Files
netbird/client/iface/iface_test.go
Riccardo Manfrin 1e5b0a5c89 [client] Make Test_ConnectPeers deterministic under Docker/eBPF kernel / Darwin CI (#6884)
## Describe your changes

Make `Test_ConnectPeers` deterministic. Two issues, both surfaced once
the
privileged suite moved into a `--privileged` Docker container (#6425):

1. The peers used `getLocalIP()` as their WireGuard endpoint, i.e. the
host's
routable NIC IP (the docker bridge IP `172.17.0.2` in CI). That address
might
not hairpin reliably inside the container, so the handshake
intermittently
timed out (flaky). Use loopback (`127.1.0.x`) instead — always
self-reachable.
2. On a Linux runner with the WG kernel module the iface uses the eBPF
proxy
factory. Its manager is a singleton with one shared XDP program +
settings
map, so bringing up the two ifaces makes the second factory overwrite
the
first's `wg_port`/`proxy_port` and the handshake is dropped. The test is
   incompatible with the eBPF factory, so disable it via
`NB_DISABLE_EBPF_WG_PROXY` (peers then handshake directly over
loopback).
Running the suite across all three modes (eBPF / UDP proxy / ICE bind)
would
   need a larger refactor.

Also fixes a typo in the `ErrSharedSockStopped` message (`socked` →
`socket`).

## Issue ticket number and link

No public issue — CI flakiness follow-up to #6871 on `Test_ConnectPeers`

(https://github.com/netbirdio/netbird/blob/main/client/iface/iface_test.go).

## Stack

<!-- branch-stack -->

### Checklist
- [x] Is it a bug fix
- [ ] Is a typo/documentation fix
- [ ] Is a feature enhancement
- [ ] It is a refactor
- [ ] Created tests that fail without the change (if possible)

> 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)

Test-only change (plus a log-string typo). No public API, CLI, config,
or
behavior change.

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

N/A

<!-- codesmith:footer -->
---
<a
href="https://app.blacksmith.sh/netbirdio/codesmith/netbird/pr/6884"><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=1787485967&installation_model_id=427504&pr_number=6884&repository=netbirdio%2Fnetbird&return_to=https%3A%2F%2Fgithub.com%2Fnetbirdio%2Fnetbird%2Fpull%2F6884&signature=09fb996715d039bd02775a140e8cc03deca5cb42540790b82a744527264a30ad"><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

* **Bug Fixes**
* Corrected the “shared socket stopped” error message for clearer
output.
* **Tests**
* Improved peer connection test reliability in privileged CI by
disabling the eBPF WireGuard proxy and using fixed loopback UDP
endpoints for deterministic setup.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2026-07-24 15:23:22 +02:00

