[management] add context cancel monitoring (#5879)

(cherry picked from commit c5623307cc)

client/cmd/debug.go

@@ -199,9 +199,11 @@ func runForDuration(cmd *cobra.Command, args []string) error {
 		cmd.Println("Log level set to trace.")
 	}
 
+	needsRestoreUp := false
 	if _, err := client.Down(cmd.Context(), &proto.DownRequest{}); err != nil {
 		cmd.PrintErrf("Failed to bring service down: %v\n", status.Convert(err).Message())
 	} else {
+		needsRestoreUp = !stateWasDown
 		cmd.Println("netbird down")
 	}
 
@@ -217,6 +219,7 @@ func runForDuration(cmd *cobra.Command, args []string) error {
 	if _, err := client.Up(cmd.Context(), &proto.UpRequest{}); err != nil {
 		cmd.PrintErrf("Failed to bring service up: %v\n", status.Convert(err).Message())
 	} else {
+		needsRestoreUp = false
 		cmd.Println("netbird up")
 	}
 
@@ -264,6 +267,14 @@ func runForDuration(cmd *cobra.Command, args []string) error {
 		return fmt.Errorf("failed to bundle debug: %v", status.Convert(err).Message())
 	}
 
+	if needsRestoreUp {
+		if _, err := client.Up(cmd.Context(), &proto.UpRequest{}); err != nil {
+			cmd.PrintErrf("Failed to restore service up state: %v\n", status.Convert(err).Message())
+		} else {
+			cmd.Println("netbird up (restored)")
+		}
+	}
+
 	if stateWasDown {
 		if _, err := client.Down(cmd.Context(), &proto.DownRequest{}); err != nil {
 			cmd.PrintErrf("Failed to restore service down state: %v\n", status.Convert(err).Message())

client/cmd/expose.go

@@ -14,6 +14,7 @@ import (
 
 	log "github.com/sirupsen/logrus"
 	"github.com/spf13/cobra"
+	"google.golang.org/grpc/status"
 
 	"github.com/netbirdio/netbird/client/internal/expose"
 	"github.com/netbirdio/netbird/client/proto"
@@ -201,7 +202,7 @@ func exposeFn(cmd *cobra.Command, args []string) error {
 
 	stream, err := client.ExposeService(ctx, req)
 	if err != nil {
-		return fmt.Errorf("expose service: %w", err)
+		return fmt.Errorf("expose service: %v", status.Convert(err).Message())
 	}
 
 	if err := handleExposeReady(cmd, stream, port); err != nil {
@@ -236,7 +237,7 @@ func toExposeProtocol(exposeProtocol string) (proto.ExposeProtocol, error) {
 func handleExposeReady(cmd *cobra.Command, stream proto.DaemonService_ExposeServiceClient, port uint64) error {
 	event, err := stream.Recv()
 	if err != nil {
-		return fmt.Errorf("receive expose event: %w", err)
+		return fmt.Errorf("receive expose event: %v", status.Convert(err).Message())
 	}
 
 	ready, ok := event.Event.(*proto.ExposeServiceEvent_Ready)

client/cmd/service_test.go

@@ -4,7 +4,9 @@ import (
 	"context"
 	"fmt"
 	"os"
+	"os/signal"
 	"runtime"
+	"syscall"
 	"testing"
 	"time"
 
@@ -13,6 +15,22 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
+// TestMain intercepts when this test binary is run as a daemon subprocess.
+// On FreeBSD, the rc.d service script runs the binary via daemon(8) -r with
+// "service run ..." arguments. Since the test binary can't handle cobra CLI
+// args, it exits immediately, causing daemon -r to respawn rapidly until
+// hitting the rate limit and exiting. This makes service restart unreliable.
+// Blocking here keeps the subprocess alive until the init system sends SIGTERM.
+func TestMain(m *testing.M) {
+	if len(os.Args) > 2 && os.Args[1] == "service" && os.Args[2] == "run" {
+		sig := make(chan os.Signal, 1)
+		signal.Notify(sig, syscall.SIGTERM, os.Interrupt)
+		<-sig
+		return
+	}
+	os.Exit(m.Run())
+}
+
 const (
 	serviceStartTimeout = 10 * time.Second
 	serviceStopTimeout  = 5 * time.Second
@@ -79,6 +97,34 @@ func TestServiceLifecycle(t *testing.T) {
 	logLevel = "info"
 	daemonAddr = fmt.Sprintf("unix://%s/netbird-test.sock", tempDir)
 
+	// Ensure cleanup even if a subtest fails and Stop/Uninstall subtests don't run.
+	t.Cleanup(func() {
+		cfg, err := newSVCConfig()
+		if err != nil {
+			t.Errorf("cleanup: create service config: %v", err)
+			return
+		}
+		ctxSvc, cancel := context.WithCancel(context.Background())
+		defer cancel()
+		s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
+		if err != nil {
+			t.Errorf("cleanup: create service: %v", err)
+			return
+		}
+
+		// If the subtests already cleaned up, there's nothing to do.
+		if _, err := s.Status(); err != nil {
+			return
+		}
+
+		if err := s.Stop(); err != nil {
+			t.Errorf("cleanup: stop service: %v", err)
+		}
+		if err := s.Uninstall(); err != nil {
+			t.Errorf("cleanup: uninstall service: %v", err)
+		}
+	})
+
 	ctx := context.Background()
 
 	t.Run("Install", func(t *testing.T) {

client/firewall/create_linux.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"fmt"
 	"os"
+	"strconv"
 
 	"github.com/coreos/go-iptables/iptables"
 	"github.com/google/nftables"
@@ -35,20 +36,34 @@ const SKIP_NFTABLES_ENV = "NB_SKIP_NFTABLES_CHECK"
 type FWType int
 
 func NewFirewall(iface IFaceMapper, stateManager *statemanager.Manager, flowLogger nftypes.FlowLogger, disableServerRoutes bool, mtu uint16) (firewall.Manager, error) {
-	// on the linux system we try to user nftables or iptables
-	// in any case, because we need to allow netbird interface traffic
-	// so we use AllowNetbird traffic from these firewall managers
-	// for the userspace packet filtering firewall
+	// We run in userspace mode and force userspace firewall was requested. We don't attempt native firewall.
+	if iface.IsUserspaceBind() && forceUserspaceFirewall() {
+		log.Info("forcing userspace firewall")
+		return createUserspaceFirewall(iface, nil, disableServerRoutes, flowLogger, mtu)
+	}
+
+	// Use native firewall for either kernel or userspace, the interface appears identical to netfilter
 	fm, err := createNativeFirewall(iface, stateManager, disableServerRoutes, mtu)
 
+	// Kernel cannot fall back to anything else, need to return error
 	if !iface.IsUserspaceBind() {
 		return fm, err
 	}
 
+	// Fall back to the userspace packet filter if native is unavailable
 	if err != nil {
 		log.Warnf("failed to create native firewall: %v. Proceeding with userspace", err)
+		return createUserspaceFirewall(iface, nil, disableServerRoutes, flowLogger, mtu)
 	}
-	return createUserspaceFirewall(iface, fm, disableServerRoutes, flowLogger, mtu)
+
+	// Native firewall handles packet filtering, but the userspace WireGuard bind
+	// needs a device filter for DNS interception hooks. Install a minimal
+	// hooks-only filter that passes all traffic through to the kernel firewall.
+	if err := iface.SetFilter(&uspfilter.HooksFilter{}); err != nil {
+		log.Warnf("failed to set hooks filter, DNS via memory hooks will not work: %v", err)
+	}
+
+	return fm, nil
 }
 
 func createNativeFirewall(iface IFaceMapper, stateManager *statemanager.Manager, routes bool, mtu uint16) (firewall.Manager, error) {
@@ -160,3 +175,17 @@ func isIptablesClientAvailable(client *iptables.IPTables) bool {
 	_, err := client.ListChains("filter")
 	return err == nil
 }
+
+func forceUserspaceFirewall() bool {
+	val := os.Getenv(EnvForceUserspaceFirewall)
+	if val == "" {
+		return false
+	}
+
+	force, err := strconv.ParseBool(val)
+	if err != nil {
+		log.Warnf("failed to parse %s: %v", EnvForceUserspaceFirewall, err)
+		return false
+	}
+	return force
+}

client/firewall/iface.go

@@ -7,6 +7,12 @@ import (
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 )
 
+// EnvForceUserspaceFirewall forces the use of the userspace packet filter even when
+// native iptables/nftables is available. This only applies when the WireGuard interface
+// runs in userspace mode. When set, peer ACLs are handled by USPFilter instead of
+// kernel netfilter rules.
+const EnvForceUserspaceFirewall = "NB_FORCE_USERSPACE_FIREWALL"
+
 // IFaceMapper defines subset methods of interface required for manager
 type IFaceMapper interface {
 	Name() string

client/firewall/iptables/manager_linux.go

@@ -33,7 +33,6 @@ type Manager struct {
 type iFaceMapper interface {
 	Name() string
 	Address() wgaddr.Address
-	IsUserspaceBind() bool
 }
 
 // Create iptables firewall manager
@@ -64,10 +63,9 @@ func Create(wgIface iFaceMapper, mtu uint16) (*Manager, error) {
 func (m *Manager) Init(stateManager *statemanager.Manager) error {
 	state := &ShutdownState{
 		InterfaceState: &InterfaceState{
-			NameStr:       m.wgIface.Name(),
-			WGAddress:     m.wgIface.Address(),
-			UserspaceBind: m.wgIface.IsUserspaceBind(),
-			MTU:           m.router.mtu,
+			NameStr:   m.wgIface.Name(),
+			WGAddress: m.wgIface.Address(),
+			MTU:       m.router.mtu,
 		},
 	}
 	stateManager.RegisterState(state)
@@ -203,12 +201,10 @@ func (m *Manager) Close(stateManager *statemanager.Manager) error {
 	return nberrors.FormatErrorOrNil(merr)
 }
 
-// AllowNetbird allows netbird interface traffic
+// AllowNetbird allows netbird interface traffic.
+// This is called when USPFilter wraps the native firewall, adding blanket accept
+// rules so that packet filtering is handled in userspace instead of by netfilter.
 func (m *Manager) AllowNetbird() error {
-	if !m.wgIface.IsUserspaceBind() {
-		return nil
-	}
-
 	_, err := m.AddPeerFiltering(
 		nil,
 		net.IP{0, 0, 0, 0},
@@ -286,6 +282,22 @@ func (m *Manager) RemoveInboundDNAT(localAddr netip.Addr, protocol firewall.Prot
 	return m.router.RemoveInboundDNAT(localAddr, protocol, sourcePort, targetPort)
 }
 
+// AddOutputDNAT adds an OUTPUT chain DNAT rule for locally-generated traffic.
+func (m *Manager) AddOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	m.mutex.Lock()
+	defer m.mutex.Unlock()
+
+	return m.router.AddOutputDNAT(localAddr, protocol, sourcePort, targetPort)
+}
+
+// RemoveOutputDNAT removes an OUTPUT chain DNAT rule.
+func (m *Manager) RemoveOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	m.mutex.Lock()
+	defer m.mutex.Unlock()
+
+	return m.router.RemoveOutputDNAT(localAddr, protocol, sourcePort, targetPort)
+}
+
 const (
 	chainNameRaw = "NETBIRD-RAW"
 	chainOUTPUT  = "OUTPUT"

client/firewall/iptables/manager_linux_test.go

@@ -47,8 +47,6 @@ func (i *iFaceMock) Address() wgaddr.Address {
 	panic("AddressFunc is not set")
 }
 
-func (i *iFaceMock) IsUserspaceBind() bool { return false }
-
 func TestIptablesManager(t *testing.T) {
 	ipv4Client, err := iptables.NewWithProtocol(iptables.ProtocolIPv4)
 	require.NoError(t, err)

client/firewall/iptables/router_linux.go

@@ -36,6 +36,7 @@ const (
 	chainRTFWDOUT           = "NETBIRD-RT-FWD-OUT"
 	chainRTPRE              = "NETBIRD-RT-PRE"
 	chainRTRDR              = "NETBIRD-RT-RDR"
+	chainNATOutput          = "NETBIRD-NAT-OUTPUT"
 	chainRTMSSCLAMP         = "NETBIRD-RT-MSSCLAMP"
 	routingFinalForwardJump = "ACCEPT"
 	routingFinalNatJump     = "MASQUERADE"
@@ -43,6 +44,7 @@ const (
 	jumpManglePre  = "jump-mangle-pre"
 	jumpNatPre     = "jump-nat-pre"
 	jumpNatPost    = "jump-nat-post"
+	jumpNatOutput  = "jump-nat-output"
 	jumpMSSClamp   = "jump-mss-clamp"
 	markManglePre  = "mark-mangle-pre"
 	markManglePost = "mark-mangle-post"
@@ -387,6 +389,14 @@ func (r *router) cleanUpDefaultForwardRules() error {
 	}
 
 	log.Debug("flushing routing related tables")
+
+	// Remove jump rules from built-in chains before deleting custom chains,
+	// otherwise the chain deletion fails with "device or resource busy".
+	jumpRule := []string{"-j", chainNATOutput}
+	if err := r.iptablesClient.Delete(tableNat, "OUTPUT", jumpRule...); err != nil {
+		log.Debugf("clean OUTPUT jump rule: %v", err)
+	}
+
 	for _, chainInfo := range []struct {
 		chain string
 		table string
@@ -396,6 +406,7 @@ func (r *router) cleanUpDefaultForwardRules() error {
 		{chainRTPRE, tableMangle},
 		{chainRTNAT, tableNat},
 		{chainRTRDR, tableNat},
+		{chainNATOutput, tableNat},
 		{chainRTMSSCLAMP, tableMangle},
 	} {
 		ok, err := r.iptablesClient.ChainExists(chainInfo.table, chainInfo.chain)
@@ -970,6 +981,81 @@ func (r *router) RemoveInboundDNAT(localAddr netip.Addr, protocol firewall.Proto
 	return nil
 }
 
+// ensureNATOutputChain lazily creates the OUTPUT NAT chain and jump rule on first use.
+func (r *router) ensureNATOutputChain() error {
+	if _, exists := r.rules[jumpNatOutput]; exists {
+		return nil
+	}
+
+	chainExists, err := r.iptablesClient.ChainExists(tableNat, chainNATOutput)
+	if err != nil {
+		return fmt.Errorf("check chain %s: %w", chainNATOutput, err)
+	}
+	if !chainExists {
+		if err := r.iptablesClient.NewChain(tableNat, chainNATOutput); err != nil {
+			return fmt.Errorf("create chain %s: %w", chainNATOutput, err)
+		}
+	}
+
+	jumpRule := []string{"-j", chainNATOutput}
+	if err := r.iptablesClient.Insert(tableNat, "OUTPUT", 1, jumpRule...); err != nil {
+		if !chainExists {
+			if delErr := r.iptablesClient.ClearAndDeleteChain(tableNat, chainNATOutput); delErr != nil {
+				log.Warnf("failed to rollback chain %s: %v", chainNATOutput, delErr)
+			}
+		}
+		return fmt.Errorf("add OUTPUT jump rule: %w", err)
+	}
+	r.rules[jumpNatOutput] = jumpRule
+
+	r.updateState()
+	return nil
+}
+
+// AddOutputDNAT adds an OUTPUT chain DNAT rule for locally-generated traffic.
+func (r *router) AddOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	ruleID := fmt.Sprintf("output-dnat-%s-%s-%d-%d", localAddr.String(), protocol, sourcePort, targetPort)
+
+	if _, exists := r.rules[ruleID]; exists {
+		return nil
+	}
+
+	if err := r.ensureNATOutputChain(); err != nil {
+		return err
+	}
+
+	dnatRule := []string{
+		"-p", strings.ToLower(string(protocol)),
+		"--dport", strconv.Itoa(int(sourcePort)),
+		"-d", localAddr.String(),
+		"-j", "DNAT",
+		"--to-destination", ":" + strconv.Itoa(int(targetPort)),
+	}
+
+	if err := r.iptablesClient.Append(tableNat, chainNATOutput, dnatRule...); err != nil {
+		return fmt.Errorf("add output DNAT rule: %w", err)
+	}
+	r.rules[ruleID] = dnatRule
+
+	r.updateState()
+	return nil
+}
+
+// RemoveOutputDNAT removes an OUTPUT chain DNAT rule.
+func (r *router) RemoveOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	ruleID := fmt.Sprintf("output-dnat-%s-%s-%d-%d", localAddr.String(), protocol, sourcePort, targetPort)
+
+	if dnatRule, exists := r.rules[ruleID]; exists {
+		if err := r.iptablesClient.Delete(tableNat, chainNATOutput, dnatRule...); err != nil {
+			return fmt.Errorf("delete output DNAT rule: %w", err)
+		}
+		delete(r.rules, ruleID)
+	}
+
+	r.updateState()
+	return nil
+}
+
 func applyPort(flag string, port *firewall.Port) []string {
 	if port == nil {
 		return nil

client/firewall/iptables/state_linux.go

@@ -9,10 +9,9 @@ import (
 )
 
 type InterfaceState struct {
-	NameStr       string         `json:"name"`
-	WGAddress     wgaddr.Address `json:"wg_address"`
-	UserspaceBind bool           `json:"userspace_bind"`
-	MTU           uint16         `json:"mtu"`
+	NameStr   string         `json:"name"`
+	WGAddress wgaddr.Address `json:"wg_address"`
+	MTU       uint16         `json:"mtu"`
 }
 
 func (i *InterfaceState) Name() string {
@@ -23,10 +22,6 @@ func (i *InterfaceState) Address() wgaddr.Address {
 	return i.WGAddress
 }
 
-func (i *InterfaceState) IsUserspaceBind() bool {
-	return i.UserspaceBind
-}
-
 type ShutdownState struct {
 	sync.Mutex
 

client/firewall/manager/firewall.go

@@ -169,6 +169,14 @@ type Manager interface {
 	// RemoveInboundDNAT removes inbound DNAT rule
 	RemoveInboundDNAT(localAddr netip.Addr, protocol Protocol, sourcePort, targetPort uint16) error
 
+	// AddOutputDNAT adds an OUTPUT chain DNAT rule for locally-generated traffic.
+	// localAddr must be IPv4; the underlying iptables/nftables backends are IPv4-only.
+	AddOutputDNAT(localAddr netip.Addr, protocol Protocol, sourcePort, targetPort uint16) error
+
+	// RemoveOutputDNAT removes an OUTPUT chain DNAT rule.
+	// localAddr must be IPv4; the underlying iptables/nftables backends are IPv4-only.
+	RemoveOutputDNAT(localAddr netip.Addr, protocol Protocol, sourcePort, targetPort uint16) error
+
 	// SetupEBPFProxyNoTrack creates static notrack rules for eBPF proxy loopback traffic.
 	// This prevents conntrack from interfering with WireGuard proxy communication.
 	SetupEBPFProxyNoTrack(proxyPort, wgPort uint16) error

client/firewall/nftables/manager_linux.go

@@ -40,7 +40,6 @@ func getTableName() string {
 type iFaceMapper interface {
 	Name() string
 	Address() wgaddr.Address
-	IsUserspaceBind() bool
 }
 
 // Manager of iptables firewall
@@ -106,10 +105,9 @@ func (m *Manager) Init(stateManager *statemanager.Manager) error {
 	// cleanup using Close() without needing to store specific rules.
 	if err := stateManager.UpdateState(&ShutdownState{
 		InterfaceState: &InterfaceState{
-			NameStr:       m.wgIface.Name(),
-			WGAddress:     m.wgIface.Address(),
-			UserspaceBind: m.wgIface.IsUserspaceBind(),
-			MTU:           m.router.mtu,
+			NameStr:   m.wgIface.Name(),
+			WGAddress: m.wgIface.Address(),
+			MTU:       m.router.mtu,
 		},
 	}); err != nil {
 		log.Errorf("failed to update state: %v", err)
@@ -205,12 +203,10 @@ func (m *Manager) RemoveNatRule(pair firewall.RouterPair) error {
 	return m.router.RemoveNatRule(pair)
 }
 
-// AllowNetbird allows netbird interface traffic
+// AllowNetbird allows netbird interface traffic.
+// This is called when USPFilter wraps the native firewall, adding blanket accept
+// rules so that packet filtering is handled in userspace instead of by netfilter.
 func (m *Manager) AllowNetbird() error {
-	if !m.wgIface.IsUserspaceBind() {
-		return nil
-	}
-
 	m.mutex.Lock()
 	defer m.mutex.Unlock()
 
@@ -346,6 +342,22 @@ func (m *Manager) RemoveInboundDNAT(localAddr netip.Addr, protocol firewall.Prot
 	return m.router.RemoveInboundDNAT(localAddr, protocol, sourcePort, targetPort)
 }
 
+// AddOutputDNAT adds an OUTPUT chain DNAT rule for locally-generated traffic.
+func (m *Manager) AddOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	m.mutex.Lock()
+	defer m.mutex.Unlock()
+
+	return m.router.AddOutputDNAT(localAddr, protocol, sourcePort, targetPort)
+}
+
+// RemoveOutputDNAT removes an OUTPUT chain DNAT rule.
+func (m *Manager) RemoveOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	m.mutex.Lock()
+	defer m.mutex.Unlock()
+
+	return m.router.RemoveOutputDNAT(localAddr, protocol, sourcePort, targetPort)
+}
+
 const (
 	chainNameRawOutput     = "netbird-raw-out"
 	chainNameRawPrerouting = "netbird-raw-pre"

client/firewall/nftables/manager_linux_test.go

@@ -52,8 +52,6 @@ func (i *iFaceMock) Address() wgaddr.Address {
 	panic("AddressFunc is not set")
 }
 
-func (i *iFaceMock) IsUserspaceBind() bool { return false }
-
 func TestNftablesManager(t *testing.T) {
 
 	// just check on the local interface

client/firewall/nftables/router_linux.go

@@ -36,6 +36,7 @@ const (
 	chainNameRoutingFw     = "netbird-rt-fwd"
 	chainNameRoutingNat    = "netbird-rt-postrouting"
 	chainNameRoutingRdr    = "netbird-rt-redirect"
+	chainNameNATOutput     = "netbird-nat-output"
 	chainNameForward       = "FORWARD"
 	chainNameMangleForward = "netbird-mangle-forward"
 
@@ -1853,6 +1854,130 @@ func (r *router) RemoveInboundDNAT(localAddr netip.Addr, protocol firewall.Proto
 	return nil
 }
 
+// ensureNATOutputChain lazily creates the OUTPUT NAT chain on first use.
+func (r *router) ensureNATOutputChain() error {
+	if _, exists := r.chains[chainNameNATOutput]; exists {
+		return nil
+	}
+
+	r.chains[chainNameNATOutput] = r.conn.AddChain(&nftables.Chain{
+		Name:     chainNameNATOutput,
+		Table:    r.workTable,
+		Hooknum:  nftables.ChainHookOutput,
+		Priority: nftables.ChainPriorityNATDest,
+		Type:     nftables.ChainTypeNAT,
+	})
+
+	if err := r.conn.Flush(); err != nil {
+		delete(r.chains, chainNameNATOutput)
+		return fmt.Errorf("create NAT output chain: %w", err)
+	}
+	return nil
+}
+
+// AddOutputDNAT adds an OUTPUT chain DNAT rule for locally-generated traffic.
+func (r *router) AddOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	ruleID := fmt.Sprintf("output-dnat-%s-%s-%d-%d", localAddr.String(), protocol, sourcePort, targetPort)
+
+	if _, exists := r.rules[ruleID]; exists {
+		return nil
+	}
+
+	if err := r.ensureNATOutputChain(); err != nil {
+		return err
+	}
+
+	protoNum, err := protoToInt(protocol)
+	if err != nil {
+		return fmt.Errorf("convert protocol to number: %w", err)
+	}
+
+	exprs := []expr.Any{
+		&expr.Meta{Key: expr.MetaKeyL4PROTO, Register: 1},
+		&expr.Cmp{
+			Op:       expr.CmpOpEq,
+			Register: 1,
+			Data:     []byte{protoNum},
+		},
+		&expr.Payload{
+			DestRegister: 2,
+			Base:         expr.PayloadBaseTransportHeader,
+			Offset:       2,
+			Len:          2,
+		},
+		&expr.Cmp{
+			Op:       expr.CmpOpEq,
+			Register: 2,
+			Data:     binaryutil.BigEndian.PutUint16(sourcePort),
+		},
+	}
+
+	exprs = append(exprs, applyPrefix(netip.PrefixFrom(localAddr, 32), false)...)
+
+	exprs = append(exprs,
+		&expr.Immediate{
+			Register: 1,
+			Data:     localAddr.AsSlice(),
+		},
+		&expr.Immediate{
+			Register: 2,
+			Data:     binaryutil.BigEndian.PutUint16(targetPort),
+		},
+		&expr.NAT{
+			Type:        expr.NATTypeDestNAT,
+			Family:      uint32(nftables.TableFamilyIPv4),
+			RegAddrMin:  1,
+			RegProtoMin: 2,
+		},
+	)
+
+	dnatRule := &nftables.Rule{
+		Table:    r.workTable,
+		Chain:    r.chains[chainNameNATOutput],
+		Exprs:    exprs,
+		UserData: []byte(ruleID),
+	}
+	r.conn.AddRule(dnatRule)
+
+	if err := r.conn.Flush(); err != nil {
+		return fmt.Errorf("add output DNAT rule: %w", err)
+	}
+
+	r.rules[ruleID] = dnatRule
+
+	return nil
+}
+
+// RemoveOutputDNAT removes an OUTPUT chain DNAT rule.
+func (r *router) RemoveOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	if err := r.refreshRulesMap(); err != nil {
+		return fmt.Errorf(refreshRulesMapError, err)
+	}
+
+	ruleID := fmt.Sprintf("output-dnat-%s-%s-%d-%d", localAddr.String(), protocol, sourcePort, targetPort)
+
+	rule, exists := r.rules[ruleID]
+	if !exists {
+		return nil
+	}
+
+	if rule.Handle == 0 {
+		log.Warnf("output DNAT rule %s has no handle, removing stale entry", ruleID)
+		delete(r.rules, ruleID)
+		return nil
+	}
+
+	if err := r.conn.DelRule(rule); err != nil {
+		return fmt.Errorf("delete output DNAT rule %s: %w", ruleID, err)
+	}
+	if err := r.conn.Flush(); err != nil {
+		return fmt.Errorf("flush delete output DNAT rule: %w", err)
+	}
+	delete(r.rules, ruleID)
+
+	return nil
+}
+
 // applyNetwork generates nftables expressions for networks (CIDR) or sets
 func (r *router) applyNetwork(
 	network firewall.Network,

client/firewall/nftables/state_linux.go

@@ -8,10 +8,9 @@ import (
 )
 
 type InterfaceState struct {
-	NameStr       string         `json:"name"`
-	WGAddress     wgaddr.Address `json:"wg_address"`
-	UserspaceBind bool           `json:"userspace_bind"`
-	MTU           uint16         `json:"mtu"`
+	NameStr   string         `json:"name"`
+	WGAddress wgaddr.Address `json:"wg_address"`
+	MTU       uint16         `json:"mtu"`
 }
 
 func (i *InterfaceState) Name() string {
@@ -22,10 +21,6 @@ func (i *InterfaceState) Address() wgaddr.Address {
 	return i.WGAddress
 }
 
-func (i *InterfaceState) IsUserspaceBind() bool {
-	return i.UserspaceBind
-}
-
 type ShutdownState struct {
 	InterfaceState *InterfaceState `json:"interface_state,omitempty"`
 }

client/firewall/uspfilter/common/hooks.go

@@ -0,0 +1,37 @@
+package common
+
+import (
+	"net/netip"
+	"sync/atomic"
+)
+
+// PacketHook stores a registered hook for a specific IP:port.
+type PacketHook struct {
+	IP   netip.Addr
+	Port uint16
+	Fn   func([]byte) bool
+}
+
+// HookMatches checks if a packet's destination matches the hook and invokes it.
+func HookMatches(h *PacketHook, dstIP netip.Addr, dport uint16, packetData []byte) bool {
+	if h == nil {
+		return false
+	}
+	if h.IP == dstIP && h.Port == dport {
+		return h.Fn(packetData)
+	}
+	return false
+}
+
+// SetHook atomically stores a hook, handling nil removal.
+func SetHook(ptr *atomic.Pointer[PacketHook], ip netip.Addr, dPort uint16, hook func([]byte) bool) {
+	if hook == nil {
+		ptr.Store(nil)
+		return
+	}
+	ptr.Store(&PacketHook{
+		IP:   ip,
+		Port: dPort,
+		Fn:   hook,
+	})
+}

client/firewall/uspfilter/filter.go

@@ -140,6 +140,10 @@ type Manager struct {
 	mtu             uint16
 	mssClampValue   uint16
 	mssClampEnabled bool
+
+	// Only one hook per protocol is supported. Outbound direction only.
+	udpHookOut atomic.Pointer[common.PacketHook]
+	tcpHookOut atomic.Pointer[common.PacketHook]
 }
 
 // decoder for packages
@@ -594,6 +598,8 @@ func (m *Manager) resetState() {
 	maps.Clear(m.incomingRules)
 	maps.Clear(m.routeRulesMap)
 	m.routeRules = m.routeRules[:0]
+	m.udpHookOut.Store(nil)
+	m.tcpHookOut.Store(nil)
 
 	if m.udpTracker != nil {
 		m.udpTracker.Close()
@@ -713,6 +719,9 @@ func (m *Manager) filterOutbound(packetData []byte, size int) bool {
 			return true
 		}
 	case layers.LayerTypeTCP:
+		if m.tcpHooksDrop(uint16(d.tcp.DstPort), dstIP, packetData) {
+			return true
+		}
 		// Clamp MSS on all TCP SYN packets, including those from local IPs.
 		// SNATed routed traffic may appear as local IP but still requires clamping.
 		if m.mssClampEnabled {
@@ -895,39 +904,12 @@ func (m *Manager) trackInbound(d *decoder, srcIP, dstIP netip.Addr, ruleID []byt
 	d.dnatOrigPort = 0
 }
 
-// udpHooksDrop checks if any UDP hooks should drop the packet
 func (m *Manager) udpHooksDrop(dport uint16, dstIP netip.Addr, packetData []byte) bool {
-	m.mutex.RLock()
-	defer m.mutex.RUnlock()
+	return common.HookMatches(m.udpHookOut.Load(), dstIP, dport, packetData)
+}
 
-	// Check specific destination IP first
-	if rules, exists := m.outgoingRules[dstIP]; exists {
-		for _, rule := range rules {
-			if rule.udpHook != nil && portsMatch(rule.dPort, dport) {
-				return rule.udpHook(packetData)
-			}
-		}
-	}
-
-	// Check IPv4 unspecified address
-	if rules, exists := m.outgoingRules[netip.IPv4Unspecified()]; exists {
-		for _, rule := range rules {
-			if rule.udpHook != nil && portsMatch(rule.dPort, dport) {
-				return rule.udpHook(packetData)
-			}
-		}
-	}
-
-	// Check IPv6 unspecified address
-	if rules, exists := m.outgoingRules[netip.IPv6Unspecified()]; exists {
-		for _, rule := range rules {
-			if rule.udpHook != nil && portsMatch(rule.dPort, dport) {
-				return rule.udpHook(packetData)
-			}
-		}
-	}
-
-	return false
+func (m *Manager) tcpHooksDrop(dport uint16, dstIP netip.Addr, packetData []byte) bool {
+	return common.HookMatches(m.tcpHookOut.Load(), dstIP, dport, packetData)
 }
 
 // filterInbound implements filtering logic for incoming packets.
@@ -1278,12 +1260,6 @@ func validateRule(ip netip.Addr, packetData []byte, rules map[string]PeerRule, d
 				return rule.mgmtId, rule.drop, true
 			}
 		case layers.LayerTypeUDP:
-			// if rule has UDP hook (and if we are here we match this rule)
-			// we ignore rule.drop and call this hook
-			if rule.udpHook != nil {
-				return rule.mgmtId, rule.udpHook(packetData), true
-			}
-
 			if portsMatch(rule.sPort, uint16(d.udp.SrcPort)) && portsMatch(rule.dPort, uint16(d.udp.DstPort)) {
 				return rule.mgmtId, rule.drop, true
 			}
@@ -1342,65 +1318,14 @@ func (m *Manager) ruleMatches(rule *RouteRule, srcAddr, dstAddr netip.Addr, prot
 	return sourceMatched
 }
 
-// AddUDPPacketHook calls hook when UDP packet from given direction matched
-//
-// Hook function returns flag which indicates should be the matched package dropped or not
-func (m *Manager) AddUDPPacketHook(in bool, ip netip.Addr, dPort uint16, hook func(packet []byte) bool) string {
-	r := PeerRule{
-		id:         uuid.New().String(),
-		ip:         ip,
-		protoLayer: layers.LayerTypeUDP,
-		dPort:      &firewall.Port{Values: []uint16{dPort}},
-		ipLayer:    layers.LayerTypeIPv6,
-		udpHook:    hook,
-	}
-
-	if ip.Is4() {
-		r.ipLayer = layers.LayerTypeIPv4
-	}
-
-	m.mutex.Lock()
-	if in {
-		// Incoming UDP hooks are stored in allow rules map
-		if _, ok := m.incomingRules[r.ip]; !ok {
-			m.incomingRules[r.ip] = make(map[string]PeerRule)
-		}
-		m.incomingRules[r.ip][r.id] = r
-	} else {
-		if _, ok := m.outgoingRules[r.ip]; !ok {
-			m.outgoingRules[r.ip] = make(map[string]PeerRule)
-		}
-		m.outgoingRules[r.ip][r.id] = r
-	}
-	m.mutex.Unlock()
-
-	return r.id
+// SetUDPPacketHook sets the outbound UDP packet hook. Pass nil hook to remove.
+func (m *Manager) SetUDPPacketHook(ip netip.Addr, dPort uint16, hook func(packet []byte) bool) {
+	common.SetHook(&m.udpHookOut, ip, dPort, hook)
 }
 
-// RemovePacketHook removes packet hook by given ID
-func (m *Manager) RemovePacketHook(hookID string) error {
-	m.mutex.Lock()
-	defer m.mutex.Unlock()
-
-	// Check incoming hooks (stored in allow rules)
-	for _, arr := range m.incomingRules {
-		for _, r := range arr {
-			if r.id == hookID {
-				delete(arr, r.id)
-				return nil
-			}
-		}
-	}
-	// Check outgoing hooks
-	for _, arr := range m.outgoingRules {
-		for _, r := range arr {
-			if r.id == hookID {
-				delete(arr, r.id)
-				return nil
-			}
-		}
-	}
-	return fmt.Errorf("hook with given id not found")
+// SetTCPPacketHook sets the outbound TCP packet hook. Pass nil hook to remove.
+func (m *Manager) SetTCPPacketHook(ip netip.Addr, dPort uint16, hook func(packet []byte) bool) {
+	common.SetHook(&m.tcpHookOut, ip, dPort, hook)
 }
 
 // SetLogLevel sets the log level for the firewall manager

client/firewall/uspfilter/filter_test.go

@@ -12,6 +12,7 @@ import (
 	"github.com/google/gopacket"
 	"github.com/google/gopacket/layers"
 	"github.com/sirupsen/logrus"
+	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	wgdevice "golang.zx2c4.com/wireguard/device"
 
@@ -186,81 +187,52 @@ func TestManagerDeleteRule(t *testing.T) {
 	}
 }
 
-func TestAddUDPPacketHook(t *testing.T) {
-	tests := []struct {
-		name       string
-		in         bool
-		expDir     fw.RuleDirection
-		ip         netip.Addr
-		dPort      uint16
-		hook       func([]byte) bool
-		expectedID string
-	}{
-		{
-			name:   "Test Outgoing UDP Packet Hook",
-			in:     false,
-			expDir: fw.RuleDirectionOUT,
-			ip:     netip.MustParseAddr("10.168.0.1"),
-			dPort:  8000,
-			hook:   func([]byte) bool { return true },
-		},
-		{
-			name:   "Test Incoming UDP Packet Hook",
-			in:     true,
-			expDir: fw.RuleDirectionIN,
-			ip:     netip.MustParseAddr("::1"),
-			dPort:  9000,
-			hook:   func([]byte) bool { return false },
-		},
-	}
+func TestSetUDPPacketHook(t *testing.T) {
+	manager, err := Create(&IFaceMock{
+		SetFilterFunc: func(device.PacketFilter) error { return nil },
+	}, false, flowLogger, nbiface.DefaultMTU)
+	require.NoError(t, err)
+	t.Cleanup(func() { require.NoError(t, manager.Close(nil)) })
 
