeTraffic clears both traffic bits, leaving the epoch alone, and reports what they were
-func (i *HostInfo) takeTraffic() (in bool, out bool) {
-	old := i.state.And(^(stateIn | stateOut))
-	return old&stateIn != 0, old&stateOut != 0
-}
-
-func (i *HostInfo) setPendingDeletion(v bool) {
-	if v {
-		i.state.Or(statePendingDeletion)
-	} else {
-		i.state.And(^statePendingDeletion)
-	}
-}
-
-func (i *HostInfo) isPendingDeletion() bool {
-	return i.state.Load()&statePendingDeletion != 0
-}
-
 func (i *HostInfo) GetCert() *cert.CachedCertificate {
 	if i.ConnectionState != nil {
 		return i.ConnectionState.peerCert
@@ -930,10 +868,28 @@ func (i *HostInfo) logger(l *slog.Logger) *slog.Logger {
 
 // Utility functions
 
-func localAddrs(l *slog.Logger, allowList *LocalAllowList) []netip.Addr {
+func localAddrs(l *slog.Logger, allowList *LocalAllowList) ([]netip.Addr, error) {
+	return collectLocalAddrs(l, allowList, localInterfaces, localInterfaceAddrs)
+}
+
+// collectLocalAddrs takes its enumerators as arguments so tests can drive the filtering and the
+// failure branches without depending on the addresses of whatever host they run on. It reports
+// failures to the caller rather than logging them, because it runs on every lighthouse update and
+// only the caller can tell a new failure from a repeat of the same one.
+func collectLocalAddrs(
+	l *slog.Logger,
+	allowList *LocalAllowList,
+	interfaces func() ([]net.Interface, error),
+	interfaceAddrs func(*net.Interface) ([]net.Addr, error),
+) ([]netip.Addr, error) {
 	//FIXME: This function is pretty garbage
 	var finalAddrs []netip.Addr
-	ifaces, _ := net.Interfaces()
+	var errs []error
+	ifaces, err := interfaces()
+	if err != nil {
+		return nil, fmt.Errorf("failed to enumerate local interfaces: %w", err)
+	}
+
 	for _, i := range ifaces {
 		allow := allowList.AllowName(i.Name)
 		if l.Enabled(context.Background(), logging.LevelTrace) {
@@ -946,7 +902,12 @@ func localAddrs(l *slog.Logger, allowList *LocalAllowList) []netip.Addr {
 		if !allow {
 			continue
 		}
-		addrs, _ := i.Addrs()
+		addrs, err := interfaceAddrs(&i)
+		if err != nil {
+			errs = append(errs, fmt.Errorf("failed to get addresses for %s: %w", i.Name, err))
+			continue
+		}
+
 		for _, rawAddr := range addrs {
 			var addr netip.Addr
 			switch v := rawAddr.(type) {
@@ -981,5 +942,5 @@ func localAddrs(l *slog.Logger, allowList *LocalAllowList) []netip.Addr {
 			}
 		}
 	}
-	return finalAddrs
+	return finalAddrs, errors.Join(errs...)
 }

hostmap_test.go

@@ -1,6 +1,8 @@
 package nebula
 
 import (
+	"errors"
+	"net"
 	"net/netip"
 	"slices"
 	"testing"
@@ -402,42 +404,82 @@ func TestHostMap_RelayState(t *testing.T) {
 
 }
 
-func TestHostInfo_markOut(t *testing.T) {
+func TestCollectLocalAddrs(t *testing.T) {
-	h := &HostInfo{}
+	ifaces := []net.Interface{
-	h.markOut(5) // stamped when the tunnel was added
+		{Index: 1, Name: "lo"},
+		{Index: 2, Name: "eth0"},
+		{Index: 3, Name: "docker0"},
+	}
+	addrs := map[string][]net.Addr{
+		"lo": {
+			&net.IPNet{IP: net.ParseIP("127.0.0.1"), Mask: net.CIDRMask(8, 32)},
+			&net.IPNet{IP: net.ParseIP("::1"), Mask: net.CIDRMask(128, 128)},
+		},
+		"eth0": {
+			&net.IPNet{IP: net.ParseIP("10.0.0.5"), Mask: net.CIDRMask(24, 32)},
+			&net.IPNet{IP: net.ParseIP("fe80::1"), Mask: net.CIDRMask(64, 128)},
+			&net.IPAddr{IP: net.ParseIP("fd00::5")},
+		},
+		"docker0": {
+			&net.IPNet{IP: net.ParseIP("172.17.0.1"), Mask: net.CIDRMask(16, 32)},
+		},
+	}
 