623 lines
12 KiB
Go

//go:build privileged
package iface
import (
"context"
"fmt"
"net"
"net/netip"
"strings"
"testing"
"time"
"github.com/google/uuid"
log "github.com/sirupsen/logrus"
"github.com/stretchr/testify/assert"
"golang.zx2c4.com/wireguard/wgctrl"
"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
"github.com/netbirdio/netbird/client/iface/device"
"github.com/netbirdio/netbird/client/iface/wgaddr"
"github.com/netbirdio/netbird/client/internal/stdnet"
)
// keep darwin compatibility
const (
WgIntNumber = 2000
)
var (
key string
peerPubKey string
)
func init() {
log.SetLevel(log.DebugLevel)
privateKey, _ := wgtypes.GeneratePrivateKey()
key = privateKey.String()
peerPrivateKey, _ := wgtypes.GeneratePrivateKey()
peerPubKey = peerPrivateKey.PublicKey().String()
}
func TestWGIface_UpdateAddr(t *testing.T) {
ifaceName := fmt.Sprintf("utun%d", WgIntNumber+4)
addr := "100.64.0.1/8"
wgPort := 33100
newNet, err := stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
opts := WGIFaceOpts{
IFaceName: ifaceName,
Address: wgaddr.MustParseWGAddress(addr),
WGPort: wgPort,
WGPrivKey: key,
MTU: DefaultMTU,
TransportNet: newNet,
}
iface, err := NewWGIFace(opts)
if err != nil {
t.Fatal(err)
}
err = iface.Create()
if err != nil {
t.Fatal(err)
}
defer func() {
err = iface.Close()
if err != nil {
t.Error(err)
}
}()
_, err = iface.Up()
if err != nil {
t.Fatal(err)
}
addrs, err := getIfaceAddrs(ifaceName)
if err != nil {
t.Error(err)
}
assert.Equal(t, addr, addrs[0].String())
//update WireGuard address
addr = "100.64.0.2/8"
err = iface.UpdateAddr(wgaddr.MustParseWGAddress(addr))
if err != nil {
t.Fatal(err)
}
addrs, err = getIfaceAddrs(ifaceName)
if err != nil {
t.Error(err)
}
var found bool
for _, a := range addrs {
prefix, err := netip.ParsePrefix(a.String())
assert.NoError(t, err)
if prefix.Addr().Is4() {
found = true
assert.Equal(t, addr, prefix.String())
}
}
if !found {
t.Fatal("v4 address not found")
}
}
func getIfaceAddrs(ifaceName string) ([]net.Addr, error) {
ief, err := net.InterfaceByName(ifaceName)
if err != nil {
return nil, err
}
addrs, err := ief.Addrs()
if err != nil {
return nil, err
}
return addrs, nil
}
func Test_CreateInterface(t *testing.T) {
ifaceName := fmt.Sprintf("utun%d", WgIntNumber+1)
wgIP := "10.99.99.1/32"
newNet, err := stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
opts := WGIFaceOpts{
IFaceName: ifaceName,
Address: wgaddr.MustParseWGAddress(wgIP),
WGPort: 33100,
WGPrivKey: key,
MTU: DefaultMTU,
TransportNet: newNet,
}
iface, err := NewWGIFace(opts)
if err != nil {
t.Fatal(err)
}
err = iface.Create()
if err != nil {
t.Fatal(err)
}
defer func() {
err = iface.Close()
if err != nil {
t.Error(err)
}
}()
wg, err := wgctrl.New()
if err != nil {
t.Fatal(err)
}
defer func() {
err = wg.Close()
if err != nil {
t.Error(err)
}
}()
}
func Test_Close(t *testing.T) {
ifaceName := fmt.Sprintf("utun%d", WgIntNumber+2)
wgIP := "10.99.99.2/32"
wgPort := 33100
newNet, err := stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
opts := WGIFaceOpts{
IFaceName: ifaceName,
Address: wgaddr.MustParseWGAddress(wgIP),
WGPort: wgPort,
WGPrivKey: key,
MTU: DefaultMTU,
TransportNet: newNet,
}
iface, err := NewWGIFace(opts)
if err != nil {
t.Fatal(err)
}
err = iface.Create()
if err != nil {
t.Fatal(err)
}
wg, err := wgctrl.New()
if err != nil {
t.Fatal(err)
}
defer func() {
err = wg.Close()
if err != nil {
t.Error(err)
}
}()
err = iface.Close()
if err != nil {
t.Fatal(err)
}
}
func TestRecreation(t *testing.T) {
for i := 0; i < 100; i++ {
t.Run(fmt.Sprintf("down-%d", i), func(t *testing.T) {
ifaceName := fmt.Sprintf("utun%d", WgIntNumber+2)
wgIP := "10.99.99.2/32"
wgPort := 33100
newNet, err := stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
opts := WGIFaceOpts{
IFaceName: ifaceName,
Address: wgaddr.MustParseWGAddress(wgIP),