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			manager, err := Create(&IFaceMock{
-				SetFilterFunc: func(device.PacketFilter) error { return nil },
-			}, false, flowLogger, nbiface.DefaultMTU)
-			require.NoError(t, err)
+	var called bool
+	manager.SetUDPPacketHook(netip.MustParseAddr("10.168.0.1"), 8000, func([]byte) bool {
+		called = true
+		return true
+	})
 
-			manager.AddUDPPacketHook(tt.in, tt.ip, tt.dPort, tt.hook)
+	h := manager.udpHookOut.Load()
+	require.NotNil(t, h)
+	assert.Equal(t, netip.MustParseAddr("10.168.0.1"), h.IP)
+	assert.Equal(t, uint16(8000), h.Port)
+	assert.True(t, h.Fn(nil))
+	assert.True(t, called)
 
-			var addedRule PeerRule
-			if tt.in {
-				// Incoming UDP hooks are stored in allow rules map
-				if len(manager.incomingRules[tt.ip]) != 1 {
-					t.Errorf("expected 1 incoming rule, got %d", len(manager.incomingRules[tt.ip]))
-					return
-				}
-				for _, rule := range manager.incomingRules[tt.ip] {
-					addedRule = rule
-				}
-			} else {
-				if len(manager.outgoingRules[tt.ip]) != 1 {
-					t.Errorf("expected 1 outgoing rule, got %d", len(manager.outgoingRules[tt.ip]))
-					return
-				}
-				for _, rule := range manager.outgoingRules[tt.ip] {
-					addedRule = rule
-				}
-			}
+	manager.SetUDPPacketHook(netip.MustParseAddr("10.168.0.1"), 8000, nil)
+	assert.Nil(t, manager.udpHookOut.Load())
+}
 
-			if tt.ip.Compare(addedRule.ip) != 0 {
-				t.Errorf("expected ip %s, got %s", tt.ip, addedRule.ip)
-				return
-			}
-			if tt.dPort != addedRule.dPort.Values[0] {
-				t.Errorf("expected dPort %d, got %d", tt.dPort, addedRule.dPort.Values[0])
-				return
-			}
-			if layers.LayerTypeUDP != addedRule.protoLayer {
-				t.Errorf("expected protoLayer %s, got %s", layers.LayerTypeUDP, addedRule.protoLayer)
-				return
-			}
-			if addedRule.udpHook == nil {
-				t.Errorf("expected udpHook to be set")
-				return
-			}
-		})
-	}
+func TestSetTCPPacketHook(t *testing.T) {
+	manager, err := Create(&IFaceMock{
+		SetFilterFunc: func(device.PacketFilter) error { return nil },
+	}, false, flowLogger, nbiface.DefaultMTU)
+	require.NoError(t, err)
+	t.Cleanup(func() { require.NoError(t, manager.Close(nil)) })
+
+	var called bool
+	manager.SetTCPPacketHook(netip.MustParseAddr("10.168.0.1"), 53, func([]byte) bool {
+		called = true
+		return true
+	})
+
+	h := manager.tcpHookOut.Load()
+	require.NotNil(t, h)
+	assert.Equal(t, netip.MustParseAddr("10.168.0.1"), h.IP)
+	assert.Equal(t, uint16(53), h.Port)
+	assert.True(t, h.Fn(nil))
+	assert.True(t, called)
+
+	manager.SetTCPPacketHook(netip.MustParseAddr("10.168.0.1"), 53, nil)
+	assert.Nil(t, manager.tcpHookOut.Load())
 }
 
 // TestPeerRuleLifecycleDenyRules verifies that deny rules are correctly added
@@ -530,39 +502,12 @@ func TestRemovePacketHook(t *testing.T) {
 		require.NoError(t, manager.Close(nil))
 	}()
 
-	// Add a UDP packet hook
-	hookFunc := func(data []byte) bool { return true }
-	hookID := manager.AddUDPPacketHook(false, netip.MustParseAddr("192.168.0.1"), 8080, hookFunc)
+	manager.SetUDPPacketHook(netip.MustParseAddr("192.168.0.1"), 8080, func([]byte) bool { return true })
 
-	// Assert the hook is added by finding it in the manager's outgoing rules
-	found := false
-	for _, arr := range manager.outgoingRules {
-		for _, rule := range arr {
-			if rule.id == hookID {
-				found = true
-				break
-			}
-		}
-	}
+	require.NotNil(t, manager.udpHookOut.Load(), "hook should be registered")
 
-	if !found {
-		t.Fatalf("The hook was not added properly.")
-	}
-
-	// Now remove the packet hook
-	err = manager.RemovePacketHook(hookID)
-	if err != nil {
-		t.Fatalf("Failed to remove hook: %s", err)
-	}
-
-	// Assert the hook is removed by checking it in the manager's outgoing rules
-	for _, arr := range manager.outgoingRules {
-		for _, rule := range arr {
-			if rule.id == hookID {
-				t.Fatalf("The hook was not removed properly.")
-			}
-		}
-	}
+	manager.SetUDPPacketHook(netip.MustParseAddr("192.168.0.1"), 8080, nil)
+	assert.Nil(t, manager.udpHookOut.Load(), "hook should be removed")
 }
 
 func TestProcessOutgoingHooks(t *testing.T) {
@@ -592,8 +537,7 @@ func TestProcessOutgoingHooks(t *testing.T) {
 	}
 
 	hookCalled := false
-	hookID := manager.AddUDPPacketHook(
-		false,
+	manager.SetUDPPacketHook(
 		netip.MustParseAddr("100.10.0.100"),
 		53,
 		func([]byte) bool {
@@ -601,7 +545,6 @@ func TestProcessOutgoingHooks(t *testing.T) {
 			return true
 		},
 	)
-	require.NotEmpty(t, hookID)
 
 	// Create test UDP packet
 	ipv4 := &layers.IPv4{

client/firewall/uspfilter/hooks_filter.go

@@ -0,0 +1,90 @@
+package uspfilter
+
+import (
+	"encoding/binary"
+	"net/netip"
+	"sync/atomic"
+
+	"github.com/netbirdio/netbird/client/firewall/uspfilter/common"
+	"github.com/netbirdio/netbird/client/iface/device"
+)
+
+const (
+	ipv4HeaderMinLen = 20
+	ipv4ProtoOffset  = 9
+	ipv4FlagsOffset  = 6
+	ipv4DstOffset    = 16
+	ipProtoUDP       = 17
+	ipProtoTCP       = 6
+	ipv4FragOffMask  = 0x1fff
+	// dstPortOffset is the offset of the destination port within a UDP or TCP header.
+	dstPortOffset = 2
+)
+
+// HooksFilter is a minimal packet filter that only handles outbound DNS hooks.
+// It is installed on the WireGuard interface when the userspace bind is active
+// but a full firewall filter (Manager) is not needed because a native kernel
+// firewall (nftables/iptables) handles packet filtering.
+type HooksFilter struct {
+	udpHook atomic.Pointer[common.PacketHook]
+	tcpHook atomic.Pointer[common.PacketHook]
+}
+
+var _ device.PacketFilter = (*HooksFilter)(nil)
+
+// FilterOutbound checks outbound packets for DNS hook matches.
+// Only IPv4 packets matching the registered hook IP:port are intercepted.
+// IPv6 and non-IP packets pass through unconditionally.
+func (f *HooksFilter) FilterOutbound(packetData []byte, _ int) bool {
+	if len(packetData) < ipv4HeaderMinLen {
+		return false
+	}
+
+	// Only process IPv4 packets, let everything else pass through.
+	if packetData[0]>>4 != 4 {
+		return false
+	}
+
+	ihl := int(packetData[0]&0x0f) * 4
+	if ihl < ipv4HeaderMinLen || len(packetData) < ihl+4 {
+		return false
+	}
+
+	// Skip non-first fragments: they don't carry L4 headers.
+	flagsAndOffset := binary.BigEndian.Uint16(packetData[ipv4FlagsOffset : ipv4FlagsOffset+2])
+	if flagsAndOffset&ipv4FragOffMask != 0 {
+		return false
+	}
+
+	dstIP, ok := netip.AddrFromSlice(packetData[ipv4DstOffset : ipv4DstOffset+4])
+	if !ok {
+		return false
+	}
+
+	proto := packetData[ipv4ProtoOffset]
+	dstPort := binary.BigEndian.Uint16(packetData[ihl+dstPortOffset : ihl+dstPortOffset+2])
+
+	switch proto {
+	case ipProtoUDP:
+		return common.HookMatches(f.udpHook.Load(), dstIP, dstPort, packetData)
+	case ipProtoTCP:
+		return common.HookMatches(f.tcpHook.Load(), dstIP, dstPort, packetData)
+	default:
+		return false
+	}
+}
+
+// FilterInbound allows all inbound packets (native firewall handles filtering).
+func (f *HooksFilter) FilterInbound([]byte, int) bool {
+	return false
+}
+
+// SetUDPPacketHook registers the UDP packet hook.
+func (f *HooksFilter) SetUDPPacketHook(ip netip.Addr, dPort uint16, hook func([]byte) bool) {
+	common.SetHook(&f.udpHook, ip, dPort, hook)
+}
+
+// SetTCPPacketHook registers the TCP packet hook.
+func (f *HooksFilter) SetTCPPacketHook(ip netip.Addr, dPort uint16, hook func([]byte) bool) {
+	common.SetHook(&f.tcpHook, ip, dPort, hook)
+}

client/firewall/uspfilter/localip.go

@@ -144,6 +144,8 @@ func (m *localIPManager) UpdateLocalIPs(iface common.IFaceMapper) (err error) {
 	if err != nil {
 		log.Warnf("failed to get interfaces: %v", err)
 	} else {
+		// TODO: filter out down interfaces (net.FlagUp). Also handle the reverse
+		// case where an interface comes up between refreshes.
 		for _, intf := range interfaces {
 			m.processInterface(intf, &newIPv4Bitmap, ipv4Set, &ipv4Addresses)
 		}

client/firewall/uspfilter/nat.go

@@ -421,6 +421,7 @@ func (m *Manager) addPortRedirection(targetIP netip.Addr, protocol gopacket.Laye
 }
 
 // AddInboundDNAT adds an inbound DNAT rule redirecting traffic from NetBird peers to local services.
+// TODO: also delegate to nativeFirewall when available for kernel WG mode
 func (m *Manager) AddInboundDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
 	var layerType gopacket.LayerType
 	switch protocol {
@@ -466,6 +467,22 @@ func (m *Manager) RemoveInboundDNAT(localAddr netip.Addr, protocol firewall.Prot
 	return m.removePortRedirection(localAddr, layerType, sourcePort, targetPort)
 }
 
+// AddOutputDNAT delegates to the native firewall if available.
+func (m *Manager) AddOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	if m.nativeFirewall == nil {
+		return fmt.Errorf("output DNAT not supported without native firewall")
+	}
+	return m.nativeFirewall.AddOutputDNAT(localAddr, protocol, sourcePort, targetPort)
+}
+
+// RemoveOutputDNAT delegates to the native firewall if available.
+func (m *Manager) RemoveOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error {
+	if m.nativeFirewall == nil {
+		return nil
+	}
+	return m.nativeFirewall.RemoveOutputDNAT(localAddr, protocol, sourcePort, targetPort)
+}
+
 // translateInboundPortDNAT applies port-specific DNAT translation to inbound packets.
 func (m *Manager) translateInboundPortDNAT(packetData []byte, d *decoder, srcIP, dstIP netip.Addr) bool {
 	if !m.portDNATEnabled.Load() {

client/firewall/uspfilter/rule.go

@@ -18,9 +18,7 @@ type PeerRule struct {
 	protoLayer gopacket.LayerType
 	sPort      *firewall.Port
 	dPort      *firewall.Port
-	drop       bool
-
-	udpHook func([]byte) bool
+	drop bool
 }
 
 // ID returns the rule id

client/firewall/uspfilter/tracer_test.go

@@ -399,21 +399,17 @@ func TestTracePacket(t *testing.T) {
 		{
 			name: "UDPTraffic_WithHook",
 			setup: func(m *Manager) {
-				hookFunc := func([]byte) bool {
-					return true
-				}
-				m.AddUDPPacketHook(true, netip.MustParseAddr("1.1.1.1"), 53, hookFunc)
+				m.SetUDPPacketHook(netip.MustParseAddr("100.10.255.254"), 53, func([]byte) bool {
+					return true // drop (intercepted by hook)
+				})
 			},
 			packetBuilder: func() *PacketBuilder {
-				return createPacketBuilder("1.1.1.1", "100.10.0.100", "udp", 12345, 53, fw.RuleDirectionIN)
+				return createPacketBuilder("100.10.0.100", "100.10.255.254", "udp", 12345, 53, fw.RuleDirectionOUT)
 			},
 			expectedStages: []PacketStage{
 				StageReceived,
-				StageInboundPortDNAT,
-				StageInbound1to1NAT,
-				StageConntrack,
-				StageRouting,
-				StagePeerACL,
+				StageOutbound1to1NAT,
+				StageOutboundPortReverse,
 				StageCompleted,
 			},
 			expectedAllow: false,

client/iface/device/device_filter.go

@@ -15,14 +15,17 @@ type PacketFilter interface {
 	// FilterInbound filter incoming packets from external sources to host
 	FilterInbound(packetData []byte, size int) bool
 
-	// AddUDPPacketHook calls hook when UDP packet from given direction matched
-	//
-	// Hook function returns flag which indicates should be the matched package dropped or not.
-	// Hook function receives raw network packet data as argument.
-	AddUDPPacketHook(in bool, ip netip.Addr, dPort uint16, hook func(packet []byte) bool) string
+	// SetUDPPacketHook registers a hook for outbound UDP packets matching the given IP and port.
+	// Hook function returns true if the packet should be dropped.
+	// Only one UDP hook is supported; calling again replaces the previous hook.
+	// Pass nil hook to remove.
+	SetUDPPacketHook(ip netip.Addr, dPort uint16, hook func(packet []byte) bool)
 
-	// RemovePacketHook removes hook by ID
-	RemovePacketHook(hookID string) error
+	// SetTCPPacketHook registers a hook for outbound TCP packets matching the given IP and port.
+	// Hook function returns true if the packet should be dropped.
+	// Only one TCP hook is supported; calling again replaces the previous hook.
+	// Pass nil hook to remove.
+	SetTCPPacketHook(ip netip.Addr, dPort uint16, hook func(packet []byte) bool)
 }
 
 // FilteredDevice to override Read or Write of packets

client/iface/mocks/filter.go

@@ -34,18 +34,28 @@ func (m *MockPacketFilter) EXPECT() *MockPacketFilterMockRecorder {
 	return m.recorder
 }
 
-// AddUDPPacketHook mocks base method.
-func (m *MockPacketFilter) AddUDPPacketHook(arg0 bool, arg1 netip.Addr, arg2 uint16, arg3 func([]byte) bool) string {
+// SetUDPPacketHook mocks base method.
+func (m *MockPacketFilter) SetUDPPacketHook(arg0 netip.Addr, arg1 uint16, arg2 func([]byte) bool) {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "AddUDPPacketHook", arg0, arg1, arg2, arg3)
-	ret0, _ := ret[0].(string)
-	return ret0
+	m.ctrl.Call(m, "SetUDPPacketHook", arg0, arg1, arg2)
 }
 
-// AddUDPPacketHook indicates an expected call of AddUDPPacketHook.
-func (mr *MockPacketFilterMockRecorder) AddUDPPacketHook(arg0, arg1, arg2, arg3 interface{}) *gomock.Call {
+// SetUDPPacketHook indicates an expected call of SetUDPPacketHook.
+func (mr *MockPacketFilterMockRecorder) SetUDPPacketHook(arg0, arg1, arg2 interface{}) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "AddUDPPacketHook", reflect.TypeOf((*MockPacketFilter)(nil).AddUDPPacketHook), arg0, arg1, arg2, arg3)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SetUDPPacketHook", reflect.TypeOf((*MockPacketFilter)(nil).SetUDPPacketHook), arg0, arg1, arg2)
+}
+
+// SetTCPPacketHook mocks base method.
+func (m *MockPacketFilter) SetTCPPacketHook(arg0 netip.Addr, arg1 uint16, arg2 func([]byte) bool) {
+	m.ctrl.T.Helper()
+	m.ctrl.Call(m, "SetTCPPacketHook", arg0, arg1, arg2)
+}
+
+// SetTCPPacketHook indicates an expected call of SetTCPPacketHook.
+func (mr *MockPacketFilterMockRecorder) SetTCPPacketHook(arg0, arg1, arg2 interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SetTCPPacketHook", reflect.TypeOf((*MockPacketFilter)(nil).SetTCPPacketHook), arg0, arg1, arg2)
 }
 
 // FilterInbound mocks base method.
@@ -75,17 +85,3 @@ func (mr *MockPacketFilterMockRecorder) FilterOutbound(arg0 interface{}, arg1 an
 	mr.mock.ctrl.T.Helper()
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "FilterOutbound", reflect.TypeOf((*MockPacketFilter)(nil).FilterOutbound), arg0, arg1)
 }
-
-// RemovePacketHook mocks base method.
-func (m *MockPacketFilter) RemovePacketHook(arg0 string) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "RemovePacketHook", arg0)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// RemovePacketHook indicates an expected call of RemovePacketHook.
-func (mr *MockPacketFilterMockRecorder) RemovePacketHook(arg0 interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "RemovePacketHook", reflect.TypeOf((*MockPacketFilter)(nil).RemovePacketHook), arg0)
-}

client/iface/mocks/iface/mocks/filter.go

@@ -1,87 +0,0 @@
-// Code generated by MockGen. DO NOT EDIT.
-// Source: github.com/netbirdio/netbird/client/iface (interfaces: PacketFilter)
-
-// Package mocks is a generated GoMock package.
-package mocks
-
-import (
-	net "net"
-	reflect "reflect"
-
-	gomock "github.com/golang/mock/gomock"
-)
-
-// MockPacketFilter is a mock of PacketFilter interface.
-type MockPacketFilter struct {
-	ctrl     *gomock.Controller
-	recorder *MockPacketFilterMockRecorder
-}
-
-// MockPacketFilterMockRecorder is the mock recorder for MockPacketFilter.
-type MockPacketFilterMockRecorder struct {
-	mock *MockPacketFilter
-}
-
-// NewMockPacketFilter creates a new mock instance.
-func NewMockPacketFilter(ctrl *gomock.Controller) *MockPacketFilter {
-	mock := &MockPacketFilter{ctrl: ctrl}
-	mock.recorder = &MockPacketFilterMockRecorder{mock}
-	return mock
-}
-
-// EXPECT returns an object that allows the caller to indicate expected use.
-func (m *MockPacketFilter) EXPECT() *MockPacketFilterMockRecorder {
-	return m.recorder
-}
-
-// AddUDPPacketHook mocks base method.
-func (m *MockPacketFilter) AddUDPPacketHook(arg0 bool, arg1 net.IP, arg2 uint16, arg3 func(*net.UDPAddr, []byte) bool) {
-	m.ctrl.T.Helper()
-	m.ctrl.Call(m, "AddUDPPacketHook", arg0, arg1, arg2, arg3)
-}
-
-// AddUDPPacketHook indicates an expected call of AddUDPPacketHook.
-func (mr *MockPacketFilterMockRecorder) AddUDPPacketHook(arg0, arg1, arg2, arg3 interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "AddUDPPacketHook", reflect.TypeOf((*MockPacketFilter)(nil).AddUDPPacketHook), arg0, arg1, arg2, arg3)
-}
-
-// FilterInbound mocks base method.
-func (m *MockPacketFilter) FilterInbound(arg0 []byte) bool {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "FilterInbound", arg0)
-	ret0, _ := ret[0].(bool)
-	return ret0
-}
-
-// FilterInbound indicates an expected call of FilterInbound.
-func (mr *MockPacketFilterMockRecorder) FilterInbound(arg0 interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "FilterInbound", reflect.TypeOf((*MockPacketFilter)(nil).FilterInbound), arg0)
-}
-
-// FilterOutbound mocks base method.
-func (m *MockPacketFilter) FilterOutbound(arg0 []byte) bool {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "FilterOutbound", arg0)
-	ret0, _ := ret[0].(bool)
-	return ret0
-}
-
-// FilterOutbound indicates an expected call of FilterOutbound.
-func (mr *MockPacketFilterMockRecorder) FilterOutbound(arg0 interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "FilterOutbound", reflect.TypeOf((*MockPacketFilter)(nil).FilterOutbound), arg0)
-}
-
-// SetNetwork mocks base method.
-func (m *MockPacketFilter) SetNetwork(arg0 *net.IPNet) {
-	m.ctrl.T.Helper()
-	m.ctrl.Call(m, "SetNetwork", arg0)
-}
-
-// SetNetwork indicates an expected call of SetNetwork.
-func (mr *MockPacketFilterMockRecorder) SetNetwork(arg0 interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SetNetwork", reflect.TypeOf((*MockPacketFilter)(nil).SetNetwork), arg0)
-}

client/internal/acl/manager_test.go

@@ -19,6 +19,9 @@ import (
 var flowLogger = netflow.NewManager(nil, []byte{}, nil).GetLogger()
 
 func TestDefaultManager(t *testing.T) {
+	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
+
 	networkMap := &mgmProto.NetworkMap{
 		FirewallRules: []*mgmProto.FirewallRule{
 			{
@@ -135,6 +138,7 @@ func TestDefaultManager(t *testing.T) {
 func TestDefaultManagerStateless(t *testing.T) {
 	// stateless currently only in userspace, so we have to disable kernel
 	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
 	t.Setenv("NB_DISABLE_CONNTRACK", "true")
 
 	networkMap := &mgmProto.NetworkMap{
@@ -194,6 +198,7 @@ func TestDefaultManagerStateless(t *testing.T) {
 // This tests the full ACL manager -> uspfilter integration.
 func TestDenyRulesNotAccumulatedOnRepeatedApply(t *testing.T) {
 	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
 
 	networkMap := &mgmProto.NetworkMap{
 		FirewallRules: []*mgmProto.FirewallRule{
@@ -258,6 +263,7 @@ func TestDenyRulesNotAccumulatedOnRepeatedApply(t *testing.T) {
 // up when they're removed from the network map in a subsequent update.
 func TestDenyRulesCleanedUpOnRemoval(t *testing.T) {
 	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
 
 	ctrl := gomock.NewController(t)
 	defer ctrl.Finish()
@@ -339,6 +345,7 @@ func TestDenyRulesCleanedUpOnRemoval(t *testing.T) {
 // one added without leaking.
 func TestRuleUpdateChangingAction(t *testing.T) {
 	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
 
 	ctrl := gomock.NewController(t)
 	defer ctrl.Finish()

client/internal/auth/auth.go

@@ -155,7 +155,7 @@ func (a *Auth) IsLoginRequired(ctx context.Context) (bool, error) {
 	var needsLogin bool
 
 	err = a.withRetry(ctx, func(client *mgm.GrpcClient) error {
-		_, _, err := a.doMgmLogin(client, ctx, pubSSHKey)
+		err := a.doMgmLogin(client, ctx, pubSSHKey)
 		if isLoginNeeded(err) {
 			needsLogin = true
 			return nil
@@ -179,8 +179,8 @@ func (a *Auth) Login(ctx context.Context, setupKey string, jwtToken string) (err
 	var isAuthError bool
 
 	err = a.withRetry(ctx, func(client *mgm.GrpcClient) error {
-		serverKey, _, err := a.doMgmLogin(client, ctx, pubSSHKey)
-		if serverKey != nil && isRegistrationNeeded(err) {
+		err := a.doMgmLogin(client, ctx, pubSSHKey)
+		if isRegistrationNeeded(err) {
 			log.Debugf("peer registration required")
 			_, err = a.registerPeer(client, ctx, setupKey, jwtToken, pubSSHKey)
 			if err != nil {
@@ -201,13 +201,7 @@ func (a *Auth) Login(ctx context.Context, setupKey string, jwtToken string) (err
 
 // 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)
+	protoFlow, err := client.GetPKCEAuthorizationFlow()
 	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)
@@ -246,13 +240,7 @@ func (a *Auth) getPKCEFlow(client *mgm.GrpcClient) (*PKCEAuthorizationFlow, erro
 
 // 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)
+	protoFlow, err := client.GetDeviceAuthorizationFlow()
 	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)
@@ -292,28 +280,16 @@ func (a *Auth) getDeviceFlow(client *mgm.GrpcClient) (*DeviceAuthorizationFlow,
 }
 
 // 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
-	}
-
+func (a *Auth) doMgmLogin(client *mgm.GrpcClient, ctx context.Context, pubSSHKey []byte) error {
 	sysInfo := system.GetInfo(ctx)
 	a.setSystemInfoFlags(sysInfo)
-	loginResp, err := client.Login(*serverKey, sysInfo, pubSSHKey, a.config.DNSLabels)
-	return serverKey, loginResp, err
+	_, err := client.Login(sysInfo, pubSSHKey, a.config.DNSLabels)
+	return 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)
@@ -322,7 +298,7 @@ func (a *Auth) registerPeer(client *mgm.GrpcClient, ctx context.Context, setupKe
 	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)
+	loginResp, err := client.Register(validSetupKey.String(), jwtToken, info, pubSSHKey, a.config.DNSLabels)
 	if err != nil {
 		log.Errorf("failed registering peer %v", err)
 		return nil, err

client/internal/connect.go

@@ -111,6 +111,7 @@ func (c *ConnectClient) RunOniOS(
 	fileDescriptor int32,
 	networkChangeListener listener.NetworkChangeListener,
 	dnsManager dns.IosDnsManager,
+	dnsAddresses []netip.AddrPort,
 	stateFilePath string,
 ) error {
 	// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
@@ -120,6 +121,7 @@ func (c *ConnectClient) RunOniOS(
 		FileDescriptor:        fileDescriptor,
 		NetworkChangeListener: networkChangeListener,
 		DnsManager:            dnsManager,
+		HostDNSAddresses:      dnsAddresses,
 		StateFilePath:         stateFilePath,
 	}
 	return c.run(mobileDependency, nil, "")
@@ -617,12 +619,6 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
 
 // loginToManagement creates Management ServiceDependencies client, establishes a connection, logs-in and gets a global Netbird config (signal, turn, stun hosts, etc)
 func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte, config *profilemanager.Config) (*mgmProto.LoginResponse, error) {
-
-	serverPublicKey, err := client.GetServerPublicKey()
-	if err != nil {
-		return nil, gstatus.Errorf(codes.FailedPrecondition, "failed while getting Management Service public key: %s", err)
-	}
-
 	sysInfo := system.GetInfo(ctx)
 	sysInfo.SetFlags(
 		config.RosenpassEnabled,
@@ -641,12 +637,7 @@ func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte,
 		config.EnableSSHRemotePortForwarding,
 		config.DisableSSHAuth,
 	)
-	loginResp, err := client.Login(*serverPublicKey, sysInfo, pubSSHKey, config.DNSLabels)
-	if err != nil {
-		return nil, err
-	}
-
-	return loginResp, nil
+	return client.Login(sysInfo, pubSSHKey, config.DNSLabels)
 }
 
 func statusRecorderToMgmConnStateNotifier(statusRecorder *peer.Status) mgm.ConnStateNotifier {

client/internal/debug/debug.go

@@ -25,6 +25,7 @@ import (
 	"google.golang.org/protobuf/encoding/protojson"
 
 	"github.com/netbirdio/netbird/client/anonymize"
+	"github.com/netbirdio/netbird/client/configs"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/updater/installer"
@@ -52,6 +53,7 @@ resolved_domains.txt: Anonymized resolved domain IP addresses from the status re
 config.txt: Anonymized configuration information of the NetBird client.
 network_map.json: Anonymized sync response containing peer configurations, routes, DNS settings, and firewall rules.
 state.json: Anonymized client state dump containing netbird states for the active profile.
+service_params.json: Sanitized service install parameters (service.json). Sensitive environment variable values are masked. Only present when service.json exists.
 metrics.txt: Buffered client metrics in InfluxDB line protocol format. Only present when metrics collection is enabled. Peer identifiers are anonymized.
 mutex.prof: Mutex profiling information.
 goroutine.prof: Goroutine profiling information.
@@ -359,6 +361,10 @@ func (g *BundleGenerator) createArchive() error {
 		log.Errorf("failed to add corrupted state files to debug bundle: %v", err)
 	}
 
+	if err := g.addServiceParams(); err != nil {
+		log.Errorf("failed to add service params to debug bundle: %v", err)
+	}
+
 	if err := g.addMetrics(); err != nil {
 		log.Errorf("failed to add metrics to debug bundle: %v", err)
 	}
@@ -488,6 +494,90 @@ func (g *BundleGenerator) addConfig() error {
 	return nil
 }
 
+const (
+	serviceParamsFile    = "service.json"
+	serviceParamsBundle  = "service_params.json"
+	maskedValue          = "***"
+	envVarPrefix         = "NB_"
+	jsonKeyManagementURL = "management_url"
+	jsonKeyServiceEnv    = "service_env_vars"
+)
+
+var sensitiveEnvSubstrings = []string{"key", "token", "secret", "password", "credential"}
+
+// addServiceParams reads the service.json file and adds a sanitized version to the bundle.
+// Non-NB_ env vars and vars with sensitive names are masked. Other NB_ values are anonymized.
+func (g *BundleGenerator) addServiceParams() error {
+	path := filepath.Join(configs.StateDir, serviceParamsFile)
+
+	data, err := os.ReadFile(path)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return nil
+		}
+		return fmt.Errorf("read service params: %w", err)
+	}
+
+	var params map[string]any
+	if err := json.Unmarshal(data, &params); err != nil {
+		return fmt.Errorf("parse service params: %w", err)
+	}
+
+	if g.anonymize {
+		if mgmtURL, ok := params[jsonKeyManagementURL].(string); ok && mgmtURL != "" {
+			params[jsonKeyManagementURL] = g.anonymizer.AnonymizeURI(mgmtURL)
+		}
+	}
+
+	g.sanitizeServiceEnvVars(params)
+
+	sanitizedData, err := json.MarshalIndent(params, "", "  ")
+	if err != nil {
+		return fmt.Errorf("marshal sanitized service params: %w", err)
+	}
+
+	if err := g.addFileToZip(bytes.NewReader(sanitizedData), serviceParamsBundle); err != nil {
+		return fmt.Errorf("add service params to zip: %w", err)
+	}
+
+	return nil
+}
+
+// sanitizeServiceEnvVars masks or anonymizes env var values in service params.
+// Non-NB_ vars and vars with sensitive names (key, token, etc.) are fully masked.
+// Other NB_ var values are passed through the anonymizer when anonymization is enabled.
+func (g *BundleGenerator) sanitizeServiceEnvVars(params map[string]any) {
+	envVars, ok := params[jsonKeyServiceEnv].(map[string]any)
+	if !ok {
+		return
+	}
+
+	sanitized := make(map[string]any, len(envVars))
+	for k, v := range envVars {
+		val, _ := v.(string)
+		switch {
+		case !strings.HasPrefix(k, envVarPrefix) || isSensitiveEnvVar(k):
+			sanitized[k] = maskedValue
+		case g.anonymize:
+			sanitized[k] = g.anonymizer.AnonymizeString(val)
+		default:
+			sanitized[k] = val
+		}
+	}
+	params[jsonKeyServiceEnv] = sanitized
+}
+
+// isSensitiveEnvVar returns true for env var names that may contain secrets.
+func isSensitiveEnvVar(key string) bool {
+	lower := strings.ToLower(key)
+	for _, s := range sensitiveEnvSubstrings {
+		if strings.Contains(lower, s) {
+			return true
+		}
+	}
+	return false
+}
+
 func (g *BundleGenerator) addCommonConfigFields(configContent *strings.Builder) {
 	configContent.WriteString("NetBird Client Configuration:\n\n")
 

client/internal/debug/debug_test.go

@@ -1,8 +1,12 @@
 package debug
 
 import (
+	"archive/zip"
+	"bytes"
 	"encoding/json"
 	"net"
+	"os"
+	"path/filepath"
 	"strings"
 	"testing"
 
@@ -10,6 +14,7 @@ import (
 	"github.com/stretchr/testify/require"
 
 	"github.com/netbirdio/netbird/client/anonymize"
+	"github.com/netbirdio/netbird/client/configs"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 )
 
