Merge branch 'main' into feature/client-metrics

# Conflicts:
#	client/internal/debug/debug.go
#	client/internal/engine.go
#	client/server/debug.go

client/internal/auth/auth.go

@@ -0,0 +1,499 @@
+package auth
+
+import (
+	"context"
+	"net/url"
+	"sync"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+	"github.com/google/uuid"
+	log "github.com/sirupsen/logrus"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/status"
+
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	"github.com/netbirdio/netbird/client/ssh"
+	"github.com/netbirdio/netbird/client/system"
+	mgm "github.com/netbirdio/netbird/shared/management/client"
+	"github.com/netbirdio/netbird/shared/management/client/common"
+	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
+)
+
+// Auth manages authentication operations with the management server
+// It maintains a long-lived connection and automatically handles reconnection with backoff
+type Auth struct {
+	mutex         sync.RWMutex
+	client        *mgm.GrpcClient
+	config        *profilemanager.Config
+	privateKey    wgtypes.Key
+	mgmURL        *url.URL
+	mgmTLSEnabled bool
+}
+
+// NewAuth creates a new Auth instance that manages authentication flows
+// It establishes a connection to the management server that will be reused for all operations
+// The connection is automatically recreated with backoff if it becomes disconnected
+func NewAuth(ctx context.Context, privateKey string, mgmURL *url.URL, config *profilemanager.Config) (*Auth, error) {
+	// Validate WireGuard private key
+	myPrivateKey, err := wgtypes.ParseKey(privateKey)
+	if err != nil {
+		return nil, err
+	}
+
+	// Determine TLS setting based on URL scheme
+	mgmTLSEnabled := mgmURL.Scheme == "https"
+
+	log.Debugf("connecting to Management Service %s", mgmURL.String())
+	mgmClient, err := mgm.NewClient(ctx, mgmURL.Host, myPrivateKey, mgmTLSEnabled)
+	if err != nil {
+		log.Errorf("failed connecting to Management Service %s: %v", mgmURL.String(), err)
+		return nil, err
+	}
+
+	log.Debugf("connected to the Management service %s", mgmURL.String())
+
+	return &Auth{
+		client:        mgmClient,
+		config:        config,
+		privateKey:    myPrivateKey,
+		mgmURL:        mgmURL,
+		mgmTLSEnabled: mgmTLSEnabled,
+	}, nil
+}
+
+// Close closes the management client connection
+func (a *Auth) Close() error {
+	a.mutex.Lock()
+	defer a.mutex.Unlock()
+
+	if a.client == nil {
+		return nil
+	}
+	return a.client.Close()
+}
+
+// IsSSOSupported checks if the management server supports SSO by attempting to retrieve auth flow configurations.
+// Returns true if either PKCE or Device authorization flow is supported, false otherwise.
+// This function encapsulates the SSO detection logic to avoid exposing gRPC error codes to upper layers.
+// Automatically retries with backoff and reconnection on connection errors.
+func (a *Auth) IsSSOSupported(ctx context.Context) (bool, error) {
+	var supportsSSO bool
+
+	err := a.withRetry(ctx, func(client *mgm.GrpcClient) error {
+		// Try PKCE flow first
+		_, err := a.getPKCEFlow(client)
+		if err == nil {
+			supportsSSO = true
+			return nil
+		}
+
+		// Check if PKCE is not supported
+		if s, ok := status.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) {
+			// PKCE not supported, try Device flow
+			_, err = a.getDeviceFlow(client)
+			if err == nil {
+				supportsSSO = true
+				return nil
+			}
+
+			// Check if Device flow is also not supported
+			if s, ok := status.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) {
+				// Neither PKCE nor Device flow is supported
+				supportsSSO = false
+				return nil
+			}
+
+			// Device flow check returned an error other than NotFound/Unimplemented
+			return err
+		}
+
+		// PKCE flow check returned an error other than NotFound/Unimplemented
+		return err
+	})
+
+	return supportsSSO, err
+}
+
+// GetOAuthFlow returns an OAuth flow (PKCE or Device) using the existing management connection
+// This avoids creating a new connection to the management server
+func (a *Auth) GetOAuthFlow(ctx context.Context, forceDeviceAuth bool) (OAuthFlow, error) {
+	var flow OAuthFlow
+	var err error
+
+	err = a.withRetry(ctx, func(client *mgm.GrpcClient) error {
+		if forceDeviceAuth {
+			flow, err = a.getDeviceFlow(client)
+			return err
+		}
+
+		// Try PKCE flow first
+		flow, err = a.getPKCEFlow(client)
+		if err != nil {
+			// If PKCE not supported, try Device flow
+			if s, ok := status.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) {
+				flow, err = a.getDeviceFlow(client)
+				return err
+			}
+			return err
+		}
+		return nil
+	})
+
+	return flow, err
+}
+
+// IsLoginRequired checks if login is required by attempting to authenticate with the server
+// Automatically retries with backoff and reconnection on connection errors.
+func (a *Auth) IsLoginRequired(ctx context.Context) (bool, error) {
+	pubSSHKey, err := ssh.GeneratePublicKey([]byte(a.config.SSHKey))
+	if err != nil {
+		return false, err
+	}
+
+	var needsLogin bool
+
+	err = a.withRetry(ctx, func(client *mgm.GrpcClient) error {
+		_, _, err := a.doMgmLogin(client, ctx, pubSSHKey)
+		if isLoginNeeded(err) {
+			needsLogin = true
+			return nil
+		}
+		needsLogin = false
+		return err
+	})
+
+	return needsLogin, err
+}
+
+// Login attempts to log in or register the client with the management server
+// Returns error and a boolean indicating if it's an authentication error (permission denied) that should stop retries.
+// Automatically retries with backoff and reconnection on connection errors.
+func (a *Auth) Login(ctx context.Context, setupKey string, jwtToken string) (error, bool) {
+	pubSSHKey, err := ssh.GeneratePublicKey([]byte(a.config.SSHKey))
+	if err != nil {
+		return err, false
+	}
+
+	var isAuthError bool
+
+	err = a.withRetry(ctx, func(client *mgm.GrpcClient) error {
+		serverKey, _, err := a.doMgmLogin(client, ctx, pubSSHKey)
+		if serverKey != nil && isRegistrationNeeded(err) {
+			log.Debugf("peer registration required")
+			_, err = a.registerPeer(client, ctx, setupKey, jwtToken, pubSSHKey)
+			if err != nil {
+				isAuthError = isPermissionDenied(err)
+				return err
+			}
+		} else if err != nil {
+			isAuthError = isPermissionDenied(err)
+			return err
+		}
+
+		isAuthError = false
+		return nil
+	})
+
+	return err, isAuthError
+}
+
+// getPKCEFlow retrieves PKCE authorization flow configuration and creates a flow instance
+func (a *Auth) getPKCEFlow(client *mgm.GrpcClient) (*PKCEAuthorizationFlow, error) {
+	serverKey, err := client.GetServerPublicKey()
+	if err != nil {
+		log.Errorf("failed while getting Management Service public key: %v", err)
+		return nil, err
+	}
+
+	protoFlow, err := client.GetPKCEAuthorizationFlow(*serverKey)
+	if err != nil {
+		if s, ok := status.FromError(err); ok && s.Code() == codes.NotFound {
+			log.Warnf("server couldn't find pkce flow, contact admin: %v", err)
+			return nil, err
+		}
+		log.Errorf("failed to retrieve pkce flow: %v", err)
+		return nil, err
+	}
+
+	protoConfig := protoFlow.GetProviderConfig()
+	config := &PKCEAuthProviderConfig{
+		Audience:              protoConfig.GetAudience(),
+		ClientID:              protoConfig.GetClientID(),
+		ClientSecret:          protoConfig.GetClientSecret(),
+		TokenEndpoint:         protoConfig.GetTokenEndpoint(),
+		AuthorizationEndpoint: protoConfig.GetAuthorizationEndpoint(),
+		Scope:                 protoConfig.GetScope(),
+		RedirectURLs:          protoConfig.GetRedirectURLs(),
+		UseIDToken:            protoConfig.GetUseIDToken(),
+		ClientCertPair:        a.config.ClientCertKeyPair,
+		DisablePromptLogin:    protoConfig.GetDisablePromptLogin(),
+		LoginFlag:             common.LoginFlag(protoConfig.GetLoginFlag()),
+	}
+
+	if err := validatePKCEConfig(config); err != nil {
+		return nil, err
+	}
+
+	flow, err := NewPKCEAuthorizationFlow(*config)
+	if err != nil {
+		return nil, err
+	}
+
+	return flow, nil
+}
+
+// getDeviceFlow retrieves device authorization flow configuration and creates a flow instance
+func (a *Auth) getDeviceFlow(client *mgm.GrpcClient) (*DeviceAuthorizationFlow, error) {
+	serverKey, err := client.GetServerPublicKey()
+	if err != nil {
+		log.Errorf("failed while getting Management Service public key: %v", err)
+		return nil, err
+	}
+
+	protoFlow, err := client.GetDeviceAuthorizationFlow(*serverKey)
+	if err != nil {
+		if s, ok := status.FromError(err); ok && s.Code() == codes.NotFound {
+			log.Warnf("server couldn't find device flow, contact admin: %v", err)
+			return nil, err
+		}
+		log.Errorf("failed to retrieve device flow: %v", err)
+		return nil, err
+	}
+
+	protoConfig := protoFlow.GetProviderConfig()
+	config := &DeviceAuthProviderConfig{
+		Audience:           protoConfig.GetAudience(),
+		ClientID:           protoConfig.GetClientID(),
+		ClientSecret:       protoConfig.GetClientSecret(),
+		Domain:             protoConfig.Domain,
+		TokenEndpoint:      protoConfig.GetTokenEndpoint(),
+		DeviceAuthEndpoint: protoConfig.GetDeviceAuthEndpoint(),
+		Scope:              protoConfig.GetScope(),
+		UseIDToken:         protoConfig.GetUseIDToken(),
+	}
+
+	// Keep compatibility with older management versions
+	if config.Scope == "" {
+		config.Scope = "openid"
+	}
+
+	if err := validateDeviceAuthConfig(config); err != nil {
+		return nil, err
+	}
+
+	flow, err := NewDeviceAuthorizationFlow(*config)
+	if err != nil {
+		return nil, err
+	}
+
+	return flow, nil
+}
+
+// doMgmLogin performs the actual login operation with the management service
+func (a *Auth) doMgmLogin(client *mgm.GrpcClient, ctx context.Context, pubSSHKey []byte) (*wgtypes.Key, *mgmProto.LoginResponse, error) {
+	serverKey, err := client.GetServerPublicKey()
+	if err != nil {
+		log.Errorf("failed while getting Management Service public key: %v", err)
+		return nil, nil, err
+	}
+
+	sysInfo := system.GetInfo(ctx)
+	a.setSystemInfoFlags(sysInfo)
+	loginResp, err := client.Login(*serverKey, sysInfo, pubSSHKey, a.config.DNSLabels)
+	return serverKey, loginResp, err
+}
+
+// registerPeer checks whether setupKey was provided via cmd line and if not then it prompts user to enter a key.
+// Otherwise tries to register with the provided setupKey via command line.
+func (a *Auth) registerPeer(client *mgm.GrpcClient, ctx context.Context, setupKey string, jwtToken string, pubSSHKey []byte) (*mgmProto.LoginResponse, error) {
+	serverPublicKey, err := client.GetServerPublicKey()
+	if err != nil {
+		log.Errorf("failed while getting Management Service public key: %v", err)
+		return nil, err
+	}
+
+	validSetupKey, err := uuid.Parse(setupKey)
+	if err != nil && jwtToken == "" {
+		return nil, status.Errorf(codes.InvalidArgument, "invalid setup-key or no sso information provided, err: %v", err)
+	}
+
+	log.Debugf("sending peer registration request to Management Service")
+	info := system.GetInfo(ctx)
+	a.setSystemInfoFlags(info)
+	loginResp, err := client.Register(*serverPublicKey, validSetupKey.String(), jwtToken, info, pubSSHKey, a.config.DNSLabels)
+	if err != nil {
+		log.Errorf("failed registering peer %v", err)
+		return nil, err
+	}
+
+	log.Infof("peer has been successfully registered on Management Service")
+
+	return loginResp, nil
+}
+
+// setSystemInfoFlags sets all configuration flags on the provided system info
+func (a *Auth) setSystemInfoFlags(info *system.Info) {
+	info.SetFlags(
+		a.config.RosenpassEnabled,
+		a.config.RosenpassPermissive,
+		a.config.ServerSSHAllowed,
+		a.config.DisableClientRoutes,
+		a.config.DisableServerRoutes,
+		a.config.DisableDNS,
+		a.config.DisableFirewall,
+		a.config.BlockLANAccess,
+		a.config.BlockInbound,
+		a.config.LazyConnectionEnabled,
+		a.config.EnableSSHRoot,
+		a.config.EnableSSHSFTP,
+		a.config.EnableSSHLocalPortForwarding,
+		a.config.EnableSSHRemotePortForwarding,
+		a.config.DisableSSHAuth,
+	)
+}
+
+// reconnect closes the current connection and creates a new one
+// It checks if the brokenClient is still the current client before reconnecting
+// to avoid multiple threads reconnecting unnecessarily
+func (a *Auth) reconnect(ctx context.Context, brokenClient *mgm.GrpcClient) error {
+	a.mutex.Lock()
+	defer a.mutex.Unlock()
+
+	// Double-check: if client has already been replaced by another thread, skip reconnection
+	if a.client != brokenClient {
+		log.Debugf("client already reconnected by another thread, skipping")
+		return nil
+	}
+
+	// Create new connection FIRST, before closing the old one
+	// This ensures a.client is never nil, preventing panics in other threads
+	log.Debugf("reconnecting to Management Service %s", a.mgmURL.String())
+	mgmClient, err := mgm.NewClient(ctx, a.mgmURL.Host, a.privateKey, a.mgmTLSEnabled)
+	if err != nil {
+		log.Errorf("failed reconnecting to Management Service %s: %v", a.mgmURL.String(), err)
+		// Keep the old client if reconnection fails
+		return err
+	}
+
+	// Close old connection AFTER new one is successfully created
+	oldClient := a.client
+	a.client = mgmClient
+
+	if oldClient != nil {
+		if err := oldClient.Close(); err != nil {
+			log.Debugf("error closing old connection: %v", err)
+		}
+	}
+
+	log.Debugf("successfully reconnected to Management service %s", a.mgmURL.String())
+	return nil
+}
+
+// isConnectionError checks if the error is a connection-related error that should trigger reconnection
+func isConnectionError(err error) bool {
+	if err == nil {
+		return false
+	}
+	s, ok := status.FromError(err)
+	if !ok {
+		return false
+	}
+	// These error codes indicate connection issues
+	return s.Code() == codes.Unavailable ||
+		s.Code() == codes.DeadlineExceeded ||
+		s.Code() == codes.Canceled ||
+		s.Code() == codes.Internal
+}
+
+// withRetry wraps an operation with exponential backoff retry logic
+// It automatically reconnects on connection errors
+func (a *Auth) withRetry(ctx context.Context, operation func(client *mgm.GrpcClient) error) error {
+	backoffSettings := &backoff.ExponentialBackOff{
+		InitialInterval:     500 * time.Millisecond,
+		RandomizationFactor: 0.5,
+		Multiplier:          1.5,
+		MaxInterval:         10 * time.Second,
+		MaxElapsedTime:      2 * time.Minute,
+		Stop:                backoff.Stop,
+		Clock:               backoff.SystemClock,
+	}
+	backoffSettings.Reset()
+
+	return backoff.RetryNotify(
+		func() error {
+			// Capture the client BEFORE the operation to ensure we track the correct client
+			a.mutex.RLock()
+			currentClient := a.client
+			a.mutex.RUnlock()
+
+			if currentClient == nil {
+				return status.Errorf(codes.Unavailable, "client is not initialized")
+			}
+
+			// Execute operation with the captured client
+			err := operation(currentClient)
+			if err == nil {
+				return nil
+			}
+
+			// If it's a connection error, attempt reconnection using the client that was actually used
+			if isConnectionError(err) {
+				log.Warnf("connection error detected, attempting reconnection: %v", err)
+
+				if reconnectErr := a.reconnect(ctx, currentClient); reconnectErr != nil {
+					log.Errorf("reconnection failed: %v", reconnectErr)
+					return reconnectErr
+				}
+				// Return the original error to trigger retry with the new connection
+				return err
+			}
+
+			// For authentication errors, don't retry
+			if isAuthenticationError(err) {
+				return backoff.Permanent(err)
+			}
+
+			return err
+		},
+		backoff.WithContext(backoffSettings, ctx),
+		func(err error, duration time.Duration) {
+			log.Warnf("operation failed, retrying in %v: %v", duration, err)
+		},
+	)
+}
+
+// isAuthenticationError checks if the error is an authentication-related error that should not be retried.
+// Returns true if the error is InvalidArgument or PermissionDenied, indicating that retrying won't help.
+func isAuthenticationError(err error) bool {
+	if err == nil {
+		return false
+	}
+	s, ok := status.FromError(err)
+	if !ok {
+		return false
+	}
+	return s.Code() == codes.InvalidArgument || s.Code() == codes.PermissionDenied
+}
+
+// isPermissionDenied checks if the error is a PermissionDenied error.
+// This is used to determine if early exit from backoff is needed (e.g., when the server responded but denied access).
+func isPermissionDenied(err error) bool {
+	if err == nil {
+		return false
+	}
+	s, ok := status.FromError(err)
+	if !ok {
+		return false
+	}
+	return s.Code() == codes.PermissionDenied
+}
+
+func isLoginNeeded(err error) bool {
+	return isAuthenticationError(err)
+}
+
+func isRegistrationNeeded(err error) bool {
+	return isPermissionDenied(err)
+}

