Refactor

client/cmd/debug.go

@@ -19,7 +19,6 @@ import (
 	"github.com/netbirdio/netbird/client/server"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 	"github.com/netbirdio/netbird/upload-server/types"
-	"github.com/netbirdio/netbird/version"
 )
 
 const errCloseConnection = "Failed to close connection: %v"
@@ -101,7 +100,6 @@ func debugBundle(cmd *cobra.Command, _ []string) error {
 		Anonymize:    anonymizeFlag,
 		SystemInfo:   systemInfoFlag,
 		LogFileCount: logFileCount,
-		CliVersion:   version.NetbirdVersion(),
 	}
 	if uploadBundleFlag {
 		request.UploadURL = uploadBundleURLFlag
@@ -300,7 +298,6 @@ func runForDuration(cmd *cobra.Command, args []string) error {
 		Anonymize:    anonymizeFlag,
 		SystemInfo:   systemInfoFlag,
 		LogFileCount: logFileCount,
-		CliVersion:   version.NetbirdVersion(),
 	}
 	if uploadBundleFlag {
 		request.UploadURL = uploadBundleURLFlag
@@ -435,7 +432,6 @@ func generateDebugBundle(config *profilemanager.Config, recorder *peer.Status, c
 			SyncResponse:   syncResponse,
 			LogPath:        logFilePath,
 			CPUProfile:     nil,
-			DaemonVersion:  version.NetbirdVersion(), // acting as daemon
 		},
 		debug.BundleConfig{
 			IncludeSystemInfo: true,

client/cmd/service_controller.go

@@ -102,7 +102,7 @@ func (p *program) Stop(srv service.Service) error {
 }
 
 // Common setup for service control commands
-func setupServiceControlCommand(cmd *cobra.Command, ctx context.Context, cancel context.CancelFunc, consoleLog bool) (service.Service, error) {
+func setupServiceControlCommand(cmd *cobra.Command, ctx context.Context, cancel context.CancelFunc) (service.Service, error) {
 	// rootCmd env vars are already applied by PersistentPreRunE.
 	SetFlagsFromEnvVars(serviceCmd)
 
@@ -112,14 +112,8 @@ func setupServiceControlCommand(cmd *cobra.Command, ctx context.Context, cancel
 		return nil, err
 	}
 
-	if consoleLog {
-		if err := util.InitLog(logLevel, util.LogConsole); err != nil {
-			return nil, fmt.Errorf("init log: %w", err)
-		}
-	} else {
-		if err := util.InitLog(logLevel, logFiles...); err != nil {
-			return nil, fmt.Errorf("init log: %w", err)
-		}
+	if err := util.InitLog(logLevel, logFiles...); err != nil {
+		return nil, fmt.Errorf("init log: %w", err)
 	}
 
 	cfg, err := newSVCConfig()
@@ -144,7 +138,7 @@ var runCmd = &cobra.Command{
 		SetupCloseHandler(ctx, cancel)
 		SetupDebugHandler(ctx, nil, nil, nil, util.FindFirstLogPath(logFiles))
 
-		s, err := setupServiceControlCommand(cmd, ctx, cancel, false)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel)
 		if err != nil {
 			return err
 		}
@@ -158,7 +152,7 @@ var startCmd = &cobra.Command{
 	Short: "starts NetBird service",
 	RunE: func(cmd *cobra.Command, args []string) error {
 		ctx, cancel := context.WithCancel(cmd.Context())
-		s, err := setupServiceControlCommand(cmd, ctx, cancel, false)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel)
 		if err != nil {
 			return err
 		}
@@ -176,7 +170,7 @@ var stopCmd = &cobra.Command{
 	Short: "stops NetBird service",
 	RunE: func(cmd *cobra.Command, args []string) error {
 		ctx, cancel := context.WithCancel(cmd.Context())
-		s, err := setupServiceControlCommand(cmd, ctx, cancel, false)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel)
 		if err != nil {
 			return err
 		}
@@ -194,7 +188,7 @@ var restartCmd = &cobra.Command{
 	Short: "restarts NetBird service",
 	RunE: func(cmd *cobra.Command, args []string) error {
 		ctx, cancel := context.WithCancel(cmd.Context())
-		s, err := setupServiceControlCommand(cmd, ctx, cancel, false)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel)
 		if err != nil {
 			return err
 		}
@@ -212,7 +206,7 @@ var svcStatusCmd = &cobra.Command{
 	Short: "shows NetBird service status",
 	RunE: func(cmd *cobra.Command, args []string) error {
 		ctx, cancel := context.WithCancel(cmd.Context())
-		s, err := setupServiceControlCommand(cmd, ctx, cancel, true)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel)
 		if err != nil {
 			return err
 		}

client/cmd/status.go

@@ -43,16 +43,16 @@ func init() {
 	ipsFilterMap = make(map[string]struct{})
 	prefixNamesFilterMap = make(map[string]struct{})
 	statusCmd.PersistentFlags().BoolVarP(&detailFlag, "detail", "d", false, "display detailed status information in human-readable format")
-	statusCmd.PersistentFlags().BoolVarP(&jsonFlag, "json", "j", false, "display detailed status information in json format")
-	statusCmd.PersistentFlags().BoolVarP(&yamlFlag, "yaml", "y", false, "display detailed status information in yaml format")
-	statusCmd.PersistentFlags().BoolVarP(&ipv4Flag, "ipv4", "4", false, "display only NetBird IPv4 of this peer, e.g., --ipv4 will output 100.64.0.33")
-	statusCmd.PersistentFlags().BoolVarP(&ipv6Flag, "ipv6", "6", false, "display only NetBird IPv6 of this peer")
+	statusCmd.PersistentFlags().BoolVar(&jsonFlag, "json", false, "display detailed status information in json format")
+	statusCmd.PersistentFlags().BoolVar(&yamlFlag, "yaml", false, "display detailed status information in yaml format")
+	statusCmd.PersistentFlags().BoolVar(&ipv4Flag, "ipv4", false, "display only NetBird IPv4 of this peer, e.g., --ipv4 will output 100.64.0.33")
+	statusCmd.PersistentFlags().BoolVar(&ipv6Flag, "ipv6", false, "display only NetBird IPv6 of this peer")
 	statusCmd.MarkFlagsMutuallyExclusive("detail", "json", "yaml", "ipv4", "ipv6")
-	statusCmd.PersistentFlags().StringSliceVarP(&ipsFilter, "filter-by-ips", "I", []string{}, "filters the detailed output by a list of one or more IPs (v4 or v6), e.g., --filter-by-ips 100.64.0.100,fd00::1")
-	statusCmd.PersistentFlags().StringSliceVarP(&prefixNamesFilter, "filter-by-names", "N", []string{}, "filters the detailed output by a list of one or more peer FQDN or hostnames, e.g., --filter-by-names peer-a,peer-b.netbird.cloud")
-	statusCmd.PersistentFlags().StringVarP(&statusFilter, "filter-by-status", "S", "", "filters the detailed output by connection status(idle|connecting|connected), e.g., --filter-by-status connected")
-	statusCmd.PersistentFlags().StringVarP(&connectionTypeFilter, "filter-by-connection-type", "T", "", "filters the detailed output by connection type (P2P|Relayed), e.g., --filter-by-connection-type P2P")
-	statusCmd.PersistentFlags().StringVarP(&checkFlag, "check", "C", "", "run a health check and exit with code 0 on success, 1 on failure (live|ready|startup)")
+	statusCmd.PersistentFlags().StringSliceVar(&ipsFilter, "filter-by-ips", []string{}, "filters the detailed output by a list of one or more IPs (v4 or v6), e.g., --filter-by-ips 100.64.0.100,fd00::1")
+	statusCmd.PersistentFlags().StringSliceVar(&prefixNamesFilter, "filter-by-names", []string{}, "filters the detailed output by a list of one or more peer FQDN or hostnames, e.g., --filter-by-names peer-a,peer-b.netbird.cloud")
+	statusCmd.PersistentFlags().StringVar(&statusFilter, "filter-by-status", "", "filters the detailed output by connection status(idle|connecting|connected), e.g., --filter-by-status connected")
+	statusCmd.PersistentFlags().StringVar(&connectionTypeFilter, "filter-by-connection-type", "", "filters the detailed output by connection type (P2P|Relayed), e.g., --filter-by-connection-type P2P")
+	statusCmd.PersistentFlags().StringVar(&checkFlag, "check", "", "run a health check and exit with code 0 on success, 1 on failure (live|ready|startup)")
 }
 
 func statusFunc(cmd *cobra.Command, args []string) error {

client/embed/embed.go

@@ -336,7 +336,7 @@ func (c *Client) ListenTCP(address string) (net.Listener, error) {
 	if err != nil {
 		return nil, fmt.Errorf("split host port: %w", err)
 	}
-	listenAddr := net.JoinHostPort(addr.String(), port)
+	listenAddr := fmt.Sprintf("%s:%s", addr, port)
 
 	tcpAddr, err := net.ResolveTCPAddr("tcp", listenAddr)
 	if err != nil {
@@ -357,7 +357,7 @@ func (c *Client) ListenUDP(address string) (net.PacketConn, error) {
 	if err != nil {
 		return nil, fmt.Errorf("split host port: %w", err)
 	}
-	listenAddr := net.JoinHostPort(addr.String(), port)
+	listenAddr := fmt.Sprintf("%s:%s", addr, port)
 
 	udpAddr, err := net.ResolveUDPAddr("udp", listenAddr)
 	if err != nil {

client/installer.nsis

@@ -260,23 +260,15 @@ WriteRegStr ${REG_ROOT} "${UNINSTALL_PATH}"  "Publisher" "${COMP_NAME}"
 
 WriteRegStr ${REG_ROOT} "${UI_REG_APP_PATH}" "" "$INSTDIR\${UI_APP_EXE}"
 
-; Drop Run, App Paths and Uninstall entries left in the 32-bit registry view
-; or HKCU by legacy installers.
-DetailPrint "Cleaning legacy 32-bit / HKCU entries..."
-DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}"
-SetRegView 32
-DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
-DeleteRegKey HKLM "${REG_APP_PATH}"
-DeleteRegKey HKLM "${UI_REG_APP_PATH}"
-DeleteRegKey HKLM "${UNINSTALL_PATH}"
-SetRegView 64
-
+; Create autostart registry entry based on checkbox
 DetailPrint "Autostart enabled: $AutostartEnabled"
 ${If} $AutostartEnabled == "1"
     WriteRegStr HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}" '"$INSTDIR\${UI_APP_EXE}.exe"'
     DetailPrint "Added autostart registry entry: $INSTDIR\${UI_APP_EXE}.exe"
 ${Else}
     DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+    ; Legacy: pre-HKLM installs wrote to HKCU; clean that up too.
+    DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}"
     DetailPrint "Autostart not enabled by user"
 ${EndIf}
 
@@ -307,16 +299,11 @@ ExecWait '"$INSTDIR\${MAIN_APP_EXE}" service uninstall'
 DetailPrint "Terminating Netbird UI process..."
 ExecWait `taskkill /im ${UI_APP_EXE}.exe /f`
 
-; Remove autostart entries from every view a previous installer may have used.
+; Remove autostart registry entry
 DetailPrint "Removing autostart registry entry if exists..."
 DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+; Legacy: pre-HKLM installs wrote to HKCU; clean that up too.
 DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}"
-SetRegView 32
-DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
-DeleteRegKey HKLM "${REG_APP_PATH}"
-DeleteRegKey HKLM "${UI_REG_APP_PATH}"
-DeleteRegKey HKLM "${UNINSTALL_PATH}"
-SetRegView 64
 
 ; Handle data deletion based on checkbox
 DetailPrint "Checking if user requested data deletion..."

client/internal/connect.go

@@ -116,6 +116,7 @@ func (c *ConnectClient) RunOniOS(
 	fileDescriptor int32,
 	networkChangeListener listener.NetworkChangeListener,
 	dnsManager dns.IosDnsManager,
+	dnsAddresses []netip.AddrPort,
 	stateFilePath string,
 ) error {
 	// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
@@ -125,6 +126,7 @@ func (c *ConnectClient) RunOniOS(
 		FileDescriptor:        fileDescriptor,
 		NetworkChangeListener: networkChangeListener,
 		DnsManager:            dnsManager,
+		HostDNSAddresses:      dnsAddresses,
 		StateFilePath:         stateFilePath,
 	}
 	return c.run(mobileDependency, nil, "")

client/internal/debug/debug.go

@@ -45,11 +45,8 @@ netbird.out: Most recent, anonymized stdout log file of the NetBird client.
 routes.txt: Detailed system routing table in tabular format including destination, gateway, interface, metrics, and protocol information, if --system-info flag was provided.
 interfaces.txt: Anonymized network interface information, if --system-info flag was provided.
 ip_rules.txt: Detailed IP routing rules in tabular format including priority, source, destination, interfaces, table, and action information (Linux only), if --system-info flag was provided.
-iptables.txt: Anonymized iptables (IPv4) rules with packet counters, if --system-info flag was provided.
-ip6tables.txt: Anonymized ip6tables (IPv6) rules with packet counters, if --system-info flag was provided.
-ipset.txt: Anonymized ipset list output, if --system-info flag was provided.
-nftables.txt: Anonymized nftables rules with packet counters across all families (ip, ip6, inet, etc.), if --system-info flag was provided.
-sysctls.txt: Forwarding, reverse-path filter, source-validation, and conntrack accounting sysctl values that the NetBird client may read or modify, if --system-info flag was provided (Linux only).
+iptables.txt: Anonymized iptables rules with packet counters, if --system-info flag was provided.
+nftables.txt: Anonymized nftables rules with packet counters, if --system-info flag was provided.
 resolv.conf: DNS resolver configuration from /etc/resolv.conf (Unix systems only), if --system-info flag was provided.
 scutil_dns.txt: DNS configuration from scutil --dns (macOS only), if --system-info flag was provided.
 resolved_domains.txt: Anonymized resolved domain IP addresses from the status recorder.
@@ -168,33 +165,22 @@ The config.txt file contains anonymized configuration information of the NetBird
 Other non-sensitive configuration options are included without anonymization.
 
 Firewall Rules (Linux only)
-The bundle includes the following firewall-related files:
+The bundle includes two separate firewall rule files:
 
 iptables.txt:
-- IPv4 iptables ruleset with packet counters using 'iptables-save' and 'iptables -v -n -L'
+- Complete iptables ruleset with packet counters using 'iptables -v -n -L'
 - Includes all tables (filter, nat, mangle, raw, security)
 - Shows packet and byte counters for each rule
 - All IP addresses are anonymized
 - Chain names, table names, and other non-sensitive information remain unchanged
 
-ip6tables.txt:
-- IPv6 ip6tables ruleset with packet counters using 'ip6tables-save' and 'ip6tables -v -n -L'
-- Same table coverage and anonymization as iptables.txt
-- Omitted when ip6tables is not installed or no IPv6 rules are present
-
-ipset.txt:
-- Output of 'ipset list' (family-agnostic)
-- IP addresses are anonymized; set names and types remain unchanged
-
 nftables.txt:
-- Complete nftables ruleset across all families (ip, ip6, inet, arp, bridge, netdev) via 'nft -a list ruleset'
+- Complete nftables ruleset obtained via 'nft -a list ruleset'
 - Includes rule handle numbers and packet counters
-- All IP addresses are anonymized; chain/table names remain unchanged
-
-sysctls.txt:
-- Forwarding (IPv4 + IPv6, global and per-interface), reverse-path filter, source-validation, conntrack accounting, and TCP-related sysctls that netbird may read or modify
-- Per-interface keys are enumerated from /proc/sys/net/ipv{4,6}/conf
-- Interface names anonymized when --anonymize is set
+- All tables, chains, and rules are included
+- Shows packet and byte counters for each rule
+- All IP addresses are anonymized
+- Chain names, table names, and other non-sensitive information remain unchanged
 
 IP Rules (Linux only)
 The ip_rules.txt file contains detailed IP routing rule information:
@@ -254,8 +240,6 @@ type BundleGenerator struct {
 	capturePath    string
 	refreshStatus  func() // Optional callback to refresh status before bundle generation
 	clientMetrics  MetricsExporter
-	daemonVersion  string
-	cliVersion     string
 
 	anonymize         bool
 	includeSystemInfo bool
@@ -280,8 +264,6 @@ type GeneratorDependencies struct {
 	CapturePath    string
 	RefreshStatus  func()
 	ClientMetrics  MetricsExporter
-	DaemonVersion  string
-	CliVersion     string
 }
 
 func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGenerator {
@@ -303,8 +285,6 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
 		capturePath:    deps.CapturePath,
 		refreshStatus:  deps.RefreshStatus,
 		clientMetrics:  deps.ClientMetrics,
-		daemonVersion:  deps.DaemonVersion,
-		cliVersion:     deps.CliVersion,
 
 		anonymize:         cfg.Anonymize,
 		includeSystemInfo: cfg.IncludeSystemInfo,
@@ -432,10 +412,6 @@ func (g *BundleGenerator) addSystemInfo() {
 		log.Errorf("failed to add firewall rules to debug bundle: %v", err)
 	}
 
-	if err := g.addSysctls(); err != nil {
-		log.Errorf("failed to add sysctls to debug bundle: %v", err)
-	}
-
 	if err := g.addDNSInfo(); err != nil {
 		log.Errorf("failed to add DNS info to debug bundle: %v", err)
 	}
@@ -465,11 +441,9 @@ func (g *BundleGenerator) addStatus() error {
 		protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
 		protoFullStatus.Events = g.statusRecorder.GetEventHistory()
 		overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, nbstatus.ConvertOptions{
-			Anonymize:     g.anonymize,
-			ProfileName:   profName,
-			DaemonVersion: g.daemonVersion,
+			Anonymize:   g.anonymize,
+			ProfileName: profName,
 		})
-		overview.CliVersion = g.cliVersion
 		statusOutput := overview.FullDetailSummary()
 
 		statusReader := strings.NewReader(statusOutput)
@@ -1047,8 +1021,7 @@ func (g *BundleGenerator) addRotatedLogFiles(logDir string) {
 		return
 	}
 