@@ -420,6 +425,226 @@ func TestAnonymizeNetworkMap(t *testing.T) {
 	}
 }
 
+func TestIsSensitiveEnvVar(t *testing.T) {
+	tests := []struct {
+		key       string
+		sensitive bool
+	}{
+		{"NB_SETUP_KEY", true},
+		{"NB_API_TOKEN", true},
+		{"NB_CLIENT_SECRET", true},
+		{"NB_PASSWORD", true},
+		{"NB_CREDENTIAL", true},
+		{"NB_LOG_LEVEL", false},
+		{"NB_MANAGEMENT_URL", false},
+		{"NB_HOSTNAME", false},
+		{"HOME", false},
+		{"PATH", false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.key, func(t *testing.T) {
+			assert.Equal(t, tt.sensitive, isSensitiveEnvVar(tt.key))
+		})
+	}
+}
+
+func TestSanitizeServiceEnvVars(t *testing.T) {
+	tests := []struct {
+		name      string
+		anonymize bool
+		input     map[string]any
+		check     func(t *testing.T, params map[string]any)
+	}{
+		{
+			name:      "no env vars key",
+			anonymize: false,
+			input:     map[string]any{"management_url": "https://mgmt.example.com"},
+			check: func(t *testing.T, params map[string]any) {
+				t.Helper()
+				assert.Equal(t, "https://mgmt.example.com", params["management_url"], "non-env fields should be untouched")
+				_, ok := params[jsonKeyServiceEnv]
+				assert.False(t, ok, "service_env_vars should not be added")
+			},
+		},
+		{
+			name:      "non-NB vars are masked",
+			anonymize: false,
+			input: map[string]any{
+				jsonKeyServiceEnv: map[string]any{
+					"HOME":       "/root",
+					"PATH":       "/usr/bin",
+					"NB_LOG_LEVEL": "debug",
+				},
+			},
+			check: func(t *testing.T, params map[string]any) {
+				t.Helper()
+				env := params[jsonKeyServiceEnv].(map[string]any)
+				assert.Equal(t, maskedValue, env["HOME"], "non-NB_ var should be masked")
+				assert.Equal(t, maskedValue, env["PATH"], "non-NB_ var should be masked")
+				assert.Equal(t, "debug", env["NB_LOG_LEVEL"], "safe NB_ var should pass through")
+			},
+		},
+		{
+			name:      "sensitive NB vars are masked",
+			anonymize: false,
+			input: map[string]any{
+				jsonKeyServiceEnv: map[string]any{
+					"NB_SETUP_KEY":  "abc123",
+					"NB_API_TOKEN":  "tok_xyz",
+					"NB_LOG_LEVEL":  "info",
+				},
+			},
+			check: func(t *testing.T, params map[string]any) {
+				t.Helper()
+				env := params[jsonKeyServiceEnv].(map[string]any)
+				assert.Equal(t, maskedValue, env["NB_SETUP_KEY"], "sensitive NB_ var should be masked")
+				assert.Equal(t, maskedValue, env["NB_API_TOKEN"], "sensitive NB_ var should be masked")
+				assert.Equal(t, "info", env["NB_LOG_LEVEL"], "safe NB_ var should pass through")
+			},
+		},
+		{
+			name:      "safe NB vars anonymized when anonymize is true",
+			anonymize: true,
+			input: map[string]any{
+				jsonKeyServiceEnv: map[string]any{
+					"NB_MANAGEMENT_URL": "https://mgmt.example.com:443",
+					"NB_LOG_LEVEL":      "debug",
+					"NB_SETUP_KEY":      "secret",
+					"SOME_OTHER":        "val",
+				},
+			},
+			check: func(t *testing.T, params map[string]any) {
+				t.Helper()
+				env := params[jsonKeyServiceEnv].(map[string]any)
+				// Safe NB_ values should be anonymized (not the original, not masked)
+				mgmtVal := env["NB_MANAGEMENT_URL"].(string)
+				assert.NotEqual(t, "https://mgmt.example.com:443", mgmtVal, "should be anonymized")
+				assert.NotEqual(t, maskedValue, mgmtVal, "should not be masked")
+
+				logVal := env["NB_LOG_LEVEL"].(string)
+				assert.NotEqual(t, maskedValue, logVal, "safe NB_ var should not be masked")
+
+				// Sensitive and non-NB_ still masked
+				assert.Equal(t, maskedValue, env["NB_SETUP_KEY"])
+				assert.Equal(t, maskedValue, env["SOME_OTHER"])
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses())
+			g := &BundleGenerator{
+				anonymize:  tt.anonymize,
+				anonymizer: anonymizer,
+			}
+			g.sanitizeServiceEnvVars(tt.input)
+			tt.check(t, tt.input)
+		})
+	}
+}
+
+func TestAddServiceParams(t *testing.T) {
+	t.Run("missing service.json returns nil", func(t *testing.T) {
+		g := &BundleGenerator{
+			anonymizer: anonymize.NewAnonymizer(anonymize.DefaultAddresses()),
+		}
+
+		origStateDir := configs.StateDir
+		configs.StateDir = t.TempDir()
+		t.Cleanup(func() { configs.StateDir = origStateDir })
+
+		err := g.addServiceParams()
+		assert.NoError(t, err)
+	})
+
+	t.Run("management_url anonymized when anonymize is true", func(t *testing.T) {
+		dir := t.TempDir()
+		origStateDir := configs.StateDir
+		configs.StateDir = dir
+		t.Cleanup(func() { configs.StateDir = origStateDir })
+
+		input := map[string]any{
+			jsonKeyManagementURL: "https://api.example.com:443",
+			jsonKeyServiceEnv: map[string]any{
+				"NB_LOG_LEVEL": "trace",
+			},
+		}
+		data, err := json.Marshal(input)
+		require.NoError(t, err)
+		require.NoError(t, os.WriteFile(filepath.Join(dir, serviceParamsFile), data, 0600))
+
+		var buf bytes.Buffer
+		zw := zip.NewWriter(&buf)
+
+		g := &BundleGenerator{
+			anonymize:  true,
+			anonymizer: anonymize.NewAnonymizer(anonymize.DefaultAddresses()),
+			archive:    zw,
+		}
+
+		require.NoError(t, g.addServiceParams())
+		require.NoError(t, zw.Close())
+
+		zr, err := zip.NewReader(bytes.NewReader(buf.Bytes()), int64(buf.Len()))
+		require.NoError(t, err)
+		require.Len(t, zr.File, 1)
+		assert.Equal(t, serviceParamsBundle, zr.File[0].Name)
+
+		rc, err := zr.File[0].Open()
+		require.NoError(t, err)
+		defer rc.Close()
+
+		var result map[string]any
+		require.NoError(t, json.NewDecoder(rc).Decode(&result))
+
+		mgmt := result[jsonKeyManagementURL].(string)
+		assert.NotEqual(t, "https://api.example.com:443", mgmt, "management_url should be anonymized")
+		assert.NotEmpty(t, mgmt)
+
+		env := result[jsonKeyServiceEnv].(map[string]any)
+		assert.NotEqual(t, maskedValue, env["NB_LOG_LEVEL"], "safe NB_ var should not be masked")
+	})
+
+	t.Run("management_url preserved when anonymize is false", func(t *testing.T) {
+		dir := t.TempDir()
+		origStateDir := configs.StateDir
+		configs.StateDir = dir
+		t.Cleanup(func() { configs.StateDir = origStateDir })
+
+		input := map[string]any{
+			jsonKeyManagementURL: "https://api.example.com:443",
+		}
+		data, err := json.Marshal(input)
+		require.NoError(t, err)
+		require.NoError(t, os.WriteFile(filepath.Join(dir, serviceParamsFile), data, 0600))
+
+		var buf bytes.Buffer
+		zw := zip.NewWriter(&buf)
+
+		g := &BundleGenerator{
+			anonymize:  false,
+			anonymizer: anonymize.NewAnonymizer(anonymize.DefaultAddresses()),
+			archive:    zw,
+		}
+
+		require.NoError(t, g.addServiceParams())
+		require.NoError(t, zw.Close())
+
+		zr, err := zip.NewReader(bytes.NewReader(buf.Bytes()), int64(buf.Len()))
+		require.NoError(t, err)
+
+		rc, err := zr.File[0].Open()
+		require.NoError(t, err)
+		defer rc.Close()
+
+		var result map[string]any
+		require.NoError(t, json.NewDecoder(rc).Decode(&result))
+
+		assert.Equal(t, "https://api.example.com:443", result[jsonKeyManagementURL], "management_url should be preserved")
+	})
+}
+
 // Helper function to check if IP is in CGNAT range
 func isInCGNATRange(ip net.IP) bool {
 	cgnat := net.IPNet{

client/internal/dns/handler_chain.go

@@ -73,6 +73,9 @@ func (w *ResponseWriterChain) WriteMsg(m *dns.Msg) error {
 		return nil
 	}
 	w.response = m
+	if m.MsgHdr.Truncated {
+		w.SetMeta("truncated", "true")
+	}
 	return w.ResponseWriter.WriteMsg(m)
 }
 
@@ -195,10 +198,14 @@ func (c *HandlerChain) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 
 	startTime := time.Now()
 	requestID := resutil.GenerateRequestID()
-	logger := log.WithFields(log.Fields{
+	fields := log.Fields{
 		"request_id": requestID,
 		"dns_id":     fmt.Sprintf("%04x", r.Id),
-	})
+	}
+	if addr := w.RemoteAddr(); addr != nil {
+		fields["client"] = addr.String()
+	}
+	logger := log.WithFields(fields)
 
 	question := r.Question[0]
 	qname := strings.ToLower(question.Name)
@@ -261,9 +268,9 @@ func (c *HandlerChain) logResponse(logger *log.Entry, cw *ResponseWriterChain, q
 		meta += " " + k + "=" + v
 	}
 
-	logger.Tracef("response: domain=%s rcode=%s answers=%s%s took=%s",
+	logger.Tracef("response: domain=%s rcode=%s answers=%s size=%dB%s took=%s",
 		qname, dns.RcodeToString[cw.response.Rcode], resutil.FormatAnswers(cw.response.Answer),
-		meta, time.Since(startTime))
+		cw.response.Len(), meta, time.Since(startTime))
 }
 
 func (c *HandlerChain) isHandlerMatch(qname string, entry HandlerEntry) bool {

client/internal/dns/local/local_test.go

@@ -1263,9 +1263,9 @@ func TestLocalResolver_AuthoritativeFlag(t *testing.T) {
 	})
 }
 
-// TestLocalResolver_Stop tests cleanup on Stop
+// TestLocalResolver_Stop tests cleanup on GracefullyStop
 func TestLocalResolver_Stop(t *testing.T) {
-	t.Run("Stop clears all state", func(t *testing.T) {
+	t.Run("GracefullyStop clears all state", func(t *testing.T) {
 		resolver := NewResolver()
 		resolver.Update([]nbdns.CustomZone{{
 			Domain: "example.com.",
@@ -1285,7 +1285,7 @@ func TestLocalResolver_Stop(t *testing.T) {
 		assert.False(t, resolver.isInManagedZone("host.example.com."))
 	})
 
-	t.Run("Stop is safe to call multiple times", func(t *testing.T) {
+	t.Run("GracefullyStop is safe to call multiple times", func(t *testing.T) {
 		resolver := NewResolver()
 		resolver.Update([]nbdns.CustomZone{{
 			Domain: "example.com.",
@@ -1299,7 +1299,7 @@ func TestLocalResolver_Stop(t *testing.T) {
 		resolver.Stop()
 	})
 
-	t.Run("Stop cancels in-flight external resolution", func(t *testing.T) {
+	t.Run("GracefullyStop cancels in-flight external resolution", func(t *testing.T) {
 		resolver := NewResolver()
 
 		lookupStarted := make(chan struct{})

client/internal/dns/mock_server.go

@@ -90,6 +90,11 @@ func (m *MockServer) SetRouteChecker(func(netip.Addr) bool) {
 	// Mock implementation - no-op
 }
 
+// SetFirewall mock implementation of SetFirewall from Server interface
+func (m *MockServer) SetFirewall(Firewall) {
+	// Mock implementation - no-op
+}
+
 // BeginBatch mock implementation of BeginBatch from Server interface
 func (m *MockServer) BeginBatch() {
 	// Mock implementation - no-op

client/internal/dns/response_writer.go

@@ -104,3 +104,23 @@ func (r *responseWriter) TsigTimersOnly(bool) {
 // After a call to Hijack(), the DNS package will not do anything with the connection.
 func (r *responseWriter) Hijack() {
 }
+
+// remoteAddrFromPacket extracts the source IP:port from a decoded packet for logging.
+func remoteAddrFromPacket(packet gopacket.Packet) *net.UDPAddr {
+	var srcIP net.IP
+	if ipv4 := packet.Layer(layers.LayerTypeIPv4); ipv4 != nil {
+		srcIP = ipv4.(*layers.IPv4).SrcIP
+	} else if ipv6 := packet.Layer(layers.LayerTypeIPv6); ipv6 != nil {
+		srcIP = ipv6.(*layers.IPv6).SrcIP
+	}
+
+	var srcPort int
+	if udp := packet.Layer(layers.LayerTypeUDP); udp != nil {
+		srcPort = int(udp.(*layers.UDP).SrcPort)
+	}
+
+	if srcIP == nil {
+		return nil
+	}
+	return &net.UDPAddr{IP: srcIP, Port: srcPort}
+}

client/internal/dns/server.go

@@ -58,6 +58,7 @@ type Server interface {
 	UpdateServerConfig(domains dnsconfig.ServerDomains) error
 	PopulateManagementDomain(mgmtURL *url.URL) error
 	SetRouteChecker(func(netip.Addr) bool)
+	SetFirewall(Firewall)
 }
 
 type nsGroupsByDomain struct {
@@ -151,7 +152,7 @@ func NewDefaultServer(ctx context.Context, config DefaultServerConfig) (*Default
 	if config.WgInterface.IsUserspaceBind() {
 		dnsService = NewServiceViaMemory(config.WgInterface)
 	} else {
-		dnsService = newServiceViaListener(config.WgInterface, addrPort)
+		dnsService = newServiceViaListener(config.WgInterface, addrPort, nil)
 	}
 
 	server := newDefaultServer(ctx, config.WgInterface, dnsService, config.StatusRecorder, config.StateManager, config.DisableSys)
@@ -186,11 +187,16 @@ func NewDefaultServerIos(
 	ctx context.Context,
 	wgInterface WGIface,
 	iosDnsManager IosDnsManager,
+	hostsDnsList []netip.AddrPort,
 	statusRecorder *peer.Status,
 	disableSys bool,
 ) *DefaultServer {
+	log.Debugf("iOS host dns address list is: %v", hostsDnsList)
 	ds := newDefaultServer(ctx, wgInterface, NewServiceViaMemory(wgInterface), statusRecorder, nil, disableSys)
 	ds.iosDnsManager = iosDnsManager
+	ds.hostsDNSHolder.set(hostsDnsList)
+	ds.permanent = true
+	ds.addHostRootZone()
 	return ds
 }
 
@@ -374,6 +380,17 @@ func (s *DefaultServer) DnsIP() netip.Addr {
 	return s.service.RuntimeIP()
 }
 
+// SetFirewall sets the firewall used for DNS port DNAT rules.
+// This must be called before Initialize when using the listener-based service,
+// because the firewall is typically not available at construction time.
+func (s *DefaultServer) SetFirewall(fw Firewall) {
+	if svc, ok := s.service.(*serviceViaListener); ok {
+		svc.listenerFlagLock.Lock()
+		svc.firewall = fw
+		svc.listenerFlagLock.Unlock()
+	}
+}
+
 // Stop stops the server
 func (s *DefaultServer) Stop() {
 	s.probeMu.Lock()
@@ -395,8 +412,12 @@ func (s *DefaultServer) Stop() {
 	maps.Clear(s.extraDomains)
 }
 
-func (s *DefaultServer) disableDNS() error {
-	defer s.service.Stop()
+func (s *DefaultServer) disableDNS() (retErr error) {
+	defer func() {
+		if err := s.service.Stop(); err != nil {
+			retErr = errors.Join(retErr, fmt.Errorf("stop DNS service: %w", err))
+		}
+	}()
 
 	if s.isUsingNoopHostManager() {
 		return nil

client/internal/dns/server_test.go

@@ -476,8 +476,8 @@ func TestDNSFakeResolverHandleUpdates(t *testing.T) {
 
 	packetfilter := pfmock.NewMockPacketFilter(ctrl)
 	packetfilter.EXPECT().FilterOutbound(gomock.Any(), gomock.Any()).AnyTimes()
-	packetfilter.EXPECT().AddUDPPacketHook(gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any())
-	packetfilter.EXPECT().RemovePacketHook(gomock.Any())
+	packetfilter.EXPECT().SetUDPPacketHook(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
+	packetfilter.EXPECT().SetTCPPacketHook(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
 
 	if err := wgIface.SetFilter(packetfilter); err != nil {
 		t.Errorf("set packet filter: %v", err)
@@ -1071,7 +1071,7 @@ func (m *mockHandler) ID() types.HandlerID                   { return types.Hand
 type mockService struct{}
 
 func (m *mockService) Listen() error                   { return nil }
-func (m *mockService) Stop()                           {}
+func (m *mockService) Stop() error                     { return nil }
 func (m *mockService) RuntimeIP() netip.Addr           { return netip.MustParseAddr("127.0.0.1") }
 func (m *mockService) RuntimePort() int                { return 53 }
 func (m *mockService) RegisterMux(string, dns.Handler) {}

client/internal/dns/service.go

@@ -4,15 +4,25 @@ import (
 	"net/netip"
 
 	"github.com/miekg/dns"
+
+	firewall "github.com/netbirdio/netbird/client/firewall/manager"
 )
 
 const (
 	DefaultPort = 53
 )
 
+// Firewall provides DNAT capabilities for DNS port redirection.
+// This is used when the DNS server cannot bind port 53 directly
+// and needs firewall rules to redirect traffic.
+type Firewall interface {
+	AddOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error
+	RemoveOutputDNAT(localAddr netip.Addr, protocol firewall.Protocol, sourcePort, targetPort uint16) error
+}
+
 type service interface {
 	Listen() error
-	Stop()
+	Stop() error
 	RegisterMux(domain string, handler dns.Handler)
 	DeregisterMux(key string)
 	RuntimePort() int

client/internal/dns/service_listener.go

@@ -10,9 +10,13 @@ import (
 	"sync"
 	"time"
 
+	"github.com/hashicorp/go-multierror"
 	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
 
+	nberrors "github.com/netbirdio/netbird/client/errors"
+
+	firewall "github.com/netbirdio/netbird/client/firewall/manager"
 	"github.com/netbirdio/netbird/client/internal/ebpf"
 	ebpfMgr "github.com/netbirdio/netbird/client/internal/ebpf/manager"
 )
@@ -31,25 +35,33 @@ type serviceViaListener struct {
 	dnsMux            *dns.ServeMux
 	customAddr        *netip.AddrPort
 	server            *dns.Server
+	tcpServer         *dns.Server
 	listenIP          netip.Addr
 	listenPort        uint16
 	listenerIsRunning bool
 	listenerFlagLock  sync.Mutex
 	ebpfService       ebpfMgr.Manager
+	firewall          Firewall
+	tcpDNATConfigured bool
 }
 
-func newServiceViaListener(wgIface WGIface, customAddr *netip.AddrPort) *serviceViaListener {
+func newServiceViaListener(wgIface WGIface, customAddr *netip.AddrPort, fw Firewall) *serviceViaListener {
 	mux := dns.NewServeMux()
 
 	s := &serviceViaListener{
 		wgInterface: wgIface,
 		dnsMux:      mux,
 		customAddr:  customAddr,
+		firewall:    fw,
 		server: &dns.Server{
 			Net:     "udp",
 			Handler: mux,
 			UDPSize: 65535,
 		},
+		tcpServer: &dns.Server{
+			Net:     "tcp",
+			Handler: mux,
+		},
 	}
 
 	return s
@@ -70,43 +82,86 @@ func (s *serviceViaListener) Listen() error {
 		return fmt.Errorf("eval listen address: %w", err)
 	}
 	s.listenIP = s.listenIP.Unmap()
-	s.server.Addr = net.JoinHostPort(s.listenIP.String(), strconv.Itoa(int(s.listenPort)))
-	log.Debugf("starting dns on %s", s.server.Addr)
-	go func() {
-		s.setListenerStatus(true)
-		defer s.setListenerStatus(false)
+	addr := net.JoinHostPort(s.listenIP.String(), strconv.Itoa(int(s.listenPort)))
+	s.server.Addr = addr
+	s.tcpServer.Addr = addr
 
-		err := s.server.ListenAndServe()
-		if err != nil {
-			log.Errorf("dns server running with %d port returned an error: %v. Will not retry", s.listenPort, err)
+	log.Debugf("starting dns on %s (UDP + TCP)", addr)
+	s.listenerIsRunning = true
+
+	go func() {
+		if err := s.server.ListenAndServe(); err != nil {
+			log.Errorf("failed to run DNS UDP server on port %d: %v", s.listenPort, err)
+		}
+
+		s.listenerFlagLock.Lock()
+		unexpected := s.listenerIsRunning
+		s.listenerIsRunning = false
+		s.listenerFlagLock.Unlock()
+
+		if unexpected {
+			if err := s.tcpServer.Shutdown(); err != nil {
+				log.Debugf("failed to shutdown DNS TCP server: %v", err)
+			}
 		}
 	}()
 
+	go func() {
+		if err := s.tcpServer.ListenAndServe(); err != nil {
+			log.Errorf("failed to run DNS TCP server on port %d: %v", s.listenPort, err)
+		}
+	}()
+
+	// When eBPF redirects UDP port 53 to our listen port, TCP still needs
+	// a DNAT rule because eBPF only handles UDP.
+	if s.ebpfService != nil && s.firewall != nil && s.listenPort != DefaultPort {
+		if err := s.firewall.AddOutputDNAT(s.listenIP, firewall.ProtocolTCP, DefaultPort, s.listenPort); err != nil {
+			log.Warnf("failed to add DNS TCP DNAT rule, TCP DNS on port 53 will not work: %v", err)
+		} else {
+			s.tcpDNATConfigured = true
+			log.Infof("added DNS TCP DNAT rule: %s:%d -> %s:%d", s.listenIP, DefaultPort, s.listenIP, s.listenPort)
+		}
+	}
+
 	return nil
 }
 
-func (s *serviceViaListener) Stop() {
+func (s *serviceViaListener) Stop() error {
 	s.listenerFlagLock.Lock()
 	defer s.listenerFlagLock.Unlock()
 
 	if !s.listenerIsRunning {
-		return
+		return nil
 	}
+	s.listenerIsRunning = false
 
 	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 	defer cancel()
 
-	err := s.server.ShutdownContext(ctx)
-	if err != nil {
-		log.Errorf("stopping dns server listener returned an error: %v", err)
+	var merr *multierror.Error
+
+	if err := s.server.ShutdownContext(ctx); err != nil {
+		merr = multierror.Append(merr, fmt.Errorf("stop DNS UDP server: %w", err))
+	}
+
+	if err := s.tcpServer.ShutdownContext(ctx); err != nil {
+		merr = multierror.Append(merr, fmt.Errorf("stop DNS TCP server: %w", err))
+	}
+
+	if s.tcpDNATConfigured && s.firewall != nil {
+		if err := s.firewall.RemoveOutputDNAT(s.listenIP, firewall.ProtocolTCP, DefaultPort, s.listenPort); err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("remove DNS TCP DNAT rule: %w", err))
+		}
+		s.tcpDNATConfigured = false
 	}
 
 	if s.ebpfService != nil {
-		err = s.ebpfService.FreeDNSFwd()
-		if err != nil {
-			log.Errorf("stopping traffic forwarder returned an error: %v", err)
+		if err := s.ebpfService.FreeDNSFwd(); err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("stop traffic forwarder: %w", err))
 		}
 	}
+
+	return nberrors.FormatErrorOrNil(merr)
 }
 
 func (s *serviceViaListener) RegisterMux(pattern string, handler dns.Handler) {
@@ -133,12 +188,6 @@ func (s *serviceViaListener) RuntimeIP() netip.Addr {
 	return s.listenIP
 }
 
-func (s *serviceViaListener) setListenerStatus(running bool) {
-	s.listenerFlagLock.Lock()
-	defer s.listenerFlagLock.Unlock()
-
-	s.listenerIsRunning = running
-}
 
 // evalListenAddress figure out the listen address for the DNS server
 // first check the 53 port availability on WG interface or lo, if not success
@@ -187,18 +236,28 @@ func (s *serviceViaListener) testFreePort(port int) (netip.Addr, bool) {
 }
 
 func (s *serviceViaListener) tryToBind(ip netip.Addr, port int) bool {
-	addrString := net.JoinHostPort(ip.String(), strconv.Itoa(port))
-	udpAddr := net.UDPAddrFromAddrPort(netip.MustParseAddrPort(addrString))
-	probeListener, err := net.ListenUDP("udp", udpAddr)
+	addrPort := netip.AddrPortFrom(ip, uint16(port))
+
+	udpAddr := net.UDPAddrFromAddrPort(addrPort)
+	udpLn, err := net.ListenUDP("udp", udpAddr)
 	if err != nil {
-		log.Warnf("binding dns on %s is not available, error: %s", addrString, err)
+		log.Warnf("binding dns UDP on %s is not available: %s", addrPort, err)
 		return false
 	}
-
-	err = probeListener.Close()
-	if err != nil {
-		log.Errorf("got an error closing the probe listener, error: %s", err)
+	if err := udpLn.Close(); err != nil {
+		log.Debugf("close UDP probe listener: %s", err)
 	}
+
+	tcpAddr := net.TCPAddrFromAddrPort(addrPort)
+	tcpLn, err := net.ListenTCP("tcp", tcpAddr)
+	if err != nil {
+		log.Warnf("binding dns TCP on %s is not available: %s", addrPort, err)
+		return false
+	}
+	if err := tcpLn.Close(); err != nil {
+		log.Debugf("close TCP probe listener: %s", err)
+	}
+
 	return true
 }
 

client/internal/dns/service_listener_test.go

@@ -0,0 +1,86 @@
+package dns
+
+import (
+	"fmt"
+	"net"
+	"net/netip"
+	"testing"
+	"time"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestServiceViaListener_TCPAndUDP(t *testing.T) {
+	handler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
+		m := new(dns.Msg)
+		m.SetReply(r)
+		m.Answer = append(m.Answer, &dns.A{
+			Hdr: dns.RR_Header{Name: r.Question[0].Name, Rrtype: dns.TypeA, Class: dns.ClassINET, Ttl: 60},
+			A:   net.ParseIP("192.0.2.1"),
+		})
+		if err := w.WriteMsg(m); err != nil {
+			t.Logf("write msg: %v", err)
+		}
+	})
+
+	// Create a service using a custom address to avoid needing root
+	svc := newServiceViaListener(nil, nil, nil)
+	svc.dnsMux.Handle(".", handler)
+
+	// Bind both transports up front to avoid TOCTOU races.
+	udpAddr := net.UDPAddrFromAddrPort(netip.AddrPortFrom(customIP, 0))
+	udpConn, err := net.ListenUDP("udp", udpAddr)
+	if err != nil {
+		t.Skip("cannot bind to 127.0.0.153, skipping")
+	}
+	port := uint16(udpConn.LocalAddr().(*net.UDPAddr).Port)
+
+	tcpAddr := net.TCPAddrFromAddrPort(netip.AddrPortFrom(customIP, port))
+	tcpLn, err := net.ListenTCP("tcp", tcpAddr)
+	if err != nil {
+		udpConn.Close()
+		t.Skip("cannot bind TCP on same port, skipping")
+	}
+
+	addr := fmt.Sprintf("%s:%d", customIP, port)
+	svc.server.PacketConn = udpConn
+	svc.tcpServer.Listener = tcpLn
+	svc.listenIP = customIP
+	svc.listenPort = port
+
+	go func() {
+		if err := svc.server.ActivateAndServe(); err != nil {
+			t.Logf("udp server: %v", err)
+		}
+	}()
+	go func() {
+		if err := svc.tcpServer.ActivateAndServe(); err != nil {
+			t.Logf("tcp server: %v", err)
+		}
+	}()
+	svc.listenerIsRunning = true
+
+	defer func() {
+		require.NoError(t, svc.Stop())
+	}()
+
+	q := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+
+	// Test UDP query
+	udpClient := &dns.Client{Net: "udp", Timeout: 2 * time.Second}
+	udpResp, _, err := udpClient.Exchange(q, addr)
+	require.NoError(t, err, "UDP query should succeed")
+	require.NotNil(t, udpResp)
+	require.NotEmpty(t, udpResp.Answer)
+	assert.Contains(t, udpResp.Answer[0].String(), "192.0.2.1", "UDP response should contain expected IP")
+
+	// Test TCP query
+	tcpClient := &dns.Client{Net: "tcp", Timeout: 2 * time.Second}
+	tcpResp, _, err := tcpClient.Exchange(q, addr)
+	require.NoError(t, err, "TCP query should succeed")
+	require.NotNil(t, tcpResp)
+	require.NotEmpty(t, tcpResp.Answer)
+	assert.Contains(t, tcpResp.Answer[0].String(), "192.0.2.1", "TCP response should contain expected IP")
+}

client/internal/dns/service_memory.go

@@ -1,6 +1,7 @@
 package dns
 
 import (
+	"errors"
 	"fmt"
 	"net/netip"
 	"sync"
@@ -10,6 +11,7 @@ import (
 	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/client/iface"
 	nbnet "github.com/netbirdio/netbird/client/net"
 )
 
@@ -18,7 +20,8 @@ type ServiceViaMemory struct {
 	dnsMux            *dns.ServeMux
 	runtimeIP         netip.Addr
 	runtimePort       int
-	udpFilterHookID   string
+	tcpDNS            *tcpDNSServer
+	tcpHookSet        bool
 	listenerIsRunning bool
 	listenerFlagLock  sync.Mutex
 }
@@ -28,14 +31,13 @@ func NewServiceViaMemory(wgIface WGIface) *ServiceViaMemory {
 	if err != nil {
 		log.Errorf("get last ip from network: %v", err)
 	}
-	s := &ServiceViaMemory{
+
+	return &ServiceViaMemory{
 		wgInterface: wgIface,
 		dnsMux:      dns.NewServeMux(),
-
 		runtimeIP:   lastIP,
 		runtimePort: DefaultPort,
 	}
-	return s
 }
 
 func (s *ServiceViaMemory) Listen() error {
@@ -46,10 +48,8 @@ func (s *ServiceViaMemory) Listen() error {
 		return nil
 	}
 
-	var err error
-	s.udpFilterHookID, err = s.filterDNSTraffic()
-	if err != nil {
-		return fmt.Errorf("filter dns traffice: %w", err)
+	if err := s.filterDNSTraffic(); err != nil {
+		return fmt.Errorf("filter dns traffic: %w", err)
 	}
 	s.listenerIsRunning = true
 
@@ -57,19 +57,29 @@ func (s *ServiceViaMemory) Listen() error {
 	return nil
 }
 
-func (s *ServiceViaMemory) Stop() {
+func (s *ServiceViaMemory) Stop() error {
 	s.listenerFlagLock.Lock()
 	defer s.listenerFlagLock.Unlock()
 
 	if !s.listenerIsRunning {
-		return
+		return nil
 	}
 
-	if err := s.wgInterface.GetFilter().RemovePacketHook(s.udpFilterHookID); err != nil {
-		log.Errorf("unable to remove DNS packet hook: %s", err)
+	filter := s.wgInterface.GetFilter()
+	if filter != nil {
+		filter.SetUDPPacketHook(s.runtimeIP, uint16(s.runtimePort), nil)
+		if s.tcpHookSet {
+			filter.SetTCPPacketHook(s.runtimeIP, uint16(s.runtimePort), nil)
+		}
+	}
+
+	if s.tcpDNS != nil {
+		s.tcpDNS.Stop()
 	}
 
 	s.listenerIsRunning = false
+
+	return nil
 }
 
 func (s *ServiceViaMemory) RegisterMux(pattern string, handler dns.Handler) {
@@ -88,10 +98,18 @@ func (s *ServiceViaMemory) RuntimeIP() netip.Addr {
 	return s.runtimeIP
 }
 
-func (s *ServiceViaMemory) filterDNSTraffic() (string, error) {
+func (s *ServiceViaMemory) filterDNSTraffic() error {
 	filter := s.wgInterface.GetFilter()
 	if filter == nil {
-		return "", fmt.Errorf("can't set DNS filter, filter not initialized")
+		return errors.New("DNS filter not initialized")
+	}
+
+	// Create TCP DNS server lazily here since the device may not exist at construction time.
+	if s.tcpDNS == nil {
+		if dev := s.wgInterface.GetDevice(); dev != nil {
+			// MTU only affects TCP segment sizing; DNS messages are small so this has no practical impact.
+			s.tcpDNS = newTCPDNSServer(s.dnsMux, dev.Device, s.runtimeIP, uint16(s.runtimePort), iface.DefaultMTU)
+		}
 	}
 
 	firstLayerDecoder := layers.LayerTypeIPv4
@@ -100,12 +118,16 @@ func (s *ServiceViaMemory) filterDNSTraffic() (string, error) {
 	}
 
 	hook := func(packetData []byte) bool {
-		// Decode the packet
 		packet := gopacket.NewPacket(packetData, firstLayerDecoder, gopacket.Default)
 
-		// Get the UDP layer
 		udpLayer := packet.Layer(layers.LayerTypeUDP)
-		udp := udpLayer.(*layers.UDP)
+		if udpLayer == nil {
+			return true
+		}
+		udp, ok := udpLayer.(*layers.UDP)
+		if !ok {
+			return true
+		}
 
 		msg := new(dns.Msg)
 		if err := msg.Unpack(udp.Payload); err != nil {
@@ -113,13 +135,30 @@ func (s *ServiceViaMemory) filterDNSTraffic() (string, error) {
 			return true
 		}
 
-		writer := responseWriter{
-			packet: packet,
-			device: s.wgInterface.GetDevice().Device,
+		dev := s.wgInterface.GetDevice()
+		if dev == nil {
+			return true
 		}
-		go s.dnsMux.ServeDNS(&writer, msg)
+
+		writer := &responseWriter{
+			remote: remoteAddrFromPacket(packet),
+			packet: packet,
+			device: dev.Device,
+		}
+		go s.dnsMux.ServeDNS(writer, msg)
 		return true
 	}
 
