Merge PR #5971 and add NRPT root-zone catch-all in RouteAll mode

# Conflicts:
#	client/internal/dns/upstream.go

.golangci.yaml

@@ -92,6 +92,9 @@ linters:
       - linters:
           - unused
         path: client/firewall/iptables/rule\.go
+      - linters:
+          - unused
+        path: client/internal/dns/dnsfw/(types|syscall|zsyscall)_windows.*\.go
       - linters:
           - gosec
           - mirror

client/internal/connect.go

@@ -116,7 +116,6 @@ 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.
@@ -126,7 +125,6 @@ func (c *ConnectClient) RunOniOS(
 		FileDescriptor:        fileDescriptor,
 		NetworkChangeListener: networkChangeListener,
 		DnsManager:            dnsManager,
-		HostDNSAddresses:      dnsAddresses,
 		StateFilePath:         stateFilePath,
 	}
 	return c.run(mobileDependency, nil, "")

client/internal/dns/dnsfw/config.go

@@ -0,0 +1,63 @@
+package dnsfw
+
+import (
+	"os"
+	"strconv"
+	"strings"
+
+	log "github.com/sirupsen/logrus"
+)
+
+const (
+	// EnvDisable disables the DNS firewall entirely when set to a truthy value.
+	EnvDisable = "NB_DISABLE_DNS_FIREWALL"
+	// EnvPorts overrides the comma-separated list of remote ports to block.
+	// Empty disables the firewall.
+	EnvPorts = "NB_DNS_FIREWALL_PORTS"
+	// EnvStrict enables strict mode: permit DNS only to the virtual DNS IP
+	// and the netbird daemon. Default mode also permits anything on the
+	// netbird tunnel interface, which is safer if NRPT is silently ignored
+	// by Windows but lets apps reach custom DNS servers via the tunnel.
+	EnvStrict = "NB_DNS_FIREWALL_STRICT"
+)
+
+// defaultBlockedPorts are the well-known DNS ports we block for non-netbird
+// processes: 53 (plain DNS) and 853 (DNS-over-TLS).
+var defaultBlockedPorts = []uint16{53, 853}
+
+// blockedPorts returns the effective port list, honoring env overrides.
+// A nil return means the firewall should not be installed.
+func blockedPorts() []uint16 {
+	if disabled, _ := strconv.ParseBool(os.Getenv(EnvDisable)); disabled {
+		log.Infof("dns firewall disabled via %s", EnvDisable)
+		return nil
+	}
+
+	override, ok := os.LookupEnv(EnvPorts)
+	if !ok {
+		return defaultBlockedPorts
+	}
+
+	var ports []uint16
+	for _, raw := range strings.Split(override, ",") {
+		raw = strings.TrimSpace(raw)
+		if raw == "" {
+			continue
+		}
+		port, err := strconv.ParseUint(raw, 10, 16)
+		if err != nil {
+			log.Warnf("dns firewall: ignoring invalid port %q in %s: %v", raw, EnvPorts, err)
+			continue
+		}
+		if port == 0 {
+			log.Warnf("dns firewall: ignoring port 0 in %s", EnvPorts)
+			continue
+		}
+		ports = append(ports, uint16(port))
+	}
+	if len(ports) == 0 {
+		log.Infof("dns firewall disabled: %s yielded no valid ports", EnvPorts)
+		return nil
+	}
+	return ports
+}

client/internal/dns/dnsfw/config_test.go

@@ -0,0 +1,39 @@
+package dnsfw
+
+import (
+	"reflect"
+	"testing"
+)
+
+func TestBlockedPorts(t *testing.T) {
+	tests := []struct {
+		name     string
+		disable  string
+		ports    string
+		setPorts bool
+		want     []uint16
+	}{
+		{name: "default", want: defaultBlockedPorts},
+		{name: "disabled", disable: "true", want: nil},
+		{name: "disabled false keeps default", disable: "false", want: defaultBlockedPorts},
+		{name: "override single port", ports: "53", setPorts: true, want: []uint16{53}},
+		{name: "override multi", ports: "53, 853 ,5353", setPorts: true, want: []uint16{53, 853, 5353}},
+		{name: "override empty disables", ports: "", setPorts: true, want: nil},
+		{name: "override invalid skipped", ports: "53,not-a-port,853", setPorts: true, want: []uint16{53, 853}},
+		{name: "override zero skipped", ports: "53,0,853", setPorts: true, want: []uint16{53, 853}},
+		{name: "override only invalid disables", ports: "abc", setPorts: true, want: nil},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Setenv(EnvDisable, tc.disable)
+			if tc.setPorts {
+				t.Setenv(EnvPorts, tc.ports)
+			}
+			got := blockedPorts()
+			if !reflect.DeepEqual(got, tc.want) {
+				t.Fatalf("blockedPorts() = %v, want %v", got, tc.want)
+			}
+		})
+	}
+}

client/internal/dns/dnsfw/dnsfw.go

@@ -0,0 +1,16 @@
+// Package dnsfw blocks DNS traffic from non-netbird processes when netbird is
+// managing the host's DNS, so that resolvers running on apps or libraries
+// outside netbird cannot bypass the configured DNS path.
+//
+// Implementation is Windows-only (uses WFP). On other platforms New returns
+// a no-op manager.
+package dnsfw
+
+import "net/netip"
+
+// Manager controls the per-tunnel DNS firewall. Both methods must be safe
+// to call multiple times.
+type Manager interface {
+	Enable(ifaceGUID string, virtualDNSIP netip.Addr) error
+	Disable() error
+}

client/internal/dns/dnsfw/dnsfw_other.go

@@ -0,0 +1,15 @@
+//go:build !windows
+
+package dnsfw
+
+import "net/netip"
+
+type noopManager struct{}
+
+func (noopManager) Enable(string, netip.Addr) error { return nil }
+func (noopManager) Disable() error                  { return nil }
+
+// New returns a no-op manager on non-Windows platforms.
+func New() Manager {
+	return noopManager{}
+}

client/internal/dns/dnsfw/dnsfw_windows.go

@@ -0,0 +1,144 @@
+//go:build windows
+
+package dnsfw
+
+import (
+	"fmt"
+	"net/netip"
+	"os"
+	"strconv"
+	"sync"
+	"unsafe"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/sys/windows"
+)
+
+var (
+	modIphlpapi                    = windows.NewLazyDLL("iphlpapi.dll")
+	procConvertInterfaceGuidToLuid = modIphlpapi.NewProc("ConvertInterfaceGuidToLuid")
+)
+
+type windowsManager struct {
+	mu sync.Mutex
+	// session is the WFP engine handle. Zero when disabled.
+	session uintptr
+}
+
+// Enable installs the dns firewall. Strict mode propagates failures;
+// non-strict mode logs and returns nil so partial protection is preserved.
+func (m *windowsManager) Enable(ifaceGUID string, virtualDNSIP netip.Addr) error {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	ports := blockedPorts()
+	if len(ports) == 0 {
+		return nil
+	}
+
+	if m.session != 0 {
+		if err := m.disableLocked(); err != nil {
+			return fmt.Errorf("reset existing dns firewall session: %w", err)
+		}
+	}
+
+	strict := strictMode()
+
+	luid, err := luidFromGUID(ifaceGUID)
+	if err != nil {
+		return m.failOrLog(strict, fmt.Errorf("resolve tun luid from guid %s: %w", ifaceGUID, err))
+	}
+
+	exe, err := os.Executable()
+	if err != nil {
+		return m.failOrLog(strict, fmt.Errorf("resolve daemon executable path: %w", err))
+	}
+
+	cfg := installConfig{
+		tunLUID:      luid,
+		daemonExe:    exe,
+		blockedPorts: ports,
+		strict:       strict,
+		virtualDNSIP: virtualDNSIP,
+	}
+	// session==0 signals a hard failure; non-zero with non-nil err is a partial install.
+	session, installErr := installFilters(cfg)
+	if session == 0 {
+		return m.failOrLog(strict, fmt.Errorf("install dns firewall filters: %w", installErr))
+	}
+
+	if installErr != nil && strict {
+		_ = closeSession(session)
+		return fmt.Errorf("strict dns firewall: partial install: %w", installErr)
+	}
+
+	m.session = session
+	log.Infof("dns firewall installed: iface=%s daemon=%s ports=%v strict=%v virtual_dns=%s",
+		ifaceGUID, exe, ports, strict, virtualDNSIP)
+	if installErr != nil {
+		log.Warnf("dns firewall partially installed (some filters failed): %v", installErr)
+	}
+	return nil
+}
+
+func (m *windowsManager) Disable() error {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	return m.disableLocked()
+}
+
+func (m *windowsManager) disableLocked() error {
+	if m.session == 0 {
+		return nil
+	}
+	session := m.session
+	m.session = 0
+	if err := closeSession(session); err != nil {
+		return fmt.Errorf("close wfp session: %w", err)
+	}
+	log.Info("dns firewall removed")
+	return nil
+}
+
+// failOrLog returns err unchanged in strict mode. In non-strict mode the
+// error is logged and nil is returned.
+func (m *windowsManager) failOrLog(strict bool, err error) error {
+	if strict {
+		return err
+	}
+	log.Errorf("dns firewall: %v", err)
+	return nil
+}
+
+// New returns a Windows DNS firewall manager backed by WFP.
+func New() Manager {
+	return &windowsManager{}
+}
+
+// strictMode reports whether strict mode is enabled via env.
+func strictMode() bool {
+	v, _ := strconv.ParseBool(os.Getenv(EnvStrict))
+	return v
+}
+
+// luidFromGUID converts a Windows interface GUID string to its LUID.
+func luidFromGUID(ifaceGUID string) (luid uint64, err error) {
+	defer func() {
+		if r := recover(); r != nil {
+			err = fmt.Errorf("panic in luidFromGUID: %v", r)
+		}
+	}()
+
+	guid, err := windows.GUIDFromString(ifaceGUID)
+	if err != nil {
+		return 0, fmt.Errorf("parse guid: %w", err)
+	}
+	rc, _, _ := procConvertInterfaceGuidToLuid.Call(
+		uintptr(unsafe.Pointer(&guid)),
+		uintptr(unsafe.Pointer(&luid)),
+	)
+	if rc != 0 {
+		return 0, fmt.Errorf("ConvertInterfaceGuidToLuid returned %d", rc)
+	}
+	return luid, nil
+}

client/internal/dns/dnsfw/dnsfw_windows_test.go

@@ -0,0 +1,72 @@
+//go:build windows
+
+package dnsfw
+
+import (
+	"net/netip"
+	"os"
+	"testing"
+)
+
+func TestStrictMode(t *testing.T) {
+	tests := []struct {
+		name string
+		val  string
+		set  bool
+		want bool
+	}{
+		{name: "unset", want: false},
+		{name: "true", val: "true", set: true, want: true},
+		{name: "1", val: "1", set: true, want: true},
+		{name: "false", val: "false", set: true, want: false},
+		{name: "invalid is false", val: "garbage", set: true, want: false},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Setenv(EnvStrict, tc.val)
+			if !tc.set {
+				os.Unsetenv(EnvStrict)
+			}
+			if got := strictMode(); got != tc.want {
+				t.Fatalf("strictMode() = %v, want %v", got, tc.want)
+			}
+		})
+	}
+}
+
+func TestWindowsManagerDisableIdempotent(t *testing.T) {
+	m := &windowsManager{}
+	if err := m.Disable(); err != nil {
+		t.Fatalf("first Disable on fresh manager: %v", err)
+	}
+	if err := m.Disable(); err != nil {
+		t.Fatalf("second Disable on fresh manager: %v", err)
+	}
+	if m.session != 0 {
+		t.Fatalf("session should remain zero, got %d", m.session)
+	}
+}
+
+func TestWindowsManagerEnableNoOpWhenDisabledByEnv(t *testing.T) {
+	t.Setenv(EnvDisable, "true")
+
+	m := &windowsManager{}
+	if err := m.Enable("00000000-0000-0000-0000-000000000000", netip.Addr{}); err != nil {
+		t.Fatalf("Enable should be a no-op when firewall disabled by env: %v", err)
+	}
+	if m.session != 0 {
+		t.Fatalf("session must remain zero when env disables firewall, got %d", m.session)
+	}
+}
+
+func TestWindowsManagerEnableNoOpWhenPortsEmpty(t *testing.T) {
+	t.Setenv(EnvPorts, "")
+
+	m := &windowsManager{}
+	if err := m.Enable("00000000-0000-0000-0000-000000000000", netip.Addr{}); err != nil {
+		t.Fatalf("Enable should be a no-op when ports list is empty: %v", err)
+	}
+	if m.session != 0 {
+		t.Fatalf("session must remain zero when ports list is empty, got %d", m.session)
+	}
+}

client/internal/dns/dnsfw/helpers_windows.go

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2019-2021 WireGuard LLC. All Rights Reserved.
+ *
+ * Adapted from wireguard-windows tunnel/firewall/helpers.go.
+ */
+
+package dnsfw
+
+import (
+	"errors"
+	"fmt"
+	"runtime"
+	"syscall"
+
+	"golang.org/x/sys/windows"
+)
+
+func createWtFwpmDisplayData0(name, description string) (*wtFwpmDisplayData0, error) {
+	namePtr, err := windows.UTF16PtrFromString(name)
+	if err != nil {
+		return nil, wrapErr(err)
+	}
+
+	descriptionPtr, err := windows.UTF16PtrFromString(description)
+	if err != nil {
+		return nil, wrapErr(err)
+	}
+
+	return &wtFwpmDisplayData0{
+		name:        namePtr,
+		description: descriptionPtr,
+	}, nil
+}
+
+func filterWeight(weight uint8) wtFwpValue0 {
+	return wtFwpValue0{
+		_type: cFWP_UINT8,
+		value: uintptr(weight),
+	}
+}
+
+func wrapErr(err error) error {
+	var errno syscall.Errno
+	if !errors.As(err, &errno) {
+		return err
+	}
+	_, file, line, ok := runtime.Caller(1)
+	if !ok {
+		return fmt.Errorf("wfp error at unknown location: %w", err)
+	}
+	return fmt.Errorf("wfp error at %s:%d: %w", file, line, err)
+}

client/internal/dns/dnsfw/rules_windows.go

@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2019-2021 WireGuard LLC. All Rights Reserved.
+ * Copyright (C) 2026 NetBird GmbH. All Rights Reserved.
+ *
+ * Filter installers adapted from wireguard-windows tunnel/firewall/rules.go.
+ * The block-DNS approach (port 53 + UDP/TCP) matches what wireguard-windows
+ * uses for its kill-switch DNS leak protection. We extend it with a
+ * configurable port set so we also cover :853 (DoT) and any future ports.
+ */
+
+package dnsfw
+
+import (
+	"encoding/binary"
+	"fmt"
+	"net/netip"
+	"unsafe"
+
+	"github.com/hashicorp/go-multierror"
+	"golang.org/x/sys/windows"
+
+	nberrors "github.com/netbirdio/netbird/client/errors"
+)
+
+// Filters install at outbound ALE_AUTH_CONNECT layers only; inbound replies
+// follow the authorized outbound flow.
+
+// permitTunInterface installs a permit filter for any traffic whose local
+// interface is the netbird tunnel.
+func permitTunInterface(session uintptr, base *baseObjects, weight uint8, ifLUID uint64) error {
+	cond := wtFwpmFilterCondition0{
+		fieldKey:  cFWPM_CONDITION_IP_LOCAL_INTERFACE,
+		matchType: cFWP_MATCH_EQUAL,
+		conditionValue: wtFwpConditionValue0{
+			_type: cFWP_UINT64,
+			value: uintptr(unsafe.Pointer(&ifLUID)),
+		},
+	}
+
+	filter := wtFwpmFilter0{
+		providerKey:         &base.provider,
+		subLayerKey:         base.filters,
+		weight:              filterWeight(weight),
+		numFilterConditions: 1,
+		filterCondition:     (*wtFwpmFilterCondition0)(unsafe.Pointer(&cond)),
+		action:              wtFwpmAction0{_type: cFWP_ACTION_PERMIT},
+	}
+
+	return addOutboundFilters(session, &filter, "Permit netbird tunnel")
+}
+
+// permitDaemonByAppID installs a permit filter matching the netbird daemon
+// executable by App-ID. App-ID alone is sufficient because netbird.exe is a
+// dedicated binary.
+func permitDaemonByAppID(session uintptr, base *baseObjects, daemonExe string, weight uint8) error {
+	appID, err := daemonAppID(daemonExe)
+	if err != nil {
+		return err
+	}
+	defer fwpmFreeMemory0(unsafe.Pointer(&appID))
+
+	cond := wtFwpmFilterCondition0{
+		fieldKey:  cFWPM_CONDITION_ALE_APP_ID,
+		matchType: cFWP_MATCH_EQUAL,
+		conditionValue: wtFwpConditionValue0{
+			_type: cFWP_BYTE_BLOB_TYPE,
+			value: uintptr(unsafe.Pointer(appID)),
+		},
+	}
+
+	filter := wtFwpmFilter0{
+		providerKey:         &base.provider,
+		subLayerKey:         base.filters,
+		weight:              filterWeight(weight),
+		numFilterConditions: 1,
+		filterCondition:     (*wtFwpmFilterCondition0)(unsafe.Pointer(&cond)),
+		action:              wtFwpmAction0{_type: cFWP_ACTION_PERMIT},
+	}
+
+	return addOutboundFilters(session, &filter, "Permit netbird daemon")
+}
+
+// permitVirtualDNSIP installs a permit filter for DNS-port traffic destined
+// for the in-tunnel virtual DNS IP. Used in strict mode in lieu of
+// permitTunInterface.
+func permitVirtualDNSIP(session uintptr, base *baseObjects, ip netip.Addr, ports []uint16, weight uint8) error {
+	var merr *multierror.Error
+	for _, port := range ports {
+		if err := permitDNSToHost(session, base, ip, port, weight); err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("permit %s:%d: %w", ip, port, err))
+		}
+	}
+	return nberrors.FormatErrorOrNil(merr)
+}
+
+func permitDNSToHost(session uintptr, base *baseObjects, ip netip.Addr, port uint16, weight uint8) error {
+	if !ip.IsValid() {
+		return fmt.Errorf("invalid address")
+	}
+
+	var addrCond wtFwpmFilterCondition0
+	var layer windows.GUID
+	// v6 backing must outlive fwpmFilterAdd0; keep it on this stack frame.
+	var v6 wtFwpByteArray16
+
+	if ip.Is4() {
+		v4 := ip.As4()
+		addrCond = wtFwpmFilterCondition0{
+			fieldKey:  cFWPM_CONDITION_IP_REMOTE_ADDRESS,
+			matchType: cFWP_MATCH_EQUAL,
+			conditionValue: wtFwpConditionValue0{
+				_type: cFWP_UINT32,
+				value: uintptr(binary.BigEndian.Uint32(v4[:])),
+			},
+		}
+		layer = cFWPM_LAYER_ALE_AUTH_CONNECT_V4
+	} else {
+		v6 = wtFwpByteArray16{byteArray16: ip.As16()}
+		addrCond = wtFwpmFilterCondition0{
+			fieldKey:  cFWPM_CONDITION_IP_REMOTE_ADDRESS,
+			matchType: cFWP_MATCH_EQUAL,
+			conditionValue: wtFwpConditionValue0{
+				_type: cFWP_BYTE_ARRAY16_TYPE,
+				value: uintptr(unsafe.Pointer(&v6)),
+			},
+		}
+		layer = cFWPM_LAYER_ALE_AUTH_CONNECT_V6
+	}
+
+	conditions := [2]wtFwpmFilterCondition0{
+		addrCond,
+		{
+			fieldKey:  cFWPM_CONDITION_IP_REMOTE_PORT,
+			matchType: cFWP_MATCH_EQUAL,
+			conditionValue: wtFwpConditionValue0{
+				_type: cFWP_UINT16,
+				value: uintptr(port),
+			},
+		},
+	}
+	filter := wtFwpmFilter0{
+		providerKey:         &base.provider,
+		subLayerKey:         base.filters,
+		weight:              filterWeight(weight),
+		numFilterConditions: uint32(len(conditions)),
+		filterCondition:     (*wtFwpmFilterCondition0)(unsafe.Pointer(&conditions[0])),
+		action:              wtFwpmAction0{_type: cFWP_ACTION_PERMIT},
+	}
+
+	display, err := createWtFwpmDisplayData0(fmt.Sprintf("Permit DNS to %s:%d", ip, port), "")
+	if err != nil {
+		return wrapErr(err)
+	}
+	filter.displayData = *display
+	filter.layerKey = layer
+
+	var filterID uint64
+	if err := fwpmFilterAdd0(session, &filter, 0, &filterID); err != nil {
+		return wrapErr(err)
+	}
+	_ = v6
+	return nil
+}
+
+// blockDNSPorts installs a deny filter for outbound traffic to each of the
+// given remote ports over UDP or TCP. Per-port and per-layer failures are
+// accumulated; partial coverage is preferred over zero coverage.
+func blockDNSPorts(session uintptr, base *baseObjects, ports []uint16, weight uint8) error {
+	var merr *multierror.Error
+	for _, port := range ports {
+		if err := blockDNSPort(session, base, port, weight); err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("block port %d: %w", port, err))
+		}
+	}
+	return nberrors.FormatErrorOrNil(merr)
+}
+
+func blockDNSPort(session uintptr, base *baseObjects, port uint16, weight uint8) error {
+	conditions := [3]wtFwpmFilterCondition0{
+		{
+			fieldKey:  cFWPM_CONDITION_IP_REMOTE_PORT,
+			matchType: cFWP_MATCH_EQUAL,
+			conditionValue: wtFwpConditionValue0{
+				_type: cFWP_UINT16,
+				value: uintptr(port),
+			},
+		},
+		{
+			fieldKey:  cFWPM_CONDITION_IP_PROTOCOL,
+			matchType: cFWP_MATCH_EQUAL,
+			conditionValue: wtFwpConditionValue0{
+				_type: cFWP_UINT8,
+				value: uintptr(cIPPROTO_UDP),
+			},
+		},
+		// Repeat the IP_PROTOCOL condition for logical OR with TCP.
+		{
+			fieldKey:  cFWPM_CONDITION_IP_PROTOCOL,
+			matchType: cFWP_MATCH_EQUAL,
+			conditionValue: wtFwpConditionValue0{
+				_type: cFWP_UINT8,
+				value: uintptr(cIPPROTO_TCP),
+			},
+		},
+	}
+
+	filter := wtFwpmFilter0{
+		providerKey:         &base.provider,
+		subLayerKey:         base.filters,
+		weight:              filterWeight(weight),
+		numFilterConditions: uint32(len(conditions)),
+		filterCondition:     (*wtFwpmFilterCondition0)(unsafe.Pointer(&conditions[0])),
+		action:              wtFwpmAction0{_type: cFWP_ACTION_BLOCK},
+	}
+
+	return addOutboundFilters(session, &filter, fmt.Sprintf("Block DNS port %d", port))
+}
+
+// addOutboundFilters installs the same filter on the v4 and v6 outbound ALE
+// connect layers. v4 and v6 are installed independently: failure on one
+// layer does not abort the other, and the accumulated errors are returned.
+// Partial coverage is preferred over zero coverage.
+func addOutboundFilters(session uintptr, filter *wtFwpmFilter0, name string) error {
+	layers := [...]struct {
+		layer windows.GUID
+		label string
+	}{
+		{cFWPM_LAYER_ALE_AUTH_CONNECT_V4, name + " (IPv4)"},
+		{cFWPM_LAYER_ALE_AUTH_CONNECT_V6, name + " (IPv6)"},
+	}
+
+	var merr *multierror.Error
+	for _, l := range layers {
+		display, err := createWtFwpmDisplayData0(l.label, "")
+		if err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("%s: %w", l.label, wrapErr(err)))
+			continue
+		}
+		filter.displayData = *display
+		filter.layerKey = l.layer
+
+		var filterID uint64
+		if err := fwpmFilterAdd0(session, filter, 0, &filterID); err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("%s: %w", l.label, wrapErr(err)))
+		}
+	}
+	return nberrors.FormatErrorOrNil(merr)
+}