client/internal/auth/device_flow.go

@@ -15,7 +15,6 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
-	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/util/embeddedroots"
 )
 
@@ -26,12 +25,56 @@ const (
 
 var _ OAuthFlow = &DeviceAuthorizationFlow{}
 
+// DeviceAuthProviderConfig has all attributes needed to initiate a device authorization flow
+type DeviceAuthProviderConfig struct {
+	// ClientID An IDP application client id
+	ClientID string
+	// ClientSecret An IDP application client secret
+	ClientSecret string
+	// Domain An IDP API domain
+	// Deprecated. Use OIDCConfigEndpoint instead
+	Domain string
+	// Audience An Audience for to authorization validation
+	Audience string
+	// TokenEndpoint is the endpoint of an IDP manager where clients can obtain access token
+	TokenEndpoint string
+	// DeviceAuthEndpoint is the endpoint of an IDP manager where clients can obtain device authorization code
+	DeviceAuthEndpoint string
+	// Scopes provides the scopes to be included in the token request
+	Scope string
+	// UseIDToken indicates if the id token should be used for authentication
+	UseIDToken bool
+	// LoginHint is used to pre-fill the email/username field during authentication
+	LoginHint string
+}
+
+// validateDeviceAuthConfig validates device authorization provider configuration
+func validateDeviceAuthConfig(config *DeviceAuthProviderConfig) error {
+	errorMsgFormat := "invalid provider configuration received from management: %s value is empty. Contact your NetBird administrator"
+
+	if config.Audience == "" {
+		return fmt.Errorf(errorMsgFormat, "Audience")
+	}
+	if config.ClientID == "" {
+		return fmt.Errorf(errorMsgFormat, "Client ID")
+	}
+	if config.TokenEndpoint == "" {
+		return fmt.Errorf(errorMsgFormat, "Token Endpoint")
+	}
+	if config.DeviceAuthEndpoint == "" {
+		return fmt.Errorf(errorMsgFormat, "Device Auth Endpoint")
+	}
+	if config.Scope == "" {
+		return fmt.Errorf(errorMsgFormat, "Device Auth Scopes")
+	}
+	return nil
+}
+
 // DeviceAuthorizationFlow implements the OAuthFlow interface,
 // for the Device Authorization Flow.
 type DeviceAuthorizationFlow struct {
-	providerConfig internal.DeviceAuthProviderConfig
-
-	HTTPClient HTTPClient
+	providerConfig DeviceAuthProviderConfig
+	HTTPClient     HTTPClient
 }
 
 // RequestDeviceCodePayload used for request device code payload for auth0
@@ -57,7 +100,7 @@ type TokenRequestResponse struct {
 }
 
 // NewDeviceAuthorizationFlow returns device authorization flow client
-func NewDeviceAuthorizationFlow(config internal.DeviceAuthProviderConfig) (*DeviceAuthorizationFlow, error) {
+func NewDeviceAuthorizationFlow(config DeviceAuthProviderConfig) (*DeviceAuthorizationFlow, error) {
 	httpTransport := http.DefaultTransport.(*http.Transport).Clone()
 	httpTransport.MaxIdleConns = 5
 
@@ -89,6 +132,11 @@ func (d *DeviceAuthorizationFlow) GetClientID(ctx context.Context) string {
 	return d.providerConfig.ClientID
 }
 
+// SetLoginHint sets the login hint for the device authorization flow
+func (d *DeviceAuthorizationFlow) SetLoginHint(hint string) {
+	d.providerConfig.LoginHint = hint
+}
+
 // RequestAuthInfo requests a device code login flow information from Hosted
 func (d *DeviceAuthorizationFlow) RequestAuthInfo(ctx context.Context) (AuthFlowInfo, error) {
 	form := url.Values{}
@@ -199,14 +247,22 @@ func (d *DeviceAuthorizationFlow) requestToken(info AuthFlowInfo) (TokenRequestR
 }
 
