Compare commits

..

5 Commits

75 changed files with 4546 additions and 1539 deletions

View File

@@ -26,7 +26,8 @@ import (
"github.com/netbirdio/netbird/client/internal/routemanager"
"github.com/netbirdio/netbird/client/internal/stdnet"
"github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netevents"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/formatter"
"github.com/netbirdio/netbird/route"
@@ -81,10 +82,13 @@ type Client struct {
deviceName string
uiVersion string
networkChangeListener listener.NetworkChangeListener
// netMgr outlives engine restarts: it mirrors the OS connectivity, not
// the engine lifecycle. Run and RunWithoutLogin inject its state and
// sweeper into each new ConnectClient.
netMgr *netevents.Manager
// netState outlives engine restarts: it mirrors the OS connectivity, not
// the engine lifecycle. Run and RunWithoutLogin inject it into each new
// ConnectClient, which distributes it to every reconnection loop.
netState *netstate.State
// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
sweeper *netsweep.Sweeper
stateMu sync.RWMutex
connectClient *internal.ConnectClient
@@ -148,17 +152,16 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
execWorkaround(androidSDKVersion)
net.SetAndroidProtectSocketFn(tunAdapter.ProtectSocket)
system.SetIFaceDiscover(iFaceDiscover)
recorder := peer.NewRecorder("")
return &Client{
deviceName: deviceName,
uiVersion: uiVersion,
tunAdapter: tunAdapter,
iFaceDiscover: iFaceDiscover,
recorder: recorder,
recorder: peer.NewRecorder(""),
ctxCancelLock: &sync.Mutex{},
networkChangeListener: networkChangeListener,
netMgr: netevents.NewManager(recorder),
netState: netstate.New(),
sweeper: netsweep.New(),
}
}
@@ -199,9 +202,8 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
}
// todo do not throw error in case of cancelled context
ctx = internal.CtxInitState(ctx)
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetEvents(c.netMgr))
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
c.setState(cfg, cacheDir, cfgFile, connectClient)
// This path runs the interactive SSO flow, so reaching here means the peer
// is authenticated again — release the latch Status() reports from. Clear
@@ -243,7 +245,7 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
// todo do not throw error in case of cancelled context
ctx = internal.CtxInitState(ctx)
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetEvents(c.netMgr))
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
c.setState(cfg, cacheDir, cfgFile, connectClient)
return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
}
@@ -295,12 +297,9 @@ func (c *Client) GetTunSettings() (*TunSettings, error) {
// While unavailable, the internal reconnect loops suspend their attempts and
// the connection listener reports NoNetwork instead of Connecting; when
// availability returns, the loops resume immediately with a fresh backoff.
// Losing the last network also sweeps the registered connections: nothing can
// redial while offline, so the stale sockets would otherwise stay silently
// "connected" until their own timeouts and the client would keep reporting
// Connected with no network at all.
func (c *Client) SetNetworkAvailable(available bool) {
c.netMgr.SetNetworkAvailable(available)
c.netState.Set(available)
c.recorder.SetNetworkAvailable(available)
}
// NotifyNetworkChange marks the management, signal and relay connections
@@ -308,7 +307,8 @@ func (c *Client) SetNetworkAvailable(available bool) {
// whatever has not redialed on the new network by then. The engine and the
// TUN device stay untouched.
func (c *Client) NotifyNetworkChange() {
c.netMgr.NotifyNetworkChange()
c.sweeper.MarkNetworkChange()
log.Infof("network change: connections marked stale")
}
// DebugBundle generates a debug bundle, uploads it, and returns the upload key.

View File

@@ -16,14 +16,9 @@ import (
"google.golang.org/grpc"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netevents/sweep"
"github.com/netbirdio/netbird/client/netsweep"
)
// Sweeper registers in-flight dials for the network change sweep.
type Sweeper interface {
StartDial(ctx context.Context) *sweep.Dial
}
func WithCustomDialer(_ bool, _ string) grpc.DialOption {
return grpc.WithContextDialer(dialContext)
}
@@ -31,7 +26,7 @@ func WithCustomDialer(_ bool, _ string) grpc.DialOption {
// WithSweeper dials like WithCustomDialer but registers connections and
// dials with the sweeper. Append it after WithCustomDialer: gRPC applies
// dial options in order, so the later context dialer wins.
func WithSweeper(sweeper Sweeper) grpc.DialOption {
func WithSweeper(sweeper *netsweep.Sweeper) grpc.DialOption {
return grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) {
dial := sweeper.StartDial(ctx)
defer dial.Release()

View File

@@ -1,19 +1,12 @@
package grpc
import (
"context"
"google.golang.org/grpc"
"github.com/netbirdio/netbird/client/netevents/sweep"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/util/wsproxy/client"
)
// Sweeper registers in-flight dials for the network change sweep.
type Sweeper interface {
StartDial(ctx context.Context) *sweep.Dial
}
// WithCustomDialer returns a gRPC dial option that uses WebSocket transport for WASM/JS environments.
// The component parameter specifies the WebSocket proxy component path (e.g., "/management", "/signal").
func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
@@ -21,6 +14,6 @@ func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
}
// WithSweeper is a no-op on WASM/JS: there is no network change signal.
func WithSweeper(_ Sweeper) grpc.DialOption {
func WithSweeper(_ *netsweep.Sweeper) grpc.DialOption {
return grpc.EmptyDialOption{}
}

View File

@@ -6,19 +6,16 @@ import (
"time"
"github.com/cenkalti/backoff/v4"
)
// ChangeWatcher exposes OS network availability transitions.
type ChangeWatcher interface {
Changed() <-chan struct{}
}
"github.com/netbirdio/netbird/client/netstate"
)
// Retry mirrors backoff.Retry, but the sleep between attempts also wakes on
// OS network availability transitions: an operation cut down by a network
// change retries the moment the network settles instead of sleeping through
// the recovery. A nil watcher never fires, leaving plain backoff.Retry
// the recovery. A nil netState never fires, leaving plain backoff.Retry
// behavior.
func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff, watcher ChangeWatcher) error {
func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff, netState *netstate.State) error {
bo.Reset()
for {
err := operation()
@@ -39,14 +36,10 @@ func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff,
return err
}
var changed <-chan struct{}
if watcher != nil {
changed = watcher.Changed()
}
timer := time.NewTimer(next)
select {
case <-timer.C:
case <-changed:
case <-netState.Changed():
timer.Stop()
case <-ctx.Done():
timer.Stop()

View File

@@ -10,7 +10,7 @@ import (
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/client/netevents/netstate"
"github.com/netbirdio/netbird/client/netstate"
)
func TestRetryWakesOnNetworkChange(t *testing.T) {

View File

@@ -38,7 +38,8 @@ import (
"github.com/netbirdio/netbird/client/internal/updater"
"github.com/netbirdio/netbird/client/internal/updater/installer"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netevents"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
cProto "github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/ssh"
sshconfig "github.com/netbirdio/netbird/client/ssh/config"
@@ -72,17 +73,28 @@ type ConnectClient struct {
persistSyncResponse bool
// netEvents gates every reconnection loop on OS-reported network
// availability and sweeps connections on network change.
netEvents *netevents.Manager
// netState gates every reconnection loop on OS-reported network
// availability. Nil (the default) disables gating; mobile platforms
// inject it via WithNetworkState.
netState *netstate.State
// sweeper cuts the management, signal and relay connections on network
// change; nil disables it.
sweeper *netsweep.Sweeper
}
// ConnectClientOption configures optional ConnectClient behavior.
type ConnectClientOption func(*ConnectClient)
// WithNetEvents injects the OS network event handling.
func WithNetEvents(events *netevents.Manager) ConnectClientOption {
return func(c *ConnectClient) { c.netEvents = events }
// WithNetworkState injects the OS network availability state that gates every
// reconnection loop; without it gating is disabled.
func WithNetworkState(netState *netstate.State) ConnectClientOption {
return func(c *ConnectClient) { c.netState = netState }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) ConnectClientOption {
return func(c *ConnectClient) { c.sweeper = sweeper }
}
func NewConnectClient(
@@ -293,7 +305,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
}
// suspend connection attempts while the OS reports no usable network
if waited, err := c.netEvents.Wait(c.ctx); err != nil {
if waited, err := c.netState.Wait(c.ctx); err != nil {
return nil
} else if waited {
backOff.Reset()
@@ -311,7 +323,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
log.Debugf("connecting to the Management service %s", c.config.ManagementURL.Host)
mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled,
mgm.WithNetEvents(c.netEvents))
mgm.WithNetworkState(c.netState), mgm.WithSweeper(c.sweeper))
if err != nil {
// On daemon shutdown / Down() the parent context is cancelled
// and the dial fails with "context canceled". Wrapping that
@@ -386,7 +398,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
}()
// with the global Netbird config in hand connect (just a connection, no stream yet) Signal
signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netEvents)
signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netState, c.sweeper)
if err != nil {
log.Error(err)
return wrapErr(err)
@@ -423,7 +435,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
}
relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
relayClient.WithNetEvents(c.netEvents))
relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper))
c.statusRecorder.SetRelayMgr(relayManager)
if len(relayURLs) > 0 {
if token != nil {
@@ -451,7 +463,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
UpdateManager: c.updateManager,
ClientMetrics: c.clientMetrics,
MetricsCtx: c.ctx,
NetState: c.netEvents,
NetState: c.netState,
}, mobileDependency)
engine.SetSyncResponsePersistence(c.persistSyncResponse)
c.engine = engine
@@ -711,7 +723,7 @@ func selectMTU(localMTU uint16, peerMTU int32) uint16 {
}
// connectToSignal creates Signal Service client and established a connection
func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netEvents *netevents.Manager) (*signal.GrpcClient, error) {
func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netState *netstate.State, sweeper *netsweep.Sweeper) (*signal.GrpcClient, error) {
var sigTLSEnabled bool
if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
sigTLSEnabled = true
@@ -720,7 +732,7 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
}
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
signal.WithNetEvents(netEvents))
signal.WithNetworkState(netState), signal.WithSweeper(sweeper))
if err != nil {
log.Errorf("error while connecting to the Signal Exchange Service %s: %s", wtConfig.Signal.Uri, err)
return nil, gstatus.Errorf(codes.FailedPrecondition, "failed connecting to Signal Service : %s", err)

View File

@@ -59,7 +59,7 @@ import (
"github.com/netbirdio/netbird/client/internal/syncstore"
"github.com/netbirdio/netbird/client/internal/updater"
"github.com/netbirdio/netbird/client/jobexec"
"github.com/netbirdio/netbird/client/netevents"
"github.com/netbirdio/netbird/client/netstate"
cProto "github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/system"
nbdns "github.com/netbirdio/netbird/dns"
@@ -184,7 +184,7 @@ type EngineServices struct {
MetricsCtx context.Context
// NetState gates the reconnection loops on OS-reported network
// availability; nil disables gating.
NetState *netevents.Manager
NetState *netstate.State
}
// Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -210,7 +210,7 @@ type Engine struct {
// netState gates the peer reconnection guards on OS-reported network
// availability; nil disables gating.
netState *netevents.Manager
netState *netstate.State
// STUNs is a list of STUN servers used by ICE
STUNs []*stun.URI

View File

@@ -26,7 +26,7 @@ import (
"github.com/netbirdio/netbird/client/internal/portforward"
"github.com/netbirdio/netbird/client/internal/rosenpass"
"github.com/netbirdio/netbird/client/internal/stdnet"
"github.com/netbirdio/netbird/client/netevents"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/route"
relayClient "github.com/netbirdio/netbird/shared/relay/client"
)
@@ -97,7 +97,7 @@ type ConnConfig struct {
// NetworkState gates the reconnection guard on OS-reported network
// availability; nil disables gating.
NetworkState *netevents.Manager
NetworkState *netstate.State
}
type Conn struct {

View File

@@ -6,6 +6,8 @@ import (
"github.com/cenkalti/backoff/v4"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netstate"
)
// ConnStatus represents the connection state as seen by the guard.
@@ -22,12 +24,6 @@ const (
type connStatusFunc func() ConnStatus
// NetworkWatcher is the availability view the guard gates reconnects on.
type NetworkWatcher interface {
IsOnline() bool
Changed() <-chan struct{}
}
// Guard is responsible for the reconnection logic.
// It will trigger to send an offer to the peer then has connection issues.
// Watch these events:
@@ -43,14 +39,14 @@ type Guard struct {
srWatcher *SRWatcher
// netState gates reconnect attempts on OS-reported network availability;
// nil disables gating.
netState NetworkWatcher
netState *netstate.State
relayedConnDisconnected chan struct{}
iCEConnDisconnected chan struct{}
}
// NewGuard creates a reconnection guard for a peer connection. A nil netState
// disables network availability gating.
func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netState NetworkWatcher) *Guard {
func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netState *netstate.State) *Guard {
return &Guard{
log: log,
isConnectedOnAllWay: isConnectedFn,
@@ -108,17 +104,14 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
iceState := &iceRetryState{log: g.log}
defer iceState.reset()
var netChanged <-chan struct{}
if g.netState != nil {
netChanged = g.netState.Changed()
}
netChanged := g.netState.Changed()
for {
select {
case <-tickerChannel:
// skip attempts while the OS reports no usable network; the
// netChanged case below resumes the loop once it returns
if g.netState != nil && !g.netState.IsOnline() {
if !g.netState.IsOnline() {
continue
}
switch g.isConnectedOnAllWay() {

View File

@@ -9,7 +9,7 @@ import (
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal/peer/ice"
"github.com/netbirdio/netbird/client/netevents/netstate"
"github.com/netbirdio/netbird/client/netstate"
)
// newTestGuardWithNetState builds a guard with a realistic MaxInterval: the

View File

@@ -37,32 +37,23 @@
// Updater Process (Setup):
//
// 1. Receives parameters from service via command-line arguments
// 2. Terminates the UI so the installer does not have to replace a locked image
// file, which would otherwise leave the install needing a reboot
// 3. Runs installer with appropriate silent/quiet flags:
// 2. Runs installer with appropriate silent/quiet flags:
// - Windows EXE: installer.exe /S
// - Windows MSI: msiexec.exe /i installer.msi /qn /norestart REBOOT=ReallySuppress /l*v msi.log
// - Windows MSI: msiexec.exe /i installer.msi /quiet /qn /l*v msi.log
// - macOS PKG: installer -pkg installer.pkg -target /
// - macOS Homebrew: brew upgrade netbirdio/tap/netbird
// 4. Installer terminates the daemon
// 5. Installer replaces binaries with new version
// 6. Updater waits for installer to complete. On Windows, MSI exit codes 3010
// (ERROR_SUCCESS_REBOOT_REQUIRED) and 1641 (ERROR_SUCCESS_REBOOT_INITIATED)
// are a pending-reboot outcome, not a failure: the install succeeded, but
// some files are only replaced on the next restart (the reboot itself is
// suppressed via /norestart and REBOOT=ReallySuppress), and the flow
// continues as on success
// 7. Updater restarts daemon:
// 3. Installer terminates daemon and UI processes
// 4. Installer replaces binaries with new version
// 5. Updater waits for installer to complete
// 6. Updater restarts daemon:
// - Windows: netbird.exe service start
// - macOS/Linux: netbird service start
// 8. Updater restarts UI:
// - Windows: Launches netbird-ui.exe using CreateProcessAsUser in every
// session it was terminated in, falling back to the active console session
// 7. Updater restarts UI:
// - Windows: Launches netbird-ui.exe as active console user using CreateProcessAsUser
// - macOS: Uses launchctl asuser to launch NetBird.app for console user
// - Linux: Not implemented (UI typically auto-starts)
// 9. Updater writes result.json with success/error status (a pending reboot is
// recorded as success)
// 10. Updater process exits
// 8. Updater writes result.json with success/error status
// 9. Updater process exits
//
// # Result Communication
//

View File

@@ -2,7 +2,6 @@ package installer
import (
"context"
"errors"
"fmt"
"os"
"os/exec"
@@ -23,12 +22,6 @@ const (
msiLogFile = "msi.log"
// ERROR_SUCCESS_REBOOT_REQUIRED and ERROR_SUCCESS_REBOOT_INITIATED
msiRebootRequired = 3010
msiRebootInitiated = 1641
processExitWait = 10 * time.Second
msiDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.msi"
exeDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.exe"
)
@@ -45,8 +38,6 @@ var (
func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string, daemonFolder string) (resultErr error) {
resultHandler := NewResultHandler(u.tempDir)
var uiSessions []uint32
// Always ensure daemon and UI are restarted after setup
defer func() {
log.Infof("starting daemon back")
@@ -55,7 +46,7 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
}
log.Infof("starting UI back")
if err := u.startUI(daemonFolder, uiSessions); err != nil {
if err := u.startUIAsUser(daemonFolder); err != nil {
log.Errorf("failed to start UI: %v", err)
}
@@ -84,14 +75,6 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
return
}
// The UI holds an open handle on its own image. Left running, Restart Manager
// cannot shut it down (msiexec runs as LocalSystem here, the UI as the
// interactive user), so the MSI falls back to replacing the file on reboot and
// marks the install as restart-required. The deferred close-application action
// in the package runs too late to prevent that, it happens after
// InstallValidate has already registered the file as in use.
uiSessions = killUI()
var cmd *exec.Cmd
switch installerType {
case TypeExe:
@@ -101,9 +84,7 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
installerDir := filepath.Dir(installerFile)
logPath := filepath.Join(installerDir, msiLogFile)
log.Infof("run msi installer: %s", installerFile)
// REBOOT=ReallySuppress: a silent install has no way to ask, so without it
// msiexec reboots the machine on its own if it decides one is needed.
cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/qn", "/norestart", "REBOOT=ReallySuppress", "/l*v", logPath)
cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/quiet", "/qn", "/l*v", logPath)
}
cmd.Dir = filepath.Dir(installerFile)
@@ -114,13 +95,9 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
}
log.Infof("installer started with PID %d", cmd.Process.Pid)
if err := cmd.Wait(); err != nil {
if !isRebootPending(err) {
resultErr = err
log.Errorf("installer process finished with error: %v", err)
return
}
log.Warnf("installer completed but reported a pending reboot, some files will be replaced on the next restart")
if resultErr = cmd.Wait(); resultErr != nil {
log.Errorf("installer process finished with error: %v", resultErr)
return
}
return nil
@@ -140,142 +117,16 @@ func (u *Installer) startDaemon(daemonFolder string) error {
return nil
}
func (u *Installer) startUI(daemonFolder string, sessionIDs []uint32) error {
func (u *Installer) startUIAsUser(daemonFolder string) error {
uiPath := filepath.Join(daemonFolder, uiName)
log.Infof("starting netbird-ui: %s", uiPath)
if len(sessionIDs) == 0 {
sessionID := windows.WTSGetActiveConsoleSessionId()
if sessionID == 0xFFFFFFFF {
return fmt.Errorf("no active user session found")
}
sessionIDs = []uint32{sessionID}
// Get the active console session ID
sessionID := windows.WTSGetActiveConsoleSessionId()
if sessionID == 0xFFFFFFFF {
return fmt.Errorf("no active user session found")
}
var errs []error
for _, sessionID := range sessionIDs {
if err := startUIInSession(uiPath, sessionID); err != nil {
errs = append(errs, fmt.Errorf("session %d: %w", sessionID, err))
continue
}
log.Infof("netbird-ui started successfully in session %d", sessionID)
}
return errors.Join(errs...)
}
// isRebootPending reports whether the installer exit code means it succeeded but
// left work for the next restart. The reboot itself is suppressed, so this is not
// a failure.
func isRebootPending(err error) bool {
var exitErr *exec.ExitError
if !errors.As(err, &exitErr) {
return false
}
switch exitErr.ExitCode() {
case msiRebootRequired, msiRebootInitiated:
return true
default:
return false
}
}
// killUI terminates any running netbird-ui process and returns the IDs of the
// interactive sessions the terminated processes belonged to. Setup starts the
// UI again in those sessions once the installer is done.
func killUI() []uint32 {
pids, err := processIDsByName(uiName)
if err != nil {
log.Warnf("failed to look up %s processes: %v", uiName, err)
return nil
}
sessions := make(map[uint32]struct{})
for _, pid := range pids {
var sessionID uint32
if err := windows.ProcessIdToSessionId(pid, &sessionID); err != nil {
log.Warnf("failed to look up session of %s (PID %d): %v", uiName, pid, err)
}
if err := terminateProcess(pid); err != nil {
log.Warnf("failed to terminate %s (PID %d): %v", uiName, pid, err)
continue
}
log.Infof("terminated %s (PID %d) in session %d", uiName, pid, sessionID)
if sessionID != 0 {
sessions[sessionID] = struct{}{}
}
}
sessionIDs := make([]uint32, 0, len(sessions))
for sessionID := range sessions {
sessionIDs = append(sessionIDs, sessionID)
}
return sessionIDs
}
func processIDsByName(name string) ([]uint32, error) {
snapshot, err := windows.CreateToolhelp32Snapshot(windows.TH32CS_SNAPPROCESS, 0)
if err != nil {
return nil, fmt.Errorf("create process snapshot: %w", err)
}
defer func() {
if err := windows.CloseHandle(snapshot); err != nil {
log.Warnf("failed to close process snapshot: %v", err)
}
}()
var entry windows.ProcessEntry32
entry.Size = uint32(unsafe.Sizeof(entry))
var pids []uint32
for err = windows.Process32First(snapshot, &entry); err == nil; err = windows.Process32Next(snapshot, &entry) {
if strings.EqualFold(windows.UTF16ToString(entry.ExeFile[:]), name) {
pids = append(pids, entry.ProcessID)
}
}
if !errors.Is(err, windows.ERROR_NO_MORE_FILES) {
return nil, fmt.Errorf("enumerate processes: %w", err)
}
return pids, nil
}
func terminateProcess(pid uint32) error {
handle, err := windows.OpenProcess(windows.PROCESS_TERMINATE|windows.SYNCHRONIZE, false, pid)
if err != nil {
// The process may have exited between enumeration and now.
if errors.Is(err, windows.ERROR_INVALID_PARAMETER) {
return nil
}
return fmt.Errorf("open process: %w", err)
}
defer func() {
if err := windows.CloseHandle(handle); err != nil {
log.Warnf("failed to close process handle: %v", err)
}
}()
if err := windows.TerminateProcess(handle, 0); err != nil {
return fmt.Errorf("terminate process: %w", err)
}
// Wait for the handle to signal so the image file is released before the
// installer tries to overwrite it. A timeout is reported through the returned
// event, not through err, which stays nil unless the wait itself failed.
event, err := windows.WaitForSingleObject(handle, uint32(processExitWait.Milliseconds()))
if err != nil {
return fmt.Errorf("wait for process exit: %w", err)
}
if event != windows.WAIT_OBJECT_0 {
return fmt.Errorf("wait for process exit: unexpected wait result %#x", event)
}
return nil
}
func startUIInSession(uiPath string, sessionID uint32) error {
// Get the user token for that session
var userToken windows.Token
err := windows.WTSQueryUserToken(sessionID, &userToken)
@@ -346,6 +197,7 @@ func startUIInSession(uiPath string, sessionID uint32) error {
log.Warnf("failed to close thread handle: %v", err)
}
log.Infof("netbird-ui started successfully in session %d", sessionID)
return nil
}

View File

@@ -1,108 +0,0 @@
package installer
import (
"errors"
"os/exec"
"slices"
"strconv"
"testing"
)
// exitErrorWithCode returns a real *exec.ExitError carrying the given exit code.
func exitErrorWithCode(t *testing.T, code int) error {
t.Helper()
err := exec.Command("cmd.exe", "/c", "exit "+strconv.Itoa(code)).Run()
if err == nil {
t.Fatalf("expected a non-zero exit for code %d", code)
}
return err
}
func TestIsRebootPending(t *testing.T) {
tests := []struct {
name string
code int
want bool
}{
{name: "reboot required", code: msiRebootRequired, want: true},
{name: "reboot initiated", code: msiRebootInitiated, want: true},
{name: "generic failure", code: 1603, want: false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
if got := isRebootPending(exitErrorWithCode(t, tt.code)); got != tt.want {
t.Errorf("isRebootPending(exit %d) = %v, want %v", tt.code, got, tt.want)
}
})
}
}
// TestProcessIDsByNameAndTerminate spawns a long-running system process, finds it
// by name and terminates it, covering the path the updater uses to release the UI
// image file before the installer replaces it.
func TestProcessIDsByNameAndTerminate(t *testing.T) {
cmd := exec.Command("ping.exe", "-n", "60", "127.0.0.1")
if err := cmd.Start(); err != nil {
t.Fatalf("start ping: %v", err)
}
pid := uint32(cmd.Process.Pid)
killed := false
t.Cleanup(func() {
if !killed {
_ = cmd.Process.Kill()
}
_ = cmd.Wait()
})
// Name matching must be case-insensitive: the snapshot reports PING.EXE.
pids, err := processIDsByName("ping.exe")
if err != nil {
t.Fatalf("processIDsByName: %v", err)
}
if !slices.Contains(pids, pid) {
t.Fatalf("PID %d not among the ping.exe processes found: %v", pid, pids)
}
if err := terminateProcess(pid); err != nil {
t.Fatalf("terminateProcess: %v", err)
}
killed = true
// terminateProcess only returns once the handle has signalled, so the process
// is already gone and Wait must not block. It exits with the code passed to
// TerminateProcess, which is 0, so Wait reports no error.
if err := cmd.Wait(); err != nil {
t.Fatalf("wait for terminated ping: %v", err)
}
if !cmd.ProcessState.Exited() {
t.Error("process did not exit after terminateProcess")
}
remaining, err := processIDsByName("ping.exe")
if err != nil {
t.Fatalf("processIDsByName after terminate: %v", err)
}
if slices.Contains(remaining, pid) {
t.Errorf("PID %d still listed after terminateProcess", pid)
}
}
func TestProcessIDsByNameNoMatch(t *testing.T) {
pids, err := processIDsByName("netbird-nonexistent-process.exe")
if err != nil {
t.Fatalf("processIDsByName: %v", err)
}
if len(pids) != 0 {
t.Errorf("expected no matches, got %v", pids)
}
}
func TestIsRebootPendingNonExitError(t *testing.T) {
if isRebootPending(errors.New("start installer: file not found")) {
t.Error("a non-exit error must not be treated as a pending reboot")
}
}