client/internal/dns/dnsfw/session_windows.go

@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2019-2021 WireGuard LLC. All Rights Reserved.
+ * Copyright (C) 2026 NetBird GmbH. All Rights Reserved.
+ *
+ * Session lifecycle and the high-level Install/Close entry points adapted
+ * from wireguard-windows tunnel/firewall.
+ */
+
+package dnsfw
+
+import (
+	"errors"
+	"fmt"
+	"net/netip"
+	"unsafe"
+
+	"github.com/hashicorp/go-multierror"
+	"golang.org/x/sys/windows"
+
+	nberrors "github.com/netbirdio/netbird/client/errors"
+)
+
+// installConfig is the input to installFilters.
+type installConfig struct {
+	tunLUID      uint64
+	daemonExe    string
+	blockedPorts []uint16
+	// strict, when true, narrows the carve-out from "anything on tun" to
+	// "DNS only to virtualDNSIP". virtualDNSIP must be valid in this case.
+	strict       bool
+	virtualDNSIP netip.Addr
+}
+
+// baseObjects holds the GUIDs of the WFP provider and sublayer registered
+// for our session. Both are randomly generated per session.
+type baseObjects struct {
+	provider windows.GUID
+	filters  windows.GUID
+}
+
+// installFilters opens a dynamic WFP session and installs the netbird DNS
+// firewall filters. Returns a zero session on hard failure (session create,
+// base objects); a non-zero session with a non-nil error is a partial install
+// (some per-filter installs failed) and is safe to close.
+func installFilters(cfg installConfig) (session uintptr, err error) {
+	defer func() {
+		if r := recover(); r != nil {
+			// Dynamic session: kernel will clean up on process exit even
+			// if we leave the handle dangling here.
+			err = fmt.Errorf("panic in installFilters: %v", r)
+		}
+	}()
+
+	if len(cfg.blockedPorts) == 0 {
+		return 0, errors.New("dns firewall: no blocked ports configured")
+	}
+	if cfg.strict && !cfg.virtualDNSIP.IsValid() {
+		return 0, errors.New("dns firewall: strict mode requires a valid virtual DNS IP")
+	}
+
+	session, err = createSession()
+	if err != nil {
+		return 0, err
+	}
+
+	base, err := registerBaseObjects(session)
+	if err != nil {
+		_ = fwpmEngineClose0(session)
+		return 0, fmt.Errorf("register base objects: %w", err)
+	}
+
+	var merr *multierror.Error
+	if cfg.strict {
+		if err := permitVirtualDNSIP(session, base, cfg.virtualDNSIP, cfg.blockedPorts, 15); err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("permit virtual dns: %w", err))
+		}
+	} else {
+		if err := permitTunInterface(session, base, 15, cfg.tunLUID); err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("permit tun interface: %w", err))
+		}
+	}
+	if err := permitDaemonByAppID(session, base, cfg.daemonExe, 14); err != nil {
+		merr = multierror.Append(merr, fmt.Errorf("permit netbird daemon: %w", err))
+	}
+	if err := blockDNSPorts(session, base, cfg.blockedPorts, 10); err != nil {
+		merr = multierror.Append(merr, fmt.Errorf("block dns ports: %w", err))
+	}
+
+	return session, nberrors.FormatErrorOrNil(merr)
+}
+
+// closeSession tears down a WFP session previously opened by installFilters.
+// All filters owned by the session are removed.
+func closeSession(session uintptr) (err error) {
+	defer func() {
+		if r := recover(); r != nil {
+			err = fmt.Errorf("panic in closeSession: %v", r)
+		}
+	}()
+
+	if session == 0 {
+		return nil
+	}
+	if err := fwpmEngineClose0(session); err != nil {
+		return wrapErr(err)
+	}
+	return nil
+}
+
+func createSession() (uintptr, error) {
+	displayData, err := createWtFwpmDisplayData0("NetBird DNS firewall", "NetBird DNS firewall dynamic session")
+	if err != nil {
+		return 0, wrapErr(err)
+	}
+	session := wtFwpmSession0{
+		displayData:          *displayData,
+		flags:                cFWPM_SESSION_FLAG_DYNAMIC,
+		txnWaitTimeoutInMSec: windows.INFINITE,
+	}
+	var handle uintptr
+	if err := fwpmEngineOpen0(nil, cRPC_C_AUTHN_WINNT, nil, &session, unsafe.Pointer(&handle)); err != nil {
+		return 0, wrapErr(err)
+	}
+	return handle, nil
+}
+
+func registerBaseObjects(session uintptr) (*baseObjects, error) {
+	bo := &baseObjects{}
+	var err error
+	if bo.provider, err = windows.GenerateGUID(); err != nil {
+		return nil, wrapErr(err)
+	}
+	if bo.filters, err = windows.GenerateGUID(); err != nil {
+		return nil, wrapErr(err)
+	}
+
+	displayData, err := createWtFwpmDisplayData0("NetBird DNS firewall", "NetBird DNS firewall provider")
+	if err != nil {
+		return nil, wrapErr(err)
+	}
+	provider := wtFwpmProvider0{
+		providerKey: bo.provider,
+		displayData: *displayData,
+	}
+	if err := fwpmProviderAdd0(session, &provider, 0); err != nil {
+		return nil, wrapErr(err)
+	}
+
+	subDisplay, err := createWtFwpmDisplayData0("NetBird DNS firewall filters", "Permit and block filters")
+	if err != nil {
+		return nil, wrapErr(err)
+	}
+	sublayer := wtFwpmSublayer0{
+		subLayerKey: bo.filters,
+		displayData: *subDisplay,
+		providerKey: &bo.provider,
+		weight:      ^uint16(0),
+	}
+	if err := fwpmSubLayerAdd0(session, &sublayer, 0); err != nil {
+		return nil, wrapErr(err)
+	}
+	return bo, nil
+}
+
+// daemonAppID returns the WFP App-ID byte blob for the given executable path.
+func daemonAppID(path string) (*wtFwpByteBlob, error) {
+	pathPtr, err := windows.UTF16PtrFromString(path)
+	if err != nil {
+		return nil, wrapErr(err)
+	}
+	var appID *wtFwpByteBlob
+	if err := fwpmGetAppIdFromFileName0(pathPtr, unsafe.Pointer(&appID)); err != nil {
+		return nil, wrapErr(err)
+	}
+	return appID, nil
+}

client/internal/dns/dnsfw/syscall_windows.go

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2019-2021 WireGuard LLC. All Rights Reserved.
+ *
+ * Adapted from wireguard-windows tunnel/firewall/syscall_windows.go.
+ */
+
+package dnsfw
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmengineopen0
+//sys	fwpmEngineOpen0(serverName *uint16, authnService wtRpcCAuthN, authIdentity *uintptr, session *wtFwpmSession0, engineHandle unsafe.Pointer) (err error) [failretval!=0] = fwpuclnt.FwpmEngineOpen0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmengineclose0
+//sys	fwpmEngineClose0(engineHandle uintptr) (err error) [failretval!=0] = fwpuclnt.FwpmEngineClose0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmsublayeradd0
+//sys	fwpmSubLayerAdd0(engineHandle uintptr, subLayer *wtFwpmSublayer0, sd uintptr) (err error) [failretval!=0] = fwpuclnt.FwpmSubLayerAdd0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmgetappidfromfilename0
+//sys	fwpmGetAppIdFromFileName0(fileName *uint16, appID unsafe.Pointer) (err error) [failretval!=0] = fwpuclnt.FwpmGetAppIdFromFileName0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmfreememory0
+//sys	fwpmFreeMemory0(p unsafe.Pointer) = fwpuclnt.FwpmFreeMemory0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmfilteradd0
+//sys	fwpmFilterAdd0(engineHandle uintptr, filter *wtFwpmFilter0, sd uintptr, id *uint64) (err error) [failretval!=0] = fwpuclnt.FwpmFilterAdd0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/Fwpmu/nf-fwpmu-fwpmtransactionbegin0
+//sys	fwpmTransactionBegin0(engineHandle uintptr, flags uint32) (err error) [failretval!=0] = fwpuclnt.FwpmTransactionBegin0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmtransactioncommit0
+//sys	fwpmTransactionCommit0(engineHandle uintptr) (err error) [failretval!=0] = fwpuclnt.FwpmTransactionCommit0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmtransactionabort0
+//sys	fwpmTransactionAbort0(engineHandle uintptr) (err error) [failretval!=0] = fwpuclnt.FwpmTransactionAbort0
+
+// https://docs.microsoft.com/en-us/windows/desktop/api/fwpmu/nf-fwpmu-fwpmprovideradd0
+//sys	fwpmProviderAdd0(engineHandle uintptr, provider *wtFwpmProvider0, sd uintptr) (err error) [failretval!=0] = fwpuclnt.FwpmProviderAdd0

client/internal/dns/dnsfw/types_windows.go

@@ -0,0 +1,414 @@
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2019-2021 WireGuard LLC. All Rights Reserved.
+ *
+ * Adapted from wireguard-windows tunnel/firewall/types_windows.go.
+ */
+
+package dnsfw
+
+import "golang.org/x/sys/windows"
+
+const (
+	anysizeArray = 1 // ANYSIZE_ARRAY defined in winnt.h
+
+	wtFwpBitmapArray64_Size = 8
+
+	wtFwpByteArray16_Size = 16
+
+	wtFwpByteArray6_Size = 6
+
+	wtFwpmAction0_Size              = 20
+	wtFwpmAction0_filterType_Offset = 4
+
+	wtFwpV4AddrAndMask_Size        = 8
+	wtFwpV4AddrAndMask_mask_Offset = 4
+
+	wtFwpV6AddrAndMask_Size                = 17
+	wtFwpV6AddrAndMask_prefixLength_Offset = 16
+)
+
+type wtFwpActionFlag uint32
+
+const (
+	cFWP_ACTION_FLAG_TERMINATING     wtFwpActionFlag = 0x00001000
+	cFWP_ACTION_FLAG_NON_TERMINATING wtFwpActionFlag = 0x00002000
+	cFWP_ACTION_FLAG_CALLOUT         wtFwpActionFlag = 0x00004000
+)
+
+// FWP_ACTION_TYPE defined in fwptypes.h
+type wtFwpActionType uint32
+
+const (
+	cFWP_ACTION_BLOCK               wtFwpActionType = wtFwpActionType(0x00000001 | cFWP_ACTION_FLAG_TERMINATING)
+	cFWP_ACTION_PERMIT              wtFwpActionType = wtFwpActionType(0x00000002 | cFWP_ACTION_FLAG_TERMINATING)
+	cFWP_ACTION_CALLOUT_TERMINATING wtFwpActionType = wtFwpActionType(0x00000003 | cFWP_ACTION_FLAG_CALLOUT | cFWP_ACTION_FLAG_TERMINATING)
+	cFWP_ACTION_CALLOUT_INSPECTION  wtFwpActionType = wtFwpActionType(0x00000004 | cFWP_ACTION_FLAG_CALLOUT | cFWP_ACTION_FLAG_NON_TERMINATING)
+	cFWP_ACTION_CALLOUT_UNKNOWN     wtFwpActionType = wtFwpActionType(0x00000005 | cFWP_ACTION_FLAG_CALLOUT)
+	cFWP_ACTION_CONTINUE            wtFwpActionType = wtFwpActionType(0x00000006 | cFWP_ACTION_FLAG_NON_TERMINATING)
+	cFWP_ACTION_NONE                wtFwpActionType = 0x00000007
+	cFWP_ACTION_NONE_NO_MATCH       wtFwpActionType = 0x00000008
+	cFWP_ACTION_BITMAP_INDEX_SET    wtFwpActionType = 0x00000009
+)
+
+// FWP_BYTE_BLOB defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ns-fwptypes-fwp_byte_blob_)
+type wtFwpByteBlob struct {
+	size uint32
+	data *uint8
+}
+
+// FWP_MATCH_TYPE defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ne-fwptypes-fwp_match_type_)
+type wtFwpMatchType uint32
+
+const (
+	cFWP_MATCH_EQUAL                  wtFwpMatchType = 0
+	cFWP_MATCH_GREATER                wtFwpMatchType = cFWP_MATCH_EQUAL + 1
+	cFWP_MATCH_LESS                   wtFwpMatchType = cFWP_MATCH_GREATER + 1
+	cFWP_MATCH_GREATER_OR_EQUAL       wtFwpMatchType = cFWP_MATCH_LESS + 1
+	cFWP_MATCH_LESS_OR_EQUAL          wtFwpMatchType = cFWP_MATCH_GREATER_OR_EQUAL + 1
+	cFWP_MATCH_RANGE                  wtFwpMatchType = cFWP_MATCH_LESS_OR_EQUAL + 1
+	cFWP_MATCH_FLAGS_ALL_SET          wtFwpMatchType = cFWP_MATCH_RANGE + 1
+	cFWP_MATCH_FLAGS_ANY_SET          wtFwpMatchType = cFWP_MATCH_FLAGS_ALL_SET + 1
+	cFWP_MATCH_FLAGS_NONE_SET         wtFwpMatchType = cFWP_MATCH_FLAGS_ANY_SET + 1
+	cFWP_MATCH_EQUAL_CASE_INSENSITIVE wtFwpMatchType = cFWP_MATCH_FLAGS_NONE_SET + 1
+	cFWP_MATCH_NOT_EQUAL              wtFwpMatchType = cFWP_MATCH_EQUAL_CASE_INSENSITIVE + 1
+	cFWP_MATCH_PREFIX                 wtFwpMatchType = cFWP_MATCH_NOT_EQUAL + 1
+	cFWP_MATCH_NOT_PREFIX             wtFwpMatchType = cFWP_MATCH_PREFIX + 1
+	cFWP_MATCH_TYPE_MAX               wtFwpMatchType = cFWP_MATCH_NOT_PREFIX + 1
+)
+
+// FWPM_ACTION0 defined in fwpmtypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwpmtypes/ns-fwpmtypes-fwpm_action0_)
+type wtFwpmAction0 struct {
+	_type      wtFwpActionType
+	filterType windows.GUID // Windows type: GUID
+}
+
+// Defined in fwpmu.h. 4cd62a49-59c3-4969-b7f3-bda5d32890a4
+var cFWPM_CONDITION_IP_LOCAL_INTERFACE = windows.GUID{
+	Data1: 0x4cd62a49,
+	Data2: 0x59c3,
+	Data3: 0x4969,
+	Data4: [8]byte{0xb7, 0xf3, 0xbd, 0xa5, 0xd3, 0x28, 0x90, 0xa4},
+}
+
+// Defined in fwpmu.h. b235ae9a-1d64-49b8-a44c-5ff3d9095045
+var cFWPM_CONDITION_IP_REMOTE_ADDRESS = windows.GUID{
+	Data1: 0xb235ae9a,
+	Data2: 0x1d64,
+	Data3: 0x49b8,
+	Data4: [8]byte{0xa4, 0x4c, 0x5f, 0xf3, 0xd9, 0x09, 0x50, 0x45},
+}
+
+// Defined in fwpmu.h. 3971ef2b-623e-4f9a-8cb1-6e79b806b9a7
+var cFWPM_CONDITION_IP_PROTOCOL = windows.GUID{
+	Data1: 0x3971ef2b,
+	Data2: 0x623e,
+	Data3: 0x4f9a,
+	Data4: [8]byte{0x8c, 0xb1, 0x6e, 0x79, 0xb8, 0x06, 0xb9, 0xa7},
+}
+
+// Defined in fwpmu.h. 0c1ba1af-5765-453f-af22-a8f791ac775b
+var cFWPM_CONDITION_IP_LOCAL_PORT = windows.GUID{
+	Data1: 0x0c1ba1af,
+	Data2: 0x5765,
+	Data3: 0x453f,
+	Data4: [8]byte{0xaf, 0x22, 0xa8, 0xf7, 0x91, 0xac, 0x77, 0x5b},
+}
+
+// Defined in fwpmu.h. c35a604d-d22b-4e1a-91b4-68f674ee674b
+var cFWPM_CONDITION_IP_REMOTE_PORT = windows.GUID{
+	Data1: 0xc35a604d,
+	Data2: 0xd22b,
+	Data3: 0x4e1a,
+	Data4: [8]byte{0x91, 0xb4, 0x68, 0xf6, 0x74, 0xee, 0x67, 0x4b},
+}
+
+// Defined in fwpmu.h. d78e1e87-8644-4ea5-9437-d809ecefc971
+var cFWPM_CONDITION_ALE_APP_ID = windows.GUID{
+	Data1: 0xd78e1e87,
+	Data2: 0x8644,
+	Data3: 0x4ea5,
+	Data4: [8]byte{0x94, 0x37, 0xd8, 0x09, 0xec, 0xef, 0xc9, 0x71},
+}
+
+// af043a0a-b34d-4f86-979c-c90371af6e66
+var cFWPM_CONDITION_ALE_USER_ID = windows.GUID{
+	Data1: 0xaf043a0a,
+	Data2: 0xb34d,
+	Data3: 0x4f86,
+	Data4: [8]byte{0x97, 0x9c, 0xc9, 0x03, 0x71, 0xaf, 0x6e, 0x66},
+}
+
+// d9ee00de-c1ef-4617-bfe3-ffd8f5a08957
+var cFWPM_CONDITION_IP_LOCAL_ADDRESS = windows.GUID{
+	Data1: 0xd9ee00de,
+	Data2: 0xc1ef,
+	Data3: 0x4617,
+	Data4: [8]byte{0xbf, 0xe3, 0xff, 0xd8, 0xf5, 0xa0, 0x89, 0x57},
+}
+
+var (
+	cFWPM_CONDITION_ICMP_TYPE = cFWPM_CONDITION_IP_LOCAL_PORT
+	cFWPM_CONDITION_ICMP_CODE = cFWPM_CONDITION_IP_REMOTE_PORT
+)
+
+// 7bc43cbf-37ba-45f1-b74a-82ff518eeb10
+var cFWPM_CONDITION_L2_FLAGS = windows.GUID{
+	Data1: 0x7bc43cbf,
+	Data2: 0x37ba,
+	Data3: 0x45f1,
+	Data4: [8]byte{0xb7, 0x4a, 0x82, 0xff, 0x51, 0x8e, 0xeb, 0x10},
+}
+
+type wtFwpmL2Flags uint32
+
+const cFWP_CONDITION_L2_IS_VM2VM wtFwpmL2Flags = 0x00000010
+
+var cFWPM_CONDITION_FLAGS = windows.GUID{
+	Data1: 0x632ce23b,
+	Data2: 0x5167,
+	Data3: 0x435c,
+	Data4: [8]byte{0x86, 0xd7, 0xe9, 0x03, 0x68, 0x4a, 0xa8, 0x0c},
+}
+
+type wtFwpmFlags uint32
+
+const cFWP_CONDITION_FLAG_IS_LOOPBACK wtFwpmFlags = 0x00000001
+
+// Defined in fwpmtypes.h
+type wtFwpmFilterFlags uint32
+
+const (
+	cFWPM_FILTER_FLAG_NONE                                wtFwpmFilterFlags = 0x00000000
+	cFWPM_FILTER_FLAG_PERSISTENT                          wtFwpmFilterFlags = 0x00000001
+	cFWPM_FILTER_FLAG_BOOTTIME                            wtFwpmFilterFlags = 0x00000002
+	cFWPM_FILTER_FLAG_HAS_PROVIDER_CONTEXT                wtFwpmFilterFlags = 0x00000004
+	cFWPM_FILTER_FLAG_CLEAR_ACTION_RIGHT                  wtFwpmFilterFlags = 0x00000008
+	cFWPM_FILTER_FLAG_PERMIT_IF_CALLOUT_UNREGISTERED      wtFwpmFilterFlags = 0x00000010
+	cFWPM_FILTER_FLAG_DISABLED                            wtFwpmFilterFlags = 0x00000020
+	cFWPM_FILTER_FLAG_INDEXED                             wtFwpmFilterFlags = 0x00000040
+	cFWPM_FILTER_FLAG_HAS_SECURITY_REALM_PROVIDER_CONTEXT wtFwpmFilterFlags = 0x00000080
+	cFWPM_FILTER_FLAG_SYSTEMOS_ONLY                       wtFwpmFilterFlags = 0x00000100
+	cFWPM_FILTER_FLAG_GAMEOS_ONLY                         wtFwpmFilterFlags = 0x00000200
+	cFWPM_FILTER_FLAG_SILENT_MODE                         wtFwpmFilterFlags = 0x00000400
+	cFWPM_FILTER_FLAG_IPSEC_NO_ACQUIRE_INITIATE           wtFwpmFilterFlags = 0x00000800
+)
+
+// FWPM_LAYER_ALE_AUTH_CONNECT_V4 (c38d57d1-05a7-4c33-904f-7fbceee60e82) defined in fwpmu.h
+var cFWPM_LAYER_ALE_AUTH_CONNECT_V4 = windows.GUID{
+	Data1: 0xc38d57d1,
+	Data2: 0x05a7,
+	Data3: 0x4c33,
+	Data4: [8]byte{0x90, 0x4f, 0x7f, 0xbc, 0xee, 0xe6, 0x0e, 0x82},
+}
+
+// e1cd9fe7-f4b5-4273-96c0-592e487b8650
+var cFWPM_LAYER_ALE_AUTH_RECV_ACCEPT_V4 = windows.GUID{
+	Data1: 0xe1cd9fe7,
+	Data2: 0xf4b5,
+	Data3: 0x4273,
+	Data4: [8]byte{0x96, 0xc0, 0x59, 0x2e, 0x48, 0x7b, 0x86, 0x50},
+}
+
+// FWPM_LAYER_ALE_AUTH_CONNECT_V6 (4a72393b-319f-44bc-84c3-ba54dcb3b6b4) defined in fwpmu.h
+var cFWPM_LAYER_ALE_AUTH_CONNECT_V6 = windows.GUID{
+	Data1: 0x4a72393b,
+	Data2: 0x319f,
+	Data3: 0x44bc,
+	Data4: [8]byte{0x84, 0xc3, 0xba, 0x54, 0xdc, 0xb3, 0xb6, 0xb4},
+}
+
+// a3b42c97-9f04-4672-b87e-cee9c483257f
+var cFWPM_LAYER_ALE_AUTH_RECV_ACCEPT_V6 = windows.GUID{
+	Data1: 0xa3b42c97,
+	Data2: 0x9f04,
+	Data3: 0x4672,
+	Data4: [8]byte{0xb8, 0x7e, 0xce, 0xe9, 0xc4, 0x83, 0x25, 0x7f},
+}
+
+// 94c44912-9d6f-4ebf-b995-05ab8a088d1b
+var cFWPM_LAYER_OUTBOUND_MAC_FRAME_NATIVE = windows.GUID{
+	Data1: 0x94c44912,
+	Data2: 0x9d6f,
+	Data3: 0x4ebf,
+	Data4: [8]byte{0xb9, 0x95, 0x05, 0xab, 0x8a, 0x08, 0x8d, 0x1b},
+}
+
+// d4220bd3-62ce-4f08-ae88-b56e8526df50
+var cFWPM_LAYER_INBOUND_MAC_FRAME_NATIVE = windows.GUID{
+	Data1: 0xd4220bd3,
+	Data2: 0x62ce,
+	Data3: 0x4f08,
+	Data4: [8]byte{0xae, 0x88, 0xb5, 0x6e, 0x85, 0x26, 0xdf, 0x50},
+}
+
+// FWP_BITMAP_ARRAY64 defined in fwtypes.h
+type wtFwpBitmapArray64 struct {
+	bitmapArray64 [8]uint8 // Windows type: [8]UINT8
+}
+
+// FWP_BYTE_ARRAY6 defined in fwtypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ns-fwptypes-fwp_byte_array6_)
+type wtFwpByteArray6 struct {
+	byteArray6 [6]uint8 // Windows type: [6]UINT8
+}
+
+// FWP_BYTE_ARRAY16 defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ns-fwptypes-fwp_byte_array16_)
+type wtFwpByteArray16 struct {
+	byteArray16 [16]uint8 // Windows type [16]UINT8
+}
+
+// FWP_CONDITION_VALUE0 defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ns-fwptypes-fwp_condition_value0).
+type wtFwpConditionValue0 wtFwpValue0
+
+// FWP_DATA_TYPE defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ne-fwptypes-fwp_data_type_)
+type wtFwpDataType uint
+
+const (
+	cFWP_EMPTY                         wtFwpDataType = 0
+	cFWP_UINT8                         wtFwpDataType = cFWP_EMPTY + 1
+	cFWP_UINT16                        wtFwpDataType = cFWP_UINT8 + 1
+	cFWP_UINT32                        wtFwpDataType = cFWP_UINT16 + 1
+	cFWP_UINT64                        wtFwpDataType = cFWP_UINT32 + 1
+	cFWP_INT8                          wtFwpDataType = cFWP_UINT64 + 1
+	cFWP_INT16                         wtFwpDataType = cFWP_INT8 + 1
+	cFWP_INT32                         wtFwpDataType = cFWP_INT16 + 1
+	cFWP_INT64                         wtFwpDataType = cFWP_INT32 + 1
+	cFWP_FLOAT                         wtFwpDataType = cFWP_INT64 + 1
+	cFWP_DOUBLE                        wtFwpDataType = cFWP_FLOAT + 1
+	cFWP_BYTE_ARRAY16_TYPE             wtFwpDataType = cFWP_DOUBLE + 1
+	cFWP_BYTE_BLOB_TYPE                wtFwpDataType = cFWP_BYTE_ARRAY16_TYPE + 1
+	cFWP_SID                           wtFwpDataType = cFWP_BYTE_BLOB_TYPE + 1
+	cFWP_SECURITY_DESCRIPTOR_TYPE      wtFwpDataType = cFWP_SID + 1
+	cFWP_TOKEN_INFORMATION_TYPE        wtFwpDataType = cFWP_SECURITY_DESCRIPTOR_TYPE + 1
+	cFWP_TOKEN_ACCESS_INFORMATION_TYPE wtFwpDataType = cFWP_TOKEN_INFORMATION_TYPE + 1
+	cFWP_UNICODE_STRING_TYPE           wtFwpDataType = cFWP_TOKEN_ACCESS_INFORMATION_TYPE + 1
+	cFWP_BYTE_ARRAY6_TYPE              wtFwpDataType = cFWP_UNICODE_STRING_TYPE + 1
+	cFWP_BITMAP_INDEX_TYPE             wtFwpDataType = cFWP_BYTE_ARRAY6_TYPE + 1
+	cFWP_BITMAP_ARRAY64_TYPE           wtFwpDataType = cFWP_BITMAP_INDEX_TYPE + 1
+	cFWP_SINGLE_DATA_TYPE_MAX          wtFwpDataType = 0xff
+	cFWP_V4_ADDR_MASK                  wtFwpDataType = cFWP_SINGLE_DATA_TYPE_MAX + 1
+	cFWP_V6_ADDR_MASK                  wtFwpDataType = cFWP_V4_ADDR_MASK + 1
+	cFWP_RANGE_TYPE                    wtFwpDataType = cFWP_V6_ADDR_MASK + 1
+	cFWP_DATA_TYPE_MAX                 wtFwpDataType = cFWP_RANGE_TYPE + 1
+)
+
+// FWP_V4_ADDR_AND_MASK defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ns-fwptypes-fwp_v4_addr_and_mask).
+type wtFwpV4AddrAndMask struct {
+	addr uint32
+	mask uint32
+}
+
+// FWP_V6_ADDR_AND_MASK defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ns-fwptypes-fwp_v6_addr_and_mask).
+type wtFwpV6AddrAndMask struct {
+	addr         [16]uint8
+	prefixLength uint8
+}
+
+// FWP_VALUE0 defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ns-fwptypes-fwp_value0_)
+type wtFwpValue0 struct {
+	_type wtFwpDataType
+	value uintptr
+}
+
+// FWPM_DISPLAY_DATA0 defined in fwptypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwptypes/ns-fwptypes-fwpm_display_data0).
+type wtFwpmDisplayData0 struct {
+	name        *uint16 // Windows type: *wchar_t
+	description *uint16 // Windows type: *wchar_t
+}
+
+// FWPM_FILTER_CONDITION0 defined in fwpmtypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwpmtypes/ns-fwpmtypes-fwpm_filter_condition0).
+type wtFwpmFilterCondition0 struct {
+	fieldKey       windows.GUID // Windows type: GUID
+	matchType      wtFwpMatchType
+	conditionValue wtFwpConditionValue0
+}
+
+// FWPM_PROVIDER0 defined in fwpmtypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwpmtypes/ns-fwpmtypes-fwpm_provider0_)
+type wtFwpProvider0 struct {
+	providerKey  windows.GUID // Windows type: GUID
+	displayData  wtFwpmDisplayData0
+	flags        uint32
+	providerData wtFwpByteBlob
+	serviceName  *uint16 // Windows type: *wchar_t
+}
+
+type wtFwpmSessionFlagsValue uint32
+
+const (
+	cFWPM_SESSION_FLAG_DYNAMIC wtFwpmSessionFlagsValue = 0x00000001 // FWPM_SESSION_FLAG_DYNAMIC defined in fwpmtypes.h
+)
+
+// FWPM_SESSION0 defined in fwpmtypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwpmtypes/ns-fwpmtypes-fwpm_session0).
+type wtFwpmSession0 struct {
+	sessionKey           windows.GUID // Windows type: GUID
+	displayData          wtFwpmDisplayData0
+	flags                wtFwpmSessionFlagsValue // Windows type UINT32
+	txnWaitTimeoutInMSec uint32
+	processId            uint32 // Windows type: DWORD
+	sid                  *windows.SID
+	username             *uint16 // Windows type: *wchar_t
+	kernelMode           uint8   // Windows type: BOOL
+}
+
+type wtFwpmSublayerFlags uint32
+
+const (
+	cFWPM_SUBLAYER_FLAG_PERSISTENT wtFwpmSublayerFlags = 0x00000001 // FWPM_SUBLAYER_FLAG_PERSISTENT defined in fwpmtypes.h
+)
+
+// FWPM_SUBLAYER0 defined in fwpmtypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwpmtypes/ns-fwpmtypes-fwpm_sublayer0_)
+type wtFwpmSublayer0 struct {
+	subLayerKey  windows.GUID // Windows type: GUID
+	displayData  wtFwpmDisplayData0
+	flags        wtFwpmSublayerFlags
+	providerKey  *windows.GUID // Windows type: *GUID
+	providerData wtFwpByteBlob
+	weight       uint16
+}
+
+// Defined in rpcdce.h
+type wtRpcCAuthN uint32
+
+const (
+	cRPC_C_AUTHN_NONE    wtRpcCAuthN = 0
+	cRPC_C_AUTHN_WINNT   wtRpcCAuthN = 10
+	cRPC_C_AUTHN_DEFAULT wtRpcCAuthN = 0xFFFFFFFF
+)
+
+// FWPM_PROVIDER0 defined in fwpmtypes.h
+// (https://docs.microsoft.com/sv-se/windows/desktop/api/fwpmtypes/ns-fwpmtypes-fwpm_provider0).
+type wtFwpmProvider0 struct {
+	providerKey  windows.GUID
+	displayData  wtFwpmDisplayData0
+	flags        uint32
+	providerData wtFwpByteBlob
+	serviceName  *uint16
+}
+
+type wtIPProto uint32
+
+const (
+	cIPPROTO_ICMP   wtIPProto = 1
+	cIPPROTO_ICMPV6 wtIPProto = 58
+	cIPPROTO_TCP    wtIPProto = 6
+	cIPPROTO_UDP    wtIPProto = 17
+)
+
+const (
+	cFWP_ACTRL_MATCH_FILTER = 1
+)