 // WaitToken waits user's login and authorize the app. Once the user's authorize
-// it retrieves the access token from Hosted's endpoint and validates it before returning
+// it retrieves the access token from Hosted's endpoint and validates it before returning.
+// The method creates a timeout context internally based on info.ExpiresIn.
 func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo) (TokenInfo, error) {
+	// Create timeout context based on flow expiration
+	timeout := time.Duration(info.ExpiresIn) * time.Second
+	waitCtx, cancel := context.WithTimeout(ctx, timeout)
+	defer cancel()
+
 	interval := time.Duration(info.Interval) * time.Second
 	ticker := time.NewTicker(interval)
+	defer ticker.Stop()
+
 	for {
 		select {
-		case <-ctx.Done():
-			return TokenInfo{}, ctx.Err()
+		case <-waitCtx.Done():
+			return TokenInfo{}, waitCtx.Err()
 		case <-ticker.C:
 
 			tokenResponse, err := d.requestToken(info)

client/internal/auth/device_flow_test.go

@@ -12,8 +12,6 @@ import (
 
 	"github.com/golang-jwt/jwt/v5"
 	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal"
 )
 
 type mockHTTPClient struct {
@@ -115,18 +113,19 @@ func TestHosted_RequestDeviceCode(t *testing.T) {
 				err:     testCase.inputReqError,
 			}
 
-			deviceFlow := &DeviceAuthorizationFlow{
-				providerConfig: internal.DeviceAuthProviderConfig{
-					Audience:           expectedAudience,
-					ClientID:           expectedClientID,
-					Scope:              expectedScope,
-					TokenEndpoint:      "test.hosted.com/token",
-					DeviceAuthEndpoint: "test.hosted.com/device/auth",
-					UseIDToken:         false,
-				},
-				HTTPClient: &httpClient,
+			config := DeviceAuthProviderConfig{
+				Audience:           expectedAudience,
+				ClientID:           expectedClientID,
+				Scope:              expectedScope,
+				TokenEndpoint:      "test.hosted.com/token",
+				DeviceAuthEndpoint: "test.hosted.com/device/auth",
+				UseIDToken:         false,
 			}
 
+			deviceFlow, err := NewDeviceAuthorizationFlow(config)
+			require.NoError(t, err, "creating device flow should not fail")
+			deviceFlow.HTTPClient = &httpClient
+
 			authInfo, err := deviceFlow.RequestAuthInfo(context.TODO())
 			testCase.testingErrFunc(t, err, testCase.expectedErrorMSG)
 
@@ -280,18 +279,19 @@ func TestHosted_WaitToken(t *testing.T) {
 				countResBody: testCase.inputCountResBody,
 			}
 
-			deviceFlow := DeviceAuthorizationFlow{
-				providerConfig: internal.DeviceAuthProviderConfig{
-					Audience:           testCase.inputAudience,
-					ClientID:           clientID,
-					TokenEndpoint:      "test.hosted.com/token",
-					DeviceAuthEndpoint: "test.hosted.com/device/auth",
-					Scope:              "openid",
-					UseIDToken:         false,
-				},
-				HTTPClient: &httpClient,
+			config := DeviceAuthProviderConfig{
+				Audience:           testCase.inputAudience,
+				ClientID:           clientID,
+				TokenEndpoint:      "test.hosted.com/token",
+				DeviceAuthEndpoint: "test.hosted.com/device/auth",
+				Scope:              "openid",
+				UseIDToken:         false,
 			}
 
+			deviceFlow, err := NewDeviceAuthorizationFlow(config)
+			require.NoError(t, err, "creating device flow should not fail")
+			deviceFlow.HTTPClient = &httpClient
+
 			ctx, cancel := context.WithTimeout(context.TODO(), testCase.inputTimeout)
 			defer cancel()
 			tokenInfo, err := deviceFlow.WaitToken(ctx, testCase.inputInfo)

client/internal/auth/oauth.go

@@ -10,7 +10,6 @@ import (
 	"google.golang.org/grpc/codes"
 	gstatus "google.golang.org/grpc/status"
 
-	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 )
 
@@ -87,19 +86,33 @@ func NewOAuthFlow(ctx context.Context, config *profilemanager.Config, isUnixDesk
 
 // authenticateWithPKCEFlow initializes the Proof Key for Code Exchange flow auth flow
 func authenticateWithPKCEFlow(ctx context.Context, config *profilemanager.Config, hint string) (OAuthFlow, error) {
-	pkceFlowInfo, err := internal.GetPKCEAuthorizationFlowInfo(ctx, config.PrivateKey, config.ManagementURL, config.ClientCertKeyPair)
+	authClient, err := NewAuth(ctx, config.PrivateKey, config.ManagementURL, config)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create auth client: %v", err)
+	}
+	defer authClient.Close()
+
+	pkceFlowInfo, err := authClient.getPKCEFlow(authClient.client)
 	if err != nil {
 		return nil, fmt.Errorf("getting pkce authorization flow info failed with error: %v", err)
 	}
 
-	pkceFlowInfo.ProviderConfig.LoginHint = hint
+	if hint != "" {
+		pkceFlowInfo.SetLoginHint(hint)
+	}
 
-	return NewPKCEAuthorizationFlow(pkceFlowInfo.ProviderConfig)
+	return pkceFlowInfo, nil
 }
 
 // authenticateWithDeviceCodeFlow initializes the Device Code auth Flow
 func authenticateWithDeviceCodeFlow(ctx context.Context, config *profilemanager.Config, hint string) (OAuthFlow, error) {
-	deviceFlowInfo, err := internal.GetDeviceAuthorizationFlowInfo(ctx, config.PrivateKey, config.ManagementURL)
+	authClient, err := NewAuth(ctx, config.PrivateKey, config.ManagementURL, config)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create auth client: %v", err)
+	}
+	defer authClient.Close()
+
+	deviceFlowInfo, err := authClient.getDeviceFlow(authClient.client)
 	if err != nil {
 		switch s, ok := gstatus.FromError(err); {
 		case ok && s.Code() == codes.NotFound:
@@ -114,7 +127,9 @@ func authenticateWithDeviceCodeFlow(ctx context.Context, config *profilemanager.
 		}
 	}
 
-	deviceFlowInfo.ProviderConfig.LoginHint = hint
+	if hint != "" {
+		deviceFlowInfo.SetLoginHint(hint)
+	}
 
-	return NewDeviceAuthorizationFlow(deviceFlowInfo.ProviderConfig)
+	return deviceFlowInfo, nil
 }

client/internal/auth/pkce_flow.go

@@ -20,7 +20,6 @@ import (
 	log "github.com/sirupsen/logrus"
 	"golang.org/x/oauth2"
 
-	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/templates"
 	"github.com/netbirdio/netbird/shared/management/client/common"
 )
@@ -35,17 +34,67 @@ const (
 	defaultPKCETimeoutSeconds = 300
 )
 
+// PKCEAuthProviderConfig has all attributes needed to initiate PKCE authorization flow
+type PKCEAuthProviderConfig struct {
+	// ClientID An IDP application client id
+	ClientID string
+	// ClientSecret An IDP application client secret
+	ClientSecret string
+	// Audience An Audience for to authorization validation
+	Audience string
+	// TokenEndpoint is the endpoint of an IDP manager where clients can obtain access token
+	TokenEndpoint string
+	// AuthorizationEndpoint is the endpoint of an IDP manager where clients can obtain authorization code
+	AuthorizationEndpoint string
+	// Scopes provides the scopes to be included in the token request
+	Scope string
+	// RedirectURL handles authorization code from IDP manager
+	RedirectURLs []string
+	// UseIDToken indicates if the id token should be used for authentication
+	UseIDToken bool
+	// ClientCertPair is used for mTLS authentication to the IDP
+	ClientCertPair *tls.Certificate
+	// DisablePromptLogin makes the PKCE flow to not prompt the user for login
+	DisablePromptLogin bool
+	// LoginFlag is used to configure the PKCE flow login behavior
+	LoginFlag common.LoginFlag
+	// LoginHint is used to pre-fill the email/username field during authentication
+	LoginHint string
+}
+
+// validatePKCEConfig validates PKCE provider configuration
+func validatePKCEConfig(config *PKCEAuthProviderConfig) error {
+	errorMsgFormat := "invalid provider configuration received from management: %s value is empty. Contact your NetBird administrator"
+
+	if config.ClientID == "" {
+		return fmt.Errorf(errorMsgFormat, "Client ID")
+	}
+	if config.TokenEndpoint == "" {
+		return fmt.Errorf(errorMsgFormat, "Token Endpoint")
+	}
+	if config.AuthorizationEndpoint == "" {
+		return fmt.Errorf(errorMsgFormat, "Authorization Auth Endpoint")
+	}
+	if config.Scope == "" {
+		return fmt.Errorf(errorMsgFormat, "PKCE Auth Scopes")
+	}
+	if config.RedirectURLs == nil {
+		return fmt.Errorf(errorMsgFormat, "PKCE Redirect URLs")
+	}
+	return nil
+}
+
 // PKCEAuthorizationFlow implements the OAuthFlow interface for
 // the Authorization Code Flow with PKCE.
 type PKCEAuthorizationFlow struct {
-	providerConfig internal.PKCEAuthProviderConfig
+	providerConfig PKCEAuthProviderConfig
 	state          string
 	codeVerifier   string
 	oAuthConfig    *oauth2.Config
 }
 
 // NewPKCEAuthorizationFlow returns new PKCE authorization code flow.
-func NewPKCEAuthorizationFlow(config internal.PKCEAuthProviderConfig) (*PKCEAuthorizationFlow, error) {
+func NewPKCEAuthorizationFlow(config PKCEAuthProviderConfig) (*PKCEAuthorizationFlow, error) {
 	var availableRedirectURL string
 
 	excludedRanges := getSystemExcludedPortRanges()
@@ -124,10 +173,21 @@ func (p *PKCEAuthorizationFlow) RequestAuthInfo(ctx context.Context) (AuthFlowIn
 	}, nil
 }
 
+// SetLoginHint sets the login hint for the PKCE authorization flow
+func (p *PKCEAuthorizationFlow) SetLoginHint(hint string) {
+	p.providerConfig.LoginHint = hint
+}
+
 // WaitToken waits for the OAuth token in the PKCE Authorization Flow.
 // It starts an HTTP server to receive the OAuth token callback and waits for the token or an error.
 // Once the token is received, it is converted to TokenInfo and validated before returning.
-func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, _ AuthFlowInfo) (TokenInfo, error) {
+// The method creates a timeout context internally based on info.ExpiresIn.
+func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo) (TokenInfo, error) {
+	// Create timeout context based on flow expiration
+	timeout := time.Duration(info.ExpiresIn) * time.Second
+	waitCtx, cancel := context.WithTimeout(ctx, timeout)
+	defer cancel()
+
 	tokenChan := make(chan *oauth2.Token, 1)
 	errChan := make(chan error, 1)
 
