Compare commits

..

2 Commits

Author SHA1 Message Date
pascal
ed58cfc63a handle envelop on grpc GetNetworkMap 2026-07-28 17:48:41 +02:00
Zoltan Papp
63c320b6a9 [client] Serialize iOS tunnel reconfiguration callbacks (#6870)
On iOS the tunnel reconfiguration (setTunnelNetworkSettings) was driven
from three independent Go paths without serialization: route prefix
updates via the route notifier's own delivery loop, interface IP/IPv6
set synchronously from the engine start goroutine, and DNS config
applied from the DNS apply chain through a separate Swift object. The
three sources mutated the shared Swift settings-manager state
concurrently and triggered overlapping updateTunnel() calls, losing or
half-applying route and DNS settings.

Introduce client/internal/tunnelnotifier: a single notifier that
implements both listener.NetworkChangeListener and dns.IosDnsManager,
queues all four callbacks (OnNetworkChanged, SetInterfaceIP,
SetInterfaceIPv6, ApplyDns) in one FIFO and delivers them one-by-one
from a single goroutine, so calls into Swift never overlap and arrive in
order. RunOniOS wraps the two Swift objects into the notifier and closes
it after the run loop exits.

The route notifier keeps its prefix dedup but delegates delivery to the
shared notifier instead of maintaining its own queue and loop; the dedup
check and the enqueue stay under one mutex so queue order matches
state-update order. Setting the interface IP becomes asynchronous, which
is safe: on iOS wgInterface.Create() only uses the TunFd, and the FIFO
preserves the IP -> routes/DNS relative order.

The package is build-tag free so the unit tests run on any platform
under -race. Android is unaffected: it receives all settings atomically
in one configureInterface call and serializes TUN rebuilds on a single
handler thread.

## Describe your changes

## Issue ticket number and link

## Stack

<!-- branch-stack -->

### Checklist
- [x] Is it a bug fix
- [ ] Is a typo/documentation fix
- [ ] Is a feature enhancement
- [x] It is a refactor
- [ ] Created tests that fail without the change (if possible)
- [ ] This change does **not** modify the public API, gRPC protocols,
functionality behavior, CLI / service flags, or introduce a new feature
— **OR** I have discussed it with the NetBird team beforehand (link the
issue / Slack thread in the description). See
[CONTRIBUTING.md](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTING.md#discuss-changes-with-the-netbird-team-first).

> By submitting this pull request, you confirm that you have read and
agree to the terms of the [Contributor License
Agreement](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT.md).

## Documentation
Select exactly one:

- [ ] I added/updated documentation for this change
- [x] Documentation is **not needed** for this change (explain why)

### Docs PR URL (required if "docs added" is checked)
Paste the PR link from https://github.com/netbirdio/docs here:

https://github.com/netbirdio/docs/pull/__

<!-- codesmith:footer -->
---
<a
href="https://app.blacksmith.sh/netbirdio/codesmith/netbird/pr/6870"><picture><source
media="(prefers-color-scheme: dark)"
srcset="https://pr-comments-assets.blacksmith.sh/codesmith/view-with-codesmith-dark-v2.svg"><source
media="(prefers-color-scheme: light)"
srcset="https://pr-comments-assets.blacksmith.sh/codesmith/view-with-codesmith-light-v2.svg"><img
alt="View with [code]smith"
src="https://pr-comments-assets.blacksmith.sh/codesmith/view-with-codesmith-dark-v2.svg"></picture></a>
<a
href="https://backend.blacksmith.sh/track/enable-autofix?expires=1787404610&installation_model_id=427504&pr_number=6870&repository=netbirdio%2Fnetbird&return_to=https%3A%2F%2Fgithub.com%2Fnetbirdio%2Fnetbird%2Fpull%2F6870&signature=7db66c4ec4262cc21137b3d3e1fd5e905950eab82ef46236a13ac3d512ff2a16"><picture><source
media="(prefers-color-scheme: dark)"
srcset="https://pr-comments-assets.blacksmith.sh/codesmith/autofix-with-codesmith-dark.svg"><source
media="(prefers-color-scheme: light)"
srcset="https://pr-comments-assets.blacksmith.sh/codesmith/autofix-with-codesmith-light.svg"><img
alt="Autofix with [code]smith"
src="https://pr-comments-assets.blacksmith.sh/codesmith/autofix-with-codesmith-dark.svg"></picture></a>
<sup>Need help on this PR? Tag <code>@codesmith-bot</code> with what you
need. Autofix is disabled.</sup>