client/internal/dns/dnsfw/types_windows_32.go

@@ -0,0 +1,92 @@
+//go:build windows && (386 || arm)
+
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2019-2021 WireGuard LLC. All Rights Reserved.
+ *
+ * Adapted from wireguard-windows tunnel/firewall/types_windows_32.go.
+ */
+
+package dnsfw
+
+import "golang.org/x/sys/windows"
+
+const (
+	wtFwpByteBlob_Size        = 8
+	wtFwpByteBlob_data_Offset = 4
+
+	wtFwpConditionValue0_Size         = 8
+	wtFwpConditionValue0_uint8_Offset = 4
+
+	wtFwpmDisplayData0_Size               = 8
+	wtFwpmDisplayData0_description_Offset = 4
+
+	wtFwpmFilter0_Size                       = 152
+	wtFwpmFilter0_displayData_Offset         = 16
+	wtFwpmFilter0_flags_Offset               = 24
+	wtFwpmFilter0_providerKey_Offset         = 28
+	wtFwpmFilter0_providerData_Offset        = 32
+	wtFwpmFilter0_layerKey_Offset            = 40
+	wtFwpmFilter0_subLayerKey_Offset         = 56
+	wtFwpmFilter0_weight_Offset              = 72
+	wtFwpmFilter0_numFilterConditions_Offset = 80
+	wtFwpmFilter0_filterCondition_Offset     = 84
+	wtFwpmFilter0_action_Offset              = 88
+	wtFwpmFilter0_providerContextKey_Offset  = 112
+	wtFwpmFilter0_reserved_Offset            = 128
+	wtFwpmFilter0_filterID_Offset            = 136
+	wtFwpmFilter0_effectiveWeight_Offset     = 144
+
+	wtFwpmFilterCondition0_Size                  = 28
+	wtFwpmFilterCondition0_matchType_Offset      = 16
+	wtFwpmFilterCondition0_conditionValue_Offset = 20
+
+	wtFwpmSession0_Size                        = 48
+	wtFwpmSession0_displayData_Offset          = 16
+	wtFwpmSession0_flags_Offset                = 24
+	wtFwpmSession0_txnWaitTimeoutInMSec_Offset = 28
+	wtFwpmSession0_processId_Offset            = 32
+	wtFwpmSession0_sid_Offset                  = 36
+	wtFwpmSession0_username_Offset             = 40
+	wtFwpmSession0_kernelMode_Offset           = 44
+
+	wtFwpmSublayer0_Size                = 44
+	wtFwpmSublayer0_displayData_Offset  = 16
+	wtFwpmSublayer0_flags_Offset        = 24
+	wtFwpmSublayer0_providerKey_Offset  = 28
+	wtFwpmSublayer0_providerData_Offset = 32
+	wtFwpmSublayer0_weight_Offset       = 40
+
+	wtFwpProvider0_Size                = 40
+	wtFwpProvider0_displayData_Offset  = 16
+	wtFwpProvider0_flags_Offset        = 24
+	wtFwpProvider0_providerData_Offset = 28
+	wtFwpProvider0_serviceName_Offset  = 36
+
+	wtFwpTokenInformation_Size = 16
+
+	wtFwpValue0_Size         = 8
+	wtFwpValue0_value_Offset = 4
+)
+
+// FWPM_FILTER0 defined in fwpmtypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwpmtypes/ns-fwpmtypes-fwpm_filter0).
+type wtFwpmFilter0 struct {
+	filterKey           windows.GUID // Windows type: GUID
+	displayData         wtFwpmDisplayData0
+	flags               wtFwpmFilterFlags
+	providerKey         *windows.GUID // Windows type: *GUID
+	providerData        wtFwpByteBlob
+	layerKey            windows.GUID // Windows type: GUID
+	subLayerKey         windows.GUID // Windows type: GUID
+	weight              wtFwpValue0
+	numFilterConditions uint32
+	filterCondition     *wtFwpmFilterCondition0
+	action              wtFwpmAction0
+	offset1             [4]byte       // Layout correction field
+	providerContextKey  windows.GUID  // Windows type: GUID
+	reserved            *windows.GUID // Windows type: *GUID
+	offset2             [4]byte       // Layout correction field
+	filterID            uint64
+	effectiveWeight     wtFwpValue0
+}

client/internal/dns/dnsfw/types_windows_64.go

@@ -0,0 +1,89 @@
+//go:build windows && (amd64 || arm64)
+
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2019-2021 WireGuard LLC. All Rights Reserved.
+ *
+ * Adapted from wireguard-windows tunnel/firewall/types_windows_64.go.
+ */
+
+package dnsfw
+
+import "golang.org/x/sys/windows"
+
+const (
+	wtFwpByteBlob_Size        = 16
+	wtFwpByteBlob_data_Offset = 8
+
+	wtFwpConditionValue0_Size         = 16
+	wtFwpConditionValue0_uint8_Offset = 8
+
+	wtFwpmDisplayData0_Size               = 16
+	wtFwpmDisplayData0_description_Offset = 8
+
+	wtFwpmFilter0_Size                       = 200
+	wtFwpmFilter0_displayData_Offset         = 16
+	wtFwpmFilter0_flags_Offset               = 32
+	wtFwpmFilter0_providerKey_Offset         = 40
+	wtFwpmFilter0_providerData_Offset        = 48
+	wtFwpmFilter0_layerKey_Offset            = 64
+	wtFwpmFilter0_subLayerKey_Offset         = 80
+	wtFwpmFilter0_weight_Offset              = 96
+	wtFwpmFilter0_numFilterConditions_Offset = 112
+	wtFwpmFilter0_filterCondition_Offset     = 120
+	wtFwpmFilter0_action_Offset              = 128
+	wtFwpmFilter0_providerContextKey_Offset  = 152
+	wtFwpmFilter0_reserved_Offset            = 168
+	wtFwpmFilter0_filterID_Offset            = 176
+	wtFwpmFilter0_effectiveWeight_Offset     = 184
+
+	wtFwpmFilterCondition0_Size                  = 40
+	wtFwpmFilterCondition0_matchType_Offset      = 16
+	wtFwpmFilterCondition0_conditionValue_Offset = 24
+
+	wtFwpmSession0_Size                        = 72
+	wtFwpmSession0_displayData_Offset          = 16
+	wtFwpmSession0_flags_Offset                = 32
+	wtFwpmSession0_txnWaitTimeoutInMSec_Offset = 36
+	wtFwpmSession0_processId_Offset            = 40
+	wtFwpmSession0_sid_Offset                  = 48
+	wtFwpmSession0_username_Offset             = 56
+	wtFwpmSession0_kernelMode_Offset           = 64
+
+	wtFwpmSublayer0_Size                = 72
+	wtFwpmSublayer0_displayData_Offset  = 16
+	wtFwpmSublayer0_flags_Offset        = 32
+	wtFwpmSublayer0_providerKey_Offset  = 40
+	wtFwpmSublayer0_providerData_Offset = 48
+	wtFwpmSublayer0_weight_Offset       = 64
+
+	wtFwpProvider0_Size                = 64
+	wtFwpProvider0_displayData_Offset  = 16
+	wtFwpProvider0_flags_Offset        = 32
+	wtFwpProvider0_providerData_Offset = 40
+	wtFwpProvider0_serviceName_Offset  = 56
+
+	wtFwpValue0_Size         = 16
+	wtFwpValue0_value_Offset = 8
+)
+
+// FWPM_FILTER0 defined in fwpmtypes.h
+// (https://docs.microsoft.com/en-us/windows/desktop/api/fwpmtypes/ns-fwpmtypes-fwpm_filter0).
+type wtFwpmFilter0 struct {
+	filterKey           windows.GUID // Windows type: GUID
+	displayData         wtFwpmDisplayData0
+	flags               wtFwpmFilterFlags // Windows type: UINT32
+	providerKey         *windows.GUID     // Windows type: *GUID
+	providerData        wtFwpByteBlob
+	layerKey            windows.GUID // Windows type: GUID
+	subLayerKey         windows.GUID // Windows type: GUID
+	weight              wtFwpValue0
+	numFilterConditions uint32
+	filterCondition     *wtFwpmFilterCondition0
+	action              wtFwpmAction0
+	offset1             [4]byte       // Layout correction field
+	providerContextKey  windows.GUID  // Windows type: GUID
+	reserved            *windows.GUID // Windows type: *GUID
+	filterID            uint64
+	effectiveWeight     wtFwpValue0
+}

client/internal/dns/dnsfw/zsyscall_windows.go

@@ -0,0 +1,130 @@
+// Code generated by 'go generate'; DO NOT EDIT.
+
+package dnsfw
+
+import (
+	"syscall"
+	"unsafe"
+
+	"golang.org/x/sys/windows"
+)
+
+var _ unsafe.Pointer
+
+// Do the interface allocations only once for common
+// Errno values.
+const (
+	errnoERROR_IO_PENDING = 997
+)
+
+var (
+	errERROR_IO_PENDING error = syscall.Errno(errnoERROR_IO_PENDING)
+	errERROR_EINVAL     error = syscall.EINVAL
+)
+
+// errnoErr returns common boxed Errno values, to prevent
+// allocations at runtime.
+func errnoErr(e syscall.Errno) error {
+	switch e {
+	case 0:
+		return errERROR_EINVAL
+	case errnoERROR_IO_PENDING:
+		return errERROR_IO_PENDING
+	}
+	// TODO: add more here, after collecting data on the common
+	// error values see on Windows. (perhaps when running
+	// all.bat?)
+	return e
+}
+
+var (
+	modfwpuclnt = windows.NewLazySystemDLL("fwpuclnt.dll")
+
+	procFwpmEngineClose0          = modfwpuclnt.NewProc("FwpmEngineClose0")
+	procFwpmEngineOpen0           = modfwpuclnt.NewProc("FwpmEngineOpen0")
+	procFwpmFilterAdd0            = modfwpuclnt.NewProc("FwpmFilterAdd0")
+	procFwpmFreeMemory0           = modfwpuclnt.NewProc("FwpmFreeMemory0")
+	procFwpmGetAppIdFromFileName0 = modfwpuclnt.NewProc("FwpmGetAppIdFromFileName0")
+	procFwpmProviderAdd0          = modfwpuclnt.NewProc("FwpmProviderAdd0")
+	procFwpmSubLayerAdd0          = modfwpuclnt.NewProc("FwpmSubLayerAdd0")
+	procFwpmTransactionAbort0     = modfwpuclnt.NewProc("FwpmTransactionAbort0")
+	procFwpmTransactionBegin0     = modfwpuclnt.NewProc("FwpmTransactionBegin0")
+	procFwpmTransactionCommit0    = modfwpuclnt.NewProc("FwpmTransactionCommit0")
+)
+
+func fwpmEngineClose0(engineHandle uintptr) (err error) {
+	r1, _, e1 := syscall.Syscall(procFwpmEngineClose0.Addr(), 1, uintptr(engineHandle), 0, 0)
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}
+
+func fwpmEngineOpen0(serverName *uint16, authnService wtRpcCAuthN, authIdentity *uintptr, session *wtFwpmSession0, engineHandle unsafe.Pointer) (err error) {
+	r1, _, e1 := syscall.Syscall6(procFwpmEngineOpen0.Addr(), 5, uintptr(unsafe.Pointer(serverName)), uintptr(authnService), uintptr(unsafe.Pointer(authIdentity)), uintptr(unsafe.Pointer(session)), uintptr(engineHandle), 0)
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}
+
+func fwpmFilterAdd0(engineHandle uintptr, filter *wtFwpmFilter0, sd uintptr, id *uint64) (err error) {
+	r1, _, e1 := syscall.Syscall6(procFwpmFilterAdd0.Addr(), 4, uintptr(engineHandle), uintptr(unsafe.Pointer(filter)), uintptr(sd), uintptr(unsafe.Pointer(id)), 0, 0)
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}
+
+func fwpmFreeMemory0(p unsafe.Pointer) {
+	syscall.Syscall(procFwpmFreeMemory0.Addr(), 1, uintptr(p), 0, 0)
+	return
+}
+
+func fwpmGetAppIdFromFileName0(fileName *uint16, appID unsafe.Pointer) (err error) {
+	r1, _, e1 := syscall.Syscall(procFwpmGetAppIdFromFileName0.Addr(), 2, uintptr(unsafe.Pointer(fileName)), uintptr(appID), 0)
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}
+
+func fwpmProviderAdd0(engineHandle uintptr, provider *wtFwpmProvider0, sd uintptr) (err error) {
+	r1, _, e1 := syscall.Syscall(procFwpmProviderAdd0.Addr(), 3, uintptr(engineHandle), uintptr(unsafe.Pointer(provider)), uintptr(sd))
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}
+
+func fwpmSubLayerAdd0(engineHandle uintptr, subLayer *wtFwpmSublayer0, sd uintptr) (err error) {
+	r1, _, e1 := syscall.Syscall(procFwpmSubLayerAdd0.Addr(), 3, uintptr(engineHandle), uintptr(unsafe.Pointer(subLayer)), uintptr(sd))
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}
+
+func fwpmTransactionAbort0(engineHandle uintptr) (err error) {
+	r1, _, e1 := syscall.Syscall(procFwpmTransactionAbort0.Addr(), 1, uintptr(engineHandle), 0, 0)
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}
+
+func fwpmTransactionBegin0(engineHandle uintptr, flags uint32) (err error) {
+	r1, _, e1 := syscall.Syscall(procFwpmTransactionBegin0.Addr(), 2, uintptr(engineHandle), uintptr(flags), 0)
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}
+
+func fwpmTransactionCommit0(engineHandle uintptr) (err error) {
+	r1, _, e1 := syscall.Syscall(procFwpmTransactionCommit0.Addr(), 1, uintptr(engineHandle), 0, 0)
+	if r1 != 0 {
+		err = errnoErr(e1)
+	}
+	return
+}

client/internal/dns/host.go

@@ -16,6 +16,10 @@ type hostManager interface {
 	restoreHostDNS() error
 	supportCustomPort() bool
 	string() string
+	// getOriginalNameservers returns the OS-side resolvers used as PriorityFallback
+	// upstreams: pre-takeover snapshots on desktop, the OS-pushed list on Android,
+	// hardcoded Quad9 on iOS, nil for noop / mock.
+	getOriginalNameservers() []netip.Addr
 }
 
 type SystemDNSSettings struct {
@@ -131,3 +135,11 @@ func (n noopHostConfigurator) supportCustomPort() bool {
 func (n noopHostConfigurator) string() string {
 	return "noop"
 }
+
+func (n noopHostConfigurator) getOriginalNameservers() []netip.Addr {
+	return nil
+}
+
+func (m *mockHostConfigurator) getOriginalNameservers() []netip.Addr {
+	return nil
+}

client/internal/dns/host_android.go

@@ -1,14 +1,20 @@
 package dns
 
 import (
+	"net/netip"
+
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 )
 