-	// This regex will match both logs rotated by us and logrotate on linux
-	pattern := filepath.Join(logDir, "client*.log.*")
+	pattern := filepath.Join(logDir, "client-*.log.gz")
 	files, err := filepath.Glob(pattern)
 	if err != nil {
 		log.Warnf("failed to glob rotated logs: %v", err)
@@ -1081,12 +1054,7 @@ func (g *BundleGenerator) addRotatedLogFiles(logDir string) {
 
 	for i := 0; i < maxFiles; i++ {
 		name := filepath.Base(files[i])
-		if strings.HasSuffix(name, ".gz") {
-			err = g.addSingleLogFileGz(files[i], name)
-		} else {
-			err = g.addSingleLogfile(files[i], name)
-		}
-		if err != nil {
+		if err := g.addSingleLogFileGz(files[i], name); err != nil {
 			log.Warnf("failed to add rotated log %s: %v", name, err)
 		}
 	}

client/internal/debug/debug_linux.go

@@ -124,18 +124,15 @@ func getSystemdLogs(serviceName string) (string, error) {
 // addFirewallRules collects and adds firewall rules to the archive
 func (g *BundleGenerator) addFirewallRules() error {
 	log.Info("Collecting firewall rules")
-	g.addIPTablesRulesToBundle("iptables-save", "iptables", "iptables.txt")
-	g.addIPTablesRulesToBundle("ip6tables-save", "ip6tables", "ip6tables.txt")
-
-	ipsetOutput, err := collectIPSets()
+	iptablesRules, err := collectIPTablesRules()
 	if err != nil {
-		log.Warnf("Failed to collect ipset information: %v", err)
+		log.Warnf("Failed to collect iptables rules: %v", err)
 	} else {
 		if g.anonymize {
-			ipsetOutput = g.anonymizer.AnonymizeString(ipsetOutput)
+			iptablesRules = g.anonymizer.AnonymizeString(iptablesRules)
 		}
-		if err := g.addFileToZip(strings.NewReader(ipsetOutput), "ipset.txt"); err != nil {
-			log.Warnf("Failed to add ipset output to bundle: %v", err)
+		if err := g.addFileToZip(strings.NewReader(iptablesRules), "iptables.txt"); err != nil {
+			log.Warnf("Failed to add iptables rules to bundle: %v", err)
 		}
 	}
 
@@ -154,65 +151,44 @@ func (g *BundleGenerator) addFirewallRules() error {
 	return nil
 }
 
-// addIPTablesRulesToBundle collects iptables/ip6tables rules and writes them to the bundle.
-func (g *BundleGenerator) addIPTablesRulesToBundle(saveBin, listBin, filename string) {
-	rules, err := collectIPTablesRules(saveBin, listBin)
-	if err != nil {
-		log.Warnf("Failed to collect %s rules: %v", listBin, err)
-		return
-	}
-	if g.anonymize {
-		rules = g.anonymizer.AnonymizeString(rules)
-	}
-	if err := g.addFileToZip(strings.NewReader(rules), filename); err != nil {
-		log.Warnf("Failed to add %s rules to bundle: %v", listBin, err)
-	}
-}
-
-// collectIPTablesRules collects rules using both <saveBin> and verbose listing via <listBin>.
-// Returns an error when neither command produced any output (e.g. the binary is missing),
-// so the caller can skip writing an empty file.
-func collectIPTablesRules(saveBin, listBin string) (string, error) {
+// collectIPTablesRules collects rules using both iptables-save and verbose listing
+func collectIPTablesRules() (string, error) {
 	var builder strings.Builder
-	var collected bool
-	var firstErr error
 
-	saveOutput, err := runCommand(saveBin)
-	switch {
-	case err != nil:
-		firstErr = err
-		log.Warnf("Failed to collect %s output: %v", saveBin, err)
-	case strings.TrimSpace(saveOutput) == "":
-		log.Debugf("%s produced no output, skipping", saveBin)
-	default:
-		builder.WriteString(fmt.Sprintf("=== %s output ===\n", saveBin))
+	saveOutput, err := collectIPTablesSave()
+	if err != nil {
+		log.Warnf("Failed to collect iptables rules using iptables-save: %v", err)
+	} else {
+		builder.WriteString("=== iptables-save output ===\n")
 		builder.WriteString(saveOutput)
 		builder.WriteString("\n")
-		collected = true
 	}
 
-	listHeader := fmt.Sprintf("=== %s -v -n -L output ===\n", listBin)
-	builder.WriteString(listHeader)
+	ipsetOutput, err := collectIPSets()
+	if err != nil {
+		log.Warnf("Failed to collect ipset information: %v", err)
+	} else {
+		builder.WriteString("=== ipset list output ===\n")
+		builder.WriteString(ipsetOutput)
+		builder.WriteString("\n")
+	}
+
+	builder.WriteString("=== iptables -v -n -L output ===\n")
 
 	tables := []string{"filter", "nat", "mangle", "raw", "security"}
+
 	for _, table := range tables {
-		stats, err := runCommand(listBin, "-v", "-n", "-L", "-t", table)
+		builder.WriteString(fmt.Sprintf("*%s\n", table))
+
+		stats, err := getTableStatistics(table)
 		if err != nil {
-			if firstErr == nil {
-				firstErr = err
-			}
-			log.Warnf("Failed to get %s statistics for table %s: %v", listBin, table, err)
+			log.Warnf("Failed to get statistics for table %s: %v", table, err)
 			continue
 		}
-		builder.WriteString(fmt.Sprintf("*%s\n", table))
 		builder.WriteString(stats)
 		builder.WriteString("\n")
-		collected = true
 	}
 
-	if !collected {
-		return "", fmt.Errorf("collect %s rules: %w", listBin, firstErr)
-	}
 	return builder.String(), nil
 }
 
@@ -238,15 +214,34 @@ func collectIPSets() (string, error) {
 	return ipsets, nil
 }
 
-// runCommand executes a command and returns its stdout, wrapping stderr in the error on failure.
-func runCommand(name string, args ...string) (string, error) {
-	cmd := exec.Command(name, args...)
+// collectIPTablesSave uses iptables-save to get rule definitions
+func collectIPTablesSave() (string, error) {
+	cmd := exec.Command("iptables-save")
 	var stdout, stderr bytes.Buffer
 	cmd.Stdout = &stdout
 	cmd.Stderr = &stderr
 
 	if err := cmd.Run(); err != nil {
-		return "", fmt.Errorf("execute %s: %w (stderr: %s)", name, err, stderr.String())
+		return "", fmt.Errorf("execute iptables-save: %w (stderr: %s)", err, stderr.String())
+	}
+
+	rules := stdout.String()
+	if strings.TrimSpace(rules) == "" {
+		return "", fmt.Errorf("no iptables rules found")
+	}
+
+	return rules, nil
+}
+
+// getTableStatistics gets verbose statistics for an entire table using iptables command
+func getTableStatistics(table string) (string, error) {
+	cmd := exec.Command("iptables", "-v", "-n", "-L", "-t", table)
+	var stdout, stderr bytes.Buffer
+	cmd.Stdout = &stdout
+	cmd.Stderr = &stderr
+
+	if err := cmd.Run(); err != nil {
+		return "", fmt.Errorf("execute iptables -v -n -L: %w (stderr: %s)", err, stderr.String())
 	}
 
 	return stdout.String(), nil
@@ -809,91 +804,3 @@ func formatSetKeyType(keyType nftables.SetDatatype) string {
 		return fmt.Sprintf("type-%v", keyType)
 	}
 }
-
-// addSysctls collects forwarding and netbird-managed sysctl values and writes them to the bundle.
-func (g *BundleGenerator) addSysctls() error {
-	log.Info("Collecting sysctls")
-	content := collectSysctls()
-	if g.anonymize {
-		content = g.anonymizer.AnonymizeString(content)
-	}
-	if err := g.addFileToZip(strings.NewReader(content), "sysctls.txt"); err != nil {
-		return fmt.Errorf("add sysctls to bundle: %w", err)
-	}
-	return nil
-}
-
-// collectSysctls reads every sysctl that the netbird client may modify, plus
-// global IPv4/IPv6 forwarding, and returns a formatted dump grouped by topic.
-// Per-interface values are enumerated by listing /proc/sys/net/ipv{4,6}/conf.
-func collectSysctls() string {
-	var builder strings.Builder
-
-	writeSysctlGroup(&builder, "forwarding", []string{
-		"net.ipv4.ip_forward",
-		"net.ipv6.conf.all.forwarding",
-		"net.ipv6.conf.default.forwarding",
-	})
-	writeSysctlGroup(&builder, "ipv4 per-interface forwarding", listInterfaceSysctls("ipv4", "forwarding"))
-	writeSysctlGroup(&builder, "ipv6 per-interface forwarding", listInterfaceSysctls("ipv6", "forwarding"))
-	writeSysctlGroup(&builder, "rp_filter", append(
-		[]string{"net.ipv4.conf.all.rp_filter", "net.ipv4.conf.default.rp_filter"},
-		listInterfaceSysctls("ipv4", "rp_filter")...,
-	))
-	writeSysctlGroup(&builder, "src_valid_mark", append(
-		[]string{"net.ipv4.conf.all.src_valid_mark", "net.ipv4.conf.default.src_valid_mark"},
-		listInterfaceSysctls("ipv4", "src_valid_mark")...,
-	))
-	writeSysctlGroup(&builder, "conntrack", []string{
-		"net.netfilter.nf_conntrack_acct",
-		"net.netfilter.nf_conntrack_tcp_loose",
-	})
-	writeSysctlGroup(&builder, "tcp", []string{
-		"net.ipv4.tcp_tw_reuse",
-	})
-
-	return builder.String()
-}
-
-func writeSysctlGroup(builder *strings.Builder, title string, keys []string) {
-	builder.WriteString(fmt.Sprintf("=== %s ===\n", title))
-	for _, key := range keys {
-		value, err := readSysctl(key)
-		if err != nil {
-			builder.WriteString(fmt.Sprintf("%s = <error: %v>\n", key, err))
-			continue
-		}
-		builder.WriteString(fmt.Sprintf("%s = %s\n", key, value))
-	}
-	builder.WriteString("\n")
-}
-
-// listInterfaceSysctls returns net.ipvX.conf.<iface>.<leaf> keys for every
-// interface present in /proc/sys/net/ipvX/conf, skipping "all" and "default"
-// (callers add those explicitly so they appear first).
-func listInterfaceSysctls(family, leaf string) []string {
-	dir := fmt.Sprintf("/proc/sys/net/%s/conf", family)
-	entries, err := os.ReadDir(dir)
-	if err != nil {
-		return nil
-	}
-	var keys []string
-	for _, e := range entries {
-		name := e.Name()
-		if name == "all" || name == "default" {
-			continue
-		}
-		keys = append(keys, fmt.Sprintf("net.%s.conf.%s.%s", family, name, leaf))
-	}
-	sort.Strings(keys)
-	return keys
-}
-
-func readSysctl(key string) (string, error) {
-	path := fmt.Sprintf("/proc/sys/%s", strings.ReplaceAll(key, ".", "/"))
-	value, err := os.ReadFile(path)
-	if err != nil {
-		return "", err
-	}
-	return strings.TrimSpace(string(value)), nil
-}

client/internal/debug/debug_logfiles_test.go

@@ -1,103 +0,0 @@
-package debug
-
-import (
-	"archive/zip"
-	"bytes"
-	"compress/gzip"
-	"io"
-	"os"
-	"path/filepath"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/require"
-)
-
-// TestAddRotatedLogFiles_PicksUpAllVariants asserts that the rotated-log
-// glob picks up logs rotated by timberjack (gzipped) and by logrotate (plain
-// and gzipped), and skips unrelated files.
-func TestAddRotatedLogFiles_PicksUpAllVariants(t *testing.T) {
-	dir := t.TempDir()
-
-	writeFile(t, filepath.Join(dir, "client.log"), "active log\n")
-	writeFile(t, filepath.Join(dir, "other.log"), "unrelated\n")
-
-	timberjackRotated := "client-2026-05-21T10-30-45.000.log.gz"
-	writeGzFile(t, filepath.Join(dir, timberjackRotated), "timberjack rotated content\n")
-
-	logrotatePlain := "client.log.1"
-	writeFile(t, filepath.Join(dir, logrotatePlain), "logrotate plain content\n")
-
-	logrotateGz := "client.log.2.gz"
-	writeGzFile(t, filepath.Join(dir, logrotateGz), "logrotate gz content\n")
-
-	names := runAddRotatedLogFiles(t, dir, 10)
-
-	require.Contains(t, names, timberjackRotated, "timberjack rotated file should be in bundle")
-	require.Contains(t, names, logrotatePlain, "logrotate plain rotated file should be in bundle")
-	require.Contains(t, names, logrotateGz, "logrotate gzipped rotated file should be in bundle")
-	require.NotContains(t, names, "client.log", "active log should not be added by addRotatedLogFiles")
-	require.NotContains(t, names, "other.log", "unrelated files should not be in bundle")
-}
-
-// TestAddRotatedLogFiles_RespectsLogFileCount asserts that only the newest
-// logFileCount rotated files are bundled, ordered by mtime.
-func TestAddRotatedLogFiles_RespectsLogFileCount(t *testing.T) {
-	dir := t.TempDir()
-
-	oldest := filepath.Join(dir, "client.log.3")
-	middle := filepath.Join(dir, "client.log.2")
-	newest := filepath.Join(dir, "client.log.1")
-	writeFile(t, oldest, "old\n")
-	writeFile(t, middle, "mid\n")
-	writeFile(t, newest, "new\n")
-
-	now := time.Now()
-	require.NoError(t, os.Chtimes(oldest, now.Add(-2*time.Hour), now.Add(-2*time.Hour)))
-	require.NoError(t, os.Chtimes(middle, now.Add(-1*time.Hour), now.Add(-1*time.Hour)))
-	require.NoError(t, os.Chtimes(newest, now, now))
-
-	names := runAddRotatedLogFiles(t, dir, 2)
-
-	require.Contains(t, names, "client.log.1")
-	require.Contains(t, names, "client.log.2")
-	require.NotContains(t, names, "client.log.3", "oldest file should be dropped when logFileCount=2")
-}
-
-// runAddRotatedLogFiles calls addRotatedLogFiles against a fresh in-memory
-// zip writer and returns the set of entry names that ended up in the archive.
-func runAddRotatedLogFiles(t *testing.T, dir string, logFileCount uint32) map[string]struct{} {
-	t.Helper()
-
-	var buf bytes.Buffer
-	g := &BundleGenerator{
-		archive:      zip.NewWriter(&buf),
-		logFileCount: logFileCount,
-	}
-	g.addRotatedLogFiles(dir)
-	require.NoError(t, g.archive.Close())
-
-	zr, err := zip.NewReader(bytes.NewReader(buf.Bytes()), int64(buf.Len()))
-	require.NoError(t, err)
-
-	names := make(map[string]struct{}, len(zr.File))
-	for _, f := range zr.File {
-		names[f.Name] = struct{}{}
-	}
-	return names
-}
-
-func writeFile(t *testing.T, path, content string) {
-	t.Helper()
-	require.NoError(t, os.WriteFile(path, []byte(content), 0o644))
-}
-
-func writeGzFile(t *testing.T, path, content string) {
-	t.Helper()
-	var buf bytes.Buffer
-	gw := gzip.NewWriter(&buf)
-	_, err := io.WriteString(gw, content)
-	require.NoError(t, err)
-	require.NoError(t, gw.Close())
-	require.NoError(t, os.WriteFile(path, buf.Bytes(), 0o644))
-}

client/internal/debug/debug_nonlinux.go

@@ -17,8 +17,3 @@ func (g *BundleGenerator) addIPRules() error {
 	// IP rules are only supported on Linux
 	return nil
 }
-
-func (g *BundleGenerator) addSysctls() error {
-	// Sysctl collection is only supported on Linux
-	return nil
-}

client/internal/dns/host.go

@@ -16,10 +16,6 @@ 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 {
@@ -135,11 +131,3 @@ 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

@@ -1,20 +1,14 @@
 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(holder *hostsDNSHolder) (*androidHostManager, error) {
-	return &androidHostManager{holder: holder}, nil
+func newHostManager() (*androidHostManager, error) {
+	return &androidHostManager{}, nil
 }
 
 func (a androidHostManager) applyDNSConfig(HostDNSConfig, *statemanager.Manager) error {
@@ -32,12 +26,3 @@ 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

@@ -3,7 +3,6 @@ package dns
 import (
 	"encoding/json"
 	"fmt"
-	"net/netip"
 
 	log "github.com/sirupsen/logrus"
 
@@ -21,14 +20,6 @@ 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

@@ -7,7 +7,6 @@ import (
 	"io"
 	"net/netip"
 	"os/exec"
-	"slices"
 	"strings"
 	"syscall"
 	"time"
@@ -45,11 +44,9 @@ const (
 
 	nrptMaxDomainsPerRule = 50
 
-	interfaceConfigPath           = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`
-	interfaceConfigPathV6         = `SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces`
-	interfaceConfigNameServerKey  = "NameServer"
-	interfaceConfigDhcpNameSrvKey = "DhcpNameServer"
-	interfaceConfigSearchListKey  = "SearchList"
+	interfaceConfigPath          = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`
+	interfaceConfigNameServerKey = "NameServer"
+	interfaceConfigSearchListKey = "SearchList"
 
 	// Network interface DNS registration settings
 	disableDynamicUpdateKey           = "DisableDynamicUpdate"
@@ -70,11 +67,10 @@ const (
 )
 
 type registryConfigurator struct {
-	guid            string
-	routingAll      bool
-	gpo             bool
-	nrptEntryCount  int
-	origNameservers []netip.Addr
+	guid           string
+	routingAll     bool
+	gpo            bool
+	nrptEntryCount int
 }
 
 func newHostManager(wgInterface WGIface) (*registryConfigurator, error) {
@@ -98,17 +94,6 @@ func newHostManager(wgInterface WGIface) (*registryConfigurator, error) {
 		gpo:  useGPO,
 	}
 