View File

@@ -22,7 +22,8 @@ import (
"github.com/netbirdio/netbird/client/internal/listener"
"github.com/netbirdio/netbird/client/internal/peer"
"github.com/netbirdio/netbird/client/internal/profilemanager"
"github.com/netbirdio/netbird/client/netevents"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/formatter"
"github.com/netbirdio/netbird/route"
@@ -83,10 +84,12 @@ type Client struct {
onHostDnsFn func([]string)
dnsManager dns.IosDnsManager
loginComplete bool
// netMgr outlives engine restarts: it mirrors the OS connectivity, not
// the engine lifecycle. Run injects its state and sweeper into each new
// ConnectClient.
netMgr *netevents.Manager
// netState outlives engine restarts: it mirrors the OS connectivity, not
// the engine lifecycle. Run injects it into each new ConnectClient, which
// distributes it to every reconnection loop.
netState *netstate.State
// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
sweeper *netsweep.Sweeper
// preloadedConfig holds config loaded from JSON (used on tvOS where file writes are blocked)
preloadedConfig *profilemanager.Config
@@ -97,7 +100,6 @@ type Client struct {
// NewClient instantiate a new Client
func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osVersion string, osName string, networkChangeListener NetworkChangeListener, dnsManager DnsManager) *Client {
recorder := peer.NewRecorder("")
return &Client{
cfgFile: cfgFile,
stateFile: stateFile,
@@ -106,11 +108,12 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV
deviceName: deviceName,
osName: osName,
osVersion: osVersion,
recorder: recorder,
recorder: peer.NewRecorder(""),
ctxCancelLock: &sync.Mutex{},
networkChangeListener: networkChangeListener,
dnsManager: dnsManager,
netMgr: netevents.NewManager(recorder),
netState: netstate.New(),
sweeper: netsweep.New(),
}
}
@@ -187,7 +190,7 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
cfg.WgIface = interfaceName
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetEvents(c.netMgr))
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
c.setState(cfg, connectClient)
// Persist the latest sync response so DebugBundle can include the network
// map. On iOS this is backed by disk to keep it out of the constrained
@@ -200,11 +203,10 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
// (e.g. from NWPathMonitor). While unavailable, the internal reconnect loops
// suspend their attempts and the connection listener reports NoNetwork
// instead of Connecting; when availability returns, the loops resume
// immediately with a fresh backoff. Losing the last network also sweeps the
// registered connections, so the client does not keep reporting Connected
// over stale sockets with no network at all.
// immediately with a fresh backoff.
func (c *Client) SetNetworkAvailable(available bool) {
c.netMgr.SetNetworkAvailable(available)
c.netState.Set(available)
c.recorder.SetNetworkAvailable(available)
}
// NotifyNetworkChange marks the management, signal and relay connections
@@ -212,7 +214,8 @@ func (c *Client) SetNetworkAvailable(available bool) {
// whatever has not redialed on the new network by then. The engine and the
// TUN device stay untouched.
func (c *Client) NotifyNetworkChange() {
c.netMgr.NotifyNetworkChange()
c.sweeper.MarkNetworkChange()
log.Infof("network change: connections marked stale")
}
// Stop the internal client and free the resources

View File

@@ -1,158 +0,0 @@
// Package netevents owns the OS network event handling shared by the mobile
// bindings: availability changes park or wake the reconnection loops and drive
// the NoNetwork listener state, and both losing the last network and switching
// networks sweep the stale connections so their owners redial immediately.
package netevents
import (
"context"
"time"
"github.com/cenkalti/backoff/v4"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netevents/netstate"
"github.com/netbirdio/netbird/client/netevents/sweep"
)
// Recorder receives the availability changes for listener state reporting.
type Recorder interface {
SetNetworkAvailable(available bool)
}
// Manager ties the network availability state, the connection sweeper and the
// status recorder together; it outlives engine restarts. A nil *Manager is
// the valid no-events value: the read methods report always-online and never
// sweep.
type Manager struct {
netState *netstate.State
sweeper *sweep.Sweeper
recorder Recorder
}
// NewManager creates a Manager reporting into recorder, starting online.
func NewManager(recorder Recorder) *Manager {
return &Manager{
netState: netstate.New(),
sweeper: sweep.New(),
recorder: recorder,
}
}
// SetNetworkAvailable records OS-reported network availability. While
// unavailable, the reconnection loops suspend their attempts and the
// connection listener reports NoNetwork instead of Connecting; when
// availability returns, the loops resume immediately with a fresh backoff.
// Losing the last network also sweeps the registered connections: nothing can
// redial while offline, so the stale sockets would otherwise stay silently
// "connected" until their own timeouts and the client would keep reporting
// Connected with no network at all.
func (m *Manager) SetNetworkAvailable(available bool) {
if !available && m.netState.IsOnline() {
m.sweeper.MarkNetworkChange()
}
m.netState.Set(available)
m.recorder.SetNetworkAvailable(available)
}
// NotifyNetworkChange marks the management, signal and relay connections
// stale after the OS switched networks and schedules a sweep that cuts
// whatever has not redialed on the new network by then. The engine and the
// TUN device stay untouched.
func (m *Manager) NotifyNetworkChange() {
m.sweeper.MarkNetworkChange()
log.Infof("network change: connections marked stale")
}
// IsOnline reports whether the OS reports at least one usable network.
func (m *Manager) IsOnline() bool {
if m == nil {
return true
}
return m.netState.IsOnline()
}
// Changed returns a channel closed on the next availability transition.
func (m *Manager) Changed() <-chan struct{} {
if m == nil {
return nil
}
return m.netState.Changed()
}
// Wait blocks while the network is offline; see netstate.State.Wait.
func (m *Manager) Wait(ctx context.Context) (bool, error) {
if m == nil {
return false, nil
}
return m.netState.Wait(ctx)
}
// WaitSettled waits until an online verdict holds for a full settleWindow, or
// while offline until the budget runs out. Returns false when ctx is
// cancelled. The settle window exists because a disconnect often precedes the
// OS offline flag by a few milliseconds, so a fresh online verdict cannot be
// trusted immediately. A nil Manager has no events to watch: it degrades to a
// fixed budget-long sleep.
func (m *Manager) WaitSettled(ctx context.Context, budget, settleWindow time.Duration) bool {
if m == nil {
select {
case <-time.After(budget):
return true
case <-ctx.Done():
return false
}
}
budgetTimer := time.NewTimer(budget)
defer budgetTimer.Stop()
settle := time.NewTimer(settleWindow)
defer settle.Stop()
for {
// Channel first, flag second: a flip in between still fires the channel.
changedCh := m.netState.Changed()
if m.netState.IsOnline() {
select {
case <-settle.C:
return true
case <-changedCh:
case <-ctx.Done():
return false
}
} else {
select {
case <-budgetTimer.C:
return true
case <-changedCh:
case <-ctx.Done():
return false
}
}
if !settle.Stop() {
select {
case <-settle.C:
default:
}
}
settle.Reset(settleWindow)
}
}
// StartDial registers an in-flight dial with the sweeper; see sweep.Sweeper.StartDial.
func (m *Manager) StartDial(ctx context.Context) *sweep.Dial {
if m == nil {
return (*sweep.Sweeper)(nil).StartDial(ctx)
}
return m.sweeper.StartDial(ctx)
}
// QuickRetryBackoff wraps bo for a quick retry after a network change; see
// sweep.Sweeper.QuickRetryBackoff.
func (m *Manager) QuickRetryBackoff(ctx context.Context, bo backoff.BackOff) backoff.BackOff {
if m == nil {
return bo
}
return m.sweeper.QuickRetryBackoff(ctx, bo, m.netState)
}

View File

@@ -1,34 +0,0 @@
package netevents
import (
"context"
"testing"
"time"
"github.com/stretchr/testify/assert"
)
type recorderStub struct{}
func (recorderStub) SetNetworkAvailable(bool) {}
func TestWaitSettledAfterOutage(t *testing.T) {
const budget = 1500 * time.Millisecond
const settleWindow = 200 * time.Millisecond
const outage = 2 * settleWindow
m := NewManager(recorderStub{})
m.SetNetworkAvailable(false)
start := time.Now()
go func() {
time.Sleep(outage)
m.SetNetworkAvailable(true)
}()
ok := m.WaitSettled(context.Background(), budget, settleWindow)
elapsed := time.Since(start)
assert.True(t, ok, "recovered network must let the caller proceed")
assert.GreaterOrEqual(t, elapsed, outage+settleWindow, "an online verdict must hold a full settle window before it is trusted")
}

View File

@@ -1,10 +1,10 @@
// Package sweep cuts network-bound activity when the OS switches networks:
// Package netsweep cuts network-bound activity when the OS switches networks:
// a sweep closes the registered connections and aborts the in-flight dials, so
// their owners redial immediately instead of waiting for the old sockets to
// time out.
//
// A nil *Sweeper disables everything: all methods are nil-safe no-ops.
package sweep
package netsweep
import (
"context"
@@ -16,7 +16,7 @@ import (
"github.com/cenkalti/backoff/v4"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netevents/netstate"
"github.com/netbirdio/netbird/client/netstate"
)
// DefaultSweepDelay absorbs network flapping while the OS settles on a
@@ -34,7 +34,7 @@ type Config struct {
// ErrSwept reports that a dial finished after a network change swept its
// registration. The connection is already closed; the caller must treat it
// as a failed dial and redial on the new network.
var ErrSwept = errors.New("sweep: connection swept by network change")
var ErrSwept = errors.New("netsweep: connection swept by network change")
// sweepID identifies one registration in a sweeper. Connections and dials
// draw from the same counter, so an id is unique across both registries.

View File

@@ -1,4 +1,4 @@
package sweep
package netsweep
import (
"context"

View File

@@ -1,11 +1,11 @@
package sweep
package netsweep
import (
"time"
"github.com/cenkalti/backoff/v4"
"github.com/netbirdio/netbird/client/netevents/netstate"
"github.com/netbirdio/netbird/client/netstate"
)
const quickRetryDelay = 200 * time.Millisecond

View File

@@ -1,4 +1,4 @@
package sweep
package netsweep
import (
"context"

View File

@@ -30,11 +30,6 @@ func GetInfo(ctx context.Context) *Info {
kernelVersion = osInfo[2]
}
addrs, err := networkAddresses()
if err != nil {
log.Warnf("discover network addresses: %s", err)
}
gio := &Info{
GoOS: runtime.GOOS,
Kernel: kernel,
@@ -46,7 +41,6 @@ func GetInfo(ctx context.Context) *Info {
NetbirdVersion: version.NetbirdVersion(),
UIVersion: extractUIVersion(ctx),
KernelVersion: kernelVersion,
NetworkAddresses: addrs,
SystemSerialNumber: serial(),
SystemProductName: productModel(),
SystemManufacturer: productManufacturer(),

View File

@@ -1,4 +1,4 @@
//go:build !ios && !android
//go:build !ios
package system

View File

@@ -1,89 +0,0 @@
package system
import (
"net/netip"
"strings"
)
var iFaceDiscover IFaceDiscover
type IFaceDiscover interface {
IFaces() (string, error)
}
// SetIFaceDiscover configures the Android interface discovery provider.
func SetIFaceDiscover(discover IFaceDiscover) {
iFaceDiscover = discover
}
func networkAddresses() ([]NetworkAddress, error) {
if iFaceDiscover == nil {
return nil, nil
}
ifaces, err := iFaceDiscover.IFaces()
if err != nil {
return nil, err
}
var netAddresses []NetworkAddress
for _, line := range strings.Split(ifaces, "\n") {
addresses, ok := interfaceAddresses(line)
if !ok {
continue
}
for _, address := range addresses {
netAddr, ok := toNetworkAddress(address)
if !ok {
continue
}
if isDuplicated(netAddresses, netAddr) {
continue
}
netAddresses = append(netAddresses, netAddr)
}
}
return netAddresses, nil
}
func interfaceAddresses(line string) ([]string, bool) {
parts := strings.Split(line, "|")
if len(parts) != 2 {
return nil, false
}
flags := strings.Fields(parts[0])
if len(flags) != 8 {
return nil, false
}
up, loopback := flags[3], flags[5]
if up != "true" || loopback == "true" {
return nil, false
}
return strings.Fields(parts[1]), true
}
func toNetworkAddress(address string) (NetworkAddress, bool) {
prefix, err := netip.ParsePrefix(address)
if err != nil {
return NetworkAddress{}, false
}
if prefix.Addr().Is4In6() {
if prefix.Bits() < 96 {
return NetworkAddress{}, false
}
prefix = netip.PrefixFrom(prefix.Addr().Unmap(), prefix.Bits()-96)
}
ip := prefix.Addr()
if ip.IsLoopback() || ip.IsLinkLocalUnicast() || ip.IsMulticast() {
return NetworkAddress{}, false
}
return NetworkAddress{NetIP: prefix}, true
}
func isDuplicated(addresses []NetworkAddress, addr NetworkAddress) bool {
for _, duplicated := range addresses {
if duplicated.NetIP == addr.NetIP {
return true
}
}
return false
}

View File

@@ -1,4 +1,4 @@
//go:build !ios && !android
//go:build !ios
package system

View File

@@ -281,6 +281,8 @@ read_enable_crowdsec() {
echo "CrowdSec checks client IPs against a community threat intelligence database" > /dev/stderr
echo "and blocks known malicious sources before they reach your services." > /dev/stderr
echo "A local CrowdSec LAPI container will be added to your deployment." > /dev/stderr
echo "It also enables the AppSec (WAF) endpoint, so services can inspect HTTP" > /dev/stderr
echo "requests for exploits. Both stay off per service until you enable them." > /dev/stderr
echo -n "Enable CrowdSec? [y/N]: " > /dev/stderr
read -r CHOICE < /dev/tty
@@ -554,7 +556,8 @@ generate_configuration_files() {
# TCP ServersTransport for PROXY protocol v2 to the proxy backend
render_traefik_dynamic > traefik-dynamic.yaml
if [[ "$ENABLE_CROWDSEC" == "true" ]]; then
mkdir -p crowdsec
mkdir -p crowdsec/acquis.d
render_crowdsec_appsec_acquis > crowdsec/acquis.d/appsec.yaml
fi
fi
;;
@@ -589,6 +592,23 @@ generate_configuration_files() {
return 0
}
# The AppSec (WAF) listener only exists if an appsec acquisition datasource is
# configured. One datasource is one listener carrying one merged rule set: the
# protocol has no rule-set selector, so per-service rule variation would need
# either a second datasource on another port or pre_eval hooks filtering on
# req.Host.
render_crowdsec_appsec_acquis() {
cat <<EOF
source: appsec
listen_addr: 0.0.0.0:7422
appsec_configs:
- crowdsecurity/appsec-default
labels:
type: appsec
EOF
return 0
}
start_services_and_show_instructions() {
# For built-in Traefik, start containers immediately
# For NPM, start containers first (NPM needs services running to create proxy)
@@ -805,7 +825,11 @@ render_docker_compose_traefik_builtin() {
restart: unless-stopped
networks: [netbird]
environment:
COLLECTIONS: crowdsecurity/linux
# appsec-generic-rules is required alongside appsec-virtual-patching:
# the appsec-default config references crowdsecurity/generic-* and
# crowdsecurity/experimental-*, which only that collection provides, and
# the engine exits at startup if they are missing.
COLLECTIONS: crowdsecurity/linux crowdsecurity/appsec-virtual-patching crowdsecurity/appsec-generic-rules
volumes:
- ./crowdsec:/etc/crowdsec
- crowdsec_db:/var/lib/crowdsec/data
@@ -1071,6 +1095,11 @@ EOF
cat <<EOF
NB_PROXY_CROWDSEC_API_URL=http://crowdsec:8080
NB_PROXY_CROWDSEC_API_KEY=$CROWDSEC_BOUNCER_KEY
# AppSec (WAF) request inspection. Separate endpoint from the LAPI above and
# validated with the same bouncer key. Setting it makes the proxy advertise the
# AppSec capability, which is what lets a service select appsec_mode; nothing is
# inspected until a service opts in.
NB_PROXY_CROWDSEC_APPSEC_URL=http://crowdsec:7422/
EOF
fi

View File

@@ -23,6 +23,9 @@ type Domain struct {
// SupportsCrowdSec is populated at query time from proxy cluster capabilities.
// Not persisted.
SupportsCrowdSec *bool `gorm:"-"`
// SupportsAppSec is populated at query time from proxy cluster capabilities.
// Not persisted.
SupportsAppSec *bool `gorm:"-"`
// SupportsPrivate is populated at query time from proxy cluster capabilities. Not persisted.
SupportsPrivate *bool `gorm:"-"`
}

View File

@@ -49,6 +49,7 @@ func domainToApi(d *domain.Domain) api.ReverseProxyDomain {
SupportsCustomPorts: d.SupportsCustomPorts,
RequireSubdomain: d.RequireSubdomain,
SupportsCrowdsec: d.SupportsCrowdSec,
SupportsAppsec: d.SupportsAppSec,
SupportsPrivate: d.SupportsPrivate,
}
if d.TargetCluster != "" {

View File

@@ -39,6 +39,7 @@ type proxyManager interface {
ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
}
@@ -98,6 +99,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
d.SupportsCustomPorts = m.proxyManager.ClusterSupportsCustomPorts(ctx, cluster)
d.RequireSubdomain = m.proxyManager.ClusterRequireSubdomain(ctx, cluster)
d.SupportsCrowdSec = m.proxyManager.ClusterSupportsCrowdSec(ctx, cluster)
d.SupportsAppSec = m.proxyManager.ClusterSupportsAppSec(ctx, cluster)
d.SupportsPrivate = m.proxyManager.ClusterSupportsPrivate(ctx, cluster)
ret = append(ret, d)
}
@@ -115,6 +117,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
if d.TargetCluster != "" {
cd.SupportsCustomPorts = m.proxyManager.ClusterSupportsCustomPorts(ctx, d.TargetCluster)
cd.SupportsCrowdSec = m.proxyManager.ClusterSupportsCrowdSec(ctx, d.TargetCluster)
cd.SupportsAppSec = m.proxyManager.ClusterSupportsAppSec(ctx, d.TargetCluster)
cd.SupportsPrivate = m.proxyManager.ClusterSupportsPrivate(ctx, d.TargetCluster)
}
// Custom domains never require a subdomain by default since

View File

@@ -46,6 +46,10 @@ func (m *mockProxyManager) ClusterSupportsCrowdSec(_ context.Context, _ string)
return nil
}
func (m *mockProxyManager) ClusterSupportsAppSec(_ context.Context, _ string) *bool {
return nil
}
func (m *mockProxyManager) ClusterSupportsPrivate(_ context.Context, _ string) *bool {
return nil
}

View File

@@ -19,6 +19,7 @@ type Manager interface {
ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
CleanupStale(ctx context.Context, inactivityDuration time.Duration) error
GetAccountProxy(ctx context.Context, accountID string) (*Proxy, error)

View File

@@ -21,6 +21,7 @@ type store interface {
GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
GetClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
CleanupStaleProxies(ctx context.Context, inactivityDuration time.Duration) error
GetProxyByAccountID(ctx context.Context, accountID string) (*proxy.Proxy, error)
@@ -138,6 +139,13 @@ func (m Manager) ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string
return m.store.GetClusterSupportsCrowdSec(ctx, clusterAddr)
}
// ClusterSupportsAppSec returns whether all active proxies in the cluster have
// a CrowdSec AppSec endpoint configured (unanimous). Returns nil when no proxy
// has reported capabilities.
func (m Manager) ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool {
return m.store.GetClusterSupportsAppSec(ctx, clusterAddr)
}
// ClusterSupportsPrivate reports whether any active proxy claims the private capability (nil = unreported).
func (m Manager) ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
return m.store.GetClusterSupportsPrivate(ctx, clusterAddr)

View File

@@ -99,6 +99,9 @@ func (m *mockStore) GetClusterRequireSubdomain(_ context.Context, _ string) *boo
func (m *mockStore) GetClusterSupportsCrowdSec(_ context.Context, _ string) *bool {
return nil
}
func (m *mockStore) GetClusterSupportsAppSec(_ context.Context, _ string) *bool {
return nil
}
func (m *mockStore) GetClusterSupportsPrivate(_ context.Context, _ string) *bool {
return nil
}

View File

@@ -50,20 +50,6 @@ func (mr *MockManagerMockRecorder) CleanupStale(ctx, inactivityDuration interfac
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CleanupStale", reflect.TypeOf((*MockManager)(nil).CleanupStale), ctx, inactivityDuration)
}
// ClusterSupportsCustomPorts mocks base method.
func (m *MockManager) ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "ClusterSupportsCustomPorts", ctx, clusterAddr)
ret0, _ := ret[0].(*bool)
return ret0
}
// ClusterSupportsCustomPorts indicates an expected call of ClusterSupportsCustomPorts.
func (mr *MockManagerMockRecorder) ClusterSupportsCustomPorts(ctx, clusterAddr interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsCustomPorts", reflect.TypeOf((*MockManager)(nil).ClusterSupportsCustomPorts), ctx, clusterAddr)
}
// ClusterRequireSubdomain mocks base method.
func (m *MockManager) ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool {
m.ctrl.T.Helper()
@@ -78,6 +64,20 @@ func (mr *MockManagerMockRecorder) ClusterRequireSubdomain(ctx, clusterAddr inte
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterRequireSubdomain", reflect.TypeOf((*MockManager)(nil).ClusterRequireSubdomain), ctx, clusterAddr)
}
// ClusterSupportsAppSec mocks base method.
func (m *MockManager) ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "ClusterSupportsAppSec", ctx, clusterAddr)
ret0, _ := ret[0].(*bool)
return ret0
}
// ClusterSupportsAppSec indicates an expected call of ClusterSupportsAppSec.
func (mr *MockManagerMockRecorder) ClusterSupportsAppSec(ctx, clusterAddr interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsAppSec", reflect.TypeOf((*MockManager)(nil).ClusterSupportsAppSec), ctx, clusterAddr)
}
// ClusterSupportsCrowdSec mocks base method.
func (m *MockManager) ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool {
m.ctrl.T.Helper()
@@ -92,6 +92,20 @@ func (mr *MockManagerMockRecorder) ClusterSupportsCrowdSec(ctx, clusterAddr inte
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsCrowdSec", reflect.TypeOf((*MockManager)(nil).ClusterSupportsCrowdSec), ctx, clusterAddr)
}
// ClusterSupportsCustomPorts mocks base method.
func (m *MockManager) ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "ClusterSupportsCustomPorts", ctx, clusterAddr)
ret0, _ := ret[0].(*bool)
return ret0
}
// ClusterSupportsCustomPorts indicates an expected call of ClusterSupportsCustomPorts.
func (mr *MockManagerMockRecorder) ClusterSupportsCustomPorts(ctx, clusterAddr interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsCustomPorts", reflect.TypeOf((*MockManager)(nil).ClusterSupportsCustomPorts), ctx, clusterAddr)
}
// ClusterSupportsPrivate mocks base method.
func (m *MockManager) ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
m.ctrl.T.Helper()
@@ -121,6 +135,35 @@ func (mr *MockManagerMockRecorder) Connect(ctx, proxyID, sessionID, clusterAddre
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "Connect", reflect.TypeOf((*MockManager)(nil).Connect), ctx, proxyID, sessionID, clusterAddress, ipAddress, accountID, capabilities)
}
// CountAccountProxies mocks base method.
func (m *MockManager) CountAccountProxies(ctx context.Context, accountID string) (int64, error) {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "CountAccountProxies", ctx, accountID)
ret0, _ := ret[0].(int64)
ret1, _ := ret[1].(error)
return ret0, ret1
}
// CountAccountProxies indicates an expected call of CountAccountProxies.
func (mr *MockManagerMockRecorder) CountAccountProxies(ctx, accountID interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CountAccountProxies", reflect.TypeOf((*MockManager)(nil).CountAccountProxies), ctx, accountID)
}
// DeleteAccountCluster mocks base method.
func (m *MockManager) DeleteAccountCluster(ctx context.Context, clusterAddress, accountID string) error {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "DeleteAccountCluster", ctx, clusterAddress, accountID)
ret0, _ := ret[0].(error)
return ret0
}
// DeleteAccountCluster indicates an expected call of DeleteAccountCluster.
func (mr *MockManagerMockRecorder) DeleteAccountCluster(ctx, clusterAddress, accountID interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccountCluster", reflect.TypeOf((*MockManager)(nil).DeleteAccountCluster), ctx, clusterAddress, accountID)
}
// Disconnect mocks base method.
func (m *MockManager) Disconnect(ctx context.Context, proxyID, sessionID string) error {
m.ctrl.T.Helper()
@@ -135,6 +178,21 @@ func (mr *MockManagerMockRecorder) Disconnect(ctx, proxyID, sessionID interface{
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "Disconnect", reflect.TypeOf((*MockManager)(nil).Disconnect), ctx, proxyID, sessionID)
}
// GetAccountProxy mocks base method.
func (m *MockManager) GetAccountProxy(ctx context.Context, accountID string) (*Proxy, error) {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "GetAccountProxy", ctx, accountID)
ret0, _ := ret[0].(*Proxy)
ret1, _ := ret[1].(error)
return ret0, ret1
}
// GetAccountProxy indicates an expected call of GetAccountProxy.
func (mr *MockManagerMockRecorder) GetAccountProxy(ctx, accountID interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountProxy", reflect.TypeOf((*MockManager)(nil).GetAccountProxy), ctx, accountID)
}
// GetActiveClusterAddresses mocks base method.
func (m *MockManager) GetActiveClusterAddresses(ctx context.Context) ([]string, error) {
m.ctrl.T.Helper()
@@ -150,6 +208,7 @@ func (mr *MockManagerMockRecorder) GetActiveClusterAddresses(ctx interface{}) *g
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveClusterAddresses", reflect.TypeOf((*MockManager)(nil).GetActiveClusterAddresses), ctx)
}
// GetActiveClusterAddressesForAccount mocks base method.
func (m *MockManager) GetActiveClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error) {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "GetActiveClusterAddressesForAccount", ctx, accountID)
@@ -158,6 +217,7 @@ func (m *MockManager) GetActiveClusterAddressesForAccount(ctx context.Context, a
return ret0, ret1
}
// GetActiveClusterAddressesForAccount indicates an expected call of GetActiveClusterAddressesForAccount.
func (mr *MockManagerMockRecorder) GetActiveClusterAddressesForAccount(ctx, accountID interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveClusterAddressesForAccount", reflect.TypeOf((*MockManager)(nil).GetActiveClusterAddressesForAccount), ctx, accountID)
@@ -177,36 +237,6 @@ func (mr *MockManagerMockRecorder) Heartbeat(ctx, p interface{}) *gomock.Call {
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "Heartbeat", reflect.TypeOf((*MockManager)(nil).Heartbeat), ctx, p)
}
// GetAccountProxy mocks base method.
func (m *MockManager) GetAccountProxy(ctx context.Context, accountID string) (*Proxy, error) {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "GetAccountProxy", ctx, accountID)
ret0, _ := ret[0].(*Proxy)
ret1, _ := ret[1].(error)
return ret0, ret1
}
// GetAccountProxy indicates an expected call of GetAccountProxy.
func (mr *MockManagerMockRecorder) GetAccountProxy(ctx, accountID interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountProxy", reflect.TypeOf((*MockManager)(nil).GetAccountProxy), ctx, accountID)
}
// CountAccountProxies mocks base method.
func (m *MockManager) CountAccountProxies(ctx context.Context, accountID string) (int64, error) {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "CountAccountProxies", ctx, accountID)
ret0, _ := ret[0].(int64)
ret1, _ := ret[1].(error)
return ret0, ret1
}
// CountAccountProxies indicates an expected call of CountAccountProxies.
func (mr *MockManagerMockRecorder) CountAccountProxies(ctx, accountID interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CountAccountProxies", reflect.TypeOf((*MockManager)(nil).CountAccountProxies), ctx, accountID)
}
// IsClusterAddressAvailable mocks base method.
func (m *MockManager) IsClusterAddressAvailable(ctx context.Context, clusterAddress, accountID string) (bool, error) {
m.ctrl.T.Helper()
@@ -222,20 +252,6 @@ func (mr *MockManagerMockRecorder) IsClusterAddressAvailable(ctx, clusterAddress
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "IsClusterAddressAvailable", reflect.TypeOf((*MockManager)(nil).IsClusterAddressAvailable), ctx, clusterAddress, accountID)
}
// DeleteAccountCluster mocks base method.
func (m *MockManager) DeleteAccountCluster(ctx context.Context, clusterAddress, accountID string) error {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "DeleteAccountCluster", ctx, clusterAddress, accountID)
ret0, _ := ret[0].(error)
return ret0
}
// DeleteAccountCluster indicates an expected call of DeleteAccountCluster.
func (mr *MockManagerMockRecorder) DeleteAccountCluster(ctx, clusterAddress, accountID interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccountCluster", reflect.TypeOf((*MockManager)(nil).DeleteAccountCluster), ctx, clusterAddress, accountID)
}
// MockController is a mock of Controller interface.
type MockController struct {
ctrl *gomock.Controller