+// androidHostManager is a noop on the OS side (Android's VPN service handles
+// DNS for us) but tracks the OS-reported resolver list pushed via
+// OnUpdatedHostDNSServer so it can serve as the fallback nameserver source.
 type androidHostManager struct {
+	holder *hostsDNSHolder
 }
 
-func newHostManager() (*androidHostManager, error) {
-	return &androidHostManager{}, nil
+func newHostManager(holder *hostsDNSHolder) (*androidHostManager, error) {
+	return &androidHostManager{holder: holder}, nil
 }
 
 func (a androidHostManager) applyDNSConfig(HostDNSConfig, *statemanager.Manager) error {
@@ -26,3 +32,12 @@ func (a androidHostManager) supportCustomPort() bool {
 func (a androidHostManager) string() string {
 	return "none"
 }
+
+func (a androidHostManager) getOriginalNameservers() []netip.Addr {
+	hosts := a.holder.get()
+	out := make([]netip.Addr, 0, len(hosts))
+	for ap := range hosts {
+		out = append(out, ap.Addr())
+	}
+	return out
+}

client/internal/dns/host_ios.go

@@ -3,6 +3,7 @@ package dns
 import (
 	"encoding/json"
 	"fmt"
+	"net/netip"
 
 	log "github.com/sirupsen/logrus"
 
@@ -20,6 +21,14 @@ func newHostManager(dnsManager IosDnsManager) (*iosHostManager, error) {
 	}, nil
 }
 
+func (a iosHostManager) getOriginalNameservers() []netip.Addr {
+	// Quad9 v4+v6: 9.9.9.9, 2620:fe::fe.
+	return []netip.Addr{
+		netip.AddrFrom4([4]byte{9, 9, 9, 9}),
+		netip.AddrFrom16([16]byte{0x26, 0x20, 0x00, 0xfe, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xfe}),
+	}
+}
+
 func (a iosHostManager) applyDNSConfig(config HostDNSConfig, _ *statemanager.Manager) error {
 	jsonData, err := json.Marshal(config)
 	if err != nil {

client/internal/dns/host_windows.go

@@ -7,6 +7,7 @@ import (
 	"io"
 	"net/netip"
 	"os/exec"
+	"slices"
 	"strings"
 	"syscall"
 	"time"
@@ -16,6 +17,7 @@ import (
 	"golang.org/x/sys/windows/registry"
 
 	nberrors "github.com/netbirdio/netbird/client/errors"
+	"github.com/netbirdio/netbird/client/internal/dns/dnsfw"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/internal/winregistry"
 )
@@ -44,9 +46,11 @@ const (
 
 	nrptMaxDomainsPerRule = 50
 
-	interfaceConfigPath          = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`
-	interfaceConfigNameServerKey = "NameServer"
-	interfaceConfigSearchListKey = "SearchList"
+	interfaceConfigPath           = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`
+	interfaceConfigPathV6         = `SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces`
+	interfaceConfigNameServerKey  = "NameServer"
+	interfaceConfigDhcpNameSrvKey = "DhcpNameServer"
+	interfaceConfigSearchListKey  = "SearchList"
 
 	// Network interface DNS registration settings
 	disableDynamicUpdateKey           = "DisableDynamicUpdate"
@@ -67,10 +71,12 @@ const (
 )
 
 type registryConfigurator struct {
-	guid           string
-	routingAll     bool
-	gpo            bool
-	nrptEntryCount int
+	guid            string
+	routingAll      bool
+	gpo             bool
+	nrptEntryCount  int
+	dnsFirewall     dnsfw.Manager
+	origNameservers []netip.Addr
 }
 
 func newHostManager(wgInterface WGIface) (*registryConfigurator, error) {
@@ -90,10 +96,22 @@ func newHostManager(wgInterface WGIface) (*registryConfigurator, error) {
 	}
 
 	configurator := &registryConfigurator{
-		guid: guid,
-		gpo:  useGPO,
+		guid:        guid,
+		gpo:         useGPO,
+		dnsFirewall: dnsfw.New(),
 	}
 
+	origNameservers, err := configurator.captureOriginalNameservers()
+	switch {
+	case err != nil:
+		log.Warnf("capture original nameservers from non-WG adapters: %v", err)
+	case len(origNameservers) == 0:
+		log.Warnf("no original nameservers captured from non-WG adapters; DNS fallback will be empty")
+	default:
+		log.Debugf("captured %d original nameservers from non-WG adapters: %v", len(origNameservers), origNameservers)
+	}
+	configurator.origNameservers = origNameservers
+
 	if err := configurator.configureInterface(); err != nil {
 		log.Errorf("failed to configure interface settings: %v", err)
 	}
@@ -101,6 +119,98 @@ func newHostManager(wgInterface WGIface) (*registryConfigurator, error) {
 	return configurator, nil
 }
 
+// captureOriginalNameservers reads DNS addresses from every Tcpip(6) interface
+// registry key except the WG adapter. v4 and v6 servers live in separate
+// hives (Tcpip vs Tcpip6) keyed by the same interface GUID.
+func (r *registryConfigurator) captureOriginalNameservers() ([]netip.Addr, error) {
+	seen := make(map[netip.Addr]struct{})
+	var out []netip.Addr
+	var merr *multierror.Error
+	for _, root := range []string{interfaceConfigPath, interfaceConfigPathV6} {
+		addrs, err := r.captureFromTcpipRoot(root)
+		if err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("%s: %w", root, err))
+			continue
+		}
+		for _, addr := range addrs {
+			if _, dup := seen[addr]; dup {
+				continue
+			}
+			seen[addr] = struct{}{}
+			out = append(out, addr)
+		}
+	}
+	return out, nberrors.FormatErrorOrNil(merr)
+}
+
+func (r *registryConfigurator) captureFromTcpipRoot(rootPath string) ([]netip.Addr, error) {
+	root, err := registry.OpenKey(registry.LOCAL_MACHINE, rootPath, registry.READ)
+	if err != nil {
+		return nil, fmt.Errorf("open key: %w", err)
+	}
+	defer closer(root)
+
+	guids, err := root.ReadSubKeyNames(-1)
+	if err != nil {
+		return nil, fmt.Errorf("read subkeys: %w", err)
+	}
+
+	var out []netip.Addr
+	for _, guid := range guids {
+		if strings.EqualFold(guid, r.guid) {
+			continue
+		}
+		out = append(out, readInterfaceNameservers(rootPath, guid)...)
+	}
+	return out, nil
+}
+
+func readInterfaceNameservers(rootPath, guid string) []netip.Addr {
+	keyPath := rootPath + "\\" + guid
+	k, err := registry.OpenKey(registry.LOCAL_MACHINE, keyPath, registry.QUERY_VALUE)
+	if err != nil {
+		return nil
+	}
+	defer closer(k)
+
+	// Static NameServer wins over DhcpNameServer for actual resolution.
+	for _, name := range []string{interfaceConfigNameServerKey, interfaceConfigDhcpNameSrvKey} {
+		raw, _, err := k.GetStringValue(name)
+		if err != nil || raw == "" {
+			continue
+		}
+		if out := parseRegistryNameservers(raw); len(out) > 0 {
+			return out
+		}
+	}
+	return nil
+}
+
+func parseRegistryNameservers(raw string) []netip.Addr {
+	var out []netip.Addr
+	for _, field := range strings.FieldsFunc(raw, func(r rune) bool { return r == ',' || r == ' ' || r == '\t' }) {
+		addr, err := netip.ParseAddr(strings.TrimSpace(field))
+		if err != nil {
+			continue
+		}
+		addr = addr.Unmap()
+		if !addr.IsValid() || addr.IsUnspecified() {
+			continue
+		}
+		// Drop unzoned link-local: not routable without a scope id. If
+		// the user wrote "fe80::1%eth0" ParseAddr preserves the zone.
+		if addr.IsLinkLocalUnicast() && addr.Zone() == "" {
+			continue
+		}
+		out = append(out, addr)
+	}
+	return out
+}
+
+func (r *registryConfigurator) getOriginalNameservers() []netip.Addr {
+	return slices.Clone(r.origNameservers)
+}
+
 func (r *registryConfigurator) supportCustomPort() bool {
 	return false
 }
@@ -169,16 +279,8 @@ func (r *registryConfigurator) disableWINSForInterface() error {
 }
 
 func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager *statemanager.Manager) error {
-	if config.RouteAll {
-		if err := r.addDNSSetupForAll(config.ServerIP); err != nil {
-			return fmt.Errorf("add dns setup: %w", err)
-		}
-	} else if r.routingAll {
-		if err := r.deleteInterfaceRegistryKeyProperty(interfaceConfigNameServerKey); err != nil {
-			return fmt.Errorf("delete interface registry key property: %w", err)
-		}
-		r.routingAll = false
-		log.Infof("removed %s as main DNS forwarder for this peer", config.ServerIP)
+	if err := r.applyRouteAll(config); err != nil {
+		return err
 	}
 
 	r.updateState(stateManager)
@@ -194,6 +296,13 @@ func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager
 		matchDomains = append(matchDomains, "."+strings.TrimSuffix(dConf.Domain, "."))
 	}
 
+	// In RouteAll mode, install an NRPT root-zone rule so the system DNS client
+	// steers every query to the NetBird resolver even if the per-interface
+	// NameServer setting is bypassed or overridden by another adapter.
+	if config.RouteAll {
+		matchDomains = append(matchDomains, ".")
+	}
+
 	if err := r.removeDNSMatchPolicies(); err != nil {
 		log.Errorf("cleanup old dns match policies: %s", err)
 	}
@@ -220,6 +329,35 @@ func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager
 	return nil
 }
 
+func (r *registryConfigurator) applyRouteAll(config HostDNSConfig) error {
+	if config.RouteAll {
+		if err := r.dnsFirewall.Enable(r.guid, config.ServerIP); err != nil {
+			return fmt.Errorf("dns firewall: %w", err)
+		}
+		if err := r.addDNSSetupForAll(config.ServerIP); err != nil {
+			merr := multierror.Append(nil, fmt.Errorf("add dns setup: %w", err))
+			if dErr := r.dnsFirewall.Disable(); dErr != nil {
+				merr = multierror.Append(merr, fmt.Errorf("rollback dns firewall: %w", dErr))
+			}
+			return nberrors.FormatErrorOrNil(merr)
+		}
+		return nil
+	}
+
+	if err := r.dnsFirewall.Disable(); err != nil {
+		log.Errorf("disable dns firewall: %v", err)
+	}
+	if !r.routingAll {
+		return nil
+	}
+	if err := r.deleteInterfaceRegistryKeyProperty(interfaceConfigNameServerKey); err != nil {
+		return fmt.Errorf("delete interface registry key property: %w", err)
+	}
+	r.routingAll = false
+	log.Infof("removed %s as main DNS forwarder for this peer", config.ServerIP)
+	return nil
+}
+
 func (r *registryConfigurator) updateState(stateManager *statemanager.Manager) {
 	if err := stateManager.UpdateState(&ShutdownState{
 		Guid:           r.guid,
@@ -406,6 +544,10 @@ func (r *registryConfigurator) restoreHostDNS() error {
 		return fmt.Errorf("remove interface registry key: %w", err)
 	}
 
+	if err := r.dnsFirewall.Disable(); err != nil {
+		log.Errorf("disable dns firewall: %v", err)
+	}
+
 	go r.flushDNSCache()
 
 	return nil

client/internal/dns/host_windows_test.go

@@ -8,6 +8,8 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"golang.org/x/sys/windows/registry"
+
+	"github.com/netbirdio/netbird/client/internal/dns/dnsfw"
 )
 
 // TestNRPTEntriesCleanupOnConfigChange tests that old NRPT entries are properly cleaned up
@@ -34,8 +36,9 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) {
 	}()
 
 	cfg := &registryConfigurator{
-		guid: testGUID,
-		gpo:  false,
+		guid:        testGUID,
+		gpo:         false,
+		dnsFirewall: dnsfw.New(),
 	}
 
 	// Create 125 domains which will result in 3 NRPT rules (50+50+25)
@@ -134,8 +137,9 @@ func TestNRPTDomainBatching(t *testing.T) {
 	}()
 
 	cfg := &registryConfigurator{
-		guid: testGUID,
-		gpo:  false,
+		guid:        testGUID,
+		gpo:         false,
+		dnsFirewall: dnsfw.New(),
 	}
 
 	testCases := []struct {

client/internal/dns/hosts_dns_holder.go

@@ -25,6 +25,7 @@ func (h *hostsDNSHolder) set(list []netip.AddrPort) {
 	h.mutex.Unlock()
 }
 
+//nolint:unused
 func (h *hostsDNSHolder) get() map[netip.AddrPort]struct{} {
 	h.mutex.RLock()
 	l := h.unprotectedDNSList

client/internal/dns/local/local.go

@@ -76,8 +76,6 @@ func (d *Resolver) ID() types.HandlerID {
 	return "local-resolver"
 }
 
-func (d *Resolver) ProbeAvailability(context.Context) {}
-
 // ServeDNS handles a DNS request
 func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	logger := log.WithFields(log.Fields{

client/internal/dns/mock_server.go

@@ -9,6 +9,7 @@ import (
 
 	dnsconfig "github.com/netbirdio/netbird/client/internal/dns/config"
 	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
@@ -70,10 +71,6 @@ func (m *MockServer) SearchDomains() []string {
 	return make([]string, 0)
 }
 
-// ProbeAvailability mocks implementation of ProbeAvailability from the Server interface
-func (m *MockServer) ProbeAvailability() {
-}
-
 func (m *MockServer) UpdateServerConfig(domains dnsconfig.ServerDomains) error {
 	if m.UpdateServerConfigFunc != nil {
 		return m.UpdateServerConfigFunc(domains)
@@ -85,8 +82,8 @@ func (m *MockServer) PopulateManagementDomain(mgmtURL *url.URL) error {
 	return nil
 }
 
-// SetRouteChecker mock implementation of SetRouteChecker from Server interface
-func (m *MockServer) SetRouteChecker(func(netip.Addr) bool) {
+// SetRouteSources mock implementation of SetRouteSources from Server interface
+func (m *MockServer) SetRouteSources(selected, active func() route.HAMap) {
 	// Mock implementation - no-op
 }
 

client/internal/dns/network_manager_unix.go

@@ -8,6 +8,7 @@ import (
 	"errors"
 	"fmt"
 	"net/netip"
+	"slices"
 	"strings"
 	"time"
 
@@ -32,6 +33,15 @@ const (
 	networkManagerDbusDeviceGetAppliedConnectionMethod                              = networkManagerDbusDeviceInterface + ".GetAppliedConnection"
 	networkManagerDbusDeviceReapplyMethod                                           = networkManagerDbusDeviceInterface + ".Reapply"
 	networkManagerDbusDeviceDeleteMethod                                            = networkManagerDbusDeviceInterface + ".Delete"
+	networkManagerDbusDeviceIp4ConfigProperty                                       = networkManagerDbusDeviceInterface + ".Ip4Config"
+	networkManagerDbusDeviceIp6ConfigProperty                                       = networkManagerDbusDeviceInterface + ".Ip6Config"
+	networkManagerDbusDeviceIfaceProperty                                           = networkManagerDbusDeviceInterface + ".Interface"
+	networkManagerDbusGetDevicesMethod                                              = networkManagerDest + ".GetDevices"
+	networkManagerDbusIp4ConfigInterface                                            = "org.freedesktop.NetworkManager.IP4Config"
+	networkManagerDbusIp6ConfigInterface                                            = "org.freedesktop.NetworkManager.IP6Config"
+	networkManagerDbusIp4ConfigNameserverDataProperty                               = networkManagerDbusIp4ConfigInterface + ".NameserverData"
+	networkManagerDbusIp4ConfigNameserversProperty                                  = networkManagerDbusIp4ConfigInterface + ".Nameservers"
+	networkManagerDbusIp6ConfigNameserversProperty                                  = networkManagerDbusIp6ConfigInterface + ".Nameservers"
 	networkManagerDbusDefaultBehaviorFlag              networkManagerConfigBehavior = 0
 	networkManagerDbusIPv4Key                                                       = "ipv4"
 	networkManagerDbusIPv6Key                                                       = "ipv6"
@@ -51,9 +61,10 @@ var supportedNetworkManagerVersionConstraints = []string{
 }
 
 type networkManagerDbusConfigurator struct {
-	dbusLinkObject dbus.ObjectPath
-	routingAll     bool
-	ifaceName      string
+	dbusLinkObject  dbus.ObjectPath
+	routingAll      bool
+	ifaceName       string
+	origNameservers []netip.Addr
 }
 
 // the types below are based on dbus specification, each field is mapped to a dbus type
@@ -92,10 +103,200 @@ func newNetworkManagerDbusConfigurator(wgInterface string) (*networkManagerDbusC
 
 	log.Debugf("got network manager dbus Link Object: %s from net interface %s", s, wgInterface)
 
