added missing func.

- Skip systemd-resolved initialization on Android (ChromeOS crash fix)
- Skip system DNS discovery commands on iOS mobile (sandbox restrictions)
- Skip route-based DNS discovery on Android
- Skip systemd resolver on Android
- Add mobile platform checks to prevent sandbox access violations

These changes ensure ctrld works correctly in mobile sandboxed environments
where system commands and file access are restricted.

.github/workflows/ci.yml

@@ -9,7 +9,7 @@ jobs:
       fail-fast: false
       matrix:
         os: ["windows-latest", "ubuntu-latest", "macOS-latest"]
-        go: ["1.24.x"]
+        go: ["1.25.x"]
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v3
@@ -21,6 +21,6 @@ jobs:
       - run: "go test -race ./..."
       - uses: dominikh/staticcheck-action@v1.4.0
         with:
-          version: "2025.1.1"
+          version: "2026.1"
           install-go: false
           cache-key: ${{ matrix.go }}

cmd/cli/cli.go

@@ -638,6 +638,19 @@ const defaultDeactivationPin = -1
 // cdDeactivationPin is used in cd mode to decide whether stop and uninstall commands can be run.
 var cdDeactivationPin atomic.Int64
 
+// Brute-force protection for the deactivation PIN endpoint on the control socket.
+// After deactivationMaxFailedAttempts consecutive wrong PINs, further attempts are
+// rejected for deactivationLockoutSeconds. Counter resets on a correct PIN.
+const (
+	deactivationMaxFailedAttempts = 5
+	deactivationLockoutSeconds    = 60
+)
+
+var (
+	deactivationFailedAttempts atomic.Int64
+	deactivationLockedUntil    atomic.Int64
+)
+
 func init() {
 	cdDeactivationPin.Store(defaultDeactivationPin)
 }
@@ -1245,7 +1258,7 @@ func tryUpdateListenerConfigIntercept(cfg *ctrld.Config, notifyFunc func(), fata
 		return false, true
 	}
 
-	hasExplicitConfig := lc.IP != "" && lc.IP != "0.0.0.0" && lc.Port != 0
+	hasExplicitConfig := isExplicitInterceptListener(lc.IP, lc.Port)
 	if !hasExplicitConfig {
 		// Set defaults for intercept mode
 		if lc.IP == "" || lc.IP == "0.0.0.0" {
@@ -1303,6 +1316,16 @@ func tryUpdateListenerConfigIntercept(cfg *ctrld.Config, notifyFunc func(), fata
 	return updated, false
 }
 
+func isExplicitInterceptListener(ip string, port int) bool {
+	if ip == "" || ip == "0.0.0.0" || port == 0 {
+		return false
+	}
+	// 127.0.0.1:53 is the default macOS DNS-intercept listener. It can appear
+	// in generated/custom Control D configs, but it should still be allowed to
+	// fall back to 127.0.0.1:5354 when mDNSResponder already owns port 53.
+	return !(ip == "127.0.0.1" && port == 53)
+}
+
 // tryUpdateListenerConfig tries updating listener config with a working one.
 // If fatal is true, and there's listen address conflicted, the function do
 // fatal error.
@@ -1809,6 +1832,9 @@ var errInvalidDeactivationPin = errors.New("deactivation pin is invalid")
 // errRequiredDeactivationPin indicates that the deactivation pin is required but not provided by users.
 var errRequiredDeactivationPin = errors.New("deactivation pin is required to stop or uninstall the service")
 
+// errTooManyDeactivationPin represents an error indicating excessive deactivation PIN request attempts.
+var errTooManyDeactivationPin = errors.New("too many request attempts")
+
 // checkDeactivationPin validates if the deactivation pin matches one in ControlD config.
 func checkDeactivationPin(s service.Service, stopCh chan struct{}) error {
 	mainLog.Load().Debug().Msg("Checking deactivation pin")
@@ -1837,6 +1863,9 @@ func checkDeactivationPin(s service.Service, stopCh chan struct{}) error {
 		case http.StatusBadRequest:
 			mainLog.Load().Error().Msg(errRequiredDeactivationPin.Error())
 			return errRequiredDeactivationPin // pin is required
+		case http.StatusTooManyRequests:
+			mainLog.Load().Error().Msg(errTooManyDeactivationPin.Error())
+			return errTooManyDeactivationPin
 		case http.StatusOK:
 			return nil // valid pin
 		case http.StatusNotFound:
@@ -1849,7 +1878,9 @@ func checkDeactivationPin(s service.Service, stopCh chan struct{}) error {
 