@@ -138,7 +198,7 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, _ AuthFlowInfo) (
 
 	server := &http.Server{Addr: fmt.Sprintf(":%s", parsedURL.Port())}
 	defer func() {
-		shutdownCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
+		shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 		defer cancel()
 
 		if err := server.Shutdown(shutdownCtx); err != nil {
@@ -149,8 +209,8 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, _ AuthFlowInfo) (
 	go p.startServer(server, tokenChan, errChan)
 
 	select {
-	case <-ctx.Done():
-		return TokenInfo{}, ctx.Err()
+	case <-waitCtx.Done():
+		return TokenInfo{}, waitCtx.Err()
 	case token := <-tokenChan:
 		return p.parseOAuthToken(token)
 	case err := <-errChan:

client/internal/auth/pkce_flow_test.go

@@ -9,7 +9,6 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
-	"github.com/netbirdio/netbird/client/internal"
 	mgm "github.com/netbirdio/netbird/shared/management/client/common"
 )
 
@@ -50,7 +49,7 @@ func TestPromptLogin(t *testing.T) {
 
 	for _, tc := range tt {
 		t.Run(tc.name, func(t *testing.T) {
-			config := internal.PKCEAuthProviderConfig{
+			config := PKCEAuthProviderConfig{
 				ClientID:              "test-client-id",
 				Audience:              "test-audience",
 				TokenEndpoint:         "https://test-token-endpoint.com/token",

client/internal/auth/pkce_flow_windows_test.go

@@ -9,8 +9,6 @@ import (
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal"
 )
 
 func TestParseExcludedPortRanges(t *testing.T) {
@@ -95,7 +93,7 @@ func TestNewPKCEAuthorizationFlow_WithActualExcludedPorts(t *testing.T) {
 
 	availablePort := 65432
 
-	config := internal.PKCEAuthProviderConfig{
+	config := PKCEAuthProviderConfig{
 		ClientID:              "test-client-id",
 		Audience:              "test-audience",
 		TokenEndpoint:         "https://test-token-endpoint.com/token",

client/internal/debug/debug.go

@@ -59,6 +59,7 @@ block.prof: Block profiling information.
 heap.prof: Heap profiling information (snapshot of memory allocations).
 allocs.prof: Allocations profiling information.
 threadcreate.prof: Thread creation profiling information.
+cpu.prof: CPU profiling information.
 stack_trace.txt: Complete stack traces of all goroutines at the time of bundle creation.
 
 
@@ -231,6 +232,8 @@ type BundleGenerator struct {
 	statusRecorder *peer.Status
 	syncResponse   *mgmProto.SyncResponse
 	logPath        string
+	cpuProfile     []byte
+	refreshStatus  func() // Optional callback to refresh status before bundle generation
 	clientMetrics  MetricsExporter
 
 	anonymize         bool
@@ -251,6 +254,8 @@ type GeneratorDependencies struct {
 	StatusRecorder *peer.Status
 	SyncResponse   *mgmProto.SyncResponse
 	LogPath        string
+	CPUProfile     []byte
+	RefreshStatus  func() // Optional callback to refresh status before bundle generation
 	ClientMetrics  MetricsExporter
 }
 
@@ -268,6 +273,8 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
 		statusRecorder: deps.StatusRecorder,
 		syncResponse:   deps.SyncResponse,
 		logPath:        deps.LogPath,
+		cpuProfile:     deps.CPUProfile,
+		refreshStatus:  deps.RefreshStatus,
 		clientMetrics:  deps.ClientMetrics,
 
 		anonymize:         cfg.Anonymize,
@@ -332,6 +339,10 @@ func (g *BundleGenerator) createArchive() error {
 		log.Errorf("failed to add profiles to debug bundle: %v", err)
 	}
 
+	if err := g.addCPUProfile(); err != nil {
+		log.Errorf("failed to add CPU profile to debug bundle: %v", err)
+	}
+
 	if err := g.addStackTrace(); err != nil {
 		log.Errorf("failed to add stack trace to debug bundle: %v", err)
 	}
@@ -412,6 +423,10 @@ func (g *BundleGenerator) addStatus() error {
 			profName = activeProf.Name
 		}
 
+		if g.refreshStatus != nil {
+			g.refreshStatus()
+		}
+
 		fullStatus := g.statusRecorder.GetFullStatus()
 		protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
 		protoFullStatus.Events = g.statusRecorder.GetEventHistory()
@@ -554,6 +569,19 @@ func (g *BundleGenerator) addProf() (err error) {
 	return nil
 }
 
+func (g *BundleGenerator) addCPUProfile() error {
+	if len(g.cpuProfile) == 0 {
+		return nil
+	}
+
+	reader := bytes.NewReader(g.cpuProfile)
+	if err := g.addFileToZip(reader, "cpu.prof"); err != nil {
+		return fmt.Errorf("add CPU profile to zip: %w", err)
+	}
+
+	return nil
+}
+
 func (g *BundleGenerator) addStackTrace() error {
 	buf := make([]byte, 5242880) // 5 MB buffer
 	n := runtime.Stack(buf, true)

client/internal/device_auth.go

@@ -1,136 +0,0 @@
-package internal
-
-import (
-	"context"
-	"fmt"
-	"net/url"
-
-	log "github.com/sirupsen/logrus"
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-	"google.golang.org/grpc/codes"
-	"google.golang.org/grpc/status"
-
-	mgm "github.com/netbirdio/netbird/shared/management/client"
-)
-
-// DeviceAuthorizationFlow represents Device Authorization Flow information
-type DeviceAuthorizationFlow struct {
-	Provider       string
-	ProviderConfig DeviceAuthProviderConfig
-}
-
-// DeviceAuthProviderConfig has all attributes needed to initiate a device authorization flow
-type DeviceAuthProviderConfig struct {
-	// ClientID An IDP application client id
-	ClientID string
-	// ClientSecret An IDP application client secret
-	ClientSecret string
-	// Domain An IDP API domain
-	// Deprecated. Use OIDCConfigEndpoint instead
-	Domain string
-	// Audience An Audience for to authorization validation
-	Audience string
-	// TokenEndpoint is the endpoint of an IDP manager where clients can obtain access token
-	TokenEndpoint string
-	// DeviceAuthEndpoint is the endpoint of an IDP manager where clients can obtain device authorization code
-	DeviceAuthEndpoint string
-	// Scopes provides the scopes to be included in the token request
-	Scope string
-	// UseIDToken indicates if the id token should be used for authentication
-	UseIDToken bool
-	// LoginHint is used to pre-fill the email/username field during authentication
-	LoginHint string
-}
-
-// GetDeviceAuthorizationFlowInfo initialize a DeviceAuthorizationFlow instance and return with it
-func GetDeviceAuthorizationFlowInfo(ctx context.Context, privateKey string, mgmURL *url.URL) (DeviceAuthorizationFlow, error) {
-	// validate our peer's Wireguard PRIVATE key
-	myPrivateKey, err := wgtypes.ParseKey(privateKey)
-	if err != nil {
-		log.Errorf("failed parsing Wireguard key %s: [%s]", privateKey, err.Error())
-		return DeviceAuthorizationFlow{}, err
-	}
-
-	var mgmTLSEnabled bool
-	if mgmURL.Scheme == "https" {
-		mgmTLSEnabled = true
-	}
-
-	log.Debugf("connecting to Management Service %s", mgmURL.String())
-	mgmClient, err := mgm.NewClient(ctx, mgmURL.Host, myPrivateKey, mgmTLSEnabled)
-	if err != nil {
-		log.Errorf("failed connecting to Management Service %s %v", mgmURL.String(), err)
-		return DeviceAuthorizationFlow{}, err
-	}
-	log.Debugf("connected to the Management service %s", mgmURL.String())
-
-	defer func() {
-		err = mgmClient.Close()
-		if err != nil {
-			log.Warnf("failed to close the Management service client %v", err)
-		}
-	}()
-
-	serverKey, err := mgmClient.GetServerPublicKey()
-	if err != nil {
-		log.Errorf("failed while getting Management Service public key: %v", err)
-		return DeviceAuthorizationFlow{}, err
-	}
-
-	protoDeviceAuthorizationFlow, err := mgmClient.GetDeviceAuthorizationFlow(*serverKey)
-	if err != nil {
-		if s, ok := status.FromError(err); ok && s.Code() == codes.NotFound {
-			log.Warnf("server couldn't find device flow, contact admin: %v", err)
-			return DeviceAuthorizationFlow{}, err
-		}
-		log.Errorf("failed to retrieve device flow: %v", err)
-		return DeviceAuthorizationFlow{}, err
-	}
-
-	deviceAuthorizationFlow := DeviceAuthorizationFlow{
-		Provider: protoDeviceAuthorizationFlow.Provider.String(),
-
-		ProviderConfig: DeviceAuthProviderConfig{
-			Audience:           protoDeviceAuthorizationFlow.GetProviderConfig().GetAudience(),
-			ClientID:           protoDeviceAuthorizationFlow.GetProviderConfig().GetClientID(),
-			ClientSecret:       protoDeviceAuthorizationFlow.GetProviderConfig().GetClientSecret(),
-			Domain:             protoDeviceAuthorizationFlow.GetProviderConfig().Domain,
-			TokenEndpoint:      protoDeviceAuthorizationFlow.GetProviderConfig().GetTokenEndpoint(),
-			DeviceAuthEndpoint: protoDeviceAuthorizationFlow.GetProviderConfig().GetDeviceAuthEndpoint(),
-			Scope:              protoDeviceAuthorizationFlow.GetProviderConfig().GetScope(),
-			UseIDToken:         protoDeviceAuthorizationFlow.GetProviderConfig().GetUseIDToken(),
-		},
-	}
-
-	// keep compatibility with older management versions
-	if deviceAuthorizationFlow.ProviderConfig.Scope == "" {
-		deviceAuthorizationFlow.ProviderConfig.Scope = "openid"
-	}
-
-	err = isDeviceAuthProviderConfigValid(deviceAuthorizationFlow.ProviderConfig)
-	if err != nil {
-		return DeviceAuthorizationFlow{}, err
-	}
-
-	return deviceAuthorizationFlow, nil
-}
-
-func isDeviceAuthProviderConfigValid(config DeviceAuthProviderConfig) error {
-	errorMSGFormat := "invalid provider configuration received from management: %s value is empty. Contact your NetBird administrator"
-	if config.Audience == "" {
-		return fmt.Errorf(errorMSGFormat, "Audience")
-	}
-	if config.ClientID == "" {
-		return fmt.Errorf(errorMSGFormat, "Client ID")
-	}
-	if config.TokenEndpoint == "" {
-		return fmt.Errorf(errorMSGFormat, "Token Endpoint")
-	}
-	if config.DeviceAuthEndpoint == "" {
-		return fmt.Errorf(errorMSGFormat, "Device Auth Endpoint")
-	}
-	if config.Scope == "" {
-		return fmt.Errorf(errorMSGFormat, "Device Auth Scopes")
-	}
-	return nil
-}

client/internal/dns/local/local.go

@@ -81,7 +81,10 @@ func (d *Resolver) ProbeAvailability() {}
 
 // ServeDNS handles a DNS request
 func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
-	logger := log.WithField("request_id", resutil.GetRequestID(w))
+	logger := log.WithFields(log.Fields{
+		"request_id": resutil.GetRequestID(w),
+		"dns_id":     fmt.Sprintf("%04x", r.Id),
+	})
 
 	if len(r.Question) == 0 {
 		logger.Debug("received local resolver request with no question")

client/internal/dns/upstream.go

@@ -71,6 +71,11 @@ type upstreamResolverBase struct {
 	statusRecorder *peer.Status
 }
 
