Files
tailscale/ipn/ipnlocal/node_backend_test.go
T
Brad FitzpatrickandBrendan Creane 2ae2808b64 ipn/ipnlocal: don't evict another node's index entries on netmap deltas
When applying netmap deltas, nodeBackend evicted its index entries
(nodeByAddr, nodeByKey, nodeByWGString, nodeByStableID, nodeByName)
derived from a node's last-known value without checking that the entry
still pointed at that node. Control can reassign a churning ephemeral
peer's Tailscale IP (or MagicDNS name) to a newer peer and deliver the
new peer's upsert before the old peer's removal, either in an earlier
MapResponse or reordered within one batch by the NodeID sort in
netmap.MutationsFromMapResponse. The removal then wiped the new
owner's entry.

The peers map itself stayed correct in every ordering, so WireGuard
kept the peer and handshakes succeeded, but WhoIs lookups by IP failed
until the next full netmap rebuilt the indexes. On App Connectors that
surfaced as "peerapi: unknown peer" and refused DNS connections from
affected clients, with a toggle of Tailscale (forcing a full netmap)
as the only recovery.

Make every index eviction conditional on the entry still mapping to
the node being removed or replaced, and add a regression test covering
the cross-batch, intra-batch, and upsert-eviction orderings.

Also add an end-to-end test in tstest/integration showing that a
MapResponse reusing an address is handled incrementally rather than as
a full netmap, and that LocalBackend.WhoIs still resolves the reused
address afterwards, which is the lookup PeerAPI makes before it
accepts a connection.

Updates tailscale/corp#47435

Co-authored-by: Brendan Creane <bcreane@gmail.com>
Signed-off-by: Brendan Creane <bcreane@gmail.com>
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
Change-Id: I3f8c2a9d41e07b6a5cd2e94f78b013c6ad2f5e91
2026-09-04 12:13:31 -07:00

717 lines
24 KiB
Go

// Copyright (c) Tailscale Inc & contributors
// SPDX-License-Identifier: BSD-3-Clause
package ipnlocal
import (
"context"
"errors"
"fmt"
"iter"
"maps"
"net/netip"
"slices"
"testing"
"time"
"tailscale.com/net/routecheck/peernode"
"tailscale.com/tailcfg"
"tailscale.com/tailcfg/nodecap"
"tailscale.com/tstest"
"tailscale.com/types/key"
"tailscale.com/types/netmap"
"tailscale.com/util/dnsname"
"tailscale.com/util/eventbus"
"tailscale.com/util/mak"
"tailscale.com/util/set"
)
func TestNodeBackendReadiness(t *testing.T) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
// The node backend is not ready until [nodeBackend.ready] is called,
// and [nodeBackend.Wait] should fail with [context.DeadlineExceeded].
ctx, cancelCtx := context.WithTimeout(context.Background(), 100*time.Millisecond)
defer cancelCtx()
if err := nb.Wait(ctx); err != ctx.Err() {
t.Fatalf("Wait: got %v; want %v", err, ctx.Err())
}
// Start a goroutine to wait for the node backend to become ready.
waitDone := make(chan struct{})
go func() {
if err := nb.Wait(context.Background()); err != nil {
t.Errorf("Wait: got %v; want nil", err)
}
close(waitDone)
}()
// Call [nodeBackend.ready] to indicate that the node backend is now ready.
go nb.ready()
// Once the backend is called, [nodeBackend.Wait] should return immediately without error.
if err := nb.Wait(context.Background()); err != nil {
t.Fatalf("Wait: got %v; want nil", err)
}
// And any pending waiters should also be unblocked.
<-waitDone
}
func TestNodeBackendShutdown(t *testing.T) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
shutdownCause := errors.New("test shutdown")
// Start a goroutine to wait for the node backend to become ready.