<!-- codesmith:autofix:disabled -->
<!-- /codesmith:footer -->

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Improved iOS tunnel networking by coordinating network, interface,
route, and DNS updates through a unified notifier.
* Updated iOS behavior so route/prefix changes are applied immediately
instead of via queued/background delivery.

* **Bug Fixes**
* Improved reliability by ensuring network and DNS-related callbacks are
invoked in order without overlap.
* Ensured pending updates are drained and handled correctly during
shutdown.

* **Tests**
* Added coverage for FIFO ordering, non-overlapping callback execution,
interleaved DNS/route updates, and graceful shutdown behavior.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2026-07-28 16:51:01 +02:00
8 changed files with 375 additions and 381 deletions

View File

@@ -75,24 +75,6 @@ type Client struct {
connectClient *internal.ConnectClient
config *profilemanager.Config
cacheDir string
stateChangeMu sync.Mutex
stateChangeSubID string
eventSub *peer.EventSubscription
// Closed to stop the watch goroutines from delivering buffered items to a
// listener that has been removed or replaced. See stopStateChangeWatchLocked.
stateChangeDone chan struct{}
// Latched "the server wants an interactive login": survives the engine
// restarts that replace the run loop's context state. See Client.Status.
// Guarded by loginRequiredMu together with loginCleared, which counts
// clears so a stale observation cannot re-latch over one.
loginRequiredMu sync.Mutex
loginRequired bool
loginCleared uint64
extendMu sync.Mutex
extendCancel context.CancelFunc
}
func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cc *internal.ConnectClient) {
@@ -166,16 +148,11 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
if err != nil {
return err
}
// todo do not throw error in case of cancelled context
ctx = internal.CtxInitState(ctx)
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
c.setState(cfg, cacheDir, connectClient)
// This path runs the interactive SSO flow, so reaching here means the peer
// is authenticated again — release the latch Status() reports from. Clear
// only once the fresh connect client is installed: until then Status()
// still reads the previous run's context state, which holds the NeedsLogin
// that prompted this login, and would re-latch what was just cleared.
c.clearLoginRequired()
return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
}

