Files
netbird/client/internal/peer/conn_test.go
Riccardo Manfrin 39193396f5 [client] Fix WGWatcher silently failing to restart on fast disconnect/reconnect (#6664)
* Stick new watcher creation to actual existence of af the conn

and its removal to the removal of such same conn.
Avoid debouncing and cross lock dead locking

* Discriminate not updated from timeout handshakes

* [Recheck watcher ctx cancellation under conn.mu in onWGDisconnected

onWGDisconnected only checked conn.ctx (the engine-scoped context), never
the watcher's own context. disableWgWatcherIfNeeded cancels the wgWatcherCtx,
not conn.ctx, so a disabled watcher's timeout callback did not see the
cancellation.

handshakeCheck runs lock-free, so between the ctx check in periodicHandshakeCheck
and acquiring conn.mu a fast disconnect/reconnect can slip in: the stale watcher
then acquires the lock and tears down the *new*, healthy connection based on the
old timeout, forcing the guard into an unnecessary reconnect (flap).

Recheck watcherCtx.Err() under conn.mu so a superseded watcher exits without
touching the connection that replaced it.

* Remove verbose comments

* Fixup merge conflict leftovers

* Fixup context brought by onWGDisconnected
2026-07-14 10:21:59 +02:00

389 lines
11 KiB
Go

package peer
import (
"context"
"fmt"
"os"
"testing"
"time"
log "github.com/sirupsen/logrus"
"github.com/stretchr/testify/assert"
"github.com/netbirdio/netbird/client/iface"
"github.com/netbirdio/netbird/client/internal/peer/dispatcher"
"github.com/netbirdio/netbird/client/internal/peer/guard"
"github.com/netbirdio/netbird/client/internal/peer/ice"
"github.com/netbirdio/netbird/client/internal/stdnet"
"github.com/netbirdio/netbird/util"
)
var testDispatcher = dispatcher.NewConnectionDispatcher()
var connConf = ConnConfig{
Key: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
LocalKey: "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
Timeout: time.Second,
LocalWgPort: 51820,
ICEConfig: ice.Config{
InterfaceBlackList: nil,
},
}
func TestMain(m *testing.M) {
_ = util.InitLog("trace", util.LogConsole)
code := m.Run()
os.Exit(code)
}
func TestNewConn_interfaceFilter(t *testing.T) {
ignore := []string{iface.WgInterfaceDefault, "tun0", "zt", "ZeroTier", "utun", "wg", "ts",
"Tailscale", "tailscale"}
filter := stdnet.InterfaceFilter(ignore)
for _, s := range ignore {
assert.Equal(t, filter(s), false)
}
}
func TestConn_GetKey(t *testing.T) {
swWatcher := guard.NewSRWatcher(nil, nil, nil, connConf.ICEConfig)
sd := ServiceDependencies{
SrWatcher: swWatcher,
PeerConnDispatcher: testDispatcher,
}
conn, err := NewConn(connConf, sd)
if err != nil {
return
}
got := conn.GetKey()
assert.Equal(t, got, connConf.Key, "they should be equal")
}
func TestConn_OnRemoteOffer(t *testing.T) {
swWatcher := guard.NewSRWatcher(nil, nil, nil, connConf.ICEConfig)
sd := ServiceDependencies{
StatusRecorder: NewRecorder("https://mgm"),
SrWatcher: swWatcher,
PeerConnDispatcher: testDispatcher,
}
conn, err := NewConn(connConf, sd)
if err != nil {
return
}
onNewOfferChan := make(chan struct{})
conn.handshaker.AddRelayListener(func(remoteOfferAnswer *OfferAnswer) {
onNewOfferChan <- struct{}{}
})
conn.OnRemoteOffer(OfferAnswer{
IceCredentials: IceCredentials{
UFrag: "test",
Pwd: "test",
},
WgListenPort: 0,
Version: "",
})
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
select {
case <-onNewOfferChan:
// success
case <-ctx.Done():
t.Error("expected to receive a new offer notification, but timed out")
}
}
func TestConn_OnRemoteAnswer(t *testing.T) {
swWatcher := guard.NewSRWatcher(nil, nil, nil, connConf.ICEConfig)
sd := ServiceDependencies{
StatusRecorder: NewRecorder("https://mgm"),
SrWatcher: swWatcher,
PeerConnDispatcher: testDispatcher,
}
conn, err := NewConn(connConf, sd)
if err != nil {
return
}
onNewOfferChan := make(chan struct{})
conn.handshaker.AddRelayListener(func(remoteOfferAnswer *OfferAnswer) {