View File

@@ -20,6 +20,9 @@ type Capabilities struct {
RequireSubdomain *bool
// SupportsCrowdsec indicates whether this proxy has CrowdSec configured.
SupportsCrowdsec *bool
// SupportsAppsec indicates whether this proxy has a CrowdSec AppSec (WAF)
// endpoint configured.
SupportsAppsec *bool
// Private indicates whether this proxy supports inbound access via Wireguard
// tunnel and netbird-only authentication policies
Private *bool
@@ -74,5 +77,6 @@ type Cluster struct {
SupportsCustomPorts *bool
RequireSubdomain *bool
SupportsCrowdSec *bool
SupportsAppSec *bool
Private *bool
}

View File

@@ -204,6 +204,7 @@ func (h *handler) getClusters(w http.ResponseWriter, r *http.Request) {
SupportsCustomPorts: c.SupportsCustomPorts,
RequireSubdomain: c.RequireSubdomain,
SupportsCrowdsec: c.SupportsCrowdSec,
SupportsAppsec: c.SupportsAppSec,
Private: c.Private,
})
}

View File

@@ -82,6 +82,7 @@ type CapabilityProvider interface {
ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
}
@@ -137,6 +138,7 @@ func (m *Manager) GetClusters(ctx context.Context, accountID, userID string) ([]
clusters[i].SupportsCustomPorts = m.capabilities.ClusterSupportsCustomPorts(ctx, clusters[i].Address)
clusters[i].RequireSubdomain = m.capabilities.ClusterRequireSubdomain(ctx, clusters[i].Address)
clusters[i].SupportsCrowdSec = m.capabilities.ClusterSupportsCrowdSec(ctx, clusters[i].Address)
clusters[i].SupportsAppSec = m.capabilities.ClusterSupportsAppSec(ctx, clusters[i].Address)
clusters[i].Private = m.capabilities.ClusterSupportsPrivate(ctx, clusters[i].Address)
}

View File

@@ -165,6 +165,22 @@ type AccessRestrictions struct {
AllowedCountries []string `json:"allowed_countries,omitempty" gorm:"serializer:json"`
BlockedCountries []string `json:"blocked_countries,omitempty" gorm:"serializer:json"`
CrowdSecMode string `json:"crowdsec_mode,omitempty" gorm:"serializer:json"`
// AllowMatch controls how the allowlists combine: "" or "all" require
// matching every allowlist (AND), "any" requires matching at least one (OR).
// Empty is treated as "all" for backward compatibility with existing records.
AllowMatch string `json:"allow_match,omitempty" gorm:"serializer:json"`
// AppSecMode is the CrowdSec AppSec (WAF) request inspection mode: "",
// "off", "enforce", or "observe". HTTP services only.
AppSecMode string `json:"appsec_mode,omitempty" gorm:"serializer:json"`
}
// isEmpty reports whether no restriction is configured. Both conversions drop
// the object entirely in that case, so a field missing from this check is
// silently discarded on the way to the API and the proxy.
func (r AccessRestrictions) isEmpty() bool {
return len(r.AllowedCIDRs) == 0 && len(r.BlockedCIDRs) == 0 &&
len(r.AllowedCountries) == 0 && len(r.BlockedCountries) == 0 &&
r.CrowdSecMode == "" && r.AllowMatch == "" && r.AppSecMode == ""
}
// Copy returns a deep copy of the AccessRestrictions.
@@ -175,6 +191,8 @@ func (r AccessRestrictions) Copy() AccessRestrictions {
AllowedCountries: slices.Clone(r.AllowedCountries),
BlockedCountries: slices.Clone(r.BlockedCountries),
CrowdSecMode: r.CrowdSecMode,
AllowMatch: r.AllowMatch,
AppSecMode: r.AppSecMode,
}
}
@@ -808,13 +826,23 @@ func restrictionsFromAPI(r *api.AccessRestrictions) (AccessRestrictions, error)
}
res.CrowdSecMode = string(*r.CrowdsecMode)
}
if r.AllowMatch != nil {
if !r.AllowMatch.Valid() {
return AccessRestrictions{}, fmt.Errorf("invalid allow_match %q", *r.AllowMatch)
}
res.AllowMatch = string(*r.AllowMatch)
}
if r.AppsecMode != nil {
if !r.AppsecMode.Valid() {
return AccessRestrictions{}, fmt.Errorf("invalid appsec_mode %q", *r.AppsecMode)
}
res.AppSecMode = string(*r.AppsecMode)
}
return res, nil
}
func restrictionsToAPI(r AccessRestrictions) *api.AccessRestrictions {
if len(r.AllowedCIDRs) == 0 && len(r.BlockedCIDRs) == 0 &&
len(r.AllowedCountries) == 0 && len(r.BlockedCountries) == 0 &&
r.CrowdSecMode == "" {
if r.isEmpty() {
return nil
}
res := &api.AccessRestrictions{}
@@ -834,13 +862,19 @@ func restrictionsToAPI(r AccessRestrictions) *api.AccessRestrictions {
mode := api.AccessRestrictionsCrowdsecMode(r.CrowdSecMode)
res.CrowdsecMode = &mode
}
if r.AllowMatch != "" {
match := api.AccessRestrictionsAllowMatch(r.AllowMatch)
res.AllowMatch = &match
}
if r.AppSecMode != "" {
mode := api.AccessRestrictionsAppsecMode(r.AppSecMode)
res.AppsecMode = &mode
}
return res
}
func restrictionsToProto(r AccessRestrictions) *proto.AccessRestrictions {
if len(r.AllowedCIDRs) == 0 && len(r.BlockedCIDRs) == 0 &&
len(r.AllowedCountries) == 0 && len(r.BlockedCountries) == 0 &&
r.CrowdSecMode == "" {
if r.isEmpty() {
return nil
}
return &proto.AccessRestrictions{
@@ -849,6 +883,8 @@ func restrictionsToProto(r AccessRestrictions) *proto.AccessRestrictions {
AllowedCountries: r.AllowedCountries,
BlockedCountries: r.BlockedCountries,
CrowdsecMode: r.CrowdSecMode,
AllowMatch: r.AllowMatch,
AppsecMode: r.AppSecMode,
}
}
@@ -874,6 +910,11 @@ func (s *Service) Validate() error {
if err := validateAccessRestrictions(&s.Restrictions); err != nil {
return err
}
// AppSec inspects HTTP requests, so it cannot apply to the L4 modes, which
// forward opaque byte streams.
if appSecEnabled(s.Restrictions.AppSecMode) && s.Mode != ModeHTTP {
return fmt.Errorf("appsec_mode is only supported for HTTP services, got mode %q", s.Mode)
}
if err := s.validatePrivateRequirements(); err != nil {
return err
}
@@ -1242,10 +1283,39 @@ func validateCrowdSecMode(mode string) error {
}
}
func validateAllowMatch(mode string) error {
switch mode {
case "", "all", "any":
return nil
default:
return fmt.Errorf("allow_match %q is invalid", mode)
}
}
func validateAppSecMode(mode string) error {
switch mode {
case "", "off", "enforce", "observe":
return nil
default:
return fmt.Errorf("appsec_mode %q is invalid", mode)
}
}
// appSecEnabled reports whether the mode asks for request inspection.
func appSecEnabled(mode string) bool {
return mode == "enforce" || mode == "observe"
}
func validateAccessRestrictions(r *AccessRestrictions) error {
if err := validateCrowdSecMode(r.CrowdSecMode); err != nil {
return err
}
if err := validateAllowMatch(r.AllowMatch); err != nil {
return err
}
if err := validateAppSecMode(r.AppSecMode); err != nil {
return err
}
if len(r.AllowedCIDRs) > maxCIDREntries {
return fmt.Errorf("allowed_cidrs: exceeds maximum of %d entries", maxCIDREntries)

View File

@@ -26,6 +26,17 @@ func validProxy() *Service {
}
}
// validL4Proxy returns a service that passes validation in one of the L4 modes.
func validL4Proxy(mode string) *Service {
rp := validProxy()
rp.Mode = mode
rp.ListenPort = 9000
rp.Targets = []*Target{
{TargetId: "peer-1", TargetType: TargetTypePeer, Host: "10.0.0.1", Port: 5432, Protocol: mode, Enabled: true},
}
return rp
}
func TestValidate_Valid(t *testing.T) {
require.NoError(t, validProxy().Validate())
}
@@ -1302,6 +1313,65 @@ func TestValidate_Private_AcceptsClusterTargetWithAccessGroups(t *testing.T) {
require.NoError(t, rp.Validate())
}
func TestRestrictions_AllowMatch_RoundTrip(t *testing.T) {
anyMatch := api.AccessRestrictionsAllowMatchAny
apiIn := &api.AccessRestrictions{
AllowedCidrs: &[]string{"203.0.113.0/24"},
AllowedCountries: &[]string{"US"},
AllowMatch: &anyMatch,
}
model, err := restrictionsFromAPI(apiIn)
require.NoError(t, err)
assert.Equal(t, "any", model.AllowMatch)
apiOut := restrictionsToAPI(model)
require.NotNil(t, apiOut.AllowMatch)
assert.Equal(t, api.AccessRestrictionsAllowMatchAny, *apiOut.AllowMatch)
protoOut := restrictionsToProto(model)
require.NotNil(t, protoOut)
assert.Equal(t, "any", protoOut.AllowMatch)
}
func TestRestrictions_AllowMatch_EmptyDefaultsToAll(t *testing.T) {
// A stored record with no allow_match (existing services) stays empty and
// must not surface a value on the API, preserving AND behavior downstream.
model, err := restrictionsFromAPI(&api.AccessRestrictions{
AllowedCidrs: &[]string{"203.0.113.0/24"},
})
require.NoError(t, err)
assert.Empty(t, model.AllowMatch, "unset allow_match stays empty")
apiOut := restrictionsToAPI(model)
require.NotNil(t, apiOut)
assert.Nil(t, apiOut.AllowMatch, "empty allow_match is omitted from the API response")
}
func TestRestrictions_AllowMatchOnly_Preserved(t *testing.T) {
// allow_match set without any list must not be dropped by the emptiness
// guards, so it round-trips through both the API and proto conversions.
model := AccessRestrictions{AllowMatch: "any"}
apiOut := restrictionsToAPI(model)
require.NotNil(t, apiOut, "allow-match-only restriction must not be omitted from the API response")
require.NotNil(t, apiOut.AllowMatch)
assert.Equal(t, api.AccessRestrictionsAllowMatchAny, *apiOut.AllowMatch)
protoOut := restrictionsToProto(model)
require.NotNil(t, protoOut, "allow-match-only restriction must not be omitted from the proto output")
assert.Equal(t, "any", protoOut.AllowMatch)
}
func TestValidate_RejectsInvalidAllowMatch(t *testing.T) {
rp := validProxy()
rp.Restrictions = AccessRestrictions{
AllowedCIDRs: []string{"203.0.113.0/24"},
AllowMatch: "sometimes",
}
assert.ErrorContains(t, rp.Validate(), "allow_match")
}
func TestValidate_Private_RejectsNonHTTPMode(t *testing.T) {
rp := validProxy()
rp.Private = true
@@ -1315,3 +1385,68 @@ func TestValidate_Private_RejectsNonHTTPMode(t *testing.T) {
}}
assert.ErrorContains(t, rp.Validate(), "HTTP")
}
func TestRestrictions_AppSecMode_RoundTrip(t *testing.T) {
mode := api.AccessRestrictionsAppsecModeEnforce
apiIn := &api.AccessRestrictions{AppsecMode: &mode}
model, err := restrictionsFromAPI(apiIn)
require.NoError(t, err)
assert.Equal(t, "enforce", model.AppSecMode)
// appsec_mode alone must keep the restrictions object alive on both the API
// and proto legs: it is meaningful without any CIDR or country entry.
apiOut := restrictionsToAPI(model)
require.NotNil(t, apiOut, "appsec_mode alone must not collapse the restrictions to nil")
require.NotNil(t, apiOut.AppsecMode)
assert.Equal(t, api.AccessRestrictionsAppsecModeEnforce, *apiOut.AppsecMode)
protoOut := restrictionsToProto(model)
require.NotNil(t, protoOut, "appsec_mode alone must reach the proxy")
assert.Equal(t, "enforce", protoOut.AppsecMode)
}
func TestRestrictions_AppSecMode_EmptyIsOmitted(t *testing.T) {
model, err := restrictionsFromAPI(&api.AccessRestrictions{
AllowedCidrs: &[]string{"203.0.113.0/24"},
})
require.NoError(t, err)
assert.Empty(t, model.AppSecMode)
apiOut := restrictionsToAPI(model)
require.NotNil(t, apiOut)
assert.Nil(t, apiOut.AppsecMode, "empty appsec_mode is omitted from the API response")
}
func TestRestrictions_AppSecMode_CopyIsDeep(t *testing.T) {
original := AccessRestrictions{AppSecMode: "observe", CrowdSecMode: "enforce"}
assert.Equal(t, original, original.Copy(), "Copy must carry every mode field")
}
func TestValidate_RejectsInvalidAppSecMode(t *testing.T) {
rp := validProxy()
rp.Restrictions = AccessRestrictions{AppSecMode: "sometimes"}
assert.ErrorContains(t, rp.Validate(), "appsec_mode")
}
func TestValidate_RejectsAppSecOnL4Modes(t *testing.T) {
// AppSec inspects HTTP requests, so the L4 modes cannot honor it. Accepting
// the field there would report protection that never runs.
for _, mode := range []string{ModeTCP, ModeUDP, ModeTLS} {
t.Run(mode, func(t *testing.T) {
rp := validL4Proxy(mode)
rp.Restrictions = AccessRestrictions{AppSecMode: "enforce"}
assert.ErrorContains(t, rp.Validate(), "appsec_mode is only supported for HTTP services")
})
}
}
func TestValidate_AllowsAppSecOffOnL4Modes(t *testing.T) {
for _, mode := range []string{ModeTCP, ModeUDP, ModeTLS} {
t.Run(mode, func(t *testing.T) {
rp := validL4Proxy(mode)
rp.Restrictions = AccessRestrictions{AppSecMode: "off"}
require.NoError(t, rp.Validate(), "an explicit off must not be rejected on L4 services")
})
}
}

View File

@@ -562,6 +562,7 @@ func (s *ProxyServiceServer) registerProxyConnection(ctx context.Context, params
SupportsCustomPorts: c.SupportsCustomPorts,
RequireSubdomain: c.RequireSubdomain,
SupportsCrowdsec: c.SupportsCrowdsec,
SupportsAppsec: c.SupportsAppsec,
Private: c.Private,
}
}

View File

@@ -6491,6 +6491,7 @@ var validCapabilityColumns = map[string]struct{}{
"supports_custom_ports": {},
"require_subdomain": {},
"supports_crowdsec": {},
"supports_appsec": {},
"private": {},
}
@@ -6521,6 +6522,14 @@ func (s *SqlStore) GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr s
return s.getClusterUnanimousCapability(ctx, clusterAddr, "supports_crowdsec")
}
// GetClusterSupportsAppSec returns whether all active proxies in the cluster
// have a CrowdSec AppSec endpoint configured. Returns nil when no proxy
// reported the capability. Unanimous for the same reason as CrowdSec: a single
// proxy without AppSec would let requests through uninspected.
func (s *SqlStore) GetClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool {
return s.getClusterUnanimousCapability(ctx, clusterAddr, "supports_appsec")
}
// getClusterUnanimousCapability returns an aggregated boolean capability
// requiring all active proxies in the cluster to report true.
func (s *SqlStore) getClusterUnanimousCapability(ctx context.Context, clusterAddr, column string) *bool {

View File

@@ -0,0 +1,119 @@
package store
import (
"context"
"fmt"
"os"
"runtime"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
)
// Capabilities travel proxy → gRPC → embedded gorm columns → aggregation → API.
// A field dropped at any of those hops reads as "capability absent", which is
// indistinguishable from a proxy that never reported it: the dashboard simply
// hides the feature and nothing fails. These assertions cover the persistence
// and aggregation hops.
func TestSqlStore_ClusterCapabilityAggregation(t *testing.T) {
if os.Getenv("CI") == "true" && (runtime.GOOS == "darwin" || runtime.GOOS == "windows") {
t.Skip("skip CI tests on darwin and windows")
}
yes, no := true, false
tests := []struct {
name string
reported []*bool // one entry per connected proxy in the cluster
wantAppSec *bool
wantAssertion string
}{
{
name: "unreported stays unknown",
reported: []*bool{nil},
wantAppSec: nil,
wantAssertion: "an unreported capability must not read as false",
},
{
name: "single proxy reporting true",
reported: []*bool{&yes},
wantAppSec: &yes,
wantAssertion: "a reported capability must survive persistence",
},
{
name: "one proxy without it disables the cluster",
reported: []*bool{&yes, &no},
wantAppSec: &no,
wantAssertion: "capability must be unanimous, so a rolling upgrade cannot leave traffic uninspected",
},
{
name: "one proxy yet to report disables the cluster",
reported: []*bool{&yes, nil},
wantAppSec: &no,
wantAssertion: "a proxy that has not reported must not count as capable",
},
}
runTestForAllEngines(t, "", func(t *testing.T, store Store) {
ctx := context.Background()
for i, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cluster := fmt.Sprintf("cluster-%d.proxy.example", i)
for j, reported := range tt.reported {
require.NoError(t, store.SaveProxy(ctx, &proxy.Proxy{
ID: fmt.Sprintf("proxy-%d-%d", i, j),
ClusterAddress: cluster,
Status: proxy.StatusConnected,
LastSeen: time.Now(),
Capabilities: proxy.Capabilities{SupportsAppsec: reported},
}))
}
got := store.GetClusterSupportsAppSec(ctx, cluster)
if tt.wantAppSec == nil {
assert.Nil(t, got, tt.wantAssertion)
return
}
require.NotNil(t, got, tt.wantAssertion)
assert.Equal(t, *tt.wantAppSec, *got, tt.wantAssertion)
})
}
})
}
// AppSec and IP reputation are separate endpoints, so a cluster can have either
// without the other. Gating one on the other would silently disable a feature
// the operator configured.
func TestSqlStore_ClusterCapabilitiesAreIndependent(t *testing.T) {
if os.Getenv("CI") == "true" && (runtime.GOOS == "darwin" || runtime.GOOS == "windows") {
t.Skip("skip CI tests on darwin and windows")
}
runTestForAllEngines(t, "", func(t *testing.T, store Store) {
ctx := context.Background()
const cluster = "independent.proxy.example"
yes, no := true, false
require.NoError(t, store.SaveProxy(ctx, &proxy.Proxy{
ID: "proxy-independent",
ClusterAddress: cluster,
Status: proxy.StatusConnected,
LastSeen: time.Now(),
Capabilities: proxy.Capabilities{
SupportsAppsec: &yes,
SupportsCrowdsec: &no,
},
}))
appsec := store.GetClusterSupportsAppSec(ctx, cluster)
crowdsec := store.GetClusterSupportsCrowdSec(ctx, cluster)
require.NotNil(t, appsec)
require.NotNil(t, crowdsec)
assert.True(t, *appsec, "AppSec must not be gated on CrowdSec")
assert.False(t, *crowdsec, "CrowdSec must not be implied by AppSec")
})
}

View File

@@ -133,3 +133,46 @@ func TestSqlStore_GetAccount_ServiceTargetOptionsRoundtrip(t *testing.T) {
assert.True(t, tg.Options.DisableAccessLog, "options disable access log")
})
}
func TestSqlStore_GetAccount_ServiceRestrictionsRoundtrip(t *testing.T) {
if os.Getenv("CI") == "true" && (runtime.GOOS == "darwin" || runtime.GOOS == "windows") {
t.Skip("skip CI tests on darwin and windows")
}
runTestForAllEngines(t, "", func(t *testing.T, store Store) {
ctx := context.Background()
account := newAccountWithId(ctx, "account_svc_restrictions", "testuser", "")
require.NoError(t, store.SaveAccount(ctx, account))
svc := &rpservice.Service{
ID: "svc-restrictions",
AccountID: account.Id,
Name: "restricted-svc",
Domain: "restricted.example",
Enabled: true,
Mode: rpservice.ModeHTTP,
Restrictions: rpservice.AccessRestrictions{
AllowedCIDRs: []string{"203.0.113.0/24"},
AllowedCountries: []string{"US"},
AllowMatch: "any",
CrowdSecMode: "observe",
AppSecMode: "enforce",
},
}
require.NoError(t, store.CreateService(ctx, svc))
loaded, err := store.GetAccount(ctx, account.Id)
require.NoError(t, err)
require.Len(t, loaded.Services, 1)
// Restrictions are stored as a JSON blob; confirm the whole struct,
// including allow_match and the CrowdSec modes, survives the read path
// (Postgres pgx path included via runTestForAllEngines).
got := loaded.Services[0].Restrictions
assert.Equal(t, []string{"203.0.113.0/24"}, got.AllowedCIDRs)
assert.Equal(t, []string{"US"}, got.AllowedCountries)
assert.Equal(t, "any", got.AllowMatch)
assert.Equal(t, "observe", got.CrowdSecMode)
assert.Equal(t, "enforce", got.AppSecMode)
})
}

View File

@@ -329,6 +329,7 @@ type Store interface {
GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
GetClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
CleanupStaleProxies(ctx context.Context, inactivityDuration time.Duration) error
GetAllProxies(ctx context.Context) ([]*proxy.Proxy, error)

View File

@@ -1878,6 +1878,20 @@ func (mr *MockStoreMockRecorder) GetClusterRequireSubdomain(ctx, clusterAddr int
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterRequireSubdomain", reflect.TypeOf((*MockStore)(nil).GetClusterRequireSubdomain), ctx, clusterAddr)
}
// GetClusterSupportsAppSec mocks base method.
func (m *MockStore) GetClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool {
m.ctrl.T.Helper()
ret := m.ctrl.Call(m, "GetClusterSupportsAppSec", ctx, clusterAddr)
ret0, _ := ret[0].(*bool)
return ret0
}
// GetClusterSupportsAppSec indicates an expected call of GetClusterSupportsAppSec.
func (mr *MockStoreMockRecorder) GetClusterSupportsAppSec(ctx, clusterAddr interface{}) *gomock.Call {
mr.mock.ctrl.T.Helper()
return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterSupportsAppSec", reflect.TypeOf((*MockStore)(nil).GetClusterSupportsAppSec), ctx, clusterAddr)
}
// GetClusterSupportsCrowdSec mocks base method.
func (m *MockStore) GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool {
m.ctrl.T.Helper()