View File

@@ -1,309 +0,0 @@
//go:build android
package android
import (
"context"
"fmt"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal"
"github.com/netbirdio/netbird/client/internal/auth"
"github.com/netbirdio/netbird/client/internal/auth/sessionwatch"
"github.com/netbirdio/netbird/client/internal/peer"
cProto "github.com/netbirdio/netbird/client/proto"
)
// StateChangeListener receives client state notifications.
//
// OnStateChanged is a payload-free wake-up whenever the state snapshot
// changed: connection state, the run-loop status label (e.g. NeedsLogin) or
// the session deadline. It mirrors the daemon's SubscribeStatus stream
// trigger — on each signal the consumer pulls the fresh values via
// Status() / SessionExpiresAtUnix().
//
// OnSessionExpiring forwards the engine's session-expiry warnings, fired at
// sessionwatch.WarningLead before the deadline and again at FinalWarningLead
// (finalWarning true). The second one is suppressed when the user dismissed
// the first via DismissSessionWarning. The daemon turns the same events into
// its tray notification.
type StateChangeListener interface {
OnStateChanged()
OnSessionExpiring(expiresAtUnix int64, leadMinutes int64, finalWarning bool)
}
// Status returns the connect run-loop's status label — the same value the
// desktop daemon serves in StatusResponse.Status. "NeedsLogin" means the
// management server rejected the peer and an interactive login is required.
//
// The label is latched: the run loop keeps its status in a per-run context
// state, which a restart replaces with a fresh Idle one, so an engine restart
// (network change, always-on) would otherwise erase the fact that the peer
// still needs to log in. Only a successful interactive login or extend clears
// it — see clearLoginRequired.
func (c *Client) Status() string {
latched, generation := c.loginRequiredState()
if latched {
return string(internal.StatusNeedsLogin)
}
cc := c.getConnectClient()
if cc == nil {
return string(internal.StatusIdle)
}
status := cc.Status()
if status == internal.StatusNeedsLogin {
c.latchLoginRequired(generation)
}
return string(status)
}
func (c *Client) loginRequiredState() (bool, uint64) {
c.loginRequiredMu.Lock()
defer c.loginRequiredMu.Unlock()
return c.loginRequired, c.loginCleared
}
// latchLoginRequired records a NeedsLogin observation, unless a clear landed
// while the caller was reading the run loop's status: cc.Status() is read
// outside the lock, so a login or extend completing in that window would
// otherwise be undone by this stale observation, stranding the UI on
// "login required" over a healthy session.
func (c *Client) latchLoginRequired(observedGeneration uint64) {
c.loginRequiredMu.Lock()
defer c.loginRequiredMu.Unlock()
if c.loginCleared != observedGeneration {
return
}
c.loginRequired = true
}
// clearLoginRequired releases the latch after a successful interactive login
// or session extend, and invalidates any observation already in flight.
func (c *Client) clearLoginRequired() {
c.loginRequiredMu.Lock()
defer c.loginRequiredMu.Unlock()
c.loginRequired = false
c.loginCleared++
}
// SessionExpiresAtUnix returns the SSO session deadline as unix seconds, or 0
// when no deadline is known (not SSO-registered, expiry disabled, or the
// engine has not received one yet). A past value means the session expired.
// Mirror of StatusResponse.sessionExpiresAt on the desktop daemon.
func (c *Client) SessionExpiresAtUnix() int64 {
deadline := c.recorder.GetSessionExpiresAt()
if deadline.IsZero() {
return 0
}
return deadline.Unix()
}
// SetStateChangeListener registers the state notification listener.
// Replaces any previously registered listener; remove it with
// RemoveStateChangeListener.
func (c *Client) SetStateChangeListener(listener StateChangeListener) {
c.stateChangeMu.Lock()
defer c.stateChangeMu.Unlock()
c.stopStateChangeWatchLocked()
if listener == nil {
return
}
// Both subscriptions are buffered (one pending tick, ten pending events),
// so unsubscribing is not enough to stop callbacks: the loops would drain
// what is already queued and deliver it to a listener the caller has
// already removed or replaced. Gate every callback on this registration's
// own signal, which is closed before unsubscribing.
done := make(chan struct{})
c.stateChangeDone = done
id, ch := c.recorder.SubscribeToStateChanges()
c.stateChangeSubID = id
// The channel is closed by UnsubscribeFromStateChanges, which ends the
// goroutine. Ticks are coalesced (buffer of one), so a burst of changes
// wakes the listener once.
go func() {
for range ch {
select {
case <-done:
return
default:
}
listener.OnStateChanged()
}
}()
c.eventSub = c.recorder.SubscribeToEvents()
go watchSessionWarnings(c.eventSub, listener, done)
}
// RemoveStateChangeListener unregisters the state notification listener.
func (c *Client) RemoveStateChangeListener() {
c.stateChangeMu.Lock()
defer c.stateChangeMu.Unlock()
c.stopStateChangeWatchLocked()
}