-	return &networkManagerDbusConfigurator{
+	c := &networkManagerDbusConfigurator{
 		dbusLinkObject: dbus.ObjectPath(s),
 		ifaceName:      wgInterface,
-	}, nil
+	}
+
+	origNameservers, err := c.captureOriginalNameservers()
+	switch {
+	case err != nil:
+		log.Warnf("capture original nameservers from NetworkManager: %v", err)
+	case len(origNameservers) == 0:
+		log.Warnf("no original nameservers captured from non-WG NetworkManager devices; DNS fallback will be empty")
+	default:
+		log.Debugf("captured %d original nameservers from non-WG NetworkManager devices: %v", len(origNameservers), origNameservers)
+	}
+	c.origNameservers = origNameservers
+	return c, nil
+}
+
+// captureOriginalNameservers reads DNS servers from every NM device's
+// IP4Config / IP6Config except our WG device.
+func (n *networkManagerDbusConfigurator) captureOriginalNameservers() ([]netip.Addr, error) {
+	devices, err := networkManagerListDevices()
+	if err != nil {
+		return nil, fmt.Errorf("list devices: %w", err)
+	}
+
+	seen := make(map[netip.Addr]struct{})
+	var out []netip.Addr
+	for _, dev := range devices {
+		if dev == n.dbusLinkObject {
+			continue
+		}
+		ifaceName := readNetworkManagerDeviceInterface(dev)
+		for _, addr := range readNetworkManagerDeviceDNS(dev) {
+			addr = addr.Unmap()
+			if !addr.IsValid() || addr.IsUnspecified() {
+				continue
+			}
+			// IP6Config.Nameservers is a byte slice without zone info;
+			// reattach the device's interface name so a captured fe80::…
+			// stays routable.
+			if addr.IsLinkLocalUnicast() && ifaceName != "" {
+				addr = addr.WithZone(ifaceName)
+			}
+			if _, dup := seen[addr]; dup {
+				continue
+			}
+			seen[addr] = struct{}{}
+			out = append(out, addr)
+		}
+	}
+	return out, nil
+}
+
+func readNetworkManagerDeviceInterface(devicePath dbus.ObjectPath) string {
+	obj, closeConn, err := getDbusObject(networkManagerDest, devicePath)
+	if err != nil {
+		return ""
+	}
+	defer closeConn()
+	v, err := obj.GetProperty(networkManagerDbusDeviceIfaceProperty)
+	if err != nil {
+		return ""
+	}
+	s, _ := v.Value().(string)
+	return s
+}
+
+func networkManagerListDevices() ([]dbus.ObjectPath, error) {
+	obj, closeConn, err := getDbusObject(networkManagerDest, networkManagerDbusObjectNode)
+	if err != nil {
+		return nil, fmt.Errorf("dbus NetworkManager: %w", err)
+	}
+	defer closeConn()
+	var devs []dbus.ObjectPath
+	if err := obj.Call(networkManagerDbusGetDevicesMethod, dbusDefaultFlag).Store(&devs); err != nil {
+		return nil, err
+	}
+	return devs, nil
+}
+
+func readNetworkManagerDeviceDNS(devicePath dbus.ObjectPath) []netip.Addr {
+	obj, closeConn, err := getDbusObject(networkManagerDest, devicePath)
+	if err != nil {
+		return nil
+	}
+	defer closeConn()
+
+	var out []netip.Addr
+	if path := readNetworkManagerConfigPath(obj, networkManagerDbusDeviceIp4ConfigProperty); path != "" {
+		out = append(out, readIPv4ConfigDNS(path)...)
+	}
+	if path := readNetworkManagerConfigPath(obj, networkManagerDbusDeviceIp6ConfigProperty); path != "" {
+		out = append(out, readIPv6ConfigDNS(path)...)
+	}
+	return out
+}
+
+func readNetworkManagerConfigPath(obj dbus.BusObject, property string) dbus.ObjectPath {
+	v, err := obj.GetProperty(property)
+	if err != nil {
+		return ""
+	}
+	path, ok := v.Value().(dbus.ObjectPath)
+	if !ok || path == "/" {
+		return ""
+	}
+	return path
+}
+
+func readIPv4ConfigDNS(path dbus.ObjectPath) []netip.Addr {
+	obj, closeConn, err := getDbusObject(networkManagerDest, path)
+	if err != nil {
+		return nil
+	}
+	defer closeConn()
+
+	// NameserverData (NM 1.13+) carries strings; older NMs only expose the
+	// legacy uint32 Nameservers property.
+	if out := readIPv4NameserverData(obj); len(out) > 0 {
+		return out
+	}
+	return readIPv4LegacyNameservers(obj)
+}
+
+func readIPv4NameserverData(obj dbus.BusObject) []netip.Addr {
+	v, err := obj.GetProperty(networkManagerDbusIp4ConfigNameserverDataProperty)
+	if err != nil {
+		return nil
+	}
+	entries, ok := v.Value().([]map[string]dbus.Variant)
+	if !ok {
+		return nil
+	}
+	var out []netip.Addr
+	for _, entry := range entries {
+		addrVar, ok := entry["address"]
+		if !ok {
+			continue
+		}
+		s, ok := addrVar.Value().(string)
+		if !ok {
+			continue
+		}
+		if a, err := netip.ParseAddr(s); err == nil {
+			out = append(out, a)
+		}
+	}
+	return out
+}
+
+func readIPv4LegacyNameservers(obj dbus.BusObject) []netip.Addr {
+	v, err := obj.GetProperty(networkManagerDbusIp4ConfigNameserversProperty)
+	if err != nil {
+		return nil
+	}
+	raw, ok := v.Value().([]uint32)
+	if !ok {
+		return nil
+	}
+	out := make([]netip.Addr, 0, len(raw))
+	for _, n := range raw {
+		var b [4]byte
+		binary.LittleEndian.PutUint32(b[:], n)
+		out = append(out, netip.AddrFrom4(b))
+	}
+	return out
+}
+
+func readIPv6ConfigDNS(path dbus.ObjectPath) []netip.Addr {
+	obj, closeConn, err := getDbusObject(networkManagerDest, path)
+	if err != nil {
+		return nil
+	}
+	defer closeConn()
+	v, err := obj.GetProperty(networkManagerDbusIp6ConfigNameserversProperty)
+	if err != nil {
+		return nil
+	}
+	raw, ok := v.Value().([][]byte)
+	if !ok {
+		return nil
+	}
+	out := make([]netip.Addr, 0, len(raw))
+	for _, b := range raw {
+		if a, ok := netip.AddrFromSlice(b); ok {
+			out = append(out, a)
+		}
+	}
+	return out
+}
+
+func (n *networkManagerDbusConfigurator) getOriginalNameservers() []netip.Addr {
+	return slices.Clone(n.origNameservers)
 }
 
 func (n *networkManagerDbusConfigurator) supportCustomPort() bool {

client/internal/dns/server_android.go

@@ -1,5 +1,5 @@
 package dns
 
 func (s *DefaultServer) initialize() (manager hostManager, err error) {
-	return newHostManager()
+	return newHostManager(s.hostsDNSHolder)
 }

client/internal/dns/server_test.go

@@ -6,7 +6,7 @@ import (
 	"net"
 	"net/netip"
 	"os"
-	"strings"
+	"runtime"
 	"testing"
 	"time"
 
@@ -15,6 +15,7 @@ import (
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/mock"
+	"github.com/stretchr/testify/require"
 	"golang.zx2c4.com/wireguard/tun/netstack"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
@@ -31,8 +32,10 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
+	"github.com/netbirdio/netbird/client/proto"
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/formatter"
+	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
@@ -101,16 +104,17 @@ func init() {
 	formatter.SetTextFormatter(log.StandardLogger())
 }
 
-func generateDummyHandler(domain string, servers []nbdns.NameServer) *upstreamResolverBase {
+func generateDummyHandler(d string, servers []nbdns.NameServer) *upstreamResolverBase {
 	var srvs []netip.AddrPort
 	for _, srv := range servers {
 		srvs = append(srvs, srv.AddrPort())
 	}
-	return &upstreamResolverBase{
-		domain:          domain,
-		upstreamServers: srvs,
-		cancel:          func() {},
+	u := &upstreamResolverBase{
+		domain: domain.Domain(d),
+		cancel: func() {},
 	}
+	u.addRace(srvs)
+	return u
 }
 
 func TestUpdateDNSServer(t *testing.T) {
@@ -653,74 +657,8 @@ func TestDNSServerStartStop(t *testing.T) {
 	}
 }
 
-func TestDNSServerUpstreamDeactivateCallback(t *testing.T) {
-	hostManager := &mockHostConfigurator{}
-	server := DefaultServer{
-		ctx:           context.Background(),
-		service:       NewServiceViaMemory(&mocWGIface{}),
-		localResolver: local.NewResolver(),
-		handlerChain:  NewHandlerChain(),
-		hostManager:   hostManager,
-		currentConfig: HostDNSConfig{
-			Domains: []DomainConfig{
-				{false, "domain0", false},
-				{false, "domain1", false},
-				{false, "domain2", false},
-			},
-		},
-		statusRecorder: peer.NewRecorder("mgm"),
-	}
-
-	var domainsUpdate string
-	hostManager.applyDNSConfigFunc = func(config HostDNSConfig, statemanager *statemanager.Manager) error {
-		domains := []string{}
-		for _, item := range config.Domains {
-			if item.Disabled {
-				continue
-			}
-			domains = append(domains, item.Domain)
-		}
-		domainsUpdate = strings.Join(domains, ",")
-		return nil
-	}
-
-	deactivate, reactivate := server.upstreamCallbacks(&nbdns.NameServerGroup{
-		Domains: []string{"domain1"},
-		NameServers: []nbdns.NameServer{
-			{IP: netip.MustParseAddr("8.8.0.0"), NSType: nbdns.UDPNameServerType, Port: 53},
-		},
-	}, nil, 0)
-
-	deactivate(nil)
-	expected := "domain0,domain2"
-	domains := []string{}
-	for _, item := range server.currentConfig.Domains {
-		if item.Disabled {
-			continue
-		}
-		domains = append(domains, item.Domain)
-	}
-	got := strings.Join(domains, ",")
-	if expected != got {
-		t.Errorf("expected domains list: %q, got %q", expected, got)
-	}
-
-	reactivate()
-	expected = "domain0,domain1,domain2"
-	domains = []string{}
-	for _, item := range server.currentConfig.Domains {
-		if item.Disabled {
-			continue
-		}
-		domains = append(domains, item.Domain)
-	}
-	got = strings.Join(domains, ",")
-	if expected != got {
-		t.Errorf("expected domains list: %q, got %q", expected, domainsUpdate)
-	}
-}
-
 func TestDNSPermanent_updateHostDNS_emptyUpstream(t *testing.T) {
+	skipUnlessAndroid(t)
 	wgIFace, err := createWgInterfaceWithBind(t)
 	if err != nil {
 		t.Fatal("failed to initialize wg interface")
@@ -748,6 +686,7 @@ func TestDNSPermanent_updateHostDNS_emptyUpstream(t *testing.T) {
 }
 
 func TestDNSPermanent_updateUpstream(t *testing.T) {
+	skipUnlessAndroid(t)
 	wgIFace, err := createWgInterfaceWithBind(t)
 	if err != nil {
 		t.Fatal("failed to initialize wg interface")
@@ -841,6 +780,7 @@ func TestDNSPermanent_updateUpstream(t *testing.T) {
 }
 
 func TestDNSPermanent_matchOnly(t *testing.T) {
+	skipUnlessAndroid(t)
 	wgIFace, err := createWgInterfaceWithBind(t)
 	if err != nil {
 		t.Fatal("failed to initialize wg interface")
@@ -913,6 +853,18 @@ func TestDNSPermanent_matchOnly(t *testing.T) {
 	}
 }
 
+// skipUnlessAndroid marks tests that exercise the mobile-permanent DNS path,
+// which only matches a real production setup on android (NewDefaultServerPermanentUpstream
+// + androidHostManager). On non-android the desktop host manager replaces it
+// during Initialize and the assertion stops making sense. Skipped here until we
+// have an android CI runner.
+func skipUnlessAndroid(t *testing.T) {
+	t.Helper()
+	if runtime.GOOS != "android" {
+		t.Skip("requires android runner; mobile-permanent path doesn't match production on this OS")
+	}
+}
+
 func createWgInterfaceWithBind(t *testing.T) (*iface.WGIface, error) {
 	t.Helper()
 	ov := os.Getenv("NB_WG_KERNEL_DISABLED")
@@ -1065,7 +1017,6 @@ type mockHandler struct {
 
 func (m *mockHandler) ServeDNS(dns.ResponseWriter, *dns.Msg) {}
 func (m *mockHandler) Stop()                                 {}
-func (m *mockHandler) ProbeAvailability(context.Context)     {}
 func (m *mockHandler) ID() types.HandlerID                   { return types.HandlerID(m.Id) }
 
 type mockService struct{}
@@ -2085,6 +2036,598 @@ func TestLocalResolverPriorityConstants(t *testing.T) {
 	assert.Equal(t, "local.example.com", localMuxUpdates[0].domain)
 }
 
+// TestBuildUpstreamHandler_MergesGroupsPerDomain verifies that multiple
+// admin-defined nameserver groups targeting the same domain collapse into a
+// single handler with each group preserved as a sequential inner list.
+func TestBuildUpstreamHandler_MergesGroupsPerDomain(t *testing.T) {
+	wgInterface := &mocWGIface{}
+	service := NewServiceViaMemory(wgInterface)
+	server := &DefaultServer{
+		ctx:           context.Background(),
+		wgInterface:   wgInterface,
+		service:       service,
+		localResolver: local.NewResolver(),
+		handlerChain:  NewHandlerChain(),
+		hostManager:   &noopHostConfigurator{},
+		dnsMuxMap:     make(registeredHandlerMap),
+	}
+
+	groups := []*nbdns.NameServerGroup{
+		{
+			NameServers: []nbdns.NameServer{
+				{IP: netip.MustParseAddr("192.0.2.1"), NSType: nbdns.UDPNameServerType, Port: 53},
+			},
+			Domains: []string{"example.com"},
+		},
+		{
+			NameServers: []nbdns.NameServer{
+				{IP: netip.MustParseAddr("192.0.2.2"), NSType: nbdns.UDPNameServerType, Port: 53},
+				{IP: netip.MustParseAddr("192.0.2.3"), NSType: nbdns.UDPNameServerType, Port: 53},
+			},
+			Domains: []string{"example.com"},
+		},
+	}
+
+	muxUpdates, err := server.buildUpstreamHandlerUpdate(groups)
+	require.NoError(t, err)
+	require.Len(t, muxUpdates, 1, "same-domain groups should merge into one handler")
+	assert.Equal(t, "example.com", muxUpdates[0].domain)
+	assert.Equal(t, PriorityUpstream, muxUpdates[0].priority)
+
+	handler := muxUpdates[0].handler.(*upstreamResolver)
+	require.Len(t, handler.upstreamServers, 2, "handler should have two groups")
+	assert.Equal(t, upstreamRace{netip.MustParseAddrPort("192.0.2.1:53")}, handler.upstreamServers[0])
+	assert.Equal(t, upstreamRace{
+		netip.MustParseAddrPort("192.0.2.2:53"),
+		netip.MustParseAddrPort("192.0.2.3:53"),
+	}, handler.upstreamServers[1])
+}
+
+// TestEvaluateNSGroupHealth covers the records-only verdict. The gate
+// (overlay route selected-but-no-active-peer) is intentionally NOT an
+// input to the evaluator anymore: the verdict drives the Enabled flag,
+// which must always reflect what we actually observed. Gate-aware event
+// suppression is tested separately in the projection test.
+//
+// Matrix per upstream: {no record, fresh Ok, fresh Fail, stale Fail,
+// stale Ok, Ok newer than Fail, Fail newer than Ok}.
+// Group verdict: any fresh-working → Healthy; any fresh-broken with no
+// fresh-working → Unhealthy; otherwise Undecided.
+func TestEvaluateNSGroupHealth(t *testing.T) {
+	now := time.Now()
+	a := netip.MustParseAddrPort("192.0.2.1:53")
+	b := netip.MustParseAddrPort("192.0.2.2:53")
+
+	recentOk := UpstreamHealth{LastOk: now.Add(-2 * time.Second)}
+	recentFail := UpstreamHealth{LastFail: now.Add(-1 * time.Second), LastErr: "timeout"}
+	staleOk := UpstreamHealth{LastOk: now.Add(-10 * time.Minute)}
+	staleFail := UpstreamHealth{LastFail: now.Add(-10 * time.Minute), LastErr: "timeout"}
+	okThenFail := UpstreamHealth{
+		LastOk:   now.Add(-10 * time.Second),
+		LastFail: now.Add(-1 * time.Second),
+		LastErr:  "timeout",
+	}
+	failThenOk := UpstreamHealth{
+		LastOk:   now.Add(-1 * time.Second),
+		LastFail: now.Add(-10 * time.Second),
+		LastErr:  "timeout",
+	}
+
+	tests := []struct {
+		name         string
+		health       map[netip.AddrPort]UpstreamHealth
+		servers      []netip.AddrPort
+		wantVerdict  nsGroupVerdict
+		wantErrSubst string
+	}{
+		{
+			name:        "no record, undecided",
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictUndecided,
+		},
+		{
+			name:        "fresh success, healthy",
+			health:      map[netip.AddrPort]UpstreamHealth{a: recentOk},
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictHealthy,
+		},
+		{
+			name:         "fresh failure, unhealthy",
+			health:       map[netip.AddrPort]UpstreamHealth{a: recentFail},
+			servers:      []netip.AddrPort{a},
+			wantVerdict:  nsVerdictUnhealthy,
+			wantErrSubst: "timeout",
+		},
+		{
+			name:        "only stale success, undecided",
+			health:      map[netip.AddrPort]UpstreamHealth{a: staleOk},
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictUndecided,
+		},
+		{
+			name:        "only stale failure, undecided",
+			health:      map[netip.AddrPort]UpstreamHealth{a: staleFail},
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictUndecided,
+		},
+		{
+			name:         "both fresh, fail newer, unhealthy",
+			health:       map[netip.AddrPort]UpstreamHealth{a: okThenFail},
+			servers:      []netip.AddrPort{a},
+			wantVerdict:  nsVerdictUnhealthy,
+			wantErrSubst: "timeout",
+		},
+		{
+			name:        "both fresh, ok newer, healthy",
+			health:      map[netip.AddrPort]UpstreamHealth{a: failThenOk},
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictHealthy,
+		},
+		{
+			name: "two upstreams, one success wins",
+			health: map[netip.AddrPort]UpstreamHealth{
+				a: recentFail,
+				b: recentOk,
+			},
+			servers:     []netip.AddrPort{a, b},
+			wantVerdict: nsVerdictHealthy,
+		},
+		{
+			name: "two upstreams, one fail one unseen, unhealthy",
+			health: map[netip.AddrPort]UpstreamHealth{
+				a: recentFail,
+			},
+			servers:      []netip.AddrPort{a, b},
+			wantVerdict:  nsVerdictUnhealthy,
+			wantErrSubst: "timeout",
+		},
+		{
+			name: "two upstreams, all recent failures, unhealthy",
+			health: map[netip.AddrPort]UpstreamHealth{
+				a: {LastFail: now.Add(-5 * time.Second), LastErr: "timeout"},
+				b: {LastFail: now.Add(-1 * time.Second), LastErr: "SERVFAIL"},
+			},
+			servers:      []netip.AddrPort{a, b},
+			wantVerdict:  nsVerdictUnhealthy,
+			wantErrSubst: "SERVFAIL",
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			verdict, err := evaluateNSGroupHealth(tc.health, tc.servers, now)
+			assert.Equal(t, tc.wantVerdict, verdict, "verdict mismatch")
+			if tc.wantErrSubst != "" {
+				require.Error(t, err)
+				assert.Contains(t, err.Error(), tc.wantErrSubst)
+			} else {
+				assert.NoError(t, err)
+			}
+		})
+	}
+}
+
+// healthStubHandler is a minimal dnsMuxMap entry that exposes a fixed
+// UpstreamHealth snapshot, letting tests drive recomputeNSGroupStates
+// without spinning up real handlers.
+type healthStubHandler struct {
+	health map[netip.AddrPort]UpstreamHealth
+}
+
+func (h *healthStubHandler) ServeDNS(dns.ResponseWriter, *dns.Msg) {}
+func (h *healthStubHandler) Stop()                                 {}
+func (h *healthStubHandler) ID() types.HandlerID                   { return "health-stub" }
+func (h *healthStubHandler) UpstreamHealth() map[netip.AddrPort]UpstreamHealth {
+	return h.health
+}
+
+// TestProjection_SteadyStateIsSilent guards against duplicate events:
+// while a group stays Unhealthy tick after tick, only the first
+// Unhealthy transition may emit. Same for staying Healthy.
+func TestProjection_SteadyStateIsSilent(t *testing.T) {
+	fx := newProjTestFixture(t)
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "first fail emits warning")
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.tick()
+	fx.expectNoEvent("staying unhealthy must not re-emit")
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectEvent("recovered", "recovery on transition")
+
+	fx.tick()
+	fx.tick()
+	fx.expectNoEvent("staying healthy must not re-emit")
+}
+
+// projTestFixture is the common setup for the projection tests: a
+// single-upstream group whose route classification the test can flip by
+// assigning to selected/active. Callers drive failures/successes by
+// mutating stub.health and calling refreshHealth.
+type projTestFixture struct {
+	t        *testing.T
+	recorder *peer.Status
+	events   <-chan *proto.SystemEvent
+	server   *DefaultServer
+	stub     *healthStubHandler
+	group    *nbdns.NameServerGroup
+	srv      netip.AddrPort
+	selected route.HAMap
+	active   route.HAMap
+}
+
+func newProjTestFixture(t *testing.T) *projTestFixture {
+	t.Helper()
+	recorder := peer.NewRecorder("mgm")
+	sub := recorder.SubscribeToEvents()
+	t.Cleanup(func() { recorder.UnsubscribeFromEvents(sub) })
+
+	srv := netip.MustParseAddrPort("100.64.0.1:53")
+	fx := &projTestFixture{
+		t:        t,
+		recorder: recorder,
+		events:   sub.Events(),
+		stub:     &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{}},
+		srv:      srv,
+		group: &nbdns.NameServerGroup{
+			Domains:     []string{"example.com"},
+			NameServers: []nbdns.NameServer{{IP: srv.Addr(), NSType: nbdns.UDPNameServerType, Port: int(srv.Port())}},
+		},
+	}
+	fx.server = &DefaultServer{
+		ctx:              context.Background(),
+		wgInterface:      &mocWGIface{},
+		statusRecorder:   recorder,
+		dnsMuxMap:        make(registeredHandlerMap),
+		selectedRoutes:   func() route.HAMap { return fx.selected },
+		activeRoutes:     func() route.HAMap { return fx.active },
+		warningDelayBase: defaultWarningDelayBase,
+	}
+	fx.server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: fx.stub, priority: PriorityUpstream}
+
+	fx.server.mux.Lock()
+	fx.server.updateNSGroupStates([]*nbdns.NameServerGroup{fx.group})
+	fx.server.mux.Unlock()
+	return fx
+}
+
+func (f *projTestFixture) setHealth(h UpstreamHealth) {
+	f.stub.health = map[netip.AddrPort]UpstreamHealth{f.srv: h}
+}
+
+func (f *projTestFixture) tick() []peer.NSGroupState {
+	f.server.refreshHealth()
+	return f.recorder.GetDNSStates()
+}
+
+func (f *projTestFixture) expectNoEvent(why string) {
+	f.t.Helper()
+	select {
+	case evt := <-f.events:
+		f.t.Fatalf("unexpected event (%s): %+v", why, evt)
+	case <-time.After(100 * time.Millisecond):
+	}
+}
+
+func (f *projTestFixture) expectEvent(substr, why string) *proto.SystemEvent {
+	f.t.Helper()
+	select {
+	case evt := <-f.events:
+		assert.Contains(f.t, evt.Message, substr, why)
+		return evt
+	case <-time.After(time.Second):
+		f.t.Fatalf("expected event (%s) with %q", why, substr)
+		return nil
+	}
+}
+
+var overlayNetForTest = netip.MustParsePrefix("100.64.0.0/16")
+var overlayMapForTest = route.HAMap{"overlay": {{Network: overlayNetForTest}}}
+
+// TestProjection_PublicFailEmitsImmediately covers rule 1: an upstream
+// that is not inside any selected route (public DNS) fires the warning
+// on the first Unhealthy tick, no grace period.
+func TestProjection_PublicFailEmitsImmediately(t *testing.T) {
+	fx := newProjTestFixture(t)
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.False(t, states[0].Enabled)
+	fx.expectEvent("unreachable", "public DNS failure")
+}
+
+// TestProjection_OverlayConnectedFailEmitsImmediately covers rule 2:
+// the upstream is inside a selected route AND the route has a Connected
+// peer. Tunnel is up, failure is real, emit immediately.
+func TestProjection_OverlayConnectedFailEmitsImmediately(t *testing.T) {
+	fx := newProjTestFixture(t)
+	fx.selected = overlayMapForTest
+	fx.active = overlayMapForTest
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.False(t, states[0].Enabled)
+	fx.expectEvent("unreachable", "overlay + connected failure")
+}
+
+// TestProjection_OverlayNotConnectedDelaysWarning covers rule 3: the
+// upstream is routed but no peer is Connected (Connecting/Idle/missing).
+// First tick: Unhealthy display, no warning. After the grace window
+// elapses with no recovery, the warning fires.
+func TestProjection_OverlayNotConnectedDelaysWarning(t *testing.T) {
+	grace := 50 * time.Millisecond
+	fx := newProjTestFixture(t)
+	fx.server.warningDelayBase = grace
+	fx.selected = overlayMapForTest
+	// active stays nil: routed but not connected.
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.False(t, states[0].Enabled, "display must reflect failure even during grace window")
+	fx.expectNoEvent("first fail tick within grace window")
+
+	time.Sleep(grace + 10*time.Millisecond)
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "warning after grace window")
+}
+
+// TestProjection_OverlayAddrNoRouteDelaysWarning covers an upstream
+// whose address is inside the WireGuard overlay range but is not
+// covered by any selected route (peer-to-peer DNS without an explicit
+// route). Until a peer reports Connected for that address, startup
+// failures must be held just like the routed case.
+func TestProjection_OverlayAddrNoRouteDelaysWarning(t *testing.T) {
+	recorder := peer.NewRecorder("mgm")
+	sub := recorder.SubscribeToEvents()
+	t.Cleanup(func() { recorder.UnsubscribeFromEvents(sub) })
+
+	overlayPeer := netip.MustParseAddrPort("100.66.100.5:53")
+	server := &DefaultServer{
+		ctx:              context.Background(),
+		wgInterface:      &mocWGIface{},
+		statusRecorder:   recorder,
+		dnsMuxMap:        make(registeredHandlerMap),
+		selectedRoutes:   func() route.HAMap { return nil },
+		activeRoutes:     func() route.HAMap { return nil },
+		warningDelayBase: 50 * time.Millisecond,
+	}
+	group := &nbdns.NameServerGroup{
+		Domains:     []string{"example.com"},
+		NameServers: []nbdns.NameServer{{IP: overlayPeer.Addr(), NSType: nbdns.UDPNameServerType, Port: int(overlayPeer.Port())}},
+	}
+	stub := &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{
+		overlayPeer: {LastFail: time.Now(), LastErr: "timeout"},
+	}}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+
+	server.mux.Lock()
+	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
+	server.mux.Unlock()
+	server.refreshHealth()
+
+	select {
+	case evt := <-sub.Events():
+		t.Fatalf("unexpected event during grace window: %+v", evt)
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	time.Sleep(60 * time.Millisecond)
+	stub.health = map[netip.AddrPort]UpstreamHealth{overlayPeer: {LastFail: time.Now(), LastErr: "timeout"}}
+	server.refreshHealth()
+
+	select {
+	case evt := <-sub.Events():
+		assert.Contains(t, evt.Message, "unreachable")
+	case <-time.After(time.Second):
+		t.Fatal("expected warning after grace window")
+	}
+}
+
+// TestProjection_StopClearsHealthState verifies that Stop wipes the
+// per-group projection state so a subsequent Start doesn't inherit
+// sticky flags (notably everHealthy) that would bypass the grace
+// window during the next peer handshake.
+func TestProjection_StopClearsHealthState(t *testing.T) {
+	wgIface := &mocWGIface{}
+	server := &DefaultServer{
+		ctx:               context.Background(),
+		wgInterface:       wgIface,
+		service:           NewServiceViaMemory(wgIface),
+		hostManager:       &noopHostConfigurator{},
+		extraDomains:      map[domain.Domain]int{},
+		dnsMuxMap:         make(registeredHandlerMap),
+		statusRecorder:    peer.NewRecorder("mgm"),
+		selectedRoutes:    func() route.HAMap { return nil },
+		activeRoutes:      func() route.HAMap { return nil },
+		warningDelayBase:  defaultWarningDelayBase,
+		currentConfigHash: ^uint64(0),
+	}
+	server.ctx, server.ctxCancel = context.WithCancel(context.Background())
+
+	srv := netip.MustParseAddrPort("8.8.8.8:53")
+	group := &nbdns.NameServerGroup{
+		Domains:     []string{"example.com"},
+		NameServers: []nbdns.NameServer{{IP: srv.Addr(), NSType: nbdns.UDPNameServerType, Port: int(srv.Port())}},
+	}
+	stub := &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{srv: {LastOk: time.Now()}}}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+
+	server.mux.Lock()
+	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
+	server.mux.Unlock()
+	server.refreshHealth()
+
+	server.healthProjectMu.Lock()
+	p, ok := server.nsGroupProj[generateGroupKey(group)]
+	server.healthProjectMu.Unlock()
+	require.True(t, ok, "projection state should exist after tick")
+	require.True(t, p.everHealthy, "tick with success must set everHealthy")
+
+	server.Stop()
+
+	server.healthProjectMu.Lock()
+	cleared := server.nsGroupProj == nil
+	server.healthProjectMu.Unlock()
+	assert.True(t, cleared, "Stop must clear nsGroupProj")
+}
+
+// TestProjection_OverlayRecoversDuringGrace covers the happy path of
+// rule 3: startup failures while the peer is handshaking, then the peer
+// comes up and a query succeeds before the grace window elapses. No
+// warning should ever have fired, and no recovery either.
+func TestProjection_OverlayRecoversDuringGrace(t *testing.T) {
+	fx := newProjTestFixture(t)
+	fx.server.warningDelayBase = 200 * time.Millisecond
+	fx.selected = overlayMapForTest
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectNoEvent("fail within grace, warning suppressed")
+
+	fx.active = overlayMapForTest
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.True(t, states[0].Enabled)
+	fx.expectNoEvent("recovery without prior warning must not emit")
+}
+
+// TestProjection_RecoveryOnlyAfterWarning enforces the invariant the
+// whole design leans on: recovery events only appear when a warning
+// event was actually emitted for the current streak. A Healthy verdict
+// without a prior warning is silent, so the user never sees "recovered"
+// out of thin air.
+func TestProjection_RecoveryOnlyAfterWarning(t *testing.T) {
+	fx := newProjTestFixture(t)
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.True(t, states[0].Enabled)
+	fx.expectNoEvent("first healthy tick should not recover anything")
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "public fail emits immediately")
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectEvent("recovered", "recovery follows real warning")
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "second cycle warning")
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectEvent("recovered", "second cycle recovery")
+}
+
+// TestProjection_EverHealthyOverridesDelay covers rule 4: once a group
+// has ever been Healthy, subsequent failures skip the grace window even
+// if classification says "routed + not connected". The system has
+// proved it can work, so any new failure is real.
+func TestProjection_EverHealthyOverridesDelay(t *testing.T) {
+	fx := newProjTestFixture(t)
+	// Large base so any emission must come from the everHealthy bypass, not elapsed time.
+	fx.server.warningDelayBase = time.Hour
+	fx.selected = overlayMapForTest
+	fx.active = overlayMapForTest
+
+	// Establish "ever healthy".
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectNoEvent("first healthy tick")
+
+	// Peer drops. Query fails. Routed + not connected → normally grace,
+	// but everHealthy flag bypasses it.
+	fx.active = nil
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "failure after ever-healthy must be immediate")
+}
+
+// TestProjection_ReconnectBlipEmitsPair covers the explicit tradeoff
+// from the design discussion: once a group has been healthy, a brief
+// reconnect that produces a failing tick will fire warning + recovery.
+// This is by design: user-visible blips are accurate signal, not noise.
+func TestProjection_ReconnectBlipEmitsPair(t *testing.T) {
+	fx := newProjTestFixture(t)
+	fx.selected = overlayMapForTest
+	fx.active = overlayMapForTest
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "blip warning")
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectEvent("recovered", "blip recovery")
+}
+
+// TestProjection_MixedGroupEmitsImmediately covers the multi-upstream
+// rule: a group with at least one public upstream is in the "immediate"
+// category regardless of the other upstreams' routing, because the
+// public one has no peer-startup excuse. Prevents public-DNS failures
+// from being hidden behind a routed sibling.
+func TestProjection_MixedGroupEmitsImmediately(t *testing.T) {
+	recorder := peer.NewRecorder("mgm")
+	sub := recorder.SubscribeToEvents()
+	t.Cleanup(func() { recorder.UnsubscribeFromEvents(sub) })
+	events := sub.Events()
+
+	public := netip.MustParseAddrPort("8.8.8.8:53")
+	overlay := netip.MustParseAddrPort("100.64.0.1:53")
+	overlayMap := route.HAMap{"overlay": {{Network: netip.MustParsePrefix("100.64.0.0/16")}}}
+
+	server := &DefaultServer{
+		ctx:              context.Background(),
+		statusRecorder:   recorder,
+		dnsMuxMap:        make(registeredHandlerMap),
+		selectedRoutes:   func() route.HAMap { return overlayMap },
+		activeRoutes:     func() route.HAMap { return nil },
+		warningDelayBase: time.Hour,
+	}
+	group := &nbdns.NameServerGroup{
+		Domains: []string{"example.com"},
+		NameServers: []nbdns.NameServer{
+			{IP: public.Addr(), NSType: nbdns.UDPNameServerType, Port: int(public.Port())},
+			{IP: overlay.Addr(), NSType: nbdns.UDPNameServerType, Port: int(overlay.Port())},
+		},
+	}
+	stub := &healthStubHandler{
+		health: map[netip.AddrPort]UpstreamHealth{
+			public:  {LastFail: time.Now(), LastErr: "servfail"},
+			overlay: {LastFail: time.Now(), LastErr: "timeout"},
+		},
+	}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+
+	server.mux.Lock()
+	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
+	server.mux.Unlock()
+	server.refreshHealth()
+
+	select {
+	case evt := <-events:
+		assert.Contains(t, evt.Message, "unreachable")
+	case <-time.After(time.Second):
+		t.Fatal("expected immediate warning because group contains a public upstream")
+	}
+}
+
 func TestDNSLoopPrevention(t *testing.T) {
 	wgInterface := &mocWGIface{}
 	service := NewServiceViaMemory(wgInterface)
@@ -2183,17 +2726,18 @@ func TestDNSLoopPrevention(t *testing.T) {
 