View File

@@ -79,6 +79,11 @@ var (
geoDataDir string
crowdsecAPIURL string
crowdsecAPIKey string
appsecURL string
appsecTimeout time.Duration
appsecMaxBodyBytes int64
captureBudgetBytes int64
appsecMaxConcurrent int
)
var rootCmd = &cobra.Command{
@@ -125,6 +130,11 @@ func init() {
rootCmd.Flags().StringVar(&geoDataDir, "geo-data-dir", envStringOrDefault("NB_PROXY_GEO_DATA_DIR", "/var/lib/netbird/geolocation"), "Directory for the GeoLite2 MMDB file (auto-downloaded if missing)")
rootCmd.Flags().StringVar(&crowdsecAPIURL, "crowdsec-api-url", envStringOrDefault("NB_PROXY_CROWDSEC_API_URL", ""), "CrowdSec LAPI URL for IP reputation checks")
rootCmd.Flags().StringVar(&crowdsecAPIKey, "crowdsec-api-key", envStringOrDefault("NB_PROXY_CROWDSEC_API_KEY", ""), "CrowdSec bouncer API key")
rootCmd.Flags().StringVar(&appsecURL, "crowdsec-appsec-url", envStringOrDefault("NB_PROXY_CROWDSEC_APPSEC_URL", ""), "CrowdSec AppSec (WAF) endpoint for HTTP request inspection, e.g. http://127.0.0.1:7422/ (reuses the bouncer API key)")
rootCmd.Flags().DurationVar(&appsecTimeout, "crowdsec-appsec-timeout", envDurationOrDefault("NB_PROXY_CROWDSEC_APPSEC_TIMEOUT", 0), "Timeout for a single AppSec inspection call (0 = 200ms)")
rootCmd.Flags().IntVar(&appsecMaxConcurrent, "crowdsec-appsec-max-concurrent", int(envInt64OrDefault("NB_PROXY_CROWDSEC_APPSEC_MAX_CONCURRENT", 0)), "Cap on AppSec inspections in flight; further requests are denied in enforce mode rather than queued (0 = 256, negative = no cap)")
rootCmd.Flags().Int64Var(&captureBudgetBytes, "capture-budget-bytes", envInt64OrDefault("NB_PROXY_CAPTURE_BUDGET_BYTES", 0), "Total in-flight request-body buffering across the proxy, shared by AppSec inspection and agent-network capture (0 = 256MiB)")
rootCmd.Flags().Int64Var(&appsecMaxBodyBytes, "crowdsec-appsec-max-body-bytes", envInt64OrDefault("NB_PROXY_CROWDSEC_APPSEC_MAX_BODY_BYTES", 0), "Cap on the request body mirrored to AppSec (0 = 64KiB, negative = headers and URI only)")
}
// Execute runs the root command.
@@ -218,47 +228,59 @@ func runServer(cmd *cobra.Command, args []string) error {
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGTERM, syscall.SIGINT)
defer stop()
srv := proxy.New(ctx, proxy.Config{
ListenAddr: addr,
Logger: logger,
Version: Version,
ManagementAddress: mgmtAddr,
ProxyURL: proxyDomain,
ProxyToken: proxyToken,
CertificateDirectory: certDir,
CertificateFile: certFile,
CertificateKeyFile: certKeyFile,
GenerateACMECertificates: acmeCerts,
ACMEChallengeAddress: acmeAddr,
ACMEDirectory: acmeDir,
ACMEEABKID: acmeEABKID,
ACMEEABHMACKey: acmeEABHMACKey,
ACMEChallengeType: acmeChallengeType,
DebugEndpointEnabled: debugEndpoint,
DebugEndpointAddress: debugEndpointAddr,
HealthAddr: healthAddr,
ForwardedProto: forwardedProto,
TrustedProxies: parsedTrustedProxies,
CertLockMethod: nbacme.CertLockMethod(certLockMethod),
WildcardCertDir: wildcardCertDir,
WireguardPort: wgPort,
Performance: perf,
ProxyProtocol: proxyProtocol,
PreSharedKey: preSharedKey,
SupportsCustomPorts: supportsCustomPorts,
RequireSubdomain: requireSubdomain,
Private: private,
MaxDialTimeout: maxDialTimeout,
MaxSessionIdleTimeout: maxSessionIdleTimeout,
MappingBatchWatchdog: envDurationOrDefault("NB_PROXY_MAPPING_BATCH_WATCHDOG", 0),
GeoDataDir: geoDataDir,
CrowdSecAPIURL: crowdsecAPIURL,
CrowdSecAPIKey: crowdsecAPIKey,
})
srv := proxy.New(ctx, serverConfig(logger, proxyToken, parsedTrustedProxies, perf))
return srv.ListenAndServe(ctx, addr)
}
// serverConfig maps the parsed flags and environment onto the proxy config.
// Kept separate from runServer so registering a new flag does not grow the
// startup path.
func serverConfig(logger *log.Logger, proxyToken string, trustedProxyList *trustedproxy.List, perf embed.Performance) proxy.Config {
return proxy.Config{
ListenAddr: addr,
Logger: logger,
Version: Version,
ManagementAddress: mgmtAddr,
ProxyURL: proxyDomain,
ProxyToken: proxyToken,
CertificateDirectory: certDir,
CertificateFile: certFile,
CertificateKeyFile: certKeyFile,
GenerateACMECertificates: acmeCerts,
ACMEChallengeAddress: acmeAddr,
ACMEDirectory: acmeDir,
ACMEEABKID: acmeEABKID,
ACMEEABHMACKey: acmeEABHMACKey,
ACMEChallengeType: acmeChallengeType,
DebugEndpointEnabled: debugEndpoint,
DebugEndpointAddress: debugEndpointAddr,
HealthAddr: healthAddr,
ForwardedProto: forwardedProto,
TrustedProxies: trustedProxyList,
CertLockMethod: nbacme.CertLockMethod(certLockMethod),
WildcardCertDir: wildcardCertDir,
WireguardPort: wgPort,
Performance: perf,
ProxyProtocol: proxyProtocol,
PreSharedKey: preSharedKey,
SupportsCustomPorts: supportsCustomPorts,
RequireSubdomain: requireSubdomain,
Private: private,
MaxDialTimeout: maxDialTimeout,
MaxSessionIdleTimeout: maxSessionIdleTimeout,
MappingBatchWatchdog: envDurationOrDefault("NB_PROXY_MAPPING_BATCH_WATCHDOG", 0),
GeoDataDir: geoDataDir,
CrowdSecAPIURL: crowdsecAPIURL,
CrowdSecAPIKey: crowdsecAPIKey,
CrowdSecAppSecURL: appsecURL,
CrowdSecAppSecTimeout: appsecTimeout,
CrowdSecAppSecMaxBodyBytes: appsecMaxBodyBytes,
CrowdSecAppSecMaxConcurrent: appsecMaxConcurrent,
MiddlewareCaptureBudgetBytes: captureBudgetBytes,
}
}
func envBoolOrDefault(key string, def bool) bool {
v, exists := os.LookupEnv(key)
if !exists {
@@ -293,6 +315,19 @@ func envUint16OrDefault(key string, def uint16) uint16 {
return uint16(parsed)
}
func envInt64OrDefault(key string, def int64) int64 {
v, exists := os.LookupEnv(key)
if !exists {
return def
}
parsed, err := strconv.ParseInt(v, 10, 64)
if err != nil {
log.Warnf("parse %s=%q: %v, using default %d", key, v, err, def)
return def
}
return parsed
}
func envDurationOrDefault(key string, def time.Duration) time.Duration {
v, exists := os.LookupEnv(key)
if !exists {

View File

@@ -0,0 +1,163 @@
package appsec
import (
"bytes"
"errors"
"io"
"mime"
"net/http"
"net/url"
"slices"
"strings"
)
// bufferBody reads up to limit+1 bytes from r.Body and always restores r.Body so
// the request stays forwardable. oversize reports that the body exceeded limit, in
// which case the returned prefix must not be used for inspection: the bytes are
// only read so they can be replayed to the backend.
func bufferBody(r *http.Request, limit int64) (body []byte, oversize bool, err error) {
original := r.Body
buf, readErr := io.ReadAll(io.LimitReader(original, limit+1))
if readErr != nil && !errors.Is(readErr, io.EOF) {
// Restore what was read so a downstream retry sees a consistent stream,
// then surface the failure.
r.Body = replay(buf, original)
return nil, false, readErr
}
if int64(len(buf)) > limit {
r.Body = replay(buf, original)
return nil, true, nil
}
// The whole body is buffered, so the original is drained and can be closed.
// A close error on a drained read-only body does not invalidate the bytes.
_ = original.Close()
r.Body = io.NopCloser(bytes.NewReader(buf))
// Framing is deliberately left as the client sent it. Rewriting a chunked
// request to a fixed Content-Length here would be invisible to the client
// but not to the rest of the chain: a later body capture with a smaller cap
// sees a known length over its cap and skips capture entirely, where an
// unknown length would have given it a truncated prefix. Inspecting a
// request must not change what any other layer gets to inspect.
return buf, false, nil
}
// replay returns a ReadCloser that yields the already-read prefix followed by
// the remainder of the original stream, and closes the original.
func replay(prefix []byte, rest io.ReadCloser) io.ReadCloser {
return struct {
io.Reader
io.Closer
}{
Reader: io.MultiReader(bytes.NewReader(prefix), rest),
Closer: rest,
}
}
// redactedPlaceholder replaces a credential value in the mirrored body. It is
// inert for rule matching, and its fixed length leaks nothing about the secret.
const redactedPlaceholder = "redacted"
// redactFormFields returns the body to mirror for a URL-encoded form, with the
// values of the named fields replaced. The proxy's own password / PIN login
// form posts to the service path itself, so without this the plaintext
// credential would reach the Security Engine.
//
// Only the credential values are removed, never the whole body: dropping the
// body outright would let a caller exempt any payload from inspection just by
// appending a field named "password". Everything else in the form stays
// inspectable, which is the point.
//
// Returns body unchanged when it is not a URL-encoded form or carries none of
// the fields.
//
// Substitution happens on the raw bytes rather than by re-encoding parsed
// values. Re-encoding would drop pairs that url.ParseQuery rejects, so a
// payload hidden in a malformed pair alongside a credential-named field would
// never be inspected while a tolerant backend parser still acted on it. Working
// byte-wise also avoids reordering keys and normalizing escapes, so the engine
// sees the same bytes the backend will.
//
// Field names match case-sensitively, on purpose: the caller passes the exact
// names the login handler reads via r.FormValue, and that lookup is itself
// case-sensitive. A "Password" field is therefore never a credential as far as
// the proxy is concerned, and redacting it would only blind the WAF to a value
// the proxy does not own.
func redactFormFields(contentType string, body []byte, fields []string) []byte {
if len(fields) == 0 || len(body) == 0 {
return body
}
media, _, err := mime.ParseMediaType(contentType)
if err != nil || media != "application/x-www-form-urlencoded" {
return body
}
return redactURLEncoded(body, fields)
}
// redactURLEncoded replaces the values of the named keys in a URL-encoded
// key/value sequence, the shared syntax of a query string and a form body.
func redactURLEncoded(raw []byte, fields []string) []byte {
// Split on "&" only, matching how Go's form parser delimits pairs.
segments := bytes.Split(raw, []byte("&"))
redacted := false
for i, segment := range segments {
rawKey, _, hasValue := bytes.Cut(segment, []byte("="))
if !hasValue {
continue
}
// Compare the decoded name, so an escaped spelling of the field
// ("pass%77ord") is redacted too: the reader decodes before looking it
// up. A key that fails to decode never reaches that reader either,
// since the parser drops the pair.
name, err := url.QueryUnescape(string(rawKey))
if err != nil || !slices.Contains(fields, name) {
continue
}
// Keep the key bytes as sent and replace only the value. Assigning a
// fresh slice leaves raw untouched, which matters: the caller restored
// the request body from the same buffer.
segments[i] = []byte(string(rawKey) + "=" + redactedPlaceholder)
redacted = true
}
if !redacted {
return raw
}
return bytes.Join(segments, []byte("&"))
}
// redactQuery replaces the values of the named query parameters in a raw query
// string, leaving every other byte as sent.
func redactQuery(rawQuery string, params []string) string {
if len(params) == 0 || rawQuery == "" {
return rawQuery
}
return string(redactURLEncoded([]byte(rawQuery), params))
}
// redactCookieHeader replaces the values of the named cookies in a Cookie
// header, keeping the others intact: cookies are a zone WAF rules match on, so
// dropping the whole header would cost real coverage.
func redactCookieHeader(value string, names []string) string {
if len(names) == 0 || value == "" {
return value
}
parts := strings.Split(value, ";")
redacted := false
for i, part := range parts {
name, _, hasValue := strings.Cut(part, "=")
if !hasValue {
continue
}
// Cookie names are case-sensitive and are not percent-decoded.
if !slices.Contains(names, strings.TrimSpace(name)) {
continue
}
parts[i] = name + "=" + redactedPlaceholder
redacted = true
}
if !redacted {
return value
}
return strings.Join(parts, ";")
}

View File

@@ -0,0 +1,571 @@
// Package appsec implements the CrowdSec AppSec (WAF) side of the remediation
// component protocol: each inspected HTTP request is mirrored to the Security
// Engine's AppSec endpoint, which replies with an allow / ban / captcha verdict
// for that request.
//
// This is a separate endpoint from the LAPI decision stream used by the
// crowdsec package: LAPI answers "is this IP known bad", AppSec answers "is
// this request an attack". The two are configured and enabled independently.
package appsec
import (
"bytes"
"context"
"encoding/json"
"errors"
"fmt"
"io"
"net/http"
"net/netip"
"net/url"
"strings"
"sync"
"time"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/proxy/internal/netutil"
"github.com/netbirdio/netbird/proxy/internal/restrict"
)
// Header names the AppSec component reads off the mirrored request. IP, URI and
// Verb are mandatory: the engine answers 500 when any of them is missing.
const (
headerAPIKey = "X-Crowdsec-Appsec-Api-Key" //nolint:gosec // G101: a header name, not a credential
headerIP = "X-Crowdsec-Appsec-Ip"
headerURI = "X-Crowdsec-Appsec-Uri"
headerVerb = "X-Crowdsec-Appsec-Verb"
headerHost = "X-Crowdsec-Appsec-Host"
headerUserAgent = "X-Crowdsec-Appsec-User-Agent"
headerHTTPVersion = "X-Crowdsec-Appsec-Http-Version"
headerTransactionID = "X-Crowdsec-Appsec-Transaction-Id"
)
// headerPrefix covers every protocol header. Any client-supplied header in this
// namespace is dropped before forwarding so a caller cannot influence the
// engine's view of its own address, or replay an API key.
const headerPrefix = "X-Crowdsec-Appsec-"
// Remediation actions the engine can return.
const (
actionAllow = "allow"
actionBan = "ban"
actionCaptcha = "captcha"
)
const (
// DefaultTimeout matches the 200ms budget CrowdSec's remediation component
// spec sets for the blocking AppSec call.
DefaultTimeout = 200 * time.Millisecond
// MinTimeout and MaxTimeout bound the configured inspection timeout.
// Inspection is synchronous, so the upper bound is what keeps a
// mis-set value from parking every request to an inspected service on a
// slow engine; the lower bound keeps the call from timing out before the
// engine can realistically answer. Mirrors the per-middleware bounds the
// proxy already applies to in-path calls.
MinTimeout = 10 * time.Millisecond
MaxTimeout = 5 * time.Second
// DefaultMaxBodyBytes caps the request body mirrored to the engine.
// Requests with a larger body are inspected on headers and URI only.
DefaultMaxBodyBytes int64 = 64 << 10
// DefaultMaxConcurrent bounds inspections in flight toward the engine. The
// point is to fail fast instead of parking a goroutine per request for the
// whole timeout once the engine is saturated: a slow engine otherwise turns
// a traffic burst into a pile of waiters that all time out anyway. Sized so
// a healthy engine (single-digit milliseconds per call) never reaches it.
DefaultMaxConcurrent = 256
// MaxConcurrentLimit is the ceiling for that bound.
MaxConcurrentLimit = 4096
// MaxBodyBytesLimit is the ceiling for that cap. A single request can hold
// this much in memory; the shared Budget is what bounds the total across
// concurrent requests. Matches the proxy-wide body-capture ceiling.
MaxBodyBytesLimit int64 = 8 << 20
// maxResponseBytes bounds how much of a verdict response is read. The
// engine answers with a two-field JSON object, so anything beyond this is
// not a response we can act on.
maxResponseBytes int64 = 4 << 10
)
// Reasons the request body was not mirrored. Reported so an access-log reader
// can distinguish "inspected and clean" from "never inspected", and so an
// oversize opt-out is visible rather than silent.
const (
BypassOversize = "oversize"
BypassUpgrade = "upgrade"
BypassDisabled = "disabled"
BypassBudget = "budget_exhausted"
)
// ErrUnavailable reports that the engine could not produce a verdict: the call
// failed, timed out, or the engine rejected it (401 bad key, 500 malformed).
// Distinguished from a block verdict so the caller can apply the per-service
// mode: enforce fails closed, observe allows.
var ErrUnavailable = errors.New("appsec engine unavailable")
// Config configures a Client.
type Config struct {
// URL is the AppSec endpoint, e.g. http://127.0.0.1:7422/.
URL string
// APIKey is the CrowdSec bouncer API key. The AppSec component validates it
// against LAPI, so the same key used for the decision stream works here.
APIKey string
// Timeout bounds a single inspection call. Zero means DefaultTimeout.
Timeout time.Duration
// MaxBodyBytes caps the mirrored request body. Zero means
// DefaultMaxBodyBytes; negative disables body forwarding entirely.
MaxBodyBytes int64
// MaxConcurrent bounds inspections in flight toward the engine. Zero means
// DefaultMaxConcurrent; negative disables the bound.
MaxConcurrent int
// Budget bounds the total body buffering in flight across all inspected
// requests. Nil disables that ceiling, which leaves the worst case at
// MaxBodyBytes times the concurrent request count; callers serving
// untrusted traffic should share the proxy-wide capture budget here.
Budget Budget
Logger *log.Entry
}
// Budget is the shared allowance for in-flight body buffering. Acquire reports
// whether n bytes could be reserved; every successful Acquire is matched by a
// Release of the same n. Satisfied by the proxy's capture budget, so AppSec and
// the middleware body tap draw down one pool rather than two independent ones.
type Budget interface {
Acquire(n int64) bool
Release(n int64)
}
// Client mirrors HTTP requests to a CrowdSec AppSec endpoint. It holds no
// per-service state and is safe for concurrent use.
type Client struct {
url string
apiKey string
maxBodyBytes int64
// sem bounds in-flight inspections. Nil when the bound is disabled.
sem chan struct{}
budget Budget
http *http.Client
logger *log.Entry
}
// New validates the config and returns a Client. The endpoint is not contacted
// here: the engine may come up after the proxy.
func New(cfg Config) (*Client, error) {
if cfg.URL == "" {
return nil, errors.New("appsec url is empty")
}
if cfg.APIKey == "" {
return nil, errors.New("appsec api key is empty")
}
parsed, err := url.Parse(cfg.URL)
if err != nil {
return nil, fmt.Errorf("parse appsec url: %w", err)
}
if parsed.Scheme != "http" && parsed.Scheme != "https" {
return nil, fmt.Errorf("appsec url scheme %q is not http(s)", parsed.Scheme)
}
if parsed.Host == "" {
return nil, errors.New("appsec url has no host")
}
logger := cfg.Logger
if logger == nil {
logger = log.NewEntry(log.StandardLogger())
}
timeout := cfg.Timeout
switch {
case timeout <= 0:
timeout = DefaultTimeout
case timeout < MinTimeout:
logger.Warnf("appsec timeout %s is below the minimum, using %s", timeout, MinTimeout)
timeout = MinTimeout
case timeout > MaxTimeout:
logger.Warnf("appsec timeout %s exceeds the maximum, using %s", timeout, MaxTimeout)
timeout = MaxTimeout
}
// A negative cap is meaningful: forward no body at all.
maxBody := cfg.MaxBodyBytes
switch {
case maxBody == 0:
maxBody = DefaultMaxBodyBytes
case maxBody > MaxBodyBytesLimit:
logger.Warnf("appsec max body %d exceeds the maximum, using %d", maxBody, MaxBodyBytesLimit)
maxBody = MaxBodyBytesLimit
}
maxConcurrent := cfg.MaxConcurrent
switch {
case maxConcurrent == 0:
maxConcurrent = DefaultMaxConcurrent
case maxConcurrent > MaxConcurrentLimit:
logger.Warnf("appsec max concurrent %d exceeds the maximum, using %d", maxConcurrent, MaxConcurrentLimit)
maxConcurrent = MaxConcurrentLimit
}
var sem chan struct{}
if maxConcurrent > 0 {
sem = make(chan struct{}, maxConcurrent)
}
return &Client{
url: cfg.URL,
apiKey: cfg.APIKey,
maxBodyBytes: maxBody,
sem: sem,
budget: cfg.Budget,
logger: logger,
http: &http.Client{
Timeout: timeout,
Transport: &http.Transport{
MaxIdleConns: 100,
MaxIdleConnsPerHost: 32,
IdleConnTimeout: 90 * time.Second,
},
},
}, nil
}
// Request is one inspection request.
type Request struct {
// HTTP is the in-flight client request. Inspect buffers and restores its
// body, so the request stays forwardable afterwards.
HTTP *http.Request
// ClientIP is the resolved client address (after trusted-proxy handling).
ClientIP netip.Addr
// TransactionID correlates the engine's alert with the proxy's access log
// entry. Empty lets the engine generate its own UUID.
TransactionID string
// RedactBodyFields lists form fields whose values are replaced before the
// body is mirrored. Used to keep credentials submitted to the proxy's own
// login form out of the engine while still inspecting the rest.
RedactBodyFields []string
// RedactHeaders, RedactCookies and RedactQueryParams name the credentials
// the proxy already withholds from backends: the header-auth values, its
// session cookie, and the OIDC session token. The engine logs and alerts on
// what it inspects, so mirroring them there would reintroduce the leak the
// upstream strippers exist to prevent. Only the values are replaced, so the
// surrounding headers, cookies and query stay inspectable.
RedactHeaders []string
RedactCookies []string
RedactQueryParams []string
}
// Result is the outcome of an inspection.
type Result struct {
Verdict restrict.Verdict
// BodyBypass names why the request body was not mirrored, empty when it
// was (or when the request had none). The engine still saw the headers and
// URI, so this is a coverage note, not a failure.
BodyBypass string
// Release returns the buffered body's budget reservation. Never nil, so it
// is always safe to defer. It must run only once the request has been
// served, not when Inspect returns: the buffer stays alive as r.Body for
// the backend to read, so releasing earlier would let the budget admit
// buffering that is still resident.
Release func()
}
// noopRelease is the Release for inspections that reserved no budget.
func noopRelease() {}
// Inspect mirrors r to the AppSec engine and returns its verdict. A nil error
// with restrict.Allow means the request passed. On failure it returns
// DenyAppSecUnavailable wrapped with ErrUnavailable; the caller decides whether
// that blocks, based on the per-service mode.
func (c *Client) Inspect(ctx context.Context, req Request) (Result, error) {
if c == nil {
return Result{Verdict: restrict.DenyAppSecUnavailable, Release: noopRelease}, ErrUnavailable
}
if req.HTTP == nil {
return Result{Verdict: restrict.DenyAppSecUnavailable, Release: noopRelease}, fmt.Errorf("%w: nil request", ErrUnavailable)
}
// release is carried out to the caller rather than deferred here: the
// buffered body outlives this call as r.Body.
if !c.acquireSlot() {
// Deny rather than wave through: a flood must not be a way to switch
// inspection off. Enforce blocks, observe logs and allows, exactly as
// for an unreachable engine.
return Result{Verdict: restrict.DenyAppSecUnavailable, Release: noopRelease},
fmt.Errorf("%w: %d inspections already in flight", ErrUnavailable, cap(c.sem))
}
defer c.releaseSlot()
body, bypass, release, err := c.readBody(req)
if err != nil {
return Result{Verdict: restrict.DenyAppSecUnavailable, Release: release}, fmt.Errorf("%w: read body: %w", ErrUnavailable, err)
}
outbound, err := c.buildRequest(ctx, req, body)
if err != nil {
return Result{Verdict: restrict.DenyAppSecUnavailable, BodyBypass: bypass, Release: release}, fmt.Errorf("%w: %w", ErrUnavailable, err)
}
resp, err := c.http.Do(outbound)
if err != nil {
return Result{Verdict: restrict.DenyAppSecUnavailable, BodyBypass: bypass, Release: release}, fmt.Errorf("%w: %w", ErrUnavailable, err)
}
defer func() {
// Drain before closing. net/http only returns a connection to the idle
// pool once its body is read to EOF; closing with bytes outstanding
// discards it. Every verdict carries a JSON body, so skipping this
// would cost a fresh handshake per inspected request, inside the
// timeout budget.
if _, err := io.Copy(io.Discard, io.LimitReader(resp.Body, maxResponseBytes)); err != nil {
c.logger.Tracef("drain appsec response body: %v", err)
}
if err := resp.Body.Close(); err != nil {
c.logger.Tracef("close appsec response body: %v", err)
}
}()
verdict, err := c.verdict(resp)
return Result{Verdict: verdict, BodyBypass: bypass, Release: release}, err
}
// acquireSlot takes an in-flight slot without blocking, reporting false when
// the engine is already at capacity.
func (c *Client) acquireSlot() bool {
if c.sem == nil {
return true
}
select {
case c.sem <- struct{}{}:
return true
default:
return false
}
}
// releaseSlot returns the slot. Scoped to the engine call, not the request: the
// buffered body outlives the call but the engine's attention does not.
func (c *Client) releaseSlot() {
if c.sem == nil {
return
}
select {
case <-c.sem:
default:
}
}
// readBody buffers the body so it can be mirrored, always restoring it on the
// original request. Returns nil when there is no body to forward: no body at
// all, an upgrade request, or a body over the cap. A login form is forwarded
// with its credential values redacted rather than suppressed.
// release is never nil; the caller invokes it once the request has been served.
func (c *Client) readBody(req Request) (body []byte, bypass string, release func(), err error) {
r := req.HTTP
if r.Body == nil || r.Body == http.NoBody {
return nil, "", noopRelease, nil
}
if c.maxBodyBytes < 0 {
return nil, BypassDisabled, noopRelease, nil
}
// A genuine upgrade request carries no body to inspect (net/http hands us
// http.NoBody, caught above); the hijacked stream is reached through
// Hijacker, never r.Body. The test has to be the forwarder's own, because a
// looser one would skip inspection for requests the forwarder still
// delivers to the backend with their body intact.
if netutil.IsUpgradeRequest(r.Header) {
return nil, BypassUpgrade, noopRelease, nil
}
// A Content-Length over the cap is known to be too large before reading.
if r.ContentLength > c.maxBodyBytes {
return nil, BypassOversize, noopRelease, nil
}
// Reserve the whole cap rather than the eventual length: the reservation
// has to be made before the body is read, and until then the only bound
// known is the cap. Skipping inspection when the pool is drained keeps a
// burst of large bodies from being an out-of-memory lever; the bypass is
// recorded so the gap in coverage is visible.
release = noopRelease
if c.budget != nil {
if !c.budget.Acquire(c.maxBodyBytes) {
c.logger.Debugf("appsec buffer budget exhausted, inspecting headers and URI only")
return nil, BypassBudget, noopRelease, nil
}
var once sync.Once
release = func() { once.Do(func() { c.budget.Release(c.maxBodyBytes) }) }
}
buffered, oversize, err := bufferBody(r, c.maxBodyBytes)
if err != nil {
// bufferBody restored r.Body from the bytes it did read, so the
// reservation stays held until the caller releases it.
return nil, "", release, err
}
// An oversize body was only partially read: a truncated prefix changes the
// engine's verdict in both directions, so inspect headers and URI only.
if oversize {
return nil, BypassOversize, release, nil
}
return redactFormFields(r.Header.Get("Content-Type"), buffered, req.RedactBodyFields), "", release, nil
}
// buildRequest assembles the mirrored request. Per the protocol it is a GET
// when there is no body and a POST otherwise; bytes.Reader gives the outbound
// request an accurate Content-Length, which the engine relies on to read the
// body at all.
func (c *Client) buildRequest(ctx context.Context, req Request, body []byte) (*http.Request, error) {
method := http.MethodGet
var payload io.Reader
if len(body) > 0 {
method = http.MethodPost
payload = bytes.NewReader(body)
}
outbound, err := http.NewRequestWithContext(ctx, method, c.url, payload)
if err != nil {
return nil, fmt.Errorf("build appsec request: %w", err)
}
r := req.HTTP
copyInspectableHeaders(outbound.Header, r.Header)
redactSecrets(outbound.Header, req)
outbound.Header.Set(headerAPIKey, c.apiKey)
outbound.Header.Set(headerIP, req.ClientIP.Unmap().String())
outbound.Header.Set(headerURI, mirroredURI(r.URL, req.RedactQueryParams))
outbound.Header.Set(headerVerb, r.Method)
outbound.Header.Set(headerHost, r.Host)
if ua := r.UserAgent(); ua != "" {
outbound.Header.Set(headerUserAgent, ua)
}
outbound.Header.Set(headerHTTPVersion, httpVersion(r))
if req.TransactionID != "" {
outbound.Header.Set(headerTransactionID, req.TransactionID)
}
return outbound, nil
}
// verdict maps the engine's response to a restrict.Verdict. 200 is a pass and
// 401/500 are engine-side failures; every other status carries a remediation in
// the body. The blocked status code is operator-configurable
// (blocked_http_code), so the action field decides, not the status.
func (c *Client) verdict(resp *http.Response) (restrict.Verdict, error) {
switch resp.StatusCode {
case http.StatusUnauthorized:
return restrict.DenyAppSecUnavailable, fmt.Errorf("%w: rejected api key", ErrUnavailable)
case http.StatusInternalServerError:
return restrict.DenyAppSecUnavailable, fmt.Errorf("%w: engine error", ErrUnavailable)
}
// Every status, 200 included, has to carry a decodable remediation. Taking a
// bare 200 as a pass would mean a URL pointing at anything that answers 200
// (a health endpoint, a load balancer's default page) silently allows every
// request while the service reports itself as enforcing.
var decoded struct {
Action string `json:"action"`
}
if err := json.NewDecoder(io.LimitReader(resp.Body, maxResponseBytes)).Decode(&decoded); err != nil {
// Every remediation carries a decodable action, so a response without
// one is not a verdict: most often the URL points at something that is
// not the AppSec endpoint, which answers 404 with HTML. Reported as
// unavailable rather than a ban so the access log names the real fault
// instead of sending an operator hunting for a rule that never fired.
// Enforce still blocks either way; only the recorded reason differs.
return restrict.DenyAppSecUnavailable, fmt.Errorf("%w: undecodable response (status %d): %w", ErrUnavailable, resp.StatusCode, err)
}
switch decoded.Action {
case actionAllow:
return restrict.Allow, nil
case actionCaptcha:
return restrict.DenyAppSecCaptcha, nil
case actionBan:
return restrict.DenyAppSecBan, nil
case "":
// Decodable JSON without a remediation is not a verdict either: the
// endpoint answered, but not as the engine. Same reasoning as an
// undecodable body, and the same reason to point at configuration.
return restrict.DenyAppSecUnavailable,
fmt.Errorf("%w: response carried no remediation (status %d)", ErrUnavailable, resp.StatusCode)
default:
// A remediation we do not implement still means the engine flagged the
// request, so deny.
c.logger.Debugf("unknown appsec action %q (status %d), treating as ban", decoded.Action, resp.StatusCode)
return restrict.DenyAppSecBan, nil
}
}
// copyInspectableHeaders copies the client's headers, which are what the WAF
// rules actually match on, dropping hop-by-hop headers that describe the
// proxy-to-engine connection rather than the client request, and any header in
// the AppSec protocol namespace.
func copyInspectableHeaders(dst, src http.Header) {
for name, values := range src {
if hopByHopHeaders[http.CanonicalHeaderKey(name)] {
continue
}
if strings.HasPrefix(http.CanonicalHeaderKey(name), headerPrefix) {
continue
}
dst[http.CanonicalHeaderKey(name)] = append([]string(nil), values...)
}
// Content-Length describes the mirrored payload, not the client's: net/http
// sets it from the body we actually attach. Content-Type is kept either way
// so rules matching on it still fire when the body was not forwarded.
dst.Del("Content-Length")
}
// redactSecrets replaces the credential values the proxy withholds from
// backends, so the mirrored copy does not carry them either.
func redactSecrets(dst http.Header, req Request) {
for _, name := range req.RedactHeaders {
// Presence, not Get: a header whose first value is empty still carries
// its later values to the engine, while the upstream strip deletes the
// name outright. Set collapses every value into the placeholder.
if len(dst.Values(name)) > 0 {
dst.Set(name, redactedPlaceholder)
}
}
// Every Cookie line, not just the first: a client may send several, and Get
// would leave the session cookie in any later one mirrored in the clear.
if cookies := dst.Values("Cookie"); len(cookies) > 0 {
redacted := make([]string, len(cookies))
for i, cookie := range cookies {
redacted[i] = redactCookieHeader(cookie, req.RedactCookies)
}
dst["Cookie"] = redacted
}
}
// mirroredURI renders the request target for the URI header, with the named
// query parameter values replaced.
func mirroredURI(u *url.URL, redactParams []string) string {
uri := u.RequestURI()
if u.RawQuery == "" || len(redactParams) == 0 {
return uri
}
redacted := redactQuery(u.RawQuery, redactParams)
if redacted == u.RawQuery {
return uri
}
// RequestURI is path + "?" + RawQuery; swap only the query part so the
// path keeps its original encoding.
return strings.TrimSuffix(uri, u.RawQuery) + redacted
}
var hopByHopHeaders = map[string]bool{
"Connection": true,
"Keep-Alive": true,
"Proxy-Authenticate": true,
"Proxy-Authorization": true,
"Proxy-Connection": true,
"Te": true,
"Trailer": true,
"Transfer-Encoding": true,
"Upgrade": true,
}
// httpVersion renders the two-digit form the engine parses ("11", "20").
func httpVersion(r *http.Request) string {
major, minor := r.ProtoMajor, r.ProtoMinor
if major < 0 || major > 9 || minor < 0 || minor > 9 {
return ""
}
return fmt.Sprintf("%d%d", major, minor)
}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,306 @@
package auth
import (
"crypto/ed25519"
"encoding/base64"
"io"
"net/http"
"net/http/httptest"
"strings"
"sync"
"testing"
"time"
log "github.com/sirupsen/logrus"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/proxy/internal/appsec"
"github.com/netbirdio/netbird/proxy/internal/proxy"
"github.com/netbirdio/netbird/proxy/internal/restrict"
"github.com/netbirdio/netbird/proxy/internal/types"
)
// appsecEngine is a stub AppSec component returning a fixed remediation.
func appsecEngine(t *testing.T, status int, body string) *httptest.Server {
t.Helper()
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(status)
if body != "" {
_, _ = w.Write([]byte(body))
}
}))
t.Cleanup(srv.Close)
return srv
}
// serveWithAppSec runs a request through the middleware for a domain configured
// with the given AppSec mode, returning the response and the captured metadata.
func serveWithAppSec(t *testing.T, mode restrict.AppSecMode, client *appsec.Client, r *http.Request) (*httptest.ResponseRecorder, map[string]string, bool) {
t.Helper()
mw := NewMiddleware(log.StandardLogger(), nil, nil)
mw.SetAppSec(client)
require.NoError(t, mw.AddDomain("svc.example.com", DomainSettings{
AccountID: types.AccountID("acct-1"),
ServiceID: types.ServiceID("svc-1"),
AppSecMode: mode,
}))
reached := false
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
reached = true
w.WriteHeader(http.StatusOK)
}))
cd := proxy.NewCapturedData("req-1")
r = r.WithContext(proxy.WithCapturedData(r.Context(), cd))
rec := httptest.NewRecorder()
handler.ServeHTTP(rec, r)
return rec, cd.GetMetadata(), reached
}
func appsecRequest() *http.Request {
r := httptest.NewRequest(http.MethodGet, "http://svc.example.com/?x=/etc/passwd", nil)
r.Host = "svc.example.com"
r.RemoteAddr = "203.0.113.7:44444"
return r
}
func TestCheckAppSec_EnforceBlocksBannedRequest(t *testing.T) {
srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban","http_status":403}`)
client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
require.NoError(t, err)
rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, appsecRequest())
assert.Equal(t, http.StatusForbidden, rec.Code)
assert.False(t, reached, "a banned request must not reach the backend")
assert.Equal(t, "appsec_ban", meta["appsec_verdict"])
assert.NotContains(t, meta, "appsec_mode", "enforce is the default, only observe is annotated")
}
func TestCheckAppSec_ObserveAllowsAndRecordsVerdict(t *testing.T) {
srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban","http_status":403}`)
client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
require.NoError(t, err)
rec, meta, reached := serveWithAppSec(t, restrict.AppSecObserve, client, appsecRequest())
assert.Equal(t, http.StatusOK, rec.Code)
assert.True(t, reached, "observe mode must not block")
assert.Equal(t, "appsec_ban", meta["appsec_verdict"])
assert.Equal(t, "observe", meta["appsec_mode"])
}
func TestCheckAppSec_AllowedRequestPasses(t *testing.T) {
srv := appsecEngine(t, http.StatusOK, `{"action":"allow","http_status":200}`)
client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
require.NoError(t, err)
rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, appsecRequest())
assert.Equal(t, http.StatusOK, rec.Code)
assert.True(t, reached)
assert.NotContains(t, meta, "appsec_verdict", "a clean request records no verdict")
}
func TestCheckAppSec_OffSkipsInspection(t *testing.T) {
// An engine that would ban everything; the mode must keep us away from it.
srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban"}`)
client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
require.NoError(t, err)
rec, meta, reached := serveWithAppSec(t, restrict.AppSecOff, client, appsecRequest())
assert.Equal(t, http.StatusOK, rec.Code)
assert.True(t, reached)
assert.Empty(t, meta)
}
func TestCheckAppSec_EnforceFailsClosedWithoutClient(t *testing.T) {
rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, nil, appsecRequest())
assert.Equal(t, http.StatusForbidden, rec.Code,
"enforce with no configured endpoint must deny rather than pass traffic uninspected")
assert.False(t, reached)
assert.Equal(t, "appsec_unavailable", meta["appsec_verdict"])
}
func TestCheckAppSec_ObserveAllowsWithoutClient(t *testing.T) {
rec, meta, reached := serveWithAppSec(t, restrict.AppSecObserve, nil, appsecRequest())
assert.Equal(t, http.StatusOK, rec.Code)
assert.True(t, reached)
assert.Equal(t, "appsec_unavailable", meta["appsec_verdict"])
assert.Equal(t, "observe", meta["appsec_mode"])
}
func TestCheckAppSec_EnforceFailsClosedWhenEngineUnreachable(t *testing.T) {
client, err := appsec.New(appsec.Config{URL: "http://127.0.0.1:1/", APIKey: "k"})
require.NoError(t, err)
rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, appsecRequest())
assert.Equal(t, http.StatusForbidden, rec.Code)
assert.False(t, reached)
assert.Equal(t, "appsec_unavailable", meta["appsec_verdict"])
}
func TestCheckAppSec_InspectsOverlayTraffic(t *testing.T) {
srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban"}`)
client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
require.NoError(t, err)
// Requests arriving over the WireGuard overlay skip the geo and IP-reputation
// checks, but request content is just as inspectable.
r := appsecRequest()
r = r.WithContext(types.WithOverlayOrigin(r.Context()))
rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, r)
assert.Equal(t, http.StatusForbidden, rec.Code, "overlay traffic must still be inspected")
assert.False(t, reached)
assert.Equal(t, "appsec_ban", meta["appsec_verdict"])
}
func TestCheckAppSec_UnresolvableClientIPFailsClosed(t *testing.T) {
srv := appsecEngine(t, http.StatusOK, `{"action":"allow"}`)
client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
require.NoError(t, err)
r := appsecRequest()
r.RemoteAddr = "not-an-address"
rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, r)
assert.Equal(t, http.StatusForbidden, rec.Code,
"the engine requires a client address; a request we cannot attribute must not pass")
assert.False(t, reached)
assert.Equal(t, "appsec_unavailable", meta["appsec_verdict"])
}
// The redaction sets are resolved from the domain's schemes at registration, so
// what AppSec withholds cannot drift from what those schemes actually accept.
func TestAddDomain_ResolvesRedactionSetsFromSchemes(t *testing.T) {
mw := NewMiddleware(log.StandardLogger(), nil, nil)
require.NoError(t, mw.AddDomain("svc.example.com", DomainSettings{
Schemes: []Scheme{
NewPassword(nil, "svc-1", "acct-1"),
NewHeader(nil, "svc-1", "acct-1", "X-Api-Key"),
},
SessionPublicKey: base64.StdEncoding.EncodeToString(make([]byte, ed25519.PublicKeySize)),
SessionExpiration: time.Hour,
AppSecMode: restrict.AppSecEnforce,
}))
mw.domainsMux.RLock()
config := mw.domains["svc.example.com"]
mw.domainsMux.RUnlock()
assert.Equal(t, []string{"password"}, config.redactBodyFields)
assert.Equal(t, []string{"X-Api-Key"}, config.redactHeaders)
// r.FormValue merges the query into the form, so a credential passed there
// authenticates and must be redacted alongside the OIDC session token.
assert.Equal(t, []string{"session_token", "password"}, config.redactQueryParams)
}
// countingBudget records reservations so a test can observe when the
// middleware hands them back.
type countingBudget struct {
mu sync.Mutex
total int64
used int64
maxAtOnce int64
}
func (b *countingBudget) Acquire(n int64) bool {
b.mu.Lock()
defer b.mu.Unlock()
if b.used+n > b.total {
return false
}
b.used += n
if b.used > b.maxAtOnce {
b.maxAtOnce = b.used
}
return true
}
func (b *countingBudget) Release(n int64) {
b.mu.Lock()
defer b.mu.Unlock()
b.used -= n
}
func (b *countingBudget) inUse() int64 {
b.mu.Lock()
defer b.mu.Unlock()
return b.used
}
// The buffered body stays alive as r.Body until the backend has read it, so
// Protect must hold the reservation for the whole request and return it only
// once the handler chain has unwound. Releasing inside Inspect would let the
// budget admit buffering that is still resident.
func TestProtect_AppSecBudgetHeldForRequestAndReleasedAfter(t *testing.T) {
srv := appsecEngine(t, http.StatusOK, `{"action":"allow"}`)
budget := &countingBudget{total: 1 << 20}
client, err := appsec.New(appsec.Config{
URL: srv.URL,
APIKey: "k",
MaxBodyBytes: 4096,
Budget: budget,
})
require.NoError(t, err)
mw := NewMiddleware(log.StandardLogger(), nil, nil)
mw.SetAppSec(client)
require.NoError(t, mw.AddDomain("svc.example.com", DomainSettings{
AccountID: types.AccountID("acct-1"),
ServiceID: types.ServiceID("svc-1"),
AppSecMode: restrict.AppSecEnforce,
}))
var inHandler int64
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
// The backend reads the buffered body here, so the reservation must
// still be held at this point.
inHandler = budget.inUse()
_, _ = io.ReadAll(r.Body)
w.WriteHeader(http.StatusOK)
}))
r := httptest.NewRequest(http.MethodPost, "http://svc.example.com/", strings.NewReader("payload"))
r.Host = "svc.example.com"
cd := proxy.NewCapturedData("req-1")
r = r.WithContext(proxy.WithCapturedData(r.Context(), cd))
handler.ServeHTTP(httptest.NewRecorder(), r)
assert.Equal(t, int64(4096), inHandler, "the reservation must be held while the backend reads the body")
assert.Equal(t, int64(0), budget.inUse(), "Protect must release the reservation once the request is served")
}
// A denied request never reaches the backend, but Protect still has to hand the
// reservation back or the pool leaks one cap per blocked request.
func TestProtect_AppSecBudgetReleasedOnDeny(t *testing.T) {
srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban"}`)
budget := &countingBudget{total: 1 << 20}
client, err := appsec.New(appsec.Config{
URL: srv.URL,
APIKey: "k",
MaxBodyBytes: 4096,
Budget: budget,
})
require.NoError(t, err)
r := httptest.NewRequest(http.MethodPost, "http://svc.example.com/", strings.NewReader("payload"))
r.Host = "svc.example.com"
rec, _, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, r)
assert.False(t, reached, "a banned request must not reach the backend")
assert.Equal(t, http.StatusForbidden, rec.Code)
assert.Equal(t, int64(0), budget.inUse(), "a blocked request must not leak its reservation")
}