// This test expects it to block until the node backend shuts down
// and then return the specified shutdown cause.
waitDone := make(chan struct{})
go func() {
if err := nb.Wait(context.Background()); err != shutdownCause {
t.Errorf("Wait: got %v; want %v", err, shutdownCause)
}
close(waitDone)
}()
// Call [nodeBackend.shutdown] to indicate that the node backend is shutting down.
nb.shutdown(shutdownCause)
// Calling it again is fine, but should not change the shutdown cause.
nb.shutdown(errors.New("test shutdown again"))
// After shutdown, [nodeBackend.Wait] should return with the specified shutdown cause.
if err := nb.Wait(context.Background()); err != shutdownCause {
t.Fatalf("Wait: got %v; want %v", err, shutdownCause)
}
// The context associated with the node backend should also be cancelled
// and its cancellation cause should match the shutdown cause.
if err := nb.Context().Err(); !errors.Is(err, context.Canceled) {
t.Fatalf("Context.Err: got %v; want %v", err, context.Canceled)
}
if cause := context.Cause(nb.Context()); cause != shutdownCause {
t.Fatalf("Cause: got %v; want %v", cause, shutdownCause)
}
// And any pending waiters should also be unblocked.
<-waitDone
}
func TestNodeBackendReadyAfterShutdown(t *testing.T) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
shutdownCause := errors.New("test shutdown")
nb.shutdown(shutdownCause)
nb.ready() // Calling ready after shutdown is a no-op, but should not panic, etc.
if err := nb.Wait(context.Background()); err != shutdownCause {
t.Fatalf("Wait: got %v; want %v", err, shutdownCause)
}
}
func TestNodeBackendParentContextCancellation(t *testing.T) {
ctx, cancelCtx := context.WithCancel(context.Background())
nb := newNodeBackend(ctx, tstest.WhileTestRunningLogger(t), eventbus.New())
cancelCtx()
// Cancelling the parent context should cause [nodeBackend.Wait]
// to return with [context.Canceled].
if err := nb.Wait(context.Background()); !errors.Is(err, context.Canceled) {
t.Fatalf("Wait: got %v; want %v", err, context.Canceled)
}
// And the node backend's context should also be cancelled.
if err := nb.Context().Err(); !errors.Is(err, context.Canceled) {
t.Fatalf("Context.Err: got %v; want %v", err, context.Canceled)
}
}
func TestNodeBackendConcurrentReadyAndShutdown(t *testing.T) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
// Calling [nodeBackend.ready] and [nodeBackend.shutdown] concurrently
// should not cause issues, and [nodeBackend.Wait] should unblock,
// but the result of [nodeBackend.Wait] is intentionally undefined.
go nb.ready()
go nb.shutdown(errors.New("test shutdown"))
nb.Wait(context.Background())
}
func TestNodeBackendReachability(t *testing.T) {
for _, tc := range []struct {
name string
// Cap sets [tailcfg.NodeAttrClientSideReachability] on the self
// node.
//
// When disabled, the client relies on the control plane sending
// an accurate peer.Online flag. When enabled, the client
// ignores peer.Online and is forced to return true.
cap bool
// rchk sets [tailcfg.NodeAttrClientSideReachabilityRouteCheck]
// on the self node.
//
// When enabled with [tailcfg.NodeAttrClientSideReachability]
// above, the client ignores peer.Online and determines whether
// it can reach the peer node using [routecheck] reports.
rchk bool
online bool
pong peernode.Reachability
want bool
}{
{
name: "disabled/offline",
cap: false,
online: false,
want: false,
},
{
name: "disabled/online",
cap: false,
online: true,
want: true,
},
{
name: "forced/offline",
cap: true,
rchk: false,
online: false,
want: true,
},
{
name: "forced/online",
cap: true,
rchk: false,
online: true,
want: true,
},
{
name: "routecheck/offline/needs-probe",
cap: true,
rchk: true,
online: false,
pong: peernode.Unknown,
want: false,
},
{
name: "routecheck/offline/unreachable",
cap: true,
rchk: true,
online: false,
pong: peernode.Unreachable,
want: false,
},
{
name: "routecheck/offline/reachable",
cap: true,
rchk: true,
online: false,
pong: peernode.Reachable,
want: true,
},
{