// DismissSessionWarning records the user's "Dismiss" on the first expiry
// warning and suppresses the final one for the current deadline. A refreshed
// deadline re-arms both. No-op while the engine is not running.
func (c *Client) DismissSessionWarning() {
cc := c.getConnectClient()
if cc == nil {
return
}
engine := cc.Engine()
if engine == nil {
return
}
engine.DismissSessionWarning()
}
// ExtendAuthSession runs the interactive SSO flow to obtain a fresh JWT and
// asks the management server to extend the session deadline. The tunnel is
// untouched: no resync, no reconnect. Async; the result arrives on the
// listener. Mirror of the daemon's RequestExtendAuthSession /
// WaitExtendAuthSession RPC pair, with URLOpener playing the "UI opens the
// browser" role.
//
// Only one flow may be in flight: the PKCE step binds a fixed loopback port,
// so a second concurrent flow would fail on that bind. Call
// CancelExtendAuthSession when the user abandons the browser.
func (c *Client) ExtendAuthSession(urlOpener URLOpener, isAndroidTV bool, resultListener ErrListener) {
ctx, err := c.beginExtend()
if err != nil {
resultListener.OnError(err)
return
}
go func() {
defer c.endExtend()
if err := c.extendAuthSession(ctx, urlOpener, isAndroidTV); err != nil {
resultListener.OnError(err)
return
}
resultListener.OnSuccess()
}()
}
// CancelExtendAuthSession aborts an in-flight ExtendAuthSession. The tunnel is
// left alone — unlike the login flow, which cancels the whole client context
// by stopping the engine. Without this the abandoned PKCE wait keeps its
// loopback port for the full flow timeout and blocks every later attempt.
// No-op when no flow is running.
func (c *Client) CancelExtendAuthSession() {
c.extendMu.Lock()
defer c.extendMu.Unlock()
if c.extendCancel != nil {
c.extendCancel()
}
}
func (c *Client) stopStateChangeWatchLocked() {
// Signal first, unsubscribe second: closing the channels only stops new
// items, and the loops would still hand whatever is buffered to a listener
// that is no longer registered.
if c.stateChangeDone != nil {
close(c.stateChangeDone)
c.stateChangeDone = nil
}
if c.stateChangeSubID != "" {
c.recorder.UnsubscribeFromStateChanges(c.stateChangeSubID)
c.stateChangeSubID = ""
}
if c.eventSub != nil {
// Closes the channel, which ends watchSessionWarnings.
c.recorder.UnsubscribeFromEvents(c.eventSub)
c.eventSub = nil
}
}
// watchSessionWarnings forwards the engine's session-expiry warnings to the
// listener. The event stream also carries unrelated traffic — network-map
// updates on every sync, DNS and route errors — so everything but an
// AUTHENTICATION event carrying the session-warning marker is dropped. Exits
// when the subscription is closed by UnsubscribeFromEvents, or earlier when
// done is closed — the stream buffers up to ten events, and a deregistered
// listener must not receive the ones already queued.
func watchSessionWarnings(sub *peer.EventSubscription, listener StateChangeListener, done <-chan struct{}) {
for ev := range sub.Events() {
select {
case <-done:
return
default:
}
if ev.GetCategory() != cProto.SystemEvent_AUTHENTICATION {
continue
}
meta := ev.GetMetadata()
if meta[sessionwatch.MetaSessionWarning] != "true" {
// Other AUTHENTICATION events exist (e.g. a deadline rejected as
// out of range); they carry no warning marker.
continue
}
deadline, err := sessionwatch.ParseExpiresAt(meta[sessionwatch.MetaSessionExpiresAt])
if err != nil {
log.Warnf("session warning event with unparsable deadline: %v", err)
continue
}
lead, err := sessionwatch.ParseLeadMinutes(meta[sessionwatch.MetaSessionLeadMinutes])
if err != nil {
// Informational only — the deadline above is what drives the UI.
lead = 0
}
listener.OnSessionExpiring(deadline.Unix(), int64(lead),
meta[sessionwatch.MetaSessionFinal] == "true")
}
}
func (c *Client) beginExtend() (context.Context, error) {
c.extendMu.Lock()
defer c.extendMu.Unlock()
if c.extendCancel != nil {
return nil, fmt.Errorf("session extend already in progress")
}
ctx, cancel := context.WithCancel(context.Background())
c.extendCancel = cancel
return ctx, nil
}
func (c *Client) endExtend() {
c.extendMu.Lock()
defer c.extendMu.Unlock()
if c.extendCancel != nil {
c.extendCancel()
c.extendCancel = nil
}
}
func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isAndroidTV bool) error {
cfg, _, cc := c.stateSnapshot()
if cfg == nil || cc == nil {
return fmt.Errorf("engine is not running")
}
engine := cc.Engine()
if engine == nil {
return fmt.Errorf("engine is not initialized")
}
authClient, err := auth.NewAuth(ctx, cfg.PrivateKey, cfg.ManagementURL, cfg)
if err != nil {
return fmt.Errorf("failed to create auth client: %v", err)
}
defer authClient.Close()
a := &Auth{ctx: ctx, config: cfg}
tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
if err != nil {
return fmt.Errorf("interactive sso login failed: %v", err)
}
if _, err := engine.ExtendAuthSession(ctx, tokenInfo.GetTokenToUse()); err != nil {
return err
}
c.clearLoginRequired()
go urlOpener.OnLoginSuccess()
return nil
}