View File

@@ -39,6 +39,11 @@ func (Header) Type() auth.Method {
return auth.MethodHeader
}
// HeaderName returns the request header this scheme reads its credential from.
func (h Header) HeaderName() string {
return h.headerName
}
// Authenticate checks for the configured header in the request. If absent,
// returns empty (unauthenticated). If present, validates via gRPC.
func (h Header) Authenticate(r *http.Request) (string, string, error) {

View File

@@ -18,6 +18,7 @@ import (
"google.golang.org/grpc"
"github.com/netbirdio/netbird/proxy/auth"
"github.com/netbirdio/netbird/proxy/internal/appsec"
"github.com/netbirdio/netbird/proxy/internal/proxy"
"github.com/netbirdio/netbird/proxy/internal/restrict"
"github.com/netbirdio/netbird/proxy/internal/types"
@@ -25,6 +26,11 @@ import (
"github.com/netbirdio/netbird/shared/management/proto"
)
// sessionCookieNames is the cookie set AppSec redacts before mirroring: the
// proxy's session cookie is a bearer credential for the service, and the
// reverse proxy already strips it before forwarding upstream.
var sessionCookieNames = []string{auth.SessionCookieName}
// errValidationUnavailable indicates that session validation failed due to
// an infrastructure error (e.g. gRPC unavailable), not an invalid token.
var errValidationUnavailable = errors.New("session validation unavailable")
@@ -59,6 +65,14 @@ type DomainConfig struct {
IPRestrictions *restrict.Filter
// Private routes the domain through ValidateTunnelPeer; failure → 403.
Private bool
// AppSecMode enables CrowdSec AppSec request inspection for this domain.
AppSecMode restrict.AppSecMode
// redact* name the credentials this domain's schemes accept, resolved once
// at registration. AppSec replaces their values before mirroring a request,
// matching what the reverse proxy strips before forwarding upstream.
redactBodyFields []string
redactHeaders []string
redactQueryParams []string
}
type validationResult struct {
@@ -82,6 +96,9 @@ type Middleware struct {
sessionValidator SessionValidator
geo restrict.GeoResolver
tunnelCache *tunnelValidationCache
// appsec is the shared CrowdSec AppSec client, nil when the proxy has no
// AppSec endpoint configured. Set once during startup, before serving.
appsec *appsec.Client
}
// NewMiddleware creates a new authentication middleware. The sessionValidator is
@@ -99,6 +116,12 @@ func NewMiddleware(logger *log.Logger, sessionValidator SessionValidator, geo re
}
}
// SetAppSec installs the shared CrowdSec AppSec client. Must be called during
// startup, before the middleware serves any request.
func (mw *Middleware) SetAppSec(client *appsec.Client) {
mw.appsec = client
}
// Protect wraps next with per-domain authentication and IP restriction checks.
// Requests whose Host is not registered pass through unchanged.
func (mw *Middleware) Protect(next http.Handler) http.Handler {
@@ -123,6 +146,14 @@ func (mw *Middleware) Protect(next http.Handler) http.Handler {
return
}
// Deferred, not released here: the inspected body stays alive as r.Body
// until the backend has read it, which happens inside next.ServeHTTP.
appSecAllowed, releaseAppSec := mw.checkAppSec(w, r, config)
defer releaseAppSec()
if !appSecAllowed {
return
}
// Private services bypass operator schemes and gate on tunnel peer.
if config.Private {
if mw.forwardWithTunnelPeer(w, r, host, config, next) {
@@ -262,6 +293,134 @@ func (mw *Middleware) checkIPRestrictions(w http.ResponseWriter, r *http.Request
return false
}
// checkAppSec mirrors the request to the CrowdSec AppSec engine when the domain
// enables inspection. Returns false when the request was blocked and a response
// has been written.
//
// The returned release frees the body-buffering budget the inspection reserved
// and is never nil. It must run only after the request has been served, since
// the buffered body stays alive as r.Body for the backend to read.
//
// Every non-allow remediation blocks with 403, captcha included: the proxy has
// no challenge flow to serve. The distinct verdict is still recorded so the
// access log shows which remediation the engine actually chose.
//
// Unlike the geo and IP-reputation checks, this runs for overlay traffic too:
// AppSec inspects request content, which is just as meaningful when the caller
// reached the proxy through the WireGuard tunnel.
func (mw *Middleware) checkAppSec(w http.ResponseWriter, r *http.Request, config DomainConfig) (bool, func()) {
if !config.AppSecMode.Enabled() {
return true, func() {}
}
verdict, release := mw.inspectAppSec(r, config)
if verdict == restrict.Allow {
return true, release
}
observe := config.AppSecMode == restrict.AppSecObserve
if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
cd.SetMetadata("appsec_verdict", verdict.String())
if observe {
cd.SetMetadata("appsec_mode", "observe")
}
}
if observe {
mw.logger.Debugf("AppSec observe: would block %s for %s (%s)", r.RemoteAddr, r.Host, verdict)
return true, release
}
mw.markDenied(r, verdict.String())
mw.logger.Debugf("AppSec: %s for %s %s", verdict, r.Host, r.RemoteAddr)
http.Error(w, "Forbidden", http.StatusForbidden)
return false, release
}
// inspectAppSec runs the AppSec call and returns its verdict. Failures come
// back as DenyAppSecUnavailable regardless of mode so observe mode still
// records that inspection did not happen; the caller decides what blocks. The
// returned release is never nil.
func (mw *Middleware) inspectAppSec(r *http.Request, config DomainConfig) (restrict.Verdict, func()) {
// Mode requested but the proxy has no AppSec endpoint configured. Management
// gates this on the cluster capability; a stale mapping can still arrive.
if mw.appsec == nil {
mw.logger.Debugf("AppSec mode %q requested for %s but no AppSec endpoint is configured", config.AppSecMode, r.Host)
return restrict.DenyAppSecUnavailable, func() {}
}
clientIP := mw.resolveClientIP(r)
if !clientIP.IsValid() {
// The engine requires a client address, and a request whose source we
// cannot establish is exactly the kind we must not wave through.
mw.logger.Debugf("AppSec: cannot resolve client address for %q", r.RemoteAddr)
return restrict.DenyAppSecUnavailable, func() {}
}
req := appsec.Request{
HTTP: r,
ClientIP: clientIP,
RedactBodyFields: config.redactBodyFields,
RedactHeaders: config.redactHeaders,
RedactCookies: sessionCookieNames,
RedactQueryParams: config.redactQueryParams,
}
if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
req.TransactionID = cd.GetRequestID()
}
result, err := mw.appsec.Inspect(r.Context(), req)
if err != nil {
mw.logger.Debugf("AppSec inspection failed for %s: %v", r.Host, err)
}
// Record when the body went uninspected: headers and URI were still
// checked, but an operator reading the log should not read a clean verdict
// as "the payload was examined". Oversize is reachable by padding, so its
// absence from the log would hide a deliberate opt-out.
if result.BodyBypass != "" {
if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
cd.SetMetadata("appsec_body_bypass", result.BodyBypass)
}
}
return result.Verdict, result.Release
}
// credentialFormFields lists the login form fields whose values are redacted
// from the mirrored body, so a password or PIN submitted to the proxy's own
// login form never reaches the Security Engine.
func credentialFormFields(schemes []Scheme) []string {
var fields []string
for _, s := range schemes {
switch s.Type() {
case auth.MethodPassword:
fields = append(fields, passwordFormId)
case auth.MethodPIN:
fields = append(fields, pinFormId)
}
}
return fields
}
// credentialHeaders lists the request headers whose values are redacted from
// the mirrored request. A header-auth scheme carries a session token the proxy
// validates and never forwards upstream, so the engine must not see it either.
func credentialHeaders(schemes []Scheme) []string {
var names []string
for _, s := range schemes {
// Structural, not a concrete Header assertion: if the scheme is ever
// registered as a pointer, a type assertion would quietly stop matching
// and the header would start reaching the engine again.
named, ok := s.(interface{ HeaderName() string })
if !ok {
continue
}
if name := named.HeaderName(); name != "" {
names = append(names, name)
}
}
return names
}
// resolveClientIP extracts the real client IP from CapturedData, falling back to r.RemoteAddr.
func (mw *Middleware) resolveClientIP(r *http.Request) netip.Addr {
if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
@@ -281,12 +440,18 @@ func (mw *Middleware) resolveClientIP(r *http.Request) netip.Addr {
return addr.Unmap()
}
// blockIPRestriction sets captured data fields for an IP-restriction block event.
func (mw *Middleware) blockIPRestriction(r *http.Request, reason string) {
// markDenied records the deny reason on the captured data so the access log
// attributes the response to the proxy rather than the backend.
func (mw *Middleware) markDenied(r *http.Request, reason string) {
if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
cd.SetOrigin(proxy.OriginAuth)
cd.SetAuthMethod(reason)
}
}
// blockIPRestriction sets captured data fields for an IP-restriction block event.
func (mw *Middleware) blockIPRestriction(r *http.Request, reason string) {
mw.markDenied(r, reason)
mw.logger.Debugf("IP restriction: %s for %s", reason, r.RemoteAddr)
}
@@ -637,45 +802,61 @@ func wasCredentialSubmitted(r *http.Request, method auth.Method) bool {
case auth.MethodPassword:
return r.FormValue("password") != ""
case auth.MethodOIDC:
return r.URL.Query().Get("session_token") != ""
return r.URL.Query().Get(sessionTokenParam) != ""
}
return false
}
// AddDomain registers authentication schemes for the given domain. With schemes a valid session public key is required.
// private=true forces ValidateTunnelPeer enforcement (403 on failure) regardless of the schemes list.
func (mw *Middleware) AddDomain(domain string, schemes []Scheme, publicKeyB64 string, expiration time.Duration, accountID types.AccountID, serviceID types.ServiceID, ipRestrictions *restrict.Filter, private bool) error {
if len(schemes) == 0 {
mw.domainsMux.Lock()
defer mw.domainsMux.Unlock()
mw.domains[domain] = DomainConfig{
AccountID: accountID,
ServiceID: serviceID,
IPRestrictions: ipRestrictions,
Private: private,
}
return nil
// DomainSettings is the per-domain configuration AddDomain applies.
type DomainSettings struct {
Schemes []Scheme
// SessionPublicKey is the base64-encoded ed25519 key used to verify session
// cookies. Required when Schemes is non-empty.
SessionPublicKey string
SessionExpiration time.Duration
AccountID types.AccountID
ServiceID types.ServiceID
IPRestrictions *restrict.Filter
// Private forces ValidateTunnelPeer enforcement (403 on failure) regardless
// of the schemes list.
Private bool
AppSecMode restrict.AppSecMode
}
// AddDomain registers authentication schemes for the given domain. With schemes
// a valid session public key is required.
func (mw *Middleware) AddDomain(domain string, settings DomainSettings) error {
credentialFields := credentialFormFields(settings.Schemes)
config := DomainConfig{
AccountID: settings.AccountID,
ServiceID: settings.ServiceID,
IPRestrictions: settings.IPRestrictions,
Private: settings.Private,
AppSecMode: settings.AppSecMode,
redactBodyFields: credentialFields,
redactHeaders: credentialHeaders(settings.Schemes),
// A credential can arrive in the query too: r.FormValue merges the URL
// query into the form, so "?password=..." authenticates just as a form
// post does and must not be mirrored in the clear either.
redactQueryParams: append([]string{sessionTokenParam}, credentialFields...),
}
pubKeyBytes, err := base64.StdEncoding.DecodeString(publicKeyB64)
if err != nil {
return fmt.Errorf("decode session public key for domain %s: %w", domain, err)
}
if len(pubKeyBytes) != ed25519.PublicKeySize {
return fmt.Errorf("invalid session public key size for domain %s: got %d, want %d", domain, len(pubKeyBytes), ed25519.PublicKeySize)
if len(settings.Schemes) > 0 {
pubKeyBytes, err := base64.StdEncoding.DecodeString(settings.SessionPublicKey)
if err != nil {
return fmt.Errorf("decode session public key for domain %s: %w", domain, err)
}
if len(pubKeyBytes) != ed25519.PublicKeySize {
return fmt.Errorf("invalid session public key size for domain %s: got %d, want %d", domain, len(pubKeyBytes), ed25519.PublicKeySize)
}
config.Schemes = settings.Schemes
config.SessionPublicKey = pubKeyBytes
config.SessionExpiration = settings.SessionExpiration
}
mw.domainsMux.Lock()
defer mw.domainsMux.Unlock()
mw.domains[domain] = DomainConfig{
Schemes: schemes,
SessionPublicKey: pubKeyBytes,
SessionExpiration: expiration,
AccountID: accountID,
ServiceID: serviceID,
IPRestrictions: ipRestrictions,
Private: private,
}
mw.domains[domain] = config
return nil
}
@@ -730,10 +911,10 @@ func (mw *Middleware) validateSessionToken(ctx context.Context, host, token stri
// parameter removed so it doesn't linger in the browser's address bar or history.
func stripSessionTokenParam(u *url.URL) string {
q := u.Query()
if !q.Has("session_token") {
if !q.Has(sessionTokenParam) {
return u.RequestURI()
}
q.Del("session_token")
q.Del(sessionTokenParam)
clean := *u
clean.RawQuery = q.Encode()
return clean.RequestURI()