name: "routecheck/online/needs-probe",
cap: true,
rchk: true,
online: true,
pong: peernode.Unknown,
want: true,
},
{
name: "routecheck/online/unreachable",
cap: true,
rchk: true,
online: true,
pong: peernode.Unreachable,
want: false,
},
{
name: "routecheck/online/reachable",
cap: true,
rchk: true,
online: true,
pong: peernode.Reachable,
want: true,
},
} {
t.Run(tc.name, func(t *testing.T) {
self := &tailcfg.Node{
ID: 1,
StableID: "stable1",
Name: "self",
}
if tc.cap {
mak.Set(&self.CapMap, nodecap.ClientSideReachability, nil)
}
if tc.rchk {
mak.Set(&self.CapMap, nodecap.ClientSideReachabilityRouteCheck, nil)
}
peer := &tailcfg.Node{
ID: 2,
StableID: "stable2",
Name: "peer",
Online: &tc.online,
}
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
nb.netMap = &netmap.NetworkMap{
SelfNode: self.View(),
Peers: []tailcfg.NodeView{peer.View()},
// HACK: AllCaps is usually populated by Control
AllCaps: set.SetOf(slices.Collect(maps.Keys(self.CapMap))),
}
got := nb.PeerIsReachable(routecheckReport(tc.pong), peer.View())
if got != tc.want {
t.Errorf("got %v, want %v", got, tc.want)
}
})
}
}
type routecheckReport peernode.Reachability
var _ RouteCheckReport = *new(routecheckReport)
func (rp routecheckReport) IsReachable(_ tailcfg.NodeID) peernode.Reachability {
return peernode.Reachability(rp)
}
func TestNodeBackendRouteManager(t *testing.T) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
mkPeer := func(id tailcfg.NodeID, stableID tailcfg.StableNodeID, addr4 string, extra ...string) tailcfg.NodeView {
n := &tailcfg.Node{
ID: id,
StableID: stableID,
Key: key.NewNode().Public(),
HomeDERP: 1, // required by the route manager's reachability filter
Addresses: []netip.Prefix{
netip.MustParsePrefix(addr4),
},
}
n.AllowedIPs = append(n.AllowedIPs, n.Addresses...)
for _, s := range extra {
n.AllowedIPs = append(n.AllowedIPs, netip.MustParsePrefix(s))
}
return n.View()
}
wantPeerFor := func(ip string, want tailcfg.NodeView) {
t.Helper()
got, ok := nb.routeMgr.Outbound().Lookup(netip.MustParseAddr(ip))
if !want.Valid() {
if ok {
t.Errorf("Outbound lookup %s = %v; want no match", ip, got)
}
return
}
if !ok || got.Key != want.Key() {
t.Errorf("Outbound lookup %s = %v, %v; want %v", ip, got, ok, want.Key())
}
}
p1 := mkPeer(1, "stable1", "100.64.0.1/32")
p2 := mkPeer(2, "stable2", "100.64.0.2/32", "0.0.0.0/0", "::/0")
// A full netmap populates the route manager.
nb.SetNetMap(&netmap.NetworkMap{Peers: []tailcfg.NodeView{p1, p2}})
wantPeerFor("100.64.0.1", p1)
wantPeerFor("100.64.0.2", p2)
wantPeerFor("8.8.8.8", tailcfg.NodeView{}) // exit node not selected
// Selecting peer 2 as the exit node resolves its stable ID and
// installs its /0 routes. The commit reports peer 2's allowed
// prefixes as changed.
if changed := nb.updateRouteManagerPrefs(routePrefs{ExitNodeID: "stable2", ExitNodeSelected: true}); len(changed) != 1 || changed[p2.Key()] == nil {
t.Errorf("updateRouteManagerPrefs(exit=stable2) changed = %v; want just %v", changed, p2.Key())
}
wantPeerFor("8.8.8.8", p2)
// A selected exit node that resolves to no current peer must
// blackhole internet traffic, not fall back to "no exit node":
// the default routes stay in the OS route set with no outbound
// peer to carry them. Peer 2's allowed prefixes lose the /0s,
// which the commit reports.
if changed := nb.updateRouteManagerPrefs(routePrefs{ExitNodeID: "no-such-node", ExitNodeSelected: true}); len(changed) != 1 || changed[p2.Key()] == nil {
t.Errorf("updateRouteManagerPrefs(exit=unresolved) changed = %v; want just %v", changed, p2.Key())
}
wantPeerFor("8.8.8.8", tailcfg.NodeView{})
if !nb.routeMgr.OSRoutes().Get(netip.MustParsePrefix("0.0.0.0/0")) {
t.Error("unresolved exit node: OSRoutes missing 0.0.0.0/0 blackhole route")
}
nb.updateRouteManagerPrefs(routePrefs{})
wantPeerFor("8.8.8.8", tailcfg.NodeView{})
if nb.routeMgr.OSRoutes().Get(netip.MustParsePrefix("0.0.0.0/0")) {
t.Error("no exit node: OSRoutes unexpectedly contains 0.0.0.0/0")
}
// Incremental deltas: add peer 3, remove peer 1.
