Take Apple signing credentials from Secrets Manager

.github/workflows/release.yml

@@ -73,8 +73,11 @@ jobs:
   build-darwin:
     name: Build Universal Darwin
     env:
-      HAS_SIGNING_CREDS: ${{ secrets.AC_USERNAME != '' }}
+      HAS_SIGNING_CREDS: ${{ secrets.APPLE_SIGNING_ROLE_ARN != '' }}
     runs-on: macos-latest
+    permissions:
+      id-token: write
+      contents: read
     steps:
       - uses: actions/checkout@v7
 
@@ -83,17 +86,68 @@ jobs:
           go-version: '1.26'
           check-latest: true
 
+      # GitHub holds ARNs, not credentials, and ARNs outlive a rotation
+      - name: Configure AWS credentials
+        if: env.HAS_SIGNING_CREDS == 'true'
+        uses: aws-actions/configure-aws-credentials@v6
+        with:
+          role-to-assume: ${{ secrets.APPLE_SIGNING_ROLE_ARN }}
+          aws-region: us-east-2
+
+      # parse-json-secrets unpacks into SIGNING_* and ASC_*, masked on the way in
+      - name: Fetch signing credentials
+        if: env.HAS_SIGNING_CREDS == 'true'
+        uses: aws-actions/aws-secretsmanager-get-secrets@v3
+        with:
+          parse-json-secrets: true
+          secret-ids: |
+            SIGNING,${{ secrets.APPLE_SIGNING_DEVELOPER_ID_ARN }}
+            ASC,${{ secrets.APPLE_NOTARY_KEY_ARN }}
+
       - name: Import certificates
         if: env.HAS_SIGNING_CREDS == 'true'
         uses: Apple-Actions/import-codesign-certs@v7
         with:
-          p12-file-base64: ${{ secrets.APPLE_DEVELOPER_CERTIFICATE_P12_BASE64 }}
-          p12-password: ${{ secrets.APPLE_DEVELOPER_CERTIFICATE_PASSWORD }}
+          p12-file-base64: ${{ env.SIGNING_P12_BASE64 }}
+          p12-password: ${{ env.SIGNING_PASSWORD }}
+
+      # The action imports but does not check the chain validates, which is how a p12
+      # missing its intermediate reaches a failing codesign
+      - name: Check the identity is usable
+        if: env.HAS_SIGNING_CREDS == 'true'
+        run: |
+          : "${SIGNING_IDENTITY_SHA1:?empty, so the secret has no identity_sha1}"
+          identities=$(security find-identity -v -p codesigning signing_temp.keychain)
+          case "$identities" in
+          *"$SIGNING_IDENTITY_SHA1"*) ;;
+          *) printf '%s\n' "$identities" >&2; exit 1 ;;
+          esac
+
+      # notarytool wants the key as a file
+      - name: Write the App Store Connect key
+        if: env.HAS_SIGNING_CREDS == 'true'
+        run: |
+          mkdir -p ~/private_keys
+          chmod 700 ~/private_keys
+          key_path="$HOME/private_keys/AuthKey_${ASC_KEY_ID}.p8"
+          (umask 077; printf '%s\n' "$ASC_PRIVATE_KEY" > "$key_path")
+          echo "ASC_P8=$key_path" >> "$GITHUB_ENV"
+
+      - name: Drop the credentials from the environment
+        if: env.HAS_SIGNING_CREDS == 'true'
+        run: |
+          # The action's own inventory, so a new field in a secret is covered
+          python3 -c '
+          import json, os
+          raw = os.environ.get("SECRETS_LIST_CLEAN_UP")
+          if raw is None and os.environ.get("SIGNING_P12_BASE64"):
+              raise SystemExit("SECRETS_LIST_CLEAN_UP is gone, fetched secrets are not being scrubbed")
+          keep = {"SIGNING_IDENTITY_SHA1", "ASC_KEY_ID", "ASC_ISSUER_ID"}
+          names = [n for n in json.loads(raw or "[]") if n not in keep]
+          print("\n".join(f"{n}=" for n in dict.fromkeys(names)))
+          ' >> "$GITHUB_ENV"
 
       - name: Build, sign, and notarize
-        env:
-          AC_USERNAME: ${{ secrets.AC_USERNAME }}
-          AC_PASSWORD: ${{ secrets.AC_PASSWORD }}
         run: |
           rm -rf release
           mkdir release
@@ -102,17 +156,34 @@ jobs:
           lipo -create -output ./release/nebula ./build/darwin-amd64/nebula ./build/darwin-arm64/nebula
           lipo -create -output ./release/nebula-cert ./build/darwin-amd64/nebula-cert ./build/darwin-arm64/nebula-cert
 