View File

@@ -64,7 +64,7 @@ func TestAddDomain_ValidKey(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
err := mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false)
err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour})
require.NoError(t, err)
mw.domainsMux.RLock()
@@ -81,7 +81,7 @@ func TestAddDomain_EmptyKey(t *testing.T) {
mw := NewMiddleware(log.StandardLogger(), nil, nil)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
err := mw.AddDomain("example.com", []Scheme{scheme}, "", time.Hour, "", "", nil, false)
err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionExpiration: time.Hour})
require.Error(t, err)
assert.Contains(t, err.Error(), "invalid session public key size")
@@ -95,7 +95,7 @@ func TestAddDomain_InvalidBase64(t *testing.T) {
mw := NewMiddleware(log.StandardLogger(), nil, nil)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
err := mw.AddDomain("example.com", []Scheme{scheme}, "not-valid-base64!!!", time.Hour, "", "", nil, false)
err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: "not-valid-base64!!!", SessionExpiration: time.Hour})
require.Error(t, err)
assert.Contains(t, err.Error(), "decode session public key")
@@ -110,7 +110,7 @@ func TestAddDomain_WrongKeySize(t *testing.T) {
shortKey := base64.StdEncoding.EncodeToString([]byte("tooshort"))
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
err := mw.AddDomain("example.com", []Scheme{scheme}, shortKey, time.Hour, "", "", nil, false)
err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: shortKey, SessionExpiration: time.Hour})
require.Error(t, err)
assert.Contains(t, err.Error(), "invalid session public key size")
@@ -123,7 +123,7 @@ func TestAddDomain_WrongKeySize(t *testing.T) {
func TestAddDomain_NoSchemes_NoKeyRequired(t *testing.T) {
mw := NewMiddleware(log.StandardLogger(), nil, nil)
err := mw.AddDomain("example.com", nil, "", time.Hour, "", "", nil, false)
err := mw.AddDomain("example.com", DomainSettings{SessionExpiration: time.Hour})
require.NoError(t, err, "domains with no auth schemes should not require a key")
mw.domainsMux.RLock()
@@ -139,8 +139,8 @@ func TestAddDomain_OverwritesPreviousConfig(t *testing.T) {
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp1.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp2.PublicKey, 2*time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp1.PublicKey, SessionExpiration: time.Hour}))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp2.PublicKey, SessionExpiration: 2 * time.Hour}))
mw.domainsMux.RLock()
config := mw.domains["example.com"]
@@ -156,7 +156,7 @@ func TestRemoveDomain(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
mw.RemoveDomain("example.com")
@@ -180,7 +180,7 @@ func TestProtect_UnknownDomainPassesThrough(t *testing.T) {
func TestProtect_DomainWithNoSchemesPassesThrough(t *testing.T) {
mw := NewMiddleware(log.StandardLogger(), nil, nil)
require.NoError(t, mw.AddDomain("example.com", nil, "", time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -197,7 +197,7 @@ func TestProtect_UnauthenticatedRequestIsBlocked(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
var backendCalled bool
backend := http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -218,7 +218,7 @@ func TestProtect_HostWithPortIsMatched(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
var backendCalled bool
backend := http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -239,7 +239,7 @@ func TestProtect_ValidSessionCookiePassesThrough(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
token, err := sessionkey.SignToken(kp.PrivateKey, "test-user", "", "example.com", auth.MethodPIN, nil, nil, time.Hour)
require.NoError(t, err)
@@ -272,7 +272,7 @@ func TestProtect_SessionCookieGroupsPropagate(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
groups := []string{"engineering", "sre"}
token, err := sessionkey.SignToken(kp.PrivateKey, "test-user", "", "example.com", auth.MethodPIN, groups, nil, time.Hour)
@@ -337,7 +337,7 @@ func TestProtect_PrivateService_TunnelPeerGroupsPropagate(t *testing.T) {
kp := generateTestKeyPair(t)
// Private service: no operator schemes — auth gates solely on the tunnel peer.
require.NoError(t, mw.AddDomain("agent.example.com", nil, kp.PublicKey, time.Hour, "acct-1", "svc-1", nil, true))
require.NoError(t, mw.AddDomain("agent.example.com", DomainSettings{SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
cd := proxy.NewCapturedData("")
cd.SetClientIP(netip.MustParseAddr("100.90.1.14")) // CGNAT tunnel source
@@ -377,7 +377,7 @@ func TestProtect_PrivateService_TunnelPeerDenied(t *testing.T) {
}}
mw := NewMiddleware(log.StandardLogger(), validator, nil)
kp := generateTestKeyPair(t)
require.NoError(t, mw.AddDomain("agent.example.com", nil, kp.PublicKey, time.Hour, "acct-1", "svc-1", nil, true))
require.NoError(t, mw.AddDomain("agent.example.com", DomainSettings{SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
cd := proxy.NewCapturedData("")
cd.SetClientIP(netip.MustParseAddr("100.90.1.14"))
@@ -405,7 +405,7 @@ func TestProtect_ExpiredSessionCookieIsRejected(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
// Sign a token that expired 1 second ago.
token, err := sessionkey.SignToken(kp.PrivateKey, "test-user", "", "example.com", auth.MethodPIN, nil, nil, -time.Second)
@@ -431,7 +431,7 @@ func TestProtect_WrongDomainCookieIsRejected(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
// Token signed for a different domain audience.
token, err := sessionkey.SignToken(kp.PrivateKey, "test-user", "", "other.com", auth.MethodPIN, nil, nil, time.Hour)
@@ -458,7 +458,7 @@ func TestProtect_WrongKeyCookieIsRejected(t *testing.T) {
kp2 := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp1.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp1.PublicKey, SessionExpiration: time.Hour}))
// Token signed with a different private key.
token, err := sessionkey.SignToken(kp2.PrivateKey, "test-user", "", "example.com", auth.MethodPIN, nil, nil, time.Hour)
@@ -495,7 +495,7 @@ func TestProtect_SchemeAuthRedirectsWithCookie(t *testing.T) {
return "", "pin", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
var backendCalled bool
backend := http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -548,7 +548,7 @@ func TestProtect_FailedAuthDoesNotSetCookie(t *testing.T) {
return "", "pin", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -584,7 +584,7 @@ func TestProtect_MultipleSchemes(t *testing.T) {
return "", "password", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{pinScheme, passwordScheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{pinScheme, passwordScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
var backendCalled bool
backend := http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -614,7 +614,7 @@ func TestProtect_InvalidTokenFromSchemeReturns400(t *testing.T) {
return "invalid-jwt-token", "", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -638,7 +638,7 @@ func TestAddDomain_RandomBytes32NotEd25519(t *testing.T) {
key := base64.StdEncoding.EncodeToString(randomBytes)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
err = mw.AddDomain("example.com", []Scheme{scheme}, key, time.Hour, "", "", nil, false)
err = mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: key, SessionExpiration: time.Hour})
require.NoError(t, err, "any 32-byte key should be accepted at registration time")
}
@@ -647,10 +647,10 @@ func TestAddDomain_InvalidKeyDoesNotCorruptExistingConfig(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
// Attempt to overwrite with an invalid key.
err := mw.AddDomain("example.com", []Scheme{scheme}, "bad", time.Hour, "", "", nil, false)
err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: "bad", SessionExpiration: time.Hour})
require.Error(t, err)
// The original valid config should still be intact.
@@ -674,7 +674,7 @@ func TestProtect_FailedPinAuthCapturesAuthMethod(t *testing.T) {
return "", "pin", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
capturedData := proxy.NewCapturedData("")
handler := mw.Protect(newPassthroughHandler())
@@ -701,7 +701,7 @@ func TestProtect_FailedPasswordAuthCapturesAuthMethod(t *testing.T) {
return "", "password", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
capturedData := proxy.NewCapturedData("")
handler := mw.Protect(newPassthroughHandler())
@@ -728,7 +728,7 @@ func TestProtect_NoCredentialsDoesNotCaptureAuthMethod(t *testing.T) {
return "", "pin", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
capturedData := proxy.NewCapturedData("")
handler := mw.Protect(newPassthroughHandler())
@@ -815,8 +815,7 @@ func TestWasCredentialSubmitted(t *testing.T) {
func TestCheckIPRestrictions_UnparseableAddress(t *testing.T) {
mw := NewMiddleware(log.StandardLogger(), nil, nil)
err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"10.0.0.0/8"}}), false)
err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"10.0.0.0/8"}})})
require.NoError(t, err)
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -851,8 +850,7 @@ func TestCheckIPRestrictions_UsesCapturedDataClientIP(t *testing.T) {
// trusted proxies), checkIPRestrictions should use that IP, not RemoteAddr.
mw := NewMiddleware(log.StandardLogger(), nil, nil)
err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"203.0.113.0/24"}}), false)
err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"203.0.113.0/24"}})})
require.NoError(t, err)
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -892,8 +890,7 @@ func TestCheckIPRestrictions_NilGeoWithCountryRules(t *testing.T) {
// Geo is nil, country restrictions are configured: must deny (fail-close).
mw := NewMiddleware(log.StandardLogger(), nil, nil)
err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
restrict.ParseFilter(restrict.FilterConfig{AllowedCountries: []string{"US"}}), false)
err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCountries: []string{"US"}})})
require.NoError(t, err)
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -916,11 +913,10 @@ func TestCheckIPRestrictions_NilGeoWithCountryRules(t *testing.T) {
func TestCheckIPRestrictions_OverlayOriginSkipsCountryRules(t *testing.T) {
mw := NewMiddleware(log.StandardLogger(), nil, nil)
err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
restrict.ParseFilter(restrict.FilterConfig{
AllowedCIDRs: []string{"100.64.0.0/10"},
AllowedCountries: []string{"US"},
}), false)
err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{
AllowedCIDRs: []string{"100.64.0.0/10"},
AllowedCountries: []string{"US"},
})})
require.NoError(t, err)
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -953,8 +949,7 @@ func TestCheckIPRestrictions_OverlayOriginSkipsCountryRules(t *testing.T) {
func TestCheckIPRestrictions_OverlayOriginRespectsCIDR(t *testing.T) {
mw := NewMiddleware(log.StandardLogger(), nil, nil)
err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"100.64.0.0/16"}}), false)
err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"100.64.0.0/16"}})})
require.NoError(t, err)
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -982,7 +977,7 @@ func TestProtect_OIDCOnlyRedirectsDirectly(t *testing.T) {
return "", oidcURL, nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -1011,7 +1006,7 @@ func TestProtect_OIDCWithOtherMethodShowsLoginPage(t *testing.T) {
return "", "pin", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{oidcScheme, pinScheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{oidcScheme, pinScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -1055,7 +1050,7 @@ func TestProtect_HeaderAuth_ForwardsOnSuccess(t *testing.T) {
kp := generateTestKeyPair(t)
hdr := newHeaderSchemeWithToken(t, kp, "X-API-Key", "secret-key")
require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
var backendCalled bool
capturedData := proxy.NewCapturedData("")
@@ -1098,7 +1093,7 @@ func TestProtect_HeaderAuth_MissingHeaderFallsThrough(t *testing.T) {
hdr := newHeaderSchemeWithToken(t, kp, "X-API-Key", "secret-key")
// Also add a PIN scheme so we can verify fallthrough behavior.
pinScheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr, pinScheme}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr, pinScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
handler := mw.Protect(newPassthroughHandler())
@@ -1118,7 +1113,7 @@ func TestProtect_HeaderAuth_WrongValueReturns401(t *testing.T) {
return &proto.AuthenticateResponse{Success: false}, nil
}}
hdr := NewHeader(mock, "svc1", "acc1", "X-API-Key")
require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
capturedData := proxy.NewCapturedData("")
handler := mw.Protect(newPassthroughHandler())
@@ -1141,7 +1136,7 @@ func TestProtect_HeaderAuth_InfraErrorReturns502(t *testing.T) {
return nil, errors.New("gRPC unavailable")
}}
hdr := NewHeader(mock, "svc1", "acc1", "X-API-Key")
require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
handler := mw.Protect(newPassthroughHandler())
@@ -1158,7 +1153,7 @@ func TestProtect_HeaderAuth_SubsequentRequestUsesSessionCookie(t *testing.T) {
kp := generateTestKeyPair(t)
hdr := newHeaderSchemeWithToken(t, kp, "X-API-Key", "secret-key")
require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusOK)
@@ -1218,7 +1213,7 @@ func TestProtect_HeaderAuth_MultipleValuesSameHeader(t *testing.T) {
// Single Header scheme (as if one entry existed), but the mock checks both values.
hdr := NewHeader(mock, "svc1", "acc1", "Authorization")
require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
var backendCalled bool
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -1276,7 +1271,7 @@ func TestProtect_OIDCOnPlainHTTP_BlockedWith400(t *testing.T) {
return "", "https://idp.example.com/authorize", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -1300,7 +1295,7 @@ func TestProtect_OIDCOverTLS_NotBlocked(t *testing.T) {
return "", "https://idp.example.com/authorize", nil
},
}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -1320,7 +1315,7 @@ func TestProtect_NonOIDCSchemes_PlainHTTP_NotBlocked(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -1350,7 +1345,7 @@ func TestProtect_TunnelPeerFastPath_RequiresInboundMarker(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())
@@ -1385,7 +1380,7 @@ func TestProtect_TunnelPeerFastPath_TakesPathWithInboundMarker(t *testing.T) {
kp := generateTestKeyPair(t)
scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
handler := mw.Protect(newPassthroughHandler())

View File

@@ -13,6 +13,10 @@ import (
"github.com/netbirdio/netbird/shared/management/proto"
)
// sessionTokenParam is the query parameter the management server uses to hand
// the minted session token back to the proxy after an OIDC login.
const sessionTokenParam = "session_token"
type urlGenerator interface {
GetOIDCURL(context.Context, *proto.GetOIDCURLRequest, ...grpc.CallOption) (*proto.GetOIDCURLResponse, error)
}
@@ -43,7 +47,7 @@ func (o OIDC) Authenticate(r *http.Request) (string, string, error) {
// Check for the session_token query param (from OIDC redirects).
// The management server passes the token in the URL because it cannot set
// cookies for the proxy's domain (cookies are domain-scoped per RFC 6265).
if token := r.URL.Query().Get("session_token"); token != "" {
if token := r.URL.Query().Get(sessionTokenParam); token != "" {
return token, "", nil
}

View File

@@ -44,7 +44,7 @@ func (s *stubSessionValidator) ValidateTunnelPeer(_ context.Context, in *proto.V
func newTunnelMiddleware(t *testing.T, validator SessionValidator) *Middleware {
t.Helper()
mw := NewMiddleware(log.New(), validator, nil)
require.NoError(t, mw.AddDomain("svc.example", nil, "", 0, "acct-1", "svc-1", nil, false))
require.NoError(t, mw.AddDomain("svc.example", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1"}))
return mw
}
@@ -235,8 +235,8 @@ func TestForwardWithTunnelPeer_RoutesAccountIDIntoCacheKey(t *testing.T) {
}
mw := NewMiddleware(log.New(), validator, nil)
require.NoError(t, mw.AddDomain("svc-a.example", nil, "", 0, "acct-a", "svc-a", nil, false))
require.NoError(t, mw.AddDomain("svc-b.example", nil, "", 0, "acct-b", "svc-b", nil, false))
require.NoError(t, mw.AddDomain("svc-a.example", DomainSettings{AccountID: "acct-a", ServiceID: "svc-a"}))
require.NoError(t, mw.AddDomain("svc-b.example", DomainSettings{AccountID: "acct-b", ServiceID: "svc-b"}))
// The fast-path requires the inbound-listener marker on the context.
// The peerstore lookup itself is account-agnostic at this level
@@ -299,7 +299,7 @@ func TestForwardWithTunnelPeer_LocalLookupShortCircuitDoesNotPopulateCache(t *te
func TestPrivateService_FailsClosedOnTunnelPeerFailure(t *testing.T) {
mw := NewMiddleware(log.New(), nil, nil)
require.NoError(t, mw.AddDomain("private.svc", nil, "", 0, "acct-1", "svc-1", nil, true))
require.NoError(t, mw.AddDomain("private.svc", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
called := false
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -328,7 +328,7 @@ func TestPrivateService_ForwardsOnTunnelPeerSuccess(t *testing.T) {
},
}
mw := NewMiddleware(log.New(), validator, nil)
require.NoError(t, mw.AddDomain("private.svc", nil, "", 0, "acct-1", "svc-1", nil, true))
require.NoError(t, mw.AddDomain("private.svc", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
called := false
handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {

View File

@@ -21,6 +21,8 @@ import (
"strconv"
"strings"
"sync"
"github.com/netbirdio/netbird/proxy/internal/netutil"
)
// MaxRoutingScanBytes bounds how far ScanRoutingFields will read into a
@@ -34,7 +36,6 @@ const MaxRoutingScanBytes int64 = 32 << 20
// metadata key by the chain when a request body is not surfaced.
const (
BypassUpgradeHeader = "upgrade_header"
BypassConnectionUpgrd = "connection_upgrade"
BypassContentType = "content_type_not_allowed"
BypassBudget = "capture_budget_exhausted"
BypassNoConfig = "no_capture_config"
@@ -125,12 +126,13 @@ func CaptureRequest(r *http.Request, cfg *Config, b Budget) (body []byte, trunca
if cfg.MaxRequestBytes <= 0 {
return nil, false, 0, BypassCapZero, release, nil
}
if r.Header.Get("Upgrade") != "" {
// The predicate has to be the forwarder's own: a looser one (either header
// on its own) skips capture for requests the forwarder still delivers to
// the upstream with their body intact, which hides them from every
// deny-capable middleware in the chain.
if netutil.IsUpgradeRequest(r.Header) {
return nil, false, 0, BypassUpgradeHeader, release, nil
}
if strings.EqualFold(r.Header.Get("Connection"), "upgrade") {
return nil, false, 0, BypassConnectionUpgrd, release, nil
}
if !contentTypeAllowed(r.Header.Get("Content-Type"), cfg.ContentTypes) {
return nil, false, 0, BypassContentType, release, nil
}

View File

@@ -0,0 +1,23 @@
package netutil
import (
"net/http"
"golang.org/x/net/http/httpguts"
)
// IsUpgradeRequest reports whether r is a protocol-upgrade request, using the
// same predicate httputil.ReverseProxy applies when it decides to hand the
// connection over instead of proxying normally.
//
// Matching the forwarder exactly matters for anything that inspects a request
// before it is proxied: a looser test (an Upgrade header on its own, say) marks
// a request as an upgrade and skips inspection, while the forwarder still
// delivers it to the backend as an ordinary request with its body intact. That
// gap is a body-inspection bypass reachable by adding one header.
func IsUpgradeRequest(h http.Header) bool {
if !httpguts.HeaderValuesContainsToken(h["Connection"], "Upgrade") {
return false
}
return h.Get("Upgrade") != ""
}

View File

@@ -50,6 +50,59 @@ const (
CrowdSecObserve CrowdSecMode = "observe"
)
// AllowMatch controls how the configured allowlists (CIDR, country) combine.
// Blocklists are always a separate hard-deny gate and are unaffected by it.
type AllowMatch string
const (
// AllowMatchAll requires the address to match every configured allowlist
// (AND). This is the default and preserves the historical behavior.
AllowMatchAll AllowMatch = "all"
// AllowMatchAny requires the address to match at least one configured
// allowlist (OR), e.g. "allowed country OR allowed CIDR".
AllowMatchAny AllowMatch = "any"
)
// normalizeAllowMatch maps unknown or empty values to the restrictive default
// (AllowMatchAll) so an unrecognized mode never loosens access.
func normalizeAllowMatch(m AllowMatch) AllowMatch {
if m == AllowMatchAny {
return AllowMatchAny
}
return AllowMatchAll
}
// AppSecMode is the per-service CrowdSec AppSec (WAF) enforcement mode.
type AppSecMode string
const (
// AppSecOff disables request inspection.
AppSecOff AppSecMode = ""
// AppSecEnforce blocks requests the engine flags, and fails closed when the
// engine is unreachable.
AppSecEnforce AppSecMode = "enforce"
// AppSecObserve records the verdict without blocking.
AppSecObserve AppSecMode = "observe"
)
// ParseAppSecMode maps a wire value to an AppSecMode. Unrecognized values map
// to AppSecOff so a typo never turns inspection into an unintended block.
func ParseAppSecMode(s string) AppSecMode {
switch AppSecMode(s) {
case AppSecEnforce:
return AppSecEnforce
case AppSecObserve:
return AppSecObserve
default:
return AppSecOff
}
}
// Enabled reports whether the mode asks for request inspection.
func (m AppSecMode) Enabled() bool {
return m == AppSecEnforce || m == AppSecObserve
}
// Filter evaluates IP restrictions. CIDR checks are performed first
// (cheap), followed by country lookups (more expensive) only when needed.
type Filter struct {
@@ -59,6 +112,9 @@ type Filter struct {
BlockedCountries []string
CrowdSec CrowdSecChecker
CrowdSecMode CrowdSecMode
// AllowMatch controls how the allowlists combine (AND vs OR). Empty means
// AllowMatchAll.
AllowMatch AllowMatch
}
// FilterConfig holds the raw configuration for building a Filter.
@@ -69,6 +125,7 @@ type FilterConfig struct {
BlockedCountries []string
CrowdSec CrowdSecChecker
CrowdSecMode CrowdSecMode
AllowMatch AllowMatch
Logger *log.Entry
}
@@ -89,6 +146,7 @@ func ParseFilter(cfg FilterConfig) *Filter {
f := &Filter{
AllowedCountries: normalizeCountryCodes(cfg.AllowedCountries),
BlockedCountries: normalizeCountryCodes(cfg.BlockedCountries),
AllowMatch: normalizeAllowMatch(cfg.AllowMatch),
}
if hasCS {
f.CrowdSec = cfg.CrowdSec
@@ -146,6 +204,13 @@ const (
// DenyCrowdSecUnavailable indicates enforce mode but the bouncer has not
// completed its initial sync.
DenyCrowdSecUnavailable
// DenyAppSecBan indicates a CrowdSec AppSec "ban" remediation.
DenyAppSecBan
// DenyAppSecCaptcha indicates a CrowdSec AppSec "captcha" remediation.
DenyAppSecCaptcha
// DenyAppSecUnavailable indicates enforce mode but the AppSec engine could
// not produce a verdict (unreachable, timed out, or it rejected the call).
DenyAppSecUnavailable
)
// String returns the deny reason string matching the HTTP auth mechanism names.
@@ -167,6 +232,12 @@ func (v Verdict) String() string {
return "crowdsec_throttle"
case DenyCrowdSecUnavailable:
return "crowdsec_unavailable"
case DenyAppSecBan:
return "appsec_ban"
case DenyAppSecCaptcha:
return "appsec_captcha"
case DenyAppSecUnavailable:
return "appsec_unavailable"
default:
return "unknown"
}
@@ -182,6 +253,16 @@ func (v Verdict) IsCrowdSec() bool {
}
}
// IsAppSec returns true when the verdict originates from an AppSec inspection.
func (v Verdict) IsAppSec() bool {
switch v {
case DenyAppSecBan, DenyAppSecCaptcha, DenyAppSecUnavailable:
return true
default:
return false
}
}
// IsObserveOnly returns true when v is a CrowdSec verdict and the filter is in
// observe mode. Callers should log the verdict but not block the request.
func (f *Filter) IsObserveOnly(v Verdict) bool {
@@ -216,6 +297,10 @@ func (f *Filter) Check(addr netip.Addr, geo GeoResolver) Verdict {
// IPv4 CIDR rules match regardless of how the address was received.
addr = addr.Unmap()
if f.AllowMatch == AllowMatchAny {
return f.checkAny(addr, geo)
}
if v := f.checkCIDR(addr); v != Allow {
return v
}
@@ -225,6 +310,68 @@ func (f *Filter) Check(addr netip.Addr, geo GeoResolver) Verdict {
return f.checkCrowdSec(addr)
}
// checkAny evaluates the filter with OR semantics across allowlists: the
// address is admitted if it matches any configured allowlist (CIDR or country).
// Blocklists remain a hard-deny gate evaluated first and are independent of the
// allow-combine mode, so a blocklist match (or unverifiable country block) still
// denies. CrowdSec runs last, as in the default path.
//
// The country is resolved at most once and shared by both the blocklist and the
// allowlist, matching what the all-mode path does. Splitting the two checks into
// separate helpers cost a second geo lookup per connection whenever both country
// lists were configured.
func (f *Filter) checkAny(addr netip.Addr, geo GeoResolver) Verdict {
for _, prefix := range f.BlockedCIDRs {
if prefix.Contains(addr) {
return DenyCIDR
}
}
cidrActive := len(f.AllowedCIDRs) > 0
cidrAllowed := false
if cidrActive {
for _, prefix := range f.AllowedCIDRs {
if prefix.Contains(addr) {
cidrAllowed = true
break
}
}
}
countryActive := len(f.AllowedCountries) > 0
// The blocklist is a hard gate, so it needs the country even when a CIDR
// allowlist already admitted the address. The allowlist needs it only when
// the CIDR list did not admit it, which is why a matching allowed CIDR
// still skips the lookup when no country blocklist is configured.
needCountry := len(f.BlockedCountries) > 0 || (countryActive && !cidrAllowed)
country := ""
if needCountry {
if geo == nil || !geo.Available() {
return DenyGeoUnavailable
}
country = geo.LookupAddr(addr).CountryCode
}
if country != "" && slices.Contains(f.BlockedCountries, country) {
return DenyCountry
}
allowed := (!cidrActive && !countryActive) ||
cidrAllowed ||
(countryActive && country != "" && slices.Contains(f.AllowedCountries, country))
if !allowed {
// Both allowlists missing is reported against the CIDR list, the one
// checked first, so the reason stays stable for existing access logs.
if cidrActive {
return DenyCIDR
}
return DenyCountry
}
return f.checkCrowdSec(addr)
}
func (f *Filter) checkCIDR(addr netip.Addr) Verdict {
if len(f.AllowedCIDRs) > 0 {
allowed := false