-	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)
 	}
@@ -116,98 +101,6 @@ 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
 }

client/internal/dns/hosts_dns_holder.go

@@ -25,7 +25,6 @@ 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

@@ -76,6 +76,8 @@ 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

@@ -9,7 +9,6 @@ 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"
 )
 
@@ -71,6 +70,10 @@ 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)
@@ -82,8 +85,8 @@ func (m *MockServer) PopulateManagementDomain(mgmtURL *url.URL) error {
 	return nil
 }
 
-// SetRouteSources mock implementation of SetRouteSources from Server interface
-func (m *MockServer) SetRouteSources(selected, active func() route.HAMap) {
+// SetRouteChecker mock implementation of SetRouteChecker from Server interface
+func (m *MockServer) SetRouteChecker(func(netip.Addr) bool) {
 	// Mock implementation - no-op
 }
 

client/internal/dns/network_manager_unix.go

@@ -8,7 +8,6 @@ import (
 	"errors"
 	"fmt"
 	"net/netip"
-	"slices"
 	"strings"
 	"time"
 
@@ -33,15 +32,6 @@ 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"
@@ -61,10 +51,9 @@ var supportedNetworkManagerVersionConstraints = []string{
 }
 
 type networkManagerDbusConfigurator struct {
-	dbusLinkObject  dbus.ObjectPath
-	routingAll      bool
-	ifaceName       string
-	origNameservers []netip.Addr
+	dbusLinkObject dbus.ObjectPath
+	routingAll     bool
+	ifaceName      string
 }
 
 // the types below are based on dbus specification, each field is mapped to a dbus type
@@ -103,200 +92,10 @@ func newNetworkManagerDbusConfigurator(wgInterface string) (*networkManagerDbusC
 
 	log.Debugf("got network manager dbus Link Object: %s from net interface %s", s, wgInterface)
 
-	c := &networkManagerDbusConfigurator{
+	return &networkManagerDbusConfigurator{
 		dbusLinkObject: dbus.ObjectPath(s),
 		ifaceName:      wgInterface,
-	}
-
-	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)
+	}, nil
 }
 
 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(s.hostsDNSHolder)
+	return newHostManager()
 }

client/internal/dns/server_test.go

@@ -6,7 +6,7 @@ import (
 	"net"
 	"net/netip"
 	"os"
-	"runtime"
+	"strings"
 	"testing"
 	"time"
 
@@ -15,7 +15,6 @@ 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"
 
@@ -32,10 +31,8 @@ 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"
 )
 
@@ -104,17 +101,16 @@ func init() {
 	formatter.SetTextFormatter(log.StandardLogger())
 }
 
-func generateDummyHandler(d string, servers []nbdns.NameServer) *upstreamResolverBase {
+func generateDummyHandler(domain string, servers []nbdns.NameServer) *upstreamResolverBase {
 	var srvs []netip.AddrPort
 	for _, srv := range servers {
 		srvs = append(srvs, srv.AddrPort())
 	}
-	u := &upstreamResolverBase{
-		domain: domain.Domain(d),
-		cancel: func() {},
+	return &upstreamResolverBase{
+		domain:          domain,
+		upstreamServers: srvs,
+		cancel:          func() {},
 	}
-	u.addRace(srvs)
-	return u
 }
 
 func TestUpdateDNSServer(t *testing.T) {
@@ -657,8 +653,74 @@ 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")
@@ -686,7 +748,6 @@ 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")
@@ -780,7 +841,6 @@ 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")
@@ -853,18 +913,6 @@ 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")
@@ -1017,6 +1065,7 @@ 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{}
@@ -2036,598 +2085,6 @@ 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)
@@ -2726,18 +2183,17 @@ func TestDNSLoopPrevention(t *testing.T) {
 
 			if tt.expectedHandlers > 0 {
 				handler := muxUpdates[0].handler.(*upstreamResolver)
-				flat := handler.flatUpstreams()
-				assert.Len(t, flat, len(tt.expectedServers))
+				assert.Len(t, handler.upstreamServers, len(tt.expectedServers))
 
 				if tt.shouldFilterOwnIP {
-					for _, upstream := range flat {
+					for _, upstream := range handler.upstreamServers {
 						assert.NotEqual(t, dnsServerIP, upstream.Addr())
 					}
 				}
 
 				for _, expected := range tt.expectedServers {
 					found := false
-					for _, upstream := range flat {
+					for _, upstream := range handler.upstreamServers {
 						if upstream.Addr() == expected {
 							found = true
 							break

client/internal/dns/systemd_linux.go

@@ -8,7 +8,6 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
-	"slices"
 	"time"
 
 	"github.com/godbus/dbus/v5"
@@ -41,17 +40,10 @@ const (
 )
 
 type systemdDbusConfigurator struct {
-	dbusLinkObject  dbus.ObjectPath
-	ifaceName       string
-	wgIndex         int
-	origNameservers []netip.Addr
+	dbusLinkObject dbus.ObjectPath
+	ifaceName      string
 }
 
-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
@@ -87,145 +79,10 @@ 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)
 
-	c := &systemdDbusConfigurator{
+	return &systemdDbusConfigurator{
 		dbusLinkObject: dbus.ObjectPath(s),
 		ifaceName:      wgInterface,
-		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)
+	}, nil
 }
 
 func (s *systemdDbusConfigurator) supportCustomPort() bool {

client/internal/dns/upstream.go

@@ -1,32 +1,3 @@
-// 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 (
@@ -40,8 +11,11 @@ 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"
@@ -51,8 +25,7 @@ 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/route"
-	"github.com/netbirdio/netbird/shared/management/domain"
+	"github.com/netbirdio/netbird/client/proto"
 )
 
 var currentMTU uint16 = iface.DefaultMTU
@@ -94,18 +67,16 @@ 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
-
-	// 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 testRecord = "com."
+
 const (
 	protoUDP = "udp"
 	protoTCP = "tcp"
@@ -113,69 +84,6 @@ 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)
@@ -192,8 +100,16 @@ func dnsProtocolFromContext(ctx context.Context) string {
 	return ""
 }
 
-// contextWithUpstreamProtocolResult stores a mutable result holder in the context.
-func contextWithUpstreamProtocolResult(ctx context.Context) (context.Context, *upstreamProtocolResult) {
+type upstreamProtocolKey struct{}
+
+// upstreamProtocolResult holds the protocol used for the upstream exchange.
+// Stored as a pointer in context so the exchange function can set it.
+type upstreamProtocolResult struct {
+	protocol string
+}
+
+// contextWithupstreamProtocolResult stores a mutable result holder in the context.
+func contextWithupstreamProtocolResult(ctx context.Context) (context.Context, *upstreamProtocolResult) {
 	r := &upstreamProtocolResult{}
 	return context.WithValue(ctx, upstreamProtocolKey{}, r), r
 }
@@ -208,37 +124,67 @@ func setUpstreamProtocol(ctx context.Context, protocol string) {
 	}
 }
 
-func newUpstreamResolverBase(ctx context.Context, statusRecorder *peer.Status, d domain.Domain) *upstreamResolverBase {
+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 {
 	ctx, cancel := context.WithCancel(ctx)
 
 	return &upstreamResolverBase{
-		ctx:             ctx,
-		cancel:          cancel,
-		domain:          d,
-		upstreamTimeout: UpstreamTimeout,
-		statusRecorder:  statusRecorder,
+		ctx:              ctx,
+		cancel:           cancel,
+		domain:           domain,
+		upstreamTimeout:  UpstreamTimeout,
+		reactivatePeriod: reactivatePeriod,
+		statusRecorder:   statusRecorder,
 	}
 }
 
 // String returns a string representation of the upstream resolver
 func (u *upstreamResolverBase) String() string {
-	return fmt.Sprintf("Upstream %s", u.flatUpstreams())
+	return fmt.Sprintf("Upstream %s", u.upstreamServers)
 }
 
-// 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.
+// ID returns the unique handler ID
 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.PunycodeString() + ":"))
-	for _, race := range u.upstreamServers {
-		hash.Write([]byte("["))
-		for _, s := range race {
-			hash.Write([]byte(s.String()))
-			hash.Write([]byte("|"))
-		}
-		hash.Write([]byte("]"))
+	hash.Write([]byte(u.domain + ":"))
+	for _, s := range servers {
+		hash.Write([]byte(s.String()))
+		hash.Write([]byte("|"))
 	}
 	return types.HandlerID("upstream-" + hex.EncodeToString(hash.Sum(nil)[:8]))
 }
@@ -248,31 +194,13 @@ func (u *upstreamResolverBase) MatchSubdomains() bool {
 }
 
 func (u *upstreamResolverBase) Stop() {
-	log.Debugf("stopping serving DNS for upstreams %s", u.flatUpstreams())
+	log.Debugf("stopping serving DNS for upstreams %s", u.upstreamServers)
 	u.cancel()
-}
 
-// 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
-}
+	u.mutex.Lock()
+	u.wg.Wait()
+	u.mutex.Unlock()
 
-// 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
@@ -314,201 +242,82 @@ 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) {
-	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)
+	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
+		}
 	}
 
 	var failures []upstreamFailure
-	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
+	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
 		}
 	}
 	return false, failures
 }
 
-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)
+// 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
 
 	// 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.
-	// 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.
+	// 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.
 	hadEdns := r.IsEdns0() != nil
+	reqUp := r
 	if !hadEdns {
-		r.SetEdns0(upstreamUDPSize(), false)
+		reqUp = r.Copy()
+		reqUp.SetEdns0(upstreamUDPSize(), false)
 	}
 
-	startTime := time.Now()
-	rm, _, err := u.upstreamClient.exchange(ctx, upstream.String(), r)
+	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)
+	}()
 
 	if err != nil {
-		// 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
+		return u.handleUpstreamError(err, upstream, startTime)
 	}
 
 	if rm == nil || !rm.Response {
-		u.markUpstreamFail(upstream, "no response")
-		return raceResult{}, &upstreamFailure{upstream: upstream, reason: "no response"}
-	}
-
-	proto := ""
-	if upstreamProto != nil {
-		proto = upstreamProto.protocol
+		return &upstreamFailure{upstream: upstream, reason: "no response"}
 	}
 
 	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.markUpstreamOk(upstream)
-			return raceResult{msg: rm, upstream: upstream, protocol: proto, ede: edeName(code)}, nil
+			u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, upstreamProto, logger)
+			return nil
 		}
-		reason := dns.RcodeToString[rm.Rcode]
-		u.markUpstreamFail(upstream, reason)
-		return raceResult{}, &upstreamFailure{upstream: upstream, reason: reason}
+		return &upstreamFailure{upstream: upstream, reason: dns.RcodeToString[rm.Rcode]}
 	}
 
 	if !hadEdns {
 		stripOPT(rm)
 	}
-
-	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
+	u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, upstreamProto, logger)
+	return nil
 }
 
 // upstreamUDPSize returns the EDNS0 UDP buffer size we advertise to upstreams,
@@ -549,23 +358,12 @@ func (u *upstreamResolverBase) handleUpstreamError(err error, upstream netip.Add
 	return &upstreamFailure{upstream: upstream, reason: reason}
 }
 
-func (u *upstreamResolverBase) debugUpstreamTimeout(upstream netip.AddrPort) string {
-	if u.statusRecorder == nil {
-		return ""
-	}
+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)
 
-	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 proto != "" {
-		resutil.SetMeta(w, "upstream_protocol", proto)
+	if upstreamProto != nil && upstreamProto.protocol != "" {
+		resutil.SetMeta(w, "upstream_protocol", upstreamProto.protocol)
 	}
 
 	// Clear Zero bit from external responses to prevent upstream servers from
@@ -574,11 +372,14 @@ 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.flatUpstreams())
+	totalUpstreams := len(u.upstreamServers)
 	failedCount := len(failures)
 	failureSummary := formatFailures(failures)
 
@@ -633,6 +434,119 @@ 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
@@ -644,6 +558,45 @@ 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 {
@@ -655,10 +608,13 @@ 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 {
-		rm, t, err := toTCPClient(client).ExchangeContext(ctx, r, upstream)
+		tcpClient := *client
+		tcpClient.Net = protoTCP
+		rm, t, err := tcpClient.ExchangeContext(ctx, r, upstream)
 		if err != nil {
 			return nil, t, fmt.Errorf("with tcp: %w", err)
 		}
@@ -678,7 +634,18 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 		opt.SetUDPSize(maxUDPPayload)
 	}
 
-	rm, t, err := client.ExchangeContext(ctx, r, upstream)
+	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)
+	}
+
 	if err != nil {
 		return nil, t, fmt.Errorf("with udp: %w", err)
 	}
@@ -692,7 +659,15 @@ 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.
 
-	rm, t, err = toTCPClient(client).ExchangeContext(ctx, r, upstream)
+	tcpClient := *client
+	tcpClient.Net = protoTCP
+
+	if ctx == nil {
+		rm, t, err = tcpClient.Exchange(r, upstream)
+	} else {
+		rm, t, err = tcpClient.ExchangeContext(ctx, r, upstream)
+	}
+
 	if err != nil {
 		return nil, t, fmt.Errorf("with tcp: %w", err)
 	}
@@ -706,25 +681,6 @@ 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) {
@@ -866,36 +822,15 @@ func findPeerForIP(ip netip.Addr, statusRecorder *peer.Status) *peer.State {
 	return bestMatch
 }
 
-// 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)
+func (u *upstreamResolverBase) debugUpstreamTimeout(upstream netip.AddrPort) string {
+	if u.statusRecorder == nil {
+		return ""
 	}
-	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
-			}
-		}
+	peerInfo := findPeerForIP(upstream.Addr(), u.statusRecorder)
+	if peerInfo == nil {
+		return ""
 	}
-	return false, haveDynamic
+
+	return fmt.Sprintf("(routes through NetBird peer %s)", FormatPeerStatus(peerInfo))
 }

client/internal/dns/upstream_android.go

@@ -11,7 +11,6 @@ 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 {
@@ -27,9 +26,9 @@ func newUpstreamResolver(
 	_ WGIface,
 	statusRecorder *peer.Status,
 	hostsDNSHolder *hostsDNSHolder,
-	d domain.Domain,
+	domain string,
 ) (*upstreamResolver, error) {
-	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, d)
+	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
 	c := &upstreamResolver{
 		upstreamResolverBase: upstreamResolverBase,
 		hostsDNSHolder:       hostsDNSHolder,

client/internal/dns/upstream_general.go

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

client/internal/dns/upstream_ios.go

@@ -15,7 +15,6 @@ import (
 	"golang.org/x/sys/unix"
 
 	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 type upstreamResolverIOS struct {
@@ -28,9 +27,9 @@ func newUpstreamResolver(
 	wgIface WGIface,
 	statusRecorder *peer.Status,
 	_ *hostsDNSHolder,
-	d domain.Domain,
+	domain string,
 ) (*upstreamResolverIOS, error) {
-	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, d)
+	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
 
 	ios := &upstreamResolverIOS{
 		upstreamResolverBase: upstreamResolverBase,
@@ -63,16 +62,9 @@ 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) ||
-		routed
+		(u.routeMatch != nil && u.routeMatch(upstreamIP))
 	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)
@@ -81,7 +73,8 @@ func (u *upstreamResolverIOS) exchange(ctx context.Context, upstream string, r *
 		}
 	}
 
-	return ExchangeWithFallback(ctx, client, r, upstream)
+	// Cannot use client.ExchangeContext because it overwrites our Dialer
+	return ExchangeWithFallback(nil, client, r, upstream)
 }
 
 // GetClientPrivate returns a new DNS client bound to the local IP of the Netbird interface.

client/internal/dns/upstream_test.go

@@ -6,7 +6,6 @@ import (
 	"net"
 	"net/netip"
 	"strings"
-	"sync/atomic"
 	"testing"
 	"time"
 
@@ -74,7 +73,7 @@ func TestUpstreamResolver_ServeDNS(t *testing.T) {
 					servers = append(servers, netip.AddrPortFrom(addrPort.Addr().Unmap(), addrPort.Port()))
 				}
 			}
-			resolver.addRace(servers)
+			resolver.upstreamServers = servers
 			resolver.upstreamTimeout = testCase.timeout
 			if testCase.cancelCTX {
 				cancel()
@@ -133,10 +132,20 @@ 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
-	delay time.Duration
+	msg *dns.Msg
+	err error
 }
 
 type mockUpstreamResolverPerServer struct {
@@ -144,19 +153,63 @@ type mockUpstreamResolverPerServer struct {
 	rtt       time.Duration
 }
 
-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)
+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
 	}
-	if r.delay > 0 {
-		select {
-		case <-time.After(r.delay):
-		case <-ctx.Done():
-			return nil, c.rtt, ctx.Err()
-		}
+	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")
 	}
-	return r.msg, c.rtt, r.err
 }
 
 func TestUpstreamResolver_Failover(t *testing.T) {
@@ -286,9 +339,9 @@ 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{
@@ -368,9 +421,9 @@ 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{
@@ -387,136 +440,6 @@ 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
@@ -742,10 +665,10 @@ 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 atomic.Uint32
+	var receivedUDPSize uint16
 	udpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
 		if opt := r.IsEdns0(); opt != nil {
-			receivedUDPSize.Store(uint32(opt.UDPSize()))
+			receivedUDPSize = opt.UDPSize()
 		}
 		m := new(dns.Msg)
 		m.SetReply(r)
@@ -776,7 +699,7 @@ func TestExchangeWithFallback_EDNS0Capped(t *testing.T) {
 	require.NotNil(t, rm)
 
 	expectedMax := uint16(currentMTU - ipUDPHeaderSize)
-	assert.Equal(t, expectedMax, uint16(receivedUDPSize.Load()),
+	assert.Equal(t, expectedMax, receivedUDPSize,
 		"upstream should see capped EDNS0, not the client's 4096")
 }
 