-          if [ -n "$AC_USERNAME" ]; then
-            codesign -s "10BC1FDDEB6CE753550156C0669109FAC49E4D1E" -f -v --timestamp --options=runtime -i "net.defined.nebula" ./release/nebula
-            codesign -s "10BC1FDDEB6CE753550156C0669109FAC49E4D1E" -f -v --timestamp --options=runtime -i "net.defined.nebula-cert" ./release/nebula-cert
+          # Unset in a fork, which has no credentials to sign with
+          if [ -n "$SIGNING_IDENTITY_SHA1" ]; then
+            codesign -s "$SIGNING_IDENTITY_SHA1" -f -v --timestamp --options=runtime -i "net.defined.nebula" ./release/nebula
+            codesign -s "$SIGNING_IDENTITY_SHA1" -f -v --timestamp --options=runtime -i "net.defined.nebula-cert" ./release/nebula-cert
           fi
 
           zip -j release/nebula-darwin.zip release/nebula-cert release/nebula
 
-          if [ -n "$AC_USERNAME" ]; then
-            xcrun notarytool submit ./release/nebula-darwin.zip --team-id "576H3XS7FP" --apple-id "$AC_USERNAME" --password "$AC_PASSWORD" --wait
+          if [ -n "$ASC_P8" ]; then
+            xcrun notarytool submit ./release/nebula-darwin.zip --key "$ASC_P8" --key-id "$ASC_KEY_ID" --issuer "$ASC_ISSUER_ID" --wait
           fi
 
+      - name: Drop the signing key
+        if: always() && env.HAS_SIGNING_CREDS == 'true'
+        run: |
+          # Locked, not deleted: import-codesign-certs deletes it in its own post
+          # step and fails the job if it is already gone. Locked is unusable.
+          security lock-keychain signing_temp.keychain || true
+          rm -f "$ASC_P8"
+          # Nothing later in this job needs AWS
+          python3 -c '
+          import json, os
+          names = json.loads(os.environ.get("SECRETS_LIST_CLEAN_UP") or "[]")
+          names += ["ASC_P8", "SIGNING_IDENTITY_SHA1", "ASC_KEY_ID", "ASC_ISSUER_ID",
+                    "AWS_ACCESS_KEY_ID", "AWS_SECRET_ACCESS_KEY", "AWS_SESSION_TOKEN"]
+          print("\n".join(f"{n}=" for n in dict.fromkeys(names)))
+          ' >> "$GITHUB_ENV"
+
       - name: Upload artifacts
         uses: actions/upload-artifact@v7
         with:

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) OutRelay(h *HostInfo) {
-	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) Out(h *HostInfo) {
+	h.out.Store(true)
 }
 
 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.state.Load()&stateIn != 0))
+	assert.True(t, hostinfo.out.Load())
+	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.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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.False(t, hostinfo.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.True(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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.sentSinceCheck())
-	assert.False(t, hostinfo.isPendingDeletion())
+	assert.True(t, hostinfo.in.Load())
+	assert.True(t, hostinfo.out.Load())
+	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.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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.False(t, hostinfo.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.True(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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.state.Load()&stateIn != 0))
+	assert.True(t, hostinfo.out.Load())
+	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.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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.sentSinceCheck())
-	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.out.Load())
+	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()
-}

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
-
-	// Traffic bits, pendingDeletion, and the rebind epoch we last sent under
-	state atomic.Uint32
-
-	promoteCounter atomic.Uint32
-	remoteIndexId  uint32
-	localIndexId   uint32
-	remotes        *RemoteList
+	remoteIndexId   uint32
+	localIndexId    uint32
 
 	// 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

hostmap_test.go

@@ -401,43 +401,3 @@ func TestHostMap_RelayState(t *testing.T) {
 	assert.Equal(t, []netip.Addr{}, h1.relayState.relays)
 
 }
-
-func TestHostInfo_markOut(t *testing.T) {
-	h := &HostInfo{}
-	h.markOut(5) // stamped when the tunnel was added
-
-	// A tunnel already on the current epoch has nothing to report, which is what keeps a fresh tunnel from
-	// requerying on its first packet
-	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
-	assert.True(t, h.markOut(6), "a bumped epoch should report a move")
-	assert.False(t, h.markOut(6), "the epoch move should only be reported once")
-
-	// Traffic and pendingDeletion live in the same word and must survive an epoch change
-	h.setPendingDeletion(true)
-	h.markIn()
-	assert.True(t, h.markOut(7))
-	assert.True(t, h.isPendingDeletion(), "pendingDeletion must survive an epoch change")
-	in, out := h.takeTraffic()
-	assert.True(t, in, "inbound traffic must survive an epoch change")
-	assert.True(t, out)
-
-	// Clearing the traffic bits leaves the epoch alone, otherwise an idle tunnel would requery forever
-	assert.False(t, h.markOut(7), "takeTraffic must not disturb the epoch")
-}
-
-// 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.
-func TestHostInfo_markOutOnly(t *testing.T) {
-	h := &HostInfo{}
-	h.markOut(5)
-
-	h.markOutOnly()
-	assert.True(t, h.sentSinceCheck(), "a relayed send is still outbound traffic")
-	assert.False(t, h.markOut(5), "a relayed send must not disturb the epoch")
-
-	assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
-	assert.False(t, h.markOut(6))
-}

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
-	if f.connectionManager.Out(hostinfo) && t != header.CloseTunnel {
+	f.connectionManager.Out(hostinfo)
+
+	// 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
-	rebindEpoch atomic.Uint32
+	// rebindCount is used to decide if an active tunnel should trigger a punch notification through a lighthouse
+	rebindCount int8
 	version     string
 
 	conntrackCacheTimeout time.Duration