View File

@@ -5,6 +5,7 @@ import (
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/proxy/internal/geolocation"
)
@@ -150,6 +151,187 @@ func TestFilter_Check_CIDRAllowThenCountryBlock(t *testing.T) {
assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr("192.168.1.1"), geo), "CIDR denied before country check")
}
// TestFilter_Check_CrossCategoryAllowlistsAreAND documents the current
// behavior: when both a CIDR allowlist and a country allowlist are set, a
// request must satisfy BOTH to be allowed (AND across categories). There is no
// way today to express "allow if in allowed country OR in allowed CIDR", e.g.
// "allow all US traffic plus our office IP abroad". This is the gap an
// any/all allow-combine mode would close; the cases marked "GAP" are the ones
// that would flip to Allow under an "any" mode.
func TestFilter_Check_CrossCategoryAllowlistsAreAND(t *testing.T) {
officeAbroad := "203.0.113.7" // in allowed CIDR, but country not in allowlist
usOutsideOffice := "1.1.1.1" // allowed country, but not in allowed CIDR
usOffice := "203.0.113.8" // both
neither := "198.51.100.1" // neither
geo := newMockGeo(map[string]string{
officeAbroad: "DE",
usOutsideOffice: "US",
usOffice: "US",
neither: "CN",
})
f := ParseFilter(FilterConfig{
AllowedCIDRs: []string{"203.0.113.0/24"},
AllowedCountries: []string{"US"},
})
assert.Equal(t, Allow, f.Check(netip.MustParseAddr(usOffice), geo), "in allowed CIDR and allowed country")
assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr(officeAbroad), geo), "GAP: in allowed CIDR but country not allowed; any-mode should Allow")
assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr(usOutsideOffice), geo), "GAP: allowed country but not in allowed CIDR; any-mode should Allow")
assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr(neither), geo), "neither: denied under both modes")
}
// TestFilter_Check_CrossCategoryBlockAndAllow locks the current (all/AND)
// cross-category semantics that the evaluator must preserve: a blocklist match
// in any category denies regardless of allowlists, and blocklists across
// categories are effectively OR (a match in either denies).
func TestFilter_Check_CrossCategoryBlockAndAllow(t *testing.T) {
geo := newMockGeo(map[string]string{
"1.1.1.1": "US",
"10.1.2.3": "US",
"2.2.2.2": "CN",
"3.3.3.3": "US",
})
t.Run("country allowlist with CIDR blocklist", func(t *testing.T) {
f := ParseFilter(FilterConfig{
AllowedCountries: []string{"US"},
BlockedCIDRs: []string{"10.1.0.0/16"},
})
assert.Equal(t, Allow, f.Check(netip.MustParseAddr("1.1.1.1"), geo), "US and not in blocked CIDR")
assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr("10.1.2.3"), geo), "US but in blocked CIDR, block wins")
assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr("2.2.2.2"), geo), "not in allowed country")
})
t.Run("blocklists across categories are OR", func(t *testing.T) {
f := ParseFilter(FilterConfig{
BlockedCIDRs: []string{"10.1.0.0/16"},
BlockedCountries: []string{"CN"},
})
assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr("10.1.2.3"), geo), "in blocked CIDR")
assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr("2.2.2.2"), geo), "in blocked country")
assert.Equal(t, Allow, f.Check(netip.MustParseAddr("3.3.3.3"), geo), "in neither blocklist")
})
}
// TestFilter_Check_AllowCIDRPlusAllowCountryDeniesGeolessLAN documents a trap
// with all/AND mode: pairing an allowed CIDR (a private LAN) with an allowed
// country denies the LAN source, because a private IP has no country in the
// geo DB and an active country allowlist denies unknown countries. Under an
// "any" mode the CIDR match alone would admit it. This is the strongest reason
// allow-CIDR + allow-country usually wants OR, not AND.
func TestFilter_Check_AllowCIDRPlusAllowCountryDeniesGeolessLAN(t *testing.T) {
geo := newMockGeo(map[string]string{}) // no entries: every lookup is unknown country
f := ParseFilter(FilterConfig{
AllowedCIDRs: []string{"192.168.50.0/24"},
AllowedCountries: []string{"US"},
})
got := f.Check(netip.MustParseAddr("192.168.50.5"), geo)
assert.Equal(t, DenyCountry, got, "GAP: LAN source in allowed CIDR is denied by the country allowlist; any-mode should Allow")
}
func TestFilter_Check_AllowMatchAny(t *testing.T) {
bannedIP := "203.0.113.9"
geo := newMockGeo(map[string]string{
"1.1.1.1": "US", // allowed country, outside allowed CIDR
"203.0.113.7": "DE", // allowed CIDR, non-allowed country
"203.0.113.8": "US", // both
bannedIP: "US", // allowed CIDR, but CrowdSec-banned
"198.51.100.1": "CN", // neither
"2.2.2.2": "CN", // blocked country, but in allowed CIDR
})
tests := []struct {
name string
config FilterConfig
addr string
geo GeoResolver
want Verdict
}{
{
name: "in allowed CIDR only",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
addr: "203.0.113.7", geo: geo, want: Allow,
},
{
name: "in allowed country only",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
addr: "1.1.1.1", geo: geo, want: Allow,
},
{
name: "in both",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
addr: "203.0.113.8", geo: geo, want: Allow,
},
{
name: "in neither",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
addr: "198.51.100.1", geo: geo, want: DenyCIDR,
},
{
name: "geoless LAN admitted via CIDR (the #597 trap, fixed)",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"192.168.50.0/24"}, AllowedCountries: []string{"US"}},
addr: "192.168.50.5", geo: newMockGeo(map[string]string{}), want: Allow,
},
{
name: "CIDR match short-circuits geo when geo unavailable",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
addr: "203.0.113.7", geo: &unavailableGeo{}, want: Allow,
},
{
name: "geo unavailable fails closed when CIDR does not match",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
addr: "1.1.1.1", geo: &unavailableGeo{}, want: DenyGeoUnavailable,
},
{
name: "block gate wins over allowed CIDR (blocked country)",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"0.0.0.0/0"}, BlockedCountries: []string{"CN"}},
addr: "2.2.2.2", geo: geo, want: DenyCountry,
},
{
name: "block gate wins over allowed country (blocked CIDR)",
config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCountries: []string{"US"}, BlockedCIDRs: []string{"203.0.113.0/24"}},
addr: "203.0.113.8", geo: geo, want: DenyCIDR,
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
f := ParseFilter(tc.config)
assert.Equal(t, tc.want, f.Check(netip.MustParseAddr(tc.addr), tc.geo))
})
}
}
func TestFilter_Check_AllowMatchAny_CrowdSecStillRuns(t *testing.T) {
bannedIP := "203.0.113.9"
cs := &mockCrowdSec{decisions: map[string]*CrowdSecDecision{bannedIP: {Type: DecisionBan}}, ready: true}
geo := newMockGeo(map[string]string{bannedIP: "US", "203.0.113.7": "US"})
f := ParseFilter(FilterConfig{
AllowMatch: AllowMatchAny,
AllowedCIDRs: []string{"203.0.113.0/24"},
CrowdSec: cs,
CrowdSecMode: CrowdSecEnforce,
})
assert.Equal(t, DenyCrowdSecBan, f.Check(netip.MustParseAddr(bannedIP), geo), "CrowdSec ban denies even when allowlist admits")
assert.Equal(t, Allow, f.Check(netip.MustParseAddr("203.0.113.7"), geo), "clean IP in allowed CIDR is allowed")
}
func TestFilter_Check_UnknownAllowMatchDefaultsToAll(t *testing.T) {
// An unrecognized allow-combine mode must fall back to the restrictive
// AND default, never loosen access.
geo := newMockGeo(map[string]string{"203.0.113.7": "DE"})
f := ParseFilter(FilterConfig{
AllowMatch: AllowMatch("bogus"),
AllowedCIDRs: []string{"203.0.113.0/24"},
AllowedCountries: []string{"US"},
})
assert.Equal(t, AllowMatchAll, f.AllowMatch, "unknown mode normalizes to all")
assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr("203.0.113.7"), geo), "AND semantics: in CIDR but wrong country denied")
}
func TestParseFilter_Empty(t *testing.T) {
f := ParseFilter(FilterConfig{})
assert.Nil(t, f)
@@ -552,3 +734,81 @@ func TestFilter_HasRestrictions_CrowdSec(t *testing.T) {
f2 := ParseFilter(FilterConfig{CrowdSec: nil, CrowdSecMode: CrowdSecEnforce})
assert.True(t, f2.HasRestrictions())
}
// countingGeo records how many times an address was resolved.
type countingGeo struct {
countries map[string]string
lookups int
}
func (c *countingGeo) LookupAddr(addr netip.Addr) geolocation.Result {
c.lookups++
return geolocation.Result{CountryCode: c.countries[addr.String()]}
}
func (c *countingGeo) Available() bool { return true }
// The geo lookup is the expensive part of the check and runs per connection, so
// "any" mode must resolve the country once and share it between the blocklist
// and the allowlist, the way "all" mode does.
func TestCheck_AnyResolvesCountryOnce(t *testing.T) {
tests := []struct {
name string
ip string
want Verdict
wantLookups int
}{
{"blocked and allowed lists both active", "203.0.113.1", Allow, 1},
{"blocked country denies", "198.51.100.1", DenyCountry, 1},
{"neither allowlist matches", "192.0.2.1", DenyCIDR, 1},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
geo := &countingGeo{countries: map[string]string{
"203.0.113.1": "US",
"198.51.100.1": "CN",
"192.0.2.1": "FR",
}}
f := ParseFilter(FilterConfig{
AllowedCIDRs: []string{"10.0.0.0/8"},
AllowedCountries: []string{"US"},
BlockedCountries: []string{"CN"},
AllowMatch: AllowMatchAny,
})
require.NotNil(t, f)
assert.Equal(t, tt.want, f.Check(netip.MustParseAddr(tt.ip), geo))
assert.Equal(t, tt.wantLookups, geo.lookups, "the country must be resolved at most once per check")
})
}
}
// A matching allowed CIDR short-circuits the allowlist, so with no country
// blocklist configured there is nothing left to resolve.
func TestCheck_AnySkipsLookupWhenCIDRAdmits(t *testing.T) {
geo := &countingGeo{countries: map[string]string{"10.1.2.3": "US"}}
f := ParseFilter(FilterConfig{
AllowedCIDRs: []string{"10.0.0.0/8"},
AllowedCountries: []string{"DE"},
AllowMatch: AllowMatchAny,
})
require.NotNil(t, f)
assert.Equal(t, Allow, f.Check(netip.MustParseAddr("10.1.2.3"), geo))
assert.Zero(t, geo.lookups, "an admitted CIDR needs no geo lookup")
}
// The blocklist is a hard gate, so it is consulted even when a CIDR allowlist
// already admitted the address.
func TestCheck_AnyBlocklistOutranksAllowedCIDR(t *testing.T) {
geo := &countingGeo{countries: map[string]string{"10.1.2.3": "CN"}}
f := ParseFilter(FilterConfig{
AllowedCIDRs: []string{"10.0.0.0/8"},
BlockedCountries: []string{"CN"},
AllowMatch: AllowMatchAny,
})
require.NotNil(t, f)
assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr("10.1.2.3"), geo))
assert.Equal(t, 1, geo.lookups)
}

View File

@@ -126,6 +126,23 @@ type Config struct {
// CrowdSecAPIKey is the CrowdSec bouncer API key. Empty disables
// CrowdSec.
CrowdSecAPIKey string
// CrowdSecAppSecURL is the CrowdSec AppSec (WAF) endpoint. Empty disables
// HTTP request inspection.
CrowdSecAppSecURL string
// CrowdSecAppSecTimeout bounds a single AppSec inspection call. Zero falls
// back to the internal default.
CrowdSecAppSecTimeout time.Duration
// CrowdSecAppSecMaxBodyBytes caps the request body mirrored to AppSec.
// Zero falls back to the internal default; negative forwards no body.
CrowdSecAppSecMaxBodyBytes int64
// CrowdSecAppSecMaxConcurrent bounds AppSec inspections in flight toward
// the engine. Zero falls back to the internal default; negative removes
// the bound.
CrowdSecAppSecMaxConcurrent int
// MiddlewareCaptureBudgetBytes bounds the total request-body buffering in
// flight across the proxy, shared by AppSec inspection and the
// agent-network capture. Zero falls back to the internal default.
MiddlewareCaptureBudgetBytes int64
}
// New builds a Server from cfg without performing any I/O. No goroutines
@@ -135,42 +152,47 @@ type Config struct {
// directly) byte-for-byte equivalent.
func New(ctx context.Context, cfg Config) *Server {
return &Server{
ctx: ctx,
ListenAddr: cfg.ListenAddr,
ID: cfg.ID,
Logger: cfg.Logger,
Version: cfg.Version,
ProxyURL: cfg.ProxyURL,
ManagementAddress: cfg.ManagementAddress,
ProxyToken: cfg.ProxyToken,
CertificateDirectory: cfg.CertificateDirectory,
CertificateFile: cfg.CertificateFile,
CertificateKeyFile: cfg.CertificateKeyFile,
GenerateACMECertificates: cfg.GenerateACMECertificates,
ACMEChallengeAddress: cfg.ACMEChallengeAddress,
ACMEDirectory: cfg.ACMEDirectory,
ACMEEABKID: cfg.ACMEEABKID,
ACMEEABHMACKey: cfg.ACMEEABHMACKey,
ACMEChallengeType: cfg.ACMEChallengeType,
CertLockMethod: cfg.CertLockMethod,
WildcardCertDir: cfg.WildcardCertDir,
DebugEndpointEnabled: cfg.DebugEndpointEnabled,
DebugEndpointAddress: cfg.DebugEndpointAddress,
HealthAddress: cfg.HealthAddr,
ForwardedProto: cfg.ForwardedProto,
TrustedProxies: cfg.TrustedProxies,
WireguardPort: cfg.WireguardPort,
ProxyProtocol: cfg.ProxyProtocol,
PreSharedKey: cfg.PreSharedKey,
Performance: cfg.Performance,
SupportsCustomPorts: cfg.SupportsCustomPorts,
RequireSubdomain: cfg.RequireSubdomain,
Private: cfg.Private,
MaxDialTimeout: cfg.MaxDialTimeout,
MaxSessionIdleTimeout: cfg.MaxSessionIdleTimeout,
MappingBatchWatchdog: cfg.MappingBatchWatchdog,
GeoDataDir: cfg.GeoDataDir,
CrowdSecAPIURL: cfg.CrowdSecAPIURL,
CrowdSecAPIKey: cfg.CrowdSecAPIKey,
ctx: ctx,
ListenAddr: cfg.ListenAddr,
ID: cfg.ID,
Logger: cfg.Logger,
Version: cfg.Version,
ProxyURL: cfg.ProxyURL,
ManagementAddress: cfg.ManagementAddress,
ProxyToken: cfg.ProxyToken,
CertificateDirectory: cfg.CertificateDirectory,
CertificateFile: cfg.CertificateFile,
CertificateKeyFile: cfg.CertificateKeyFile,
GenerateACMECertificates: cfg.GenerateACMECertificates,
ACMEChallengeAddress: cfg.ACMEChallengeAddress,
ACMEDirectory: cfg.ACMEDirectory,
ACMEEABKID: cfg.ACMEEABKID,
ACMEEABHMACKey: cfg.ACMEEABHMACKey,
ACMEChallengeType: cfg.ACMEChallengeType,
CertLockMethod: cfg.CertLockMethod,
WildcardCertDir: cfg.WildcardCertDir,
DebugEndpointEnabled: cfg.DebugEndpointEnabled,
DebugEndpointAddress: cfg.DebugEndpointAddress,
HealthAddress: cfg.HealthAddr,
ForwardedProto: cfg.ForwardedProto,
TrustedProxies: cfg.TrustedProxies,
WireguardPort: cfg.WireguardPort,
ProxyProtocol: cfg.ProxyProtocol,
PreSharedKey: cfg.PreSharedKey,
Performance: cfg.Performance,
SupportsCustomPorts: cfg.SupportsCustomPorts,
RequireSubdomain: cfg.RequireSubdomain,
Private: cfg.Private,
MaxDialTimeout: cfg.MaxDialTimeout,
MaxSessionIdleTimeout: cfg.MaxSessionIdleTimeout,
MappingBatchWatchdog: cfg.MappingBatchWatchdog,
GeoDataDir: cfg.GeoDataDir,
CrowdSecAPIURL: cfg.CrowdSecAPIURL,
CrowdSecAPIKey: cfg.CrowdSecAPIKey,
CrowdSecAppSecURL: cfg.CrowdSecAppSecURL,
CrowdSecAppSecTimeout: cfg.CrowdSecAppSecTimeout,
CrowdSecAppSecMaxBodyBytes: cfg.CrowdSecAppSecMaxBodyBytes,
CrowdSecAppSecMaxConcurrent: cfg.CrowdSecAppSecMaxConcurrent,
MiddlewareCaptureBudgetBytes: cfg.MiddlewareCaptureBudgetBytes,
}
}

45
proxy/lifecycle_test.go Normal file
View File

@@ -0,0 +1,45 @@
package proxy
import (
"context"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// New maps Config onto Server field by field, and a field left out of that
// literal still compiles: the knob is simply parsed and then dropped, so an
// operator setting it sees the default with no error anywhere. These assertions
// are the only thing standing between a new setting and that silent no-op.
func TestNew_ForwardsOperatorTuning(t *testing.T) {
cfg := Config{
ManagementAddress: "http://localhost:8080",
ProxyToken: "token",
CrowdSecAPIURL: "http://crowdsec:8080/",
CrowdSecAPIKey: "key",
CrowdSecAppSecURL: "http://crowdsec:7422/",
CrowdSecAppSecTimeout: 321 * time.Millisecond,
CrowdSecAppSecMaxBodyBytes: 4321,
CrowdSecAppSecMaxConcurrent: 17,
MiddlewareCaptureBudgetBytes: 5 << 20,
MaxDialTimeout: 7 * time.Second,
MaxSessionIdleTimeout: 11 * time.Second,
GeoDataDir: "/var/lib/geo",
}
srv := New(context.Background(), cfg)
require.NotNil(t, srv)
assert.Equal(t, cfg.CrowdSecAPIURL, srv.CrowdSecAPIURL)
assert.Equal(t, cfg.CrowdSecAPIKey, srv.CrowdSecAPIKey)
assert.Equal(t, cfg.CrowdSecAppSecURL, srv.CrowdSecAppSecURL)
assert.Equal(t, cfg.CrowdSecAppSecTimeout, srv.CrowdSecAppSecTimeout)
assert.Equal(t, cfg.CrowdSecAppSecMaxBodyBytes, srv.CrowdSecAppSecMaxBodyBytes)
assert.Equal(t, cfg.CrowdSecAppSecMaxConcurrent, srv.CrowdSecAppSecMaxConcurrent)
assert.Equal(t, cfg.MiddlewareCaptureBudgetBytes, srv.MiddlewareCaptureBudgetBytes)
assert.Equal(t, cfg.MaxDialTimeout, srv.MaxDialTimeout)
assert.Equal(t, cfg.MaxSessionIdleTimeout, srv.MaxSessionIdleTimeout)
assert.Equal(t, cfg.GeoDataDir, srv.GeoDataDir)
}

View File

@@ -240,6 +240,10 @@ func (m *testProxyManager) ClusterSupportsCrowdSec(_ context.Context, _ string)
return nil
}
func (m *testProxyManager) ClusterSupportsAppSec(_ context.Context, _ string) *bool {
return nil
}
func (m *testProxyManager) ClusterSupportsPrivate(_ context.Context, _ string) *bool {
return nil
}
@@ -562,16 +566,11 @@ func TestIntegration_ProxyConnection_ReconnectDoesNotDuplicateState(t *testing.T
addMappingCalls.Add(1)
// Apply to real auth middleware (idempotent)
err := authMw.AddDomain(
mapping.GetDomain(),
nil,
"",
0,
proxytypes.AccountID(mapping.GetAccountId()),
proxytypes.ServiceID(mapping.GetId()),
nil,
mapping.GetPrivate(),
)
err := authMw.AddDomain(mapping.GetDomain(), auth.DomainSettings{
AccountID: proxytypes.AccountID(mapping.GetAccountId()),
ServiceID: proxytypes.ServiceID(mapping.GetId()),
Private: mapping.GetPrivate(),
})
require.NoError(t, err)
// Apply to real proxy (idempotent)

View File

@@ -45,6 +45,7 @@ import (
"github.com/netbirdio/netbird/client/embed"
"github.com/netbirdio/netbird/proxy/internal/accesslog"
"github.com/netbirdio/netbird/proxy/internal/acme"
"github.com/netbirdio/netbird/proxy/internal/appsec"
"github.com/netbirdio/netbird/proxy/internal/auth"
"github.com/netbirdio/netbird/proxy/internal/certwatch"
"github.com/netbirdio/netbird/proxy/internal/conntrack"
@@ -126,6 +127,10 @@ type Server struct {
crowdsecMu sync.Mutex
crowdsecServices map[types.ServiceID]bool
// appsecClient is the shared CrowdSec AppSec client, nil when no AppSec
// endpoint is configured. Stateless, so it needs no per-service lifecycle.
appsecClient *appsec.Client
// routerReady is closed once mainRouter is fully initialized.
// The mapping worker waits on this before processing updates.
routerReady chan struct{}
@@ -238,6 +243,20 @@ type Server struct {
CrowdSecAPIURL string
// CrowdSecAPIKey is the CrowdSec bouncer API key. Empty disables CrowdSec.
CrowdSecAPIKey string
// CrowdSecAppSecURL is the CrowdSec AppSec (WAF) endpoint, e.g.
// http://127.0.0.1:7422/. Empty disables request inspection. Requires
// CrowdSecAPIKey, which the AppSec component validates against LAPI.
CrowdSecAppSecURL string
// CrowdSecAppSecTimeout bounds a single AppSec inspection call.
// Zero means appsec.DefaultTimeout.
CrowdSecAppSecTimeout time.Duration
// CrowdSecAppSecMaxBodyBytes caps the request body mirrored to the AppSec
// engine. Zero means appsec.DefaultMaxBodyBytes; negative disables body
// forwarding, leaving header and URI inspection.
CrowdSecAppSecMaxBodyBytes int64
// CrowdSecAppSecMaxConcurrent bounds AppSec inspections in flight. Zero
// means appsec.DefaultMaxConcurrent; negative removes the bound.
CrowdSecAppSecMaxConcurrent int
// MaxSessionIdleTimeout caps the per-service session idle timeout.
// Zero means no cap (the proxy honors whatever management sends).
// Set via NB_PROXY_MAX_SESSION_IDLE_TIMEOUT for shared deployments.
@@ -380,6 +399,13 @@ func (s *Server) Start(ctx context.Context) error {
s.crowdsecRegistry = crowdsec.NewRegistry(s.CrowdSecAPIURL, s.CrowdSecAPIKey, log.NewEntry(s.Logger))
s.crowdsecServices = make(map[types.ServiceID]bool)
// Must precede the mapping worker: the worker opens the management stream
// and reports proxyCapabilities, which reads appsecClient. Building it
// afterwards would both race the read and, when the worker won, advertise
// the proxy as AppSec-incapable for the lifetime of that stream.
if err := s.initAppSec(); err != nil {
return err
}
go s.newManagementMappingWorker(runCtx, s.mgmtClient)
@@ -407,6 +433,7 @@ func (s *Server) Start(ctx context.Context) error {
}()
s.auth = auth.NewMiddleware(s.Logger, s.mgmtClient, s.geo)
s.auth.SetAppSec(s.appsecClient)
s.accessLog = accesslog.NewLogger(s.mgmtClient, s.Logger, s.TrustedProxies)
s.startDebugEndpoint()
@@ -1270,6 +1297,7 @@ func (s *Server) newManagementMappingWorker(ctx context.Context, client proto.Pr
func (s *Server) proxyCapabilities() *proto.ProxyCapabilities {
supportsCrowdSec := s.crowdsecRegistry.Available()
supportsAppSec := s.appsecClient != nil
privateCapability := s.Private
// Always true: this build enforces ProxyMapping.private via the auth middleware.
supportsPrivateService := true
@@ -1277,6 +1305,7 @@ func (s *Server) proxyCapabilities() *proto.ProxyCapabilities {
SupportsCustomPorts: &s.SupportsCustomPorts,
RequireSubdomain: &s.RequireSubdomain,
SupportsCrowdsec: &supportsCrowdSec,
SupportsAppsec: &supportsAppSec,
Private: &privateCapability,
SupportsPrivateService: &supportsPrivateService,
}
@@ -1900,10 +1929,72 @@ func (s *Server) parseRestrictions(mapping *proto.ProxyMapping) *restrict.Filter
BlockedCountries: r.GetBlockedCountries(),
CrowdSec: checker,
CrowdSecMode: csMode,
AllowMatch: restrict.AllowMatch(r.GetAllowMatch()),
Logger: log.NewEntry(s.Logger),
})
}
// initAppSec builds the shared AppSec client when an endpoint is configured.
// A configured-but-invalid endpoint is a startup error rather than a silent
// downgrade: services asking for enforce would otherwise fail closed on every
// request with no indication why.
//
// Runs before the management stream opens so the reported capability is stable;
// the auth middleware picks the client up separately once it exists.
func (s *Server) initAppSec() error {
if s.CrowdSecAppSecURL == "" {
return nil
}
if s.CrowdSecAPIKey == "" {
return errors.New("crowdsec appsec url is set but the crowdsec api key is empty")
}
// Share the middleware capture budget rather than opening a second pool:
// AppSec buffers before authentication, so its ceiling has to count against
// the same proxy-wide allowance the body tap draws from.
var budget appsec.Budget
if s.middlewareManager != nil {
budget = s.middlewareManager.Budget()
}
client, err := appsec.New(appsec.Config{
URL: s.CrowdSecAppSecURL,
APIKey: s.CrowdSecAPIKey,
Timeout: s.CrowdSecAppSecTimeout,
MaxBodyBytes: s.CrowdSecAppSecMaxBodyBytes,
MaxConcurrent: s.CrowdSecAppSecMaxConcurrent,
Budget: budget,
Logger: log.NewEntry(s.Logger),
})
if err != nil {
return fmt.Errorf("init crowdsec appsec: %w", err)
}
s.appsecClient = client
s.Logger.Infof("CrowdSec AppSec inspection available at %s", s.CrowdSecAppSecURL)
return nil
}
// appSecMode resolves the per-service AppSec mode. A service asking for
// inspection on a proxy with no AppSec endpoint keeps its mode so the auth
// middleware fails closed for enforce, mirroring the CrowdSec behavior.
func (s *Server) appSecMode(mapping *proto.ProxyMapping) restrict.AppSecMode {
raw := mapping.GetAccessRestrictions().GetAppsecMode()
mode := restrict.ParseAppSecMode(raw)
// An unrecognized value disables inspection, which is the safe default but a
// silent one: with a newer management and an older proxy, a mode this build
// does not know would look identical to "off" on a service the operator set
// to enforce. Say so rather than leaving it to be discovered.
if mode == restrict.AppSecOff && raw != "" && raw != "off" {
s.Logger.Warnf("service %s requests unrecognized AppSec mode %q; this build supports %q and %q, so inspection is disabled",
mapping.GetId(), raw, restrict.AppSecEnforce, restrict.AppSecObserve)
}
if mode.Enabled() && s.appsecClient == nil {
s.Logger.Warnf("service %s requests AppSec mode %q but proxy has no AppSec endpoint configured", mapping.GetId(), mode)
}
return mode
}
// releaseCrowdSec releases the CrowdSec bouncer reference for the given
// service if it had one.
func (s *Server) releaseCrowdSec(svcID types.ServiceID) {
@@ -2070,7 +2161,17 @@ func (s *Server) updateMapping(ctx context.Context, mapping *proto.ProxyMapping)
s.warnIfGeoUnavailable(mapping.GetDomain(), mapping.GetAccessRestrictions())
maxSessionAge := time.Duration(mapping.GetAuth().GetMaxSessionAgeSeconds()) * time.Second
if err := s.auth.AddDomain(mapping.GetDomain(), schemes, mapping.GetAuth().GetSessionKey(), maxSessionAge, accountID, svcID, ipRestrictions, mapping.GetPrivate()); err != nil {
settings := auth.DomainSettings{
Schemes: schemes,
SessionPublicKey: mapping.GetAuth().GetSessionKey(),
SessionExpiration: maxSessionAge,
AccountID: accountID,
ServiceID: svcID,
IPRestrictions: ipRestrictions,
Private: mapping.GetPrivate(),
AppSecMode: s.appSecMode(mapping),
}
if err := s.auth.AddDomain(mapping.GetDomain(), settings); err != nil {
return fmt.Errorf("auth setup for domain %s: %w", mapping.GetDomain(), err)
}
m := s.protoToMapping(ctx, mapping)