WGPort: wgPort,
WGPrivKey: key,
MTU: DefaultMTU,
TransportNet: newNet,
}
iface, err := NewWGIFace(opts)
if err != nil {
t.Fatal(err)
}
for {
_, err = net.InterfaceByName(ifaceName)
if err != nil {
t.Logf("interface %s not found: err: %s", ifaceName, err)
break
}
t.Logf("interface %s found", ifaceName)
}
err = iface.Create()
if err != nil {
t.Fatal(err)
}
wg, err := wgctrl.New()
if err != nil {
t.Fatal(err)
}
defer func() {
err = wg.Close()
if err != nil {
t.Error(err)
}
}()
_, err = iface.Up()
if err != nil {
t.Fatal(err)
}
for {
_, err = net.InterfaceByName(ifaceName)
if err == nil {
t.Logf("interface %s found", ifaceName)
break
}
t.Logf("interface %s not found: err: %s", ifaceName, err)
}
start := time.Now()
err = iface.Close()
t.Logf("down time: %s", time.Since(start))
if err != nil {
t.Fatal(err)
}
})
}
}
func Test_ConfigureInterface(t *testing.T) {
ifaceName := fmt.Sprintf("utun%d", WgIntNumber+3)
wgIP := "10.99.99.5/30"
wgPort := 33100
newNet, err := stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
opts := WGIFaceOpts{
IFaceName: ifaceName,
Address: wgaddr.MustParseWGAddress(wgIP),
WGPort: wgPort,
WGPrivKey: key,
MTU: DefaultMTU,
TransportNet: newNet,
}
iface, err := NewWGIFace(opts)
if err != nil {
t.Fatal(err)
}
err = iface.Create()
if err != nil {
t.Fatal(err)
}
defer func() {
err = iface.Close()
if err != nil {
t.Error(err)
}
}()
_, err = iface.Up()
if err != nil {
t.Fatal(err)
}
wg, err := wgctrl.New()
if err != nil {
t.Fatal(err)
}
defer func() {
err = wg.Close()
if err != nil {
t.Error(err)
}
}()
wgDevice, err := wg.Device(ifaceName)
if err != nil {
t.Fatal(err)
}
if wgDevice.PrivateKey.String() != key {
t.Fatalf("Private keys don't match after configure: %s != %s", key, wgDevice.PrivateKey.String())
}
}
func Test_UpdatePeer(t *testing.T) {
ifaceName := fmt.Sprintf("utun%d", WgIntNumber+4)
wgIP := "10.99.99.9/30"
newNet, err := stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
opts := WGIFaceOpts{
IFaceName: ifaceName,
Address: wgaddr.MustParseWGAddress(wgIP),
WGPort: 33100,
WGPrivKey: key,
MTU: DefaultMTU,
TransportNet: newNet,
}
iface, err := NewWGIFace(opts)
if err != nil {
t.Fatal(err)
}
err = iface.Create()
if err != nil {
t.Fatal(err)
}
defer func() {
err = iface.Close()
if err != nil {
t.Error(err)
}
}()
_, err = iface.Up()
if err != nil {
t.Fatal(err)
}
keepAlive := 15 * time.Second
allowedIP := netip.MustParsePrefix("10.99.99.10/32")
endpoint, err := net.ResolveUDPAddr("udp", "127.0.0.1:9900")
if err != nil {
t.Fatal(err)
}
err = iface.UpdatePeer(peerPubKey, []netip.Prefix{allowedIP}, keepAlive, endpoint, nil)
if err != nil {
t.Fatal(err)
}
peer, err := getPeer(ifaceName, peerPubKey)
if err != nil {
t.Fatal(err)
}
if peer.PersistentKeepaliveInterval != keepAlive {
t.Fatal("configured peer with mismatched keepalive interval value")
}
if peer.Endpoint.String() != endpoint.String() {
t.Fatal("configured peer with mismatched endpoint")
}
var foundAllowedIP bool
for _, aip := range peer.AllowedIPs {
if aip.String() == allowedIP.String() {
foundAllowedIP = true
break
}
}
if !foundAllowedIP {
t.Fatal("configured peer with mismatched Allowed IPs")
}
}
func Test_RemovePeer(t *testing.T) {
ifaceName := fmt.Sprintf("utun%d", WgIntNumber+4)
wgIP := "10.99.99.13/30"
newNet, err := stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
opts := WGIFaceOpts{
IFaceName: ifaceName,
Address: wgaddr.MustParseWGAddress(wgIP),
WGPort: 33100,
WGPrivKey: key,
MTU: DefaultMTU,
TransportNet: newNet,
}
iface, err := NewWGIFace(opts)
if err != nil {
t.Fatal(err)
}
err = iface.Create()
if err != nil {
t.Fatal(err)
}
defer func() {
err = iface.Close()
if err != nil {
t.Error(err)
}
}()
_, err = iface.Up()
if err != nil {
t.Fatal(err)
}
keepAlive := 15 * time.Second
allowedIP := netip.MustParsePrefix("10.99.99.14/32")