-	// A tunnel already on the current epoch has nothing to report, which is what keeps a fresh tunnel from
+	enumerate := func() ([]net.Interface, error) { return ifaces, nil }
-	// requerying on its first packet
+	addrsFor := func(i *net.Interface) ([]net.Addr, error) { return addrs[i.Name], nil }
-	assert.False(t, h.markOut(5), "an unchanged epoch should not report a move")
-	assert.True(t, h.sentSinceCheck(), "the send is still recorded as traffic")
 
-	// A rebind is observed exactly once, so we requery once per rebind
+	// Loopback and link local are dropped, everything else on every interface is kept.
-	assert.True(t, h.markOut(6), "a bumped epoch should report a move")
+	out, err := collectLocalAddrs(test.NewLogger(), nil, enumerate, addrsFor)
-	assert.False(t, h.markOut(6), "the epoch move should only be reported once")
+	require.NoError(t, err)
+	assert.Equal(t, []netip.Addr{
+		netip.MustParseAddr("10.0.0.5"),
+		netip.MustParseAddr("fd00::5"),
+		netip.MustParseAddr("172.17.0.1"),
+	}, out)
 
-	// Traffic and pendingDeletion live in the same word and must survive an epoch change
+	// An interface the allow list rejects by name is never asked for its addresses.
-	h.setPendingDeletion(true)
+	c := config.NewC(test.NewLogger())
-	h.markIn()
+	c.Settings["allowlist"] = map[string]any{
-	assert.True(t, h.markOut(7))
+		"interfaces": map[string]any{`docker.*`: false},
-	assert.True(t, h.isPendingDeletion(), "pendingDeletion must survive an epoch change")
+	}
-	in, out := h.takeTraffic()
+	al, err := NewLocalAllowListFromConfig(c, "allowlist")
-	assert.True(t, in, "inbound traffic must survive an epoch change")
+	require.NoError(t, err)
-	assert.True(t, out)
 
-	// Clearing the traffic bits leaves the epoch alone, otherwise an idle tunnel would requery forever
+	asked := make(map[string]struct{})
-	assert.False(t, h.markOut(7), "takeTraffic must not disturb the epoch")
+	countingAddrsFor := func(i *net.Interface) ([]net.Addr, error) {
-}
+		asked[i.Name] = struct{}{}
-
+		return addrs[i.Name], nil
-// A relayed send records traffic but must leave the rebind epoch for the direct path to consume, otherwise
+	}
-// relaying to a host swallows the requery that gets the far side punching at our new address.
+	out, err = collectLocalAddrs(test.NewLogger(), al, enumerate, countingAddrsFor)
-func TestHostInfo_markOutOnly(t *testing.T) {
+	require.NoError(t, err)
-	h := &HostInfo{}
+	assert.Equal(t, []netip.Addr{
-	h.markOut(5)
+		netip.MustParseAddr("10.0.0.5"),
-
+		netip.MustParseAddr("fd00::5"),
-	h.markOutOnly()
+	}, out)
-	assert.True(t, h.sentSinceCheck(), "a relayed send is still outbound traffic")
+	assert.NotContains(t, asked, "docker0")
-	assert.False(t, h.markOut(5), "a relayed send must not disturb the epoch")
+
-
+	// A failure to enumerate interfaces at all is reported rather than silently advertising nothing.
-	assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
+	out, err = collectLocalAddrs(
-	assert.False(t, h.markOut(6))
+		test.NewLogger(),
+		nil,
+		func() ([]net.Interface, error) { return nil, errors.New("netlinkrib: permission denied") },
+		addrsFor,
+	)
+	assert.Nil(t, out)
+	require.EqualError(t, err, "failed to enumerate local interfaces: netlinkrib: permission denied")
+
+	// One interface failing is reported and skipped, the rest are still collected.
+	out, err = collectLocalAddrs(
+		test.NewLogger(),
+		nil,
+		enumerate,
+		func(i *net.Interface) ([]net.Addr, error) {
+			if i.Name == "eth0" {
+				return nil, errors.New("nope")
+			}
+			return addrs[i.Name], nil
+		},
+	)
+	assert.Equal(t, []netip.Addr{netip.MustParseAddr("172.17.0.1")}, out)
+	require.EqualError(t, err, "failed to get addresses for eth0: nope")
 }

