Adopt the tunnel as a mesh fact, refuse a mismatched takeover, and rekey after enrolment

Review of the ADR 0105 build (hq ADR 0105). Four things it got wrong and one path it lacked: - A predecessor spoke's tunnel names one peer, the hub, routed the whole range; recording refused it and the whole enrolment failed. Range-routed peers are skipped now — only the hub's peers are ever carried. - The range and the carried peers were conditions on the node being adopted, so converging the hub would have renumbered the mesh and dropped the peers still reaching it. They are facts of the tunnel record now, mode aside; the takeover alone is declared to an adopted node. Converging the hub is refused while a carried peer has not enrolled, naming it. - A push composed a takeover for a hub whose address or endpoint disagreed with the tunnel, which would have the host stop the found interface and raise the mesh's where no peer listens. The graph refuses to compose it, naming both and the placement that fixes it. - The host's account said taken or not; "found down and the mesh's not up" read as not taken. Three states now, and an account on every takeover. - A hub that enrolled before this feature holds a key of its own, and re-enrolling would rotate every key the mesh sealed credentials to. A node now rekeys in a report, signed with its identity key over the key it leaves, the key it takes and the tunnel; the mesh verifies against the live key, refuses a stale or foreign proof, records key and tunnel, and moves a hub to the tunnel's address. `overlay show` names the path for a hub that found no tunnel. Also: a carried IPv6 peer is routed /128, and identity.ForTest exists so the link can be tested against a real identity store.
2026-09-24 00:02:07 +02:00
parent 3c836f0abb
commit 4566c5c9aa
11 changed files with 641 additions and 49 deletions
@@ -157,19 +157,123 @@ func TestATunnelUnderAnotherKeyIsNotAdopted(t *testing.T) {
 	}
 }

-func TestAPeerRoutedARangeIsRefused(t *testing.T) {
+func TestAPeerRoutedARangeIsNotCarried(t *testing.T) {
+	// A peer routed a whole range is a spoke's view of its hub, never a machine with an address
+	// the mesh could carry: skipped, and the single-address peers beside it kept.
 	inv := fresh(t)
 	hub, err := inv.AddNodeAs(t.Context(), "anchor", true)
 	if err != nil {
 		t.Fatal(err)
 	}
 	found := theFoundTunnel()
-	found.Peers = append(found.Peers, TunnelPeer{PublicKey: "WIDE", Address: "198.51.100.0/24"})
-	err = inv.RecordTunnel(t.Context(), hub.ID, found)
-	if err == nil || !strings.Contains(err.Error(), "names a range") {
-		t.Fatalf("a peer routed a whole range was recorded as a machine with an address: %v", err)
+	found.Peers = append(found.Peers, TunnelPeer{PublicKey: "WIDE", Address: "192.0.2.0/24"})
+	if err := inv.RecordTunnel(t.Context(), hub.ID, found); err != nil {
+		t.Fatal(err)
 	}
-	if _, err := inv.TunnelOf(t.Context(), "anchor"); !errors.Is(err, ErrNoTunnel) {
-		t.Fatalf("a refused tunnel was recorded anyway: %v", err)
+	got, err := inv.TunnelOf(t.Context(), "anchor")
+	if err != nil || len(got.Peers) != 2 {
+		t.Fatalf("the range-routed peer was carried, or the others dropped: %+v %v", got.Peers, err)
+	}
+	// A single address outside the tunnel's range is still refused: it is not a peer this tunnel
+	// routes to.
+	found.Peers = []TunnelPeer{{PublicKey: "ELSEWHERE", Address: "198.51.100.7/32"}}
+	if err := inv.RecordTunnel(t.Context(), hub.ID, found); err == nil || !strings.Contains(err.Error(), "outside") {
+		t.Fatalf("a peer outside the range was recorded: %v", err)
+	}
+}
+
+// A predecessor spoke's tunnel has one peer — the hub — routed the whole range. Its enrolment must
+// not fail on it: only the hub's peers are ever carried, so a range-routed peer is skipped.