 			if tt.expectedHandlers > 0 {
 				handler := muxUpdates[0].handler.(*upstreamResolver)
-				assert.Len(t, handler.upstreamServers, len(tt.expectedServers))
+				flat := handler.flatUpstreams()
+				assert.Len(t, flat, len(tt.expectedServers))
 
 				if tt.shouldFilterOwnIP {
-					for _, upstream := range handler.upstreamServers {
+					for _, upstream := range flat {
 						assert.NotEqual(t, dnsServerIP, upstream.Addr())
 					}
 				}
 
 				for _, expected := range tt.expectedServers {
 					found := false
-					for _, upstream := range handler.upstreamServers {
+					for _, upstream := range flat {
 						if upstream.Addr() == expected {
 							found = true
 							break

client/internal/dns/systemd_linux.go

@@ -8,6 +8,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"slices"
 	"time"
 
 	"github.com/godbus/dbus/v5"
@@ -40,10 +41,17 @@ const (
 )
 
 type systemdDbusConfigurator struct {
-	dbusLinkObject dbus.ObjectPath
-	ifaceName      string
+	dbusLinkObject  dbus.ObjectPath
+	ifaceName       string
+	wgIndex         int
+	origNameservers []netip.Addr
 }
 
+const (
+	systemdDbusLinkDNSProperty          = systemdDbusLinkInterface + ".DNS"
+	systemdDbusLinkDefaultRouteProperty = systemdDbusLinkInterface + ".DefaultRoute"
+)
+
 // the types below are based on dbus specification, each field is mapped to a dbus type
 // see https://dbus.freedesktop.org/doc/dbus-specification.html#basic-types for more details on dbus types
 // see https://www.freedesktop.org/software/systemd/man/org.freedesktop.resolve1.html on resolve1 input types
@@ -79,10 +87,145 @@ func newSystemdDbusConfigurator(wgInterface string) (*systemdDbusConfigurator, e
 
 	log.Debugf("got dbus Link interface: %s from net interface %s and index %d", s, iface.Name, iface.Index)
 
-	return &systemdDbusConfigurator{
+	c := &systemdDbusConfigurator{
 		dbusLinkObject: dbus.ObjectPath(s),
 		ifaceName:      wgInterface,
-	}, nil
+		wgIndex:        iface.Index,
+	}
+
+	origNameservers, err := c.captureOriginalNameservers()
+	switch {
+	case err != nil:
+		log.Warnf("capture original nameservers from systemd-resolved: %v", err)
+	case len(origNameservers) == 0:
+		log.Warnf("no original nameservers captured from systemd-resolved default-route links; DNS fallback will be empty")
+	default:
+		log.Debugf("captured %d original nameservers from systemd-resolved default-route links: %v", len(origNameservers), origNameservers)
+	}
+	c.origNameservers = origNameservers
+	return c, nil
+}
+
+// captureOriginalNameservers reads per-link DNS from systemd-resolved for
+// every default-route link except our own WG link. Non-default-route links
+// (VPNs, docker bridges) are skipped because their upstreams wouldn't
+// actually serve host queries.
+func (s *systemdDbusConfigurator) captureOriginalNameservers() ([]netip.Addr, error) {
+	ifaces, err := net.Interfaces()
+	if err != nil {
+		return nil, fmt.Errorf("list interfaces: %w", err)
+	}
+
+	seen := make(map[netip.Addr]struct{})
+	var out []netip.Addr
+	for _, iface := range ifaces {
+		if !s.isCandidateLink(iface) {
+			continue
+		}
+		linkPath, err := getSystemdLinkPath(iface.Index)
+		if err != nil || !isSystemdLinkDefaultRoute(linkPath) {
+			continue
+		}
+		for _, addr := range readSystemdLinkDNS(linkPath) {
+			addr = normalizeSystemdAddr(addr, iface.Name)
+			if !addr.IsValid() {
+				continue
+			}
+			if _, dup := seen[addr]; dup {
+				continue
+			}
+			seen[addr] = struct{}{}
+			out = append(out, addr)
+		}
+	}
+	return out, nil
+}
+
+func (s *systemdDbusConfigurator) isCandidateLink(iface net.Interface) bool {
+	if iface.Index == s.wgIndex {
+		return false
+	}
+	if iface.Flags&net.FlagLoopback != 0 || iface.Flags&net.FlagUp == 0 {
+		return false
+	}
+	return true
+}
+
+// normalizeSystemdAddr unmaps v4-mapped-v6, drops unspecified, and reattaches
+// the link's iface name as zone for link-local v6 (Link.DNS strips it).
+// Returns the zero Addr to signal "skip this entry".
+func normalizeSystemdAddr(addr netip.Addr, ifaceName string) netip.Addr {
+	addr = addr.Unmap()
+	if !addr.IsValid() || addr.IsUnspecified() {
+		return netip.Addr{}
+	}
+	if addr.IsLinkLocalUnicast() {
+		return addr.WithZone(ifaceName)
+	}
+	return addr
+}
+
+func getSystemdLinkPath(ifIndex int) (dbus.ObjectPath, error) {
+	obj, closeConn, err := getDbusObject(systemdResolvedDest, systemdDbusObjectNode)
+	if err != nil {
+		return "", fmt.Errorf("dbus resolve1: %w", err)
+	}
+	defer closeConn()
+	var p string
+	if err := obj.Call(systemdDbusGetLinkMethod, dbusDefaultFlag, int32(ifIndex)).Store(&p); err != nil {
+		return "", err
+	}
+	return dbus.ObjectPath(p), nil
+}
+
+func isSystemdLinkDefaultRoute(linkPath dbus.ObjectPath) bool {
+	obj, closeConn, err := getDbusObject(systemdResolvedDest, linkPath)
+	if err != nil {
+		return false
+	}
+	defer closeConn()
+	v, err := obj.GetProperty(systemdDbusLinkDefaultRouteProperty)
+	if err != nil {
+		return false
+	}
+	b, ok := v.Value().(bool)
+	return ok && b
+}
+
+func readSystemdLinkDNS(linkPath dbus.ObjectPath) []netip.Addr {
+	obj, closeConn, err := getDbusObject(systemdResolvedDest, linkPath)
+	if err != nil {
+		return nil
+	}
+	defer closeConn()
+	v, err := obj.GetProperty(systemdDbusLinkDNSProperty)
+	if err != nil {
+		return nil
+	}
+	entries, ok := v.Value().([][]any)
+	if !ok {
+		return nil
+	}
+	var out []netip.Addr
+	for _, entry := range entries {
+		if len(entry) < 2 {
+			continue
+		}
+		raw, ok := entry[1].([]byte)
+		if !ok {
+			continue
+		}
+		addr, ok := netip.AddrFromSlice(raw)
+		if !ok {
+			continue
+		}
+		out = append(out, addr)
+	}
+	return out
+}
+
+func (s *systemdDbusConfigurator) getOriginalNameservers() []netip.Addr {
+	return slices.Clone(s.origNameservers)
 }
 
 func (s *systemdDbusConfigurator) supportCustomPort() bool {

client/internal/dns/upstream.go

@@ -1,3 +1,32 @@
+// Package dns implements the client-side DNS stack: listener/service on the
+// peer's tunnel address, handler chain that routes questions by domain and
+// priority, and upstream resolvers that forward what remains to configured
+// nameservers.
+//
+// # Upstream resolution and the race model
+//
+// When two or more nameserver groups target the same domain, DefaultServer
+// merges them into one upstream handler whose state is:
+//
+//	upstreamResolverBase
+//	  └── upstreamServers []upstreamRace   // one entry per source NS group
+//	        └── []netip.AddrPort           // primary, fallback, ...
+//
+// Each source nameserver group contributes one upstreamRace. Within a race
+// upstreams are tried in order: the next is used only on failure (timeout,
+// SERVFAIL, REFUSED, no response). NXDOMAIN is a valid answer and stops
+// the walk. When more than one race exists, ServeDNS fans out one
+// goroutine per race and returns the first valid answer, cancelling the
+// rest. A handler with a single race skips the fan-out.
+//
+// # Health projection
+//
+// Query outcomes are recorded per-upstream in UpstreamHealth. The server
+// periodically merges these snapshots across handlers and projects them
+// into peer.NSGroupState. There is no active probing: a group is marked
+// unhealthy only when every seen upstream has a recent failure and none
+// has a recent success. Healthy→unhealthy fires a single
+// SystemEvent_WARNING; steady-state refreshes do not duplicate it.
 package dns
 
 import (
@@ -11,11 +40,8 @@ import (
 	"slices"
 	"strings"
 	"sync"
-	"sync/atomic"
 	"time"
 
-	"github.com/cenkalti/backoff/v4"
-	"github.com/hashicorp/go-multierror"
 	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
 	"golang.zx2c4.com/wireguard/tun/netstack"
@@ -25,7 +51,8 @@ import (
 	"github.com/netbirdio/netbird/client/internal/dns/resutil"
 	"github.com/netbirdio/netbird/client/internal/dns/types"
 	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/proto"
+	"github.com/netbirdio/netbird/route"
+	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 var currentMTU uint16 = iface.DefaultMTU
@@ -67,15 +94,17 @@ const (
 	// Set longer than UpstreamTimeout to ensure context timeout takes precedence
 	ClientTimeout = 5 * time.Second
 
-	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."
+	// raceMaxTotalTimeout caps the combined time spent walking all upstreams
+	// within one race, so a slow primary can't eat the whole race budget.
+	raceMaxTotalTimeout = 5 * time.Second
+	// raceMinPerUpstreamTimeout is the floor applied when dividing
+	// raceMaxTotalTimeout across upstreams within a race.
+	raceMinPerUpstreamTimeout = 2 * time.Second
+)
 
 const (
 	protoUDP = "udp"
@@ -84,6 +113,69 @@ const (
 
 type dnsProtocolKey struct{}
 
+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
+}
+
+type upstreamClient interface {
+	exchange(ctx context.Context, upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
+}
+
+type UpstreamResolver interface {
+	serveDNS(r *dns.Msg) (*dns.Msg, time.Duration, error)
+	upstreamExchange(upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
+}
+
+// upstreamRace is an ordered list of upstreams derived from one configured
+// nameserver group. Order matters: the first upstream is tried first, the
+// second only on failure, and so on. Multiple upstreamRace values coexist
+// inside one resolver when overlapping nameserver groups target the same
+// domain; those races run in parallel and the first valid answer wins.
+type upstreamRace []netip.AddrPort
+
+// UpstreamHealth is the last query-path outcome for a single upstream,
+// consumed by nameserver-group status projection.
+type UpstreamHealth struct {
+	LastOk   time.Time
+	LastFail time.Time
+	LastErr  string
+}
+
+type upstreamResolverBase struct {
+	ctx             context.Context
+	cancel          context.CancelFunc
+	upstreamClient  upstreamClient
+	upstreamServers []upstreamRace
+	domain          domain.Domain
+	upstreamTimeout time.Duration
+
+	healthMu sync.RWMutex
+	health   map[netip.AddrPort]*UpstreamHealth
+
+	statusRecorder *peer.Status
+	// selectedRoutes returns the current set of client routes the admin
+	// has enabled. Called lazily from the query hot path when an upstream
+	// might need a tunnel-bound client (iOS) and from health projection.
+	selectedRoutes func() route.HAMap
+}
+
+type upstreamFailure struct {
+	upstream netip.AddrPort
+	reason   string
+}
+
+type raceResult struct {
+	msg      *dns.Msg
+	upstream netip.AddrPort
+	protocol string
+	ede      string
+	failures []upstreamFailure
+}
+
 // 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)
@@ -100,16 +192,8 @@ func dnsProtocolFromContext(ctx context.Context) string {
 	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) {
+// 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
 }
@@ -124,67 +208,37 @@ func setUpstreamProtocol(ctx context.Context, protocol string) {
 	}
 }
 