+type upstreamFailure struct {
+	upstream netip.AddrPort
+	reason   string
+}
+
 func newUpstreamResolverBase(ctx context.Context, statusRecorder *peer.Status, domain string) *upstreamResolverBase {
 	ctx, cancel := context.WithCancel(ctx)
 
@@ -114,7 +119,10 @@ func (u *upstreamResolverBase) Stop() {
 
 // ServeDNS handles a DNS request
 func (u *upstreamResolverBase) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
-	logger := log.WithField("request_id", resutil.GetRequestID(w))
+	logger := log.WithFields(log.Fields{
+		"request_id": resutil.GetRequestID(w),
+		"dns_id":     fmt.Sprintf("%04x", r.Id),
+	})
 
 	u.prepareRequest(r)
 
@@ -123,11 +131,13 @@ func (u *upstreamResolverBase) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 		return
 	}
 
-	if u.tryUpstreamServers(w, r, logger) {
-		return
+	ok, failures := u.tryUpstreamServers(w, r, logger)
+	if len(failures) > 0 {
+		u.logUpstreamFailures(r.Question[0].Name, failures, ok, logger)
+	}
+	if !ok {
+		u.writeErrorResponse(w, r, logger)
 	}
-
-	u.writeErrorResponse(w, r, logger)
 }
 
 func (u *upstreamResolverBase) prepareRequest(r *dns.Msg) {
@@ -136,7 +146,7 @@ func (u *upstreamResolverBase) prepareRequest(r *dns.Msg) {
 	}
 }
 
-func (u *upstreamResolverBase) tryUpstreamServers(w dns.ResponseWriter, r *dns.Msg, logger *log.Entry) bool {
+func (u *upstreamResolverBase) tryUpstreamServers(w dns.ResponseWriter, r *dns.Msg, logger *log.Entry) (bool, []upstreamFailure) {
 	timeout := u.upstreamTimeout
 	if len(u.upstreamServers) > 1 {
 		maxTotal := 5 * time.Second
@@ -149,15 +159,19 @@ func (u *upstreamResolverBase) tryUpstreamServers(w dns.ResponseWriter, r *dns.M
 		}
 	}
 
+	var failures []upstreamFailure
 	for _, upstream := range u.upstreamServers {
-		if u.queryUpstream(w, r, upstream, timeout, logger) {
-			return true
+		if failure := u.queryUpstream(w, r, upstream, timeout, logger); failure != nil {
+			failures = append(failures, *failure)
+		} else {
+			return true, failures
 		}
 	}
-	return false
+	return false, failures
 }
 
-func (u *upstreamResolverBase) queryUpstream(w dns.ResponseWriter, r *dns.Msg, upstream netip.AddrPort, timeout time.Duration, logger *log.Entry) bool {
+// queryUpstream queries a single upstream server. Returns nil on success, or failure info to try next upstream.
+func (u *upstreamResolverBase) queryUpstream(w dns.ResponseWriter, r *dns.Msg, upstream netip.AddrPort, timeout time.Duration, logger *log.Entry) *upstreamFailure {
 	var rm *dns.Msg
 	var t time.Duration
 	var err error
@@ -171,31 +185,32 @@ func (u *upstreamResolverBase) queryUpstream(w dns.ResponseWriter, r *dns.Msg, u
 	}()
 
 	if err != nil {
-		u.handleUpstreamError(err, upstream, r.Question[0].Name, startTime, timeout, logger)
-		return false
+		return u.handleUpstreamError(err, upstream, startTime)
 	}
 
 	if rm == nil || !rm.Response {
-		logger.Warnf("no response from upstream %s for question domain=%s", upstream, r.Question[0].Name)
-		return false
+		return &upstreamFailure{upstream: upstream, reason: "no response"}
 	}
 
-	return u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, logger)
+	if rm.Rcode == dns.RcodeServerFailure || rm.Rcode == dns.RcodeRefused {
+		return &upstreamFailure{upstream: upstream, reason: dns.RcodeToString[rm.Rcode]}
+	}
+
+	u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, logger)
+	return nil
 }
 
-func (u *upstreamResolverBase) handleUpstreamError(err error, upstream netip.AddrPort, domain string, startTime time.Time, timeout time.Duration, logger *log.Entry) {
+func (u *upstreamResolverBase) handleUpstreamError(err error, upstream netip.AddrPort, startTime time.Time) *upstreamFailure {
 	if !errors.Is(err, context.DeadlineExceeded) && !isTimeout(err) {
-		logger.Warnf("failed to query upstream %s for question domain=%s: %s", upstream, domain, err)
-		return
+		return &upstreamFailure{upstream: upstream, reason: err.Error()}
 	}
 
 	elapsed := time.Since(startTime)
-	timeoutMsg := fmt.Sprintf("upstream %s timed out for question domain=%s after %v (timeout=%v)", upstream, domain, elapsed.Truncate(time.Millisecond), timeout)
+	reason := fmt.Sprintf("timeout after %v", elapsed.Truncate(time.Millisecond))
 	if peerInfo := u.debugUpstreamTimeout(upstream); peerInfo != "" {
-		timeoutMsg += " " + peerInfo
+		reason += " " + peerInfo
 	}
-	timeoutMsg += fmt.Sprintf(" - error: %v", err)
-	logger.Warn(timeoutMsg)
+	return &upstreamFailure{upstream: upstream, reason: reason}
 }
 
 func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dns.Msg, upstream netip.AddrPort, domain string, t time.Duration, logger *log.Entry) bool {
@@ -215,16 +230,34 @@ func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dn
 	return true
 }
 
-func (u *upstreamResolverBase) writeErrorResponse(w dns.ResponseWriter, r *dns.Msg, logger *log.Entry) {
-	logger.Errorf("all queries to the %s failed for question domain=%s", u, r.Question[0].Name)
+func (u *upstreamResolverBase) logUpstreamFailures(domain string, failures []upstreamFailure, succeeded bool, logger *log.Entry) {
+	totalUpstreams := len(u.upstreamServers)
+	failedCount := len(failures)
+	failureSummary := formatFailures(failures)
 
+	if succeeded {
+		logger.Warnf("%d/%d upstreams failed for domain=%s: %s", failedCount, totalUpstreams, domain, failureSummary)
+	} else {
+		logger.Errorf("%d/%d upstreams failed for domain=%s: %s", failedCount, totalUpstreams, domain, failureSummary)
+	}
+}
+
+func (u *upstreamResolverBase) writeErrorResponse(w dns.ResponseWriter, r *dns.Msg, logger *log.Entry) {
 	m := new(dns.Msg)
 	m.SetRcode(r, dns.RcodeServerFailure)
 	if err := w.WriteMsg(m); err != nil {
-		logger.Errorf("failed to write error response for %s for question domain=%s: %s", u, r.Question[0].Name, err)
+		logger.Errorf("write error response for domain=%s: %s", r.Question[0].Name, err)
 	}
 }
 
+func formatFailures(failures []upstreamFailure) string {
+	parts := make([]string, 0, len(failures))
+	for _, f := range failures {
+		parts = append(parts, fmt.Sprintf("%s=%s", f.upstream, f.reason))
+	}
+	return strings.Join(parts, ", ")
+}
+
 // ProbeAvailability tests all upstream servers simultaneously and
 // disables the resolver if none work
 func (u *upstreamResolverBase) ProbeAvailability() {
@@ -468,7 +501,6 @@ func netstackExchange(ctx context.Context, nsNet *netstack.Net, r *dns.Msg, upst
 	return reply, nil
 }
 
-
 // FormatPeerStatus formats peer connection status information for debugging DNS timeouts
 func FormatPeerStatus(peerState *peer.State) string {
 	isConnected := peerState.ConnStatus == peer.StatusConnected

client/internal/dns/upstream_test.go

@@ -2,6 +2,7 @@ package dns
 
 import (
 	"context"
+	"fmt"
 	"net"
 	"net/netip"
 	"strings"
@@ -9,6 +10,8 @@ import (
 	"time"
 
 	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 	"golang.zx2c4.com/wireguard/tun/netstack"
 
 	"github.com/netbirdio/netbird/client/iface/device"
@@ -140,6 +143,23 @@ func (c mockUpstreamResolver) exchange(_ context.Context, _ string, _ *dns.Msg)
 	return c.r, c.rtt, c.err
 }
 