inside.go

@@ -297,7 +297,7 @@ func (f *Interface) SendVia(via *HostInfo,
 	c := via.ConnectionState.messageCounter.Add(1)
 
 	out = header.Encode(out, header.Version, header.Message, header.MessageRelay, relay.RemoteIndex, c)
-	f.connectionManager.OutRelay(via)
+	f.connectionManager.Out(via)
 
 	// Authenticate the header and payload, but do not encrypt for this message type.
 	// The payload consists of the inner, unencrypted Nebula header, as well as the end-to-end encrypted payload.
@@ -365,11 +365,17 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
 
 	//l.WithField("trace", string(debug.Stack())).Error("out Header ", &Header{Version, t, st, 0, hostinfo.remoteIndexId, c}, p)
 	out = header.Encode(out, header.Version, t, st, hostinfo.remoteIndexId, c)
-	// We rebound since this tunnel last sent, ask the lighthouse to get the far side punching at us again
+	f.connectionManager.Out(hostinfo)
-	if f.connectionManager.Out(hostinfo) && t != header.CloseTunnel {
+
+	// Query our LH if we haven't since the last time we've been rebound, this will cause the remote to punch against
+	// all our addrs and enable a faster roaming.
+	if t != header.CloseTunnel && hostinfo.lastRebindCount != f.rebindCount {
+		//NOTE: there is an update hole if a tunnel isn't used and exactly 256 rebinds occur before the tunnel is
+		// finally used again. This tunnel would eventually be torn down and recreated if this action didn't help.
 		f.lightHouse.QueryServer(hostinfo.vpnAddrs[0])
+		hostinfo.lastRebindCount = f.rebindCount
 		if f.l.Enabled(context.Background(), slog.LevelDebug) {
-			f.l.Debug("Lighthouse update triggered for punch due to rebind epoch",
+			f.l.Debug("Lighthouse update triggered for punch due to rebind counter",
 				"vpnAddrs", hostinfo.vpnAddrs,
 			)
 		}

interface.go

@@ -82,8 +82,8 @@ type Interface struct {
 	sendRecvErrorConfig   recvErrorConfig
 	acceptRecvErrorConfig recvErrorConfig
 
-	// Bumped on every udp rebind, tunnels compare it to decide they need a punch from the far side
+	// rebindCount is used to decide if an active tunnel should trigger a punch notification through a lighthouse
-	rebindEpoch atomic.Uint32
+	rebindCount int8
 	version     string
 
 	conntrackCacheTimeout time.Duration

lighthouse.go

@@ -40,6 +40,10 @@ type LightHouse struct {
 	// addresses rather than whatever this machine's NICs happen to be. Set it before Start.
 	localAddrsFn func(*LocalAllowList) []netip.Addr
 
+	// lastLocalAddrsErr is the previous localAddrsFn failure. Enumeration runs on every update, so an
+	// unchanged failure is demoted to Debug rather than warning every lighthouse.interval forever.
+	lastLocalAddrsErr atomic.Pointer[string]
+
 	// Local cache of answers from light houses
 	// map of vpn addr to answers
 	addrMap map[netip.Addr]*RemoteList
@@ -112,7 +116,9 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
 		l:                  l,
 	}
 	h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
-		return localAddrs(h.l, al)
+		addrs, err := localAddrs(h.l, al)
+		h.logLocalAddrsErr(err)
+		return addrs
 	}
 
 	lighthouses := make([]netip.Addr, 0)
@@ -913,6 +919,26 @@ func (lh *LightHouse) TriggerUpdate() {
 	}
 }
 