 // isCheckDeactivationPinErr reports whether there is an error during check deactivation pin process.
 func isCheckDeactivationPinErr(err error) bool {
-	return errors.Is(err, errInvalidDeactivationPin) || errors.Is(err, errRequiredDeactivationPin)
+	return errors.Is(err, errInvalidDeactivationPin) ||
+		errors.Is(err, errRequiredDeactivationPin) ||
+		errors.Is(err, errTooManyDeactivationPin)
 }
 
 // ensureUninstall ensures that s.Uninstall will remove ctrld service from system completely.
@@ -2002,17 +2033,25 @@ func doValidateCdRemoteConfig(cdUID string, fatal bool) error {
 	} else {
 		if errors.As(cfgErr, &viper.ConfigParseError{}) {
 			if configStr, _ := base64.StdEncoding.DecodeString(rc.Ctrld.CustomConfig); len(configStr) > 0 {
-				tmpDir := os.TempDir()
-				tmpConfFile := filepath.Join(tmpDir, "ctrld.toml")
 				errorLogged := false
-				// Write remote config to a temporary file to get details error.
+				// Write remote config to a uniquely named temporary file to get detailed error.
-				if we := os.WriteFile(tmpConfFile, configStr, 0600); we == nil {
+				if tmpFile, tmpErr := os.CreateTemp("", "ctrld-*.toml"); tmpErr == nil {
+					tmpConfFile := tmpFile.Name()
+					if _, err := tmpFile.Write(configStr); err != nil {
+						mainLog.Load().Error().Err(err).Msg("failed to write temporary config file")
+					}
+					if err := tmpFile.Close(); err != nil {
+						mainLog.Load().Error().Err(err).Msg("failed to save temporary config file")
+
+					}
 					if de := decoderErrorFromTomlFile(tmpConfFile); de != nil {
 						row, col := de.Position()
 						mainLog.Load().Error().Msgf("failed to parse custom config at line: %d, column: %d, error: %s", row, col, de.Error())
 						errorLogged = true
 					}
-					_ = os.Remove(tmpConfFile)
+					if err := os.Remove(tmpConfFile); err != nil {
+						mainLog.Load().Error().Err(err).Msg("failed to remove temporary config file")
+					}
 				}
 				// If we could not log details error, emit what we have already got.
 				if !errorLogged {

cmd/cli/cli_intercept_listener_test.go

@@ -0,0 +1,28 @@
+package cli
+
+import "testing"
+
+func TestIsExplicitInterceptListener(t *testing.T) {
+	tests := []struct {
+		name string
+		ip   string
+		port int
+		want bool
+	}{
+		{name: "empty", ip: "", port: 0, want: false},
+		{name: "wildcard", ip: "0.0.0.0", port: 53, want: false},
+		{name: "zero port", ip: "127.0.0.1", port: 0, want: false},
+		{name: "default intercept listener", ip: "127.0.0.1", port: 53, want: false},
+		{name: "fallback port explicit", ip: "127.0.0.1", port: 5354, want: true},
+		{name: "custom loopback explicit", ip: "127.0.0.2", port: 53, want: true},
+		{name: "custom address explicit", ip: "192.0.2.10", port: 53, want: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := isExplicitInterceptListener(tt.ip, tt.port); got != tt.want {
+				t.Fatalf("isExplicitInterceptListener(%q, %d) = %v, want %v", tt.ip, tt.port, got, tt.want)
+			}
+		})
+	}
+}

cmd/cli/control_server.go

@@ -59,12 +59,18 @@ func newControlServer(addr string) (*controlServer, error) {
 func (s *controlServer) start() error {
 	_ = os.Remove(s.addr)
 	unixListener, err := net.Listen("unix", s.addr)
-	if l, ok := unixListener.(*net.UnixListener); ok {
-		l.SetUnlinkOnClose(true)
-	}
 	if err != nil {
 		return err
 	}
+	// Restrict socket permissions to owner-only (0600) so that only the
+	// process owner (typically root) can connect. Defense-in-depth since
+	// the control server endpoints carry no authentication of their own.
+	if err := os.Chmod(s.addr, 0600); err != nil {
+		return err
+	}
+	if l, ok := unixListener.(*net.UnixListener); ok {
+		l.SetUnlinkOnClose(true)
+	}
 	go s.server.Serve(unixListener)
 	return nil
 }
@@ -219,6 +225,12 @@ func (p *prog) registerControlServerHandler() {
 			return
 		}
 