+func TestASpokesTunnelEnrolsWithItsHubPeerSkipped(t *testing.T) {
+	inv := fresh(t)
+	anAdoptedHub(t, inv)
+	spoke, err := inv.AddNodeAs(t.Context(), "home-server", true)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := inv.RecordOverlayKey(t.Context(), spoke.ID, peerThree); err != nil {
+		t.Fatal(err)
+	}
+	if err := inv.RecordTunnel(t.Context(), spoke.ID, Tunnel{
+		Interface: "wg0", Unit: "wg-quick@wg0", Config: "/etc/wireguard/wg0.conf", Port: 51900,
+		Address: "192.0.2.3/24", Range: "192.0.2.0/24", PublicKey: peerThree,
+		Peers: []TunnelPeer{{PublicKey: tunnelKey, Address: "192.0.2.0/24"}},
+	}); err != nil {
+		t.Fatalf("a spoke-shaped tunnel was refused: %v", err)
+	}
+	got, err := inv.TunnelOf(t.Context(), "home-server")
+	if err != nil || len(got.Peers) != 0 {
+		t.Fatalf("the spoke's hub was recorded as a peer to carry: %+v %v", got.Peers, err)
+	}
+	// Nothing about the hub's carried peers changed: still two, one now enrolled.
+	carried, err := inv.CarriedPeers(t.Context())
+	if err != nil || len(carried) != 2 {
+		t.Fatalf("carried peers: %+v %v", carried, err)
+	}
+	if address, err := inv.AssignAddress(t.Context(), spoke.ID, "192.0.2.0/24"); err != nil || address != "192.0.2.3" {
+		t.Fatalf("the spoke did not keep its address: %s %v", address, err)
+	}
+}
+
+// Converging the hub flips its mode and nothing else: the range stays the tunnel's and the peers
+// stay carried, or the mesh would renumber itself and drop the peers still reaching it.
+func TestConvergingTheHubKeepsTheRangeAndTheCarriedPeers(t *testing.T) {
+	inv := fresh(t)
+	hub := anAdoptedHub(t, inv)
+	if _, err := inv.AssignAddress(t.Context(), hub.ID, "192.0.2.0/24"); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := inv.Converge(t.Context(), "anchor"); err != nil {
+		t.Fatal(err)
+	}
+	tunnel, _, adopted, err := inv.AdoptedTunnel(t.Context())
+	if err != nil || !adopted || tunnel.Range != "192.0.2.0/24" {
+		t.Fatalf("converging renumbered the mesh: adopted=%t %+v %v", adopted, tunnel, err)
+	}
+	if carried, err := inv.CarriedPeers(t.Context()); err != nil || len(carried) != 2 {
+		t.Fatalf("converging dropped the carried peers: %+v %v", carried, err)
+	}
+	found, err := inv.Tunnels(t.Context())
+	if err != nil || found["anchor"].NodeAdopted {
+		t.Fatalf("a converged hub still reads as adopted for the takeover: %+v %v", found, err)
+	}
+}
+
+// A hub that enrolled with a key of its own takes the tunnel over afterwards by rekeying: the key
+// and the tunnel are recorded, the hub moves to the tunnel's address, and the same rekey applied
+// again is stale.
+func TestARekeyTakesTheTunnelOverAfterEnrolment(t *testing.T) {
+	inv := fresh(t)
+	hub, err := inv.AddNodeAs(t.Context(), "anchor", true)
+	if err != nil {
+		t.Fatal(err)
+	}
+	const own = "THE-MESHS-OWN-KEY======================="
+	if err := inv.RecordOverlayKey(t.Context(), hub.ID, own); err != nil {
+		t.Fatal(err)
+	}
+	if err := inv.SetPlace(t.Context(), "anchor", "anchor.example:51900", "hosting", true, ""); err != nil {
+		t.Fatal(err)
+	}
+	if address, err := inv.AssignAddress(t.Context(), hub.ID, "10.42.0.0/16"); err != nil || address != "10.42.0.1" {
+		t.Fatalf("before the rekey the hub is on the mesh's own range: %s %v", address, err)
+	}
+
+	if err := inv.Rekey(t.Context(), hub.ID, own, tunnelKey, theFoundTunnel()); err != nil {
+		t.Fatal(err)
+	}
+	_, _, adopted, err := inv.AdoptedTunnel(t.Context())
+	if err != nil || !adopted {
+		t.Fatalf("the tunnel is not adopted after the rekey (%v)", err)
+	}
+	placed, err := inv.Overlays(t.Context())
+	if err != nil || len(placed) != 1 || placed[0].Address != "192.0.2.1" || placed[0].Key != tunnelKey {
+		t.Fatalf("the hub did not move to the tunnel's address under the tunnel's key: %+v %v", placed, err)
+	}
+	if err := inv.Rekey(t.Context(), hub.ID, own, tunnelKey, theFoundTunnel()); !errors.Is(err, ErrStaleRekey) {
+		t.Fatalf("the same rekey applied again was not refused as stale: %v", err)
+	}
+	if err := inv.Rekey(t.Context(), hub.ID, tunnelKey, "ANOTHER-KEY=============================", theFoundTunnel()); err == nil {
+		t.Fatal("a rekey to a key that is not the tunnel's was accepted")
 	}
 }