+// logLocalAddrsErr reports a localAddrs failure at Warn the first time it is seen and at Debug while
+// it persists unchanged, so a permanent failure does not warn on every update forever.
+func (lh *LightHouse) logLocalAddrsErr(err error) {
+	if err == nil {
+		lh.lastLocalAddrsErr.Store(nil)
+		return
+	}
+
+	msg := err.Error()
+	prev := lh.lastLocalAddrsErr.Swap(&msg)
+	if prev != nil && *prev == msg {
+		if lh.l.Enabled(context.Background(), slog.LevelDebug) {
+			lh.l.Debug("Failed to collect local addresses to advertise", "error", err)
+		}
+		return
+	}
+
+	lh.l.Warn("Failed to collect local addresses to advertise", "error", err)
+}
+
 func (lh *LightHouse) SendUpdate() {
 	var v4 []*V4AddrPort
 	var v6 []*V6AddrPort

lighthouse_test.go

@@ -1,7 +1,9 @@
 package nebula
 
 import (
+	"bytes"
 	"encoding/binary"
+	"errors"
 	"fmt"
 	"net/netip"
 	"testing"
@@ -738,3 +740,32 @@ func TestLighthouse_DeletesWork(t *testing.T) {
 	out = lh.Query(testHost)
 	assert.Nil(t, out)
 }
+
+func TestLightHouse_logLocalAddrsErr(t *testing.T) {
+	out := &bytes.Buffer{}
+	lh := &LightHouse{l: test.NewLoggerWithOutput(out)}
+
+	// The first sighting of a failure warns.
+	lh.logLocalAddrsErr(errors.New("permission denied"))
+	assert.Contains(t, out.String(), "level=WARN")
+	assert.Contains(t, out.String(), "permission denied")
+
+	// Repeating unchanged does not warn again, which is what keeps a permanent failure from warning
+	// on every lighthouse.interval for the life of the process.
+	out.Reset()
+	lh.logLocalAddrsErr(errors.New("permission denied"))
+	assert.NotContains(t, out.String(), "level=WARN")
+
+	// A different failure is a new event and warns.
+	out.Reset()
+	lh.logLocalAddrsErr(errors.New("something else"))
+	assert.Contains(t, out.String(), "level=WARN")
+	assert.Contains(t, out.String(), "something else")
+
+	// Recovering resets, so the same failure returning later warns again.
+	out.Reset()
+	lh.logLocalAddrsErr(nil)
+	assert.Empty(t, out.String())
+	lh.logLocalAddrsErr(errors.New("something else"))
+	assert.Contains(t, out.String(), "level=WARN")
+}

localaddrs.go

@@ -0,0 +1,13 @@
+//go:build !android
+
+package nebula
+
+import "net"
+
+func localInterfaces() ([]net.Interface, error) {
+	return net.Interfaces()
+}
+
+func localInterfaceAddrs(i *net.Interface) ([]net.Addr, error) {
+	return i.Addrs()
+}

localaddrs_android.go

@@ -0,0 +1,32 @@
+//go:build android
+
+package nebula
+
+import (
+	"net"
+
+	"github.com/wlynxg/anet"
+)
+
+// anet relies on //go:linkname and so needs -ldflags=-checklinkname=0 on Go 1.23+. Nebula ships no
+// Android binaries of its own, so that burden falls on consumers linking Android artifacts.
+
+func init() {
+	// anet only takes its bind-free path when it believes it is on API 30+, and detecting the running
+	// device's level requires cgo. Pin it so a CGO_ENABLED=0 build cannot quietly fall back to the
+	// denied path. The bind-free path is correct on older releases too, just unnecessary there.
+	anet.SetAndroidVersion(11)
+}
+
+// The app sandbox denies bind() on netlink_route_socket, so the stdlib's RTM_GETLINK enumeration
+// fails with EACCES and we advertise no underlay addresses at all. anet reads RTM_GETADDR from an
+// unbound socket instead, so this must not be collapsed back into net.Interfaces.
+func localInterfaces() ([]net.Interface, error) {
+	return anet.Interfaces()
+}
+
+// net.Interface.Addrs goes back through the denied netlink path, so addresses have to come from anet
+// as well. anet cannot report HardwareAddr, which localAddrs does not read.
+func localInterfaceAddrs(i *net.Interface) ([]net.Addr, error) {
+	return anet.InterfaceAddrsByInterface(i)
+}