+		// Reject further attempts while locked out due to repeated wrong PINs.
+		if now := time.Now().Unix(); now < deactivationLockedUntil.Load() {
+			w.WriteHeader(http.StatusTooManyRequests)
+			return
+		}
+
 		// Re-fetch pin code from API.
 		rcReq := &controld.ResolverConfigRequest{
 			RawUID:   cdUID,
@@ -252,6 +264,7 @@ func (p *prog) registerControlServerHandler() {
 		switch req.Pin {
 		case cdDeactivationPin.Load():
 			code = http.StatusOK
+			deactivationFailedAttempts.Store(0)
 			select {
 			case p.pinCodeValidCh <- struct{}{}:
 			default:
@@ -259,6 +272,11 @@ func (p *prog) registerControlServerHandler() {
 		case defaultDeactivationPin:
 			// If the pin code was set, but users do not provide --pin, return proper code to client.
 			code = http.StatusBadRequest
+		default:
+			if deactivationFailedAttempts.Add(1) >= deactivationMaxFailedAttempts {
+				deactivationLockedUntil.Store(time.Now().Unix() + deactivationLockoutSeconds)
+				deactivationFailedAttempts.Store(0)
+			}
 		}
 		w.WriteHeader(code)
 	}))

cmd/cli/dns_intercept_darwin.go

@@ -1207,7 +1207,6 @@ func stringSlicesEqual(a, b []string) bool {
 	return true
 }
 
-
 // pfStartStabilization enters stabilization mode, suppressing all pf restores
 // until the VPN's ruleset stops changing. This prevents a death spiral where
 // ctrld and the VPN repeatedly overwrite each other's pf rules.
@@ -1284,6 +1283,10 @@ func (p *prog) pfStabilizationLoop(ctx context.Context, stableRequired time.Dura
 			p.pfStabilizing.Store(false)
 			mainLog.Load().Info().Msgf("DNS intercept: pf stable for %s — restoring anchor rules", stableRequired)
 			p.ensurePFAnchorActive()
+			routes, domainlessServers, exemptions := p.refreshDNSAfterVPNSettle("pf_stabilized")
+			if routes == 0 && domainlessServers == 0 && exemptions == 0 {
+				p.scheduleDNSAfterVPNSettleRefresh("pf_stabilized_followup", pfAnchorRecheckDelayLong)
+			}
 			p.pfLastRestoreTime.Store(time.Now().UnixMilli())
 			return
 		}
@@ -1446,6 +1449,15 @@ func (p *prog) ensurePFAnchorActive() bool {
 	return true
 }
 
+func (p *prog) scheduleDNSAfterVPNSettleRefresh(reason string, delay time.Duration) {
+	time.AfterFunc(delay, func() {
+		if p.dnsInterceptState == nil {
+			return
+		}
+		p.refreshDNSAfterVPNSettle(reason)
+	})
+}
+
 // pfWatchdog periodically checks that our pf anchor is still active.
 // Other programs (e.g., Windscribe desktop app, macOS configd) can replace
 // scheduleDelayedRechecks schedules delayed re-checks after a network change event.
@@ -1811,7 +1823,14 @@ func (p *prog) forceReloadPFMainRuleset() {
 		mainLog.Load().Error().Err(err).Msgf("DNS intercept: force reload — failed to load anchor (output: %s)", strings.TrimSpace(string(out)))
 	}
 
-	// Reset upstream transports — pf reload flushes state table, killing DoH connections.
+	// Flush stale rdr/reply states after the forced ruleset + anchor reload.
+	// Without this, macOS can keep using pre-reload state and try to send
+	// redirected DNS replies directly from loopback to tunnel client addresses
+	// (for example, 127.0.0.1:<listener> -> 100.64.0.0/10), which fails with
+	// "sendmsg: can't assign requested address".
+	flushPFStates()
+
+	// Reset upstream transports — pf reload/state flush kills existing DoH connections.
 	p.resetUpstreamTransports()
 
 	mainLog.Load().Info().Msg("DNS intercept: force reload — pf ruleset and anchor reloaded successfully")