@@ -951,7 +874,7 @@ func TestUpstreamResolver_NonRetryableEDEShortCircuits(t *testing.T) {
 	resolver := &upstreamResolverBase{
 		ctx:             ctx,
 		upstreamClient:  tracking,
-		upstreamServers: []upstreamRace{{upstream1, upstream2}},
+		upstreamServers: []netip.AddrPort{upstream1, upstream2},
 		upstreamTimeout: UpstreamTimeout,
 	}
 

client/internal/engine.go

@@ -72,7 +72,6 @@ import (
 	sProto "github.com/netbirdio/netbird/shared/signal/proto"
 	"github.com/netbirdio/netbird/util"
 	"github.com/netbirdio/netbird/util/capture"
-	"github.com/netbirdio/netbird/version"
 )
 
 // PeerConnectionTimeoutMax is a timeout of an initial connection attempt to a remote peer.
@@ -513,7 +512,16 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 
 	e.routeManager.SetRouteChangeListener(e.mobileDep.NetworkChangeListener)
 
-	e.dnsServer.SetRouteSources(e.routeManager.GetSelectedClientRoutes, e.routeManager.GetActiveClientRoutes)
+	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
+	})
 
 	if err = e.wgInterfaceCreate(); err != nil {
 		log.Errorf("failed creating tunnel interface %s: [%s]", e.config.WgIfaceName, err.Error())
@@ -1142,7 +1150,6 @@ func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobR
 		LogPath:        e.config.LogPath,
 		TempDir:        e.config.TempDir,
 		ClientMetrics:  e.clientMetrics,
-		DaemonVersion:  version.NetbirdVersion(),
 		RefreshStatus: func() {
 			e.RunHealthProbes(true)
 		},
@@ -1379,6 +1386,9 @@ 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
 }
 
@@ -1922,7 +1932,7 @@ func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
 		return dnsServer, nil
 
 	case "ios":
-		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.statusRecorder, e.config.DisableDNS)
+		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.mobileDep.HostDNSAddresses, e.statusRecorder, e.config.DisableDNS)
 		return dnsServer, nil
 
 	default:

client/internal/routemanager/manager.go

@@ -53,7 +53,6 @@ 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
@@ -486,39 +485,6 @@ 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()
@@ -738,10 +704,7 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 }
 
 func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool {
-	if len(routes) == 0 {
-		return false
-	}
-	return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)
+	return len(routes) > 0 && routes[0].Network.String() == vars.ExitNodeCIDR
 }
 
 func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) {

client/internal/routemanager/mock.go

@@ -19,7 +19,6 @@ 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)
 }
@@ -79,14 +78,6 @@ 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/internal/routeselector/routeselector.go

@@ -4,7 +4,6 @@ import (
 	"encoding/json"
 	"fmt"
 	"slices"
-	"strings"
 	"sync"
 
 	"github.com/hashicorp/go-multierror"
@@ -13,6 +12,10 @@ import (
 	"github.com/netbirdio/netbird/route"
 )
 
+const (
+	exitNodeCIDR = "0.0.0.0/0"
+)
+
 type RouteSelector struct {
 	mu               sync.RWMutex
 	deselectedRoutes map[route.NetID]struct{}
@@ -121,7 +124,13 @@ func (rs *RouteSelector) IsSelected(routeID route.NetID) bool {
 	rs.mu.RLock()
 	defer rs.mu.RUnlock()
 
-	return rs.isSelectedLocked(routeID)
+	if rs.deselectAll {
+		return false
+	}
+
+	_, deselected := rs.deselectedRoutes[routeID]
+	isSelected := !deselected
+	return isSelected
 }
 
 // FilterSelected removes unselected routes from the provided map.
@@ -135,22 +144,23 @@ func (rs *RouteSelector) FilterSelected(routes route.HAMap) route.HAMap {
 
 	filtered := route.HAMap{}
 	for id, rt := range routes {
-		if !rs.isDeselectedLocked(id.NetID()) {
+		netID := id.NetID()
+		_, deselected := rs.deselectedRoutes[netID]
+		if !deselected {
 			filtered[id] = rt
 		}
 	}
 	return filtered
 }
 
-// HasUserSelectionForRoute returns true if the user has explicitly selected or deselected this route.
-// Intended for exit-node code paths: a v6 exit-node pair (e.g. "MyExit-v6") with no explicit state of
-// its own inherits its v4 base's state, so legacy persisted selections that predate v6 pairing
-// transparently apply to the synthesized v6 entry.
+// HasUserSelectionForRoute returns true if the user has explicitly selected or deselected this specific route
 func (rs *RouteSelector) HasUserSelectionForRoute(routeID route.NetID) bool {
 	rs.mu.RLock()
 	defer rs.mu.RUnlock()
 
-	return rs.hasUserSelectionForRouteLocked(rs.effectiveNetID(routeID))
+	_, selected := rs.selectedRoutes[routeID]
+	_, deselected := rs.deselectedRoutes[routeID]
+	return selected || deselected
 }
 
 func (rs *RouteSelector) FilterSelectedExitNodes(routes route.HAMap) route.HAMap {
@@ -164,7 +174,7 @@ func (rs *RouteSelector) FilterSelectedExitNodes(routes route.HAMap) route.HAMap
 	filtered := make(route.HAMap, len(routes))
 	for id, rt := range routes {
 		netID := id.NetID()
-		if rs.isDeselectedLocked(netID) {
+		if rs.isDeselected(netID) {
 			continue
 		}
 
@@ -179,48 +189,13 @@ func (rs *RouteSelector) FilterSelectedExitNodes(routes route.HAMap) route.HAMap
 	return filtered
 }
 
-// effectiveNetID returns the v4 base for a "-v6" exit pair entry that has no explicit
-// state of its own, so selections made on the v4 entry govern the v6 entry automatically.
-// Only call this from exit-node-specific code paths: applying it to a non-exit "-v6" route
-// would make it inherit unrelated v4 state. Must be called with rs.mu held.
-func (rs *RouteSelector) effectiveNetID(id route.NetID) route.NetID {
-	name := string(id)
-	if !strings.HasSuffix(name, route.V6ExitSuffix) {
-		return id
-	}
-	if _, ok := rs.selectedRoutes[id]; ok {
-		return id
-	}
-	if _, ok := rs.deselectedRoutes[id]; ok {
-		return id
-	}
-	return route.NetID(strings.TrimSuffix(name, route.V6ExitSuffix))
-}
-
-func (rs *RouteSelector) isSelectedLocked(routeID route.NetID) bool {
-	if rs.deselectAll {
-		return false
-	}
-	_, deselected := rs.deselectedRoutes[routeID]
-	return !deselected
-}
-
-func (rs *RouteSelector) isDeselectedLocked(netID route.NetID) bool {
-	if rs.deselectAll {
-		return true
-	}
+func (rs *RouteSelector) isDeselected(netID route.NetID) bool {
 	_, deselected := rs.deselectedRoutes[netID]
-	return deselected
-}
-
-func (rs *RouteSelector) hasUserSelectionForRouteLocked(routeID route.NetID) bool {
-	_, selected := rs.selectedRoutes[routeID]
-	_, deselected := rs.deselectedRoutes[routeID]
-	return selected || deselected
+	return deselected || rs.deselectAll
 }
 
 func isExitNode(rt []*route.Route) bool {
-	return len(rt) > 0 && (route.IsV4DefaultRoute(rt[0].Network) || route.IsV6DefaultRoute(rt[0].Network))
+	return len(rt) > 0 && rt[0].Network.String() == exitNodeCIDR
 }
 
 func (rs *RouteSelector) applyExitNodeFilter(
@@ -229,23 +204,26 @@ func (rs *RouteSelector) applyExitNodeFilter(
 	rt []*route.Route,
 	out route.HAMap,
 ) {
-	// Exit-node path: apply the v4/v6 pair mirror so a deselect on the v4 base also
-	// drops the synthesized v6 entry that lacks its own explicit state.
-	effective := rs.effectiveNetID(netID)
-	if rs.hasUserSelectionForRouteLocked(effective) {
-		if rs.isSelectedLocked(effective) {
+
+	if rs.hasUserSelections() {
+		// user made explicit selects/deselects
+		if rs.IsSelected(netID) {
 			out[id] = rt
 		}
 		return
 	}
 
-	// no explicit selection for this route: defer to management's SkipAutoApply flag
+	// no explicit selections: only include routes marked !SkipAutoApply (=AutoApply)
 	sel := collectSelected(rt)
 	if len(sel) > 0 {
 		out[id] = sel
 	}
 }
 
+func (rs *RouteSelector) hasUserSelections() bool {
+	return len(rs.selectedRoutes) > 0 || len(rs.deselectedRoutes) > 0
+}
+
 func collectSelected(rt []*route.Route) []*route.Route {
 	var sel []*route.Route
 	for _, r := range rt {

client/internal/routeselector/routeselector_test.go

@@ -330,137 +330,6 @@ func TestRouteSelector_FilterSelectedExitNodes(t *testing.T) {
 	assert.Len(t, filtered, 0) // No routes should be selected
 }
 
-// TestRouteSelector_V6ExitPairInherits covers the v4/v6 exit-node pair selection
-// mirror. The mirror is scoped to exit-node code paths: HasUserSelectionForRoute
-// and FilterSelectedExitNodes resolve a "-v6" entry without explicit state to its
-// v4 base, so legacy persisted selections that predate v6 pairing transparently
-// apply to the synthesized v6 entry. General lookups (IsSelected, FilterSelected)
-// stay literal so unrelated routes named "*-v6" don't inherit unrelated state.
-func TestRouteSelector_V6ExitPairInherits(t *testing.T) {
-	all := []route.NetID{"exit1", "exit1-v6", "exit2", "exit2-v6", "corp", "corp-v6"}
-
-	t.Run("HasUserSelectionForRoute mirrors deselected v4 base", func(t *testing.T) {
-		rs := routeselector.NewRouteSelector()
-		require.NoError(t, rs.DeselectRoutes([]route.NetID{"exit1"}, all))
-
-		assert.True(t, rs.HasUserSelectionForRoute("exit1-v6"), "v6 pair sees v4 base's user selection")
-
-		// unrelated v6 with no v4 base touched is unaffected
-		assert.False(t, rs.HasUserSelectionForRoute("exit2-v6"))
-	})
-
-	t.Run("IsSelected stays literal for non-exit lookups", func(t *testing.T) {
-		rs := routeselector.NewRouteSelector()
-		require.NoError(t, rs.DeselectRoutes([]route.NetID{"corp"}, all))
-
-		// A non-exit route literally named "corp-v6" must not inherit "corp"'s state
-		// via the mirror; the mirror only applies in exit-node code paths.
-		assert.False(t, rs.IsSelected("corp"))
-		assert.True(t, rs.IsSelected("corp-v6"), "non-exit *-v6 routes must not inherit unrelated v4 state")
-	})
-
-	t.Run("explicit v6 state overrides v4 base in filter", func(t *testing.T) {
-		rs := routeselector.NewRouteSelector()
-		require.NoError(t, rs.DeselectRoutes([]route.NetID{"exit1"}, all))
-		require.NoError(t, rs.SelectRoutes([]route.NetID{"exit1-v6"}, true, all))
-
-		v4Route := &route.Route{NetID: "exit1", Network: netip.MustParsePrefix("0.0.0.0/0")}
-		v6Route := &route.Route{NetID: "exit1-v6", Network: netip.MustParsePrefix("::/0")}
-		routes := route.HAMap{
-			"exit1|0.0.0.0/0": {v4Route},
-			"exit1-v6|::/0":   {v6Route},
-		}
-
-		filtered := rs.FilterSelectedExitNodes(routes)
-		assert.NotContains(t, filtered, route.HAUniqueID("exit1|0.0.0.0/0"))
-		assert.Contains(t, filtered, route.HAUniqueID("exit1-v6|::/0"), "explicit v6 select wins over v4 base")
-	})
-
-	t.Run("non-v6-suffix routes unaffected", func(t *testing.T) {
-		rs := routeselector.NewRouteSelector()
-		require.NoError(t, rs.DeselectRoutes([]route.NetID{"exit1"}, all))
-
-		// A route literally named "exit1-something" must not pair-resolve.
-		assert.False(t, rs.HasUserSelectionForRoute("exit1-something"))
-	})
-
-	t.Run("filter v6 paired with deselected v4 base", func(t *testing.T) {
-		rs := routeselector.NewRouteSelector()
-		require.NoError(t, rs.DeselectRoutes([]route.NetID{"exit1"}, all))
-
-		v4Route := &route.Route{NetID: "exit1", Network: netip.MustParsePrefix("0.0.0.0/0")}
-		v6Route := &route.Route{NetID: "exit1-v6", Network: netip.MustParsePrefix("::/0")}
-		routes := route.HAMap{
-			"exit1|0.0.0.0/0": {v4Route},
-			"exit1-v6|::/0":   {v6Route},
-		}
-
-		filtered := rs.FilterSelectedExitNodes(routes)
-		assert.Empty(t, filtered, "deselecting v4 base must also drop the v6 pair")
-	})
-
-	t.Run("non-exit *-v6 routes pass through FilterSelectedExitNodes", func(t *testing.T) {
-		rs := routeselector.NewRouteSelector()
-		require.NoError(t, rs.DeselectRoutes([]route.NetID{"corp"}, all))
-
-		// A non-default-route entry named "corp-v6" is not an exit node and
-		// must not be skipped because its v4 base "corp" is deselected.
-		corpV6 := &route.Route{NetID: "corp-v6", Network: netip.MustParsePrefix("10.0.0.0/8")}
-		routes := route.HAMap{
-			"corp-v6|10.0.0.0/8": {corpV6},
-		}
-
-		filtered := rs.FilterSelectedExitNodes(routes)
-		assert.Contains(t, filtered, route.HAUniqueID("corp-v6|10.0.0.0/8"),
-			"non-exit *-v6 routes must not inherit unrelated v4 state in FilterSelectedExitNodes")
-	})
-}
-
-// TestRouteSelector_SkipAutoApplyPerRoute verifies that management's
-// SkipAutoApply flag governs each untouched route independently, even when
-// the user has explicit selections on other routes.
-func TestRouteSelector_SkipAutoApplyPerRoute(t *testing.T) {
-	autoApplied := &route.Route{
-		NetID:         "Auto",
-		Network:       netip.MustParsePrefix("0.0.0.0/0"),
-		SkipAutoApply: false,
-	}
-	skipApply := &route.Route{
-		NetID:         "Skip",
-		Network:       netip.MustParsePrefix("0.0.0.0/0"),
-		SkipAutoApply: true,
-	}
-	routes := route.HAMap{
-		"Auto|0.0.0.0/0": {autoApplied},
-		"Skip|0.0.0.0/0": {skipApply},
-	}
-
-	rs := routeselector.NewRouteSelector()
-	// User makes an unrelated explicit selection elsewhere.
-	require.NoError(t, rs.DeselectRoutes([]route.NetID{"Unrelated"}, []route.NetID{"Auto", "Skip", "Unrelated"}))
-
-	filtered := rs.FilterSelectedExitNodes(routes)
-	assert.Contains(t, filtered, route.HAUniqueID("Auto|0.0.0.0/0"), "AutoApply route should be included")
-	assert.NotContains(t, filtered, route.HAUniqueID("Skip|0.0.0.0/0"), "SkipAutoApply route should be excluded without explicit user selection")
-}
-
-// TestRouteSelector_V6ExitIsExitNode verifies that ::/0 routes are recognized
-// as exit nodes by the selector's filter path.
-func TestRouteSelector_V6ExitIsExitNode(t *testing.T) {
-	v6Exit := &route.Route{
-		NetID:         "V6Only",
-		Network:       netip.MustParsePrefix("::/0"),
-		SkipAutoApply: true,
-	}
-	routes := route.HAMap{
-		"V6Only|::/0": {v6Exit},
-	}
-
-	rs := routeselector.NewRouteSelector()
-	filtered := rs.FilterSelectedExitNodes(routes)
-	assert.Empty(t, filtered, "::/0 should be treated as an exit node and respect SkipAutoApply")
-}
-
 func TestRouteSelector_NewRoutesBehavior(t *testing.T) {
 	initialRoutes := []route.NetID{"route1", "route2", "route3"}
 	newRoutes := []route.NetID{"route1", "route2", "route3", "route4", "route5"}

client/ios/NetBirdSDK/client.go

@@ -162,7 +162,11 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	cfg.WgIface = interfaceName
 
 	c.connectClient = internal.NewConnectClient(ctx, cfg, c.recorder)
-	return c.connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile)
+	hostDNS := []netip.AddrPort{
+		netip.MustParseAddrPort("9.9.9.9:53"),
+		netip.MustParseAddrPort("149.112.112.112:53"),
+	}
+	return c.connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, hostDNS, c.stateFile)
 }
 
 // Stop the internal client and free the resources

client/netbird.wxs

@@ -64,13 +64,6 @@
 					<RegistryValue Name="InstalledByMSI" Type="integer" Value="1" KeyPath="yes" />
 				</RegistryKey>
 			</Component>
-			<!-- Drop the HKCU Run\Netbird value written by legacy NSIS installers. -->
-			<Component Id="NetbirdLegacyHKCUCleanup" Guid="*">
-				<RegistryValue Root="HKCU" Key="Software\NetBird GmbH\Installer"
-					Name="LegacyHKCUCleanup" Type="integer" Value="1" KeyPath="yes" />
-				<RemoveRegistryValue Root="HKCU"
-					Key="Software\Microsoft\Windows\CurrentVersion\Run" Name="Netbird" />
-			</Component>
 		</StandardDirectory>
 
 		<StandardDirectory Id="CommonAppDataFolder">
@@ -83,28 +76,10 @@
 			</Directory>
 		</StandardDirectory>
 