p3 := mkPeer(3, "stable3", "100.64.0.3/32")
deltaRes, handled := nb.UpdateNetmapDelta([]netmap.NodeMutation{
netmap.NodeMutationUpsert{Node: p3},
netmap.MakeNodeMutationRemove(1),
})
if !handled {
t.Fatal("UpdateNetmapDelta not handled")
}
if changed := deltaRes.ChangedAllowedIPs; len(changed) != 2 || changed[p3.Key()] == nil {
t.Errorf("UpdateNetmapDelta changed = %v; want entries for %v and %v", changed, p3.Key(), p1.Key())
}
if v, ok := deltaRes.ChangedAllowedIPs[p1.Key()]; !ok || v != nil {
t.Errorf("UpdateNetmapDelta changed[%v] = %v, %v; want nil, true for removed peer", p1.Key(), v, ok)
}
wantPeerFor("100.64.0.3", p3)
wantPeerFor("100.64.0.1", tailcfg.NodeView{})
// A full netmap that drops a peer removes it from the route manager.
nb.SetNetMap(&netmap.NetworkMap{Peers: []tailcfg.NodeView{p2}})
wantPeerFor("100.64.0.3", tailcfg.NodeView{})
wantPeerFor("100.64.0.2", p2)
}
// TestNodeBackendDiscoChanged exercises the full-netmap disco change
// detection: a peer whose disco key changes has restarted and needs its
// WireGuard session to send an opportunistic handshake.
func TestNodeBackendDiscoChanged(t *testing.T) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
nk := key.NewNode().Public()
mkNetMap := func(disco key.DiscoPublic) *netmap.NetworkMap {
n := &tailcfg.Node{
ID: 1,
Key: nk,
DiscoKey: disco,
HomeDERP: 1,
}
return &netmap.NetworkMap{Peers: []tailcfg.NodeView{n.View()}}
}
newDisco := func() key.DiscoPublic { return key.NewDisco().Public() }
// A brand-new peer is not a disco change.
d1 := newDisco()
if got, _ := nb.SetNetMap(mkNetMap(d1)); len(got) != 0 {
t.Errorf("SetNetMap(new peer) discoChanged = %v; want none", got)
}
// A changed disco key requires a session reset.
d2 := newDisco()
if got, _ := nb.SetNetMap(mkNetMap(d2)); !slices.Contains(got, nk) {
t.Errorf("SetNetMap(changed disco) discoChanged = %v; want %v", got, nk)
}
// An unchanged disco key does not.
if got, _ := nb.SetNetMap(mkNetMap(d2)); len(got) != 0 {
t.Errorf("SetNetMap(same disco) discoChanged = %v; want none", got)
}
// Transitions to or from a zero disco key never reset.
if got, _ := nb.SetNetMap(mkNetMap(key.DiscoPublic{})); len(got) != 0 {
t.Errorf("SetNetMap(to zero disco) discoChanged = %v; want none", got)
}
if got, _ := nb.SetNetMap(mkNetMap(d1)); len(got) != 0 {
t.Errorf("SetNetMap(from zero disco) discoChanged = %v; want none", got)
}
}
// TestNodeBackendDiscoChangedDelta is like TestNodeBackendDiscoChanged
// but for the incremental path: disco changes arriving as
// [netmap.NodeMutationUpsert] deltas.
func TestNodeBackendDiscoChangedDelta(t *testing.T) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
mkNode := func(k key.NodePublic, disco key.DiscoPublic) tailcfg.NodeView {
return (&tailcfg.Node{ID: 1, Key: k, DiscoKey: disco, HomeDERP: 1}).View()
}
newDisco := func() key.DiscoPublic { return key.NewDisco().Public() }
apply := func(muts ...netmap.NodeMutation) set.Set[key.NodePublic] {
t.Helper()
deltaRes, handled := nb.UpdateNetmapDelta(muts)
if !handled {
t.Fatal("UpdateNetmapDelta not handled")
}
return deltaRes.DiscoChanged
}
nk := key.NewNode().Public()
d1 := newDisco()
nb.SetNetMap(&netmap.NetworkMap{Peers: []tailcfg.NodeView{mkNode(nk, d1)}})
// An upserted peer with a changed disco key needs a session reset.