View File

@@ -34,6 +34,7 @@ import (
"github.com/netbirdio/netbird/client/internal/profilemanager"
"github.com/netbirdio/netbird/client/internal/statemanager"
"github.com/netbirdio/netbird/client/internal/stdnet"
"github.com/netbirdio/netbird/client/internal/tunnelnotifier"
"github.com/netbirdio/netbird/client/internal/updater"
"github.com/netbirdio/netbird/client/internal/updater/installer"
nbnet "github.com/netbirdio/netbird/client/net"
@@ -136,10 +137,13 @@ func (c *ConnectClient) RunOniOS(
// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
debug.SetGCPercent(5)
notifier := tunnelnotifier.New(networkChangeListener, dnsManager)
defer notifier.Close()
mobileDependency := MobileDependency{
FileDescriptor: fileDescriptor,
NetworkChangeListener: networkChangeListener,
DnsManager: dnsManager,
NetworkChangeListener: notifier,
DnsManager: notifier,
StateFilePath: stateFilePath,
TempDir: cacheDir,
}

View File

@@ -11,12 +11,14 @@ import (
// MobileDependency collect all dependencies for mobile platform
type MobileDependency struct {
// Android only
TunAdapter device.TunAdapter
IFaceDiscover stdnet.ExternalIFaceDiscover
// Android and iOS
NetworkChangeListener listener.NetworkChangeListener
HostDNSAddresses []netip.AddrPort
DnsReadyListener dns.ReadyListener
// Android only
TunAdapter device.TunAdapter
IFaceDiscover stdnet.ExternalIFaceDiscover
HostDNSAddresses []netip.AddrPort
DnsReadyListener dns.ReadyListener
// iOS only
DnsManager dns.IosDnsManager