+type mockUpstreamResponse struct {
+	msg *dns.Msg
+	err error
+}
+
+type mockUpstreamResolverPerServer struct {
+	responses map[string]mockUpstreamResponse
+	rtt       time.Duration
+}
+
+func (c mockUpstreamResolverPerServer) exchange(_ context.Context, upstream string, _ *dns.Msg) (*dns.Msg, time.Duration, error) {
+	if r, ok := c.responses[upstream]; ok {
+		return r.msg, c.rtt, r.err
+	}
+	return nil, c.rtt, fmt.Errorf("no mock response for %s", upstream)
+}
+
 func TestUpstreamResolver_DeactivationReactivation(t *testing.T) {
 	mockClient := &mockUpstreamResolver{
 		err: dns.ErrTime,
@@ -191,3 +211,267 @@ func TestUpstreamResolver_DeactivationReactivation(t *testing.T) {
 		t.Errorf("should be enabled")
 	}
 }
+
+func TestUpstreamResolver_Failover(t *testing.T) {
+	upstream1 := netip.MustParseAddrPort("192.0.2.1:53")
+	upstream2 := netip.MustParseAddrPort("192.0.2.2:53")
+
+	successAnswer := "192.0.2.100"
+	timeoutErr := &net.OpError{Op: "read", Err: fmt.Errorf("i/o timeout")}
+
+	testCases := []struct {
+		name            string
+		upstream1       mockUpstreamResponse
+		upstream2       mockUpstreamResponse
+		expectedRcode   int
+		expectAnswer    bool
+		expectTrySecond bool
+	}{
+		{
+			name:            "success on first upstream",
+			upstream1:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+			expectedRcode:   dns.RcodeSuccess,
+			expectAnswer:    true,
+			expectTrySecond: false,
+		},
+		{
+			name:            "SERVFAIL from first should try second",
+			upstream1:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+			expectedRcode:   dns.RcodeSuccess,
+			expectAnswer:    true,
+			expectTrySecond: true,
+		},
+		{
+			name:            "REFUSED from first should try second",
+			upstream1:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeRefused, "")},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+			expectedRcode:   dns.RcodeSuccess,
+			expectAnswer:    true,
+			expectTrySecond: true,
+		},
+		{
+			name:            "NXDOMAIN from first should NOT try second",
+			upstream1:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeNameError, "")},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+			expectedRcode:   dns.RcodeNameError,
+			expectAnswer:    false,
+			expectTrySecond: false,
+		},
+		{
+			name:            "timeout from first should try second",
+			upstream1:       mockUpstreamResponse{err: timeoutErr},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+			expectedRcode:   dns.RcodeSuccess,
+			expectAnswer:    true,
+			expectTrySecond: true,
+		},
+		{
+			name:            "no response from first should try second",
+			upstream1:       mockUpstreamResponse{msg: nil},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+			expectedRcode:   dns.RcodeSuccess,
+			expectAnswer:    true,
+			expectTrySecond: true,
+		},
+		{
+			name:            "both upstreams return SERVFAIL",
+			upstream1:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			expectedRcode:   dns.RcodeServerFailure,
+			expectAnswer:    false,
+			expectTrySecond: true,
+		},
+		{
+			name:            "both upstreams timeout",
+			upstream1:       mockUpstreamResponse{err: timeoutErr},
+			upstream2:       mockUpstreamResponse{err: timeoutErr},
+			expectedRcode:   dns.RcodeServerFailure,
+			expectAnswer:    false,
+			expectTrySecond: true,
+		},
+		{
+			name:            "first SERVFAIL then timeout",
+			upstream1:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			upstream2:       mockUpstreamResponse{err: timeoutErr},
+			expectedRcode:   dns.RcodeServerFailure,
+			expectAnswer:    false,
+			expectTrySecond: true,
+		},
+		{
+			name:            "first timeout then SERVFAIL",
+			upstream1:       mockUpstreamResponse{err: timeoutErr},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			expectedRcode:   dns.RcodeServerFailure,
+			expectAnswer:    false,
+			expectTrySecond: true,
+		},
+		{
+			name:            "first REFUSED then SERVFAIL",
+			upstream1:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeRefused, "")},
+			upstream2:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			expectedRcode:   dns.RcodeServerFailure,
+			expectAnswer:    false,
+			expectTrySecond: true,
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			var queriedUpstreams []string
+			mockClient := &mockUpstreamResolverPerServer{
+				responses: map[string]mockUpstreamResponse{
+					upstream1.String(): tc.upstream1,
+					upstream2.String(): tc.upstream2,
+				},
+				rtt: time.Millisecond,
+			}
+
+			trackingClient := &trackingMockClient{
+				inner:            mockClient,
+				queriedUpstreams: &queriedUpstreams,
+			}
+
+			ctx, cancel := context.WithCancel(context.Background())
+			defer cancel()
+
+			resolver := &upstreamResolverBase{
+				ctx:             ctx,
+				upstreamClient:  trackingClient,
+				upstreamServers: []netip.AddrPort{upstream1, upstream2},
+				upstreamTimeout: UpstreamTimeout,
+			}
+
+			var responseMSG *dns.Msg
+			responseWriter := &test.MockResponseWriter{
+				WriteMsgFunc: func(m *dns.Msg) error {
+					responseMSG = m
+					return nil
+				},
+			}
+
+			inputMSG := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+			resolver.ServeDNS(responseWriter, inputMSG)
+
+			require.NotNil(t, responseMSG, "should write a response")
+			assert.Equal(t, tc.expectedRcode, responseMSG.Rcode, "unexpected rcode")
+
+			if tc.expectAnswer {
+				require.NotEmpty(t, responseMSG.Answer, "expected answer records")
+				assert.Contains(t, responseMSG.Answer[0].String(), successAnswer)
+			}
+
+			if tc.expectTrySecond {
+				assert.Len(t, queriedUpstreams, 2, "should have tried both upstreams")
+				assert.Equal(t, upstream1.String(), queriedUpstreams[0])
+				assert.Equal(t, upstream2.String(), queriedUpstreams[1])
+			} else {
+				assert.Len(t, queriedUpstreams, 1, "should have only tried first upstream")
+				assert.Equal(t, upstream1.String(), queriedUpstreams[0])
+			}
+		})
+	}
+}
+
+type trackingMockClient struct {
+	inner            *mockUpstreamResolverPerServer
+	queriedUpstreams *[]string
+}
+
+func (t *trackingMockClient) exchange(ctx context.Context, upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error) {
+	*t.queriedUpstreams = append(*t.queriedUpstreams, upstream)
+	return t.inner.exchange(ctx, upstream, r)
+}
+
+func buildMockResponse(rcode int, answer string) *dns.Msg {
+	m := new(dns.Msg)
+	m.Response = true
+	m.Rcode = rcode
+
+	if rcode == dns.RcodeSuccess && answer != "" {
+		m.Answer = []dns.RR{
+			&dns.A{
+				Hdr: dns.RR_Header{
+					Name:   "example.com.",
+					Rrtype: dns.TypeA,
+					Class:  dns.ClassINET,
+					Ttl:    300,
+				},
+				A: net.ParseIP(answer),
+			},
+		}
+	}
+	return m
+}
+
+func TestUpstreamResolver_SingleUpstreamFailure(t *testing.T) {
+	upstream := netip.MustParseAddrPort("192.0.2.1:53")
+
+	mockClient := &mockUpstreamResolverPerServer{
+		responses: map[string]mockUpstreamResponse{
+			upstream.String(): {msg: buildMockResponse(dns.RcodeServerFailure, "")},
+		},
+		rtt: time.Millisecond,
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	resolver := &upstreamResolverBase{
+		ctx:             ctx,
+		upstreamClient:  mockClient,
+		upstreamServers: []netip.AddrPort{upstream},
+		upstreamTimeout: UpstreamTimeout,
+	}
+
+	var responseMSG *dns.Msg
+	responseWriter := &test.MockResponseWriter{
+		WriteMsgFunc: func(m *dns.Msg) error {
+			responseMSG = m
+			return nil
+		},
+	}
+
+	inputMSG := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+	resolver.ServeDNS(responseWriter, inputMSG)
+
+	require.NotNil(t, responseMSG, "should write a response")
+	assert.Equal(t, dns.RcodeServerFailure, responseMSG.Rcode, "single upstream SERVFAIL should return SERVFAIL")
+}
+
+func TestFormatFailures(t *testing.T) {
+	testCases := []struct {
+		name     string
+		failures []upstreamFailure
+		expected string
+	}{
+		{
+			name:     "empty slice",
+			failures: []upstreamFailure{},
+			expected: "",
+		},
+		{
+			name: "single failure",
+			failures: []upstreamFailure{
+				{upstream: netip.MustParseAddrPort("8.8.8.8:53"), reason: "SERVFAIL"},
+			},
+			expected: "8.8.8.8:53=SERVFAIL",
+		},
+		{
+			name: "multiple failures",
+			failures: []upstreamFailure{
+				{upstream: netip.MustParseAddrPort("8.8.8.8:53"), reason: "SERVFAIL"},
+				{upstream: netip.MustParseAddrPort("8.8.4.4:53"), reason: "timeout after 2s"},
+			},
+			expected: "8.8.8.8:53=SERVFAIL, 8.8.4.4:53=timeout after 2s",
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			result := formatFailures(tc.failures)
+			assert.Equal(t, tc.expected, result)
+		})
+	}
+}

client/internal/engine.go

@@ -516,6 +516,10 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		return fmt.Errorf("up wg interface: %w", err)
 	}
 
+	// Set up notrack rules immediately after proxy is listening to prevent
+	// conntrack entries from being created before the rules are in place
+	e.setupWGProxyNoTrack()
+
 	// Set the WireGuard interface for rosenpass after interface is up
 	if e.rpManager != nil {
 		e.rpManager.SetInterface(e.wgInterface)
@@ -628,6 +632,23 @@ func (e *Engine) initFirewall() error {
 	return nil
 }
 
+// setupWGProxyNoTrack configures connection tracking exclusion for WireGuard proxy traffic.
+// This prevents conntrack/MASQUERADE from affecting loopback traffic between WireGuard and the eBPF proxy.
+func (e *Engine) setupWGProxyNoTrack() {
+	if e.firewall == nil {
+		return
+	}
+
+	proxyPort := e.wgInterface.GetProxyPort()
+	if proxyPort == 0 {
+		return
+	}
+
+	if err := e.firewall.SetupEBPFProxyNoTrack(proxyPort, uint16(e.config.WgPort)); err != nil {
+		log.Warnf("failed to setup ebpf proxy notrack: %v", err)
+	}
+}
+
 func (e *Engine) blockLanAccess() {
 	if e.config.BlockInbound {
 		// no need to set up extra deny rules if inbound is already blocked in general
@@ -1062,6 +1083,9 @@ func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobR
 		SyncResponse:   syncResponse,
 		LogPath:        e.config.LogPath,
 		ClientMetrics:  e.clientMetrics,
+		RefreshStatus: func() {
+			e.RunHealthProbes(true)
+		},
 	}
 
 	bundleJobParams := debug.BundleConfig{
@@ -1654,6 +1678,7 @@ func (e *Engine) parseNATExternalIPMappings() []string {
 
 func (e *Engine) close() {
 	log.Debugf("removing Netbird interface %s", e.config.WgIfaceName)
+
 	if e.wgInterface != nil {
 		if err := e.wgInterface.Close(); err != nil {
 			log.Errorf("failed closing Netbird interface %s %v", e.config.WgIfaceName, err)
@@ -1845,7 +1870,7 @@ func (e *Engine) getRosenpassAddr() string {
 	return ""
 }
 
-// RunHealthProbes executes health checks for Signal, Management, Relay and WireGuard services
+// RunHealthProbes executes health checks for Signal, Management, Relay, and WireGuard services
 // and updates the status recorder with the latest states.
 func (e *Engine) RunHealthProbes(waitForResult bool) bool {
 	e.syncMsgMux.Lock()
@@ -1859,23 +1884,8 @@ func (e *Engine) RunHealthProbes(waitForResult bool) bool {
 	stuns := slices.Clone(e.STUNs)
 	turns := slices.Clone(e.TURNs)
 
-	if e.wgInterface != nil {
-		stats, err := e.wgInterface.GetStats()
-		if err != nil {
-			log.Warnf("failed to get wireguard stats: %v", err)
-			e.syncMsgMux.Unlock()
-			return false
-		}
-		for _, key := range e.peerStore.PeersPubKey() {
-			// wgStats could be zero value, in which case we just reset the stats
-			wgStats, ok := stats[key]
-			if !ok {
-				continue
-			}
-			if err := e.statusRecorder.UpdateWireGuardPeerState(key, wgStats); err != nil {
-				log.Debugf("failed to update wg stats for peer %s: %s", key, err)
-			}
-		}
+	if err := e.statusRecorder.RefreshWireGuardStats(); err != nil {
+		log.Debugf("failed to refresh WireGuard stats: %v", err)
 	}
 
 	e.syncMsgMux.Unlock()

client/internal/engine_test.go

@@ -107,6 +107,7 @@ type MockWGIface struct {
 	GetStatsFunc               func() (map[string]configurer.WGStats, error)
 	GetInterfaceGUIDStringFunc func() (string, error)
 	GetProxyFunc               func() wgproxy.Proxy
+	GetProxyPortFunc           func() uint16
 	GetNetFunc                 func() *netstack.Net
 	LastActivitiesFunc         func() map[string]monotime.Time
 }
@@ -203,6 +204,13 @@ func (m *MockWGIface) GetProxy() wgproxy.Proxy {
 	return m.GetProxyFunc()
 }
 