d2 := newDisco()
if got := apply(netmap.NodeMutationUpsert{Node: mkNode(nk, d2)}); !got.Contains(nk) {
t.Errorf("upsert(changed disco) discoChanged = %v; want %v", got, nk)
}
// An unchanged disco key does not.
if got := apply(netmap.NodeMutationUpsert{Node: mkNode(nk, d2)}); len(got) != 0 {
t.Errorf("upsert(same disco) discoChanged = %v; want none", got)
}
// A node key rotation replaces the WireGuard peer outright, so no
// disco-based reset is reported.
nk2 := key.NewNode().Public()
if got := apply(netmap.NodeMutationUpsert{Node: mkNode(nk2, newDisco())}); len(got) != 0 {
t.Errorf("upsert(rotated node key) discoChanged = %v; want none", got)
}
}
func TestNodeBackendRouteManagerExtras(t *testing.T) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
n := &tailcfg.Node{
ID: 1,
Key: key.NewNode().Public(),
HomeDERP: 1,
Addresses: []netip.Prefix{
netip.MustParsePrefix("100.64.0.1/32"),
},
}
n.AllowedIPs = n.Addresses
p1 := n.View()
nb.SetNetMap(&netmap.NetworkMap{Peers: []tailcfg.NodeView{p1}})
transit := netip.MustParsePrefix("fe80::1234/128")
extrasFor := func(peers iter.Seq2[tailcfg.NodeID, key.NodePublic]) map[tailcfg.NodeID][]netip.Prefix {
var extras map[tailcfg.NodeID][]netip.Prefix
for id, k := range peers {
if k == p1.Key() {
mak.Set(&extras, id, []netip.Prefix{transit})
}
}
return extras
}
// Installing extras reports the peer's allowed prefixes as
// changed and adds the transit IP to the outbound table.
changed := nb.updateRouteManagerExtras(extrasFor)
if len(changed) != 1 || !slices.Contains(changed[p1.Key()], transit) {
t.Errorf("updateRouteManagerExtras changed = %v; want %v including %v", changed, p1.Key(), transit)
}
if pr, ok := nb.routeMgr.Outbound().Lookup(transit.Addr()); !ok || pr.Key != p1.Key() {
t.Errorf("Outbound lookup %v = %v, %v; want %v", transit.Addr(), pr, ok, p1.Key())
}
if nb.routeMgr.OSRoutes().Get(transit) {
t.Errorf("OSRoutes contains %v; extras must not reach the OS route set", transit)
}
// An unchanged hook result is a no-op.
if changed := nb.updateRouteManagerExtras(extrasFor); changed != nil {
t.Errorf("unchanged extras reported changes: %v", changed)
}
// A hook that no longer returns extras removes them.
changed = nb.updateRouteManagerExtras(func(iter.Seq2[tailcfg.NodeID, key.NodePublic]) map[tailcfg.NodeID][]netip.Prefix {
return nil
})
if len(changed) != 1 {
t.Errorf("clearing extras changed = %v; want just %v", changed, p1.Key())
}
if _, ok := nb.routeMgr.Outbound().Lookup(transit.Addr()); ok {
t.Errorf("Outbound still routes %v after extras cleared", transit.Addr())
}
}
// Tests the live MagicDNS lookup methods backing
// [resolver.MagicDNSHosts]: forward, reverse, and subdomain-cap
// lookups must serve from the node indexes and stay correct across
// netmap deltas without any full Hosts map rebuild.
func TestNodeBackendMagicDNSHosts(t *testing.T) {
t.Run("MagicDNS-enabled", func(t *testing.T) { testNodeBackendMagicDNSHosts(t, true) })
t.Run("MagicDNS-disabled", func(t *testing.T) { testNodeBackendMagicDNSHosts(t, false) })
}
func testNodeBackendMagicDNSHosts(t *testing.T, magicDNSEnabled bool) {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
self := &tailcfg.Node{
ID: 1,
Name: "self.example.ts.net.",
Addresses: []netip.Prefix{netip.MustParsePrefix("100.64.0.1/32")},
}
p1 := &tailcfg.Node{
ID: 2,
Key: key.NewNode().Public(),
Name: "p1.example.ts.net.",
Addresses: []netip.Prefix{
netip.MustParsePrefix("100.64.0.2/32"),
netip.MustParsePrefix("fd7a:115c:a1e0::2/128"),
},
CapMap: tailcfg.NodeCapMap{nodecap.DNSSubdomainResolve: nil},
}
nb.SetNetMap(&netmap.NetworkMap{
SelfNode: self.View(),
Peers: []tailcfg.NodeView{p1.View()},
DNS: tailcfg.DNSConfig{Proxied: magicDNSEnabled},
})
wantHost := func(fqdn dnsname.FQDN, want ...netip.Addr) {
t.Helper()
ips, ok := nb.magicDNSHostAddrs(fqdn)
if len(want) == 0 {
if ok {
t.Errorf("magicDNSHostAddrs(%q) = %v; want no match", fqdn, ips)
}
return
}
if !ok || !slices.Equal(ips, want) {
t.Errorf("magicDNSHostAddrs(%q) = %v, %v; want %v", fqdn, ips, ok, want)
}
}
// The self node has IPv4, so the peer's IPv6 address is
// filtered out (issue 1152).