onNewOfferChan <- struct{}{}
})
conn.OnRemoteAnswer(OfferAnswer{
IceCredentials: IceCredentials{
UFrag: "test",
Pwd: "test",
},
WgListenPort: 0,
Version: "",
})
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
select {
case <-onNewOfferChan:
// success
case <-ctx.Done():
t.Error("expected to receive a new offer notification, but timed out")
}
}
func TestConn_presharedKey(t *testing.T) {
conn1 := Conn{
config: ConnConfig{
Key: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
LocalKey: "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
RosenpassConfig: RosenpassConfig{},
},
}
conn2 := Conn{
config: ConnConfig{
Key: "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
LocalKey: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
RosenpassConfig: RosenpassConfig{},
},
}
tests := []struct {
conn1Permissive bool
conn1RosenpassEnabled bool
conn2Permissive bool
conn2RosenpassEnabled bool
conn1ExpectedInitialKey bool
conn2ExpectedInitialKey bool
}{
{
conn1Permissive: false,
conn1RosenpassEnabled: false,
conn2Permissive: false,
conn2RosenpassEnabled: false,
conn1ExpectedInitialKey: false,
conn2ExpectedInitialKey: false,
},
{
conn1Permissive: false,
conn1RosenpassEnabled: true,
conn2Permissive: false,
conn2RosenpassEnabled: true,
conn1ExpectedInitialKey: true,
conn2ExpectedInitialKey: true,
},
{
conn1Permissive: false,
conn1RosenpassEnabled: true,
conn2Permissive: false,
conn2RosenpassEnabled: false,
conn1ExpectedInitialKey: true,
conn2ExpectedInitialKey: false,
},
{
conn1Permissive: false,
conn1RosenpassEnabled: false,
conn2Permissive: false,
conn2RosenpassEnabled: true,
conn1ExpectedInitialKey: false,
conn2ExpectedInitialKey: true,
},
{
conn1Permissive: true,
conn1RosenpassEnabled: true,
conn2Permissive: false,
conn2RosenpassEnabled: false,
conn1ExpectedInitialKey: false,
conn2ExpectedInitialKey: false,
},
{
conn1Permissive: false,
conn1RosenpassEnabled: false,
conn2Permissive: true,
conn2RosenpassEnabled: true,
conn1ExpectedInitialKey: false,
conn2ExpectedInitialKey: false,
},
{
conn1Permissive: true,
conn1RosenpassEnabled: true,
conn2Permissive: true,
conn2RosenpassEnabled: true,
conn1ExpectedInitialKey: true,
conn2ExpectedInitialKey: true,
},
{
conn1Permissive: false,
conn1RosenpassEnabled: false,
conn2Permissive: false,
conn2RosenpassEnabled: true,
conn1ExpectedInitialKey: false,
conn2ExpectedInitialKey: true,
},
{
conn1Permissive: false,
conn1RosenpassEnabled: true,
conn2Permissive: true,
conn2RosenpassEnabled: true,
conn1ExpectedInitialKey: true,
conn2ExpectedInitialKey: true,
},
}
conn1.config.RosenpassConfig.PermissiveMode = true
for i, test := range tests {
tcase := i + 1
t.Run(fmt.Sprintf("Rosenpass test case %d", tcase), func(t *testing.T) {
conn1.config.RosenpassConfig = RosenpassConfig{}
conn2.config.RosenpassConfig = RosenpassConfig{}
if test.conn1RosenpassEnabled {
conn1.config.RosenpassConfig.PubKey = []byte("dummykey")
}
conn1.config.RosenpassConfig.PermissiveMode = test.conn1Permissive
if test.conn2RosenpassEnabled {
conn2.config.RosenpassConfig.PubKey = []byte("dummykey")
}
conn2.config.RosenpassConfig.PermissiveMode = test.conn2Permissive
conn1PresharedKey := conn1.presharedKey(conn2.config.RosenpassConfig.PubKey)
conn2PresharedKey := conn2.presharedKey(conn1.config.RosenpassConfig.PubKey)
if test.conn1ExpectedInitialKey {
if conn1PresharedKey == nil {
t.Errorf("Case %d: Expected conn1 to have a non-nil key, but got nil", tcase)
}
} else {
if conn1PresharedKey != nil {
t.Errorf("Case %d: Expected conn1 to have a nil key, but got %v", tcase, conn1PresharedKey)
}
}
// Assert conn2's key expectation
if test.conn2ExpectedInitialKey {
if conn2PresharedKey == nil {
t.Errorf("Case %d: Expected conn2 to have a non-nil key, but got nil", tcase)
}
} else {
if conn2PresharedKey != nil {
t.Errorf("Case %d: Expected conn2 to have a nil key, but got %v", tcase, conn2PresharedKey)
}
}
})
}
}