+func (m *MockWGIface) GetProxyPort() uint16 {
+	if m.GetProxyPortFunc != nil {
+		return m.GetProxyPortFunc()
+	}
+	return 0
+}
+
 func (m *MockWGIface) GetNet() *netstack.Net {
 	return m.GetNetFunc()
 }

client/internal/iface_common.go

@@ -28,6 +28,7 @@ type wgIfaceBase interface {
 	Up() (*udpmux.UniversalUDPMuxDefault, error)
 	UpdateAddr(newAddr string) error
 	GetProxy() wgproxy.Proxy
+	GetProxyPort() uint16
 	UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error
 	RemoveEndpointAddress(key string) error
 	RemovePeer(peerKey string) error

client/internal/login.go

@@ -1,201 +0,0 @@
-package internal
-
-import (
-	"context"
-	"net/url"
-
-	"github.com/google/uuid"
-	log "github.com/sirupsen/logrus"
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-	"google.golang.org/grpc/codes"
-	"google.golang.org/grpc/status"
-
-	"github.com/netbirdio/netbird/client/internal/profilemanager"
-	"github.com/netbirdio/netbird/client/ssh"
-	"github.com/netbirdio/netbird/client/system"
-	mgm "github.com/netbirdio/netbird/shared/management/client"
-	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
-)
-
-// IsLoginRequired check that the server is support SSO or not
-func IsLoginRequired(ctx context.Context, config *profilemanager.Config) (bool, error) {
-	mgmURL := config.ManagementURL
-	mgmClient, err := getMgmClient(ctx, config.PrivateKey, mgmURL)
-	if err != nil {
-		return false, err
-	}
-	defer func() {
-		err = mgmClient.Close()
-		if err != nil {
-			cStatus, ok := status.FromError(err)
-			if !ok || ok && cStatus.Code() != codes.Canceled {
-				log.Warnf("failed to close the Management service client, err: %v", err)
-			}
-		}
-	}()
-	log.Debugf("connected to the Management service %s", mgmURL.String())
-
-	pubSSHKey, err := ssh.GeneratePublicKey([]byte(config.SSHKey))
-	if err != nil {
-		return false, err
-	}
-
-	_, _, err = doMgmLogin(ctx, mgmClient, pubSSHKey, config)
-	if isLoginNeeded(err) {
-		return true, nil
-	}
-	return false, err
-}
-
-// Login or register the client
-func Login(ctx context.Context, config *profilemanager.Config, setupKey string, jwtToken string) error {
-	mgmClient, err := getMgmClient(ctx, config.PrivateKey, config.ManagementURL)
-	if err != nil {
-		return err
-	}
-	defer func() {
-		err = mgmClient.Close()
-		if err != nil {
-			cStatus, ok := status.FromError(err)
-			if !ok || ok && cStatus.Code() != codes.Canceled {
-				log.Warnf("failed to close the Management service client, err: %v", err)
-			}
-		}
-	}()
-	log.Debugf("connected to the Management service %s", config.ManagementURL.String())
-
-	pubSSHKey, err := ssh.GeneratePublicKey([]byte(config.SSHKey))
-	if err != nil {
-		return err
-	}
-
-	serverKey, _, err := doMgmLogin(ctx, mgmClient, pubSSHKey, config)
-	if serverKey != nil && isRegistrationNeeded(err) {
-		log.Debugf("peer registration required")
-		_, err = registerPeer(ctx, *serverKey, mgmClient, setupKey, jwtToken, pubSSHKey, config)
-		if err != nil {
-			return err
-		}
-	} else if err != nil {
-		return err
-	}
-
-	return nil
-}
-
-func getMgmClient(ctx context.Context, privateKey string, mgmURL *url.URL) (*mgm.GrpcClient, error) {
-	// validate our peer's Wireguard PRIVATE key
-	myPrivateKey, err := wgtypes.ParseKey(privateKey)
-	if err != nil {
-		log.Errorf("failed parsing Wireguard key %s: [%s]", privateKey, err.Error())
-		return nil, err
-	}
-
-	var mgmTlsEnabled bool
-	if mgmURL.Scheme == "https" {
-		mgmTlsEnabled = true
-	}
-
-	log.Debugf("connecting to the Management service %s", mgmURL.String())
-	mgmClient, err := mgm.NewClient(ctx, mgmURL.Host, myPrivateKey, mgmTlsEnabled)
-	if err != nil {
-		log.Errorf("failed connecting to the Management service %s %v", mgmURL.String(), err)
-		return nil, err
-	}
-	return mgmClient, err
-}
-
-func doMgmLogin(ctx context.Context, mgmClient *mgm.GrpcClient, pubSSHKey []byte, config *profilemanager.Config) (*wgtypes.Key, *mgmProto.LoginResponse, error) {
-	serverKey, err := mgmClient.GetServerPublicKey()
-	if err != nil {
-		log.Errorf("failed while getting Management Service public key: %v", err)
-		return nil, nil, err
-	}
-
-	sysInfo := system.GetInfo(ctx)
-	sysInfo.SetFlags(
-		config.RosenpassEnabled,
-		config.RosenpassPermissive,
-		config.ServerSSHAllowed,
-		config.DisableClientRoutes,
-		config.DisableServerRoutes,
-		config.DisableDNS,
-		config.DisableFirewall,
-		config.BlockLANAccess,
-		config.BlockInbound,
-		config.LazyConnectionEnabled,
-		config.EnableSSHRoot,
-		config.EnableSSHSFTP,
-		config.EnableSSHLocalPortForwarding,
-		config.EnableSSHRemotePortForwarding,
-		config.DisableSSHAuth,
-	)
-	loginResp, err := mgmClient.Login(*serverKey, sysInfo, pubSSHKey, config.DNSLabels)
-	return serverKey, loginResp, err
-}
-
-// registerPeer checks whether setupKey was provided via cmd line and if not then it prompts user to enter a key.
-// Otherwise tries to register with the provided setupKey via command line.
-func registerPeer(ctx context.Context, serverPublicKey wgtypes.Key, client *mgm.GrpcClient, setupKey string, jwtToken string, pubSSHKey []byte, config *profilemanager.Config) (*mgmProto.LoginResponse, error) {
-	validSetupKey, err := uuid.Parse(setupKey)
-	if err != nil && jwtToken == "" {
-		return nil, status.Errorf(codes.InvalidArgument, "invalid setup-key or no sso information provided, err: %v", err)
-	}
-
-	log.Debugf("sending peer registration request to Management Service")
-	info := system.GetInfo(ctx)
-	info.SetFlags(
-		config.RosenpassEnabled,
-		config.RosenpassPermissive,
-		config.ServerSSHAllowed,
-		config.DisableClientRoutes,
-		config.DisableServerRoutes,
-		config.DisableDNS,
-		config.DisableFirewall,
-		config.BlockLANAccess,
-		config.BlockInbound,
-		config.LazyConnectionEnabled,
-		config.EnableSSHRoot,
-		config.EnableSSHSFTP,
-		config.EnableSSHLocalPortForwarding,
-		config.EnableSSHRemotePortForwarding,
-		config.DisableSSHAuth,
-	)
-	loginResp, err := client.Register(serverPublicKey, validSetupKey.String(), jwtToken, info, pubSSHKey, config.DNSLabels)
-	if err != nil {
-		log.Errorf("failed registering peer %v", err)
-		return nil, err
-	}
-
-	log.Infof("peer has been successfully registered on Management Service")
-
-	return loginResp, nil
-}
-
-func isLoginNeeded(err error) bool {
-	if err == nil {
-		return false
-	}
-	s, ok := status.FromError(err)
-	if !ok {
-		return false
-	}
-	if s.Code() == codes.InvalidArgument || s.Code() == codes.PermissionDenied {
-		return true
-	}
-	return false
-}
-
-func isRegistrationNeeded(err error) bool {
-	if err == nil {
-		return false
-	}
-	s, ok := status.FromError(err)
-	if !ok {
-		return false
-	}
-	if s.Code() == codes.PermissionDenied {
-		return true
-	}
-	return false
-}

client/internal/peer/status.go

@@ -1145,6 +1145,38 @@ func (d *Status) PeersStatus() (*configurer.Stats, error) {
 	return d.wgIface.FullStats()
 }
 
+// RefreshWireGuardStats fetches fresh WireGuard statistics from the interface
+// and updates the cached peer states. This ensures accurate handshake times and
+// transfer statistics in status reports without running full health probes.
+func (d *Status) RefreshWireGuardStats() error {
+	d.mux.Lock()
+	defer d.mux.Unlock()
+
+	if d.wgIface == nil {
+		return nil // silently skip if interface not set
+	}
+
+	stats, err := d.wgIface.FullStats()
+	if err != nil {
+		return fmt.Errorf("get wireguard stats: %w", err)
+	}
+
+	// Update each peer's WireGuard statistics
+	for _, peerStats := range stats.Peers {
+		peerState, ok := d.peers[peerStats.PublicKey]
+		if !ok {
+			continue
+		}
+
+		peerState.LastWireguardHandshake = peerStats.LastHandshake
+		peerState.BytesRx = peerStats.RxBytes
+		peerState.BytesTx = peerStats.TxBytes
+		d.peers[peerStats.PublicKey] = peerState
+	}
+
+	return nil
+}
+
 type EventQueue struct {
 	maxSize int
 	events  []*proto.SystemEvent

client/internal/peer/worker_ice.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"strconv"
 	"sync"
 	"time"
 
@@ -286,8 +287,8 @@ func (w *WorkerICE) connect(ctx context.Context, agent *icemaker.ThreadSafeAgent
 		RosenpassAddr:              remoteOfferAnswer.RosenpassAddr,
 		LocalIceCandidateType:      pair.Local.Type().String(),
 		RemoteIceCandidateType:     pair.Remote.Type().String(),
-		LocalIceCandidateEndpoint:  fmt.Sprintf("%s:%d", pair.Local.Address(), pair.Local.Port()),
-		RemoteIceCandidateEndpoint: fmt.Sprintf("%s:%d", pair.Remote.Address(), pair.Remote.Port()),
+		LocalIceCandidateEndpoint:  net.JoinHostPort(pair.Local.Address(), strconv.Itoa(pair.Local.Port())),
+		RemoteIceCandidateEndpoint: net.JoinHostPort(pair.Remote.Address(), strconv.Itoa(pair.Remote.Port())),
 		Relayed:                    isRelayed(pair),
 		RelayedOnLocal:             isRelayCandidate(pair.Local),
 	}
@@ -328,13 +329,7 @@ func (w *WorkerICE) closeAgent(agent *icemaker.ThreadSafeAgent, cancel context.C
 func (w *WorkerICE) punchRemoteWGPort(pair *ice.CandidatePair, remoteWgPort int) {
 	// wait local endpoint configuration
 	time.Sleep(time.Second)
-	addrString := pair.Remote.Address()
-	parsed, err := netip.ParseAddr(addrString)
-	if (err == nil) && (parsed.Is6()) {
-		addrString = fmt.Sprintf("[%s]", addrString)
-		//IPv6 Literals need to be wrapped in brackets for Resolve*Addr()
-	}
-	addr, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", addrString, remoteWgPort))
+	addr, err := net.ResolveUDPAddr("udp", net.JoinHostPort(pair.Remote.Address(), strconv.Itoa(remoteWgPort)))
 	if err != nil {
 		w.log.Warnf("got an error while resolving the udp address, err: %s", err)
 		return
@@ -386,12 +381,44 @@ func (w *WorkerICE) onICESelectedCandidatePair(agent *icemaker.ThreadSafeAgent,
 	}
 }
 