wantHost("p1.example.ts.net.", netip.MustParseAddr("100.64.0.2"))
wantHost("self.example.ts.net.", netip.MustParseAddr("100.64.0.1"))
wantHost("unknown.example.ts.net.")
// Short names are only resolved if MagicDNS is enabled.
// Otherwise, the resolver should not serve any short names.
var shortNameAddr []netip.Addr
if magicDNSEnabled {
shortNameAddr = []netip.Addr{netip.MustParseAddr("100.64.0.2")}
}
wantHost("p1.", shortNameAddr...)
if fqdn, ok := nb.magicDNSPTR(netip.MustParseAddr("100.64.0.2")); !ok || fqdn != "p1.example.ts.net." {
t.Errorf("magicDNSPTR(100.64.0.2) = %q, %v; want p1's name", fqdn, ok)
}
if got, want := nb.magicDNSSubdomainHost("p1.example.ts.net."), true; got != want {
t.Errorf("magicDNSSubdomainHost(p1) = %v; want %v", got, want)
}
if got, want := nb.magicDNSSubdomainHost("self.example.ts.net."), false; got != want {
t.Errorf("magicDNSSubdomainHost(self) = %v; want %v", got, want)
}
// Removing the peer via a delta drops its records.
if _, handled := nb.UpdateNetmapDelta([]netmap.NodeMutation{netmap.MakeNodeMutationRemove(2)}); !handled {
t.Fatal("UpdateNetmapDelta not handled")
}
wantHost("p1.example.ts.net.")
if fqdn, ok := nb.magicDNSPTR(netip.MustParseAddr("100.64.0.2")); ok {
t.Errorf("magicDNSPTR(100.64.0.2) after removal = %q; want no match", fqdn)
}
// Adding a peer via a delta serves it immediately.
p3 := &tailcfg.Node{
ID: 3,
Key: key.NewNode().Public(),
Name: "p3.example.ts.net.",
Addresses: []netip.Prefix{netip.MustParsePrefix("100.64.0.3/32")},
}
if _, handled := nb.UpdateNetmapDelta([]netmap.NodeMutation{netmap.NodeMutationUpsert{Node: p3.View()}}); !handled {
t.Fatal("UpdateNetmapDelta not handled")
}
wantHost("p3.example.ts.net.", netip.MustParseAddr("100.64.0.3"))
// Renaming a peer arrives as an upsert of the full node with a
// new Name. The old name must stop resolving and the new one
// must start (tailscale/corp#45631).
p3renamed := p3.Clone()
p3renamed.Name = "p3-renamed.example.ts.net."
if _, handled := nb.UpdateNetmapDelta([]netmap.NodeMutation{netmap.NodeMutationUpsert{Node: p3renamed.View()}}); !handled {
t.Fatal("UpdateNetmapDelta not handled")
}
wantHost("p3-renamed.example.ts.net.", netip.MustParseAddr("100.64.0.3"))
wantHost("p3.example.ts.net.")
if fqdn, ok := nb.magicDNSPTR(netip.MustParseAddr("100.64.0.3")); !ok || fqdn != "p3-renamed.example.ts.net." {
t.Errorf("magicDNSPTR(100.64.0.3) after rename = %q, %v; want p3's new name", fqdn, ok)
}
}
// TestNodeBackendIndexReuseEviction exercises netmap delta orderings in
// which one peer's address, name, or key index entry is claimed by a
// second peer before the first peer's entries are evicted. The eviction
// must keep the second peer's entries, or lookups by IP (WhoIs, and thus
// PeerAPI and App Connector DNS) would fail until the next full netmap,
// even though the peers map and the WireGuard config remain correct.