View File

@@ -21,7 +21,8 @@ import (
"google.golang.org/grpc/connectivity"
nbgrpc "github.com/netbirdio/netbird/client/grpc"
"github.com/netbirdio/netbird/client/netevents"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/encryption"
"github.com/netbirdio/netbird/shared/management/domain"
@@ -63,9 +64,12 @@ type GrpcClient struct {
connStateCallbackLock sync.RWMutex
serverURL string
// netEvents gates the stream retry loop on OS-reported network
// availability and sweeps the transport on network change.
netEvents *netevents.Manager
// netState gates the stream retry loop on OS-reported network
// availability; nil (the default) disables gating.
netState *netstate.State
// sweeper cuts the transport connections on network change; nil disables it.
sweeper *netsweep.Sweeper
// syncStreamErr holds the last Sync stream error, or nil while the stream
// is established and healthy. GetServerKey succeeds even when the peer
@@ -119,9 +123,15 @@ func MaxRecvMsgSize() int {
// Option configures optional GrpcClient behavior.
type Option func(*GrpcClient)
// WithNetEvents injects the OS network event handling.
func WithNetEvents(events *netevents.Manager) Option {
return func(c *GrpcClient) { c.netEvents = events }
// WithNetworkState injects the OS network availability state that gates the
// stream retry loop; without it gating is disabled.
func WithNetworkState(netState *netstate.State) Option {
return func(c *GrpcClient) { c.netState = netState }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) Option {
return func(c *GrpcClient) { c.sweeper = sweeper }
}
// NewClient creates a new client to Management service
@@ -142,7 +152,9 @@ func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsE
extraOpts = append(extraOpts, grpc.WithDefaultCallOptions(grpc.MaxCallRecvMsgSize(maxSize)))
log.Infof("management gRPC max receive message size set to %d bytes", maxSize)
}
extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.netEvents))
if c.sweeper != nil {
extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
}
var conn *grpc.ClientConn
operation := func() error {
@@ -223,19 +235,16 @@ func (c *GrpcClient) withMgmtStream(
ctx context.Context,
handler func(ctx context.Context, serverPubKey wgtypes.Key, backOff backoff.BackOff) error,
) error {
backOff := c.netEvents.QuickRetryBackoff(ctx, defaultBackoff(ctx))
backOff := c.sweeper.QuickRetryBackoff(ctx, defaultBackoff(ctx), c.netState)
operation := func() error {
// suspend reconnect attempts while the OS reports no usable network.
// Wait only errors on a cancelled context, which means shutdown, so
// stop the loop without reporting a failure.
if waited, err := c.netEvents.Wait(ctx); err != nil {
if waited, err := c.netState.Wait(ctx); err != nil {
log.Debugf("management connection context has been canceled while offline, this usually indicates shutdown")
return nil //nolint:nilerr // a cancelled context means shutdown, not a retryable failure
} else if waited {
backOff.Reset()
// dials attempted while offline grew the channel's internal backoff;
// reset it too, or the reconnect waits out that timer first
c.conn.ResetConnectBackoff()
}
connState := c.conn.GetState()
@@ -264,7 +273,7 @@ func (c *GrpcClient) withMgmtStream(
return handler(ctx, *serverPubKey, backOff)
}
err := nbgrpc.Retry(ctx, operation, backOff, c.netEvents)
err := nbgrpc.Retry(ctx, operation, backOff, c.netState)
if err != nil {
log.Warnf("exiting the Management service connection retry loop due to the unrecoverable error: %s", err)
}

View File

@@ -3380,6 +3380,30 @@ components:
- "observe"
default: "off"
description: CrowdSec IP reputation mode. Only available when the proxy cluster supports CrowdSec.
allow_match:
type: string
enum:
- "all"
- "any"
default: "all"
description: >-
How the allowlists (allowed_cidrs, allowed_countries) combine.
"all" (default) requires a connection to match every configured
allowlist (AND); "any" requires it to match at least one (OR), e.g.
an allowed country OR an allowed CIDR. Blocklists always reject on
match regardless of this setting.
appsec_mode:
type: string
enum:
- "off"
- "enforce"
- "observe"
default: "off"
description: >-
CrowdSec AppSec (WAF) request inspection mode. Only available when
the proxy cluster supports AppSec, and only applied to HTTP
services. "enforce" blocks requests the WAF flags; "observe" records
the verdict in the access log without blocking.
PasswordAuthConfig:
type: object
properties:
@@ -3516,6 +3540,10 @@ components:
type: boolean
description: Whether all active proxies in the cluster have CrowdSec configured
example: false
supports_appsec:
type: boolean
description: Whether all active proxies in the cluster have a CrowdSec AppSec (WAF) endpoint configured
example: false
private:
type: boolean
description: True when at least one connected proxy in this cluster is running embedded in a netbird client (`netbird proxy`) and serving over a WireGuard tunnel. Lets the dashboard distinguish per-peer / private clusters from centralised ones.
@@ -3575,6 +3603,10 @@ components:
type: boolean
description: Whether the proxy cluster has CrowdSec configured
example: false
supports_appsec:
type: boolean
description: Whether the proxy cluster has a CrowdSec AppSec (WAF) endpoint configured
example: false
supports_private:
type: boolean
description: Whether the proxy cluster supports private (NetBird-only) services. True when at least one connected proxy in the cluster runs embedded in a netbird client.

View File

@@ -17,6 +17,45 @@ const (
TokenAuthScopes tokenAuthContextKey = "TokenAuth.Scopes"
)
// Defines values for AccessRestrictionsAllowMatch.
const (
AccessRestrictionsAllowMatchAll AccessRestrictionsAllowMatch = "all"
AccessRestrictionsAllowMatchAny AccessRestrictionsAllowMatch = "any"
)
// Valid indicates whether the value is a known member of the AccessRestrictionsAllowMatch enum.
func (e AccessRestrictionsAllowMatch) Valid() bool {
switch e {
case AccessRestrictionsAllowMatchAll:
return true
case AccessRestrictionsAllowMatchAny:
return true
default:
return false
}
}
// Defines values for AccessRestrictionsAppsecMode.
const (
AccessRestrictionsAppsecModeEnforce AccessRestrictionsAppsecMode = "enforce"
AccessRestrictionsAppsecModeObserve AccessRestrictionsAppsecMode = "observe"
AccessRestrictionsAppsecModeOff AccessRestrictionsAppsecMode = "off"
)
// Valid indicates whether the value is a known member of the AccessRestrictionsAppsecMode enum.
func (e AccessRestrictionsAppsecMode) Valid() bool {
switch e {
case AccessRestrictionsAppsecModeEnforce:
return true
case AccessRestrictionsAppsecModeObserve:
return true
case AccessRestrictionsAppsecModeOff:
return true
default:
return false
}
}
// Defines values for AccessRestrictionsCrowdsecMode.
const (
AccessRestrictionsCrowdsecModeEnforce AccessRestrictionsCrowdsecMode = "enforce"
@@ -1534,12 +1573,18 @@ func (e PutApiIntegrationsMspTenantsIdInviteJSONBodyValue) Valid() bool {
// AccessRestrictions Connection-level access restrictions based on IP address or geography. Applies to both HTTP and L4 services.
type AccessRestrictions struct {
// AllowMatch How the allowlists (allowed_cidrs, allowed_countries) combine. "all" (default) requires a connection to match every configured allowlist (AND); "any" requires it to match at least one (OR), e.g. an allowed country OR an allowed CIDR. Blocklists always reject on match regardless of this setting.
AllowMatch *AccessRestrictionsAllowMatch `json:"allow_match,omitempty"`
// AllowedCidrs CIDR allowlist. If non-empty, only IPs matching these CIDRs are allowed.
AllowedCidrs *[]string `json:"allowed_cidrs,omitempty"`
// AllowedCountries ISO 3166-1 alpha-2 country codes to allow. If non-empty, only these countries are permitted.
AllowedCountries *[]string `json:"allowed_countries,omitempty"`
// AppsecMode CrowdSec AppSec (WAF) request inspection mode. Only available when the proxy cluster supports AppSec, and only applied to HTTP services. "enforce" blocks requests the WAF flags; "observe" records the verdict in the access log without blocking.
AppsecMode *AccessRestrictionsAppsecMode `json:"appsec_mode,omitempty"`
// BlockedCidrs CIDR blocklist. Connections from these CIDRs are rejected. Evaluated after allowed_cidrs.
BlockedCidrs *[]string `json:"blocked_cidrs,omitempty"`
@@ -1550,6 +1595,12 @@ type AccessRestrictions struct {
CrowdsecMode *AccessRestrictionsCrowdsecMode `json:"crowdsec_mode,omitempty"`
}
// AccessRestrictionsAllowMatch How the allowlists (allowed_cidrs, allowed_countries) combine. "all" (default) requires a connection to match every configured allowlist (AND); "any" requires it to match at least one (OR), e.g. an allowed country OR an allowed CIDR. Blocklists always reject on match regardless of this setting.
type AccessRestrictionsAllowMatch string
// AccessRestrictionsAppsecMode CrowdSec AppSec (WAF) request inspection mode. Only available when the proxy cluster supports AppSec, and only applied to HTTP services. "enforce" blocks requests the WAF flags; "observe" records the verdict in the access log without blocking.
type AccessRestrictionsAppsecMode string
// AccessRestrictionsCrowdsecMode CrowdSec IP reputation mode. Only available when the proxy cluster supports CrowdSec.
type AccessRestrictionsCrowdsecMode string
@@ -4773,6 +4824,9 @@ type ProxyCluster struct {
// RequireSubdomain Whether services on this cluster must include a subdomain label
RequireSubdomain *bool `json:"require_subdomain,omitempty"`
// SupportsAppsec Whether all active proxies in the cluster have a CrowdSec AppSec (WAF) endpoint configured
SupportsAppsec *bool `json:"supports_appsec,omitempty"`
// SupportsCrowdsec Whether all active proxies in the cluster have CrowdSec configured
SupportsCrowdsec *bool `json:"supports_crowdsec,omitempty"`
@@ -4841,6 +4895,9 @@ type ReverseProxyDomain struct {
// RequireSubdomain Whether a subdomain label is required in front of this domain. When true, the domain cannot be used bare.
RequireSubdomain *bool `json:"require_subdomain,omitempty"`
// SupportsAppsec Whether the proxy cluster has a CrowdSec AppSec (WAF) endpoint configured
SupportsAppsec *bool `json:"supports_appsec,omitempty"`
// SupportsCrowdsec Whether the proxy cluster has CrowdSec configured
SupportsCrowdsec *bool `json:"supports_crowdsec,omitempty"`

File diff suppressed because it is too large Load Diff

View File

@@ -73,6 +73,10 @@ message ProxyCapabilities {
optional bool private = 4;
// Whether the proxy enforces ProxyMapping.private (fails closed on ValidateTunnelPeer failure). Management MUST NOT stream private mappings to proxies that don't claim this.
optional bool supports_private_service = 5;
// Whether the proxy has a CrowdSec AppSec (WAF) endpoint configured and can
// inspect HTTP requests. Independent of supports_crowdsec: AppSec is a
// separate endpoint on the Security Engine and applies to HTTP services only.
optional bool supports_appsec = 6;
}
// GetMappingUpdateRequest is sent to initialise a mapping stream.
@@ -203,6 +207,14 @@ message AccessRestrictions {
repeated string blocked_countries = 4;
// CrowdSec IP reputation mode: "", "off", "enforce", or "observe".
string crowdsec_mode = 5;
// How the allowlists (CIDR, country) combine: "" or "all" require matching
// every allowlist (AND); "any" requires matching at least one (OR).
// Blocklists are always a hard-deny gate, independent of this mode.
string allow_match = 6;
// CrowdSec AppSec (WAF) request inspection mode: "", "off", "enforce", or
// "observe". HTTP services only: "enforce" and "observe" are rejected at
// validation for TCP/UDP/TLS services, which carry no requests to inspect.
string appsec_mode = 7;
}
message ProxyMapping {

View File

@@ -14,7 +14,7 @@ import (
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netevents/sweep"
"github.com/netbirdio/netbird/client/netsweep"
auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
"github.com/netbirdio/netbird/shared/relay/client/dialer"
netErr "github.com/netbirdio/netbird/shared/relay/client/dialer/net"
@@ -151,14 +151,6 @@ type transportConn interface {
Protocol() string
}
// NetEvents is the OS network event view the relay consumes: availability
// gating for the reconnect guard and dial registration for the network change
// sweep.
type NetEvents interface {
NetworkWatcher
StartDial(ctx context.Context) *sweep.Dial
}
// Client is a client for the relay server. It is responsible for establishing a connection to the relay server and
// managing connections to other peers. All exported functions are safe to call concurrently. After close the connection,
// the client can be reused by calling Connect again. When the client is closed, all connections are closed too.
@@ -194,10 +186,9 @@ type Client struct {
// the manager.
transportFallback *transportFallback
// netEvents registers the relay dial for the network change sweep; the
// read loop reports the disconnect and the guard reconnects. Shared via
// the manager.
netEvents NetEvents
// sweeper cuts the relay connection on network change; the read loop
// reports the disconnect and the guard reconnects. Shared via the manager.
sweeper *netsweep.Sweeper
// datagramFallbackTriggered guards a single fallback per connection so a
// burst of oversized datagrams triggers one reconnect, not many.
datagramFallbackTriggered atomic.Bool
@@ -409,12 +400,7 @@ func (c *Client) Close() error {
func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
// A sweep cancels this context, so a dial started on the old network
// aborts instead of waiting out its handshake timeout.
var dial *sweep.Dial
if c.netEvents != nil {
dial = c.netEvents.StartDial(ctx)
} else {
dial = (*sweep.Sweeper)(nil).StartDial(ctx)
}
dial := c.sweeper.StartDial(ctx)
defer dial.Release()
ctx = dial.Ctx()

View File

@@ -7,6 +7,8 @@ import (
"github.com/cenkalti/backoff/v4"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netstate"
)
const (
@@ -22,13 +24,6 @@ const (
verdictSettleWindow = 200 * time.Millisecond
)
// NetworkWatcher is the availability view the guard gates reconnects on.
type NetworkWatcher interface {
Wait(ctx context.Context) (bool, error)
IsOnline() bool
WaitSettled(ctx context.Context, budget, settleWindow time.Duration) bool
}
// Guard manage the reconnection tries to the Relay server in case of disconnection event.
type Guard struct {
// OnNewRelayClient is a channel that is used to notify the relay manager about a new relay client instance.
@@ -40,8 +35,9 @@ type Guard struct {
// attempts.
maxBackoffInterval time.Duration
// netState gates reconnect attempts on OS-reported network availability.
netState NetworkWatcher
// netState gates reconnect attempts on OS-reported network availability;
// nil disables gating.
netState *netstate.State
// lastErr is the error from the most recent failed reconnect attempt,
// surfaced as the home relay status while disconnected.
@@ -49,8 +45,9 @@ type Guard struct {
}
// NewGuard creates a new guard for the relay client. A non-positive
// maxBackoffInterval falls back to defaultMaxBackoffInterval.
func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState NetworkWatcher) *Guard {
// maxBackoffInterval falls back to defaultMaxBackoffInterval. A nil netState
// disables network availability gating.
func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState *netstate.State) *Guard {
if maxBackoffInterval <= 0 {
maxBackoffInterval = defaultMaxBackoffInterval
}
@@ -100,14 +97,12 @@ func (g *Guard) StartReconnectTrys(ctx context.Context, relayClient *Client) {
select {
case <-ticker.C:
// suspend reconnect attempts while the OS reports no usable network
if g.netState != nil {
if waited, err := g.netState.Wait(ctx); err != nil {
return
} else if waited {
ticker.Stop()
ticker = g.exponentTicker(ctx)
continue
}
if waited, err := g.netState.Wait(ctx); err != nil {
return
} else if waited {
ticker.Stop()
ticker = g.exponentTicker(ctx)
continue
}
if err := g.retry(ctx); err != nil {
log.Errorf("failed to pick new Relay server: %s", err)
@@ -134,18 +129,13 @@ func (g *Guard) tryToQuickReconnect(parentCtx context.Context, rc *Client) bool
return false
}
if g.netState != nil {
if ok := g.netState.WaitSettled(parentCtx, quickReconnectBudget, verdictSettleWindow); !ok {
return false
}
// Still offline after the budget: leave the retry to the ticker.
if !g.netState.IsOnline() {
return false
}
} else {
if cancelled := waiteBeforeRetry(parentCtx); !cancelled {
return false
}
if ok := g.waitForNetwork(parentCtx); !ok {
return false
}
// Still offline after the budget: leave the retry to the ticker.
if !g.netState.IsOnline() {
return false
}
log.Infof("try to reconnect to Relay server: %s", rc.connectionURL)
@@ -210,14 +200,47 @@ func (g *Guard) exponentTicker(ctx context.Context) *backoff.Ticker {
return backoff.NewTicker(bo)
}
func waiteBeforeRetry(ctx context.Context) bool {
timer := time.NewTimer(quickReconnectBudget)
defer timer.Stop()
// waitForNetwork waits out the settle window while online, or waits for the
// network to return while offline, within the budget. Returns false when ctx
// is cancelled. Without an injected netState it degrades to a fixed
// budget-long sleep, the pre-netstate behavior.
func (g *Guard) waitForNetwork(ctx context.Context) bool {
budget := time.NewTimer(quickReconnectBudget)
defer budget.Stop()
select {
case <-timer.C:
return true
case <-ctx.Done():
return false
settleWindow := verdictSettleWindow
if g.netState == nil {
settleWindow = quickReconnectBudget
}
settle := time.NewTimer(settleWindow)
defer settle.Stop()
for {
// Channel first, flag second: a flip in between still fires the channel.
changedCh := g.netState.Changed()
if g.netState.IsOnline() {
select {
case <-settle.C:
return true
case <-changedCh:
case <-ctx.Done():
return false
}
} else {
select {
case <-budget.C:
return true
case <-changedCh:
case <-ctx.Done():
return false
}
}
if !settle.Stop() {
select {
case <-settle.C:
default:
}
}
settle.Reset(settleWindow)
}
}

View File

@@ -0,0 +1,30 @@
package client
import (
"context"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/netbirdio/netbird/client/netstate"
)
func TestWaitForNetworkSettlesAfterOutage(t *testing.T) {
ns := netstate.New()
ns.Set(false)
g := NewGuard(nil, 0, ns)
const outage = 2 * verdictSettleWindow
start := time.Now()
go func() {
time.Sleep(outage)
ns.Set(true)
}()
ok := g.waitForNetwork(context.Background())
elapsed := time.Since(start)
assert.True(t, ok, "recovered network must let the quick reconnect proceed")
assert.GreaterOrEqual(t, elapsed, outage+verdictSettleWindow, "reconnect must wait a full settle window after the network returns")
}

View File

@@ -12,6 +12,8 @@ import (
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
relayAuth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
)
@@ -65,9 +67,15 @@ func WithMaxBackoffInterval(d time.Duration) ManagerOption {
return func(m *Manager) { m.maxBackoffInterval = d }
}
// WithNetEvents injects the OS network event handling.
func WithNetEvents(events NetEvents) ManagerOption {
return func(m *Manager) { m.netEvents = events }
// WithNetworkState injects the OS network availability state that gates the
// reconnect guard; without it reconnect attempts are not gated.
func WithNetworkState(netState *netstate.State) ManagerOption {
return func(m *Manager) { m.netState = netState }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) ManagerOption {
return func(m *Manager) { m.sweeper = sweeper }
}
// Manager is a manager for the relay client instances. It establishes one persistent connection to the given relay URL
@@ -97,7 +105,8 @@ type Manager struct {
mtu uint16
maxBackoffInterval time.Duration
netEvents NetEvents
netState *netstate.State
sweeper *netsweep.Sweeper
cleanupInterval time.Duration
keepUnusedServerTime time.Duration
@@ -134,9 +143,9 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
for _, opt := range opts {
opt(m)
}
m.serverPicker.NetEvents = m.netEvents
m.serverPicker.Sweeper = m.sweeper
m.serverPicker.ServerURLs.Store(serverURLs)
m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval, m.netEvents)
m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval, m.netState)
return m
}
@@ -361,7 +370,7 @@ func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string
relayClient := NewClientWithServerIP(serverAddress, serverIP, m.tokenStore, m.peerID, m.mtu)
relayClient.SetTransportFallback(m.transportFallback)
relayClient.netEvents = m.netEvents
relayClient.sweeper = m.sweeper
err := relayClient.Connect(m.ctx)
if err != nil {
rt.Lock()

View File

@@ -9,6 +9,7 @@ import (
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netsweep"
auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
)
@@ -30,7 +31,7 @@ type ServerPicker struct {
MTU uint16
ConnectionTimeout time.Duration
TransportFallback *transportFallback
NetEvents NetEvents
Sweeper *netsweep.Sweeper
}
func (sp *ServerPicker) PickServer(parentCtx context.Context) (*Client, error) {
@@ -74,7 +75,7 @@ func (sp *ServerPicker) startConnection(ctx context.Context, resultChan chan con
log.Infof("try to connecting to relay server: %s", url)
relayClient := NewClient(url, sp.TokenStore, sp.PeerID, sp.MTU)
relayClient.SetTransportFallback(sp.TransportFallback)
relayClient.netEvents = sp.NetEvents
relayClient.sweeper = sp.Sweeper
err := relayClient.Connect(ctx)
resultChan <- connResult{
RelayClient: relayClient,

View File

@@ -19,7 +19,8 @@ import (
"google.golang.org/grpc/status"
nbgrpc "github.com/netbirdio/netbird/client/grpc"
"github.com/netbirdio/netbird/client/netevents"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/encryption"
"github.com/netbirdio/netbird/shared/management/client"
"github.com/netbirdio/netbird/shared/signal/proto"
@@ -66,9 +67,12 @@ type GrpcClient struct {
connStateCallback ConnStateNotifier
connStateCallbackLock sync.RWMutex
// netEvents gates the Receive retry loop on OS-reported network
// availability and sweeps the transport on network change.
netEvents *netevents.Manager
// netState gates the Receive retry loop on OS-reported network
// availability; nil (the default) disables gating.
netState *netstate.State
// sweeper cuts the transport connections on network change; nil disables it.
sweeper *netsweep.Sweeper
onReconnectedListenerFn func()
@@ -96,9 +100,15 @@ type GrpcClient struct {
// Option configures optional GrpcClient behavior.
type Option func(*GrpcClient)
// WithNetEvents injects the OS network event handling.
func WithNetEvents(events *netevents.Manager) Option {
return func(c *GrpcClient) { c.netEvents = events }
// WithNetworkState injects the OS network availability state that gates the
// Receive retry loop; without it gating is disabled.
func WithNetworkState(netState *netstate.State) Option {
return func(c *GrpcClient) { c.netState = netState }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) Option {
return func(c *GrpcClient) { c.sweeper = sweeper }
}
// NewClient creates a new Signal client
@@ -116,7 +126,9 @@ func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled boo
}
var extraOpts []grpc.DialOption
extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.netEvents))
if c.sweeper != nil {
extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
}
var conn *grpc.ClientConn
operation := func() error {
@@ -186,20 +198,17 @@ func defaultBackoff(ctx context.Context) backoff.BackOff {
// The connection retry logic will try to reconnect for 30 min and if wasn't successful will propagate the error to the function caller.
func (c *GrpcClient) Receive(ctx context.Context, msgHandler func(msg *proto.Message) error) error {
backOff := c.netEvents.QuickRetryBackoff(ctx, defaultBackoff(ctx))
backOff := c.sweeper.QuickRetryBackoff(ctx, defaultBackoff(ctx), c.netState)
operation := func() error {
// suspend reconnect attempts while the OS reports no usable network.
// Wait only errors on a cancelled context, which means shutdown, so
// stop the loop without reporting a failure.
if waited, err := c.netEvents.Wait(ctx); err != nil {
if waited, err := c.netState.Wait(ctx); err != nil {
log.Debugf("signal connection context has been canceled while offline, this usually indicates shutdown")
return nil
} else if waited {
backOff.Reset()
// dials attempted while offline grew the channel's internal backoff;
// reset it too, or the reconnect waits out that timer first
c.signalConn.ResetConnectBackoff()
}
c.notifyStreamDisconnected()
@@ -272,7 +281,7 @@ func (c *GrpcClient) Receive(ctx context.Context, msgHandler func(msg *proto.Mes
return nil
}
err := nbgrpc.Retry(ctx, operation, backOff, c.netEvents)
err := nbgrpc.Retry(ctx, operation, backOff, c.netState)
if err != nil {
log.Errorf("exiting the Signal service connection retry loop due to the unrecoverable error: %v", err)
return err