-	return filter.AddUDPPacketHook(false, s.runtimeIP, uint16(s.runtimePort), hook), nil
+	filter.SetUDPPacketHook(s.runtimeIP, uint16(s.runtimePort), hook)
+
+	if s.tcpDNS != nil {
+		tcpHook := func(packetData []byte) bool {
+			s.tcpDNS.InjectPacket(packetData)
+			return true
+		}
+		filter.SetTCPPacketHook(s.runtimeIP, uint16(s.runtimePort), tcpHook)
+		s.tcpHookSet = true
+	}
+
+	return nil
 }

client/internal/dns/tcpstack.go

@@ -0,0 +1,444 @@
+package dns
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"net/netip"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	"github.com/miekg/dns"
+	log "github.com/sirupsen/logrus"
+	"golang.zx2c4.com/wireguard/tun"
+	"gvisor.dev/gvisor/pkg/buffer"
+	"gvisor.dev/gvisor/pkg/tcpip"
+	"gvisor.dev/gvisor/pkg/tcpip/adapters/gonet"
+	"gvisor.dev/gvisor/pkg/tcpip/header"
+	"gvisor.dev/gvisor/pkg/tcpip/network/ipv4"
+	"gvisor.dev/gvisor/pkg/tcpip/stack"
+	"gvisor.dev/gvisor/pkg/tcpip/transport/tcp"
+	"gvisor.dev/gvisor/pkg/waiter"
+)
+
+const (
+	dnsTCPReceiveWindow = 8192
+	dnsTCPMaxInFlight   = 16
+	dnsTCPIdleTimeout   = 30 * time.Second
+	dnsTCPReadTimeout   = 5 * time.Second
+)
+
+// tcpDNSServer is an on-demand TCP DNS server backed by a minimal gvisor stack.
+// It is started lazily when a truncated DNS response is detected and shuts down
+// after a period of inactivity to conserve resources.
+type tcpDNSServer struct {
+	mu     sync.Mutex
+	s      *stack.Stack
+	ep     *dnsEndpoint
+	mux    *dns.ServeMux
+	tunDev tun.Device
+	ip     netip.Addr
+	port   uint16
+	mtu    uint16
+
+	running bool
+	closed  bool
+	timerID uint64
+	timer   *time.Timer
+}
+
+func newTCPDNSServer(mux *dns.ServeMux, tunDev tun.Device, ip netip.Addr, port uint16, mtu uint16) *tcpDNSServer {
+	return &tcpDNSServer{
+		mux:    mux,
+		tunDev: tunDev,
+		ip:     ip,
+		port:   port,
+		mtu:    mtu,
+	}
+}
+
+// InjectPacket ensures the stack is running and delivers a raw IP packet into
+// the gvisor stack for TCP processing. Combining both operations under a single
+// lock prevents a race where the idle timer could stop the stack between
+// start and delivery.
+func (t *tcpDNSServer) InjectPacket(payload []byte) {
+	t.mu.Lock()
+	defer t.mu.Unlock()
+
+	if t.closed {
+		return
+	}
+
+	if !t.running {
+		if err := t.startLocked(); err != nil {
+			log.Errorf("failed to start TCP DNS stack: %v", err)
+			return
+		}
+		t.running = true
+		log.Debugf("TCP DNS stack started on %s:%d (triggered by %s)", t.ip, t.port, srcAddrFromPacket(payload))
+	}
+	t.resetTimerLocked()
+
+	ep := t.ep
+	if ep == nil || ep.dispatcher == nil {
+		return
+	}
+
+	pkt := stack.NewPacketBuffer(stack.PacketBufferOptions{
+		Payload: buffer.MakeWithData(payload),
+	})
+	// DeliverNetworkPacket takes ownership of the packet buffer; do not DecRef.
+	ep.dispatcher.DeliverNetworkPacket(ipv4.ProtocolNumber, pkt)
+}
+
+// Stop tears down the gvisor stack and releases resources permanently.
+// After Stop, InjectPacket becomes a no-op.
+func (t *tcpDNSServer) Stop() {
+	t.mu.Lock()
+	defer t.mu.Unlock()
+
+	t.stopLocked()
+	t.closed = true
+}
+
+func (t *tcpDNSServer) startLocked() error {
+	// TODO: add ipv6.NewProtocol when IPv6 overlay support lands.
+	s := stack.New(stack.Options{
+		NetworkProtocols:   []stack.NetworkProtocolFactory{ipv4.NewProtocol},
+		TransportProtocols: []stack.TransportProtocolFactory{tcp.NewProtocol},
+		HandleLocal:        false,
+	})
+
+	nicID := tcpip.NICID(1)
+	ep := &dnsEndpoint{
+		tunDev: t.tunDev,
+	}
+	ep.mtu.Store(uint32(t.mtu))
+
+	if err := s.CreateNIC(nicID, ep); err != nil {
+		s.Close()
+		s.Wait()
+		return fmt.Errorf("create NIC: %v", err)
+	}
+
+	protoAddr := tcpip.ProtocolAddress{
+		Protocol: ipv4.ProtocolNumber,
+		AddressWithPrefix: tcpip.AddressWithPrefix{
+			Address:   tcpip.AddrFromSlice(t.ip.AsSlice()),
+			PrefixLen: 32,
+		},
+	}
+	if err := s.AddProtocolAddress(nicID, protoAddr, stack.AddressProperties{}); err != nil {
+		s.Close()
+		s.Wait()
+		return fmt.Errorf("add protocol address: %s", err)
+	}
+
+	if err := s.SetPromiscuousMode(nicID, true); err != nil {
+		s.Close()
+		s.Wait()
+		return fmt.Errorf("set promiscuous mode: %s", err)
+	}
+	if err := s.SetSpoofing(nicID, true); err != nil {
+		s.Close()
+		s.Wait()
+		return fmt.Errorf("set spoofing: %s", err)
+	}
+
+	defaultSubnet, err := tcpip.NewSubnet(
+		tcpip.AddrFrom4([4]byte{0, 0, 0, 0}),
+		tcpip.MaskFromBytes([]byte{0, 0, 0, 0}),
+	)
+	if err != nil {
+		s.Close()
+		s.Wait()
+		return fmt.Errorf("create default subnet: %w", err)
+	}
+
+	s.SetRouteTable([]tcpip.Route{
+		{Destination: defaultSubnet, NIC: nicID},
+	})
+
+	tcpFwd := tcp.NewForwarder(s, dnsTCPReceiveWindow, dnsTCPMaxInFlight, func(r *tcp.ForwarderRequest) {
+		t.handleTCPDNS(r)
+	})
+	s.SetTransportProtocolHandler(tcp.ProtocolNumber, tcpFwd.HandlePacket)
+
+	t.s = s
+	t.ep = ep
+	return nil
+}
+
+func (t *tcpDNSServer) stopLocked() {
+	if !t.running {
+		return
+	}
+
+	if t.timer != nil {
+		t.timer.Stop()
+		t.timer = nil
+	}
+
+	if t.s != nil {
+		t.s.Close()
+		t.s.Wait()
+		t.s = nil
+	}
+	t.ep = nil
+	t.running = false
+
+	log.Debugf("TCP DNS stack stopped")
+}
+
+func (t *tcpDNSServer) resetTimerLocked() {
+	if t.timer != nil {
+		t.timer.Stop()
+	}
+	t.timerID++
+	id := t.timerID
+	t.timer = time.AfterFunc(dnsTCPIdleTimeout, func() {
+		t.mu.Lock()
+		defer t.mu.Unlock()
+
+		// Only stop if this timer is still the active one.
+		// A racing InjectPacket may have replaced it.
+		if t.timerID != id {
+			return
+		}
+		t.stopLocked()
+	})
+}
+
+func (t *tcpDNSServer) handleTCPDNS(r *tcp.ForwarderRequest) {
+	id := r.ID()
+
+	wq := waiter.Queue{}
+	ep, epErr := r.CreateEndpoint(&wq)
+	if epErr != nil {
+		log.Debugf("TCP DNS: failed to create endpoint: %v", epErr)
+		r.Complete(true)
+		return
+	}
+	r.Complete(false)
+
+	conn := gonet.NewTCPConn(&wq, ep)
+	defer func() {
+		if err := conn.Close(); err != nil {
+			log.Tracef("TCP DNS: close conn: %v", err)
+		}
+	}()
+
+	// Reset idle timer on activity
+	t.mu.Lock()
+	t.resetTimerLocked()
+	t.mu.Unlock()
+
+	localAddr := &net.TCPAddr{
+		IP:   id.LocalAddress.AsSlice(),
+		Port: int(id.LocalPort),
+	}
+	remoteAddr := &net.TCPAddr{
+		IP:   id.RemoteAddress.AsSlice(),
+		Port: int(id.RemotePort),
+	}
+
+	for {
+		if err := conn.SetReadDeadline(time.Now().Add(dnsTCPReadTimeout)); err != nil {
+			log.Debugf("TCP DNS: set deadline for %s: %v", remoteAddr, err)
+			break
+		}
+
+		msg, err := readTCPDNSMessage(conn)
+		if err != nil {
+			if !errors.Is(err, io.EOF) && !errors.Is(err, io.ErrUnexpectedEOF) {
+				log.Debugf("TCP DNS: read from %s: %v", remoteAddr, err)
+			}
+			break
+		}
+
+		writer := &tcpResponseWriter{
+			conn:       conn,
+			localAddr:  localAddr,
+			remoteAddr: remoteAddr,
+		}
+		t.mux.ServeDNS(writer, msg)
+	}
+}
+
+// dnsEndpoint implements stack.LinkEndpoint for writing packets back via the tun device.
+type dnsEndpoint struct {
+	dispatcher stack.NetworkDispatcher
+	tunDev     tun.Device
+	mtu        atomic.Uint32
+}
+
+func (e *dnsEndpoint) Attach(dispatcher stack.NetworkDispatcher)    { e.dispatcher = dispatcher }
+func (e *dnsEndpoint) IsAttached() bool                             { return e.dispatcher != nil }
+func (e *dnsEndpoint) MTU() uint32                                  { return e.mtu.Load() }
+func (e *dnsEndpoint) Capabilities() stack.LinkEndpointCapabilities { return stack.CapabilityNone }
+func (e *dnsEndpoint) MaxHeaderLength() uint16                      { return 0 }
+func (e *dnsEndpoint) LinkAddress() tcpip.LinkAddress               { return "" }
+func (e *dnsEndpoint) Wait()                                        { /* no async work */ }
+func (e *dnsEndpoint) ARPHardwareType() header.ARPHardwareType      { return header.ARPHardwareNone }
+func (e *dnsEndpoint) AddHeader(*stack.PacketBuffer)                { /* IP-level endpoint, no link header */ }
+func (e *dnsEndpoint) ParseHeader(*stack.PacketBuffer) bool         { return true }
+func (e *dnsEndpoint) Close()                                       { /* lifecycle managed by tcpDNSServer */ }
+func (e *dnsEndpoint) SetLinkAddress(tcpip.LinkAddress)             { /* no link address for tun */ }
+func (e *dnsEndpoint) SetMTU(mtu uint32)                            { e.mtu.Store(mtu) }
+func (e *dnsEndpoint) SetOnCloseAction(func())                      { /* not needed */ }
+
+const tunPacketOffset = 40
+
+func (e *dnsEndpoint) WritePackets(pkts stack.PacketBufferList) (int, tcpip.Error) {
+	var written int
+	for _, pkt := range pkts.AsSlice() {
+		data := stack.PayloadSince(pkt.NetworkHeader())
+		if data == nil {
+			continue
+		}
+
+		raw := data.AsSlice()
+		buf := make([]byte, tunPacketOffset, tunPacketOffset+len(raw))
+		buf = append(buf, raw...)
+		data.Release()
+
+		if _, err := e.tunDev.Write([][]byte{buf}, tunPacketOffset); err != nil {
+			log.Tracef("TCP DNS endpoint: failed to write packet: %v", err)
+			continue
+		}
+		written++
+	}
+	return written, nil
+}
+
+// tcpResponseWriter implements dns.ResponseWriter for TCP DNS connections.
+type tcpResponseWriter struct {
+	conn       *gonet.TCPConn
+	localAddr  net.Addr
+	remoteAddr net.Addr
+}
+
+func (w *tcpResponseWriter) LocalAddr() net.Addr {
+	return w.localAddr
+}
+
+func (w *tcpResponseWriter) RemoteAddr() net.Addr {
+	return w.remoteAddr
+}
+
+func (w *tcpResponseWriter) WriteMsg(msg *dns.Msg) error {
+	data, err := msg.Pack()
+	if err != nil {
+		return fmt.Errorf("pack: %w", err)
+	}
+
+	// DNS TCP: 2-byte length prefix + message
+	buf := make([]byte, 2+len(data))
+	buf[0] = byte(len(data) >> 8)
+	buf[1] = byte(len(data))
+	copy(buf[2:], data)
+
+	if _, err = w.conn.Write(buf); err != nil {
+		return err
+	}
+	return nil
+}
+
+func (w *tcpResponseWriter) Write(data []byte) (int, error) {
+	buf := make([]byte, 2+len(data))
+	buf[0] = byte(len(data) >> 8)
+	buf[1] = byte(len(data))
+	copy(buf[2:], data)
+	if _, err := w.conn.Write(buf); err != nil {
+		return 0, err
+	}
+	return len(data), nil
+}
+
+func (w *tcpResponseWriter) Close() error {
+	return w.conn.Close()
+}
+
+func (w *tcpResponseWriter) TsigStatus() error   { return nil }
+func (w *tcpResponseWriter) TsigTimersOnly(bool) { /* TSIG not supported */ }
+func (w *tcpResponseWriter) Hijack()             { /* not supported */ }
+
+// readTCPDNSMessage reads a single DNS message from a TCP connection (length-prefixed).
+func readTCPDNSMessage(conn *gonet.TCPConn) (*dns.Msg, error) {
+	// DNS over TCP uses a 2-byte length prefix
+	lenBuf := make([]byte, 2)
+	if _, err := io.ReadFull(conn, lenBuf); err != nil {
+		return nil, fmt.Errorf("read length: %w", err)
+	}
+
+	msgLen := int(lenBuf[0])<<8 | int(lenBuf[1])
+	if msgLen == 0 || msgLen > 65535 {
+		return nil, fmt.Errorf("invalid message length: %d", msgLen)
+	}
+
+	msgBuf := make([]byte, msgLen)
+	if _, err := io.ReadFull(conn, msgBuf); err != nil {
+		return nil, fmt.Errorf("read message: %w", err)
+	}
+
+	msg := new(dns.Msg)
+	if err := msg.Unpack(msgBuf); err != nil {
+		return nil, fmt.Errorf("unpack: %w", err)
+	}
+	return msg, nil
+}
+
+// srcAddrFromPacket extracts the source IP:port from a raw IP+TCP packet for logging.
+// Supports both IPv4 and IPv6.
+func srcAddrFromPacket(pkt []byte) netip.AddrPort {
+	if len(pkt) == 0 {
+		return netip.AddrPort{}
+	}
+
+	srcIP, transportOffset := srcIPFromPacket(pkt)
+	if !srcIP.IsValid() || len(pkt) < transportOffset+2 {
+		return netip.AddrPort{}
+	}
+
+	srcPort := uint16(pkt[transportOffset])<<8 | uint16(pkt[transportOffset+1])
+	return netip.AddrPortFrom(srcIP.Unmap(), srcPort)
+}
+
+func srcIPFromPacket(pkt []byte) (netip.Addr, int) {
+	switch header.IPVersion(pkt) {
+	case 4:
+		return srcIPv4(pkt)
+	case 6:
+		return srcIPv6(pkt)
+	default:
+		return netip.Addr{}, 0
+	}
+}
+
+func srcIPv4(pkt []byte) (netip.Addr, int) {
+	if len(pkt) < header.IPv4MinimumSize {
+		return netip.Addr{}, 0
+	}
+	hdr := header.IPv4(pkt)
+	src := hdr.SourceAddress()
+	ip, ok := netip.AddrFromSlice(src.AsSlice())
+	if !ok {
+		return netip.Addr{}, 0
+	}
+	return ip, int(hdr.HeaderLength())
+}
+
+func srcIPv6(pkt []byte) (netip.Addr, int) {
+	if len(pkt) < header.IPv6MinimumSize {
+		return netip.Addr{}, 0
+	}
+	hdr := header.IPv6(pkt)
+	src := hdr.SourceAddress()
+	ip, ok := netip.AddrFromSlice(src.AsSlice())
+	if !ok {
+		return netip.Addr{}, 0
+	}
+	return ip, header.IPv6MinimumSize
+}

client/internal/dns/upstream.go

@@ -41,10 +41,61 @@ const (
 
 	reactivatePeriod = 30 * time.Second
 	probeTimeout     = 2 * time.Second
+
+	// ipv6HeaderSize + udpHeaderSize, used to derive the maximum DNS UDP
+	// payload from the tunnel MTU.
+	ipUDPHeaderSize = 60 + 8
 )
 
 const testRecord = "com."
 
+const (
+	protoUDP = "udp"
+	protoTCP = "tcp"
+)
+
+type dnsProtocolKey struct{}
+
+// contextWithDNSProtocol stores the inbound DNS protocol ("udp" or "tcp") in context.
+func contextWithDNSProtocol(ctx context.Context, network string) context.Context {
+	return context.WithValue(ctx, dnsProtocolKey{}, network)
+}
+
+// dnsProtocolFromContext retrieves the inbound DNS protocol from context.
+func dnsProtocolFromContext(ctx context.Context) string {
+	if ctx == nil {
+		return ""
+	}
+	if v, ok := ctx.Value(dnsProtocolKey{}).(string); ok {
+		return v
+	}
+	return ""
+}
+
+type upstreamProtocolKey struct{}
+
+// upstreamProtocolResult holds the protocol used for the upstream exchange.
+// Stored as a pointer in context so the exchange function can set it.
+type upstreamProtocolResult struct {
+	protocol string
+}
+
+// contextWithupstreamProtocolResult stores a mutable result holder in the context.
+func contextWithupstreamProtocolResult(ctx context.Context) (context.Context, *upstreamProtocolResult) {
+	r := &upstreamProtocolResult{}
+	return context.WithValue(ctx, upstreamProtocolKey{}, r), r
+}
+
+// setUpstreamProtocol sets the upstream protocol on the result holder in context, if present.
+func setUpstreamProtocol(ctx context.Context, protocol string) {
+	if ctx == nil {
+		return
+	}
+	if r, ok := ctx.Value(upstreamProtocolKey{}).(*upstreamProtocolResult); ok && r != nil {
+		r.protocol = protocol
+	}
+}
+
 type upstreamClient interface {
 	exchange(ctx context.Context, upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
 }
@@ -138,7 +189,16 @@ func (u *upstreamResolverBase) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 		return
 	}
 
-	ok, failures := u.tryUpstreamServers(w, r, logger)
+	// Propagate inbound protocol so upstream exchange can use TCP directly
+	// when the request came in over TCP.
+	ctx := u.ctx
+	if addr := w.RemoteAddr(); addr != nil {
+		network := addr.Network()
+		ctx = contextWithDNSProtocol(ctx, network)
+		resutil.SetMeta(w, "protocol", network)
+	}
+
+	ok, failures := u.tryUpstreamServers(ctx, w, r, logger)
 	if len(failures) > 0 {
 		u.logUpstreamFailures(r.Question[0].Name, failures, ok, logger)
 	}
@@ -153,7 +213,7 @@ func (u *upstreamResolverBase) prepareRequest(r *dns.Msg) {
 	}
 }
 
-func (u *upstreamResolverBase) tryUpstreamServers(w dns.ResponseWriter, r *dns.Msg, logger *log.Entry) (bool, []upstreamFailure) {
+func (u *upstreamResolverBase) tryUpstreamServers(ctx context.Context, w dns.ResponseWriter, r *dns.Msg, logger *log.Entry) (bool, []upstreamFailure) {
 	timeout := u.upstreamTimeout
 	if len(u.upstreamServers) > 1 {
 		maxTotal := 5 * time.Second
@@ -168,7 +228,7 @@ func (u *upstreamResolverBase) tryUpstreamServers(w dns.ResponseWriter, r *dns.M
 
 	var failures []upstreamFailure
 	for _, upstream := range u.upstreamServers {
-		if failure := u.queryUpstream(w, r, upstream, timeout, logger); failure != nil {
+		if failure := u.queryUpstream(ctx, w, r, upstream, timeout, logger); failure != nil {
 			failures = append(failures, *failure)
 		} else {
 			return true, failures
@@ -178,15 +238,17 @@ func (u *upstreamResolverBase) tryUpstreamServers(w dns.ResponseWriter, r *dns.M
 }
 
 // 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 {
+func (u *upstreamResolverBase) queryUpstream(parentCtx context.Context, 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
 
 	var startTime time.Time
+	var upstreamProto *upstreamProtocolResult
 	func() {
-		ctx, cancel := context.WithTimeout(u.ctx, timeout)
+		ctx, cancel := context.WithTimeout(parentCtx, timeout)
 		defer cancel()
+		ctx, upstreamProto = contextWithupstreamProtocolResult(ctx)
 		startTime = time.Now()
 		rm, t, err = u.upstreamClient.exchange(ctx, upstream.String(), r)
 	}()
@@ -203,7 +265,7 @@ func (u *upstreamResolverBase) queryUpstream(w dns.ResponseWriter, r *dns.Msg, u
 		return &upstreamFailure{upstream: upstream, reason: dns.RcodeToString[rm.Rcode]}
 	}
 
-	u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, logger)
+	u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, upstreamProto, logger)
 	return nil
 }
 
@@ -220,10 +282,13 @@ func (u *upstreamResolverBase) handleUpstreamError(err error, upstream netip.Add
 	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 {
+func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dns.Msg, upstream netip.AddrPort, domain string, t time.Duration, upstreamProto *upstreamProtocolResult, logger *log.Entry) bool {
 	u.successCount.Add(1)
 
 	resutil.SetMeta(w, "upstream", upstream.String())
+	if upstreamProto != nil && upstreamProto.protocol != "" {
+		resutil.SetMeta(w, "upstream_protocol", upstreamProto.protocol)
+	}
 
 	// Clear Zero bit from external responses to prevent upstream servers from
 	// manipulating our internal fallthrough signaling mechanism
@@ -428,13 +493,42 @@ func (u *upstreamResolverBase) testNameserver(baseCtx context.Context, externalC
 	return err
 }
 
+// clientUDPMaxSize returns the maximum UDP response size the client accepts.
+func clientUDPMaxSize(r *dns.Msg) int {
+	if opt := r.IsEdns0(); opt != nil {
+		return int(opt.UDPSize())
+	}
+	return dns.MinMsgSize
+}
+
 // ExchangeWithFallback exchanges a DNS message with the upstream server.
 // It first tries to use UDP, and if it is truncated, it falls back to TCP.
+// If the inbound request came over TCP (via context), it skips the UDP attempt.
 // If the passed context is nil, this will use Exchange instead of ExchangeContext.
 func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, upstream string) (*dns.Msg, time.Duration, error) {
-	// MTU - ip + udp headers
-	// Note: this could be sent out on an interface that is not ours, but higher MTU settings could break truncation handling.
-	client.UDPSize = uint16(currentMTU - (60 + 8))
+	// If the request came in over TCP, go straight to TCP upstream.
+	if dnsProtocolFromContext(ctx) == protoTCP {
+		tcpClient := *client
+		tcpClient.Net = protoTCP
+		rm, t, err := tcpClient.ExchangeContext(ctx, r, upstream)
+		if err != nil {
+			return nil, t, fmt.Errorf("with tcp: %w", err)
+		}
+		setUpstreamProtocol(ctx, protoTCP)
+		return rm, t, nil
+	}
+
+	clientMaxSize := clientUDPMaxSize(r)
+
+	// Cap EDNS0 to our tunnel MTU so the upstream doesn't send a
+	// response larger than our read buffer.
+	// Note: the query could be sent out on an interface that is not ours,
+	// but higher MTU settings could break truncation handling.
+	maxUDPPayload := uint16(currentMTU - ipUDPHeaderSize)
+	client.UDPSize = maxUDPPayload
+	if opt := r.IsEdns0(); opt != nil && opt.UDPSize() > maxUDPPayload {
+		opt.SetUDPSize(maxUDPPayload)
+	}
 
 	var (
 		rm  *dns.Msg
@@ -453,25 +547,32 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 	}
 
 	if rm == nil || !rm.MsgHdr.Truncated {
+		setUpstreamProtocol(ctx, protoUDP)
 		return rm, t, nil
 	}
 
-	log.Tracef("udp response for domain=%s type=%v class=%v is truncated, trying TCP.",
-		r.Question[0].Name, r.Question[0].Qtype, r.Question[0].Qclass)
+	// TODO: if the upstream's truncated UDP response already contains more
+	// data than the client's buffer, we could truncate locally and skip
+	// the TCP retry.
 
-	client.Net = "tcp"
+	tcpClient := *client
+	tcpClient.Net = protoTCP
 
 	if ctx == nil {
-		rm, t, err = client.Exchange(r, upstream)
+		rm, t, err = tcpClient.Exchange(r, upstream)
 	} else {
-		rm, t, err = client.ExchangeContext(ctx, r, upstream)
+		rm, t, err = tcpClient.ExchangeContext(ctx, r, upstream)
 	}
 
 	if err != nil {
 		return nil, t, fmt.Errorf("with tcp: %w", err)
 	}
 
-	// TODO: once TCP is implemented, rm.Truncate() if the request came in over UDP
+	setUpstreamProtocol(ctx, protoTCP)
+
+	if rm.Len() > clientMaxSize {
+		rm.Truncate(clientMaxSize)
+	}
 
 	return rm, t, nil
 }
@@ -479,18 +580,46 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 // ExchangeWithNetstack performs a DNS exchange using netstack for dialing.
 // This is needed when netstack is enabled to reach peer IPs through the tunnel.
 func ExchangeWithNetstack(ctx context.Context, nsNet *netstack.Net, r *dns.Msg, upstream string) (*dns.Msg, error) {
-	reply, err := netstackExchange(ctx, nsNet, r, upstream, "udp")
+	// If request came in over TCP, go straight to TCP upstream
+	if dnsProtocolFromContext(ctx) == protoTCP {
+		rm, err := netstackExchange(ctx, nsNet, r, upstream, protoTCP)
+		if err != nil {
+			return nil, err
+		}
+		setUpstreamProtocol(ctx, protoTCP)
+		return rm, nil
+	}
+
+	clientMaxSize := clientUDPMaxSize(r)
+
+	// Cap EDNS0 to our tunnel MTU so the upstream doesn't send a
+	// response larger than what we can read over UDP.
+	maxUDPPayload := uint16(currentMTU - ipUDPHeaderSize)
+	if opt := r.IsEdns0(); opt != nil && opt.UDPSize() > maxUDPPayload {
+		opt.SetUDPSize(maxUDPPayload)
+	}
+
+	reply, err := netstackExchange(ctx, nsNet, r, upstream, protoUDP)
 	if err != nil {
 		return nil, err
 	}
 
-	// If response is truncated, retry with TCP
 	if reply != nil && reply.MsgHdr.Truncated {
-		log.Tracef("udp response for domain=%s type=%v class=%v is truncated, trying TCP",
-			r.Question[0].Name, r.Question[0].Qtype, r.Question[0].Qclass)
-		return netstackExchange(ctx, nsNet, r, upstream, "tcp")
+		rm, err := netstackExchange(ctx, nsNet, r, upstream, protoTCP)
+		if err != nil {
+			return nil, err
+		}
+
+		setUpstreamProtocol(ctx, protoTCP)
+		if rm.Len() > clientMaxSize {
+			rm.Truncate(clientMaxSize)
+		}
+
+		return rm, nil
 	}
 
+	setUpstreamProtocol(ctx, protoUDP)
+
 	return reply, nil
 }
 
@@ -511,7 +640,7 @@ func netstackExchange(ctx context.Context, nsNet *netstack.Net, r *dns.Msg, upst
 		}
 	}
 
-	dnsConn := &dns.Conn{Conn: conn}
+	dnsConn := &dns.Conn{Conn: conn, UDPSize: uint16(currentMTU - ipUDPHeaderSize)}
 
 	if err := dnsConn.WriteMsg(r); err != nil {
 		return nil, fmt.Errorf("write %s message: %w", network, err)

client/internal/dns/upstream_android.go

@@ -51,7 +51,7 @@ func (u *upstreamResolver) exchangeWithinVPN(ctx context.Context, upstream strin
 	upstreamExchangeClient := &dns.Client{
 		Timeout: ClientTimeout,
 	}
-	return upstreamExchangeClient.ExchangeContext(ctx, r, upstream)
+	return ExchangeWithFallback(ctx, upstreamExchangeClient, r, upstream)
 }
 
 // exchangeWithoutVPN protect the UDP socket by Android SDK to avoid to goes through the VPN
@@ -76,7 +76,7 @@ func (u *upstreamResolver) exchangeWithoutVPN(ctx context.Context, upstream stri
 		Timeout: timeout,
 	}
 
-	return upstreamExchangeClient.ExchangeContext(ctx, r, upstream)
+	return ExchangeWithFallback(ctx, upstreamExchangeClient, r, upstream)
 }
 
 func (u *upstreamResolver) isLocalResolver(upstream string) bool {

client/internal/dns/upstream_test.go

@@ -475,3 +475,298 @@ func TestFormatFailures(t *testing.T) {
 		})
 	}
 }
+
+func TestDNSProtocolContext(t *testing.T) {
+	t.Run("roundtrip udp", func(t *testing.T) {
+		ctx := contextWithDNSProtocol(context.Background(), protoUDP)
+		assert.Equal(t, protoUDP, dnsProtocolFromContext(ctx))
+	})
+
+	t.Run("roundtrip tcp", func(t *testing.T) {
+		ctx := contextWithDNSProtocol(context.Background(), protoTCP)
+		assert.Equal(t, protoTCP, dnsProtocolFromContext(ctx))
+	})
+
+	t.Run("missing returns empty", func(t *testing.T) {
+		assert.Equal(t, "", dnsProtocolFromContext(context.Background()))
+	})
+}
+
+func TestExchangeWithFallback_TCPContext(t *testing.T) {
+	// Start a local DNS server that responds on TCP only
+	tcpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
+		m := new(dns.Msg)
+		m.SetReply(r)
+		m.Answer = append(m.Answer, &dns.A{
+			Hdr: dns.RR_Header{Name: r.Question[0].Name, Rrtype: dns.TypeA, Class: dns.ClassINET, Ttl: 60},
+			A:   net.ParseIP("10.0.0.1"),
+		})
+		if err := w.WriteMsg(m); err != nil {
+			t.Logf("write msg: %v", err)
+		}
+	})
+
+	tcpServer := &dns.Server{
+		Addr:    "127.0.0.1:0",
+		Net:     "tcp",
+		Handler: tcpHandler,
+	}
+
+	tcpLn, err := net.Listen("tcp", "127.0.0.1:0")
+	require.NoError(t, err)
+	tcpServer.Listener = tcpLn
+
+	go func() {
+		if err := tcpServer.ActivateAndServe(); err != nil {
+			t.Logf("tcp server: %v", err)
+		}
+	}()
+	defer func() {
+		_ = tcpServer.Shutdown()
+	}()
+
+	upstream := tcpLn.Addr().String()
+
+	// With TCP context, should connect directly via TCP without trying UDP
+	ctx := contextWithDNSProtocol(context.Background(), protoTCP)
+	client := &dns.Client{Timeout: 2 * time.Second}
+	r := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+
+	rm, _, err := ExchangeWithFallback(ctx, client, r, upstream)
+	require.NoError(t, err)
+	require.NotNil(t, rm)
+	require.NotEmpty(t, rm.Answer)
+	assert.Contains(t, rm.Answer[0].String(), "10.0.0.1")
+}
+
+func TestExchangeWithFallback_UDPFallbackToTCP(t *testing.T) {
+	// UDP handler returns a truncated response to trigger TCP retry.
+	udpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
+		m := new(dns.Msg)
+		m.SetReply(r)
+		m.Truncated = true
+		if err := w.WriteMsg(m); err != nil {
+			t.Logf("write msg: %v", err)
+		}
+	})
+
+	// TCP handler returns the full answer.
+	tcpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
+		m := new(dns.Msg)
+		m.SetReply(r)
+		m.Answer = append(m.Answer, &dns.A{
+			Hdr: dns.RR_Header{Name: r.Question[0].Name, Rrtype: dns.TypeA, Class: dns.ClassINET, Ttl: 60},
+			A:   net.ParseIP("10.0.0.3"),
+		})
+		if err := w.WriteMsg(m); err != nil {
+			t.Logf("write msg: %v", err)
+		}
+	})
+
+	udpPC, err := net.ListenPacket("udp", "127.0.0.1:0")
+	require.NoError(t, err)
+	addr := udpPC.LocalAddr().String()
+
+	udpServer := &dns.Server{
+		PacketConn: udpPC,
+		Net:        "udp",
+		Handler:    udpHandler,
+	}
+
+	tcpLn, err := net.Listen("tcp", addr)
+	require.NoError(t, err)
+
+	tcpServer := &dns.Server{
+		Listener: tcpLn,
+		Net:      "tcp",
+		Handler:  tcpHandler,
+	}
+
+	go func() {
+		if err := udpServer.ActivateAndServe(); err != nil {
+			t.Logf("udp server: %v", err)
+		}
+	}()
+	go func() {
+		if err := tcpServer.ActivateAndServe(); err != nil {
+			t.Logf("tcp server: %v", err)
+		}
+	}()
+	defer func() {
+		_ = udpServer.Shutdown()
+		_ = tcpServer.Shutdown()
+	}()
+
+	ctx := context.Background()
+	client := &dns.Client{Timeout: 2 * time.Second}
+	r := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+
+	rm, _, err := ExchangeWithFallback(ctx, client, r, addr)
+	require.NoError(t, err, "should fall back to TCP after truncated UDP response")
+	require.NotNil(t, rm)
+	require.NotEmpty(t, rm.Answer, "TCP response should contain the full answer")
+	assert.Contains(t, rm.Answer[0].String(), "10.0.0.3")
+	assert.False(t, rm.Truncated, "TCP response should not be truncated")
+}
+
+func TestExchangeWithFallback_TCPContextSkipsUDP(t *testing.T) {
+	// Start only a TCP server (no UDP). With TCP context it should succeed.
+	tcpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
+		m := new(dns.Msg)
+		m.SetReply(r)
+		m.Answer = append(m.Answer, &dns.A{
+			Hdr: dns.RR_Header{Name: r.Question[0].Name, Rrtype: dns.TypeA, Class: dns.ClassINET, Ttl: 60},
+			A:   net.ParseIP("10.0.0.2"),
+		})
+		if err := w.WriteMsg(m); err != nil {
+			t.Logf("write msg: %v", err)
+		}
+	})
+
+	tcpLn, err := net.Listen("tcp", "127.0.0.1:0")
+	require.NoError(t, err)
+
+	tcpServer := &dns.Server{
+		Listener: tcpLn,
+		Net:      "tcp",
+		Handler:  tcpHandler,
+	}
+
+	go func() {
+		if err := tcpServer.ActivateAndServe(); err != nil {
+			t.Logf("tcp server: %v", err)
+		}
+	}()
+	defer func() {
+		_ = tcpServer.Shutdown()
+	}()
+
+	upstream := tcpLn.Addr().String()
+
+	// TCP context: should skip UDP entirely and go directly to TCP
+	ctx := contextWithDNSProtocol(context.Background(), protoTCP)
+	client := &dns.Client{Timeout: 2 * time.Second}
+	r := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+
+	rm, _, err := ExchangeWithFallback(ctx, client, r, upstream)
+	require.NoError(t, err)
+	require.NotNil(t, rm)
+	require.NotEmpty(t, rm.Answer)
+	assert.Contains(t, rm.Answer[0].String(), "10.0.0.2")
+
+	// Without TCP context, trying to reach a TCP-only server via UDP should fail
+	ctx2 := context.Background()
+	client2 := &dns.Client{Timeout: 500 * time.Millisecond}
+	_, _, err = ExchangeWithFallback(ctx2, client2, r, upstream)
+	assert.Error(t, err, "should fail when no UDP server and no TCP context")
+}
+
+func TestExchangeWithFallback_EDNS0Capped(t *testing.T) {
+	// Verify that a client EDNS0 larger than our MTU-derived limit gets
+	// capped in the outgoing request so the upstream doesn't send a
+	// response larger than our read buffer.
+	var receivedUDPSize uint16
+	udpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
+		if opt := r.IsEdns0(); opt != nil {
+			receivedUDPSize = opt.UDPSize()
+		}
+		m := new(dns.Msg)
+		m.SetReply(r)
+		m.Answer = append(m.Answer, &dns.A{
+			Hdr: dns.RR_Header{Name: r.Question[0].Name, Rrtype: dns.TypeA, Class: dns.ClassINET, Ttl: 60},
+			A:   net.ParseIP("10.0.0.1"),
+		})
+		if err := w.WriteMsg(m); err != nil {
+			t.Logf("write msg: %v", err)
+		}
+	})
+
+	udpPC, err := net.ListenPacket("udp", "127.0.0.1:0")
+	require.NoError(t, err)
+	addr := udpPC.LocalAddr().String()
+
+	udpServer := &dns.Server{PacketConn: udpPC, Net: "udp", Handler: udpHandler}
+	go func() { _ = udpServer.ActivateAndServe() }()
+	t.Cleanup(func() { _ = udpServer.Shutdown() })
+
+	ctx := context.Background()
+	client := &dns.Client{Timeout: 2 * time.Second}
+	r := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+	r.SetEdns0(4096, false)
+
+	rm, _, err := ExchangeWithFallback(ctx, client, r, addr)
+	require.NoError(t, err)
+	require.NotNil(t, rm)
+
+	expectedMax := uint16(currentMTU - ipUDPHeaderSize)
+	assert.Equal(t, expectedMax, receivedUDPSize,
+		"upstream should see capped EDNS0, not the client's 4096")
+}
+
+func TestExchangeWithFallback_TCPTruncatesToClientSize(t *testing.T) {
+	// When the client advertises a large EDNS0 (4096) and the upstream
+	// truncates, the TCP response should NOT be truncated since the full
+	// answer fits within the client's original buffer.
+	udpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
+		m := new(dns.Msg)
+		m.SetReply(r)
+		m.Truncated = true
+		if err := w.WriteMsg(m); err != nil {
+			t.Logf("write msg: %v", err)
+		}
+	})
+
+	tcpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
+		m := new(dns.Msg)
+		m.SetReply(r)
+		// Add enough records to exceed MTU but fit within 4096
+		for i := range 20 {
+			m.Answer = append(m.Answer, &dns.TXT{
+				Hdr: dns.RR_Header{Name: r.Question[0].Name, Rrtype: dns.TypeTXT, Class: dns.ClassINET, Ttl: 60},
+				Txt: []string{fmt.Sprintf("record-%d-padding-data-to-make-it-longer", i)},
+			})
+		}
+		if err := w.WriteMsg(m); err != nil {
+			t.Logf("write msg: %v", err)
+		}
+	})
+
+	udpPC, err := net.ListenPacket("udp", "127.0.0.1:0")
+	require.NoError(t, err)
+	addr := udpPC.LocalAddr().String()
+
+	udpServer := &dns.Server{PacketConn: udpPC, Net: "udp", Handler: udpHandler}
+	tcpLn, err := net.Listen("tcp", addr)
+	require.NoError(t, err)
+	tcpServer := &dns.Server{Listener: tcpLn, Net: "tcp", Handler: tcpHandler}
+
+	go func() { _ = udpServer.ActivateAndServe() }()
+	go func() { _ = tcpServer.ActivateAndServe() }()
+	t.Cleanup(func() {
+		_ = udpServer.Shutdown()
+		_ = tcpServer.Shutdown()
+	})
+
+	ctx := context.Background()
+	client := &dns.Client{Timeout: 2 * time.Second}
+
+	// Client with large buffer: should get all records without truncation
+	r := new(dns.Msg).SetQuestion("example.com.", dns.TypeTXT)
+	r.SetEdns0(4096, false)
+
+	rm, _, err := ExchangeWithFallback(ctx, client, r, addr)
+	require.NoError(t, err)
+	require.NotNil(t, rm)
+	assert.Len(t, rm.Answer, 20, "large EDNS0 client should get all records")
+	assert.False(t, rm.Truncated, "response should not be truncated for large buffer client")
+
+	// Client with small buffer: should get truncated response
+	r2 := new(dns.Msg).SetQuestion("example.com.", dns.TypeTXT)
+	r2.SetEdns0(512, false)
+
+	rm2, _, err := ExchangeWithFallback(ctx, &dns.Client{Timeout: 2 * time.Second}, r2, addr)
+	require.NoError(t, err)
+	require.NotNil(t, rm2)
+	assert.Less(t, len(rm2.Answer), 20, "small EDNS0 client should get fewer records")
+	assert.True(t, rm2.Truncated, "response should be truncated for small buffer client")
+}

client/internal/dnsfwd/forwarder.go

@@ -237,8 +237,8 @@ func (f *DNSForwarder) writeResponse(logger *log.Entry, w dns.ResponseWriter, re
 		return
 	}
 