func TestNodeBackendIndexReuseEviction(t *testing.T) {
addr := netip.MustParseAddr("100.64.0.1")
mkPeer := func(id tailcfg.NodeID, a netip.Addr) tailcfg.NodeView {
return (&tailcfg.Node{
ID: id,
StableID: tailcfg.StableNodeID(fmt.Sprintf("stable%d", id)),
Key: makeNodeKeyFromID(id),
Name: "runner.example.ts.net.",
HomeDERP: 1,
Addresses: []netip.Prefix{netip.PrefixFrom(a, a.BitLen())},
}).View()
}
newBackend := func(t *testing.T, initial ...tailcfg.NodeView) *nodeBackend {
nb := newNodeBackend(t.Context(), tstest.WhileTestRunningLogger(t), eventbus.New())
nb.SetNetMap(&netmap.NetworkMap{Peers: initial})
return nb
}
apply := func(t *testing.T, nb *nodeBackend, muts ...netmap.NodeMutation) {
t.Helper()
if _, handled := nb.UpdateNetmapDelta(muts); !handled {
t.Fatal("UpdateNetmapDelta not handled")
}
}
wantAddr := func(t *testing.T, nb *nodeBackend, a netip.Addr, want tailcfg.NodeID) {
t.Helper()
got, ok := nb.NodeByAddr(a)
if want == 0 {
if ok {
t.Errorf("NodeByAddr(%v) = %v; want no match", a, got)
}
return
}
if !ok || got != want {
t.Errorf("NodeByAddr(%v) = %v, %v; want %v", a, got, ok, want)
}
}
t.Run("remove-after-reuse", func(t *testing.T) {
// Peer 1 owns the address. Control reassigns it (and the
// MagicDNS name) to new peer 2 in one delta batch and removes
// peer 1 in a later batch, as happens with churning ephemeral
// peers. The removal of peer 1 must not evict peer 2's claims.
nb := newBackend(t, mkPeer(1, addr))
apply(t, nb, netmap.NodeMutationUpsert{Node: mkPeer(2, addr)})
apply(t, nb, netmap.MakeNodeMutationRemove(1))
wantAddr(t, nb, addr, 2)
if nid, ok := nb.NodeByName("runner.example.ts.net"); !ok || nid != 2 {
t.Errorf("NodeByName = %v, %v; want 2", nid, ok)
}
if nid, ok := nb.NodeByKey(makeNodeKeyFromID(2)); !ok || nid != 2 {
t.Errorf("NodeByKey(peer 2) = %v, %v; want 2", nid, ok)
}
if nid, ok := nb.NodeByKey(makeNodeKeyFromID(1)); ok {
t.Errorf("NodeByKey(peer 1) = %v; want no match after removal", nid)
}
// Removing the current owner still evicts.
apply(t, nb, netmap.MakeNodeMutationRemove(2))
wantAddr(t, nb, addr, 0)
})
t.Run("single-response-sort-order", func(t *testing.T) {
// Within one MapResponse, MutationsFromMapResponse sorts by
// NodeID, which can order the upsert of the address's new
// owner before the removal of its old owner.
nb := newBackend(t, mkPeer(10, addr))
muts, ok := netmap.MutationsFromMapResponse(&tailcfg.MapResponse{
PeersRemoved: []tailcfg.NodeID{10},
PeersChanged: []*tailcfg.Node{mkPeer(2, addr).AsStruct()},
}, time.Unix(123, 0))
if !ok {
t.Fatal("MutationsFromMapResponse failed")
}
apply(t, nb, muts...)
wantAddr(t, nb, addr, 2)
})
t.Run("upsert-eviction", func(t *testing.T) {
// Peer 2 claims peer 1's address. A later upsert of peer 1
// with a new address evicts entries derived from peer 1's old
// value, which must not include peer 2's claim.
nb := newBackend(t, mkPeer(1, addr))
apply(t, nb, netmap.NodeMutationUpsert{Node: mkPeer(2, addr)})
addr2 := netip.MustParseAddr("100.64.0.9")
apply(t, nb, netmap.NodeMutationUpsert{Node: mkPeer(1, addr2)})
wantAddr(t, nb, addr, 2)
wantAddr(t, nb, addr2, 1)
})
}