View File

@@ -3,7 +3,6 @@
package notifier
import (
"container/list"
"net/netip"
"slices"
"sort"
@@ -16,20 +15,12 @@ import (
type Notifier struct {
mu sync.Mutex
cond *sync.Cond
currentPrefixes []string
listener listener.NetworkChangeListener
queue *list.List
closed bool
}
func NewNotifier() *Notifier {
n := &Notifier{
queue: list.New(),
}
n.cond = sync.NewCond(&n.mu)
go n.deliverLoop()
return n
return &Notifier{}
}
func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
@@ -59,44 +50,19 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) {
sort.Strings(newNets)
n.mu.Lock()
defer n.mu.Unlock()
if slices.Equal(n.currentPrefixes, newNets) {
n.mu.Unlock()
return
}
n.currentPrefixes = newNets
routes := strings.Join(n.currentPrefixes, ",")
n.queue.PushBack(routes)
n.cond.Signal()
n.mu.Unlock()
if n.listener != nil {
n.listener.OnNetworkChanged(strings.Join(n.currentPrefixes, ","))
}
}
func (n *Notifier) Close() {
n.mu.Lock()
n.closed = true
n.cond.Signal()
n.mu.Unlock()
}
func (n *Notifier) GetInitialRouteRanges() []string {
return nil
}
func (n *Notifier) deliverLoop() {
for {
n.mu.Lock()
for n.queue.Len() == 0 && !n.closed {
n.cond.Wait()
}
if n.closed && n.queue.Len() == 0 {
n.mu.Unlock()
return
}
routes := n.queue.Remove(n.queue.Front()).(string)
l := n.listener
n.mu.Unlock()
if l != nil {
l.OnNetworkChanged(routes)
}
}
}

View File

@@ -0,0 +1,124 @@
package tunnelnotifier
import (
"container/list"
"sync"
"github.com/netbirdio/netbird/client/internal/dns"
"github.com/netbirdio/netbird/client/internal/listener"
)
type eventKind int
const (
eventRoutes eventKind = iota
eventIfaceIP
eventIfaceIPv6
eventDNS
)
var (
_ listener.NetworkChangeListener = (*Notifier)(nil)
_ dns.IosDnsManager = (*Notifier)(nil)
)
type event struct {
kind eventKind
payload string
}
type Notifier struct {
mu sync.Mutex
cond *sync.Cond
queue *list.List
closed bool
done chan struct{}
listener listener.NetworkChangeListener
dnsManager dns.IosDnsManager
}
func New(l listener.NetworkChangeListener, dm dns.IosDnsManager) *Notifier {
n := &Notifier{
queue: list.New(),
done: make(chan struct{}),
listener: l,
dnsManager: dm,
}
n.cond = sync.NewCond(&n.mu)
go n.deliverLoop()
return n
}
func (n *Notifier) OnNetworkChanged(routes string) {
n.enqueue(event{kind: eventRoutes, payload: routes})
}
func (n *Notifier) SetInterfaceIP(ip string) {
n.enqueue(event{kind: eventIfaceIP, payload: ip})
}
func (n *Notifier) SetInterfaceIPv6(ip string) {
n.enqueue(event{kind: eventIfaceIPv6, payload: ip})
}
func (n *Notifier) ApplyDns(config string) {
n.enqueue(event{kind: eventDNS, payload: config})
}
// Close stops accepting new events and blocks until the delivery loop has
// drained all queued events and exited.
func (n *Notifier) Close() {
n.mu.Lock()
n.closed = true
n.cond.Signal()
n.mu.Unlock()
<-n.done
}
func (n *Notifier) enqueue(ev event) {
n.mu.Lock()
defer n.mu.Unlock()
if n.closed {
return
}
n.queue.PushBack(ev)
n.cond.Signal()
}
func (n *Notifier) deliverLoop() {
defer close(n.done)
for {
n.mu.Lock()
for n.queue.Len() == 0 && !n.closed {
n.cond.Wait()
}
if n.closed && n.queue.Len() == 0 {
n.mu.Unlock()
return
}
ev := n.queue.Remove(n.queue.Front()).(event)
l := n.listener
dm := n.dnsManager
n.mu.Unlock()
switch ev.kind {
case eventRoutes:
if l != nil {
l.OnNetworkChanged(ev.payload)
}
case eventIfaceIP:
if l != nil {
l.SetInterfaceIP(ev.payload)
}
case eventIfaceIPv6:
if l != nil {
l.SetInterfaceIPv6(ev.payload)
}
case eventDNS:
if dm != nil {
dm.ApplyDns(ev.payload)
}
}
}
}