-	logger.Tracef("response: domain=%s rcode=%s answers=%s took=%s",
-		qname, dns.RcodeToString[resp.Rcode], resutil.FormatAnswers(resp.Answer), time.Since(startTime))
+	logger.Tracef("response: domain=%s rcode=%s answers=%s size=%dB took=%s",
+		qname, dns.RcodeToString[resp.Rcode], resutil.FormatAnswers(resp.Answer), resp.Len(), time.Since(startTime))
 }
 
 // udpResponseWriter wraps a dns.ResponseWriter to handle UDP-specific truncation.
@@ -263,20 +263,28 @@ func (u *udpResponseWriter) WriteMsg(resp *dns.Msg) error {
 
 func (f *DNSForwarder) handleDNSQueryUDP(w dns.ResponseWriter, query *dns.Msg) {
 	startTime := time.Now()
-	logger := log.WithFields(log.Fields{
+	fields := log.Fields{
 		"request_id": resutil.GenerateRequestID(),
 		"dns_id":     fmt.Sprintf("%04x", query.Id),
-	})
+	}
+	if addr := w.RemoteAddr(); addr != nil {
+		fields["client"] = addr.String()
+	}
+	logger := log.WithFields(fields)
 
 	f.handleDNSQuery(logger, &udpResponseWriter{ResponseWriter: w, query: query}, query, startTime)
 }
 
 func (f *DNSForwarder) handleDNSQueryTCP(w dns.ResponseWriter, query *dns.Msg) {
 	startTime := time.Now()
-	logger := log.WithFields(log.Fields{
+	fields := log.Fields{
 		"request_id": resutil.GenerateRequestID(),
 		"dns_id":     fmt.Sprintf("%04x", query.Id),
-	})
+	}
+	if addr := w.RemoteAddr(); addr != nil {
+		fields["client"] = addr.String()
+	}
+	logger := log.WithFields(fields)
 
 	f.handleDNSQuery(logger, w, query, startTime)
 }

client/internal/engine.go

@@ -46,6 +46,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer/guard"
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
+	"github.com/netbirdio/netbird/client/internal/portforward"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/relay"
 	"github.com/netbirdio/netbird/client/internal/rosenpass"
@@ -210,9 +211,10 @@ type Engine struct {
 	// checks are the client-applied posture checks that need to be evaluated on the client
 	checks []*mgmProto.Checks
 
-	relayManager *relayClient.Manager
-	stateManager *statemanager.Manager
-	srWatcher    *guard.SRWatcher
+	relayManager       *relayClient.Manager
+	stateManager       *statemanager.Manager
+	portForwardManager *portforward.Manager
+	srWatcher          *guard.SRWatcher
 
 	// Sync response persistence (protected by syncRespMux)
 	syncRespMux         sync.RWMutex
@@ -259,26 +261,27 @@ func NewEngine(
 	mobileDep MobileDependency,
 ) *Engine {
 	engine := &Engine{
-		clientCtx:      clientCtx,
-		clientCancel:   clientCancel,
-		signal:         services.SignalClient,
-		signaler:       peer.NewSignaler(services.SignalClient, config.WgPrivateKey),
-		mgmClient:      services.MgmClient,
-		relayManager:   services.RelayManager,
-		peerStore:      peerstore.NewConnStore(),
-		syncMsgMux:     &sync.Mutex{},
-		config:         config,
-		mobileDep:      mobileDep,
-		STUNs:          []*stun.URI{},
-		TURNs:          []*stun.URI{},
-		networkSerial:  0,
-		statusRecorder: services.StatusRecorder,
-		stateManager:   services.StateManager,
-		checks:         services.Checks,
-		probeStunTurn:  relay.NewStunTurnProbe(relay.DefaultCacheTTL),
-		jobExecutor:    jobexec.NewExecutor(),
-		clientMetrics:  services.ClientMetrics,
-		updateManager:  services.UpdateManager,
+		clientCtx:          clientCtx,
+		clientCancel:       clientCancel,
+		signal:             services.SignalClient,
+		signaler:           peer.NewSignaler(services.SignalClient, config.WgPrivateKey),
+		mgmClient:          services.MgmClient,
+		relayManager:       services.RelayManager,
+		peerStore:          peerstore.NewConnStore(),
+		syncMsgMux:         &sync.Mutex{},
+		config:             config,
+		mobileDep:          mobileDep,
+		STUNs:              []*stun.URI{},
+		TURNs:              []*stun.URI{},
+		networkSerial:      0,
+		statusRecorder:     services.StatusRecorder,
+		stateManager:       services.StateManager,
+		portForwardManager: portforward.NewManager(),
+		checks:             services.Checks,
+		probeStunTurn:      relay.NewStunTurnProbe(relay.DefaultCacheTTL),
+		jobExecutor:        jobexec.NewExecutor(),
+		clientMetrics:      services.ClientMetrics,
+		updateManager:      services.UpdateManager,
 	}
 
 	log.Infof("I am: %s", config.WgPrivateKey.PublicKey().String())
@@ -500,7 +503,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 	e.routeManager.SetRouteChangeListener(e.mobileDep.NetworkChangeListener)
 
 	e.dnsServer.SetRouteChecker(func(ip netip.Addr) bool {
-		for _, routes := range e.routeManager.GetClientRoutes() {
+		for _, routes := range e.routeManager.GetSelectedClientRoutes() {
 			for _, r := range routes {
 				if r.Network.Contains(ip) {
 					return true
@@ -521,6 +524,11 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		return err
 	}
 
+	// Inject firewall into DNS server now that it's available.
+	// The DNS server is created before the firewall because the route manager
+	// depends on the DNS server, and the firewall depends on the wg interface.
+	e.dnsServer.SetFirewall(e.firewall)
+
 	e.udpMux, err = e.wgInterface.Up()
 	if err != nil {
 		log.Errorf("failed to pull up wgInterface [%s]: %s", e.wgInterface.Name(), err.Error())
@@ -532,6 +540,13 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 	// conntrack entries from being created before the rules are in place
 	e.setupWGProxyNoTrack()
 
+	// Start after interface is up since port may have been resolved from 0 or changed if occupied
+	e.shutdownWg.Add(1)
+	go func() {
+		defer e.shutdownWg.Done()
+		e.portForwardManager.Start(e.ctx, uint16(e.config.WgPort))
+	}()
+
 	// Set the WireGuard interface for rosenpass after interface is up
 	if e.rpManager != nil {
 		e.rpManager.SetInterface(e.wgInterface)
@@ -1535,12 +1550,13 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 	}
 
 	serviceDependencies := peer.ServiceDependencies{
-		StatusRecorder:  e.statusRecorder,
-		Signaler:        e.signaler,
-		IFaceDiscover:   e.mobileDep.IFaceDiscover,
-		RelayManager:    e.relayManager,
-		SrWatcher:       e.srWatcher,
-		MetricsRecorder: e.clientMetrics,
+		StatusRecorder:     e.statusRecorder,
+		Signaler:           e.signaler,
+		IFaceDiscover:      e.mobileDep.IFaceDiscover,
+		RelayManager:       e.relayManager,
+		SrWatcher:          e.srWatcher,
+		PortForwardManager: e.portForwardManager,
+		MetricsRecorder:    e.clientMetrics,
 	}
 	peerConn, err := peer.NewConn(config, serviceDependencies)
 	if err != nil {
@@ -1697,6 +1713,12 @@ func (e *Engine) close() {
 	if e.rpManager != nil {
 		_ = e.rpManager.Close()
 	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+	if err := e.portForwardManager.GracefullyStop(ctx); err != nil {
+		log.Warnf("failed to gracefully stop port forwarding manager: %s", err)
+	}
 }
 
 func (e *Engine) readInitialSettings() ([]*route.Route, *nbdns.Config, bool, error) {
@@ -1800,7 +1822,7 @@ func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
 		return dnsServer, nil
 
 	case "ios":
-		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.statusRecorder, e.config.DisableDNS)
+		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.mobileDep.HostDNSAddresses, e.statusRecorder, e.config.DisableDNS)
 		return dnsServer, nil
 
 	default:
@@ -1837,6 +1859,11 @@ func (e *Engine) GetExposeManager() *expose.Manager {
 	return e.exposeManager
 }
 
+// IsBlockInbound returns whether inbound connections are blocked.
+func (e *Engine) IsBlockInbound() bool {
+	return e.config.BlockInbound
+}
+
 // GetClientMetrics returns the client metrics
 func (e *Engine) GetClientMetrics() *metrics.ClientMetrics {
 	return e.clientMetrics

client/internal/engine_test.go

@@ -828,7 +828,7 @@ func TestEngine_UpdateNetworkMapWithRoutes(t *testing.T) {
 				WgPrivateKey: key,
 				WgPort:       33100,
 				MTU:          iface.DefaultMTU,
-	}, EngineServices{
+			}, EngineServices{
 				SignalClient:   &signal.MockClient{},
 				MgmClient:      &mgmt.MockClient{},
 				RelayManager:   relayMgr,
@@ -1035,7 +1035,7 @@ func TestEngine_UpdateNetworkMapWithDNSUpdate(t *testing.T) {
 				WgPrivateKey: key,
 				WgPort:       33100,
 				MTU:          iface.DefaultMTU,
-	}, EngineServices{
+			}, EngineServices{
 				SignalClient:   &signal.MockClient{},
 				MgmClient:      &mgmt.MockClient{},
 				RelayManager:   relayMgr,
@@ -1538,13 +1538,8 @@ func createEngine(ctx context.Context, cancel context.CancelFunc, setupKey strin
 		return nil, err
 	}
 
-	publicKey, err := mgmtClient.GetServerPublicKey()
-	if err != nil {
-		return nil, err
-	}
-
 	info := system.GetInfo(ctx)
-	resp, err := mgmtClient.Register(*publicKey, setupKey, "", info, nil, nil)
+	resp, err := mgmtClient.Register(setupKey, "", info, nil, nil)
 	if err != nil {
 		return nil, err
 	}
@@ -1566,7 +1561,7 @@ func createEngine(ctx context.Context, cancel context.CancelFunc, setupKey strin
 	}
 
 	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String(), iface.DefaultMTU)
-e, err := NewEngine(ctx, cancel, conf, EngineServices{
+	e, err := NewEngine(ctx, cancel, conf, EngineServices{
 		SignalClient:   signalClient,
 		MgmClient:      mgmtClient,
 		RelayManager:   relayMgr,

client/internal/peer/conn.go

@@ -22,6 +22,7 @@ import (
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
 	"github.com/netbirdio/netbird/client/internal/peer/id"
 	"github.com/netbirdio/netbird/client/internal/peer/worker"
+	"github.com/netbirdio/netbird/client/internal/portforward"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 	"github.com/netbirdio/netbird/route"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
@@ -45,6 +46,7 @@ type ServiceDependencies struct {
 	RelayManager       *relayClient.Manager
 	SrWatcher          *guard.SRWatcher
 	PeerConnDispatcher *dispatcher.ConnectionDispatcher
+	PortForwardManager *portforward.Manager
 	MetricsRecorder    MetricsRecorder
 }
 
@@ -87,16 +89,17 @@ type ConnConfig struct {
 }
 
 type Conn struct {
-	Log            *log.Entry
-	mu             sync.Mutex
-	ctx            context.Context
-	ctxCancel      context.CancelFunc
-	config         ConnConfig
-	statusRecorder *Status
-	signaler       *Signaler
-	iFaceDiscover  stdnet.ExternalIFaceDiscover
-	relayManager   *relayClient.Manager
-	srWatcher      *guard.SRWatcher
+	Log                *log.Entry
+	mu                 sync.Mutex
+	ctx                context.Context
+	ctxCancel          context.CancelFunc
+	config             ConnConfig
+	statusRecorder     *Status
+	signaler           *Signaler
+	iFaceDiscover      stdnet.ExternalIFaceDiscover
+	relayManager       *relayClient.Manager
+	srWatcher          *guard.SRWatcher
+	portForwardManager *portforward.Manager
 
 	onConnected                               func(remoteWireGuardKey string, remoteRosenpassPubKey []byte, wireGuardIP string, remoteRosenpassAddr string)
 	onDisconnected                            func(remotePeer string)
@@ -145,19 +148,20 @@ func NewConn(config ConnConfig, services ServiceDependencies) (*Conn, error) {
 
 	dumpState := newStateDump(config.Key, connLog, services.StatusRecorder)
 	var conn = &Conn{
-		Log:             connLog,
-		config:          config,
-		statusRecorder:  services.StatusRecorder,
-		signaler:        services.Signaler,
-		iFaceDiscover:   services.IFaceDiscover,
-		relayManager:    services.RelayManager,
-		srWatcher:       services.SrWatcher,
-		statusRelay:     worker.NewAtomicStatus(),
-		statusICE:       worker.NewAtomicStatus(),
-		dumpState:       dumpState,
-		endpointUpdater: NewEndpointUpdater(connLog, config.WgConfig, isController(config)),
-		wgWatcher:       NewWGWatcher(connLog, config.WgConfig.WgInterface, config.Key, dumpState),
-		metricsRecorder: services.MetricsRecorder,
+		Log:                connLog,
+		config:             config,
+		statusRecorder:     services.StatusRecorder,
+		signaler:           services.Signaler,
+		iFaceDiscover:      services.IFaceDiscover,
+		relayManager:       services.RelayManager,
+		srWatcher:          services.SrWatcher,
+		portForwardManager: services.PortForwardManager,
+		statusRelay:        worker.NewAtomicStatus(),
+		statusICE:          worker.NewAtomicStatus(),
+		dumpState:          dumpState,
+		endpointUpdater:    NewEndpointUpdater(connLog, config.WgConfig, isController(config)),
+		wgWatcher:          NewWGWatcher(connLog, config.WgConfig.WgInterface, config.Key, dumpState),
+		metricsRecorder:    services.MetricsRecorder,
 	}
 
 	return conn, nil

client/internal/peer/worker_ice.go

@@ -16,6 +16,7 @@ import (
 	"github.com/netbirdio/netbird/client/iface/udpmux"
 	"github.com/netbirdio/netbird/client/internal/peer/conntype"
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
+	"github.com/netbirdio/netbird/client/internal/portforward"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 	"github.com/netbirdio/netbird/route"
 )
@@ -61,6 +62,9 @@ type WorkerICE struct {
 
 	// we record the last known state of the ICE agent to avoid duplicate on disconnected events
 	lastKnownState ice.ConnectionState
+
+	// portForwardAttempted tracks if we've already tried port forwarding this session
+	portForwardAttempted bool
 }
 
 func NewWorkerICE(ctx context.Context, log *log.Entry, config ConnConfig, conn *Conn, signaler *Signaler, ifaceDiscover stdnet.ExternalIFaceDiscover, statusRecorder *Status, hasRelayOnLocally bool) (*WorkerICE, error) {
@@ -214,6 +218,8 @@ func (w *WorkerICE) Close() {
 }
 
 func (w *WorkerICE) reCreateAgent(dialerCancel context.CancelFunc, candidates []ice.CandidateType) (*icemaker.ThreadSafeAgent, error) {
+	w.portForwardAttempted = false
+
 	agent, err := icemaker.NewAgent(w.ctx, w.iFaceDiscover, w.config.ICEConfig, candidates, w.localUfrag, w.localPwd)
 	if err != nil {
 		return nil, fmt.Errorf("create agent: %w", err)
@@ -370,6 +376,93 @@ func (w *WorkerICE) onICECandidate(candidate ice.Candidate) {
 			w.log.Errorf("failed signaling candidate to the remote peer %s %s", w.config.Key, err)
 		}
 	}()
+
+	if candidate.Type() == ice.CandidateTypeServerReflexive {
+		w.injectPortForwardedCandidate(candidate)
+	}
+}
+
+// injectPortForwardedCandidate signals an additional candidate using the pre-created port mapping.
+func (w *WorkerICE) injectPortForwardedCandidate(srflxCandidate ice.Candidate) {
+	pfManager := w.conn.portForwardManager
+	if pfManager == nil {
+		return
+	}
+
+	mapping := pfManager.GetMapping()
+	if mapping == nil {
+		return
+	}
+
+	w.muxAgent.Lock()
+	if w.portForwardAttempted {
+		w.muxAgent.Unlock()
+		return
+	}
+	w.portForwardAttempted = true
+	w.muxAgent.Unlock()
+
+	forwardedCandidate, err := w.createForwardedCandidate(srflxCandidate, mapping)
+	if err != nil {
+		w.log.Warnf("create forwarded candidate: %v", err)
+		return
+	}
+
+	w.log.Debugf("injecting port-forwarded candidate: %s (mapping: %d -> %d via %s, priority: %d)",
+		forwardedCandidate.String(), mapping.InternalPort, mapping.ExternalPort, mapping.NATType, forwardedCandidate.Priority())
+
+	go func() {
+		if err := w.signaler.SignalICECandidate(forwardedCandidate, w.config.Key); err != nil {
+			w.log.Errorf("signal port-forwarded candidate: %v", err)
+		}
+	}()
+}
+
+// createForwardedCandidate creates a new server reflexive candidate with the forwarded port.
+// It uses the NAT gateway's external IP with the forwarded port.
+func (w *WorkerICE) createForwardedCandidate(srflxCandidate ice.Candidate, mapping *portforward.Mapping) (ice.Candidate, error) {
+	var externalIP string
+	if mapping.ExternalIP != nil && !mapping.ExternalIP.IsUnspecified() {
+		externalIP = mapping.ExternalIP.String()
+	} else {
+		// Fallback to STUN-discovered address if NAT didn't provide external IP
+		externalIP = srflxCandidate.Address()
+	}
+
+	// Per RFC 8445, the related address for srflx is the base (host candidate address).
+	// If the original srflx has unspecified related address, use its own address as base.
+	relAddr := srflxCandidate.RelatedAddress().Address
+	if relAddr == "" || relAddr == "0.0.0.0" || relAddr == "::" {
+		relAddr = srflxCandidate.Address()
+	}
+
+	// Arbitrary +1000 boost on top of RFC 8445 priority to favor port-forwarded candidates
+	// over regular srflx during ICE connectivity checks.
+	priority := srflxCandidate.Priority() + 1000
+
+	candidate, err := ice.NewCandidateServerReflexive(&ice.CandidateServerReflexiveConfig{
+		Network:   srflxCandidate.NetworkType().String(),
+		Address:   externalIP,
+		Port:      int(mapping.ExternalPort),
+		Component: srflxCandidate.Component(),
+		Priority:  priority,
+		RelAddr:   relAddr,
+		RelPort:   int(mapping.InternalPort),
+	})
+	if err != nil {
+		return nil, fmt.Errorf("create candidate: %w", err)
+	}
+
+	for _, e := range srflxCandidate.Extensions() {
+		if e.Key == ice.ExtensionKeyCandidateID {
+			e.Value = srflxCandidate.ID()
+		}
+		if err := candidate.AddExtension(e); err != nil {
+			return nil, fmt.Errorf("add extension: %w", err)
+		}
+	}
+
+	return candidate, nil
 }
 
 func (w *WorkerICE) onICESelectedCandidatePair(agent *icemaker.ThreadSafeAgent, c1, c2 ice.Candidate) {
@@ -411,10 +504,10 @@ func (w *WorkerICE) logSuccessfulPaths(agent *icemaker.ThreadSafeAgent) {
 			if !lok || !rok {
 				continue
 			}
-			w.log.Debugf("successful ICE path %s: [%s %s %s] <-> [%s %s %s] rtt=%.3fms",
+			w.log.Debugf("successful ICE path %s: [%s %s %s:%d] <-> [%s %s %s:%d] rtt=%.3fms",
 				sessionID,
-				local.NetworkType(), local.Type(), local.Address(),
-				remote.NetworkType(), remote.Type(), remote.Address(),
+				local.NetworkType(), local.Type(), local.Address(), local.Port(),
+				remote.NetworkType(), remote.Type(), remote.Address(), remote.Port(),
 				stat.CurrentRoundTripTime*1000)
 		}
 	}

client/internal/portforward/env.go

@@ -0,0 +1,26 @@
+package portforward
+
+import (
+	"os"
+	"strconv"
+
+	log "github.com/sirupsen/logrus"
+)
+
+const (
+	envDisableNATMapper = "NB_DISABLE_NAT_MAPPER"
+)
+
+func isDisabledByEnv() bool {
+	val := os.Getenv(envDisableNATMapper)
+	if val == "" {
+		return false
+	}
+
+	disabled, err := strconv.ParseBool(val)
+	if err != nil {
+		log.Warnf("failed to parse %s: %v", envDisableNATMapper, err)
+		return false
+	}
+	return disabled
+}

client/internal/portforward/manager.go

@@ -0,0 +1,280 @@
+//go:build !js
+
+package portforward
+
+import (
+	"context"
+	"fmt"
+	"net"
+	"regexp"
+	"sync"
+	"time"
+
+	"github.com/libp2p/go-nat"
+	log "github.com/sirupsen/logrus"
+)
+
+const (
+	defaultMappingTTL  = 2 * time.Hour
+	discoveryTimeout   = 10 * time.Second
+	mappingDescription = "NetBird"
+)
+
+// upnpErrPermanentLeaseOnly matches UPnP error 725 in SOAP fault XML,
+// allowing for whitespace/newlines between tags from different router firmware.
+var upnpErrPermanentLeaseOnly = regexp.MustCompile(`<errorCode>\s*725\s*</errorCode>`)
+
+// Mapping represents an active NAT port mapping.
+type Mapping struct {
+	Protocol     string
+	InternalPort uint16
+	ExternalPort uint16
+	ExternalIP   net.IP
+	NATType      string
+	// TTL is the lease duration. Zero means a permanent lease that never expires.
+	TTL time.Duration
+}
+
+// TODO: persist mapping state for crash recovery cleanup of permanent leases.
+// Currently not done because State.Cleanup requires NAT gateway re-discovery,
+// which blocks startup for ~10s when no gateway is present (affects all clients).
+
+type Manager struct {
+	cancel context.CancelFunc
+
+	mapping     *Mapping
+	mappingLock sync.Mutex
+
+	wgPort uint16
+
+	done    chan struct{}
+	stopCtx chan context.Context
+
+	// protect exported functions
+	mu sync.Mutex
+}
+
+// NewManager creates a new port forwarding manager.
+func NewManager() *Manager {
+	return &Manager{
+		stopCtx: make(chan context.Context, 1),
+	}
+}
+
+func (m *Manager) Start(ctx context.Context, wgPort uint16) {
+	m.mu.Lock()
+	if m.cancel != nil {
+		m.mu.Unlock()
+		return
+	}
+
+	if isDisabledByEnv() {
+		log.Infof("NAT port mapper disabled via %s", envDisableNATMapper)
+		m.mu.Unlock()
+		return
+	}
+
+	if wgPort == 0 {
+		log.Warnf("invalid WireGuard port 0; NAT mapping disabled")
+		m.mu.Unlock()
+		return
+	}
+	m.wgPort = wgPort
+
+	m.done = make(chan struct{})
+	defer close(m.done)
+
+	ctx, m.cancel = context.WithCancel(ctx)
+	m.mu.Unlock()
+
+	gateway, mapping, err := m.setup(ctx)
+	if err != nil {
+		log.Infof("port forwarding setup: %v", err)
+		return
+	}
+
+	m.mappingLock.Lock()
+	m.mapping = mapping
+	m.mappingLock.Unlock()
+
+	m.renewLoop(ctx, gateway, mapping.TTL)
+
+	select {
+	case cleanupCtx := <-m.stopCtx:
+		// block the Start while cleaned up gracefully
+		m.cleanup(cleanupCtx, gateway)
+	default:
+		// return Start immediately and cleanup in background
+		cleanupCtx, cleanupCancel := context.WithTimeout(context.Background(), 10*time.Second)
+		go func() {
+			defer cleanupCancel()
+			m.cleanup(cleanupCtx, gateway)
+		}()
+	}
+}
+
+// GetMapping returns the current mapping if ready, nil otherwise
+func (m *Manager) GetMapping() *Mapping {
+	m.mappingLock.Lock()
+	defer m.mappingLock.Unlock()
+
+	if m.mapping == nil {
+		return nil
+	}
+
+	mapping := *m.mapping
+	return &mapping
+}
+
+// GracefullyStop cancels the manager and attempts to delete the port mapping.
+// After GracefullyStop returns, the manager cannot be restarted.
+func (m *Manager) GracefullyStop(ctx context.Context) error {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	if m.cancel == nil {
+		return nil
+	}
+
+	// Send cleanup context before cancelling, so Start picks it up after renewLoop exits.
+	m.startTearDown(ctx)
+
+	m.cancel()
+	m.cancel = nil
+
+	select {
+	case <-ctx.Done():
+		return ctx.Err()
+	case <-m.done:
+		return nil
+	}
+}
+
+func (m *Manager) setup(ctx context.Context) (nat.NAT, *Mapping, error) {
+	discoverCtx, discoverCancel := context.WithTimeout(ctx, discoveryTimeout)
+	defer discoverCancel()
+
+	gateway, err := nat.DiscoverGateway(discoverCtx)
+	if err != nil {
+		return nil, nil, fmt.Errorf("discover gateway: %w", err)
+	}
+
+	log.Infof("discovered NAT gateway: %s", gateway.Type())
+
+	mapping, err := m.createMapping(ctx, gateway)
+	if err != nil {
+		return nil, nil, fmt.Errorf("create port mapping: %w", err)
+	}
+	return gateway, mapping, nil
+}
+
+func (m *Manager) createMapping(ctx context.Context, gateway nat.NAT) (*Mapping, error) {
+	ctx, cancel := context.WithTimeout(ctx, 30*time.Second)
+	defer cancel()
+
+	ttl := defaultMappingTTL
+	externalPort, err := gateway.AddPortMapping(ctx, "udp", int(m.wgPort), mappingDescription, ttl)
+	if err != nil {
+		if !isPermanentLeaseRequired(err) {
+			return nil, err
+		}
+		log.Infof("gateway only supports permanent leases, retrying with indefinite duration")
+		ttl = 0
+		externalPort, err = gateway.AddPortMapping(ctx, "udp", int(m.wgPort), mappingDescription, ttl)
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	externalIP, err := gateway.GetExternalAddress()
+	if err != nil {
+		log.Debugf("failed to get external address: %v", err)
+		// todo return with err?
+	}
+
+	mapping := &Mapping{
+		Protocol:     "udp",
+		InternalPort: m.wgPort,
+		ExternalPort: uint16(externalPort),
+		ExternalIP:   externalIP,
+		NATType:      gateway.Type(),
+		TTL:          ttl,
+	}
+
+	log.Infof("created port mapping: %d -> %d via %s (external IP: %s)",
+		m.wgPort, externalPort, gateway.Type(), externalIP)
+	return mapping, nil
+}
+
+func (m *Manager) renewLoop(ctx context.Context, gateway nat.NAT, ttl time.Duration) {
+	if ttl == 0 {
+		// Permanent mappings don't expire, just wait for cancellation.
+		<-ctx.Done()
+		return
+	}
+
+	ticker := time.NewTicker(ttl / 2)
+	defer ticker.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+			if err := m.renewMapping(ctx, gateway); err != nil {
+				log.Warnf("failed to renew port mapping: %v", err)
+				continue
+			}
+		}
+	}
+}
+
+func (m *Manager) renewMapping(ctx context.Context, gateway nat.NAT) error {
+	ctx, cancel := context.WithTimeout(ctx, 30*time.Second)
+	defer cancel()
+
+	externalPort, err := gateway.AddPortMapping(ctx, m.mapping.Protocol, int(m.mapping.InternalPort), mappingDescription, m.mapping.TTL)
+	if err != nil {
+		return fmt.Errorf("add port mapping: %w", err)
+	}
+
+	if uint16(externalPort) != m.mapping.ExternalPort {
+		log.Warnf("external port changed on renewal: %d -> %d (candidate may be stale)", m.mapping.ExternalPort, externalPort)
+		m.mappingLock.Lock()
+		m.mapping.ExternalPort = uint16(externalPort)
+		m.mappingLock.Unlock()
+	}
+
+	log.Debugf("renewed port mapping: %d -> %d", m.mapping.InternalPort, m.mapping.ExternalPort)
+	return nil
+}
+
+func (m *Manager) cleanup(ctx context.Context, gateway nat.NAT) {
+	m.mappingLock.Lock()
+	mapping := m.mapping
+	m.mapping = nil
+	m.mappingLock.Unlock()
+
+	if mapping == nil {
+		return
+	}
+
+	if err := gateway.DeletePortMapping(ctx, mapping.Protocol, int(mapping.InternalPort)); err != nil {
+		log.Warnf("delete port mapping on stop: %v", err)
+		return
+	}
+
+	log.Infof("deleted port mapping for port %d", mapping.InternalPort)
+}
+
+func (m *Manager) startTearDown(ctx context.Context) {
+	select {
+	case m.stopCtx <- ctx:
+	default:
+	}
+}
+
+// isPermanentLeaseRequired checks if a UPnP error indicates the gateway only supports permanent leases (error 725).
+func isPermanentLeaseRequired(err error) bool {
+	return err != nil && upnpErrPermanentLeaseOnly.MatchString(err.Error())
+}

client/internal/portforward/manager_js.go

@@ -0,0 +1,39 @@
+package portforward
+
+import (
+	"context"
+	"net"
+	"time"
+)
+
+// Mapping represents an active NAT port mapping.
+type Mapping struct {
+	Protocol     string
+	InternalPort uint16
+	ExternalPort uint16
+	ExternalIP   net.IP
+	NATType      string
+	// TTL is the lease duration. Zero means a permanent lease that never expires.
+	TTL time.Duration
+}
+
+// Manager is a stub for js/wasm builds where NAT-PMP/UPnP is not supported.
+type Manager struct{}
+
+// NewManager returns a stub manager for js/wasm builds.
+func NewManager() *Manager {
+	return &Manager{}
+}
+
+// Start is a no-op on js/wasm: NAT-PMP/UPnP is not available in browser environments.
+func (m *Manager) Start(context.Context, uint16) {
+	// no NAT traversal in wasm
+}
+
+// GracefullyStop is a no-op on js/wasm.
+func (m *Manager) GracefullyStop(context.Context) error { return nil }
+
+// GetMapping always returns nil on js/wasm.
+func (m *Manager) GetMapping() *Mapping {
+	return nil
+}

client/internal/portforward/manager_test.go

@@ -0,0 +1,201 @@
+//go:build !js
+
+package portforward
+
+import (
+	"context"
+	"fmt"
+	"net"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+type mockNAT struct {
+	natType             string
+	deviceAddr          net.IP
+	externalAddr        net.IP
+	internalAddr        net.IP
+	mappings            map[int]int
+	addMappingErr       error
+	deleteMappingErr    error
+	onlyPermanentLeases bool
+	lastTimeout         time.Duration
+}
+
+func newMockNAT() *mockNAT {
+	return &mockNAT{
+		natType:      "Mock-NAT",
+		deviceAddr:   net.ParseIP("192.168.1.1"),
+		externalAddr: net.ParseIP("203.0.113.50"),
+		internalAddr: net.ParseIP("192.168.1.100"),
+		mappings:     make(map[int]int),
+	}
+}
+
+func (m *mockNAT) Type() string {
+	return m.natType
+}
+
+func (m *mockNAT) GetDeviceAddress() (net.IP, error) {
+	return m.deviceAddr, nil
+}
+
+func (m *mockNAT) GetExternalAddress() (net.IP, error) {
+	return m.externalAddr, nil
+}
+
+func (m *mockNAT) GetInternalAddress() (net.IP, error) {
+	return m.internalAddr, nil
+}
+
+func (m *mockNAT) AddPortMapping(ctx context.Context, protocol string, internalPort int, description string, timeout time.Duration) (int, error) {
+	if m.addMappingErr != nil {
+		return 0, m.addMappingErr
+	}
+	if m.onlyPermanentLeases && timeout != 0 {
+		return 0, fmt.Errorf("SOAP fault. Code:  | Explanation:  | Detail: <UPnPError xmlns=\"urn:schemas-upnp-org:control-1-0\"><errorCode>725</errorCode><errorDescription>OnlyPermanentLeasesSupported</errorDescription></UPnPError>")
+	}
+	externalPort := internalPort
+	m.mappings[internalPort] = externalPort
+	m.lastTimeout = timeout
+	return externalPort, nil
+}
+
+func (m *mockNAT) DeletePortMapping(ctx context.Context, protocol string, internalPort int) error {
+	if m.deleteMappingErr != nil {
+		return m.deleteMappingErr
+	}
+	delete(m.mappings, internalPort)
+	return nil
+}
+
+func TestManager_CreateMapping(t *testing.T) {
+	m := NewManager()
+	m.wgPort = 51820
+
+	gateway := newMockNAT()
+	mapping, err := m.createMapping(context.Background(), gateway)
+	require.NoError(t, err)
+	require.NotNil(t, mapping)
+
+	assert.Equal(t, "udp", mapping.Protocol)
+	assert.Equal(t, uint16(51820), mapping.InternalPort)
+	assert.Equal(t, uint16(51820), mapping.ExternalPort)
+	assert.Equal(t, "Mock-NAT", mapping.NATType)
+	assert.Equal(t, net.ParseIP("203.0.113.50").To4(), mapping.ExternalIP.To4())
+	assert.Equal(t, defaultMappingTTL, mapping.TTL)
+}
+
+func TestManager_GetMapping_ReturnsNilWhenNotReady(t *testing.T) {
+	m := NewManager()
+	assert.Nil(t, m.GetMapping())
+}
+
+func TestManager_GetMapping_ReturnsCopy(t *testing.T) {
+	m := NewManager()
+	m.mapping = &Mapping{
+		Protocol:     "udp",
+		InternalPort: 51820,
+		ExternalPort: 51820,
+	}
+
+	mapping := m.GetMapping()
+	require.NotNil(t, mapping)
+	assert.Equal(t, uint16(51820), mapping.InternalPort)
+
+	// Mutating the returned copy should not affect the manager's mapping.
+	mapping.ExternalPort = 9999
+	assert.Equal(t, uint16(51820), m.GetMapping().ExternalPort)
+}
+
+func TestManager_Cleanup_DeletesMapping(t *testing.T) {
+	m := NewManager()
+	m.mapping = &Mapping{
+		Protocol:     "udp",
+		InternalPort: 51820,
+		ExternalPort: 51820,
+	}
+
+	gateway := newMockNAT()
+	// Seed the mock so we can verify deletion.
+	gateway.mappings[51820] = 51820
+
+	m.cleanup(context.Background(), gateway)
+
+	_, exists := gateway.mappings[51820]
+	assert.False(t, exists, "mapping should be deleted from gateway")
+	assert.Nil(t, m.GetMapping(), "in-memory mapping should be cleared")
+}
+
+func TestManager_Cleanup_NilMapping(t *testing.T) {
+	m := NewManager()
+	gateway := newMockNAT()
+
+	// Should not panic or call gateway.
+	m.cleanup(context.Background(), gateway)
+}
+
+
+func TestManager_CreateMapping_PermanentLeaseFallback(t *testing.T) {
+	m := NewManager()
+	m.wgPort = 51820
+
+	gateway := newMockNAT()
+	gateway.onlyPermanentLeases = true
+
+	mapping, err := m.createMapping(context.Background(), gateway)
+	require.NoError(t, err)
+	require.NotNil(t, mapping)
+
+	assert.Equal(t, uint16(51820), mapping.InternalPort)
+	assert.Equal(t, time.Duration(0), mapping.TTL, "should return zero TTL for permanent lease")
+	assert.Equal(t, time.Duration(0), gateway.lastTimeout, "should have retried with zero duration")
+}
+
+func TestIsPermanentLeaseRequired(t *testing.T) {
+	tests := []struct {
+		name     string
+		err      error
+		expected bool
+	}{
+		{
+			name:     "nil error",
+			err:      nil,
+			expected: false,
+		},
+		{
+			name:     "UPnP error 725",
+			err:      fmt.Errorf("SOAP fault. Code:  | Detail: <UPnPError><errorCode>725</errorCode><errorDescription>OnlyPermanentLeasesSupported</errorDescription></UPnPError>"),
+			expected: true,
+		},
+		{
+			name:     "wrapped error with 725",
+			err:      fmt.Errorf("add port mapping: %w", fmt.Errorf("Detail: <errorCode>725</errorCode>")),
+			expected: true,
+		},
+		{
+			name:     "error 725 with newlines in XML",
+			err:      fmt.Errorf("<errorCode>\n  725\n</errorCode>"),
+			expected: true,
+		},
+		{
+			name:     "bare 725 without XML tag",
+			err:      fmt.Errorf("error code 725"),
+			expected: false,
+		},
+		{
+			name:     "unrelated error",
+			err:      fmt.Errorf("connection refused"),
+			expected: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equal(t, tt.expected, isPermanentLeaseRequired(tt.err))
+		})
+	}
+}

client/internal/profilemanager/config.go

@@ -41,7 +41,7 @@ const (
 
 // mgmProber is the subset of management client needed for URL migration probes.
 type mgmProber interface {
-	GetServerPublicKey() (*wgtypes.Key, error)
+	HealthCheck() error
 	Close() error
 }
 