-type upstreamClient interface {
-	exchange(ctx context.Context, upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
-}
-
-type UpstreamResolver interface {
-	serveDNS(r *dns.Msg) (*dns.Msg, time.Duration, error)
-	upstreamExchange(upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
-}
-
-type upstreamResolverBase struct {
-	ctx              context.Context
-	cancel           context.CancelFunc
-	upstreamClient   upstreamClient
-	upstreamServers  []netip.AddrPort
-	domain           string
-	disabled         bool
-	successCount     atomic.Int32
-	mutex            sync.Mutex
-	reactivatePeriod time.Duration
-	upstreamTimeout  time.Duration
-	wg               sync.WaitGroup
-
-	deactivate     func(error)
-	reactivate     func()
-	statusRecorder *peer.Status
-	routeMatch     func(netip.Addr) bool
-}
-
-type upstreamFailure struct {
-	upstream netip.AddrPort
-	reason   string
-}
-
-func newUpstreamResolverBase(ctx context.Context, statusRecorder *peer.Status, domain string) *upstreamResolverBase {
+func newUpstreamResolverBase(ctx context.Context, statusRecorder *peer.Status, d domain.Domain) *upstreamResolverBase {
 	ctx, cancel := context.WithCancel(ctx)
 
 	return &upstreamResolverBase{
-		ctx:              ctx,
-		cancel:           cancel,
-		domain:           domain,
-		upstreamTimeout:  UpstreamTimeout,
-		reactivatePeriod: reactivatePeriod,
-		statusRecorder:   statusRecorder,
+		ctx:             ctx,
+		cancel:          cancel,
+		domain:          d,
+		upstreamTimeout: UpstreamTimeout,
+		statusRecorder:  statusRecorder,
 	}
 }
 
 // String returns a string representation of the upstream resolver
 func (u *upstreamResolverBase) String() string {
-	return fmt.Sprintf("Upstream %s", u.upstreamServers)
+	return fmt.Sprintf("Upstream %s", u.flatUpstreams())
 }
 
-// ID returns the unique handler ID
+// ID returns the unique handler ID. Race groupings and within-race
+// ordering are both part of the identity: [[A,B]] and [[A],[B]] query
+// the same servers but with different semantics (serial fallback vs
+// parallel race), so their handlers must not collide.
 func (u *upstreamResolverBase) ID() types.HandlerID {
-	servers := slices.Clone(u.upstreamServers)
-	slices.SortFunc(servers, func(a, b netip.AddrPort) int { return a.Compare(b) })
-
 	hash := sha256.New()
-	hash.Write([]byte(u.domain + ":"))
-	for _, s := range servers {
-		hash.Write([]byte(s.String()))
-		hash.Write([]byte("|"))
+	hash.Write([]byte(u.domain.PunycodeString() + ":"))
+	for _, race := range u.upstreamServers {
+		hash.Write([]byte("["))
+		for _, s := range race {
+			hash.Write([]byte(s.String()))
+			hash.Write([]byte("|"))
+		}
+		hash.Write([]byte("]"))
 	}
 	return types.HandlerID("upstream-" + hex.EncodeToString(hash.Sum(nil)[:8]))
 }
@@ -194,13 +248,31 @@ func (u *upstreamResolverBase) MatchSubdomains() bool {
 }
 
 func (u *upstreamResolverBase) Stop() {
-	log.Debugf("stopping serving DNS for upstreams %s", u.upstreamServers)
+	log.Debugf("stopping serving DNS for upstreams %s", u.flatUpstreams())
 	u.cancel()
+}
 
-	u.mutex.Lock()
-	u.wg.Wait()
-	u.mutex.Unlock()
+// flatUpstreams is for logging and ID hashing only, not for dispatch.
+func (u *upstreamResolverBase) flatUpstreams() []netip.AddrPort {
+	var out []netip.AddrPort
+	for _, g := range u.upstreamServers {
+		out = append(out, g...)
+	}
+	return out
+}
 
+// setSelectedRoutes swaps the accessor used to classify overlay-routed
+// upstreams. Called when route sources are wired after the handler was
+// built (permanent / iOS constructors).
+func (u *upstreamResolverBase) setSelectedRoutes(selected func() route.HAMap) {
+	u.selectedRoutes = selected
+}
+
+func (u *upstreamResolverBase) addRace(servers []netip.AddrPort) {
+	if len(servers) == 0 {
+		return
+	}
+	u.upstreamServers = append(u.upstreamServers, slices.Clone(servers))
 }
 
 // ServeDNS handles a DNS request
@@ -242,82 +314,201 @@ func (u *upstreamResolverBase) prepareRequest(r *dns.Msg) {
 }
 
 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
-		minPerUpstream := 2 * time.Second
-		scaledTimeout := maxTotal / time.Duration(len(u.upstreamServers))
-		if scaledTimeout > minPerUpstream {
-			timeout = scaledTimeout
-		} else {
-			timeout = minPerUpstream
-		}
+	groups := u.upstreamServers
+	switch len(groups) {
+	case 0:
+		return false, nil
+	case 1:
+		return u.tryOnlyRace(ctx, w, r, groups[0], logger)
+	default:
+		return u.raceAll(ctx, w, r, groups, logger)
+	}
+}
+
+func (u *upstreamResolverBase) tryOnlyRace(ctx context.Context, w dns.ResponseWriter, r *dns.Msg, group upstreamRace, logger *log.Entry) (bool, []upstreamFailure) {
+	res := u.tryRace(ctx, r, group)
+	if res.msg == nil {
+		return false, res.failures
+	}
+	if res.ede != "" {
+		resutil.SetMeta(w, "ede", res.ede)
+	}
+	u.writeSuccessResponse(w, res.msg, res.upstream, r.Question[0].Name, res.protocol, logger)
+	return true, res.failures
+}
+
+// raceAll runs one worker per group in parallel, taking the first valid
+// answer and cancelling the rest.
+func (u *upstreamResolverBase) raceAll(ctx context.Context, w dns.ResponseWriter, r *dns.Msg, groups []upstreamRace, logger *log.Entry) (bool, []upstreamFailure) {
+	raceCtx, cancel := context.WithCancel(ctx)
+	defer cancel()
+
+	// Buffer sized to len(groups) so workers never block on send, even
+	// after the coordinator has returned.
+	results := make(chan raceResult, len(groups))
+	for _, g := range groups {
+		// tryRace clones the request per attempt, so workers never share
+		// a *dns.Msg and concurrent EDNS0 mutations can't race.
+		go func(g upstreamRace) {
+			results <- u.tryRace(raceCtx, r, g)
+		}(g)
 	}
 
 	var failures []upstreamFailure
-	for _, upstream := range u.upstreamServers {
-		if failure := u.queryUpstream(ctx, w, r, upstream, timeout, logger); failure != nil {
-			failures = append(failures, *failure)
-		} else {
-			return true, failures
+	for range groups {
+		select {
+		case res := <-results:
+			failures = append(failures, res.failures...)
+			if res.msg != nil {
+				if res.ede != "" {
+					resutil.SetMeta(w, "ede", res.ede)
+				}
+				u.writeSuccessResponse(w, res.msg, res.upstream, r.Question[0].Name, res.protocol, logger)
+				return true, failures
+			}
+		case <-ctx.Done():
+			return false, failures
 		}
 	}
 	return false, failures
 }
 
-// queryUpstream queries a single upstream server. Returns nil on success, or failure info to try next upstream.
-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
+func (u *upstreamResolverBase) tryRace(ctx context.Context, r *dns.Msg, group upstreamRace) raceResult {
+	timeout := u.upstreamTimeout
+	if len(group) > 1 {
+		// Cap the whole walk at raceMaxTotalTimeout: per-upstream timeouts
+		// still honor raceMinPerUpstreamTimeout as a floor for correctness
+		// on slow links, but the outer context ensures the combined walk
+		// cannot exceed the cap regardless of group size.
+		timeout = max(raceMaxTotalTimeout/time.Duration(len(group)), raceMinPerUpstreamTimeout)
+		var cancel context.CancelFunc
+		ctx, cancel = context.WithTimeout(ctx, raceMaxTotalTimeout)
+		defer cancel()
+	}
+
+	var failures []upstreamFailure
+	for _, upstream := range group {
+		if ctx.Err() != nil {
+			return raceResult{failures: failures}
+		}
+		// Clone the request per attempt: the exchange path mutates EDNS0
+		// options in-place, so reusing the same *dns.Msg across sequential
+		// upstreams would carry those mutations (e.g. a reduced UDP size)
+		// into the next attempt.
+		res, failure := u.queryUpstream(ctx, r.Copy(), upstream, timeout)
+		if failure != nil {
+			failures = append(failures, *failure)
+			continue
+		}
+		res.failures = failures
+		return res
+	}
+	return raceResult{failures: failures}
+}
+
+func (u *upstreamResolverBase) queryUpstream(parentCtx context.Context, r *dns.Msg, upstream netip.AddrPort, timeout time.Duration) (raceResult, *upstreamFailure) {
+	ctx, cancel := context.WithTimeout(parentCtx, timeout)
+	defer cancel()
+	ctx, upstreamProto := contextWithUpstreamProtocolResult(ctx)
 
 	// Advertise EDNS0 so the upstream may include Extended DNS Errors
 	// (RFC 8914) in failure responses; we use those to short-circuit
 	// failover for definitive answers like DNSSEC validation failures.
-	// Operate on a copy so the inbound request is unchanged: a client that
-	// did not advertise EDNS0 must not see an OPT in the response.
+	// The caller already passed a per-attempt copy, so we can mutate r
+	// directly; hadEdns reflects the original client request's state and
+	// controls whether we strip the OPT from the response.
 	hadEdns := r.IsEdns0() != nil
-	reqUp := r
 	if !hadEdns {
-		reqUp = r.Copy()
-		reqUp.SetEdns0(upstreamUDPSize(), false)
+		r.SetEdns0(upstreamUDPSize(), false)
 	}
 
-	var startTime time.Time
-	var upstreamProto *upstreamProtocolResult
-	func() {
-		ctx, cancel := context.WithTimeout(parentCtx, timeout)
-		defer cancel()
-		ctx, upstreamProto = contextWithupstreamProtocolResult(ctx)
-		startTime = time.Now()
-		rm, t, err = u.upstreamClient.exchange(ctx, upstream.String(), reqUp)
-	}()
+	startTime := time.Now()
+	rm, _, err := u.upstreamClient.exchange(ctx, upstream.String(), r)
 
 	if err != nil {
-		return u.handleUpstreamError(err, upstream, startTime)
+		// A parent cancellation (e.g., another race won and the coordinator
+		// cancelled the losers) is not an upstream failure. Check both the
+		// error chain and the parent context: a transport may surface the
+		// cancellation as a read/deadline error rather than context.Canceled.
+		if errors.Is(err, context.Canceled) || errors.Is(parentCtx.Err(), context.Canceled) {
+			return raceResult{}, &upstreamFailure{upstream: upstream, reason: "canceled"}
+		}
+		failure := u.handleUpstreamError(err, upstream, startTime)
+		u.markUpstreamFail(upstream, failure.reason)
+		return raceResult{}, failure
 	}
 
 	if rm == nil || !rm.Response {
-		return &upstreamFailure{upstream: upstream, reason: "no response"}
+		u.markUpstreamFail(upstream, "no response")
+		return raceResult{}, &upstreamFailure{upstream: upstream, reason: "no response"}
+	}
+
+	proto := ""
+	if upstreamProto != nil {
+		proto = upstreamProto.protocol
 	}
 
 	if rm.Rcode == dns.RcodeServerFailure || rm.Rcode == dns.RcodeRefused {
 		if code, ok := nonRetryableEDE(rm); ok {
-			resutil.SetMeta(w, "ede", edeName(code))
 			if !hadEdns {
 				stripOPT(rm)
 			}
-			u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, upstreamProto, logger)
-			return nil
+			u.markUpstreamOk(upstream)
+			return raceResult{msg: rm, upstream: upstream, protocol: proto, ede: edeName(code)}, nil
 		}
-		return &upstreamFailure{upstream: upstream, reason: dns.RcodeToString[rm.Rcode]}
+		reason := dns.RcodeToString[rm.Rcode]
+		u.markUpstreamFail(upstream, reason)
+		return raceResult{}, &upstreamFailure{upstream: upstream, reason: reason}
 	}
 
 	if !hadEdns {
 		stripOPT(rm)
 	}
-	u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, upstreamProto, logger)
-	return nil
+
+	u.markUpstreamOk(upstream)
+	return raceResult{msg: rm, upstream: upstream, protocol: proto}, nil
+}
+
+// healthEntry returns the mutable health record for addr, lazily creating
+// the map and the entry. Caller must hold u.healthMu.
+func (u *upstreamResolverBase) healthEntry(addr netip.AddrPort) *UpstreamHealth {
+	if u.health == nil {
+		u.health = make(map[netip.AddrPort]*UpstreamHealth)
+	}
+	h := u.health[addr]
+	if h == nil {
+		h = &UpstreamHealth{}
+		u.health[addr] = h
+	}
+	return h
+}
+
+func (u *upstreamResolverBase) markUpstreamOk(addr netip.AddrPort) {
+	u.healthMu.Lock()
+	defer u.healthMu.Unlock()
+	h := u.healthEntry(addr)
+	h.LastOk = time.Now()
+	h.LastFail = time.Time{}
+	h.LastErr = ""
+}
+
+func (u *upstreamResolverBase) markUpstreamFail(addr netip.AddrPort, reason string) {
+	u.healthMu.Lock()
+	defer u.healthMu.Unlock()
+	h := u.healthEntry(addr)
+	h.LastFail = time.Now()
+	h.LastErr = reason
+}
+
+// UpstreamHealth returns a snapshot of per-upstream query outcomes.
+func (u *upstreamResolverBase) UpstreamHealth() map[netip.AddrPort]UpstreamHealth {
+	u.healthMu.RLock()
+	defer u.healthMu.RUnlock()
+	out := make(map[netip.AddrPort]UpstreamHealth, len(u.health))
+	for k, v := range u.health {
+		out[k] = *v
+	}
+	return out
 }
 
 // upstreamUDPSize returns the EDNS0 UDP buffer size we advertise to upstreams,
@@ -358,12 +549,23 @@ 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, upstreamProto *upstreamProtocolResult, logger *log.Entry) bool {
-	u.successCount.Add(1)
+func (u *upstreamResolverBase) debugUpstreamTimeout(upstream netip.AddrPort) string {
+	if u.statusRecorder == nil {
+		return ""
+	}
 
+	peerInfo := findPeerForIP(upstream.Addr(), u.statusRecorder)
+	if peerInfo == nil {
+		return ""
+	}
+
+	return fmt.Sprintf("(routes through NetBird peer %s)", FormatPeerStatus(peerInfo))
+}
+
+func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dns.Msg, upstream netip.AddrPort, domain string, proto string, logger *log.Entry) {
 	resutil.SetMeta(w, "upstream", upstream.String())
-	if upstreamProto != nil && upstreamProto.protocol != "" {
-		resutil.SetMeta(w, "upstream_protocol", upstreamProto.protocol)
+	if proto != "" {
+		resutil.SetMeta(w, "upstream_protocol", proto)
 	}
 
 	// Clear Zero bit from external responses to prevent upstream servers from
@@ -372,14 +574,11 @@ func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dn
 
 	if err := w.WriteMsg(rm); err != nil {
 		logger.Errorf("failed to write DNS response for question domain=%s: %s", domain, err)
-		return true
 	}
-
-	return true
 }
 
 func (u *upstreamResolverBase) logUpstreamFailures(domain string, failures []upstreamFailure, succeeded bool, logger *log.Entry) {
-	totalUpstreams := len(u.upstreamServers)
+	totalUpstreams := len(u.flatUpstreams())
 	failedCount := len(failures)
 	failureSummary := formatFailures(failures)
 
@@ -434,119 +633,6 @@ func edeName(code uint16) string {
 	return fmt.Sprintf("EDE %d", code)
 }
 
-// ProbeAvailability tests all upstream servers simultaneously and
-// disables the resolver if none work
-func (u *upstreamResolverBase) ProbeAvailability(ctx context.Context) {
-	u.mutex.Lock()
-	defer u.mutex.Unlock()
-
-	// avoid probe if upstreams could resolve at least one query
-	if u.successCount.Load() > 0 {
-		return
-	}
-
-	var success bool
-	var mu sync.Mutex
-	var wg sync.WaitGroup
-
-	var errs *multierror.Error
-	for _, upstream := range u.upstreamServers {
-		wg.Add(1)
-		go func(upstream netip.AddrPort) {
-			defer wg.Done()
-			err := u.testNameserver(u.ctx, ctx, upstream, 500*time.Millisecond)
-			if err != nil {
-				mu.Lock()
-				errs = multierror.Append(errs, err)
-				mu.Unlock()
-				log.Warnf("probing upstream nameserver %s: %s", upstream, err)
-				return
-			}
-
-			mu.Lock()
-			success = true
-			mu.Unlock()
-		}(upstream)
-	}
-
-	wg.Wait()
-
-	select {
-	case <-ctx.Done():
-		return
-	case <-u.ctx.Done():
-		return
-	default:
-	}
-
-	// didn't find a working upstream server, let's disable and try later
-	if !success {
-		u.disable(errs.ErrorOrNil())
-
-		if u.statusRecorder == nil {
-			return
-		}
-
-		u.statusRecorder.PublishEvent(
-			proto.SystemEvent_WARNING,
-			proto.SystemEvent_DNS,
-			"All upstream servers failed (probe failed)",
-			"Unable to reach one or more DNS servers. This might affect your ability to connect to some services.",
-			map[string]string{"upstreams": u.upstreamServersString()},
-		)
-	}
-}
-
-// waitUntilResponse retries, in an exponential interval, querying the upstream servers until it gets a positive response
-func (u *upstreamResolverBase) waitUntilResponse() {
-	exponentialBackOff := &backoff.ExponentialBackOff{
-		InitialInterval:     500 * time.Millisecond,
-		RandomizationFactor: 0.5,
-		Multiplier:          1.1,
-		MaxInterval:         u.reactivatePeriod,
-		MaxElapsedTime:      0,
-		Stop:                backoff.Stop,
-		Clock:               backoff.SystemClock,
-	}
-
-	operation := func() error {
-		select {
-		case <-u.ctx.Done():
-			return backoff.Permanent(fmt.Errorf("exiting upstream retry loop for upstreams %s: parent context has been canceled", u.upstreamServersString()))
-		default:
-		}
-
-		for _, upstream := range u.upstreamServers {
-			if err := u.testNameserver(u.ctx, nil, upstream, probeTimeout); err != nil {
-				log.Tracef("upstream check for %s: %s", upstream, err)
-			} else {
-				// at least one upstream server is available, stop probing
-				return nil
-			}
-		}
-
-		log.Tracef("checking connectivity with upstreams %s failed. Retrying in %s", u.upstreamServersString(), exponentialBackOff.NextBackOff())
-		return fmt.Errorf("upstream check call error")
-	}
-
-	err := backoff.Retry(operation, backoff.WithContext(exponentialBackOff, u.ctx))
-	if err != nil {
-		if errors.Is(err, context.Canceled) {
-			log.Debugf("upstream retry loop exited for upstreams %s", u.upstreamServersString())
-		} else {
-			log.Warnf("upstream retry loop exited for upstreams %s: %v", u.upstreamServersString(), err)
-		}
-		return
-	}
-
-	log.Infof("upstreams %s are responsive again. Adding them back to system", u.upstreamServersString())
-	u.successCount.Add(1)
-	u.reactivate()
-	u.mutex.Lock()
-	u.disabled = false
-	u.mutex.Unlock()
-}
-
 // isTimeout returns true if the given error is a network timeout error.
 //
 // Copied from k8s.io/apimachinery/pkg/util/net.IsTimeout
@@ -558,45 +644,6 @@ func isTimeout(err error) bool {
 	return false
 }
 
-func (u *upstreamResolverBase) disable(err error) {
-	if u.disabled {
-		return
-	}
-
-	log.Warnf("Upstream resolving is Disabled for %v", reactivatePeriod)
-	u.successCount.Store(0)
-	u.deactivate(err)
-	u.disabled = true
-	u.wg.Add(1)
-	go func() {
-		defer u.wg.Done()
-		u.waitUntilResponse()
-	}()
-}
-
-func (u *upstreamResolverBase) upstreamServersString() string {
-	var servers []string
-	for _, server := range u.upstreamServers {
-		servers = append(servers, server.String())
-	}
-	return strings.Join(servers, ", ")
-}
-
-func (u *upstreamResolverBase) testNameserver(baseCtx context.Context, externalCtx context.Context, server netip.AddrPort, timeout time.Duration) error {
-	mergedCtx, cancel := context.WithTimeout(baseCtx, timeout)
-	defer cancel()
-
-	if externalCtx != nil {
-		stop2 := context.AfterFunc(externalCtx, cancel)
-		defer stop2()
-	}
-
-	r := new(dns.Msg).SetQuestion(testRecord, dns.TypeSOA)
-
-	_, _, err := u.upstreamClient.exchange(mergedCtx, server.String(), r)
-	return err
-}
-
 // clientUDPMaxSize returns the maximum UDP response size the client accepts.
 func clientUDPMaxSize(r *dns.Msg) int {
 	if opt := r.IsEdns0(); opt != nil {
@@ -608,13 +655,10 @@ func clientUDPMaxSize(r *dns.Msg) int {
 // 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) {
 	// 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)
+		rm, t, err := toTCPClient(client).ExchangeContext(ctx, r, upstream)
 		if err != nil {
 			return nil, t, fmt.Errorf("with tcp: %w", err)
 		}
@@ -634,18 +678,7 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 		opt.SetUDPSize(maxUDPPayload)
 	}
 
-	var (
-		rm  *dns.Msg
-		t   time.Duration
-		err error
-	)
-
-	if ctx == nil {
-		rm, t, err = client.Exchange(r, upstream)
-	} else {
-		rm, t, err = client.ExchangeContext(ctx, r, upstream)
-	}
-
+	rm, t, err := client.ExchangeContext(ctx, r, upstream)
 	if err != nil {
 		return nil, t, fmt.Errorf("with udp: %w", err)
 	}
@@ -659,15 +692,7 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 	// data than the client's buffer, we could truncate locally and skip
 	// the TCP retry.
 