View File

@@ -0,0 +1,192 @@
package tunnelnotifier
import (
"fmt"
"sync"
"sync/atomic"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
type call struct {
kind string
payload string
}
type recorder struct {
mu sync.Mutex
calls []call
inFlight atomic.Int32
overlap atomic.Bool
delay time.Duration
}
func (r *recorder) record(kind, payload string) {
if r.inFlight.Add(1) != 1 {
r.overlap.Store(true)
}
if r.delay > 0 {
time.Sleep(r.delay)
}
r.mu.Lock()
r.calls = append(r.calls, call{kind: kind, payload: payload})
r.mu.Unlock()
r.inFlight.Add(-1)
}
func (r *recorder) count() int {
r.mu.Lock()
defer r.mu.Unlock()
return len(r.calls)
}
func (r *recorder) snapshot() []call {
r.mu.Lock()
defer r.mu.Unlock()
out := make([]call, len(r.calls))
copy(out, r.calls)
return out
}
type fakeListener struct {
rec *recorder
}
func (f *fakeListener) OnNetworkChanged(routes string) {
f.rec.record("routes", routes)
}
func (f *fakeListener) SetInterfaceIP(ip string) {
f.rec.record("ip", ip)
}
func (f *fakeListener) SetInterfaceIPv6(ip string) {
f.rec.record("ipv6", ip)
}
type fakeDNSManager struct {
rec *recorder
}
func (f *fakeDNSManager) ApplyDns(config string) {
f.rec.record("dns", config)
}
func TestFIFOOrder(t *testing.T) {
rec := &recorder{}
n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
defer n.Close()
n.SetInterfaceIP("10.0.0.1")
n.SetInterfaceIPv6("fd00::1")
n.ApplyDns(`{"domains":[]}`)
n.OnNetworkChanged("10.0.0.0/8,192.168.0.0/16")
n.ApplyDns(`{"domains":["example.com"]}`)
require.Eventually(t, func() bool { return rec.count() == 5 }, time.Second, time.Millisecond)
expected := []call{
{kind: "ip", payload: "10.0.0.1"},
{kind: "ipv6", payload: "fd00::1"},
{kind: "dns", payload: `{"domains":[]}`},
{kind: "routes", payload: "10.0.0.0/8,192.168.0.0/16"},
{kind: "dns", payload: `{"domains":["example.com"]}`},
}
assert.Equal(t, expected, rec.snapshot())
}
func TestNoOverlappingCalls(t *testing.T) {
rec := &recorder{delay: 100 * time.Microsecond}
n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
defer n.Close()
const producers = 8
const perProducer = 25
var wg sync.WaitGroup
for i := 0; i < producers; i++ {
wg.Add(1)
go func(id int) {
defer wg.Done()
for j := 0; j < perProducer; j++ {
payload := fmt.Sprintf("%d-%d", id, j)
switch j % 4 {
case 0:
n.OnNetworkChanged(payload)
case 1:
n.SetInterfaceIP(payload)
case 2:
n.SetInterfaceIPv6(payload)
case 3:
n.ApplyDns(payload)
}
}
}(i)
}
wg.Wait()
require.Eventually(t, func() bool { return rec.count() == producers*perProducer }, 5*time.Second, time.Millisecond)
assert.False(t, rec.overlap.Load())
}
func TestDNSAndRoutesInterleaved(t *testing.T) {
rec := &recorder{delay: 100 * time.Microsecond}
n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
defer n.Close()
const events = 50
var wg sync.WaitGroup
wg.Add(2)
go func() {
defer wg.Done()
for i := 0; i < events; i++ {
n.ApplyDns(fmt.Sprintf("dns-%d", i))
}
}()
go func() {
defer wg.Done()
for i := 0; i < events; i++ {
n.OnNetworkChanged(fmt.Sprintf("routes-%d", i))
}
}()
wg.Wait()
require.Eventually(t, func() bool { return rec.count() == 2*events }, 5*time.Second, time.Millisecond)
assert.False(t, rec.overlap.Load())
var dnsSeen, routesSeen int
for _, c := range rec.snapshot() {
switch c.kind {
case "dns":
assert.Equal(t, fmt.Sprintf("dns-%d", dnsSeen), c.payload)
dnsSeen++
case "routes":
assert.Equal(t, fmt.Sprintf("routes-%d", routesSeen), c.payload)
routesSeen++
}
}
assert.Equal(t, events, dnsSeen)
assert.Equal(t, events, routesSeen)
}
func TestCloseDrainsQueue(t *testing.T) {
rec := &recorder{delay: time.Millisecond}
n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
const events = 20
for i := 0; i < events; i++ {
n.OnNetworkChanged(fmt.Sprintf("routes-%d", i))
}
n.Close()
require.Equal(t, events, rec.count(), "Close must not return before all queued events are delivered")
n.OnNetworkChanged("after-close")
n.ApplyDns("after-close")
time.Sleep(50 * time.Millisecond)
assert.Equal(t, events, rec.count())
}