@@ -777,8 +777,7 @@ func UpdateOldManagementURL(ctx context.Context, config *Config, configPath stri
 	}()
 
 	// gRPC check
-	_, err = client.GetServerPublicKey()
-	if err != nil {
+	if err = client.HealthCheck(); err != nil {
 		log.Infof("couldn't switch to the new Management %s", newURL.String())
 		return nil, err
 	}

client/internal/profilemanager/config_test.go

@@ -17,12 +17,10 @@ import (
 	"github.com/netbirdio/netbird/util"
 )
 
-type mockMgmProber struct {
-	key wgtypes.Key
-}
+type mockMgmProber struct{}
 
-func (m *mockMgmProber) GetServerPublicKey() (*wgtypes.Key, error) {
-	return &m.key, nil
+func (m *mockMgmProber) HealthCheck() error {
+	return nil
 }
 
 func (m *mockMgmProber) Close() error { return nil }
@@ -247,11 +245,7 @@ func TestWireguardPortDefaultVsExplicit(t *testing.T) {
 func TestUpdateOldManagementURL(t *testing.T) {
 	origProber := newMgmProber
 	newMgmProber = func(_ context.Context, _ string, _ wgtypes.Key, _ bool) (mgmProber, error) {
-		key, err := wgtypes.GenerateKey()
-		if err != nil {
-			return nil, err
-		}
-		return &mockMgmProber{key: key.PublicKey()}, nil
+		return &mockMgmProber{}, nil
 	}
 	t.Cleanup(func() { newMgmProber = origProber })
 

client/internal/routemanager/manager.go

@@ -52,6 +52,7 @@ type Manager interface {
 	TriggerSelection(route.HAMap)
 	GetRouteSelector() *routeselector.RouteSelector
 	GetClientRoutes() route.HAMap
+	GetSelectedClientRoutes() route.HAMap
 	GetClientRoutesWithNetID() map[route.NetID][]*route.Route
 	SetRouteChangeListener(listener listener.NetworkChangeListener)
 	InitialRouteRange() []string
@@ -167,6 +168,7 @@ func (m *DefaultManager) setupAndroidRoutes(config ManagerConfig) {
 			NetworkType: route.IPv4Network,
 		}
 		cr = append(cr, fakeIPRoute)
+		m.notifier.SetFakeIPRoute(fakeIPRoute)
 	}
 
 	m.notifier.SetInitialClientRoutes(cr, routesForComparison)
@@ -465,6 +467,16 @@ func (m *DefaultManager) GetClientRoutes() route.HAMap {
 	return maps.Clone(m.clientRoutes)
 }
 
+// GetSelectedClientRoutes returns only the currently selected/active client routes,
+// filtering out deselected exit nodes. Use this instead of GetClientRoutes when checking
+// if traffic should be routed through the tunnel.
+func (m *DefaultManager) GetSelectedClientRoutes() route.HAMap {
+	m.mux.Lock()
+	defer m.mux.Unlock()
+
+	return m.routeSelector.FilterSelectedExitNodes(maps.Clone(m.clientRoutes))
+}
+
 // GetClientRoutesWithNetID returns the current routes from the route map, but the keys consist of the network ID only
 func (m *DefaultManager) GetClientRoutesWithNetID() map[route.NetID][]*route.Route {
 	m.mux.Lock()

client/internal/routemanager/mock.go

@@ -18,6 +18,7 @@ type MockManager struct {
 	TriggerSelectionFunc         func(haMap route.HAMap)
 	GetRouteSelectorFunc         func() *routeselector.RouteSelector
 	GetClientRoutesFunc          func() route.HAMap
+	GetSelectedClientRoutesFunc  func() route.HAMap
 	GetClientRoutesWithNetIDFunc func() map[route.NetID][]*route.Route
 	StopFunc                     func(manager *statemanager.Manager)
 }
@@ -61,7 +62,7 @@ func (m *MockManager) GetRouteSelector() *routeselector.RouteSelector {
 	return nil
 }
 
-// GetClientRoutes mock implementation of GetClientRoutes from Manager interface
+// GetClientRoutes mock implementation of GetClientRoutes from the Manager interface
 func (m *MockManager) GetClientRoutes() route.HAMap {
 	if m.GetClientRoutesFunc != nil {
 		return m.GetClientRoutesFunc()
@@ -69,6 +70,14 @@ func (m *MockManager) GetClientRoutes() route.HAMap {
 	return nil
 }
 
+// GetSelectedClientRoutes mock implementation of GetSelectedClientRoutes from the Manager interface
+func (m *MockManager) GetSelectedClientRoutes() route.HAMap {
+	if m.GetSelectedClientRoutesFunc != nil {
+		return m.GetSelectedClientRoutesFunc()
+	}
+	return nil
+}
+
 // GetClientRoutesWithNetID mock implementation of GetClientRoutesWithNetID from Manager interface
 func (m *MockManager) GetClientRoutesWithNetID() map[route.NetID][]*route.Route {
 	if m.GetClientRoutesWithNetIDFunc != nil {

client/internal/routemanager/notifier/notifier_android.go

@@ -16,6 +16,7 @@ import (
 type Notifier struct {
 	initialRoutes []*route.Route
 	currentRoutes []*route.Route
+	fakeIPRoute   *route.Route
 
 	listener    listener.NetworkChangeListener
 	listenerMux sync.Mutex
@@ -31,13 +32,17 @@ func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
 	n.listener = listener
 }
 
-// SetInitialClientRoutes stores the full initial route set (including fake IP blocks)
-// and a separate comparison set (without fake IP blocks) for diff detection.
+// SetInitialClientRoutes stores the initial route sets for TUN configuration.
 func (n *Notifier) SetInitialClientRoutes(initialRoutes []*route.Route, routesForComparison []*route.Route) {
 	n.initialRoutes = filterStatic(initialRoutes)
 	n.currentRoutes = filterStatic(routesForComparison)
 }
 
+// SetFakeIPRoute stores the fake IP route to be included in every TUN rebuild.
+func (n *Notifier) SetFakeIPRoute(r *route.Route) {
+	n.fakeIPRoute = r
+}
+
 func (n *Notifier) OnNewRoutes(idMap route.HAMap) {
 	var newRoutes []*route.Route
 	for _, routes := range idMap {
@@ -69,7 +74,9 @@ func (n *Notifier) notify() {
 	}
 
 	allRoutes := slices.Clone(n.currentRoutes)
-	allRoutes = append(allRoutes, n.extraInitialRoutes()...)
+	if n.fakeIPRoute != nil {
+		allRoutes = append(allRoutes, n.fakeIPRoute)
+	}
 
 	routeStrings := n.routesToStrings(allRoutes)
 	sort.Strings(routeStrings)
@@ -78,23 +85,6 @@ func (n *Notifier) notify() {
 	}(n.listener)
 }
 
-// extraInitialRoutes returns initialRoutes whose network prefix is absent
-// from currentRoutes (e.g. the fake IP block added at setup time).
-func (n *Notifier) extraInitialRoutes() []*route.Route {
-	currentNets := make(map[netip.Prefix]struct{}, len(n.currentRoutes))
-	for _, r := range n.currentRoutes {
-		currentNets[r.Network] = struct{}{}
-	}
-
-	var extra []*route.Route
-	for _, r := range n.initialRoutes {
-		if _, ok := currentNets[r.Network]; !ok {
-			extra = append(extra, r)
-		}
-	}
-	return extra
-}
-
 func filterStatic(routes []*route.Route) []*route.Route {
 	out := make([]*route.Route, 0, len(routes))
 	for _, r := range routes {

client/internal/routemanager/notifier/notifier_ios.go

@@ -34,6 +34,10 @@ func (n *Notifier) SetInitialClientRoutes([]*route.Route, []*route.Route) {
 	// iOS doesn't care about initial routes
 }
 
+func (n *Notifier) SetFakeIPRoute(*route.Route) {
+	// Not used on iOS
+}
+
 func (n *Notifier) OnNewRoutes(route.HAMap) {
 	// Not used on iOS
 }
@@ -53,7 +57,6 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) {
 	n.currentPrefixes = newNets
 	n.notify()
 }
-
 func (n *Notifier) notify() {
 	n.listenerMux.Lock()
 	defer n.listenerMux.Unlock()

client/internal/routemanager/notifier/notifier_other.go

@@ -23,6 +23,10 @@ func (n *Notifier) SetInitialClientRoutes([]*route.Route, []*route.Route) {
 	// Not used on non-mobile platforms
 }
 
+func (n *Notifier) SetFakeIPRoute(*route.Route) {
+	// Not used on non-mobile platforms
+}
+
 func (n *Notifier) OnNewRoutes(idMap route.HAMap) {
 	// Not used on non-mobile platforms
 }

client/ios/NetBirdSDK/client.go

@@ -161,7 +161,11 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	cfg.WgIface = interfaceName
 
 	c.connectClient = internal.NewConnectClient(ctx, cfg, c.recorder)
-	return c.connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile)
+	hostDNS := []netip.AddrPort{
+		netip.MustParseAddrPort("9.9.9.9:53"),
+		netip.MustParseAddrPort("149.112.112.112:53"),
+	}
+	return c.connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, hostDNS, c.stateFile)
 }
 
 // Stop the internal client and free the resources

client/server/server.go

@@ -1359,6 +1359,10 @@ func (s *Server) ExposeService(req *proto.ExposeServiceRequest, srv proto.Daemon
 		return gstatus.Errorf(codes.FailedPrecondition, "engine not initialized")
 	}
 
+	if engine.IsBlockInbound() {
+		return gstatus.Errorf(codes.FailedPrecondition, "expose requires inbound connections but 'block inbound' is enabled, disable it first")
+	}
+
 	mgr := engine.GetExposeManager()
 	if mgr == nil {
 		return gstatus.Errorf(codes.Internal, "expose manager not available")

client/server/state_generic.go

@@ -9,6 +9,7 @@ import (
 	"github.com/netbirdio/netbird/client/ssh/config"
 )
 
+// registerStates registers all states that need crash recovery cleanup.
 func registerStates(mgr *statemanager.Manager) {
 	mgr.RegisterState(&dns.ShutdownState{})
 	mgr.RegisterState(&systemops.ShutdownState{})

client/server/state_linux.go

@@ -11,6 +11,7 @@ import (
 	"github.com/netbirdio/netbird/client/ssh/config"
 )
 
+// registerStates registers all states that need crash recovery cleanup.
 func registerStates(mgr *statemanager.Manager) {
 	mgr.RegisterState(&dns.ShutdownState{})
 	mgr.RegisterState(&systemops.ShutdownState{})

client/ssh/proxy/proxy.go

@@ -141,7 +141,7 @@ func (p *SSHProxy) runProxySSHServer(jwtToken string) error {
 
 func (p *SSHProxy) handleSSHSession(session ssh.Session) {
 	ptyReq, winCh, isPty := session.Pty()
-	hasCommand := len(session.Command()) > 0
+	hasCommand := session.RawCommand() != ""
 
 	sshClient, err := p.getOrCreateBackendClient(session.Context(), session.User())
 	if err != nil {
@@ -180,7 +180,7 @@ func (p *SSHProxy) handleSSHSession(session ssh.Session) {
 	}
 
 	if hasCommand {
-		if err := serverSession.Run(strings.Join(session.Command(), " ")); err != nil {
+		if err := serverSession.Run(session.RawCommand()); err != nil {
 			log.Debugf("run command: %v", err)
 			p.handleProxyExitCode(session, err)
 		}

client/ssh/proxy/proxy_test.go

@@ -1,6 +1,7 @@
 package proxy
 
 import (
+	"bytes"
 	"context"
 	"crypto/rand"
 	"crypto/rsa"
@@ -245,6 +246,191 @@ func TestSSHProxy_Connect(t *testing.T) {
 	cancel()
 }
 
+// TestSSHProxy_CommandQuoting verifies that the proxy preserves shell quoting
+// when forwarding commands to the backend. This is critical for tools like
+// Ansible that send commands such as:
+//
+//	/bin/sh -c '( umask 77 && mkdir -p ... ) && sleep 0'
+//
+// The single quotes must be preserved so the backend shell receives the
+// subshell expression as a single argument to -c.
+func TestSSHProxy_CommandQuoting(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+
+	sshClient, cleanup := setupProxySSHClient(t)
+	defer cleanup()
+
+	// These commands simulate what the SSH protocol delivers as exec payloads.
+	// When a user types: ssh host '/bin/sh -c "( echo hello )"'
+	// the local shell strips the outer single quotes, and the SSH exec request
+	// contains the raw string: /bin/sh -c "( echo hello )"
+	//
+	// The proxy must forward this string verbatim. Using session.Command()
+	// (shlex.Split + strings.Join) strips the inner double quotes, breaking
+	// the command on the backend.
+	tests := []struct {
+		name    string
+		command string
+		expect  string
+	}{
+		{
+			name:    "subshell_in_double_quotes",
+			command: `/bin/sh -c "( echo from-subshell ) && echo outer"`,
+			expect:  "from-subshell\nouter\n",
+		},
+		{
+			name:    "printf_with_special_chars",
+			command: `/bin/sh -c "printf '%s\n' 'hello world'"`,
+			expect:  "hello world\n",
+		},
+		{
+			name:    "nested_command_substitution",
+			command: `/bin/sh -c "echo $(echo nested)"`,
+			expect:  "nested\n",
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			session, err := sshClient.NewSession()
+			require.NoError(t, err)
+			defer func() { _ = session.Close() }()
+
+			var stderrBuf bytes.Buffer
+			session.Stderr = &stderrBuf
+
+			outputCh := make(chan []byte, 1)
+			errCh := make(chan error, 1)
+			go func() {
+				output, err := session.Output(tc.command)
+				outputCh <- output
+				errCh <- err
+			}()
+
+			select {
+			case output := <-outputCh:
+				err := <-errCh
+				if stderrBuf.Len() > 0 {
+					t.Logf("stderr: %s", stderrBuf.String())
+				}
+				require.NoError(t, err, "command should succeed: %s", tc.command)
+				assert.Equal(t, tc.expect, string(output), "output mismatch for: %s", tc.command)
+			case <-time.After(5 * time.Second):
+				t.Fatalf("command timed out: %s", tc.command)
+			}
+		})
+	}
+}
+
+// setupProxySSHClient creates a full proxy test environment and returns
+// an SSH client connected through the proxy to a backend NetBird SSH server.
+func setupProxySSHClient(t *testing.T) (*cryptossh.Client, func()) {
+	t.Helper()
+
+	const (
+		issuer   = "https://test-issuer.example.com"
+		audience = "test-audience"
+	)
+
+	jwksServer, privateKey, jwksURL := setupJWKSServer(t)
+
+	hostKey, err := nbssh.GeneratePrivateKey(nbssh.ED25519)
+	require.NoError(t, err)
+	hostPubKey, err := nbssh.GeneratePublicKey(hostKey)
+	require.NoError(t, err)
+
+	serverConfig := &server.Config{
+		HostKeyPEM: hostKey,
+		JWT: &server.JWTConfig{
+			Issuer:       issuer,
+			Audiences:    []string{audience},
+			KeysLocation: jwksURL,
+		},
+	}
+	sshServer := server.New(serverConfig)
+	sshServer.SetAllowRootLogin(true)
+
+	testUsername := testutil.GetTestUsername(t)
+	testJWTUser := "test-username"
+	testUserHash, err := sshuserhash.HashUserID(testJWTUser)
+	require.NoError(t, err)
+
+	authConfig := &sshauth.Config{
+		UserIDClaim:     sshauth.DefaultUserIDClaim,
+		AuthorizedUsers: []sshuserhash.UserIDHash{testUserHash},
+		MachineUsers: map[string][]uint32{
+			testUsername: {0},
+		},
+	}
+	sshServer.UpdateSSHAuth(authConfig)
+
+	sshServerAddr := server.StartTestServer(t, sshServer)
+
+	mockDaemon := startMockDaemon(t)
+
+	host, portStr, err := net.SplitHostPort(sshServerAddr)
+	require.NoError(t, err)
+	port, err := strconv.Atoi(portStr)
+	require.NoError(t, err)
+
+	mockDaemon.setHostKey(host, hostPubKey)
+
+	validToken := generateValidJWT(t, privateKey, issuer, audience, testJWTUser)
+	mockDaemon.setJWTToken(validToken)
+
+	proxyInstance, err := New(mockDaemon.addr, host, port, io.Discard, nil)
+	require.NoError(t, err)
+
+	origStdin := os.Stdin
+	origStdout := os.Stdout
+
+	stdinReader, stdinWriter, err := os.Pipe()
+	require.NoError(t, err)
+	stdoutReader, stdoutWriter, err := os.Pipe()
+	require.NoError(t, err)
+
+	os.Stdin = stdinReader
+	os.Stdout = stdoutWriter
+
+	clientConn, proxyConn := net.Pipe()
+
+	go func() { _, _ = io.Copy(stdinWriter, proxyConn) }()
+	go func() { _, _ = io.Copy(proxyConn, stdoutReader) }()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+
+	go func() {
+		_ = proxyInstance.Connect(ctx)
+	}()
+
+	sshConfig := &cryptossh.ClientConfig{
+		User:            testutil.GetTestUsername(t),
+		Auth:            []cryptossh.AuthMethod{},
+		HostKeyCallback: cryptossh.InsecureIgnoreHostKey(),
+		Timeout:         5 * time.Second,
+	}
+
+	sshClientConn, chans, reqs, err := cryptossh.NewClientConn(clientConn, "test", sshConfig)
+	require.NoError(t, err)
+
+	client := cryptossh.NewClient(sshClientConn, chans, reqs)
+
+	cleanupFn := func() {
+		_ = client.Close()
+		_ = clientConn.Close()
+		cancel()
+		os.Stdin = origStdin
+		os.Stdout = origStdout
+		_ = sshServer.Stop()
+		mockDaemon.stop()
+		jwksServer.Close()
+	}
+
+	return client, cleanupFn
+}
+
 type mockDaemonServer struct {
 	proto.UnimplementedDaemonServiceServer
 	hostKeys map[string][]byte

client/ssh/server/server.go

@@ -284,19 +284,21 @@ func (s *Server) closeListener(ln net.Listener) {
 // Stop closes the SSH server
 func (s *Server) Stop() error {
 	s.mu.Lock()
-	defer s.mu.Unlock()
-
-	if s.sshServer == nil {
+	sshServer := s.sshServer
+	if sshServer == nil {
+		s.mu.Unlock()
 		return nil
 	}
+	s.sshServer = nil
+	s.listener = nil
+	s.mu.Unlock()
 
-	if err := s.sshServer.Close(); err != nil {
+	// Close outside the lock: session handlers need s.mu for unregisterSession.
+	if err := sshServer.Close(); err != nil {
 		log.Debugf("close SSH server: %v", err)
 	}
 
-	s.sshServer = nil
-	s.listener = nil
-
+	s.mu.Lock()
 	maps.Clear(s.sessions)
 	maps.Clear(s.pendingAuthJWT)
 	maps.Clear(s.connections)
@@ -307,6 +309,7 @@ func (s *Server) Stop() error {
 		}
 	}
 	maps.Clear(s.remoteForwardListeners)
+	s.mu.Unlock()
 
 	return nil
 }

client/ssh/server/session_handlers.go

@@ -60,7 +60,7 @@ func (s *Server) sessionHandler(session ssh.Session) {
 	}
 
 	ptyReq, winCh, isPty := session.Pty()
-	hasCommand := len(session.Command()) > 0
+	hasCommand := session.RawCommand() != ""
 
 	if isPty && !hasCommand {
 		// ssh <host> - PTY interactive session (login)

client/system/info.go

@@ -153,6 +153,9 @@ func networkAddresses() ([]NetworkAddress, error) {
 
 	var netAddresses []NetworkAddress
 	for _, iface := range interfaces {
+		if iface.Flags&net.FlagUp == 0 {
+			continue
+		}
 		if iface.HardwareAddr.String() == "" {
 			continue
 		}

client/system/info_freebsd.go

@@ -43,18 +43,24 @@ func GetInfo(ctx context.Context) *Info {
 
 	systemHostname, _ := os.Hostname()
 
+	addrs, err := networkAddresses()
+	if err != nil {
+		log.Warnf("failed to discover network addresses: %s", err)
+	}
+
 	return &Info{
-		GoOS:           runtime.GOOS,
-		Kernel:         osInfo[0],
-		Platform:       runtime.GOARCH,
-		OS:             osName,
-		OSVersion:      osVersion,
-		Hostname:       extractDeviceName(ctx, systemHostname),
-		CPUs:           runtime.NumCPU(),
-		NetbirdVersion: version.NetbirdVersion(),
-		UIVersion:      extractUserAgent(ctx),
-		KernelVersion:  osInfo[1],
-		Environment:    env,
+		GoOS:             runtime.GOOS,
+		Kernel:           osInfo[0],
+		Platform:         runtime.GOARCH,
+		OS:               osName,
+		OSVersion:        osVersion,
+		Hostname:         extractDeviceName(ctx, systemHostname),
+		CPUs:             runtime.NumCPU(),
+		NetbirdVersion:   version.NetbirdVersion(),
+		UIVersion:        extractUserAgent(ctx),
+		KernelVersion:    osInfo[1],
+		NetworkAddresses: addrs,
+		Environment:      env,
 	}
 }
 

client/ui/debug.go

@@ -24,9 +24,10 @@ import (
 
 // Initial state for the debug collection
 type debugInitialState struct {
-	wasDown      bool
-	logLevel     proto.LogLevel
-	isLevelTrace bool
+	wasDown        bool
+	needsRestoreUp bool
+	logLevel       proto.LogLevel
+	isLevelTrace   bool
 }
 
 // Debug collection parameters
@@ -371,46 +372,51 @@ func (s *serviceClient) configureServiceForDebug(
 	conn proto.DaemonServiceClient,
 	state *debugInitialState,
 	enablePersistence bool,
-) error {
+) {
 	if state.wasDown {
 		if _, err := conn.Up(s.ctx, &proto.UpRequest{}); err != nil {
-			return fmt.Errorf("bring service up: %v", err)
+			log.Warnf("failed to bring service up: %v", err)
+		} else {
+			log.Info("Service brought up for debug")
+			time.Sleep(time.Second * 10)
 		}
-		log.Info("Service brought up for debug")
-		time.Sleep(time.Second * 10)
 	}
 
 	if !state.isLevelTrace {
 		if _, err := conn.SetLogLevel(s.ctx, &proto.SetLogLevelRequest{Level: proto.LogLevel_TRACE}); err != nil {
-			return fmt.Errorf("set log level to TRACE: %v", err)
+			log.Warnf("failed to set log level to TRACE: %v", err)
+		} else {
+			log.Info("Log level set to TRACE for debug")
 		}
-		log.Info("Log level set to TRACE for debug")
 	}
 
 	if _, err := conn.Down(s.ctx, &proto.DownRequest{}); err != nil {
-		return fmt.Errorf("bring service down: %v", err)
+		log.Warnf("failed to bring service down: %v", err)
+	} else {
+		state.needsRestoreUp = !state.wasDown
+		time.Sleep(time.Second)
 	}
-	time.Sleep(time.Second)
 
 	if enablePersistence {
 		if _, err := conn.SetSyncResponsePersistence(s.ctx, &proto.SetSyncResponsePersistenceRequest{
 			Enabled: true,
 		}); err != nil {
-			return fmt.Errorf("enable sync response persistence: %v", err)
+			log.Warnf("failed to enable sync response persistence: %v", err)
+		} else {
+			log.Info("Sync response persistence enabled for debug")
 		}
-		log.Info("Sync response persistence enabled for debug")
 	}
 
 	if _, err := conn.Up(s.ctx, &proto.UpRequest{}); err != nil {
-		return fmt.Errorf("bring service back up: %v", err)
+		log.Warnf("failed to bring service back up: %v", err)
+	} else {
+		state.needsRestoreUp = false
+		time.Sleep(time.Second * 3)
 	}
-	time.Sleep(time.Second * 3)
 
 	if _, err := conn.StartCPUProfile(s.ctx, &proto.StartCPUProfileRequest{}); err != nil {
 		log.Warnf("failed to start CPU profiling: %v", err)
 	}
-
-	return nil
 }
 
 func (s *serviceClient) collectDebugData(
@@ -424,9 +430,7 @@ func (s *serviceClient) collectDebugData(
 	var wg sync.WaitGroup
 	startProgressTracker(ctx, &wg, params.duration, progress)
 
-	if err := s.configureServiceForDebug(conn, state, params.enablePersistence); err != nil {
-		return err
-	}
+	s.configureServiceForDebug(conn, state, params.enablePersistence)
 
 	wg.Wait()
 	progress.progressBar.Hide()
@@ -482,9 +486,17 @@ func (s *serviceClient) createDebugBundleFromCollection(
 
 // Restore service to original state
 func (s *serviceClient) restoreServiceState(conn proto.DaemonServiceClient, state *debugInitialState) {
+	if state.needsRestoreUp {
+		if _, err := conn.Up(s.ctx, &proto.UpRequest{}); err != nil {
+			log.Warnf("failed to restore up state: %v", err)
+		} else {
+			log.Info("Service state restored to up")
+		}
+	}
+
 	if state.wasDown {
 		if _, err := conn.Down(s.ctx, &proto.DownRequest{}); err != nil {
-			log.Errorf("Failed to restore down state: %v", err)
+			log.Warnf("failed to restore down state: %v", err)
 		} else {
 			log.Info("Service state restored to down")
 		}
@@ -492,7 +504,7 @@ func (s *serviceClient) restoreServiceState(conn proto.DaemonServiceClient, stat
 
 	if !state.isLevelTrace {
 		if _, err := conn.SetLogLevel(s.ctx, &proto.SetLogLevelRequest{Level: state.logLevel}); err != nil {
-			log.Errorf("Failed to restore log level: %v", err)
+			log.Warnf("failed to restore log level: %v", err)
 		} else {
 			log.Info("Log level restored to original setting")
 		}

combined/cmd/config.go

@@ -179,9 +179,11 @@ type StoreConfig struct {
 
 // ReverseProxyConfig contains reverse proxy settings
 type ReverseProxyConfig struct {
-	TrustedHTTPProxies      []string `yaml:"trustedHTTPProxies"`
-	TrustedHTTPProxiesCount uint     `yaml:"trustedHTTPProxiesCount"`
-	TrustedPeers            []string `yaml:"trustedPeers"`
+	TrustedHTTPProxies            []string `yaml:"trustedHTTPProxies"`
+	TrustedHTTPProxiesCount       uint     `yaml:"trustedHTTPProxiesCount"`
+	TrustedPeers                  []string `yaml:"trustedPeers"`
+	AccessLogRetentionDays        int      `yaml:"accessLogRetentionDays"`
+	AccessLogCleanupIntervalHours int      `yaml:"accessLogCleanupIntervalHours"`
 }
 
 // DefaultConfig returns a CombinedConfig with default values
@@ -645,7 +647,9 @@ func (c *CombinedConfig) ToManagementConfig() (*nbconfig.Config, error) {
 
 	// Build reverse proxy config
 	reverseProxy := nbconfig.ReverseProxy{
-		TrustedHTTPProxiesCount: mgmt.ReverseProxy.TrustedHTTPProxiesCount,
+		TrustedHTTPProxiesCount:       mgmt.ReverseProxy.TrustedHTTPProxiesCount,
+		AccessLogRetentionDays:        mgmt.ReverseProxy.AccessLogRetentionDays,
+		AccessLogCleanupIntervalHours: mgmt.ReverseProxy.AccessLogCleanupIntervalHours,
 	}
 	for _, p := range mgmt.ReverseProxy.TrustedHTTPProxies {
 		if prefix, err := netip.ParsePrefix(p); err == nil {

combined/cmd/root.go

@@ -29,6 +29,7 @@ import (
 	"github.com/netbirdio/netbird/management/server/telemetry"
 	"github.com/netbirdio/netbird/relay/healthcheck"
 	relayServer "github.com/netbirdio/netbird/relay/server"
+	"github.com/netbirdio/netbird/relay/server/listener"
 	"github.com/netbirdio/netbird/relay/server/listener/ws"
 	sharedMetrics "github.com/netbirdio/netbird/shared/metrics"
 	"github.com/netbirdio/netbird/shared/relay/auth"
@@ -523,7 +524,7 @@ func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (*
 func createCombinedHandler(grpcServer *grpc.Server, httpHandler http.Handler, relaySrv *relayServer.Server, meter metric.Meter, cfg *CombinedConfig) http.Handler {
 	wsProxy := wsproxyserver.New(grpcServer, wsproxyserver.WithOTelMeter(meter))
 
-	var relayAcceptFn func(conn net.Conn)
+	var relayAcceptFn func(conn listener.Conn)
 	if relaySrv != nil {
 		relayAcceptFn = relaySrv.RelayAccept()
 	}
@@ -563,7 +564,7 @@ func createCombinedHandler(grpcServer *grpc.Server, httpHandler http.Handler, re
 }
 
 // handleRelayWebSocket handles incoming WebSocket connections for the relay service
-func handleRelayWebSocket(w http.ResponseWriter, r *http.Request, acceptFn func(conn net.Conn), cfg *CombinedConfig) {
+func handleRelayWebSocket(w http.ResponseWriter, r *http.Request, acceptFn func(conn listener.Conn), cfg *CombinedConfig) {
 	acceptOptions := &websocket.AcceptOptions{
 		OriginPatterns: []string{"*"},
 	}
@@ -585,15 +586,9 @@ func handleRelayWebSocket(w http.ResponseWriter, r *http.Request, acceptFn func(
 		return
 	}
 
-	lAddr, err := net.ResolveTCPAddr("tcp", cfg.Server.ListenAddress)
-	if err != nil {
-		_ = wsConn.Close(websocket.StatusInternalError, "internal error")
-		return
-	}
-
 	log.Debugf("Relay WS client connected from: %s", rAddr)
 
-	conn := ws.NewConn(wsConn, lAddr, rAddr)
+	conn := ws.NewConn(wsConn, rAddr)
 	acceptFn(conn)
 }
 

flow/client/client.go

@@ -14,7 +14,6 @@ import (
 	log "github.com/sirupsen/logrus"
 	"google.golang.org/grpc"
 	"google.golang.org/grpc/codes"
-	"google.golang.org/grpc/connectivity"
 	"google.golang.org/grpc/credentials"
 	"google.golang.org/grpc/credentials/insecure"
 	"google.golang.org/grpc/keepalive"
@@ -26,11 +25,22 @@ import (
 	"github.com/netbirdio/netbird/util/wsproxy"
 )
 
+var ErrClientClosed = errors.New("client is closed")
+
+// minHealthyDuration is the minimum time a stream must survive before a failure
+// resets the backoff timer. Streams that fail faster are considered unhealthy and
+// should not reset backoff, so that MaxElapsedTime can eventually stop retries.
+const minHealthyDuration = 5 * time.Second
+
 type GRPCClient struct {
 	realClient proto.FlowServiceClient
 	clientConn *grpc.ClientConn
 	stream     proto.FlowService_EventsClient
-	streamMu   sync.Mutex
+	target     string
+	opts       []grpc.DialOption
+	closed     bool       // prevent creating conn in the middle of the Close
+	receiving  bool       // prevent concurrent Receive calls
+	mu         sync.Mutex // protects clientConn, realClient, stream, closed, and receiving
 }
 
 func NewClient(addr, payload, signature string, interval time.Duration) (*GRPCClient, error) {
@@ -65,7 +75,8 @@ func NewClient(addr, payload, signature string, interval time.Duration) (*GRPCCl
 		grpc.WithDefaultServiceConfig(`{"healthCheckConfig": {"serviceName": ""}}`),
 	)
 
-	conn, err := grpc.NewClient(fmt.Sprintf("%s:%s", parsedURL.Hostname(), parsedURL.Port()), opts...)
+	target := parsedURL.Host
+	conn, err := grpc.NewClient(target, opts...)
 	if err != nil {
 		return nil, fmt.Errorf("creating new grpc client: %w", err)
 	}
@@ -73,30 +84,73 @@ func NewClient(addr, payload, signature string, interval time.Duration) (*GRPCCl
 	return &GRPCClient{
 		realClient: proto.NewFlowServiceClient(conn),
 		clientConn: conn,
+		target:     target,
+		opts:       opts,
 	}, nil
 }
 
 func (c *GRPCClient) Close() error {
-	c.streamMu.Lock()
-	defer c.streamMu.Unlock()
-
+	c.mu.Lock()
+	c.closed = true
 	c.stream = nil
-	if err := c.clientConn.Close(); err != nil && !errors.Is(err, context.Canceled) {
+	conn := c.clientConn
+	c.clientConn = nil
+	c.mu.Unlock()
+
+	if conn == nil {
+		return nil
+	}
+
+	if err := conn.Close(); err != nil && !errors.Is(err, context.Canceled) {
 		return fmt.Errorf("close client connection: %w", err)
 	}
 
 	return nil
 }
 
+func (c *GRPCClient) Send(event *proto.FlowEvent) error {
+	c.mu.Lock()
+	stream := c.stream
+	c.mu.Unlock()
+
+	if stream == nil {
+		return errors.New("stream not initialized")
+	}
+
+	if err := stream.Send(event); err != nil {
+		return fmt.Errorf("send flow event: %w", err)
+	}
+
+	return nil
+}
+
 func (c *GRPCClient) Receive(ctx context.Context, interval time.Duration, msgHandler func(msg *proto.FlowEventAck) error) error {
+	c.mu.Lock()
+	if c.receiving {
+		c.mu.Unlock()
+		return errors.New("concurrent Receive calls are not supported")
+	}
+	c.receiving = true
+	c.mu.Unlock()
+	defer func() {
+		c.mu.Lock()
+		c.receiving = false
+		c.mu.Unlock()
+	}()
+
 	backOff := defaultBackoff(ctx, interval)
 	operation := func() error {
-		if err := c.establishStreamAndReceive(ctx, msgHandler); err != nil {
-			if s, ok := status.FromError(err); ok && s.Code() == codes.Canceled {
-				return fmt.Errorf("receive: %w: %w", err, context.Canceled)
-			}
+		stream, err := c.establishStream(ctx)
+		if err != nil {
+			log.Errorf("failed to establish flow stream, retrying: %v", err)
+			return c.handleRetryableError(err, time.Time{}, backOff)
+		}
+
+		streamStart := time.Now()
+
+		if err := c.receive(stream, msgHandler); err != nil {
 			log.Errorf("receive failed: %v", err)
-			return fmt.Errorf("receive: %w", err)
+			return c.handleRetryableError(err, streamStart, backOff)
 		}
 		return nil
 	}
@@ -108,37 +162,106 @@ func (c *GRPCClient) Receive(ctx context.Context, interval time.Duration, msgHan
 	return nil
 }
 