-	tcpClient := *client
-	tcpClient.Net = protoTCP
-
-	if ctx == nil {
-		rm, t, err = tcpClient.Exchange(r, upstream)
-	} else {
-		rm, t, err = tcpClient.ExchangeContext(ctx, r, upstream)
-	}
-
+	rm, t, err = toTCPClient(client).ExchangeContext(ctx, r, upstream)
 	if err != nil {
 		return nil, t, fmt.Errorf("with tcp: %w", err)
 	}
@@ -681,6 +706,25 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 	return rm, t, nil
 }
 
+// toTCPClient returns a copy of c configured for TCP. If c's Dialer has a
+// *net.UDPAddr bound as LocalAddr (iOS does this to keep the source IP on
+// the tunnel interface), it is converted to the equivalent *net.TCPAddr
+// so net.Dialer doesn't reject the TCP dial with "mismatched local
+// address type".
+func toTCPClient(c *dns.Client) *dns.Client {
+	tcp := *c
+	tcp.Net = protoTCP
+	if tcp.Dialer == nil {
+		return &tcp
+	}
+	d := *tcp.Dialer
+	if ua, ok := d.LocalAddr.(*net.UDPAddr); ok {
+		d.LocalAddr = &net.TCPAddr{IP: ua.IP, Port: ua.Port, Zone: ua.Zone}
+	}
+	tcp.Dialer = &d
+	return &tcp
+}
+
 // 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) {
@@ -822,15 +866,36 @@ func findPeerForIP(ip netip.Addr, statusRecorder *peer.Status) *peer.State {
 	return bestMatch
 }
 
-func (u *upstreamResolverBase) debugUpstreamTimeout(upstream netip.AddrPort) string {
-	if u.statusRecorder == nil {
-		return ""
+// haMapRouteCount returns the total number of routes across all HA
+// groups in the map. route.HAMap is keyed by HAUniqueID with slices of
+// routes per key, so len(hm) is the number of HA groups, not routes.
+func haMapRouteCount(hm route.HAMap) int {
+	total := 0
+	for _, routes := range hm {
+		total += len(routes)
 	}
-
-	peerInfo := findPeerForIP(upstream.Addr(), u.statusRecorder)
-	if peerInfo == nil {
-		return ""
-	}
-
-	return fmt.Sprintf("(routes through NetBird peer %s)", FormatPeerStatus(peerInfo))
+	return total
+}
+
+// haMapContains checks whether ip is covered by any concrete prefix in
+// the HA map. haveDynamic is reported separately: dynamic (domain-based)
+// routes carry a placeholder Network that can't be prefix-checked, so we
+// can't know at this point whether ip is reached through one. Callers
+// decide how to interpret the unknown: health projection treats it as
+// "possibly routed" to avoid emitting false-positive warnings during
+// startup, while iOS dial selection requires a concrete match before
+// binding to the tunnel.
+func haMapContains(hm route.HAMap, ip netip.Addr) (matched, haveDynamic bool) {
+	for _, routes := range hm {
+		for _, r := range routes {
+			if r.IsDynamic() {
+				haveDynamic = true
+				continue
+			}
+			if r.Network.Contains(ip) {
+				return true, haveDynamic
+			}
+		}
+	}
+	return false, haveDynamic
 }

client/internal/dns/upstream_android.go

@@ -11,6 +11,7 @@ import (
 
 	"github.com/netbirdio/netbird/client/internal/peer"
 	nbnet "github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 type upstreamResolver struct {
@@ -26,9 +27,9 @@ func newUpstreamResolver(
 	_ WGIface,
 	statusRecorder *peer.Status,
 	hostsDNSHolder *hostsDNSHolder,
-	domain string,
+	d domain.Domain,
 ) (*upstreamResolver, error) {
-	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
+	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, d)
 	c := &upstreamResolver{
 		upstreamResolverBase: upstreamResolverBase,
 		hostsDNSHolder:       hostsDNSHolder,

client/internal/dns/upstream_general.go

@@ -12,6 +12,7 @@ import (
 	"golang.zx2c4.com/wireguard/tun/netstack"
 
 	"github.com/netbirdio/netbird/client/internal/peer"
+	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 type upstreamResolver struct {
@@ -24,9 +25,9 @@ func newUpstreamResolver(
 	wgIface WGIface,
 	statusRecorder *peer.Status,
 	_ *hostsDNSHolder,
-	domain string,
+	d domain.Domain,
 ) (*upstreamResolver, error) {
-	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
+	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, d)
 	nonIOS := &upstreamResolver{
 		upstreamResolverBase: upstreamResolverBase,
 		nsNet:                wgIface.GetNet(),

client/internal/dns/upstream_ios.go

@@ -15,6 +15,7 @@ import (
 	"golang.org/x/sys/unix"
 
 	"github.com/netbirdio/netbird/client/internal/peer"
+	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 type upstreamResolverIOS struct {
@@ -27,9 +28,9 @@ func newUpstreamResolver(
 	wgIface WGIface,
 	statusRecorder *peer.Status,
 	_ *hostsDNSHolder,
-	domain string,
+	d domain.Domain,
 ) (*upstreamResolverIOS, error) {
-	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
+	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, d)
 
 	ios := &upstreamResolverIOS{
 		upstreamResolverBase: upstreamResolverBase,
@@ -62,9 +63,16 @@ func (u *upstreamResolverIOS) exchange(ctx context.Context, upstream string, r *
 		upstreamIP = upstreamIP.Unmap()
 	}
 	addr := u.wgIface.Address()
+	var routed bool
+	if u.selectedRoutes != nil {
+		// Only a concrete prefix match binds to the tunnel: dialing
+		// through a private client for an upstream we can't prove is
+		// routed would break public resolvers.
+		routed, _ = haMapContains(u.selectedRoutes(), upstreamIP)
+	}
 	needsPrivate := addr.Network.Contains(upstreamIP) ||
 		addr.IPv6Net.Contains(upstreamIP) ||
-		(u.routeMatch != nil && u.routeMatch(upstreamIP))
+		routed
 	if needsPrivate {
 		log.Debugf("using private client to query %s via upstream %s", r.Question[0].Name, upstream)
 		client, err = GetClientPrivate(u.wgIface, upstreamIP, timeout)
@@ -73,8 +81,7 @@ func (u *upstreamResolverIOS) exchange(ctx context.Context, upstream string, r *
 		}
 	}
 
-	// Cannot use client.ExchangeContext because it overwrites our Dialer
-	return ExchangeWithFallback(nil, client, r, upstream)
+	return ExchangeWithFallback(ctx, client, r, upstream)
 }
 
 // GetClientPrivate returns a new DNS client bound to the local IP of the Netbird interface.

client/internal/dns/upstream_test.go

@@ -6,6 +6,7 @@ import (
 	"net"
 	"net/netip"
 	"strings"
+	"sync/atomic"
 	"testing"
 	"time"
 
@@ -73,7 +74,7 @@ func TestUpstreamResolver_ServeDNS(t *testing.T) {
 					servers = append(servers, netip.AddrPortFrom(addrPort.Addr().Unmap(), addrPort.Port()))
 				}
 			}
-			resolver.upstreamServers = servers
+			resolver.addRace(servers)
 			resolver.upstreamTimeout = testCase.timeout
 			if testCase.cancelCTX {
 				cancel()
@@ -132,20 +133,10 @@ func (m *mockNetstackProvider) GetInterfaceGUIDString() (string, error) {
 	return "", nil
 }
 
-type mockUpstreamResolver struct {
-	r   *dns.Msg
-	rtt time.Duration
-	err error
-}
-
-// exchange mock implementation of exchange from upstreamResolver
-func (c mockUpstreamResolver) exchange(_ context.Context, _ string, _ *dns.Msg) (*dns.Msg, time.Duration, error) {
-	return c.r, c.rtt, c.err
-}
-
 type mockUpstreamResponse struct {
-	msg *dns.Msg
-	err error
+	msg   *dns.Msg
+	err   error
+	delay time.Duration
 }
 
 type mockUpstreamResolverPerServer struct {
@@ -153,63 +144,19 @@ type mockUpstreamResolverPerServer struct {
 	rtt       time.Duration
 }
 
-func (c mockUpstreamResolverPerServer) exchange(_ context.Context, upstream string, _ *dns.Msg) (*dns.Msg, time.Duration, error) {
-	if r, ok := c.responses[upstream]; ok {
-		return r.msg, c.rtt, r.err
+func (c mockUpstreamResolverPerServer) exchange(ctx context.Context, upstream string, _ *dns.Msg) (*dns.Msg, time.Duration, error) {
+	r, ok := c.responses[upstream]
+	if !ok {
+		return nil, c.rtt, fmt.Errorf("no mock response for %s", upstream)
 	}
-	return nil, c.rtt, fmt.Errorf("no mock response for %s", upstream)
-}
-
-func TestUpstreamResolver_DeactivationReactivation(t *testing.T) {
-	mockClient := &mockUpstreamResolver{
-		err: dns.ErrTime,
-		r:   new(dns.Msg),
-		rtt: time.Millisecond,
-	}
-
-	resolver := &upstreamResolverBase{
-		ctx:              context.TODO(),
-		upstreamClient:   mockClient,
-		upstreamTimeout:  UpstreamTimeout,
-		reactivatePeriod: time.Microsecond * 100,
-	}
-	addrPort, _ := netip.ParseAddrPort("0.0.0.0:1") // Use valid port for parsing, test will still fail on connection
-	resolver.upstreamServers = []netip.AddrPort{netip.AddrPortFrom(addrPort.Addr().Unmap(), addrPort.Port())}
-
-	failed := false
-	resolver.deactivate = func(error) {
-		failed = true
-		// After deactivation, make the mock client work again
-		mockClient.err = nil
-	}
-
-	reactivated := false
-	resolver.reactivate = func() {
-		reactivated = true
-	}
-
-	resolver.ProbeAvailability(context.TODO())
-
-	if !failed {
-		t.Errorf("expected that resolving was deactivated")
-		return
-	}
-
-	if !resolver.disabled {
-		t.Errorf("resolver should be Disabled")
-		return
-	}
-
-	time.Sleep(time.Millisecond * 200)
-
-	if !reactivated {
-		t.Errorf("expected that resolving was reactivated")
-		return
-	}
-
-	if resolver.disabled {
-		t.Errorf("should be enabled")
+	if r.delay > 0 {
+		select {
+		case <-time.After(r.delay):
+		case <-ctx.Done():
+			return nil, c.rtt, ctx.Err()
+		}
 	}
+	return r.msg, c.rtt, r.err
 }
 
 func TestUpstreamResolver_Failover(t *testing.T) {
@@ -339,9 +286,9 @@ func TestUpstreamResolver_Failover(t *testing.T) {
 			resolver := &upstreamResolverBase{
 				ctx:             ctx,
 				upstreamClient:  trackingClient,
-				upstreamServers: []netip.AddrPort{upstream1, upstream2},
 				upstreamTimeout: UpstreamTimeout,
 			}
+			resolver.addRace([]netip.AddrPort{upstream1, upstream2})
 
 			var responseMSG *dns.Msg
 			responseWriter := &test.MockResponseWriter{
@@ -421,9 +368,9 @@ func TestUpstreamResolver_SingleUpstreamFailure(t *testing.T) {
 	resolver := &upstreamResolverBase{
 		ctx:             ctx,
 		upstreamClient:  mockClient,
-		upstreamServers: []netip.AddrPort{upstream},
 		upstreamTimeout: UpstreamTimeout,
 	}
+	resolver.addRace([]netip.AddrPort{upstream})
 
 	var responseMSG *dns.Msg
 	responseWriter := &test.MockResponseWriter{
@@ -440,6 +387,136 @@ func TestUpstreamResolver_SingleUpstreamFailure(t *testing.T) {
 	assert.Equal(t, dns.RcodeServerFailure, responseMSG.Rcode, "single upstream SERVFAIL should return SERVFAIL")
 }
 
+// TestUpstreamResolver_RaceAcrossGroups covers two nameserver groups
+// configured for the same domain, with one broken group. The merge+race
+// path should answer as fast as the working group and not pay the timeout
+// of the broken one on every query.
+func TestUpstreamResolver_RaceAcrossGroups(t *testing.T) {
+	broken := netip.MustParseAddrPort("192.0.2.1:53")
+	working := netip.MustParseAddrPort("192.0.2.2:53")
+	successAnswer := "192.0.2.100"
+	timeoutErr := &net.OpError{Op: "read", Err: fmt.Errorf("i/o timeout")}
+
+	mockClient := &mockUpstreamResolverPerServer{
+		responses: map[string]mockUpstreamResponse{
+			// Force the broken upstream to only unblock via timeout /
+			// cancellation so the assertion below can't pass if races
+			// were run serially.
+			broken.String():  {err: timeoutErr, delay: 500 * time.Millisecond},
+			working.String(): {msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+		},
+		rtt: time.Millisecond,
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	resolver := &upstreamResolverBase{
+		ctx:             ctx,
+		upstreamClient:  mockClient,
+		upstreamTimeout: 250 * time.Millisecond,
+	}
+	resolver.addRace([]netip.AddrPort{broken})
+	resolver.addRace([]netip.AddrPort{working})
+
+	var responseMSG *dns.Msg
+	responseWriter := &test.MockResponseWriter{
+		WriteMsgFunc: func(m *dns.Msg) error {
+			responseMSG = m
+			return nil
+		},
+	}
+
+	inputMSG := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+	start := time.Now()
+	resolver.ServeDNS(responseWriter, inputMSG)
+	elapsed := time.Since(start)
+
+	require.NotNil(t, responseMSG, "should write a response")
+	assert.Equal(t, dns.RcodeSuccess, responseMSG.Rcode)
+	require.NotEmpty(t, responseMSG.Answer)
+	assert.Contains(t, responseMSG.Answer[0].String(), successAnswer)
+	// Working group answers in a single RTT; the broken group's
+	// timeout (100ms) must not block the response.
+	assert.Less(t, elapsed, 100*time.Millisecond, "race must not wait for broken group's timeout")
+}
+
+// TestUpstreamResolver_AllGroupsFail checks that when every group fails the
+// resolver returns SERVFAIL rather than leaking a partial response.
+func TestUpstreamResolver_AllGroupsFail(t *testing.T) {
+	a := netip.MustParseAddrPort("192.0.2.1:53")
+	b := netip.MustParseAddrPort("192.0.2.2:53")
+
+	mockClient := &mockUpstreamResolverPerServer{
+		responses: map[string]mockUpstreamResponse{
+			a.String(): {msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			b.String(): {msg: buildMockResponse(dns.RcodeServerFailure, "")},
+		},
+		rtt: time.Millisecond,
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	resolver := &upstreamResolverBase{
+		ctx:             ctx,
+		upstreamClient:  mockClient,
+		upstreamTimeout: UpstreamTimeout,
+	}
+	resolver.addRace([]netip.AddrPort{a})
+	resolver.addRace([]netip.AddrPort{b})
+
+	var responseMSG *dns.Msg
+	responseWriter := &test.MockResponseWriter{
+		WriteMsgFunc: func(m *dns.Msg) error {
+			responseMSG = m
+			return nil
+		},
+	}
+
+	resolver.ServeDNS(responseWriter, new(dns.Msg).SetQuestion("example.com.", dns.TypeA))
+	require.NotNil(t, responseMSG)
+	assert.Equal(t, dns.RcodeServerFailure, responseMSG.Rcode)
+}
+
+// TestUpstreamResolver_HealthTracking verifies that query-path results are
+// recorded into per-upstream health, which is what projects back to
+// NSGroupState for status reporting.
+func TestUpstreamResolver_HealthTracking(t *testing.T) {
+	ok := netip.MustParseAddrPort("192.0.2.10:53")
+	bad := netip.MustParseAddrPort("192.0.2.11:53")
+
+	mockClient := &mockUpstreamResolverPerServer{
+		responses: map[string]mockUpstreamResponse{
+			ok.String():  {msg: buildMockResponse(dns.RcodeSuccess, "192.0.2.100")},
+			bad.String(): {msg: buildMockResponse(dns.RcodeServerFailure, "")},
+		},
+		rtt: time.Millisecond,
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	resolver := &upstreamResolverBase{
+		ctx:             ctx,
+		upstreamClient:  mockClient,
+		upstreamTimeout: UpstreamTimeout,
+	}
+	resolver.addRace([]netip.AddrPort{ok, bad})
+
+	responseWriter := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { return nil }}
+	resolver.ServeDNS(responseWriter, new(dns.Msg).SetQuestion("example.com.", dns.TypeA))
+
+	health := resolver.UpstreamHealth()
+	require.Contains(t, health, ok)
+	assert.False(t, health[ok].LastOk.IsZero(), "ok upstream should have LastOk set")
+	assert.Empty(t, health[ok].LastErr)
+
+	// bad upstream was never tried because ok answered first; its health
+	// should remain unset.
+	assert.NotContains(t, health, bad, "sibling upstream should not be queried when primary answers")
+}
+
 func TestFormatFailures(t *testing.T) {
 	testCases := []struct {
 		name     string
@@ -665,10 +742,10 @@ 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
+	var receivedUDPSize atomic.Uint32
 	udpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
 		if opt := r.IsEdns0(); opt != nil {
-			receivedUDPSize = opt.UDPSize()
+			receivedUDPSize.Store(uint32(opt.UDPSize()))
 		}
 		m := new(dns.Msg)
 		m.SetReply(r)
@@ -699,7 +776,7 @@ func TestExchangeWithFallback_EDNS0Capped(t *testing.T) {
 	require.NotNil(t, rm)
 
 	expectedMax := uint16(currentMTU - ipUDPHeaderSize)
-	assert.Equal(t, expectedMax, receivedUDPSize,
+	assert.Equal(t, expectedMax, uint16(receivedUDPSize.Load()),
 		"upstream should see capped EDNS0, not the client's 4096")
 }
 
@@ -874,7 +951,7 @@ func TestUpstreamResolver_NonRetryableEDEShortCircuits(t *testing.T) {
 	resolver := &upstreamResolverBase{
 		ctx:             ctx,
 		upstreamClient:  tracking,
-		upstreamServers: []netip.AddrPort{upstream1, upstream2},
+		upstreamServers: []upstreamRace{{upstream1, upstream2}},
 		upstreamTimeout: UpstreamTimeout,
 	}
 

client/internal/engine.go

@@ -512,16 +512,7 @@ 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.GetSelectedClientRoutes() {
-			for _, r := range routes {
-				if r.Network.Contains(ip) {
-					return true
-				}
-			}
-		}
-		return false
-	})
+	e.dnsServer.SetRouteSources(e.routeManager.GetSelectedClientRoutes, e.routeManager.GetActiveClientRoutes)
 
 	if err = e.wgInterfaceCreate(); err != nil {
 		log.Errorf("failed creating tunnel interface %s: [%s]", e.config.WgIfaceName, err.Error())
@@ -1386,9 +1377,6 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 
 	e.networkSerial = serial
 
-	// Test received (upstream) servers for availability right away instead of upon usage.
-	// If no server of a server group responds this will disable the respective handler and retry later.
-	go e.dnsServer.ProbeAvailability()
 	return nil
 }
 
@@ -1932,7 +1920,7 @@ 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.mobileDep.HostDNSAddresses, e.statusRecorder, e.config.DisableDNS)
+		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.statusRecorder, e.config.DisableDNS)
 		return dnsServer, nil
 
 	default:

client/internal/routemanager/manager.go

@@ -53,6 +53,7 @@ type Manager interface {
 	GetRouteSelector() *routeselector.RouteSelector
 	GetClientRoutes() route.HAMap
 	GetSelectedClientRoutes() route.HAMap
+	GetActiveClientRoutes() route.HAMap
 	GetClientRoutesWithNetID() map[route.NetID][]*route.Route
 	SetRouteChangeListener(listener listener.NetworkChangeListener)
 	InitialRouteRange() []string
@@ -485,6 +486,39 @@ func (m *DefaultManager) GetSelectedClientRoutes() route.HAMap {
 	return m.routeSelector.FilterSelectedExitNodes(maps.Clone(m.clientRoutes))
 }
 
+// GetActiveClientRoutes returns the subset of selected client routes
+// that are currently reachable: the route's peer is Connected and is
+// the one actively carrying the route (not just an HA sibling).
+func (m *DefaultManager) GetActiveClientRoutes() route.HAMap {
+	m.mux.Lock()
+	selected := m.routeSelector.FilterSelectedExitNodes(maps.Clone(m.clientRoutes))
+	recorder := m.statusRecorder
+	m.mux.Unlock()
+
+	if recorder == nil {
+		return selected
+	}
+
+	out := make(route.HAMap, len(selected))
+	for id, routes := range selected {
+		for _, r := range routes {
+			st, err := recorder.GetPeer(r.Peer)
+			if err != nil {
+				continue
+			}
+			if st.ConnStatus != peer.StatusConnected {
+				continue
+			}
+			if _, hasRoute := st.GetRoutes()[r.Network.String()]; !hasRoute {
+				continue
+			}
+			out[id] = routes
+			break
+		}
+	}
+	return out
+}
+
 // 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

@@ -19,6 +19,7 @@ type MockManager struct {
 	GetRouteSelectorFunc         func() *routeselector.RouteSelector
 	GetClientRoutesFunc          func() route.HAMap
 	GetSelectedClientRoutesFunc  func() route.HAMap
+	GetActiveClientRoutesFunc    func() route.HAMap
 	GetClientRoutesWithNetIDFunc func() map[route.NetID][]*route.Route
 	StopFunc                     func(manager *statemanager.Manager)
 }
@@ -78,6 +79,14 @@ func (m *MockManager) GetSelectedClientRoutes() route.HAMap {
 	return nil
 }
 
+// GetActiveClientRoutes mock implementation of GetActiveClientRoutes from the Manager interface
+func (m *MockManager) GetActiveClientRoutes() route.HAMap {
+	if m.GetActiveClientRoutesFunc != nil {
+		return m.GetActiveClientRoutesFunc()
+	}
+	return nil
+}
+
 // GetClientRoutesWithNetID mock implementation of GetClientRoutesWithNetID from Manager interface
 func (m *MockManager) GetClientRoutesWithNetID() map[route.NetID][]*route.Route {
 	if m.GetClientRoutesWithNetIDFunc != nil {

client/ios/NetBirdSDK/client.go

@@ -162,11 +162,7 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	cfg.WgIface = interfaceName
 
 	c.connectClient = internal.NewConnectClient(ctx, cfg, c.recorder)
-	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)
+	return c.connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile)
 }
 
 // Stop the internal client and free the resources