func TestConn_presharedKey_RosenpassManaged(t *testing.T) {
conn := Conn{
config: ConnConfig{
Key: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
LocalKey: "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
RosenpassConfig: RosenpassConfig{PubKey: []byte("dummykey")},
},
}
// When Rosenpass has already initialized the PSK for this peer,
// presharedKey must return nil to avoid UpdatePeer overwriting it.
conn.rosenpassInitializedPresharedKeyValidator = func(peerKey string) bool { return true }
if k := conn.presharedKey([]byte("remote")); k != nil {
t.Fatalf("expected nil presharedKey when Rosenpass manages PSK, got %v", k)
}
// When Rosenpass hasn't taken over yet, presharedKey should provide
// a non-nil initial key (deterministic or from NetBird PSK).
conn.rosenpassInitializedPresharedKeyValidator = func(peerKey string) bool { return false }
if k := conn.presharedKey([]byte("remote")); k == nil {
t.Fatalf("expected non-nil presharedKey before Rosenpass manages PSK")
}
}
func newWGTimeoutTestConn(rosenpassEnabled bool, disconnected *[]string) *Conn {
cfg := ConnConfig{
Key: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
LocalKey: "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
WgConfig: WgConfig{RemoteKey: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU="},
}
if rosenpassEnabled {
cfg.RosenpassConfig = RosenpassConfig{PubKey: []byte("dummykey")}
}
conn := &Conn{
ctx: context.Background(),
config: cfg,
Log: log.WithField("peer", cfg.Key),
metricsStages: &MetricsStages{},
}
conn.SetOnDisconnected(func(remotePeer string) {
*disconnected = append(*disconnected, remotePeer)
})
return conn
}
// TestConn_onWGDisconnected_EscalatesToRosenpassReset: repeated handshake
// timeouts with rosenpass enabled mean the preshared keys have desynced. The
// renewal exchange runs over the dead tunnel and cannot resync them, so after
// wgTimeoutEscalationThreshold consecutive timeouts the conn must report the
// peer disconnected, dropping its rosenpass state so the next configuration
// programs the rendezvous key.
func TestConn_onWGDisconnected_EscalatesToRosenpassReset(t *testing.T) {
var disconnected []string
conn := newWGTimeoutTestConn(true, &disconnected)
for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
conn.onWGDisconnected(conn.ctx)
}
assert.Empty(t, disconnected, "escalation must not fire below the threshold")
conn.onWGDisconnected(conn.ctx)
assert.Equal(t, []string{conn.config.WgConfig.RemoteKey}, disconnected,
"reaching the threshold must report the peer disconnected once")
for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
conn.onWGDisconnected(conn.ctx)
}
assert.Len(t, disconnected, 1, "escalation must restart counting after firing")
conn.onWGDisconnected(conn.ctx)
assert.Len(t, disconnected, 2, "continued timeouts must escalate again")
}
// TestConn_onWGDisconnected_CheckSuccessResetsEscalation: a successful
// handshake between timeouts means the tunnel recovered; the counter must
// start over.
func TestConn_onWGDisconnected_CheckSuccessResetsEscalation(t *testing.T) {
var disconnected []string
conn := newWGTimeoutTestConn(true, &disconnected)
for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
conn.onWGDisconnected(conn.ctx)
}
conn.onWGCheckSuccess()
for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
conn.onWGDisconnected(conn.ctx)
}
assert.Empty(t, disconnected, "handshake success must reset the timeout count")
}
// TestConn_onWGDisconnected_NoEscalationWithoutRosenpass: without rosenpass
// there is no per-peer key state to reset; repeated timeouts must not report
// disconnects.
func TestConn_onWGDisconnected_NoEscalationWithoutRosenpass(t *testing.T) {
var disconnected []string
conn := newWGTimeoutTestConn(false, &disconnected)
for i := 0; i < wgTimeoutEscalationThreshold*3; i++ {
conn.onWGDisconnected(conn.ctx)
}
assert.Empty(t, disconnected, "escalation must be limited to rosenpass connections")
}