-func (c *GRPCClient) establishStreamAndReceive(ctx context.Context, msgHandler func(msg *proto.FlowEventAck) error) error {
-	if c.clientConn.GetState() == connectivity.Shutdown {
-		return errors.New("connection to flow receiver has been shut down")
+// handleRetryableError resets the backoff timer if the stream was healthy long
+// enough and recreates the underlying ClientConn so that gRPC's internal
+// subchannel backoff does not accumulate and compete with our own retry timer.
+// A zero streamStart means the stream was never established.
+func (c *GRPCClient) handleRetryableError(err error, streamStart time.Time, backOff backoff.BackOff) error {
+	if isContextDone(err) {
+		return backoff.Permanent(err)
 	}
 
-	stream, err := c.realClient.Events(ctx, grpc.WaitForReady(true))
-	if err != nil {
-		return fmt.Errorf("create event stream: %w", err)
+	var permErr *backoff.PermanentError
+	if errors.As(err, &permErr) {
+		return err
 	}
 
-	err = stream.Send(&proto.FlowEvent{IsInitiator: true})
+	// Reset the backoff so the next retry starts with a short delay instead of
+	// continuing the already-elapsed timer. Only do this if the stream was healthy
+	// long enough; short-lived connect/drop cycles must not defeat MaxElapsedTime.
+	if !streamStart.IsZero() && time.Since(streamStart) >= minHealthyDuration {
+		backOff.Reset()
+	}
+
+	if recreateErr := c.recreateConnection(); recreateErr != nil {
+		log.Errorf("recreate connection: %v", recreateErr)
+		return recreateErr
+	}
+
+	log.Infof("connection recreated, retrying stream")
+	return fmt.Errorf("retrying after error: %w", err)
+}
+
+func (c *GRPCClient) recreateConnection() error {
+	c.mu.Lock()
+	if c.closed {
+		c.mu.Unlock()
+		return backoff.Permanent(ErrClientClosed)
+	}
+
+	conn, err := grpc.NewClient(c.target, c.opts...)
 	if err != nil {
-		log.Infof("failed to send initiator message to flow receiver but will attempt to continue. Error: %s", err)
+		c.mu.Unlock()
+		return fmt.Errorf("create new connection: %w", err)
+	}
+
+	old := c.clientConn
+	c.clientConn = conn
+	c.realClient = proto.NewFlowServiceClient(conn)
+	c.stream = nil
+	c.mu.Unlock()
+
+	_ = old.Close()
+
+	return nil
+}
+
+func (c *GRPCClient) establishStream(ctx context.Context) (proto.FlowService_EventsClient, error) {
+	c.mu.Lock()
+	if c.closed {
+		c.mu.Unlock()
+		return nil, backoff.Permanent(ErrClientClosed)
+	}
+	cl := c.realClient
+	c.mu.Unlock()
+
+	// open stream outside the lock — blocking operation
+	stream, err := cl.Events(ctx)
+	if err != nil {
+		return nil, fmt.Errorf("create event stream: %w", err)
+	}
+	streamReady := false
+	defer func() {
+		if !streamReady {
+			_ = stream.CloseSend()
+		}
+	}()
+
+	if err = stream.Send(&proto.FlowEvent{IsInitiator: true}); err != nil {
+		return nil, fmt.Errorf("send initiator: %w", err)
 	}
 
 	if err = checkHeader(stream); err != nil {
-		return fmt.Errorf("check header: %w", err)
+		return nil, fmt.Errorf("check header: %w", err)
 	}
 
-	c.streamMu.Lock()
+	c.mu.Lock()
+	if c.closed {
+		c.mu.Unlock()
+		return nil, backoff.Permanent(ErrClientClosed)
+	}
 	c.stream = stream
-	c.streamMu.Unlock()
+	c.mu.Unlock()
+	streamReady = true
 
-	return c.receive(stream, msgHandler)
+	return stream, nil
 }
 
 func (c *GRPCClient) receive(stream proto.FlowService_EventsClient, msgHandler func(msg *proto.FlowEventAck) error) error {
 	for {
 		msg, err := stream.Recv()
 		if err != nil {
-			return fmt.Errorf("receive from stream: %w", err)
+			return err
 		}
 
 		if msg.IsInitiator {
@@ -169,7 +292,7 @@ func checkHeader(stream proto.FlowService_EventsClient) error {
 func defaultBackoff(ctx context.Context, interval time.Duration) backoff.BackOff {
 	return backoff.WithContext(&backoff.ExponentialBackOff{
 		InitialInterval:     800 * time.Millisecond,
-		RandomizationFactor: 1,
+		RandomizationFactor: 0.5,
 		Multiplier:          1.7,
 		MaxInterval:         interval / 2,
 		MaxElapsedTime:      3 * 30 * 24 * time.Hour, // 3 months
@@ -178,18 +301,12 @@ func defaultBackoff(ctx context.Context, interval time.Duration) backoff.BackOff
 	}, ctx)
 }
 
-func (c *GRPCClient) Send(event *proto.FlowEvent) error {
-	c.streamMu.Lock()
-	stream := c.stream
-	c.streamMu.Unlock()
-
-	if stream == nil {
-		return errors.New("stream not initialized")
+func isContextDone(err error) bool {
+	if errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) {
+		return true
 	}
-
-	if err := stream.Send(event); err != nil {
-		return fmt.Errorf("send flow event: %w", err)
+	if s, ok := status.FromError(err); ok {
+		return s.Code() == codes.Canceled || s.Code() == codes.DeadlineExceeded
 	}
-
-	return nil
+	return false
 }

flow/client/client_test.go

@@ -2,8 +2,11 @@ package client_test
 
 import (
 	"context"
+	"encoding/binary"
 	"errors"
 	"net"
+	"sync"
+	"sync/atomic"
 	"testing"
 	"time"
 
@@ -11,6 +14,8 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/status"
 
 	flow "github.com/netbirdio/netbird/flow/client"
 	"github.com/netbirdio/netbird/flow/proto"
@@ -18,21 +23,89 @@ import (
 
 type testServer struct {
 	proto.UnimplementedFlowServiceServer
-	events  chan *proto.FlowEvent
-	acks    chan *proto.FlowEventAck
-	grpcSrv *grpc.Server
-	addr    string
+	events         chan *proto.FlowEvent
+	acks           chan *proto.FlowEventAck
+	grpcSrv        *grpc.Server
+	addr           string
+	listener       *connTrackListener
+	closeStream    chan struct{} // signal server to close the stream
+	handlerDone    chan struct{} // signaled each time Events() exits
+	handlerStarted chan struct{} // signaled each time Events() begins
+}
+
+// connTrackListener wraps a net.Listener to track accepted connections
+// so tests can forcefully close them to simulate PROTOCOL_ERROR/RST_STREAM.
+type connTrackListener struct {
+	net.Listener
+	mu    sync.Mutex
+	conns []net.Conn
+}
+
+func (l *connTrackListener) Accept() (net.Conn, error) {
+	c, err := l.Listener.Accept()
+	if err != nil {
+		return nil, err
+	}
+	l.mu.Lock()
+	l.conns = append(l.conns, c)
+	l.mu.Unlock()
+	return c, nil
+}
+
+// sendRSTStream writes a raw HTTP/2 RST_STREAM frame with PROTOCOL_ERROR
+// (error code 0x1) on every tracked connection. This produces the exact error:
+//
+//	rpc error: code = Internal desc = stream terminated by RST_STREAM with error code: PROTOCOL_ERROR
+//
+// HTTP/2 RST_STREAM frame format (9-byte header + 4-byte payload):
+//
+//	Length (3 bytes): 0x000004
+//	Type   (1 byte):  0x03 (RST_STREAM)
+//	Flags  (1 byte):  0x00
+//	Stream ID (4 bytes): target stream (must have bit 31 clear)
+//	Error Code (4 bytes): 0x00000001 (PROTOCOL_ERROR)
+func (l *connTrackListener) connCount() int {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+	return len(l.conns)
+}
+
+func (l *connTrackListener) sendRSTStream(streamID uint32) {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	frame := make([]byte, 13) // 9-byte header + 4-byte payload
+	// Length = 4 (3 bytes, big-endian)
+	frame[0], frame[1], frame[2] = 0, 0, 4
+	// Type = RST_STREAM (0x03)
+	frame[3] = 0x03
+	// Flags = 0
+	frame[4] = 0x00
+	// Stream ID (4 bytes, big-endian, bit 31 reserved = 0)
+	binary.BigEndian.PutUint32(frame[5:9], streamID)
+	// Error Code = PROTOCOL_ERROR (0x1)
+	binary.BigEndian.PutUint32(frame[9:13], 0x1)
+
+	for _, c := range l.conns {
+		_, _ = c.Write(frame)
+	}
 }
 
 func newTestServer(t *testing.T) *testServer {
-	listener, err := net.Listen("tcp", "127.0.0.1:0")
+	rawListener, err := net.Listen("tcp", "127.0.0.1:0")
 	require.NoError(t, err)
 
+	listener := &connTrackListener{Listener: rawListener}
+
 	s := &testServer{
-		events:  make(chan *proto.FlowEvent, 100),
-		acks:    make(chan *proto.FlowEventAck, 100),
-		grpcSrv: grpc.NewServer(),
-		addr:    listener.Addr().String(),
+		events:         make(chan *proto.FlowEvent, 100),
+		acks:           make(chan *proto.FlowEventAck, 100),
+		grpcSrv:        grpc.NewServer(),
+		addr:           rawListener.Addr().String(),
+		listener:       listener,
+		closeStream:    make(chan struct{}, 1),
+		handlerDone:    make(chan struct{}, 10),
+		handlerStarted: make(chan struct{}, 10),
 	}
 
 	proto.RegisterFlowServiceServer(s.grpcSrv, s)
@@ -51,11 +124,23 @@ func newTestServer(t *testing.T) *testServer {
 }
 
 func (s *testServer) Events(stream proto.FlowService_EventsServer) error {
+	defer func() {
+		select {
+		case s.handlerDone <- struct{}{}:
+		default:
+		}
+	}()
+
 	err := stream.Send(&proto.FlowEventAck{IsInitiator: true})
 	if err != nil {
 		return err
 	}
 
+	select {
+	case s.handlerStarted <- struct{}{}:
+	default:
+	}
+
 	ctx, cancel := context.WithCancel(stream.Context())
 	defer cancel()
 
@@ -91,6 +176,8 @@ func (s *testServer) Events(stream proto.FlowService_EventsServer) error {
 			if err := stream.Send(ack); err != nil {
 				return err
 			}
+		case <-s.closeStream:
+			return status.Errorf(codes.Internal, "server closing stream")
 		case <-ctx.Done():
 			return ctx.Err()
 		}
@@ -110,16 +197,13 @@ func TestReceive(t *testing.T) {
 		assert.NoError(t, err, "failed to close flow")
 	})
 
-	receivedAcks := make(map[string]bool)
+	var ackCount atomic.Int32
 	receiveDone := make(chan struct{})
 
 	go func() {
 		err := client.Receive(ctx, 1*time.Second, func(msg *proto.FlowEventAck) error {
 			if !msg.IsInitiator && len(msg.EventId) > 0 {
-				id := string(msg.EventId)
-				receivedAcks[id] = true
-
-				if len(receivedAcks) >= 3 {
+				if ackCount.Add(1) >= 3 {
 					close(receiveDone)
 				}
 			}
@@ -130,7 +214,11 @@ func TestReceive(t *testing.T) {
 		}
 	}()
 
-	time.Sleep(500 * time.Millisecond)
+	select {
+	case <-server.handlerStarted:
+	case <-time.After(3 * time.Second):
+		t.Fatal("timeout waiting for stream to be established")
+	}
 
 	for i := 0; i < 3; i++ {
 		eventID := uuid.New().String()
@@ -153,7 +241,7 @@ func TestReceive(t *testing.T) {
 		t.Fatal("timeout waiting for acks to be processed")
 	}
 
-	assert.Equal(t, 3, len(receivedAcks))
+	assert.Equal(t, int32(3), ackCount.Load())
 }
 
 func TestReceive_ContextCancellation(t *testing.T) {
@@ -254,3 +342,195 @@ func TestSend(t *testing.T) {
 		t.Fatal("timeout waiting for ack to be received by flow")
 	}
 }
+
+func TestNewClient_PermanentClose(t *testing.T) {
+	server := newTestServer(t)
+
+	client, err := flow.NewClient("http://"+server.addr, "test-payload", "test-signature", 1*time.Second)
+	require.NoError(t, err)
+
+	err = client.Close()
+	require.NoError(t, err)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	t.Cleanup(cancel)
+
+	done := make(chan error, 1)
+	go func() {
+		done <- client.Receive(ctx, 1*time.Second, func(msg *proto.FlowEventAck) error {
+			return nil
+		})
+	}()
+
+	select {
+	case err := <-done:
+		require.ErrorIs(t, err, flow.ErrClientClosed)
+	case <-time.After(2 * time.Second):
+		t.Fatal("Receive did not return after Close — stuck in retry loop")
+	}
+}
+
+func TestNewClient_CloseVerify(t *testing.T) {
+	server := newTestServer(t)
+
+	client, err := flow.NewClient("http://"+server.addr, "test-payload", "test-signature", 1*time.Second)
+	require.NoError(t, err)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	t.Cleanup(cancel)
+
+	done := make(chan error, 1)
+	go func() {
+		done <- client.Receive(ctx, 1*time.Second, func(msg *proto.FlowEventAck) error {
+			return nil
+		})
+	}()
+
+	closeDone := make(chan struct{}, 1)
+	go func() {
+		_ = client.Close()
+		closeDone <- struct{}{}
+	}()
+
+	select {
+	case err := <-done:
+		require.Error(t, err)
+	case <-time.After(2 * time.Second):
+		t.Fatal("Receive did not return after Close — stuck in retry loop")
+	}
+
+	select {
+	case <-closeDone:
+		return
+	case <-time.After(2 * time.Second):
+		t.Fatal("Close did not return — blocked in retry loop")
+	}
+
+}
+
+func TestClose_WhileReceiving(t *testing.T) {
+	server := newTestServer(t)
+	client, err := flow.NewClient("http://"+server.addr, "test-payload", "test-signature", 1*time.Second)
+	require.NoError(t, err)
+
+	ctx := context.Background() // no timeout — intentional
+	receiveDone := make(chan struct{})
+	go func() {
+		_ = client.Receive(ctx, 1*time.Second, func(msg *proto.FlowEventAck) error {
+			return nil
+		})
+		close(receiveDone)
+	}()
+
+	// Wait for the server-side handler to confirm the stream is established.
+	select {
+	case <-server.handlerStarted:
+	case <-time.After(3 * time.Second):
+		t.Fatal("timeout waiting for stream to be established")
+	}
+
+	closeDone := make(chan struct{})
+	go func() {
+		_ = client.Close()
+		close(closeDone)
+	}()
+
+	select {
+	case <-closeDone:
+		// Close returned — good
+	case <-time.After(2 * time.Second):
+		t.Fatal("Close blocked forever — Receive stuck in retry loop")
+	}
+
+	select {
+	case <-receiveDone:
+	case <-time.After(2 * time.Second):
+		t.Fatal("Receive did not exit after Close")
+	}
+}
+
+func TestReceive_ProtocolErrorStreamReconnect(t *testing.T) {
+	server := newTestServer(t)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	t.Cleanup(cancel)
+
+	client, err := flow.NewClient("http://"+server.addr, "test-payload", "test-signature", 1*time.Second)
+	require.NoError(t, err)
+	t.Cleanup(func() {
+		err := client.Close()
+		assert.NoError(t, err, "failed to close flow")
+	})
+
+	// Track acks received before and after server-side stream close
+	var ackCount atomic.Int32
+	receivedFirst := make(chan struct{})
+	receivedAfterReconnect := make(chan struct{})
+
+	go func() {
+		err := client.Receive(ctx, 1*time.Second, func(msg *proto.FlowEventAck) error {
+			if msg.IsInitiator || len(msg.EventId) == 0 {
+				return nil
+			}
+			n := ackCount.Add(1)
+			if n == 1 {
+				close(receivedFirst)
+			}
+			if n == 2 {
+				close(receivedAfterReconnect)
+			}
+			return nil
+		})
+		if err != nil && !errors.Is(err, context.Canceled) {
+			t.Logf("receive error: %v", err)
+		}
+	}()
+
+	// Wait for stream to be established, then send first ack
+	select {
+	case <-server.handlerStarted:
+	case <-time.After(3 * time.Second):
+		t.Fatal("timeout waiting for stream to be established")
+	}
+	server.acks <- &proto.FlowEventAck{EventId: []byte("before-close")}
+
+	select {
+	case <-receivedFirst:
+	case <-time.After(3 * time.Second):
+		t.Fatal("timeout waiting for first ack")
+	}
+
+	// Snapshot connection count before injecting the fault.
+	connsBefore := server.listener.connCount()
+
+	// Send a raw HTTP/2 RST_STREAM frame with PROTOCOL_ERROR on the TCP connection.
+	// gRPC multiplexes streams on stream IDs 1, 3, 5, ... (odd, client-initiated).
+	// Stream ID 1 is the client's first stream (our Events bidi stream).
+	// This produces the exact error the client sees in production:
+	//   "stream terminated by RST_STREAM with error code: PROTOCOL_ERROR"
+	server.listener.sendRSTStream(1)
+
+	// Wait for the old Events() handler to fully exit so it can no longer
+	// drain s.acks and drop our injected ack on a broken stream.
+	select {
+	case <-server.handlerDone:
+	case <-time.After(5 * time.Second):
+		t.Fatal("old Events() handler did not exit after RST_STREAM")
+	}
+
+	require.Eventually(t, func() bool {
+		return server.listener.connCount() > connsBefore
+	}, 5*time.Second, 50*time.Millisecond, "client did not open a new TCP connection after RST_STREAM")
+
+	server.acks <- &proto.FlowEventAck{EventId: []byte("after-close")}
+
+	select {
+	case <-receivedAfterReconnect:
+		// Client successfully reconnected and received ack after server-side stream close
+	case <-time.After(5 * time.Second):
+		t.Fatal("timeout waiting for ack after server-side stream close — client did not reconnect")
+	}
+
+	assert.GreaterOrEqual(t, int(ackCount.Load()), 2, "should have received acks before and after stream close")
+	assert.GreaterOrEqual(t, server.listener.connCount(), 2, "client should have created at least 2 TCP connections (original + reconnect)")
+}

go.mod

@@ -63,6 +63,7 @@ require (
 	github.com/hashicorp/go-version v1.6.0
 	github.com/jackc/pgx/v5 v5.5.5
 	github.com/libdns/route53 v1.5.0
+	github.com/libp2p/go-nat v0.2.0
 	github.com/libp2p/go-netroute v0.2.1
 	github.com/lrh3321/ipset-go v0.0.0-20250619021614-54a0a98ace81
 	github.com/mdlayher/socket v0.5.1
@@ -200,10 +201,12 @@ require (
 	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/hashicorp/go-uuid v1.0.3 // indirect
 	github.com/huandu/xstrings v1.5.0 // indirect
+	github.com/huin/goupnp v1.2.0 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/jackc/pgpassfile v1.0.0 // indirect
 	github.com/jackc/pgservicefile v0.0.0-20221227161230-091c0ba34f0a // indirect
 	github.com/jackc/puddle/v2 v2.2.1 // indirect
+	github.com/jackpal/go-nat-pmp v1.0.2 // indirect
 	github.com/jeandeaual/go-locale v0.0.0-20250612000132-0ef82f21eade // indirect
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
@@ -213,6 +216,7 @@ require (
 	github.com/kelseyhightower/envconfig v1.4.0 // indirect
 	github.com/klauspost/compress v1.18.0 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.7 // indirect
+	github.com/koron/go-ssdp v0.0.4 // indirect
 	github.com/kr/fs v0.1.0 // indirect
 	github.com/lib/pq v1.10.9 // indirect
 	github.com/libdns/libdns v0.2.2 // indirect

go.sum

@@ -281,6 +281,8 @@ github.com/hashicorp/go-version v1.6.0/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09
 github.com/hpcloud/tail v1.0.0/go.mod h1:ab1qPbhIpdTxEkNHXyeSf5vhxWSCs/tWer42PpOxQnU=
 github.com/huandu/xstrings v1.5.0 h1:2ag3IFq9ZDANvthTwTiqSSZLjDc+BedvHPAp5tJy2TI=
 github.com/huandu/xstrings v1.5.0/go.mod h1:y5/lhBue+AyNmUVz9RLU9xbLR0o4KIIExikq4ovT0aE=
+github.com/huin/goupnp v1.2.0 h1:uOKW26NG1hsSSbXIZ1IR7XP9Gjd1U8pnLaCMgntmkmY=
+github.com/huin/goupnp v1.2.0/go.mod h1:gnGPsThkYa7bFi/KWmEysQRf48l2dvR5bxr2OFckNX8=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
 github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
@@ -291,6 +293,8 @@ github.com/jackc/pgx/v5 v5.5.5 h1:amBjrZVmksIdNjxGW/IiIMzxMKZFelXbUoPNb+8sjQw=
 github.com/jackc/pgx/v5 v5.5.5/go.mod h1:ez9gk+OAat140fv9ErkZDYFWmXLfV+++K0uAOiwgm1A=
 github.com/jackc/puddle/v2 v2.2.1 h1:RhxXJtFG022u4ibrCSMSiu5aOq1i77R3OHKNJj77OAk=
 github.com/jackc/puddle/v2 v2.2.1/go.mod h1:vriiEXHvEE654aYKXXjOvZM39qJ0q+azkZFrfEOc3H4=
+github.com/jackpal/go-nat-pmp v1.0.2 h1:KzKSgb7qkJvOUTqYl9/Hg/me3pWgBmERKrTGD7BdWus=
+github.com/jackpal/go-nat-pmp v1.0.2/go.mod h1:QPH045xvCAeXUZOxsnwmrtiCoxIr9eob+4orBN1SBKc=
 github.com/jcmturner/aescts/v2 v2.0.0 h1:9YKLH6ey7H4eDBXW8khjYslgyqG2xZikXP0EQFKrle8=
 github.com/jcmturner/aescts/v2 v2.0.0/go.mod h1:AiaICIRyfYg35RUkr8yESTqvSy7csK90qZ5xfvvsoNs=
 github.com/jcmturner/dnsutils/v2 v2.0.0 h1:lltnkeZGL0wILNvrNiVCR6Ro5PGU/SeBvVO/8c/iPbo=
@@ -328,6 +332,8 @@ github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYW
 github.com/klauspost/cpuid/v2 v2.0.12/go.mod h1:g2LTdtYhdyuGPqyWyv7qRAmj1WBqxuObKfj5c0PQa7c=
 github.com/klauspost/cpuid/v2 v2.2.7 h1:ZWSB3igEs+d0qvnxR/ZBzXVmxkgt8DdzP6m9pfuVLDM=
 github.com/klauspost/cpuid/v2 v2.2.7/go.mod h1:Lcz8mBdAVJIBVzewtcLocK12l3Y+JytZYpaMropDUws=
+github.com/koron/go-ssdp v0.0.4 h1:1IDwrghSKYM7yLf7XCzbByg2sJ/JcNOZRXS2jczTwz0=
+github.com/koron/go-ssdp v0.0.4/go.mod h1:oDXq+E5IL5q0U8uSBcoAXzTzInwy5lEgC91HoKtbmZk=
 github.com/kr/fs v0.1.0 h1:Jskdu9ieNAYnjxsi0LbQp1ulIKZV1LAFgK1tWhpZgl8=
 github.com/kr/fs v0.1.0/go.mod h1:FFnZGqtBN9Gxj7eW1uZ42v5BccTP0vu6NEaFoC2HwRg=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
@@ -346,6 +352,8 @@ github.com/libdns/libdns v0.2.2 h1:O6ws7bAfRPaBsgAYt8MDe2HcNBGC29hkZ9MX2eUSX3s=
 github.com/libdns/libdns v0.2.2/go.mod h1:4Bj9+5CQiNMVGf87wjX4CY3HQJypUHRuLvlsfsZqLWQ=
 github.com/libdns/route53 v1.5.0 h1:2SKdpPFl/qgWsXQvsLNJJAoX7rSxlk7zgoL4jnWdXVA=
 github.com/libdns/route53 v1.5.0/go.mod h1:joT4hKmaTNKHEwb7GmZ65eoDz1whTu7KKYPS8ZqIh6Q=
+github.com/libp2p/go-nat v0.2.0 h1:Tyz+bUFAYqGyJ/ppPPymMGbIgNRH+WqC5QrT5fKrrGk=
+github.com/libp2p/go-nat v0.2.0/go.mod h1:3MJr+GRpRkyT65EpVPBstXLvOlAPzUVlG6Pwg9ohLJk=
 github.com/lrh3321/ipset-go v0.0.0-20250619021614-54a0a98ace81 h1:J56rFEfUTFT9j9CiRXhi1r8lUJ4W5idG3CiaBZGojNU=
 github.com/lrh3321/ipset-go v0.0.0-20250619021614-54a0a98ace81/go.mod h1:RD8ML/YdXctQ7qbcizZkw5mZ6l8Ogrl1dodBzVJduwI=
 github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0/go.mod h1:zJYVVT2jmtg6P3p1VtQj7WsuWi/y4VnjVBn7F8KPB3I=

infrastructure_files/getting-started.sh

@@ -532,14 +532,13 @@ render_docker_compose_traefik_builtin() {
     traefik_dynamic_volume="      - ./traefik-dynamic.yaml:/etc/traefik/dynamic.yaml:ro"
     proxy_service="
   # NetBird Proxy - exposes internal resources to the internet
-  # Uses host network so it can listen on arbitrary ports for TCP/UDP services
   proxy:
     image: $NETBIRD_PROXY_IMAGE
     container_name: netbird-proxy
     ports:
     - 51820:51820/udp
     restart: unless-stopped
-    network_mode: host
+    networks: [netbird]
     depends_on:
       - netbird-server
     env_file:
@@ -647,7 +646,6 @@ $traefik_dynamic_volume
     networks: [netbird]
     ports:
       - '$NETBIRD_STUN_PORT:$NETBIRD_STUN_PORT/udp'
-$(if [[ "$ENABLE_PROXY" == "true" ]]; then echo "      - '$MANAGEMENT_HOST_PORT:80'"; fi)
     volumes:
       - netbird_data:/var/lib/netbird
       - ./config.yaml:/etc/netbird/config.yaml
@@ -768,8 +766,8 @@ render_proxy_env() {
   cat <<EOF
 # NetBird Proxy Configuration
 NB_PROXY_DEBUG_LOGS=false
-# Proxy runs in host network mode for L4 port binding, connect to management via localhost
-NB_PROXY_MANAGEMENT_ADDRESS=http://localhost:$MANAGEMENT_HOST_PORT
+# Use internal Docker network to connect to management (avoids hairpin NAT issues)
+NB_PROXY_MANAGEMENT_ADDRESS=http://netbird-server:80
 # Allow insecure gRPC connection to management (required for internal Docker network)
 NB_PROXY_ALLOW_INSECURE=true
 # Public URL where this proxy is reachable (used for cluster registration)

infrastructure_files/observability/grafana/dashboards/management.json

@@ -302,7 +302,7 @@
             "uid": "${datasource}"
           },
           "editorMode": "code",
-          "expr": "rate(management_account_peer_meta_update_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
+          "expr": "rate(management_account_peer_meta_update_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
           "instant": false,
           "legendFormat": "{{cluster}}/{{environment}}/{{job}}",
           "range": true,
@@ -410,7 +410,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.5,sum(increase(management_account_get_peer_network_map_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.5,sum(increase(management_account_get_peer_network_map_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,
@@ -426,7 +426,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.9,sum(increase(management_account_get_peer_network_map_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.9,sum(increase(management_account_get_peer_network_map_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -443,7 +443,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99,sum(increase(management_account_get_peer_network_map_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.99,sum(increase(management_account_get_peer_network_map_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -545,7 +545,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.5,sum(increase(management_account_update_account_peers_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.5,sum(increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,
@@ -561,7 +561,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.9,sum(increase(management_account_update_account_peers_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.9,sum(increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -578,7 +578,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99,sum(increase(management_account_update_account_peers_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.99,sum(increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -694,7 +694,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.5,sum(increase(management_grpc_updatechannel_queue_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.5,sum(increase(management_grpc_updatechannel_queue_length_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,
@@ -710,7 +710,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.9,sum(increase(management_grpc_updatechannel_queue_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.9,sum(increase(management_grpc_updatechannel_queue_length_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -727,7 +727,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99,sum(increase(management_grpc_updatechannel_queue_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.99,sum(increase(management_grpc_updatechannel_queue_length_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -841,7 +841,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_store_persistence_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_store_persistence_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -853,7 +853,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_store_persistence_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_store_persistence_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -866,7 +866,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_store_persistence_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_store_persistence_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -963,7 +963,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_store_transaction_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_store_transaction_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -975,7 +975,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_store_transaction_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_store_transaction_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -988,7 +988,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_store_transaction_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_store_transaction_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -1085,7 +1085,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_store_global_lock_acquisition_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_store_global_lock_acquisition_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -1097,7 +1097,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_store_global_lock_acquisition_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_store_global_lock_acquisition_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -1110,7 +1110,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_store_global_lock_acquisition_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_store_global_lock_acquisition_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -1221,7 +1221,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "rate(management_idp_authenticate_request_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
+              "expr": "rate(management_idp_authenticate_request_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
               "instant": false,
               "legendFormat": "{{cluster}}/{{environment}}/{{job}}",
               "range": true,
@@ -1317,7 +1317,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "rate(management_idp_get_account_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
+              "expr": "rate(management_idp_get_account_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
               "instant": false,
               "legendFormat": "{{cluster}}/{{environment}}/{{job}}",
               "range": true,
@@ -1413,7 +1413,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "rate(management_idp_update_user_meta_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
+              "expr": "rate(management_idp_update_user_meta_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
               "instant": false,
               "legendFormat": "{{cluster}}/{{environment}}/{{job}}",
               "range": true,
@@ -1523,7 +1523,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "sum(rate(management_http_request_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",method=~\"GET|OPTIONS\"}[$__rate_interval])) by (job,method)",
+              "expr": "sum(rate(management_http_request_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",method=~\"GET|OPTIONS\"}[$__rate_interval])) by (job,method)",
               "instant": false,
               "legendFormat": "{{method}}",
               "range": true,
@@ -1619,7 +1619,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "sum(rate(management_http_request_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",method=~\"POST|PUT|DELETE\"}[$__rate_interval])) by (job,method)",
+              "expr": "sum(rate(management_http_request_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",method=~\"POST|PUT|DELETE\"}[$__rate_interval])) by (job,method)",
               "instant": false,
               "legendFormat": "{{method}}",
               "range": true,
@@ -1715,7 +1715,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -1727,7 +1727,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -1740,7 +1740,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -1837,7 +1837,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -1849,7 +1849,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -1862,7 +1862,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -1963,7 +1963,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "sum(rate(management_http_request_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (job,exported_endpoint,method)",
+              "expr": "sum(rate(management_http_request_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (job,exported_endpoint,method)",
               "hide": false,
               "instant": false,
               "legendFormat": "{{method}}-{{exported_endpoint}}",
@@ -3222,7 +3222,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "builder",
-              "expr": "sum by(le) (increase(management_grpc_updatechannel_queue_bucket{application=\"management\", environment=\"$environment\", host=~\"$host\"}[$__rate_interval]))",
+              "expr": "sum by(le) (increase(management_grpc_updatechannel_queue_length_bucket{application=\"management\", environment=\"$environment\", host=~\"$host\"}[$__rate_interval]))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,
@@ -3323,7 +3323,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "builder",
-              "expr": "sum by(le) (increase(management_account_update_account_peers_duration_ms_bucket{application=\"management\", environment=\"$environment\", host=~\"$host\"}[$__rate_interval]))",
+              "expr": "sum by(le) (increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{application=\"management\", environment=\"$environment\", host=~\"$host\"}[$__rate_interval]))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,

management/internals/modules/reverseproxy/accesslogs/manager/manager.go

@@ -106,13 +106,23 @@ func (m *managerImpl) CleanupOldAccessLogs(ctx context.Context, retentionDays in
 
 // StartPeriodicCleanup starts a background goroutine that periodically cleans up old access logs
 func (m *managerImpl) StartPeriodicCleanup(ctx context.Context, retentionDays, cleanupIntervalHours int) {
-	if retentionDays <= 0 {
-		log.WithContext(ctx).Debug("periodic access log cleanup disabled: retention days is 0 or negative")
+	if retentionDays < 0 {
+		log.WithContext(ctx).Debug("periodic access log cleanup disabled: retention days is negative")
 		return
 	}
 
+	if retentionDays == 0 {
+		retentionDays = 7
+		log.WithContext(ctx).Debugf("no retention days specified for access log cleanup, defaulting to %d days", retentionDays)
+	} else {
+		log.WithContext(ctx).Debugf("access log retention period set to %d days", retentionDays)
+	}
+
 	if cleanupIntervalHours <= 0 {
 		cleanupIntervalHours = 24
+		log.WithContext(ctx).Debugf("no cleanup interval specified for access log cleanup, defaulting to %d hours", cleanupIntervalHours)
+	} else {
+		log.WithContext(ctx).Debugf("access log cleanup interval set to %d hours", cleanupIntervalHours)
 	}
 
 	cleanupCtx, cancel := context.WithCancel(ctx)

management/internals/modules/reverseproxy/accesslogs/manager/manager_test.go

@@ -121,7 +121,7 @@ func TestCleanupWithExactBoundary(t *testing.T) {
 }
 
 func TestStartPeriodicCleanup(t *testing.T) {
-	t.Run("periodic cleanup disabled with zero retention", func(t *testing.T) {
+	t.Run("periodic cleanup disabled with negative retention", func(t *testing.T) {
 		ctrl := gomock.NewController(t)
 		defer ctrl.Finish()
 
@@ -135,7 +135,7 @@ func TestStartPeriodicCleanup(t *testing.T) {
 		ctx, cancel := context.WithCancel(context.Background())
 		defer cancel()
 
-		manager.StartPeriodicCleanup(ctx, 0, 1)
+		manager.StartPeriodicCleanup(ctx, -1, 1)
 
 		time.Sleep(100 * time.Millisecond)
 

management/internals/modules/reverseproxy/domain/domain.go

@@ -30,3 +30,8 @@ func (d *Domain) EventMeta() map[string]any {
 		"validated":      d.Validated,
 	}
 }
+
+func (d *Domain) Copy() *Domain {
+	dCopy := *d
+	return &dCopy
+}

management/internals/modules/reverseproxy/service/manager/l4_port_test.go

@@ -85,8 +85,8 @@ func setupL4Test(t *testing.T, customPortsSupported *bool) (*Manager, store.Stor
 	accountMgr := &mock_server.MockAccountManager{
 		StoreEventFunc:         func(_ context.Context, _, _, _ string, _ activity.ActivityDescriber, _ map[string]any) {},
 		UpdateAccountPeersFunc: func(_ context.Context, _ string) {},
-		GetGroupByNameFunc: func(ctx context.Context, accountID, groupName string) (*types.Group, error) {
-			return testStore.GetGroupByName(ctx, store.LockingStrengthNone, groupName, accountID)
+		GetGroupByNameFunc: func(ctx context.Context, groupName, accountID, userID string) (*types.Group, error) {
+			return testStore.GetGroupByName(ctx, store.LockingStrengthNone, accountID, groupName)
 		},
 	}
 

management/internals/modules/reverseproxy/service/manager/manager.go

@@ -1119,7 +1119,7 @@ func (m *Manager) getGroupIDsFromNames(ctx context.Context, accountID string, gr
 	}
 	groupIDs := make([]string, 0, len(groupNames))
 	for _, groupName := range groupNames {
-		g, err := m.accountManager.GetGroupByName(ctx, groupName, accountID)
+		g, err := m.accountManager.GetGroupByName(ctx, groupName, accountID, activity.SystemInitiator)
 		if err != nil {
 			return nil, fmt.Errorf("failed to get group by name %s: %w", groupName, err)
 		}

management/internals/modules/reverseproxy/service/manager/manager_test.go

@@ -698,8 +698,8 @@ func setupIntegrationTest(t *testing.T) (*Manager, store.Store) {
 	accountMgr := &mock_server.MockAccountManager{
 		StoreEventFunc:         func(_ context.Context, _, _, _ string, _ activity.ActivityDescriber, _ map[string]any) {},
 		UpdateAccountPeersFunc: func(_ context.Context, _ string) {},
-		GetGroupByNameFunc: func(ctx context.Context, accountID, groupName string) (*types.Group, error) {
-			return testStore.GetGroupByName(ctx, store.LockingStrengthNone, groupName, accountID)
+		GetGroupByNameFunc: func(ctx context.Context, groupName, accountID, userID string) (*types.Group, error) {
+			return testStore.GetGroupByName(ctx, store.LockingStrengthNone, accountID, groupName)
 		},
 	}
 

management/internals/server/config/config.go

@@ -203,7 +203,7 @@ type ReverseProxy struct {
 
 	// AccessLogRetentionDays specifies the number of days to retain access logs.
 	// Logs older than this duration will be automatically deleted during cleanup.
-	// A value of 0 or negative means logs are kept indefinitely (no cleanup).
+	// A value of 0 will default to 7 days. Negative means logs are kept indefinitely (no cleanup).
 	AccessLogRetentionDays int
 