-		<!-- Drop Run, App Paths and Uninstall entries written by legacy NSIS
-		     installers into the 32-bit registry view (HKLM\Software\Wow6432Node). -->
-		<Component Id="NetbirdLegacyWow6432Cleanup" Directory="NetbirdInstallDir"
-			Guid="bda5d628-16bd-4086-b2c1-5099d8d51763" Bitness="always32">
-			<RegistryValue Root="HKLM" Key="Software\NetBird GmbH\Installer"
-				Name="LegacyWow6432Cleanup" Type="integer" Value="1" KeyPath="yes" />
-			<RemoveRegistryValue Root="HKLM"
-				Key="Software\Microsoft\Windows\CurrentVersion\Run" Name="Netbird" />
-			<RemoveRegistryKey Action="removeOnInstall" Root="HKLM"
-				Key="Software\Microsoft\Windows\CurrentVersion\App Paths\Netbird" />
-			<RemoveRegistryKey Action="removeOnInstall" Root="HKLM"
-				Key="Software\Microsoft\Windows\CurrentVersion\App Paths\Netbird-ui" />
-			<RemoveRegistryKey Action="removeOnInstall" Root="HKLM"
-				Key="Software\Microsoft\Windows\CurrentVersion\Uninstall\Netbird" />
-		</Component>
-
 		<ComponentGroup Id="NetbirdFilesComponent">
 			<ComponentRef Id="NetbirdFiles" />
 			<ComponentRef Id="NetbirdAumidRegistry" />
 			<ComponentRef Id="NetbirdAutoStart" />
-			<ComponentRef Id="NetbirdLegacyHKCUCleanup" />
-			<ComponentRef Id="NetbirdLegacyWow6432Cleanup" />
 		</ComponentGroup>
 
 		<util:CloseApplication Id="CloseNetBird" CloseMessage="no" Target="netbird.exe" RebootPrompt="no" />

client/proto/daemon.pb.go

@@ -2709,7 +2709,6 @@ type DebugBundleRequest struct {
 	SystemInfo    bool                   `protobuf:"varint,3,opt,name=systemInfo,proto3" json:"systemInfo,omitempty"`
 	UploadURL     string                 `protobuf:"bytes,4,opt,name=uploadURL,proto3" json:"uploadURL,omitempty"`
 	LogFileCount  uint32                 `protobuf:"varint,5,opt,name=logFileCount,proto3" json:"logFileCount,omitempty"`
-	CliVersion    string                 `protobuf:"bytes,6,opt,name=cliVersion,proto3" json:"cliVersion,omitempty"`
 	unknownFields protoimpl.UnknownFields
 	sizeCache     protoimpl.SizeCache
 }
@@ -2772,13 +2771,6 @@ func (x *DebugBundleRequest) GetLogFileCount() uint32 {
 	return 0
 }
 
-func (x *DebugBundleRequest) GetCliVersion() string {
-	if x != nil {
-		return x.CliVersion
-	}
-	return ""
-}
-
 type DebugBundleResponse struct {
 	state               protoimpl.MessageState `protogen:"open.v1"`
 	Path                string                 `protobuf:"bytes,1,opt,name=path,proto3" json:"path,omitempty"`
@@ -6483,17 +6475,14 @@ const file_daemon_proto_rawDesc = "" +
 	"\x12translatedHostname\x18\x04 \x01(\tR\x12translatedHostname\x128\n" +
 	"\x0etranslatedPort\x18\x05 \x01(\v2\x10.daemon.PortInfoR\x0etranslatedPort\"G\n" +
 	"\x17ForwardingRulesResponse\x12,\n" +
-	"\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\xb4\x01\n" +
+	"\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\x94\x01\n" +
 	"\x12DebugBundleRequest\x12\x1c\n" +
 	"\tanonymize\x18\x01 \x01(\bR\tanonymize\x12\x1e\n" +
 	"\n" +
 	"systemInfo\x18\x03 \x01(\bR\n" +
 	"systemInfo\x12\x1c\n" +
 	"\tuploadURL\x18\x04 \x01(\tR\tuploadURL\x12\"\n" +
-	"\flogFileCount\x18\x05 \x01(\rR\flogFileCount\x12\x1e\n" +
-	"\n" +
-	"cliVersion\x18\x06 \x01(\tR\n" +
-	"cliVersion\"}\n" +
+	"\flogFileCount\x18\x05 \x01(\rR\flogFileCount\"}\n" +
 	"\x13DebugBundleResponse\x12\x12\n" +
 	"\x04path\x18\x01 \x01(\tR\x04path\x12 \n" +
 	"\vuploadedKey\x18\x02 \x01(\tR\vuploadedKey\x120\n" +

client/proto/daemon.proto

@@ -471,7 +471,6 @@ message DebugBundleRequest {
   bool systemInfo = 3;
   string uploadURL = 4;
   uint32 logFileCount = 5;
-  string cliVersion = 6;
 }
 
 message DebugBundleResponse {

client/proto/generate.sh

@@ -1,16 +1,17 @@
 #!/bin/bash
 set -e
 
-if ! which realpath >/dev/null 2>&1; then
-	echo realpath is not installed
-	echo run: brew install coreutils
-	exit 1
+if ! which realpath > /dev/null 2>&1
+then
+  echo realpath is not installed
+  echo run: brew install coreutils
+  exit 1
 fi
 
 old_pwd=$(pwd)
-script_path=$(dirname "$(realpath "$0")")
+script_path=$(dirname $(realpath "$0"))
 cd "$script_path"
 go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.36.6
-go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@v1.6.1
+go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@v1.1
 protoc -I ./ ./daemon.proto --go_out=../ --go-grpc_out=../ --experimental_allow_proto3_optional
 cd "$old_pwd"

client/server/debug.go

@@ -14,7 +14,6 @@ import (
 	"github.com/netbirdio/netbird/client/internal/debug"
 	"github.com/netbirdio/netbird/client/proto"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
-	"github.com/netbirdio/netbird/version"
 )
 
 // DebugBundle creates a debug bundle and returns the location.
@@ -68,8 +67,6 @@ func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) (
 			CapturePath:    capturePath,
 			RefreshStatus:  refreshStatus,
 			ClientMetrics:  clientMetrics,
-			DaemonVersion:  version.NetbirdVersion(),
-			CliVersion:     req.CliVersion,
 		},
 		debug.BundleConfig{
 			Anonymize:         req.GetAnonymize(),

client/status/status.go

@@ -547,16 +547,6 @@ func (o *OutputOverview) GeneralSummary(showURL bool, showRelays bool, showNameS
 		goarm = fmt.Sprintf(" (ARMv%s)", os.Getenv("GOARM"))
 	}
 
-	daemonVersion := "N/A"
-	if o.DaemonVersion != "" {
-		daemonVersion = o.DaemonVersion
-	}
-
-	cliVersion := version.NetbirdVersion()
-	if o.CliVersion != "" {
-		cliVersion = o.CliVersion
-	}
-
 	summary := fmt.Sprintf(
 		"OS: %s\n"+
 			"Daemon version: %s\n"+
@@ -577,8 +567,8 @@ func (o *OutputOverview) GeneralSummary(showURL bool, showRelays bool, showNameS
 			"%s"+
 			"Peers count: %s\n",
 		fmt.Sprintf("%s/%s%s", goos, goarch, goarm),
-		daemonVersion,
-		cliVersion,
+		o.DaemonVersion,
+		version.NetbirdVersion(),
 		o.ProfileName,
 		managementConnString,
 		signalConnString,

client/ui/debug.go

@@ -21,7 +21,6 @@ import (
 	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/proto"
 	uptypes "github.com/netbirdio/netbird/upload-server/types"
-	"github.com/netbirdio/netbird/version"
 )
 
 // Initial state for the debug collection
@@ -463,7 +462,6 @@ func (s *serviceClient) createDebugBundleFromCollection(
 	request := &proto.DebugBundleRequest{
 		Anonymize:  params.anonymize,
 		SystemInfo: params.systemInfo,
-		CliVersion: version.NetbirdVersion(),
 	}
 
 	if params.upload {
@@ -595,7 +593,6 @@ func (s *serviceClient) createDebugBundle(anonymize bool, systemInfo bool, uploa
 	request := &proto.DebugBundleRequest{
 		Anonymize:  anonymize,
 		SystemInfo: systemInfo,
-		CliVersion: version.NetbirdVersion(),
 	}
 
 	if uploadURL != "" {

client/ui/network.go

@@ -193,15 +193,7 @@ func getOverlappingNetworks(routes []*proto.Network) []*proto.Network {
 }
 
 func isDefaultRoute(routeRange string) bool {
-	// routeRange is the merged display string from the daemon, e.g. "0.0.0.0/0",
-	// "::/0", or "0.0.0.0/0, ::/0" when a v4 exit node has a paired v6 entry.
-	for _, part := range strings.Split(routeRange, ",") {
-		switch strings.TrimSpace(part) {
-		case "0.0.0.0/0", "::/0":
-			return true
-		}
-	}
-	return false
+	return routeRange == "0.0.0.0/0" || routeRange == "::/0"
 }
 
 func getExitNodeNetworks(routes []*proto.Network) []*proto.Network {

combined/cmd/root.go

@@ -67,6 +67,10 @@ func init() {
 	rootCmd.AddCommand(newTokenCommands())
 }
 
+func RootCmd() *cobra.Command {
+	return rootCmd
+}
+
 func Execute() error {
 	return rootCmd.Execute()
 }
@@ -168,7 +172,7 @@ func initializeConfig() error {
 // serverInstances holds all server instances created during startup.
 type serverInstances struct {
 	relaySrv      *relayServer.Server
-	mgmtSrv       *mgmtServer.BaseServer
+	mgmtSrv       mgmtServer.Server
 	signalSrv     *signalServer.Server
 	healthcheck   *healthcheck.Server
 	stunServer    *stun.Server
@@ -324,19 +328,24 @@ func setupServerHooks(servers *serverInstances, cfg *CombinedConfig) {
 		return
 	}
 
-	servers.mgmtSrv.AfterInit(func(s *mgmtServer.BaseServer) {
-		grpcSrv := s.GRPCServer()
+	if s, ok := servers.mgmtSrv.GetContainer(mgmtServer.ContainerKeyBaseServer); ok {
+		if baseServer, ok := s.(*mgmtServer.BaseServer); ok {
+			baseServer.AfterInit(func(s *mgmtServer.BaseServer) {
+				grpcSrv := s.GRPCServer()
 
-		if servers.signalSrv != nil {
-			proto.RegisterSignalExchangeServer(grpcSrv, servers.signalSrv)
-			log.Infof("Signal server registered on port %s", cfg.Server.ListenAddress)
-		}
+				if servers.signalSrv != nil {
+					proto.RegisterSignalExchangeServer(grpcSrv, servers.signalSrv)
+					log.Infof("Signal server registered on port %s", cfg.Server.ListenAddress)
+				}
 
-		s.SetHandlerFunc(createCombinedHandler(grpcSrv, s.APIHandler(), servers.relaySrv, servers.metricsServer.Meter, cfg))
-		if servers.relaySrv != nil {
-			log.Infof("Relay WebSocket handler added (path: /relay)")
+				s.SetHandlerFunc(createCombinedHandler(grpcSrv, s.APIHandler(), servers.relaySrv, servers.metricsServer.Meter, cfg))
+				if servers.relaySrv != nil {
+					log.Infof("Relay WebSocket handler added (path: /relay)")
+				}
+			})
 		}
-	})
+	}
+
 }
 
 func startServers(wg *sync.WaitGroup, srv *relayServer.Server, httpHealthcheck *healthcheck.Server, stunServer *stun.Server, metricsServer *sharedMetrics.Metrics) {
@@ -346,38 +355,32 @@ func startServers(wg *sync.WaitGroup, srv *relayServer.Server, httpHealthcheck *
 		log.Infof("Relay WebSocket multiplexed on management port (no separate relay listener)")
 	}
 
-	wg.Add(1)
-	go func() {
-		defer wg.Done()
+	wg.Go(func() {
 		log.Infof("running metrics server: %s%s", metricsServer.Addr, metricsServer.Endpoint)
 		if err := metricsServer.ListenAndServe(); !errors.Is(err, http.ErrServerClosed) {
 			log.Fatalf("failed to start metrics server: %v", err)
 		}
-	}()
+	})
 
-	wg.Add(1)
-	go func() {
-		defer wg.Done()
+	wg.Go(func() {
 		if err := httpHealthcheck.ListenAndServe(); !errors.Is(err, http.ErrServerClosed) {
 			log.Fatalf("failed to start healthcheck server: %v", err)
 		}
-	}()
+	})
 
 	if stunServer != nil {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
+		wg.Go(func() {
 			if err := stunServer.Listen(); err != nil {
 				if errors.Is(err, stun.ErrServerClosed) {
 					return
 				}
 				log.Errorf("STUN server error: %v", err)
 			}
-		}()
+		})
 	}
 }
 
-func shutdownServers(ctx context.Context, srv *relayServer.Server, httpHealthcheck *healthcheck.Server, stunServer *stun.Server, mgmtSrv *mgmtServer.BaseServer, metricsServer *sharedMetrics.Metrics) error {
+func shutdownServers(ctx context.Context, srv *relayServer.Server, httpHealthcheck *healthcheck.Server, stunServer *stun.Server, mgmtSrv mgmtServer.Server, metricsServer *sharedMetrics.Metrics) error {
 	var errs error
 
 	if err := httpHealthcheck.Shutdown(ctx); err != nil {
@@ -491,7 +494,7 @@ func handleTLSConfig(cfg *CombinedConfig) (*tls.Config, bool, error) {
 	return nil, false, nil
 }
 
-func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (*mgmtServer.BaseServer, error) {
+func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (mgmtServer.Server, error) {
 	mgmt := cfg.Management
 
 	// Extract port from listen address
@@ -502,7 +505,7 @@ func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (*
 	}
 	mgmtPort, _ := strconv.Atoi(portStr)
 
-	mgmtSrv := mgmtServer.NewServer(
+	mgmtSrv := newServer(
 		&mgmtServer.Config{
 			NbConfig:                mgmtConfig,
 			DNSDomain:               "",

combined/cmd/server.go

@@ -0,0 +1,13 @@
+package cmd
+
+import (
+	mgmtServer "github.com/netbirdio/netbird/management/internals/server"
+)
+
+var newServer = func(cfg *mgmtServer.Config) mgmtServer.Server {
+	return mgmtServer.NewServer(cfg)
+}
+
+func SetNewServer(fn func(*mgmtServer.Config) mgmtServer.Server) {
+	newServer = fn
+}

go.mod

@@ -24,13 +24,13 @@ require (
 	golang.zx2c4.com/wireguard/windows v0.5.3
 	google.golang.org/grpc v1.80.0
 	google.golang.org/protobuf v1.36.11
+	gopkg.in/natefinch/lumberjack.v2 v2.2.1
 )
 
 require (
 	fyne.io/fyne/v2 v2.7.0
 	fyne.io/systray v1.12.1-0.20260116214250-81f8e1a496f9
 	git.sr.ht/~jackmordaunt/go-toast/v2 v2.0.3
-	github.com/DeRuina/timberjack v1.4.2
 	github.com/awnumar/memguard v0.23.0
 	github.com/aws/aws-sdk-go-v2 v1.38.3
 	github.com/aws/aws-sdk-go-v2/config v1.31.6

go.sum

@@ -29,8 +29,6 @@ github.com/Azure/go-ntlmssp v0.1.0 h1:DjFo6YtWzNqNvQdrwEyr/e4nhU3vRiwenz5QX7sFz+
 github.com/Azure/go-ntlmssp v0.1.0/go.mod h1:NYqdhxd/8aAct/s4qSYZEerdPuH1liG2/X9DiVTbhpk=
 github.com/BurntSushi/toml v1.5.0 h1:W5quZX/G/csjUnuI8SUYlsHs9M38FC7znL0lIO+DvMg=
 github.com/BurntSushi/toml v1.5.0/go.mod h1:ukJfTF/6rtPPRCnwkur4qwRxa8vTRFBF0uk2lLoLwho=
-github.com/DeRuina/timberjack v1.4.2 h1:4bKlzhKdsR+2oNkgef9mqb4n11ICow8VK88RfzJPzN8=
-github.com/DeRuina/timberjack v1.4.2/go.mod h1:RLoeQrwrCGIEF8gO5nV5b/gMD0QIy7bzQhBUgpp1EqE=
 github.com/Masterminds/goutils v1.1.1 h1:5nUrii3FMTL5diU80unEVvNevw1nH4+ZV4DSLVJLSYI=
 github.com/Masterminds/goutils v1.1.1/go.mod h1:8cTjp+g8YejhMuvIA5y2vz3BpJxksy863GQaJW2MFNU=
 github.com/Masterminds/semver/v3 v3.3.0 h1:B8LGeaivUe71a5qox1ICM/JLl0NqZSW5CHyL+hmvYS0=
@@ -940,6 +938,8 @@ gopkg.in/go-playground/assert.v1 v1.2.1/go.mod h1:9RXL0bg/zibRAgZUYszZSwO/z8Y/a8
 gopkg.in/go-playground/validator.v9 v9.29.1/go.mod h1:+c9/zcJMFNgbLvly1L1V+PpxWdVbfP1avr/N00E2vyQ=
 gopkg.in/ini.v1 v1.67.0 h1:Dgnx+6+nfE+IfzjUEISNeydPJh9AXNNsWbGP9KzCsOA=
 gopkg.in/ini.v1 v1.67.0/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
+gopkg.in/natefinch/lumberjack.v2 v2.2.1 h1:bBRl1b0OH9s/DuPhuXpNl+VtCaJXFZ5/uEFST95x9zc=
+gopkg.in/natefinch/lumberjack.v2 v2.2.1/go.mod h1:YD8tP3GAjkrDg1eZH7EGmyESg/lsYskCTPBJVb9jqSc=
 gopkg.in/square/go-jose.v2 v2.6.0 h1:NGk74WTnPKBNUhNzQX7PYcTLUjoq7mzKk2OKbvwk2iI=
 gopkg.in/square/go-jose.v2 v2.6.0/go.mod h1:M9dMgbHiYLoDGQrXy7OpJDJWiKiU//h+vD76mk0e1AI=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=