err = iface.UpdatePeer(peerPubKey, []netip.Prefix{allowedIP}, keepAlive, nil, nil)
if err != nil {
t.Fatal(err)
}
err = iface.RemovePeer(peerPubKey)
if err != nil {
t.Fatal(err)
}
_, err = getPeer(ifaceName, peerPubKey)
if err.Error() != "peer not found" {
t.Fatal(err)
}
}
func Test_ConnectPeers(t *testing.T) {
t.Setenv("NB_DISABLE_EBPF_WG_PROXY", "true")
peer1ifaceName := fmt.Sprintf("utun%d", WgIntNumber+400)
peer1wgIP := netip.MustParsePrefix("10.99.99.17/30")
peer1Key, _ := wgtypes.GeneratePrivateKey()
peer1wgPort := 33100
peer2ifaceName := "utun500"
peer2wgIP := netip.MustParsePrefix("10.99.99.18/30")
peer2Key, _ := wgtypes.GeneratePrivateKey()
peer2wgPort := 33200
keepAlive := 1 * time.Second
newNet, err := stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
guid := fmt.Sprintf("{%s}", uuid.New().String())
device.CustomWindowsGUIDString = strings.ToLower(guid)
optsPeer1 := WGIFaceOpts{
IFaceName: peer1ifaceName,
Address: wgaddr.MustParseWGAddress(peer1wgIP.String()),
WGPort: peer1wgPort,
WGPrivKey: peer1Key.String(),
MTU: DefaultMTU,
TransportNet: newNet,
}
iface1, err := NewWGIFace(optsPeer1)
if err != nil {
t.Fatal(err)
}
err = iface1.Create()
if err != nil {
t.Fatal(err)
}
_, err = iface1.Up()
if err != nil {
t.Fatal(err)
}
localIP1 := "127.0.0.1"
peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP1, peer1wgPort))
if err != nil {
t.Fatal(err)
}
guid = fmt.Sprintf("{%s}", uuid.New().String())
device.CustomWindowsGUIDString = strings.ToLower(guid)
newNet, err = stdnet.NewNet(context.Background(), nil)
if err != nil {
t.Fatal(err)
}
optsPeer2 := WGIFaceOpts{
IFaceName: peer2ifaceName,
Address: wgaddr.MustParseWGAddress(peer2wgIP.String()),
WGPort: peer2wgPort,
WGPrivKey: peer2Key.String(),
MTU: DefaultMTU,
TransportNet: newNet,
}
iface2, err := NewWGIFace(optsPeer2)
if err != nil {
t.Fatal(err)
}
err = iface2.Create()
if err != nil {
t.Fatal(err)
}
_, err = iface2.Up()
if err != nil {
t.Fatal(err)
}
localIP2 := "127.0.0.1"
peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP2, peer2wgPort))
if err != nil {
t.Fatal(err)
}
defer func() {
err = iface1.Close()
if err != nil {
t.Error(err)
}
err = iface2.Close()
if err != nil {
t.Error(err)
}
}()
err = iface1.UpdatePeer(peer2Key.PublicKey().String(), []netip.Prefix{peer2wgIP}, keepAlive, peer2endpoint, nil)
if err != nil {
t.Fatal(err)
}
err = iface2.UpdatePeer(peer1Key.PublicKey().String(), []netip.Prefix{peer1wgIP}, keepAlive, peer1endpoint, nil)
if err != nil {
t.Fatal(err)
}
// The peers use userspace WireGuard (stdnet transport). A tight busy-loop
// here starves the wireguard-go goroutines that process the handshake, so
// poll on a ticker instead and yield the CPU between checks. WireGuard also
// only retries a lost handshake initiation every REKEY_TIMEOUT (5s), which
// is why the overall wait can occasionally stretch to tens of seconds.
timeout := 30 * time.Second
timeoutChannel := time.After(timeout)
ticker := time.NewTicker(500 * time.Millisecond)
defer ticker.Stop()
for {
peer, gpErr := getPeer(peer1ifaceName, peer2Key.PublicKey().String())
if gpErr != nil {
t.Fatal(gpErr)
}
if !peer.LastHandshakeTime.IsZero() {
t.Log("peers successfully handshake")
break
}
select {
case <-timeoutChannel:
t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
case <-ticker.C:
}
}
}
func getPeer(ifaceName, peerPubKey string) (wgtypes.Peer, error) {
wg, err := wgctrl.New()
if err != nil {
return wgtypes.Peer{}, err
}
defer func() {
err = wg.Close()
if err != nil {
log.Errorf("got error while closing wgctl: %v", err)
}
}()
wgDevice, err := wg.Device(ifaceName)
if err != nil {
return wgtypes.Peer{}, err
}
for _, peer := range wgDevice.Peers {
if peer.PublicKey.String() == peerPubKey {
return peer, nil
}
}
return wgtypes.Peer{}, fmt.Errorf("peer not found")
}