+func (w *WorkerICE) logSuccessfulPaths(agent *icemaker.ThreadSafeAgent) {
+	sessionID := w.SessionID()
+	stats := agent.GetCandidatePairsStats()
+	localCandidates, _ := agent.GetLocalCandidates()
+	remoteCandidates, _ := agent.GetRemoteCandidates()
+
+	localMap := make(map[string]ice.Candidate)
+	for _, c := range localCandidates {
+		localMap[c.ID()] = c
+	}
+	remoteMap := make(map[string]ice.Candidate)
+	for _, c := range remoteCandidates {
+		remoteMap[c.ID()] = c
+	}
+
+	for _, stat := range stats {
+		if stat.State == ice.CandidatePairStateSucceeded {
+			local, lok := localMap[stat.LocalCandidateID]
+			remote, rok := remoteMap[stat.RemoteCandidateID]
+			if !lok || !rok {
+				continue
+			}
+			w.log.Debugf("successful ICE path %s: [%s %s %s] <-> [%s %s %s] rtt=%.3fms",
+				sessionID,
+				local.NetworkType(), local.Type(), local.Address(),
+				remote.NetworkType(), remote.Type(), remote.Address(),
+				stat.CurrentRoundTripTime*1000)
+		}
+	}
+}
+
 func (w *WorkerICE) onConnectionStateChange(agent *icemaker.ThreadSafeAgent, dialerCancel context.CancelFunc) func(ice.ConnectionState) {
 	return func(state ice.ConnectionState) {
 		w.log.Debugf("ICE ConnectionState has changed to %s", state.String())
 		switch state {
 		case ice.ConnectionStateConnected:
 			w.lastKnownState = ice.ConnectionStateConnected
+			w.logSuccessfulPaths(agent)
 			return
 		case ice.ConnectionStateFailed, ice.ConnectionStateDisconnected, ice.ConnectionStateClosed:
 			// ice.ConnectionStateClosed happens when we recreate the agent. For the P2P to TURN switch important to

client/internal/pkce_auth.go

@@ -1,138 +0,0 @@
-package internal
-
-import (
-	"context"
-	"crypto/tls"
-	"fmt"
-	"net/url"
-
-	log "github.com/sirupsen/logrus"
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-	"google.golang.org/grpc/codes"
-	"google.golang.org/grpc/status"
-
-	mgm "github.com/netbirdio/netbird/shared/management/client"
-	"github.com/netbirdio/netbird/shared/management/client/common"
-)
-
-// PKCEAuthorizationFlow represents PKCE Authorization Flow information
-type PKCEAuthorizationFlow struct {
-	ProviderConfig PKCEAuthProviderConfig
-}
-
-// PKCEAuthProviderConfig has all attributes needed to initiate pkce authorization flow
-type PKCEAuthProviderConfig struct {
-	// ClientID An IDP application client id
-	ClientID string
-	// ClientSecret An IDP application client secret
-	ClientSecret string
-	// Audience An Audience for to authorization validation
-	Audience string
-	// TokenEndpoint is the endpoint of an IDP manager where clients can obtain access token
-	TokenEndpoint string
-	// AuthorizationEndpoint is the endpoint of an IDP manager where clients can obtain authorization code
-	AuthorizationEndpoint string
-	// Scopes provides the scopes to be included in the token request
-	Scope string
-	// RedirectURL handles authorization code from IDP manager
-	RedirectURLs []string
-	// UseIDToken indicates if the id token should be used for authentication
-	UseIDToken bool
-	// ClientCertPair is used for mTLS authentication to the IDP
-	ClientCertPair *tls.Certificate
-	// DisablePromptLogin makes the PKCE flow to not prompt the user for login
-	DisablePromptLogin bool
-	// LoginFlag is used to configure the PKCE flow login behavior
-	LoginFlag common.LoginFlag
-	// LoginHint is used to pre-fill the email/username field during authentication
-	LoginHint string
-}
-
-// GetPKCEAuthorizationFlowInfo initialize a PKCEAuthorizationFlow instance and return with it
-func GetPKCEAuthorizationFlowInfo(ctx context.Context, privateKey string, mgmURL *url.URL, clientCert *tls.Certificate) (PKCEAuthorizationFlow, error) {
-	// validate our peer's Wireguard PRIVATE key
-	myPrivateKey, err := wgtypes.ParseKey(privateKey)
-	if err != nil {
-		log.Errorf("failed parsing Wireguard key %s: [%s]", privateKey, err.Error())
-		return PKCEAuthorizationFlow{}, err
-	}
-
-	var mgmTLSEnabled bool
-	if mgmURL.Scheme == "https" {
-		mgmTLSEnabled = true
-	}
-
-	log.Debugf("connecting to Management Service %s", mgmURL.String())
-	mgmClient, err := mgm.NewClient(ctx, mgmURL.Host, myPrivateKey, mgmTLSEnabled)
-	if err != nil {
-		log.Errorf("failed connecting to Management Service %s %v", mgmURL.String(), err)
-		return PKCEAuthorizationFlow{}, err
-	}
-	log.Debugf("connected to the Management service %s", mgmURL.String())
-
-	defer func() {
-		err = mgmClient.Close()
-		if err != nil {
-			log.Warnf("failed to close the Management service client %v", err)
-		}
-	}()
-
-	serverKey, err := mgmClient.GetServerPublicKey()
-	if err != nil {
-		log.Errorf("failed while getting Management Service public key: %v", err)
-		return PKCEAuthorizationFlow{}, err
-	}
-
-	protoPKCEAuthorizationFlow, err := mgmClient.GetPKCEAuthorizationFlow(*serverKey)
-	if err != nil {
-		if s, ok := status.FromError(err); ok && s.Code() == codes.NotFound {
-			log.Warnf("server couldn't find pkce flow, contact admin: %v", err)
-			return PKCEAuthorizationFlow{}, err
-		}
-		log.Errorf("failed to retrieve pkce flow: %v", err)
-		return PKCEAuthorizationFlow{}, err
-	}
-
-	authFlow := PKCEAuthorizationFlow{
-		ProviderConfig: PKCEAuthProviderConfig{
-			Audience:              protoPKCEAuthorizationFlow.GetProviderConfig().GetAudience(),
-			ClientID:              protoPKCEAuthorizationFlow.GetProviderConfig().GetClientID(),
-			ClientSecret:          protoPKCEAuthorizationFlow.GetProviderConfig().GetClientSecret(),
-			TokenEndpoint:         protoPKCEAuthorizationFlow.GetProviderConfig().GetTokenEndpoint(),
-			AuthorizationEndpoint: protoPKCEAuthorizationFlow.GetProviderConfig().GetAuthorizationEndpoint(),
-			Scope:                 protoPKCEAuthorizationFlow.GetProviderConfig().GetScope(),
-			RedirectURLs:          protoPKCEAuthorizationFlow.GetProviderConfig().GetRedirectURLs(),
-			UseIDToken:            protoPKCEAuthorizationFlow.GetProviderConfig().GetUseIDToken(),
-			ClientCertPair:        clientCert,
-			DisablePromptLogin:    protoPKCEAuthorizationFlow.GetProviderConfig().GetDisablePromptLogin(),
-			LoginFlag:             common.LoginFlag(protoPKCEAuthorizationFlow.GetProviderConfig().GetLoginFlag()),
-		},
-	}
-
-	err = isPKCEProviderConfigValid(authFlow.ProviderConfig)
-	if err != nil {
-		return PKCEAuthorizationFlow{}, err
-	}
-
-	return authFlow, nil
-}
-
-func isPKCEProviderConfigValid(config PKCEAuthProviderConfig) error {
-	errorMSGFormat := "invalid provider configuration received from management: %s value is empty. Contact your NetBird administrator"
-	if config.ClientID == "" {
-		return fmt.Errorf(errorMSGFormat, "Client ID")
-	}
-	if config.TokenEndpoint == "" {
-		return fmt.Errorf(errorMSGFormat, "Token Endpoint")
-	}
-	if config.AuthorizationEndpoint == "" {
-		return fmt.Errorf(errorMSGFormat, "Authorization Auth Endpoint")
-	}
-	if config.Scope == "" {
-		return fmt.Errorf(errorMSGFormat, "PKCE Auth Scopes")
-	}
-	if config.RedirectURLs == nil {
-		return fmt.Errorf(errorMSGFormat, "PKCE Redirect URLs")
-	}
-	return nil
-}

client/internal/rosenpass/manager.go

@@ -17,6 +17,11 @@ import (
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 )
 
+const (
+	defaultLog         = slog.LevelInfo
+	defaultLogLevelVar = "NB_ROSENPASS_LOG_LEVEL"
+)
+
 func hashRosenpassKey(key []byte) string {
 	hasher := sha256.New()
 	hasher.Write(key)
@@ -45,7 +50,7 @@ func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error)
 	}
 
 	rpKeyHash := hashRosenpassKey(public)
-	log.Debugf("generated new rosenpass key pair with public key %s", rpKeyHash)
+	log.Tracef("generated new rosenpass key pair with public key %s", rpKeyHash)
 	return &Manager{ifaceName: wgIfaceName, rpKeyHash: rpKeyHash, spk: public, ssk: secret, preSharedKey: (*[32]byte)(preSharedKey), rpPeerIDs: make(map[string]*rp.PeerID), lock: sync.Mutex{}}, nil
 }
 
@@ -101,7 +106,7 @@ func (m *Manager) removePeer(wireGuardPubKey string) error {
 
 func (m *Manager) generateConfig() (rp.Config, error) {
 	opts := &slog.HandlerOptions{
-		Level: slog.LevelDebug,
+		Level: getLogLevel(),
 	}
 	logger := slog.New(slog.NewTextHandler(os.Stdout, opts))
 	cfg := rp.Config{Logger: logger}
@@ -133,6 +138,26 @@ func (m *Manager) generateConfig() (rp.Config, error) {
 	return cfg, nil
 }
 
+func getLogLevel() slog.Level {
+	level, ok := os.LookupEnv(defaultLogLevelVar)
+	if !ok {
+		return defaultLog
+	}
+	switch strings.ToLower(level) {
+	case "debug":
+		return slog.LevelDebug
+	case "info":
+		return slog.LevelInfo
+	case "warn":
+		return slog.LevelWarn
+	case "error":
+		return slog.LevelError
+	default:
+		log.Warnf("unknown log level: %s. Using default %s", level, defaultLog.String())
+		return defaultLog
+	}
+}
+
 func (m *Manager) OnDisconnected(peerKey string) {
 	m.lock.Lock()
 	defer m.lock.Unlock()