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

@@ -304,27 +304,10 @@ func (m Manager) getClusterAllowList(ctx context.Context, accountID string) ([]s
 	if err != nil {
 		return nil, fmt.Errorf("get BYOP cluster addresses: %w", err)
 	}
-	publicAddresses, err := m.proxyManager.GetActiveClusterAddresses(ctx)
-	if err != nil {
-		return nil, fmt.Errorf("get public cluster addresses: %w", err)
+	if len(byopAddresses) > 0 {
+		return byopAddresses, nil
 	}
-	seen := make(map[string]struct{}, len(byopAddresses)+len(publicAddresses))
-	merged := make([]string, 0, len(byopAddresses)+len(publicAddresses))
-	for _, addr := range byopAddresses {
-		if _, ok := seen[addr]; ok {
-			continue
-		}
-		seen[addr] = struct{}{}
-		merged = append(merged, addr)
-	}
-	for _, addr := range publicAddresses {
-		if _, ok := seen[addr]; ok {
-			continue
-		}
-		seen[addr] = struct{}{}
-		merged = append(merged, addr)
-	}
-	return merged, nil
+	return m.proxyManager.GetActiveClusterAddresses(ctx)
 }
 
 func extractClusterFromCustomDomains(serviceDomain string, customDomains []*domain.Domain) (string, bool) {

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

@@ -40,37 +40,22 @@ func (m *mockProxyManager) ClusterSupportsCrowdSec(_ context.Context, _ string)
 	return nil
 }
 
-func TestGetClusterAllowList_BYOPMergedWithPublic(t *testing.T) {
+func TestGetClusterAllowList_BYOPProxy(t *testing.T) {
 	pm := &mockProxyManager{
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, accID string) ([]string, error) {
 			assert.Equal(t, "acc-123", accID)
 			return []string{"byop.example.com"}, nil
 		},
 		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
-			return []string{"eu.proxy.netbird.io"}, nil
+			t.Fatal("should not call GetActiveClusterAddresses when BYOP addresses exist")
+			return nil, nil
 		},
 	}
 
 	mgr := Manager{proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.NoError(t, err)
-	assert.Equal(t, []string{"byop.example.com", "eu.proxy.netbird.io"}, result)
-}
-
-func TestGetClusterAllowList_DeduplicatesBYOPAndPublic(t *testing.T) {
-	pm := &mockProxyManager{
-		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
-			return []string{"shared.example.com", "byop.example.com"}, nil
-		},
-		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
-			return []string{"shared.example.com", "eu.proxy.netbird.io"}, nil
-		},
-	}
-
-	mgr := Manager{proxyManager: pm}
-	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
-	require.NoError(t, err)
-	assert.Equal(t, []string{"shared.example.com", "byop.example.com", "eu.proxy.netbird.io"}, result)
+	assert.Equal(t, []string{"byop.example.com"}, result)
 }
 
 func TestGetClusterAllowList_NoBYOP_FallbackToShared(t *testing.T) {
@@ -94,6 +79,10 @@ func TestGetClusterAllowList_BYOPError_ReturnsError(t *testing.T) {
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
 			return nil, errors.New("db error")
 		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			t.Fatal("should not call GetActiveClusterAddresses when BYOP lookup fails")
+			return nil, nil
+		},
 	}
 
 	mgr := Manager{proxyManager: pm}
@@ -103,23 +92,6 @@ func TestGetClusterAllowList_BYOPError_ReturnsError(t *testing.T) {
 	assert.Contains(t, err.Error(), "BYOP cluster addresses")
 }
 
-func TestGetClusterAllowList_PublicError_ReturnsError(t *testing.T) {
-	pm := &mockProxyManager{
-		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
-			return []string{"byop.example.com"}, nil
-		},
-		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
-			return nil, errors.New("db error")
-		},
-	}
-
-	mgr := Manager{proxyManager: pm}
-	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
-	require.Error(t, err)
-	assert.Nil(t, result)
-	assert.Contains(t, err.Error(), "public cluster addresses")
-}
-
 func TestGetClusterAllowList_BYOPEmptySlice_FallbackToShared(t *testing.T) {
 	pm := &mockProxyManager{
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
@@ -136,19 +108,3 @@ func TestGetClusterAllowList_BYOPEmptySlice_FallbackToShared(t *testing.T) {
 	assert.Equal(t, []string{"eu.proxy.netbird.io"}, result)
 }
 
-func TestGetClusterAllowList_PublicEmpty_BYOPOnly(t *testing.T) {
-	pm := &mockProxyManager{
-		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
-			return []string{"byop.example.com"}, nil
-		},
-		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
-			return nil, nil
-		},
-	}
-
-	mgr := Manager{proxyManager: pm}
-	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
-	require.NoError(t, err)
-	assert.Equal(t, []string{"byop.example.com"}, result)
-}
-

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

@@ -306,10 +306,6 @@ func (m *Manager) validateSubdomainRequirement(ctx context.Context, domain, clus
 func (m *Manager) persistNewService(ctx context.Context, accountID string, svc *service.Service) error {
 	customPorts := m.clusterCustomPorts(ctx, svc)
 
-	if err := validateTargetReferences(ctx, m.store, accountID, svc.Targets); err != nil {
-		return err
-	}
-
 	return m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if svc.Domain != "" {
 			if err := m.checkDomainAvailable(ctx, transaction, svc.Domain, ""); err != nil {
@@ -325,6 +321,10 @@ func (m *Manager) persistNewService(ctx context.Context, accountID string, svc *
 			return err
 		}
 
+		if err := validateTargetReferences(ctx, transaction, accountID, svc.Targets); err != nil {
+			return err
+		}
+
 		if err := transaction.CreateService(ctx, svc); err != nil {
 			return fmt.Errorf("create service: %w", err)
 		}
@@ -435,10 +435,6 @@ func (m *Manager) assignPort(ctx context.Context, tx store.Store, cluster string
 func (m *Manager) persistNewEphemeralService(ctx context.Context, accountID, peerID string, svc *service.Service) error {
 	customPorts := m.clusterCustomPorts(ctx, svc)
 
-	if err := validateTargetReferences(ctx, m.store, accountID, svc.Targets); err != nil {
-		return err
-	}
-
 	return m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if err := m.validateEphemeralPreconditions(ctx, transaction, accountID, peerID, svc); err != nil {
 			return err
@@ -452,6 +448,10 @@ func (m *Manager) persistNewEphemeralService(ctx context.Context, accountID, pee
 			return err
 		}
 
+		if err := validateTargetReferences(ctx, transaction, accountID, svc.Targets); err != nil {
+			return err
+		}
+
 		if err := transaction.CreateService(ctx, svc); err != nil {
 			return fmt.Errorf("create service: %w", err)
 		}
@@ -552,22 +552,10 @@ func (m *Manager) persistServiceUpdate(ctx context.Context, accountID string, se
 	svcForCaps.ProxyCluster = effectiveCluster
 	customPorts := m.clusterCustomPorts(ctx, &svcForCaps)
 
-	if err := validateTargetReferences(ctx, m.store, accountID, service.Targets); err != nil {
-		return nil, err
-	}
-
-	// Validate subdomain requirement *before* the transaction: the underlying
-	// capability lookup talks to the main DB pool, and SQLite's single-connection
-	// pool would self-deadlock if this ran while the tx already held the only
-	// connection.
-	if err := m.validateSubdomainRequirement(ctx, service.Domain, effectiveCluster); err != nil {
-		return nil, err
-	}
-
 	var updateInfo serviceUpdateInfo
 
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		return m.executeServiceUpdate(ctx, transaction, accountID, service, &updateInfo, customPorts, effectiveCluster)
+		return m.executeServiceUpdate(ctx, transaction, accountID, service, &updateInfo, customPorts)
 	})
 
 	return &updateInfo, err
@@ -597,7 +585,7 @@ func (m *Manager) resolveEffectiveCluster(ctx context.Context, accountID string,
 	return existing.ProxyCluster, nil
 }
 
-func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.Store, accountID string, service *service.Service, updateInfo *serviceUpdateInfo, customPorts *bool, effectiveCluster string) error {
+func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.Store, accountID string, service *service.Service, updateInfo *serviceUpdateInfo, customPorts *bool) error {
 	existingService, err := transaction.GetServiceByID(ctx, store.LockingStrengthUpdate, accountID, service.ID)
 	if err != nil {
 		return err
@@ -615,13 +603,17 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	updateInfo.domainChanged = existingService.Domain != service.Domain
 
 	if updateInfo.domainChanged {
-		if err := m.handleDomainChange(ctx, transaction, service, effectiveCluster); err != nil {
+		if err := m.handleDomainChange(ctx, transaction, accountID, service); err != nil {
 			return err
 		}
 	} else {
 		service.ProxyCluster = existingService.ProxyCluster
 	}
 
+	if err := m.validateSubdomainRequirement(ctx, service.Domain, service.ProxyCluster); err != nil {
+		return err
+	}
+
 	m.preserveExistingAuthSecrets(service, existingService)
 	if err := validateHeaderAuthValues(service.Auth.HeaderAuths); err != nil {
 		return err
@@ -636,6 +628,9 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	if err := m.checkPortConflict(ctx, transaction, service); err != nil {
 		return err
 	}
+	if err := validateTargetReferences(ctx, transaction, accountID, service.Targets); err != nil {
+		return err
+	}
 	if err := transaction.UpdateService(ctx, service); err != nil {
 		return fmt.Errorf("update service: %w", err)
 	}
@@ -643,18 +638,20 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	return nil
 }
 
-// handleDomainChange validates the new domain is free inside the transaction
-// and applies the pre-resolved cluster (computed outside the tx by
-// resolveEffectiveCluster). It must NOT call clusterDeriver here: that talks
-// to the main DB pool and would self-deadlock under SQLite (max_open_conns=1)
-// because the transaction already holds the only connection.
-func (m *Manager) handleDomainChange(ctx context.Context, transaction store.Store, svc *service.Service, effectiveCluster string) error {
+func (m *Manager) handleDomainChange(ctx context.Context, transaction store.Store, accountID string, svc *service.Service) error {
 	if err := m.checkDomainAvailable(ctx, transaction, svc.Domain, svc.ID); err != nil {
 		return err
 	}
-	if effectiveCluster != "" {
-		svc.ProxyCluster = effectiveCluster
+
+	if m.clusterDeriver != nil {
+		newCluster, err := m.clusterDeriver.DeriveClusterFromDomain(ctx, accountID, svc.Domain)
+		if err != nil {
+			log.WithError(err).Warnf("could not derive cluster from domain %s", svc.Domain)
+		} else {
+			svc.ProxyCluster = newCluster
+		}
 	}
+
 	return nil
 }
 

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

@@ -381,14 +381,13 @@ func (s *Service) buildPathMappings() []*proto.PathMapping {
 		}
 
 		// HTTP/HTTPS: build full URL
-		hostNoBrackets := strings.TrimSuffix(strings.TrimPrefix(target.Host, "["), "]")
 		targetURL := url.URL{
 			Scheme: target.Protocol,
-			Host:   bracketIPv6Host(hostNoBrackets),
+			Host:   target.Host,
 			Path:   "/",
 		}
 		if target.Port > 0 && !isDefaultPort(target.Protocol, target.Port) {
-			targetURL.Host = net.JoinHostPort(hostNoBrackets, strconv.FormatUint(uint64(target.Port), 10))
+			targetURL.Host = net.JoinHostPort(targetURL.Host, strconv.FormatUint(uint64(target.Port), 10))
 		}
 
 		path := "/"
@@ -406,19 +405,6 @@ func (s *Service) buildPathMappings() []*proto.PathMapping {
 	return pathMappings
 }
 
-// bracketIPv6Host wraps host in square brackets when it is an IPv6 literal, as
-// required for the Host field of net/url.URL (RFC 3986 §3.2.2). v4-mapped IPv6
-// addresses are bracketed too since their textual form contains colons.
-func bracketIPv6Host(host string) string {
-	if strings.HasPrefix(host, "[") {
-		return host
-	}
-	if addr, err := netip.ParseAddr(host); err == nil && addr.Is6() {
-		return "[" + host + "]"
-	}
-	return host
-}
-
 func operationToProtoType(op Operation) proto.ProxyMappingUpdateType {
 	switch op {
 	case Create:

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

@@ -351,83 +351,6 @@ func TestToProtoMapping_PortInTargetURL(t *testing.T) {
 			port:       80,
 			wantTarget: "https://10.0.0.1:80/",
 		},
-		{
-			name:       "domain host without port is unchanged",
-			protocol:   "http",
-			host:       "example.com",
-			port:       0,
-			wantTarget: "http://example.com/",
-		},
-		{
-			name:       "domain host with non-default port is unchanged",
-			protocol:   "http",
-			host:       "example.com",
-			port:       8080,
-			wantTarget: "http://example.com:8080/",
-		},
-		{
-			name:       "ipv6 host without port is bracketed",
-			protocol:   "http",
-			host:       "fb00:cafe:1::3",
-			port:       0,
-			wantTarget: "http://[fb00:cafe:1::3]/",
-		},
-		{
-			name:       "ipv6 host with default port omits port and brackets host",
-			protocol:   "http",
-			host:       "fb00:cafe:1::3",
-			port:       80,
-			wantTarget: "http://[fb00:cafe:1::3]/",
-		},
-		{
-			name:       "ipv6 host with non-default port is bracketed",
-			protocol:   "http",
-			host:       "fb00:cafe:1::3",
-			port:       8080,
-			wantTarget: "http://[fb00:cafe:1::3]:8080/",
-		},
-		{
-			name:       "ipv6 loopback without port is bracketed",
-			protocol:   "http",
-			host:       "::1",
-			port:       0,
-			wantTarget: "http://[::1]/",
-		},
-		{
-			name:       "ipv6 host with 5-digit port is bracketed",
-			protocol:   "http",
-			host:       "fb00:cafe::1",
-			port:       18080,
-			wantTarget: "http://[fb00:cafe::1]:18080/",
-		},
-		{
-			name:       "pre-bracketed ipv6 without port stays single-bracketed",
-			protocol:   "http",
-			host:       "[fb00:cafe::1]",
-			port:       0,
-			wantTarget: "http://[fb00:cafe::1]/",
-		},
-		{
-			name:       "pre-bracketed ipv6 with port is not double-bracketed",
-			protocol:   "http",
-			host:       "[fb00:cafe::1]",
-			port:       8080,
-			wantTarget: "http://[fb00:cafe::1]:8080/",
-		},
-		{
-			name:       "v4-mapped ipv6 host without port is bracketed",
-			protocol:   "http",
-			host:       "::ffff:10.0.0.1",
-			port:       0,
-			wantTarget: "http://[::ffff:10.0.0.1]/",
-		},
-		{
-			name:       "full-form 8-group ipv6 without port is bracketed",
-			protocol:   "http",
-			host:       "fb00:cafe:1:0:0:0:0:3",
-			port:       0,
-			wantTarget: "http://[fb00:cafe:1:0:0:0:0:3]/",
-		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {

management/internals/server/server.go

@@ -34,6 +34,8 @@ const (
 	ManagementLegacyPort = 33073
 	// DefaultSelfHostedDomain is the default domain used for self-hosted fresh installs.
 	DefaultSelfHostedDomain = "netbird.selfhosted"
+
+	ContainerKeyBaseServer = "baseServer"
 )
 
 type Server interface {
@@ -91,7 +93,7 @@ type Config struct {
 
 // NewServer initializes and configures a new Server instance
 func NewServer(cfg *Config) *BaseServer {
-	return &BaseServer{
+	s := &BaseServer{
 		Config:                      cfg.NbConfig,
 		container:                   make(map[string]any),
 		dnsDomain:                   cfg.DNSDomain,
@@ -104,6 +106,9 @@ func NewServer(cfg *Config) *BaseServer {
 		mgmtMetricsPort:             cfg.MgmtMetricsPort,
 		autoResolveDomains:          cfg.AutoResolveDomains,
 	}
+	s.container[ContainerKeyBaseServer] = s
+
+	return s
 }
 
 func (s *BaseServer) AfterInit(fn func(s *BaseServer)) {

management/internals/shared/grpc/proxy.go

@@ -394,13 +394,6 @@ func (s *ProxyServiceServer) sendSnapshot(ctx context.Context, conn *proxyConnec
 		if end > len(mappings) {
 			end = len(mappings)
 		}
-		for _, m := range mappings[i:end] {
-			token, err := s.tokenStore.GenerateToken(m.AccountId, m.Id, s.proxyTokenTTL())
-			if err != nil {
-				return fmt.Errorf("generate auth token for service %s: %w", m.Id, err)
-			}
-			m.AuthToken = token
-		}
 		if err := conn.stream.Send(&proto.GetMappingUpdateResponse{
 			Mapping:             mappings[i:end],
 			InitialSyncComplete: end == len(mappings),
@@ -432,14 +425,18 @@ func (s *ProxyServiceServer) snapshotServiceMappings(ctx context.Context, conn *
 		return nil, fmt.Errorf("get services from store: %w", err)
 	}
 
-	oidcCfg := s.GetOIDCValidationConfig()
 	var mappings []*proto.ProxyMapping
 	for _, service := range services {
 		if !service.Enabled || service.ProxyCluster == "" || service.ProxyCluster != conn.address {
 			continue
 		}
 