 	// AccessLogCleanupIntervalHours specifies how often (in hours) to run the cleanup routine.

management/server/account.go

@@ -742,11 +742,6 @@ func (am *DefaultAccountManager) DeleteAccount(ctx context.Context, accountID, u
 		return status.Errorf(status.Internal, "failed to build user infos for account %s: %v", accountID, err)
 	}
 
-	err = am.serviceManager.DeleteAllServices(ctx, accountID, userID)
-	if err != nil {
-		return status.Errorf(status.Internal, "failed to delete service %s: %v", accountID, err)
-	}
-
 	for _, otherUser := range account.Users {
 		if otherUser.Id == userID {
 			continue

management/server/account/manager.go

@@ -75,7 +75,7 @@ type Manager interface {
 	GetUsersFromAccount(ctx context.Context, accountID, userID string) (map[string]*types.UserInfo, error)
 	GetGroup(ctx context.Context, accountId, groupID, userID string) (*types.Group, error)
 	GetAllGroups(ctx context.Context, accountID, userID string) ([]*types.Group, error)
-	GetGroupByName(ctx context.Context, groupName, accountID string) (*types.Group, error)
+	GetGroupByName(ctx context.Context, groupName, accountID, userID string) (*types.Group, error)
 	CreateGroup(ctx context.Context, accountID, userID string, group *types.Group) error
 	UpdateGroup(ctx context.Context, accountID, userID string, group *types.Group) error
 	CreateGroups(ctx context.Context, accountID, userID string, newGroups []*types.Group) error

management/server/account/manager_mock.go

@@ -736,18 +736,18 @@ func (mr *MockManagerMockRecorder) GetGroup(ctx, accountId, groupID, userID inte
 }
 
 // GetGroupByName mocks base method.
-func (m *MockManager) GetGroupByName(ctx context.Context, groupName, accountID string) (*types.Group, error) {
+func (m *MockManager) GetGroupByName(ctx context.Context, groupName, accountID, userID string) (*types.Group, error) {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetGroupByName", ctx, groupName, accountID)
+	ret := m.ctrl.Call(m, "GetGroupByName", ctx, groupName, accountID, userID)
 	ret0, _ := ret[0].(*types.Group)
 	ret1, _ := ret[1].(error)
 	return ret0, ret1
 }
 
 // GetGroupByName indicates an expected call of GetGroupByName.
-func (mr *MockManagerMockRecorder) GetGroupByName(ctx, groupName, accountID interface{}) *gomock.Call {
+func (mr *MockManagerMockRecorder) GetGroupByName(ctx, groupName, accountID, userID interface{}) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetGroupByName", reflect.TypeOf((*MockManager)(nil).GetGroupByName), ctx, groupName, accountID)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetGroupByName", reflect.TypeOf((*MockManager)(nil).GetGroupByName), ctx, groupName, accountID, userID)
 }
 
 // GetIdentityProvider mocks base method.

management/server/account_request_buffer.go

@@ -63,20 +63,11 @@ func (ac *AccountRequestBuffer) GetAccountWithBackpressure(ctx context.Context,
 
 	log.WithContext(ctx).Tracef("requesting account %s with backpressure", accountID)
 	startTime := time.Now()
+	ac.getAccountRequestCh <- req
 
-	select {
-	case <-ctx.Done():
-		return nil, ctx.Err()
-	case ac.getAccountRequestCh <- req:
-	}
-
-	select {
-	case <-ctx.Done():
-		return nil, ctx.Err()
-	case result := <-req.ResultChan:
-		log.WithContext(ctx).Tracef("got account with backpressure after %s", time.Since(startTime))
-		return result.Account, result.Err
-	}
+	result := <-req.ResultChan
+	log.WithContext(ctx).Tracef("got account with backpressure after %s", time.Since(startTime))
+	return result.Account, result.Err
 }
 
 func (ac *AccountRequestBuffer) processGetAccountBatch(ctx context.Context, accountID string) {

management/server/account_test.go

@@ -15,7 +15,6 @@ import (
 	"time"
 
 	"github.com/golang/mock/gomock"
-	"github.com/netbirdio/netbird/shared/management/status"
 	"github.com/prometheus/client_golang/prometheus/push"
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
@@ -23,6 +22,9 @@ import (
 	"go.opentelemetry.io/otel/metric/noop"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
+	"github.com/netbirdio/netbird/shared/management/status"
+
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller"
@@ -1815,6 +1817,13 @@ func TestAccount_Copy(t *testing.T) {
 				Targets:   []*service.Target{},
 			},
 		},
+		Domains: []*domain.Domain{
+			{
+				ID:        "domain1",
+				Domain:    "test.com",
+				AccountID: "account1",
+			},
+		},
 		NetworkMapCache: &types.NetworkMapBuilder{},
 	}
 	account.InitOnce()

management/server/group.go

@@ -61,7 +61,10 @@ func (am *DefaultAccountManager) GetAllGroups(ctx context.Context, accountID, us
 }
 
 // GetGroupByName filters all groups in an account by name and returns the one with the most peers
-func (am *DefaultAccountManager) GetGroupByName(ctx context.Context, groupName, accountID string) (*types.Group, error) {
+func (am *DefaultAccountManager) GetGroupByName(ctx context.Context, groupName, accountID, userID string) (*types.Group, error) {
+	if err := am.CheckGroupPermissions(ctx, accountID, userID); err != nil {
+		return nil, err
+	}
 	return am.Store.GetGroupByName(ctx, store.LockingStrengthNone, accountID, groupName)
 }
 

management/server/http/handlers/groups/groups_handler.go

@@ -52,7 +52,7 @@ func (h *handler) getAllGroups(w http.ResponseWriter, r *http.Request) {
 	groupName := r.URL.Query().Get("name")
 	if groupName != "" {
 		// Get single group by name
-		group, err := h.accountManager.GetGroupByName(r.Context(), groupName, accountID)
+		group, err := h.accountManager.GetGroupByName(r.Context(), groupName, accountID, userID)
 		if err != nil {
 			util.WriteError(r.Context(), err, w)
 			return
@@ -118,7 +118,7 @@ func (h *handler) updateGroup(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	allGroup, err := h.accountManager.GetGroupByName(r.Context(), "All", accountID)
+	allGroup, err := h.accountManager.GetGroupByName(r.Context(), "All", accountID, userID)
 	if err != nil {
 		util.WriteError(r.Context(), err, w)
 		return

management/server/http/handlers/groups/groups_handler_test.go

@@ -71,7 +71,7 @@ func initGroupTestData(initGroups ...*types.Group) *handler {
 
 				return groups, nil
 			},
-			GetGroupByNameFunc: func(ctx context.Context, groupName, _ string) (*types.Group, error) {
+			GetGroupByNameFunc: func(ctx context.Context, groupName, _, _ string) (*types.Group, error) {
 				if groupName == "All" {
 					return &types.Group{ID: "id-all", Name: "All", Issued: types.GroupIssuedAPI}, nil
 				}

management/server/migration/migration.go

@@ -489,6 +489,102 @@ func MigrateJsonToTable[T any](ctx context.Context, db *gorm.DB, columnName stri
 	return nil
 }
 
+// hasForeignKey checks whether a foreign key constraint exists on the given table and column.
+func hasForeignKey(db *gorm.DB, table, column string) bool {
+	var count int64
+
+	switch db.Name() {
+	case "postgres":
+		db.Raw(`
+			SELECT COUNT(*) FROM information_schema.key_column_usage kcu
+			JOIN information_schema.table_constraints tc
+			  ON tc.constraint_name = kcu.constraint_name
+			  AND tc.table_schema = kcu.table_schema
+			WHERE tc.constraint_type = 'FOREIGN KEY'
+			  AND kcu.table_name = ?
+			  AND kcu.column_name = ?
+		`, table, column).Scan(&count)
+	case "mysql":
+		db.Raw(`
+			SELECT COUNT(*) FROM information_schema.key_column_usage
+			WHERE table_schema = DATABASE()
+			  AND table_name = ?
+			  AND column_name = ?
+			  AND referenced_table_name IS NOT NULL
+		`, table, column).Scan(&count)
+	default: // sqlite
+		type fkInfo struct {
+			From string
+		}
+		var fks []fkInfo
+		db.Raw(fmt.Sprintf("PRAGMA foreign_key_list(%s)", table)).Scan(&fks)
+		for _, fk := range fks {
+			if fk.From == column {
+				return true
+			}
+		}
+		return false
+	}
+
+	return count > 0
+}
+
+// CleanupOrphanedResources deletes rows from the table of model T where the foreign
+// key column (fkColumn) references a row in the table of model R that no longer exists.
+func CleanupOrphanedResources[T any, R any](ctx context.Context, db *gorm.DB, fkColumn string) error {
+	var model T
+	var refModel R
+
+	if !db.Migrator().HasTable(&model) {
+		log.WithContext(ctx).Debugf("table for %T does not exist, no cleanup needed", model)
+		return nil
+	}
+
+	if !db.Migrator().HasTable(&refModel) {
+		log.WithContext(ctx).Debugf("referenced table for %T does not exist, no cleanup needed", refModel)
+		return nil
+	}
+
+	stmtT := &gorm.Statement{DB: db}
+	if err := stmtT.Parse(&model); err != nil {
+		return fmt.Errorf("parse model %T: %w", model, err)
+	}
+	childTable := stmtT.Schema.Table
+
+	stmtR := &gorm.Statement{DB: db}
+	if err := stmtR.Parse(&refModel); err != nil {
+		return fmt.Errorf("parse reference model %T: %w", refModel, err)
+	}
+	parentTable := stmtR.Schema.Table
+
+	if !db.Migrator().HasColumn(&model, fkColumn) {
+		log.WithContext(ctx).Debugf("column %s does not exist in table %s, no cleanup needed", fkColumn, childTable)
+		return nil
+	}
+
+	// If a foreign key constraint already exists on the column, the DB itself
+	// enforces referential integrity and orphaned rows cannot exist.
+	if hasForeignKey(db, childTable, fkColumn) {
+		log.WithContext(ctx).Debugf("foreign key constraint for %s already exists on %s, no cleanup needed", fkColumn, childTable)
+		return nil
+	}
+
+	result := db.Exec(
+		fmt.Sprintf(
+			"DELETE FROM %s WHERE %s NOT IN (SELECT id FROM %s)",
+			childTable, fkColumn, parentTable,
+		),
+	)
+	if result.Error != nil {
+		return fmt.Errorf("cleanup orphaned rows in %s: %w", childTable, result.Error)
+	}
+
+	log.WithContext(ctx).Infof("Cleaned up %d orphaned rows from %s where %s had no matching row in %s",
+		result.RowsAffected, childTable, fkColumn, parentTable)
+
+	return nil
+}
+
 func RemoveDuplicatePeerKeys(ctx context.Context, db *gorm.DB) error {
 	if !db.Migrator().HasTable("peers") {
 		log.WithContext(ctx).Debug("peers table does not exist, skipping duplicate key cleanup")

management/server/migration/migration_test.go

@@ -441,3 +441,197 @@ func TestRemoveDuplicatePeerKeys_NoTable(t *testing.T) {
 	err := migration.RemoveDuplicatePeerKeys(context.Background(), db)
 	require.NoError(t, err, "Should not fail when table does not exist")
 }
+
+type testParent struct {
+	ID string `gorm:"primaryKey"`
+}
+
+func (testParent) TableName() string {
+	return "test_parents"
+}
+
+type testChild struct {
+	ID       string `gorm:"primaryKey"`
+	ParentID string
+}
+
+func (testChild) TableName() string {
+	return "test_children"
+}
+
+type testChildWithFK struct {
+	ID       string      `gorm:"primaryKey"`
+	ParentID string      `gorm:"index"`
+	Parent   *testParent `gorm:"foreignKey:ParentID"`
+}
+
+func (testChildWithFK) TableName() string {
+	return "test_children"
+}
+
+func setupOrphanTestDB(t *testing.T, models ...any) *gorm.DB {
+	t.Helper()
+	db := setupDatabase(t)
+	for _, m := range models {
+		_ = db.Migrator().DropTable(m)
+	}
+	err := db.AutoMigrate(models...)
+	require.NoError(t, err, "Failed to auto-migrate tables")
+	return db
+}
+
+func TestCleanupOrphanedResources_NoChildTable(t *testing.T) {
+	db := setupDatabase(t)
+	_ = db.Migrator().DropTable(&testChild{})
+	_ = db.Migrator().DropTable(&testParent{})
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err, "Should not fail when child table does not exist")
+}
+
+func TestCleanupOrphanedResources_NoParentTable(t *testing.T) {
+	db := setupDatabase(t)
+	_ = db.Migrator().DropTable(&testParent{})
+	_ = db.Migrator().DropTable(&testChild{})
+
+	err := db.AutoMigrate(&testChild{})
+	require.NoError(t, err)
+
+	err = migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err, "Should not fail when parent table does not exist")
+}
+
+func TestCleanupOrphanedResources_EmptyTables(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err, "Should not fail on empty tables")
+
+	var count int64
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(0), count)
+}
+
+func TestCleanupOrphanedResources_NoOrphans(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	require.NoError(t, db.Create(&testParent{ID: "p1"}).Error)
+	require.NoError(t, db.Create(&testParent{ID: "p2"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c1", ParentID: "p1"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c2", ParentID: "p2"}).Error)
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err)
+
+	var count int64
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(2), count, "All children should remain when no orphans")
+}
+
+func TestCleanupOrphanedResources_AllOrphans(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c1", "gone1").Error)
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c2", "gone2").Error)
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c3", "gone3").Error)
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err)
+
+	var count int64
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(0), count, "All orphaned children should be deleted")
+}
+
+func TestCleanupOrphanedResources_MixedValidAndOrphaned(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	require.NoError(t, db.Create(&testParent{ID: "p1"}).Error)
+	require.NoError(t, db.Create(&testParent{ID: "p2"}).Error)
+
+	require.NoError(t, db.Create(&testChild{ID: "c1", ParentID: "p1"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c2", ParentID: "p2"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c3", ParentID: "p1"}).Error)
+
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c4", "gone1").Error)
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c5", "gone2").Error)
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err)
+
+	var remaining []testChild
+	require.NoError(t, db.Order("id").Find(&remaining).Error)
+
+	assert.Len(t, remaining, 3, "Only valid children should remain")
+	assert.Equal(t, "c1", remaining[0].ID)
+	assert.Equal(t, "c2", remaining[1].ID)
+	assert.Equal(t, "c3", remaining[2].ID)
+}
+
+func TestCleanupOrphanedResources_Idempotent(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	require.NoError(t, db.Create(&testParent{ID: "p1"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c1", ParentID: "p1"}).Error)
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c2", "gone").Error)
+
+	ctx := context.Background()
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](ctx, db, "parent_id")
+	require.NoError(t, err)
+
+	var count int64
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(1), count)
+
+	err = migration.CleanupOrphanedResources[testChild, testParent](ctx, db, "parent_id")
+	require.NoError(t, err)
+
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(1), count, "Count should remain the same after second run")
+}
+
+func TestCleanupOrphanedResources_SkipsWhenForeignKeyExists(t *testing.T) {
+	engine := os.Getenv("NETBIRD_STORE_ENGINE")
+	if engine != "postgres" && engine != "mysql" {
+		t.Skip("FK constraint early-exit test requires postgres or mysql")
+	}
+
+	db := setupDatabase(t)
+	_ = db.Migrator().DropTable(&testChildWithFK{})
+	_ = db.Migrator().DropTable(&testParent{})
+
+	err := db.AutoMigrate(&testParent{}, &testChildWithFK{})
+	require.NoError(t, err)
+
+	require.NoError(t, db.Create(&testParent{ID: "p1"}).Error)
+	require.NoError(t, db.Create(&testParent{ID: "p2"}).Error)
+	require.NoError(t, db.Create(&testChildWithFK{ID: "c1", ParentID: "p1"}).Error)
+	require.NoError(t, db.Create(&testChildWithFK{ID: "c2", ParentID: "p2"}).Error)
+
+	switch engine {
+	case "postgres":
+		require.NoError(t, db.Exec("ALTER TABLE test_children DROP CONSTRAINT fk_test_children_parent").Error)
+		require.NoError(t, db.Exec("DELETE FROM test_parents WHERE id = ?", "p2").Error)
+		require.NoError(t, db.Exec(
+			"ALTER TABLE test_children ADD CONSTRAINT fk_test_children_parent "+
+				"FOREIGN KEY (parent_id) REFERENCES test_parents(id) NOT VALID",
+		).Error)
+	case "mysql":
+		require.NoError(t, db.Exec("SET FOREIGN_KEY_CHECKS = 0").Error)
+		require.NoError(t, db.Exec("ALTER TABLE test_children DROP FOREIGN KEY fk_test_children_parent").Error)
+		require.NoError(t, db.Exec("DELETE FROM test_parents WHERE id = ?", "p2").Error)
+		require.NoError(t, db.Exec(
+			"ALTER TABLE test_children ADD CONSTRAINT fk_test_children_parent "+
+				"FOREIGN KEY (parent_id) REFERENCES test_parents(id)",
+		).Error)
+		require.NoError(t, db.Exec("SET FOREIGN_KEY_CHECKS = 1").Error)
+	}
+
+	err = migration.CleanupOrphanedResources[testChildWithFK, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err)
+
+	var count int64
+	db.Model(&testChildWithFK{}).Count(&count)
+	assert.Equal(t, int64(2), count, "Both rows should survive — migration must skip when FK constraint exists")
+}

management/server/mock_server/account_mock.go

@@ -46,7 +46,7 @@ type MockAccountManager struct {
 	AddPeerFunc                           func(ctx context.Context, accountID string, setupKey string, userId string, peer *nbpeer.Peer, temporary bool) (*nbpeer.Peer, *types.NetworkMap, []*posture.Checks, error)
 	GetGroupFunc                          func(ctx context.Context, accountID, groupID, userID string) (*types.Group, error)
 	GetAllGroupsFunc                      func(ctx context.Context, accountID, userID string) ([]*types.Group, error)
-	GetGroupByNameFunc                    func(ctx context.Context, accountID, groupName string) (*types.Group, error)
+	GetGroupByNameFunc                    func(ctx context.Context, groupName, accountID, userID string) (*types.Group, error)
 	SaveGroupFunc                         func(ctx context.Context, accountID, userID string, group *types.Group, create bool) error
 	SaveGroupsFunc                        func(ctx context.Context, accountID, userID string, groups []*types.Group, create bool) error
 	DeleteGroupFunc                       func(ctx context.Context, accountID, userId, groupID string) error
@@ -406,9 +406,9 @@ func (am *MockAccountManager) AddPeer(
 }
 
 // GetGroupByName mock implementation of GetGroupByName from server.AccountManager interface
-func (am *MockAccountManager) GetGroupByName(ctx context.Context, accountID, groupName string) (*types.Group, error) {
+func (am *MockAccountManager) GetGroupByName(ctx context.Context, groupName, accountID, userID string) (*types.Group, error) {
 	if am.GetGroupByNameFunc != nil {
-		return am.GetGroupByNameFunc(ctx, accountID, groupName)
+		return am.GetGroupByNameFunc(ctx, groupName, accountID, userID)
 	}
 	return nil, status.Errorf(codes.Unimplemented, "method GetGroupByName is not implemented")
 }

management/server/store/sql_store.go

@@ -396,6 +396,11 @@ func (s *SqlStore) DeleteAccount(ctx context.Context, account *types.Account) er
 			return result.Error
 		}
 
+		result = tx.Select(clause.Associations).Delete(account.Services, "account_id = ?", account.Id)
+		if result.Error != nil {
+			return result.Error
+		}
+
 		result = tx.Select(clause.Associations).Delete(account)
 		if result.Error != nil {
 			return result.Error
@@ -1012,10 +1017,10 @@ func (s *SqlStore) GetAccountsCounter(ctx context.Context) (int64, error) {
 // GetCustomDomainsCounts returns the total and validated custom domain counts.
 func (s *SqlStore) GetCustomDomainsCounts(ctx context.Context) (int64, int64, error) {
 	var total, validated int64
-	if err := s.db.WithContext(ctx).Model(&domain.Domain{}).Count(&total).Error; err != nil {
+	if err := s.db.Model(&domain.Domain{}).Count(&total).Error; err != nil {
 		return 0, 0, err
 	}
-	if err := s.db.WithContext(ctx).Model(&domain.Domain{}).Where("validated = ?", true).Count(&validated).Error; err != nil {
+	if err := s.db.Model(&domain.Domain{}).Where("validated = ?", true).Count(&validated).Error; err != nil {
 		return 0, 0, err
 	}
 	return total, validated, nil
@@ -2080,7 +2085,8 @@ func (s *SqlStore) getPostureChecks(ctx context.Context, accountID string) ([]*p
 func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpservice.Service, error) {
 	const serviceQuery = `SELECT id, account_id, name, domain, enabled, auth,
 		meta_created_at, meta_certificate_issued_at, meta_status, proxy_cluster,
-		pass_host_header, rewrite_redirects, session_private_key, session_public_key
+		pass_host_header, rewrite_redirects, session_private_key, session_public_key,
+		mode, listen_port, port_auto_assigned, source, source_peer, terminated
 		FROM services WHERE account_id = $1`
 
 	const targetsQuery = `SELECT id, account_id, service_id, path, host, port, protocol,
@@ -2097,6 +2103,9 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 		var auth []byte
 		var createdAt, certIssuedAt sql.NullTime
 		var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
+		var mode, source, sourcePeer sql.NullString
+		var terminated, portAutoAssigned sql.NullBool
+		var listenPort sql.NullInt64
 		err := row.Scan(
 			&s.ID,
 			&s.AccountID,
@@ -2112,6 +2121,12 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 			&s.RewriteRedirects,
 			&sessionPrivateKey,
 			&sessionPublicKey,
+			&mode,
+			&listenPort,
+			&portAutoAssigned,
+			&source,
+			&sourcePeer,
+			&terminated,
 		)
 		if err != nil {
 			return nil, err
@@ -2143,7 +2158,24 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 		if sessionPublicKey.Valid {
 			s.SessionPublicKey = sessionPublicKey.String
 		}
-
+		if mode.Valid {
+			s.Mode = mode.String
+		}
+		if source.Valid {
+			s.Source = source.String
+		}
+		if sourcePeer.Valid {
+			s.SourcePeer = sourcePeer.String
+		}
+		if terminated.Valid {
+			s.Terminated = terminated.Bool
+		}
+		if portAutoAssigned.Valid {
+			s.PortAutoAssigned = portAutoAssigned.Bool
+		}
+		if listenPort.Valid {
+			s.ListenPort = uint16(listenPort.Int64)
+		}
 		s.Targets = []*rpservice.Target{}
 		return &s, nil
 	})
@@ -4410,7 +4442,7 @@ func (s *SqlStore) DeletePAT(ctx context.Context, userID, patID string) error {
 
 // GetProxyAccessTokenByHashedToken retrieves a proxy access token by its hashed value.
 func (s *SqlStore) GetProxyAccessTokenByHashedToken(ctx context.Context, lockStrength LockingStrength, hashedToken types.HashedProxyToken) (*types.ProxyAccessToken, error) {
-	tx := s.db.WithContext(ctx)
+	tx := s.db
 	if lockStrength != LockingStrengthNone {
 		tx = tx.Clauses(clause.Locking{Strength: string(lockStrength)})
 	}
@@ -4429,7 +4461,7 @@ func (s *SqlStore) GetProxyAccessTokenByHashedToken(ctx context.Context, lockStr
 
 // GetAllProxyAccessTokens retrieves all proxy access tokens.
 func (s *SqlStore) GetAllProxyAccessTokens(ctx context.Context, lockStrength LockingStrength) ([]*types.ProxyAccessToken, error) {
-	tx := s.db.WithContext(ctx)
+	tx := s.db
 	if lockStrength != LockingStrengthNone {
 		tx = tx.Clauses(clause.Locking{Strength: string(lockStrength)})
 	}
@@ -4445,7 +4477,7 @@ func (s *SqlStore) GetAllProxyAccessTokens(ctx context.Context, lockStrength Loc
 
 // SaveProxyAccessToken saves a proxy access token to the database.
 func (s *SqlStore) SaveProxyAccessToken(ctx context.Context, token *types.ProxyAccessToken) error {
-	if result := s.db.WithContext(ctx).Create(token); result.Error != nil {
+	if result := s.db.Create(token); result.Error != nil {
 		return status.Errorf(status.Internal, "save proxy access token: %v", result.Error)
 	}
 	return nil
@@ -4453,7 +4485,7 @@ func (s *SqlStore) SaveProxyAccessToken(ctx context.Context, token *types.ProxyA
 
 // RevokeProxyAccessToken revokes a proxy access token by its ID.
 func (s *SqlStore) RevokeProxyAccessToken(ctx context.Context, tokenID string) error {
-	result := s.db.WithContext(ctx).Model(&types.ProxyAccessToken{}).Where(idQueryCondition, tokenID).Update("revoked", true)
+	result := s.db.Model(&types.ProxyAccessToken{}).Where(idQueryCondition, tokenID).Update("revoked", true)
 	if result.Error != nil {
 		return status.Errorf(status.Internal, "revoke proxy access token: %v", result.Error)
 	}
@@ -4467,7 +4499,7 @@ func (s *SqlStore) RevokeProxyAccessToken(ctx context.Context, tokenID string) e
 
 // MarkProxyAccessTokenUsed updates the last used timestamp for a proxy access token.
 func (s *SqlStore) MarkProxyAccessTokenUsed(ctx context.Context, tokenID string) error {
-	result := s.db.WithContext(ctx).Model(&types.ProxyAccessToken{}).
+	result := s.db.Model(&types.ProxyAccessToken{}).
 		Where(idQueryCondition, tokenID).
 		Update("last_used", time.Now().UTC())
 	if result.Error != nil {
@@ -5136,7 +5168,7 @@ func (s *SqlStore) EphemeralServiceExists(ctx context.Context, lockStrength Lock
 
 // GetServicesByClusterAndPort returns services matching the given proxy cluster, mode, and listen port.
 func (s *SqlStore) GetServicesByClusterAndPort(ctx context.Context, lockStrength LockingStrength, proxyCluster string, mode string, listenPort uint16) ([]*rpservice.Service, error) {
-	tx := s.db.WithContext(ctx)
+	tx := s.db
 	if lockStrength != LockingStrengthNone {
 		tx = tx.Clauses(clause.Locking{Strength: string(lockStrength)})
 	}
@@ -5152,7 +5184,7 @@ func (s *SqlStore) GetServicesByClusterAndPort(ctx context.Context, lockStrength
 
 // GetServicesByCluster returns all services for the given proxy cluster.
 func (s *SqlStore) GetServicesByCluster(ctx context.Context, lockStrength LockingStrength, proxyCluster string) ([]*rpservice.Service, error) {
-	tx := s.db.WithContext(ctx)
+	tx := s.db
 	if lockStrength != LockingStrengthNone {
 		tx = tx.Clauses(clause.Locking{Strength: string(lockStrength)})
 	}
@@ -5262,7 +5294,7 @@ func (s *SqlStore) GetAccountAccessLogs(ctx context.Context, lockStrength Lockin
 	var logs []*accesslogs.AccessLogEntry
 	var totalCount int64
 
-	baseQuery := s.db.WithContext(ctx).
+	baseQuery := s.db.
 		Model(&accesslogs.AccessLogEntry{}).
 		Where(accountIDCondition, accountID)
 
@@ -5273,7 +5305,7 @@ func (s *SqlStore) GetAccountAccessLogs(ctx context.Context, lockStrength Lockin
 		return nil, 0, status.Errorf(status.Internal, "failed to count access logs")
 	}
 
-	query := s.db.WithContext(ctx).
+	query := s.db.
 		Where(accountIDCondition, accountID)
 
 	query = s.applyAccessLogFilters(query, filter)
@@ -5310,7 +5342,7 @@ func (s *SqlStore) GetAccountAccessLogs(ctx context.Context, lockStrength Lockin
 
 // DeleteOldAccessLogs deletes all access logs older than the specified time
 func (s *SqlStore) DeleteOldAccessLogs(ctx context.Context, olderThan time.Time) (int64, error) {
-	result := s.db.WithContext(ctx).
+	result := s.db.
 		Where("timestamp < ?", olderThan).
 		Delete(&accesslogs.AccessLogEntry{})
 
@@ -5399,7 +5431,7 @@ func (s *SqlStore) GetServiceTargetByTargetID(ctx context.Context, lockStrength
 
 // SaveProxy saves or updates a proxy in the database
 func (s *SqlStore) SaveProxy(ctx context.Context, p *proxy.Proxy) error {
-	result := s.db.WithContext(ctx).Save(p)
+	result := s.db.Save(p)
 	if result.Error != nil {
 		log.WithContext(ctx).Errorf("failed to save proxy: %v", result.Error)
 		return status.Errorf(status.Internal, "failed to save proxy")
@@ -5411,7 +5443,7 @@ func (s *SqlStore) SaveProxy(ctx context.Context, p *proxy.Proxy) error {
 func (s *SqlStore) UpdateProxyHeartbeat(ctx context.Context, proxyID, clusterAddress, ipAddress string) error {
 	now := time.Now()
 
-	result := s.db.WithContext(ctx).
+	result := s.db.
 		Model(&proxy.Proxy{}).
 		Where("id = ? AND status = ?", proxyID, "connected").
 		Update("last_seen", now)
@@ -5430,7 +5462,7 @@ func (s *SqlStore) UpdateProxyHeartbeat(ctx context.Context, proxyID, clusterAdd
 			ConnectedAt:    &now,
 			Status:         "connected",
 		}
-		if err := s.db.WithContext(ctx).Save(p).Error; err != nil {
+		if err := s.db.Save(p).Error; err != nil {
 			log.WithContext(ctx).Errorf("failed to create proxy on heartbeat: %v", err)
 			return status.Errorf(status.Internal, "failed to create proxy on heartbeat")
 		}
@@ -5443,7 +5475,7 @@ func (s *SqlStore) UpdateProxyHeartbeat(ctx context.Context, proxyID, clusterAdd
 func (s *SqlStore) GetActiveProxyClusterAddresses(ctx context.Context) ([]string, error) {
 	var addresses []string
 
-	result := s.db.WithContext(ctx).
+	result := s.db.
 		Model(&proxy.Proxy{}).
 		Where("status = ? AND last_seen > ?", "connected", time.Now().Add(-proxyActiveThreshold)).
 		Distinct("cluster_address").
@@ -5512,7 +5544,7 @@ func (s *SqlStore) getClusterCapability(ctx context.Context, clusterAddr, column
 		AnyTrue       bool
 	}
 
-	err := s.db.WithContext(ctx).
+	err := s.db.
 		Model(&proxy.Proxy{}).
 		Select("COUNT(CASE WHEN "+column+" IS NOT NULL THEN 1 END) > 0 AS has_capability, "+
 			"COALESCE(MAX(CASE WHEN "+column+" = true THEN 1 ELSE 0 END), 0) = 1 AS any_true").
@@ -5536,7 +5568,7 @@ func (s *SqlStore) getClusterCapability(ctx context.Context, clusterAddr, column
 func (s *SqlStore) CleanupStaleProxies(ctx context.Context, inactivityDuration time.Duration) error {
 	cutoffTime := time.Now().Add(-inactivityDuration)
 
-	result := s.db.WithContext(ctx).
+	result := s.db.
 		Where("last_seen < ?", cutoffTime).
 		Delete(&proxy.Proxy{})
 

management/server/store/sql_store_test.go

@@ -22,6 +22,8 @@ import (
 	"github.com/stretchr/testify/require"
 
 	nbdns "github.com/netbirdio/netbird/dns"
+	proxydomain "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
+	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/netbirdio/netbird/management/internals/modules/zones"
 	"github.com/netbirdio/netbird/management/internals/modules/zones/records"
 	resourceTypes "github.com/netbirdio/netbird/management/server/networks/resources/types"
@@ -350,6 +352,35 @@ func TestSqlite_DeleteAccount(t *testing.T) {
 		},
 	}
 
+	account.Services = []*rpservice.Service{
+		{
+			ID:        "service_id",
+			AccountID: account.Id,
+			Name:      "test service",
+			Domain:    "svc.example.com",
+			Enabled:   true,
+			Targets: []*rpservice.Target{
+				{
+					AccountID: account.Id,
+					ServiceID: "service_id",
+					Host:      "localhost",
+					Port:      8080,
+					Protocol:  "http",
+					Enabled:   true,
+				},
+			},
+		},
+	}
+
+	account.Domains = []*proxydomain.Domain{
+		{
+			ID:        "domain_id",
+			Domain:    "custom.example.com",
+			AccountID: account.Id,
+			Validated: true,
+		},
+	}
+
 	err = store.SaveAccount(context.Background(), account)
 	require.NoError(t, err)
 
@@ -411,6 +442,20 @@ func TestSqlite_DeleteAccount(t *testing.T) {
 		require.NoError(t, err, "expecting no error after removing DeleteAccount when searching for network resources")
 		require.Len(t, resources, 0, "expecting no network resources to be found after DeleteAccount")
 	}
+
+	domains, err := store.ListCustomDomains(context.Background(), account.Id)
+	require.NoError(t, err, "expecting no error after DeleteAccount when searching for custom domains")
+	require.Len(t, domains, 0, "expecting no custom domains to be found after DeleteAccount")
+
+	var services []*rpservice.Service
+	err = store.(*SqlStore).db.Model(&rpservice.Service{}).Find(&services, "account_id = ?", account.Id).Error
+	require.NoError(t, err, "expecting no error after DeleteAccount when searching for services")
+	require.Len(t, services, 0, "expecting no services to be found after DeleteAccount")
+
+	var targets []*rpservice.Target
+	err = store.(*SqlStore).db.Model(&rpservice.Target{}).Find(&targets, "account_id = ?", account.Id).Error
+	require.NoError(t, err, "expecting no error after DeleteAccount when searching for service targets")
+	require.Len(t, targets, 0, "expecting no service targets to be found after DeleteAccount")
 }
 
 func Test_GetAccount(t *testing.T) {

management/server/store/sqlstore_bench_test.go

@@ -20,6 +20,7 @@ import (
 	"github.com/stretchr/testify/assert"
 
 	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	resourceTypes "github.com/netbirdio/netbird/management/server/networks/resources/types"
 	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
@@ -265,6 +266,7 @@ func setupBenchmarkDB(b testing.TB) (*SqlStore, func(), string) {
 		&nbdns.NameServerGroup{}, &posture.Checks{}, &networkTypes.Network{},
 		&routerTypes.NetworkRouter{}, &resourceTypes.NetworkResource{},
 		&types.AccountOnboarding{}, &service.Service{}, &service.Target{},
+		&domain.Domain{},
 	}
 
 	for i := len(models) - 1; i >= 0; i-- {