View File

@@ -25,6 +25,7 @@ import (
"github.com/netbirdio/netbird/encryption"
"github.com/netbirdio/netbird/shared/management/domain"
nbmgmtgrpc "github.com/netbirdio/netbird/shared/management/grpc"
nbnetworkmap "github.com/netbirdio/netbird/shared/management/networkmap"
"github.com/netbirdio/netbird/shared/management/proto"
"github.com/netbirdio/netbird/util/wsproxy"
)
@@ -472,11 +473,48 @@ func (c *GrpcClient) GetNetworkMap(sysInfo *system.Info) (*proto.NetworkMap, err
return nil, err
}
if decryptedResp.GetNetworkMap() == nil {
var nm *proto.NetworkMap
if version := decryptedResp.GetVersion(); version == int32(nbmgmtgrpc.ComponentNetworkMap) {
// Components-format peer: decode the envelope back to typed
// components, run Calculate() locally, and convert to the wire
// NetworkMap shape the rest of the engine consumes. Components are
// retained so future incremental updates can apply deltas instead
// of doing a full reconstruction.
envelope := decryptedResp.GetNetworkMapEnvelope()
if envelope == nil {
return nil, fmt.Errorf("received a SyncReponse indicating use of components network map, but components are missing")
}
localKey := c.key.String()
dnsName := ""
if pc := decryptedResp.GetPeerConfig(); pc != nil {
// PeerConfig.Fqdn = "<dns_label>.<dns_domain>" — extract the
// shared domain by stripping the peer's own label prefix. Falls
// back to empty if the FQDN doesn't have the expected shape.
dnsName = extractDNSDomainFromFQDN(pc.GetFqdn())
}
result, err := nbnetworkmap.EnvelopeToNetworkMap(c.ctx, envelope, localKey, dnsName)
if err != nil {
return nil, fmt.Errorf("decode network map envelope: %w", err)
}
nm = result.NetworkMap
} else {
nm = decryptedResp.GetNetworkMap()
}
if nm == nil {
return nil, fmt.Errorf("invalid msg, required network map")
}
return decryptedResp.GetNetworkMap(), nil
return nm, nil
}
func extractDNSDomainFromFQDN(fqdn string) string {
for i := 0; i < len(fqdn); i++ {
if fqdn[i] == '.' && i+1 < len(fqdn) {
return fqdn[i+1:]
}
}
return ""
}
func (c *GrpcClient) connectToSyncStream(ctx context.Context, serverPubKey wgtypes.Key, sysInfo *system.Info) (proto.ManagementService_SyncClient, error) {