-		m := service.ToProtoMapping(rpservice.Create, "", oidcCfg)
+		token, err := s.tokenStore.GenerateToken(service.AccountID, service.ID, s.proxyTokenTTL())
+		if err != nil {
+			return nil, fmt.Errorf("generate auth token for service %s: %w", service.ID, err)
+		}
+
+		m := service.ToProtoMapping(rpservice.Create, token, s.GetOIDCValidationConfig())
 		if !proxyAcceptsMapping(conn, m) {
 			continue
 		}

management/internals/shared/grpc/proxy_snapshot_test.go

@@ -4,7 +4,6 @@ import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/golang/mock/gomock"
 	"github.com/stretchr/testify/assert"
@@ -173,55 +172,3 @@ func TestSendSnapshot_EmptySnapshot(t *testing.T) {
 	assert.Empty(t, stream.messages[0].Mapping)
 	assert.True(t, stream.messages[0].InitialSyncComplete)
 }
-
-type hookingStream struct {
-	grpc.ServerStream
-	onSend func(*proto.GetMappingUpdateResponse)
-}
-
-func (s *hookingStream) Send(m *proto.GetMappingUpdateResponse) error {
-	if s.onSend != nil {
-		s.onSend(m)
-	}
-	return nil
-}
-
-func (s *hookingStream) Context() context.Context     { return context.Background() }
-func (s *hookingStream) SetHeader(metadata.MD) error  { return nil }
-func (s *hookingStream) SendHeader(metadata.MD) error { return nil }
-func (s *hookingStream) SetTrailer(metadata.MD)       {}
-func (s *hookingStream) SendMsg(any) error            { return nil }
-func (s *hookingStream) RecvMsg(any) error            { return nil }
-
-func TestSendSnapshot_TokensRemainValidUnderSlowSend(t *testing.T) {
-	const cluster = "cluster.example.com"
-	const batchSize = 2
-	const totalServices = 6
-	const ttl = 100 * time.Millisecond
-	const sendDelay = 200 * time.Millisecond
-
-	ctrl := gomock.NewController(t)
-	mgr := rpservice.NewMockManager(ctrl)
-	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
-
-	s := newSnapshotTestServer(t, batchSize)
-	s.serviceManager = mgr
-	s.tokenTTL = ttl
-
-	var validateErrs []error
-	stream := &hookingStream{
-		onSend: func(resp *proto.GetMappingUpdateResponse) {
-			for _, m := range resp.Mapping {
-				if err := s.tokenStore.ValidateAndConsume(m.AuthToken, m.AccountId, m.Id); err != nil {
-					validateErrs = append(validateErrs, fmt.Errorf("svc %s: %w", m.Id, err))
-				}
-			}
-			time.Sleep(sendDelay)
-		},
-	}
-	conn := &proxyConnection{proxyID: "proxy-a", address: cluster, stream: stream}
-
-	require.NoError(t, s.sendSnapshot(context.Background(), conn))
-	require.Empty(t, validateErrs,
-		"tokens must remain valid even when batches are sent slowly: lazy per-batch generation guarantees freshness")
-}

management/internals/shared/grpc/server.go

@@ -522,11 +522,10 @@ func (s *Server) sendJob(ctx context.Context, peerKey wgtypes.Key, job *job.Even
 }
 
 func (s *Server) cancelPeerRoutines(ctx context.Context, accountID string, peer *nbpeer.Peer, streamStartTime time.Time) {
-	uncanceledCTX := context.WithoutCancel(ctx)
-	unlock := s.acquirePeerLockByUID(uncanceledCTX, peer.Key)
+	unlock := s.acquirePeerLockByUID(ctx, peer.Key)
 	defer unlock()
 
-	s.cancelPeerRoutinesWithoutLock(uncanceledCTX, accountID, peer, streamStartTime)
+	s.cancelPeerRoutinesWithoutLock(ctx, accountID, peer, streamStartTime)
 }
 
 func (s *Server) cancelPeerRoutinesWithoutLock(ctx context.Context, accountID string, peer *nbpeer.Peer, streamStartTime time.Time) {

management/internals/shared/grpc/validate_session_test.go

@@ -326,25 +326,17 @@ func (m *testValidateSessionServiceManager) GetActiveClusters(_ context.Context,
 	return nil, nil
 }
 
-func (m *testValidateSessionServiceManager) DeleteAccountCluster(_ context.Context, _, _, _ string) error {
-	return nil
-}
-
 type testValidateSessionProxyManager struct{}
 
-func (m *testValidateSessionProxyManager) Connect(_ context.Context, _, _, _, _ string, _ *string, _ *proxy.Capabilities) (*proxy.Proxy, error) {
-	return nil, nil
-}
-
-func (m *testValidateSessionProxyManager) Disconnect(_ context.Context, _, _ string) error {
+func (m *testValidateSessionProxyManager) Connect(_ context.Context, _, _, _ string, _ *string, _ *proxy.Capabilities) error {
 	return nil
 }
 
-func (m *testValidateSessionProxyManager) Heartbeat(_ context.Context, _ *proxy.Proxy) error {
+func (m *testValidateSessionProxyManager) Disconnect(_ context.Context, _ string) error {
 	return nil
 }
 
-func (m *testValidateSessionProxyManager) DeleteAccountCluster(_ context.Context, _, _ string) error {
+func (m *testValidateSessionProxyManager) Heartbeat(_ context.Context, _, _, _ string) error {
 	return nil
 }
 

management/server/account.go

@@ -291,15 +291,10 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 		return nil, status.NewPermissionDeniedError()
 	}
 
-	// Canonicalize the incoming range so a caller-supplied prefix with host bits
-	// (e.g. 100.64.1.1/16) compares equal to the masked form stored on network.Net.
-	newSettings.NetworkRange = newSettings.NetworkRange.Masked()
-
 	var oldSettings *types.Settings
 	var updateAccountPeers bool
 	var groupChangesAffectPeers bool
 	var reloadReverseProxy bool
-	var effectiveOldNetworkRange netip.Prefix
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		var groupsUpdated bool
@@ -313,16 +308,6 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 			return err
 		}
 
-		// No lock: the transaction already holds Settings(Update), and network.Net is
-		// only mutated by reallocateAccountPeerIPs, which is reachable only through
-		// this same code path. A Share lock here would extend an unnecessary row lock
-		// and complicate ordering against updatePeerIPv6InTransaction.
-		network, err := transaction.GetAccountNetwork(ctx, store.LockingStrengthNone, accountID)
-		if err != nil {
-			return fmt.Errorf("get account network: %w", err)
-		}
-		effectiveOldNetworkRange = prefixFromIPNet(network.Net)
-
 		if oldSettings.Extra != nil && newSettings.Extra != nil &&
 			oldSettings.Extra.PeerApprovalEnabled && !newSettings.Extra.PeerApprovalEnabled {
 			approvedCount, err := transaction.ApproveAccountPeers(ctx, accountID)
@@ -336,7 +321,7 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 			}
 		}
 
-		if newSettings.NetworkRange.IsValid() && newSettings.NetworkRange != effectiveOldNetworkRange {
+		if oldSettings.NetworkRange != newSettings.NetworkRange {
 			if err = am.reallocateAccountPeerIPs(ctx, transaction, accountID, newSettings.NetworkRange); err != nil {
 				return err
 			}
@@ -411,9 +396,9 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 		}
 		am.StoreEvent(ctx, userID, accountID, accountID, activity.AccountDNSDomainUpdated, eventMeta)
 	}
-	if newSettings.NetworkRange.IsValid() && newSettings.NetworkRange != effectiveOldNetworkRange {
+	if oldSettings.NetworkRange != newSettings.NetworkRange {
 		eventMeta := map[string]any{
-			"old_network_range": effectiveOldNetworkRange.String(),
+			"old_network_range": oldSettings.NetworkRange.String(),
 			"new_network_range": newSettings.NetworkRange.String(),
 		}
 		am.StoreEvent(ctx, userID, accountID, accountID, activity.AccountNetworkRangeUpdated, eventMeta)
@@ -458,22 +443,6 @@ func ipv6SettingsChanged(old, updated *types.Settings) bool {
 	return !slices.Equal(oldGroups, newGroups)
 }
 
-// prefixFromIPNet returns the overlay prefix actually allocated on the account
-// network, or an invalid prefix if none is set. Settings.NetworkRange is a
-// user-facing override that is empty on legacy accounts, so the effective
-// range must be read from network.Net to compare against an incoming update.
-func prefixFromIPNet(ipNet net.IPNet) netip.Prefix {
-	if ipNet.IP == nil {
-		return netip.Prefix{}
-	}
-	addr, ok := netip.AddrFromSlice(ipNet.IP)
-	if !ok {
-		return netip.Prefix{}
-	}
-	ones, _ := ipNet.Mask.Size()
-	return netip.PrefixFrom(addr.Unmap(), ones)
-}
-
 func (am *DefaultAccountManager) validateSettingsUpdate(ctx context.Context, transaction store.Store, newSettings, oldSettings *types.Settings, userID, accountID string) error {
 	halfYearLimit := 180 * 24 * time.Hour
 	if newSettings.PeerLoginExpiration > halfYearLimit {
@@ -2518,18 +2487,6 @@ func (am *DefaultAccountManager) buildIPv6AllowedPeers(ctx context.Context, tran
 			allowedPeers[peerID] = struct{}{}
 		}
 	}
-
-	// Embedded proxy peers sit outside regular group membership but must
-	// participate in any v6-enabled overlay to reach v6-only peers.
-	peers, err := transaction.GetAccountPeers(ctx, store.LockingStrengthNone, accountID, "", "")
-	if err != nil {
-		return nil, fmt.Errorf("get peers: %w", err)
-	}
-	for _, p := range peers {
-		if p.ProxyMeta.Embedded {
-			allowedPeers[p.ID] = struct{}{}
-		}
-	}
 	return allowedPeers, nil
 }
 

management/server/account_test.go

@@ -3970,96 +3970,6 @@ func TestDefaultAccountManager_UpdateAccountSettings_NetworkRangeChange(t *testi
 	}
 }
 
-// TestDefaultAccountManager_UpdateAccountSettings_NetworkRangePreserved guards against
-// peer IP reallocation when a settings update carries the network range that is already
-// in use. Legacy accounts have Settings.NetworkRange unset in the DB while network.Net
-// holds the actual allocated overlay; the dashboard backfills the GET response from
-// network.Net and echoes the value back on PUT, so the diff must be against the
-// effective range to avoid renumbering every peer on an unrelated settings change.
-func TestDefaultAccountManager_UpdateAccountSettings_NetworkRangePreserved(t *testing.T) {
-	manager, _, account, peer1, peer2, peer3 := setupNetworkMapTest(t)
-	ctx := context.Background()
-
-	settings, err := manager.Store.GetAccountSettings(ctx, store.LockingStrengthNone, account.Id)
-	require.NoError(t, err)
-	require.False(t, settings.NetworkRange.IsValid(), "precondition: new accounts leave Settings.NetworkRange unset")
-
-	network, err := manager.Store.GetAccountNetwork(ctx, store.LockingStrengthNone, account.Id)
-	require.NoError(t, err)
-	require.NotNil(t, network.Net.IP, "precondition: network.Net should be allocated")
-	addr, ok := netip.AddrFromSlice(network.Net.IP)
-	require.True(t, ok)
-	ones, _ := network.Net.Mask.Size()
-	effective := netip.PrefixFrom(addr.Unmap(), ones)
-	require.True(t, effective.IsValid())
-
-	before := map[string]netip.Addr{peer1.ID: peer1.IP, peer2.ID: peer2.IP, peer3.ID: peer3.IP}
-
-	// Round-trip the effective range as if the dashboard echoed back the GET-backfilled value.
-	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
-		PeerLoginExpirationEnabled: true,
-		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
-		NetworkRange:               effective,
-		Extra:                      &types.ExtraSettings{},
-	})
-	require.NoError(t, err)
-
-	peers, err := manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
-	require.NoError(t, err)
-	require.Len(t, peers, len(before))
-	for _, p := range peers {
-		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change when range matches effective", p.ID)
-	}
-
-	// Carrying the same range with host bits set must also be a no-op once canonicalized.
-	hostBitsForm := netip.PrefixFrom(peer1.IP, ones)
-	require.NotEqual(t, effective, hostBitsForm, "precondition: host-bit form should differ before masking")
-	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
-		PeerLoginExpirationEnabled: true,
-		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
-		NetworkRange:               hostBitsForm,
-		Extra:                      &types.ExtraSettings{},
-	})
-	require.NoError(t, err)
-
-	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
-	require.NoError(t, err)
-	for _, p := range peers {
-		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change for host-bit-set equivalent range", p.ID)
-	}
-
-	// Omitting NetworkRange (invalid prefix) must also be a no-op.
-	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
-		PeerLoginExpirationEnabled: true,
-		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
-		Extra:                      &types.ExtraSettings{},
-	})
-	require.NoError(t, err)
-
-	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
-	require.NoError(t, err)
-	for _, p := range peers {
-		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change when NetworkRange omitted", p.ID)
-	}
-
-	// Sanity: an actually different range still triggers reallocation.
-	newRange := netip.MustParsePrefix("100.99.0.0/16")
-	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
-		PeerLoginExpirationEnabled: true,
-		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
-		NetworkRange:               newRange,
-		Extra:                      &types.ExtraSettings{},
-	})
-	require.NoError(t, err)
-
-	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
-	require.NoError(t, err)
-	for _, p := range peers {
-		assert.True(t, newRange.Contains(p.IP), "peer %s should be in new range %s, got %s", p.ID, newRange, p.IP)
-		assert.NotEqual(t, before[p.ID], p.IP, "peer %s IP should change on real range update", p.ID)
-	}
-}
-
 func TestDefaultAccountManager_UpdateAccountSettings_IPv6EnabledGroups(t *testing.T) {
 	manager, _, account, peer1, peer2, peer3 := setupNetworkMapTest(t)
 	ctx := context.Background()

management/server/peer.go

@@ -762,19 +762,16 @@ func (am *DefaultAccountManager) AddPeer(ctx context.Context, accountID, setupKe
 		newPeer.IP = freeIP
 
 		if len(settings.IPv6EnabledGroups) > 0 && network.NetV6.IP != nil {
-			// Embedded proxy peers are not group members but participate in any
-			// IPv6-enabled overlay so reverse-proxy traffic reaches v6-only peers.
-			allocate := peer.ProxyMeta.Embedded
-			if !allocate {
-				var allGroupID string
-				if allGroup, err := am.Store.GetGroupByName(ctx, store.LockingStrengthNone, accountID, types.GroupAllName); err == nil {
-					allGroupID = allGroup.ID
-				} else {
+			var allGroupID string
+			if !peer.ProxyMeta.Embedded {
+				allGroup, err := am.Store.GetGroupByName(ctx, store.LockingStrengthNone, accountID, "All")
+				if err != nil {
 					log.WithContext(ctx).Debugf("get All group for IPv6 allocation: %v", err)
+				} else {
+					allGroupID = allGroup.ID
 				}
-				allocate = peerWillHaveIPv6(settings, peerAddConfig.GroupsToAdd, allGroupID)
 			}
-			if allocate {
+			if peerWillHaveIPv6(settings, peerAddConfig.GroupsToAdd, allGroupID) {
 				v6Prefix, err := netip.ParsePrefix(network.NetV6.String())
 				if err != nil {
 					return nil, nil, nil, fmt.Errorf("parse IPv6 prefix: %w", err)

management/server/store/sql_store.go

@@ -8,7 +8,6 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
-	"net/url"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -2795,27 +2794,12 @@ func NewSqliteStore(ctx context.Context, dataDir string, metrics telemetry.AppMe
 		connStr = filepath.Join(dataDir, filePath)
 	}
 
-	// Compose query parameters. User-provided ?_busy_timeout (or its mattn alias
-	// ?_timeout) overrides our default; otherwise inject 30s so SQLite waits at
-	// most that long on a lock instead of blocking the only Go-side connection.
-	// mattn/go-sqlite3 applies PRAGMA from the DSN on every fresh connection, so
-	// the value survives ConnMaxIdleTime/ConnMaxLifetime recycling. cache=shared
-	// stays the default on non-Windows for the same reason as before.
-	parsed, _ := url.ParseQuery(query)
-	var defaults []string
-	if parsed.Get("_busy_timeout") == "" && parsed.Get("_timeout") == "" {
-		defaults = append(defaults, "_busy_timeout=30000")
-	}
-	if !hasQuery && runtime.GOOS != "windows" {
-		// To avoid `The process cannot access the file because it is being used by another process` on Windows
-		defaults = append(defaults, "cache=shared")
-	}
-	parts := defaults
+	// Append query parameters: user-provided take precedence, otherwise default to cache=shared on non-Windows
 	if hasQuery {
-		parts = append(parts, query)
-	}
-	if len(parts) > 0 {
-		connStr += "?" + strings.Join(parts, "&")
+		connStr += "?" + query
+	} else if runtime.GOOS != "windows" {
+		// To avoid `The process cannot access the file because it is being used by another process` on Windows
+		connStr += "?cache=shared"
 	}
 
 	db, err := gorm.Open(sqlite.Open(connStr), getGormConfig())
@@ -3418,7 +3402,7 @@ func (s *SqlStore) IncrementNetworkSerial(ctx context.Context, accountId string)
 }
 
 func (s *SqlStore) ExecuteInTransaction(ctx context.Context, operation func(store Store) error) error {
-	timeoutCtx, cancel := context.WithTimeout(ctx, s.transactionTimeout)
+	timeoutCtx, cancel := context.WithTimeout(context.Background(), s.transactionTimeout)
 	defer cancel()
 
 	startTime := time.Now()

management/server/store/sql_store_test.go

@@ -4592,55 +4592,3 @@ func TestSqlStore_DeleteZoneDNSRecords(t *testing.T) {
 	require.NoError(t, err)
 	assert.Equal(t, 0, len(remainingRecords))
 }
-
-// TestNewSqliteStore_BusyTimeoutApplied opens a fresh SQLite store and verifies
-// that the _busy_timeout DSN parameter took effect at the driver level. Without
-// this, lock contention on the single SQLite connection waits indefinitely on
-// the Go side and can be hidden behind the 5-minute transactionTimeout.
-func TestNewSqliteStore_BusyTimeoutApplied(t *testing.T) {
-	dir := t.TempDir()
-	store, err := NewSqliteStore(context.Background(), dir, nil, true)
-	require.NoError(t, err)
-	t.Cleanup(func() {
-		_ = store.Close(context.Background())
-	})
-
-	sqlDB, err := store.db.DB()
-	require.NoError(t, err)
-	row := sqlDB.QueryRow("PRAGMA busy_timeout")
-	var busyTimeout int
-	require.NoError(t, row.Scan(&busyTimeout))
-	assert.Equal(t, 30000, busyTimeout, "SQLite busy_timeout must be set via DSN so it survives connection recycling")
-}
-
-// TestNewSqliteStore_BusyTimeoutRespectsUserOverride confirms that an operator
-// passing _busy_timeout or its mattn alias _timeout via NB_STORE_ENGINE_SQLITE_FILE
-// wins over our 30s default. This guards the DSN merge logic in NewSqliteStore.
-func TestNewSqliteStore_BusyTimeoutRespectsUserOverride(t *testing.T) {
-	cases := []struct {
-		name     string
-		envFile  string
-		expected int
-	}{
-		{name: "explicit _busy_timeout wins", envFile: "store.db?_busy_timeout=5000", expected: 5000},
-		{name: "alias _timeout wins", envFile: "store.db?_timeout=7000", expected: 7000},
-	}
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv("NB_STORE_ENGINE_SQLITE_FILE", tc.envFile)
-			dir := t.TempDir()
-			store, err := NewSqliteStore(context.Background(), dir, nil, true)
-			require.NoError(t, err)
-			t.Cleanup(func() {
-				_ = store.Close(context.Background())
-			})
-
-			sqlDB, err := store.db.DB()
-			require.NoError(t, err)
-			row := sqlDB.QueryRow("PRAGMA busy_timeout")
-			var busyTimeout int
-			require.NoError(t, row.Scan(&busyTimeout))
-			assert.Equal(t, tc.expected, busyTimeout)
-		})
-	}
-}

management/server/types/account.go

@@ -598,21 +598,28 @@ func (a *Account) GetPeerGroups(peerID string) LookupMap {
 	return groupList
 }
 
-// PeerIPv6Allowed reports whether the given peer participates in the IPv6 overlay.
+// PeerIPv6Allowed reports whether the given peer is in any of the account's IPv6 enabled groups.
 // Returns false if IPv6 is disabled or no groups are configured.
 func (a *Account) PeerIPv6Allowed(peerID string) bool {
-	_, ok := a.peerIPv6AllowedSet()[peerID]
-	return ok
+	if len(a.Settings.IPv6EnabledGroups) == 0 {
+		return false
+	}
+
+	for _, groupID := range a.Settings.IPv6EnabledGroups {
+		group, ok := a.Groups[groupID]
+		if !ok {
+			continue
+		}
+		if slices.Contains(group.Peers, peerID) {
+			return true
+		}
+	}
+	return false
 }
 
-// peerIPv6AllowedSet returns the set of peer IDs that participate in the IPv6 overlay:
-// members of any IPv6-enabled group, plus every embedded proxy peer (which sit outside
-// regular group membership but must reach v6-enabled peers).
+// peerIPv6AllowedSet returns a set of peer IDs that belong to any IPv6-enabled group.
 func (a *Account) peerIPv6AllowedSet() map[string]struct{} {
 	result := make(map[string]struct{})
-	if len(a.Settings.IPv6EnabledGroups) == 0 {
-		return result
-	}
 	for _, groupID := range a.Settings.IPv6EnabledGroups {
 		group, ok := a.Groups[groupID]
 		if !ok {
@@ -622,11 +629,6 @@ func (a *Account) peerIPv6AllowedSet() map[string]struct{} {
 			result[peerID] = struct{}{}
 		}
 	}
-	for id, p := range a.Peers {
-		if p != nil && p.ProxyMeta.Embedded {
-			result[id] = struct{}{}
-		}
-	}
 	return result
 }
 

management/server/types/group.go

@@ -92,12 +92,9 @@ func (g *Group) HasPeers() bool {
 	return len(g.Peers) > 0
 }
 
-// GroupAllName is the reserved name of the default group that contains every peer in an account.
-const GroupAllName = "All"
-
 // IsGroupAll checks if the group is a default "All" group.
 func (g *Group) IsGroupAll() bool {
-	return g.Name == GroupAllName
+	return g.Name == "All"
 }
 
 // AddPeer adds peerID to Peers if not present, returning true if added.

management/server/types/ipv6_groups_test.go

@@ -232,33 +232,3 @@ func TestIPv6RecalculationOnGroupChange(t *testing.T) {
 		assert.True(t, account.PeerIPv6Allowed("peer3"), "peer3 now in infra")
 	})
 }
-
-func TestPeerIPv6AllowedEmbeddedProxy(t *testing.T) {
-	account := &Account{
-		Peers: map[string]*nbpeer.Peer{
-			"peer1": {ID: "peer1"},
-			"proxy": {ID: "proxy", ProxyMeta: nbpeer.ProxyMeta{Embedded: true, Cluster: "netbird.test"}},
-		},
-		Groups: map[string]*Group{
-			"group-devs": {ID: "group-devs", Peers: []string{"peer1"}},
-		},
-		Settings: &Settings{},
-	}
-
-	t.Run("embedded proxy allowed when any v6 group exists, without group membership", func(t *testing.T) {
-		account.Settings.IPv6EnabledGroups = []string{"group-devs"}
-		assert.True(t, account.PeerIPv6Allowed("proxy"), "embedded proxy participates in v6 overlay")
-		assert.True(t, account.PeerIPv6Allowed("peer1"), "regular peer in enabled group still allowed")
-	})
-
-	t.Run("embedded proxy denied when no v6 group enabled", func(t *testing.T) {
-		account.Settings.IPv6EnabledGroups = nil
-		assert.False(t, account.PeerIPv6Allowed("proxy"), "v6 disabled account-wide denies embedded proxies too")
-	})
-
-	t.Run("non-embedded peer outside any enabled group is not pulled in", func(t *testing.T) {
-		account.Settings.IPv6EnabledGroups = []string{"group-devs"}
-		account.Peers["lonely"] = &nbpeer.Peer{ID: "lonely"}
-		assert.False(t, account.PeerIPv6Allowed("lonely"), "embedded-proxy bypass must not leak to regular peers")
-	})
-}

util/log.go

@@ -1,16 +1,15 @@
 package util
 
 import (
-	"fmt"
 	"io"
 	"os"
 	"path/filepath"
 	"slices"
 	"strconv"
 
-	"github.com/DeRuina/timberjack"
 	log "github.com/sirupsen/logrus"
 	"google.golang.org/grpc/grpclog"
+	"gopkg.in/natefinch/lumberjack.v2"
 
 	"github.com/netbirdio/netbird/formatter"
 )
@@ -60,12 +59,7 @@ func InitLogger(logger *log.Logger, logLevel string, logs ...string) error {
 		case "":
 			logger.Warnf("empty log path received: %#v", logPath)
 		default:
-			writer, err := setupLogFile(logPath, isRotationDisabled(logger))
-			if err != nil {
-				logger.Errorf("failed setting up log file: %s, %s", logPath, err)
-				return err
-			}
-			writers = append(writers, writer)
+			writers = append(writers, newRotatedOutput(logPath))
 		}
 	}
 
@@ -100,43 +94,17 @@ func FindFirstLogPath(logs []string) string {
 	return ""
 }
 
-func isRotationDisabled(logger *log.Logger) bool {
-	v, _ := os.LookupEnv("NB_LOG_DISABLE_ROTATION")
-	disabled, _ := strconv.ParseBool(v)
-	if disabled {
-		logger.Warnf("log rotation is disabled by env flag")
-		return true
-	}
-	conflict, configPath := FindFirstLogrotateConflict()
-	if conflict {
-		logger.Warnf("log rotation conflict detected in: %#v, rotation is disabled", configPath)
-		return true
-	}
-	return false
-}
-
-func setupLogFile(logPath string, disableRotation bool) (io.Writer, error) {
-	if disableRotation {
-		file, err := os.OpenFile(logPath, os.O_WRONLY|os.O_APPEND|os.O_CREATE, 0600)
-		if err != nil {
-			return nil, fmt.Errorf("failed opening log file: %s", err)
-		}
-		return file, nil
-	}
-	return newRotatedOutput(logPath), nil
-}
-
 func newRotatedOutput(logPath string) io.Writer {
 	maxLogSize := getLogMaxSize()
-	timberjackLogger := &timberjack.Logger{
+	lumberjackLogger := &lumberjack.Logger{
 		// Log file absolute path, os agnostic
-		Filename:    filepath.ToSlash(logPath),
-		MaxSize:     maxLogSize, // MB
-		MaxBackups:  10,
-		MaxAge:      30, // days
-		Compression: "gzip",
+		Filename:   filepath.ToSlash(logPath),
+		MaxSize:    maxLogSize, // MB
+		MaxBackups: 10,
+		MaxAge:     30, // days
+		Compress:   true,
 	}
-	return timberjackLogger
+	return lumberjackLogger
 }
 
 func setGRPCLibLogger(logger *log.Logger) {

util/log_test.go

@@ -1,96 +0,0 @@
-package util
-
-import (
-	"io"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-	"time"
-
-	log "github.com/sirupsen/logrus"
-	"github.com/stretchr/testify/require"
-)
-
-// TestSetupLogFile_RotatesOnSize drives >MaxSize bytes through the writer
-// returned by setupLogFile and asserts a backup file appears.
-func TestSetupLogFile_RotatesOnSize(t *testing.T) {
-	t.Setenv("NB_LOG_MAX_SIZE_MB", "1")
-
-	dir := t.TempDir()
-	logPath := filepath.Join(dir, "netbird.log")
-
-	w, err := setupLogFile(logPath, false)
-	require.NoError(t, err)
-	t.Cleanup(func() {
-		if c, ok := w.(io.Closer); ok {
-			_ = c.Close()
-		}
-	})
-
-	chunk := []byte(strings.Repeat("x", 64*1024) + "\n")
-	for range 20 {
-		_, err := w.Write(chunk)
-		require.NoError(t, err)
-	}
-
-	info, err := os.Stat(logPath)
-	require.NoError(t, err)
-	require.Less(t, info.Size(), int64(1<<20),
-		"active log should be < 1 MB after rotation, got %d", info.Size())
-
-	require.Eventually(t, func() bool {
-		entries, _ := os.ReadDir(dir)
-		for _, e := range entries {
-			name := e.Name()
-			if name == filepath.Base(logPath) {
-				continue
-			}
-			if strings.HasPrefix(name, "netbird-") && strings.HasSuffix(name, ".log.gz") {
-				return true
-			}
-		}
-		return false
-	}, 5*time.Second, 50*time.Millisecond, "expected a rotated backup file in %s", dir)
-}
-
-// TestSetupLogFile_RotationDisabled verifies that with rotation off, the file
-// grows past MaxSize and no backups are created.
-func TestSetupLogFile_RotationDisabled(t *testing.T) {
-	t.Setenv("NB_LOG_MAX_SIZE_MB", "1")
-
-	dir := t.TempDir()
-	logPath := filepath.Join(dir, "netbird.log")
-
-	w, err := setupLogFile(logPath, true)
-	require.NoError(t, err)
-
-	f, ok := w.(*os.File)
-	require.True(t, ok, "expected plain *os.File when rotation is disabled, got %T", w)
-	t.Cleanup(func() { _ = f.Close() })
-
-	chunk := []byte(strings.Repeat("y", 64*1024) + "\n")
-	for range 20 {
-		_, err := w.Write(chunk)
-		require.NoError(t, err)
-	}
-
-	info, err := os.Stat(logPath)
-	require.NoError(t, err)
-	require.GreaterOrEqual(t, info.Size(), int64(1<<20),
-		"file should exceed MaxSize when rotation is disabled, got %d", info.Size())
-
-	entries, err := os.ReadDir(dir)
-	require.NoError(t, err)
-	require.Len(t, entries, 1, "no backup files should exist when rotation is disabled, got %v", entries)
-}
-
-// TestIsRotationDisabled_EnvFlag covers the NB_LOG_DISABLE_ROTATION env path.
-// The logrotate-conflict branch is exercised separately on linux.
-func TestIsRotationDisabled_EnvFlag(t *testing.T) {
-	logger := log.New()
-	logger.SetOutput(io.Discard)
-
-	t.Setenv("NB_LOG_DISABLE_ROTATION", "true")
-	require.True(t, isRotationDisabled(logger))
-}

util/logrotate_linux.go

@@ -1,93 +0,0 @@
-//go:build linux
-
-package util
-
-import (
-	"bufio"
-	"errors"
-	"io/fs"
-	"os"
-	"path/filepath"
-	"strings"
-
-	log "github.com/sirupsen/logrus"
-)
-
-const (
-	defaultLogrotateConfPath = "/etc/logrotate.conf"
-	defaultLogrotateConfDir  = "/etc/logrotate.d"
-	netbirdString            = "netbird"
-)
-
-// FindLogrotateConflicts scans the standard logrotate locations for
-// indications of conflict with netbird. It returns true and the config file
-// path if a conflict was found.
-func FindFirstLogrotateConflict() (bool, string) {
-	return findFirstLogrotateConflictIn(defaultLogrotateConfPath, defaultLogrotateConfDir)
-}
-
-func findFirstLogrotateConflictIn(confPath, confDir string) (bool, string) {
-	for _, f := range listLogrotateConfigs(confPath, confDir) {
-		present, err := scanLogrotateFile(f, netbirdString)
-		if err != nil {
-			if !errors.Is(err, fs.ErrNotExist) {
-				log.Debugf("scan %s: %v", f, err)
-			}
-			continue
-		}
-		if present {
-			return present, f
-		}
-	}
-	return false, ""
-}
-
-// listLogrotateConfigs returns all config files for logrotate.
-func listLogrotateConfigs(confPath, confDir string) []string {
-	files := []string{confPath}
-	entries, err := os.ReadDir(confDir)
-	if err != nil {
-		return files
-	}
-	for _, e := range entries {
-		if e.IsDir() {
-			continue
-		}
-		files = append(files, filepath.Join(confDir, e.Name()))
-	}
-	return files
-}
-
-// scanLogrotateFile reads a config and reports if a non-comment line
-// contains the given substring.
-func scanLogrotateFile(path string, substring string) (bool, error) {
-	f, err := os.Open(path)
-	if err != nil {
-		return false, err
-	}
-	defer func() {
-		if err := f.Close(); err != nil {
-			log.Debugf("close %s: %v", path, err)
-		}
-	}()
-
-	scanner := bufio.NewScanner(f)
-	for scanner.Scan() {
-		line := strings.TrimSpace(stripLogrotateComment(scanner.Text()))
-		if line == "" {
-			continue
-		}
-		if strings.Contains(line, substring) {
-			return true, nil
-		}
-	}
-	if err := scanner.Err(); err != nil {
-		return false, err
-	}
-	return false, nil
-}
-
-func stripLogrotateComment(line string) string {
-	before, _, _ := strings.Cut(line, "#")
-	return before
-}

util/logrotate_linux_test.go

@@ -1,95 +0,0 @@
-//go:build linux
-
-package util
-
-import (
-	"os"
-	"path/filepath"
-	"testing"
-
-	"github.com/stretchr/testify/require"
-)
-
-func TestFindFirstLogrotateConflict(t *testing.T) {
-	t.Run("conflict in confDir", func(t *testing.T) {
-		confPath, confDir := newLogrotateLayout(t)
-		conflictPath := filepath.Join(confDir, "netbird")
-		writeLogrotateConfig(t, conflictPath, `/var/log/netbird/*.log {
-    daily
-    rotate 7
-}`)
-		writeLogrotateConfig(t, filepath.Join(confDir, "nginx"), `/var/log/nginx/*.log { daily }`)
-
-		got, path := findFirstLogrotateConflictIn(confPath, confDir)
-		require.True(t, got)
-		require.Equal(t, conflictPath, path)
-	})
-
-	t.Run("conflict in main conf file", func(t *testing.T) {
-		confPath, confDir := newLogrotateLayout(t)
-		writeLogrotateConfig(t, confPath, `weekly
-rotate 4
-include /etc/logrotate.d
-/var/log/netbird/client.log { rotate 5 }`)
-
-		got, path := findFirstLogrotateConflictIn(confPath, confDir)
-		require.True(t, got)
-		require.Equal(t, confPath, path)
-	})
-
-	t.Run("no conflict when netbird is absent", func(t *testing.T) {
-		confPath, confDir := newLogrotateLayout(t)
-		writeLogrotateConfig(t, filepath.Join(confDir, "nginx"), `/var/log/nginx/*.log { daily }`)
-		writeLogrotateConfig(t, filepath.Join(confDir, "syslog"), `/var/log/syslog { weekly }`)
-
-		got, path := findFirstLogrotateConflictIn(confPath, confDir)
-		require.False(t, got)
-		require.Empty(t, path)
-	})
-
-	t.Run("commented-out netbird line is ignored", func(t *testing.T) {
-		confPath, confDir := newLogrotateLayout(t)
-		writeLogrotateConfig(t, filepath.Join(confDir, "misc"), `# /var/log/netbird/*.log { daily }
-/var/log/other.log { weekly }`)
-
-		got, path := findFirstLogrotateConflictIn(confPath, confDir)
-		require.False(t, got)
-		require.Empty(t, path)
-	})
-
-	t.Run("subdirectories in confDir are ignored", func(t *testing.T) {
-		confPath, confDir := newLogrotateLayout(t)
-		sub := filepath.Join(confDir, "nested")
-		require.NoError(t, os.MkdirAll(sub, 0o755))
-		writeLogrotateConfig(t, filepath.Join(sub, "netbird"), `/var/log/netbird/*.log { daily }`)
-
-		got, path := findFirstLogrotateConflictIn(confPath, confDir)
-		require.False(t, got)
-		require.Empty(t, path)
-	})
-
-	t.Run("missing paths return no conflict", func(t *testing.T) {
-		dir := t.TempDir()
-		got, path := findFirstLogrotateConflictIn(
-			filepath.Join(dir, "does-not-exist.conf"),
-			filepath.Join(dir, "does-not-exist.d"),
-		)
-		require.False(t, got)
-		require.Empty(t, path)
-	})
-}
-
-// newLogrotateLayout creates a temp logrotate.conf path and logrotate.d dir,
-// returning their paths. The conf file itself is not created.
-func newLogrotateLayout(t *testing.T) (confPath, confDir string) {
-	t.Helper()
-	root := t.TempDir()
-	confDir = filepath.Join(root, "logrotate.d")
-	require.NoError(t, os.MkdirAll(confDir, 0o755))
-	return filepath.Join(root, "logrotate.conf"), confDir
-}
-
-func writeLogrotateConfig(t *testing.T, path, body string) {
-	t.Helper()
-	require.NoError(t, os.WriteFile(path, []byte(body), 0o644))
-}

util/logrotate_nonlinux.go

@@ -1,10 +0,0 @@
-//go:build !linux
-
-package util
-
-// FindLogrotateConflicts scans the standard logrotate locations for
-// indications of conflict with netbird. It will always return false for
-// non-linux devices.
-func FindFirstLogrotateConflict() (bool, string) {
-	return false, ""
-}