cmd/cli/dns_intercept_settle.go

@@ -0,0 +1,50 @@
+package cli
+
+import "github.com/Control-D-Inc/ctrld"
+
+var initializeOsResolver = ctrld.InitializeOsResolver
+
+func (p *prog) refreshDNSAfterVPNSettle(reason string) (routes, domainlessServers, exemptions int) {
+	mainLog.Load().Info().Msgf("DNS intercept: refreshing OS/VPN DNS route state after VPN settle (%s)", reason)
+	ns := initializeOsResolver(true)
+	mainLog.Load().Debug().Msgf("DNS intercept: post-settle OS resolver nameservers: %v", ns)
+
+	if p.vpnDNS == nil {
+		mainLog.Load().Debug().Msg("DNS intercept: post-settle VPN DNS route refresh skipped — manager unavailable")
+		return 0, 0, 0
+	}
+
+	beforeExemptions := p.vpnDNS.CurrentExemptions()
+	routes, domainlessServers, exemptions = p.vpnDNS.RefreshRoutesOnly()
+	afterExemptions := p.vpnDNS.CurrentExemptions()
+
+	if vpnDNSExemptionsEqual(beforeExemptions, afterExemptions) {
+		mainLog.Load().Info().Msgf("DNS intercept: post-settle VPN DNS route refresh completed — %d routes, %d domainless servers, %d exemptions (pf unchanged)",
+			routes, domainlessServers, exemptions)
+		return routes, domainlessServers, exemptions
+	}
+
+	if err := p.exemptVPNDNSServers(afterExemptions); err != nil {
+		mainLog.Load().Warn().Err(err).Msg("DNS intercept: post-settle VPN DNS exemption update failed")
+	} else {
+		mainLog.Load().Info().Msgf("DNS intercept: post-settle VPN DNS exemptions changed — updated pf/WFP with %d exemptions", len(afterExemptions))
+	}
+	return routes, domainlessServers, exemptions
+}
+
+func vpnDNSExemptionsEqual(a, b []vpnDNSExemption) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	seen := make(map[vpnDNSExemption]int, len(a))
+	for _, ex := range a {
+		seen[ex]++
+	}
+	for _, ex := range b {
+		if seen[ex] == 0 {
+			return false
+		}
+		seen[ex]--
+	}
+	return true
+}

cmd/cli/dns_intercept_settle_test.go

@@ -0,0 +1,49 @@
+package cli
+
+import (
+	"context"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func TestRefreshDNSAfterVPNSettleRefreshesOSResolverAndVPNRoutes(t *testing.T) {
+	oldInitialize := initializeOsResolver
+	defer func() { initializeOsResolver = oldInitialize }()
+
+	var initialized []bool
+	initializeOsResolver = func(force bool) []string {
+		initialized = append(initialized, force)
+		return []string{"10.102.26.10:53"}
+	}
+
+	var exemptionUpdates [][]vpnDNSExemption
+	p := &prog{}
+	p.vpnDNS = newVPNDNSManager(func(exemptions []vpnDNSExemption) error {
+		exemptionUpdates = append(exemptionUpdates, append([]vpnDNSExemption{}, exemptions...))
+		return nil
+	})
+	p.vpnDNS.discoverVPNDNS = func(context.Context) []ctrld.VPNDNSConfig {
+		return []ctrld.VPNDNSConfig{{
+			InterfaceName: "utun4",
+			Servers:       []string{"10.102.26.10"},
+			Domains:       []string{"bmwgroup.net"},
+		}}
+	}
+
+	routes, domainlessServers, exemptions := p.refreshDNSAfterVPNSettle("test")
+
+	if routes != 1 || domainlessServers != 0 || exemptions != 1 {
+		t.Fatalf("expected 1 route, 0 domainless servers, 1 exemption, got routes=%d domainless=%d exemptions=%d",
+			routes, domainlessServers, exemptions)
+	}
+	if len(initialized) != 1 || !initialized[0] {
+		t.Fatalf("expected forced OS resolver refresh once, got %v", initialized)
+	}
+	if got := p.vpnDNS.UpstreamForDomain("jira.cc.bmwgroup.net."); len(got) != 1 || got[0] != "10.102.26.10" {
+		t.Fatalf("expected refreshed VPN DNS route, got %v", got)
+	}
+	if len(exemptionUpdates) != 0 {
+		t.Fatalf("expected route-only refresh to avoid pf exemption updates, got %+v", exemptionUpdates)
+	}
+}

cmd/cli/dns_proxy.go

@@ -548,6 +548,7 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 		if vpnServers := p.vpnDNS.UpstreamForDomain(domain); len(vpnServers) > 0 {
 			ctrld.Log(ctx, mainLog.Load().Debug(), "VPN DNS route matched for domain %s, using servers: %v", domain, vpnServers)
 
+			var gotTransportFailure bool
 			for _, server := range vpnServers {
 				upstreamConfig := p.vpnDNS.upstreamConfigFor(server)
 				ctrld.Log(ctx, mainLog.Load().Debug(), "Querying VPN DNS server: %s", server)
@@ -561,6 +562,7 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 				answer, err := dnsResolver.Resolve(resolveCtx, req.msg)
 				cancel()
 				if answer != nil {
+					p.vpnDNS.VPNDNSReachable()
 					ctrld.Log(ctx, mainLog.Load().Debug(), "VPN DNS query successful")
 					if p.cache != nil {
 						ttl := 60 * time.Second
@@ -573,9 +575,22 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 					}
 					return &proxyResponse{answer: answer}
 				}
+				gotTransportFailure = true
 				ctrld.Log(ctx, mainLog.Load().Debug().Err(err), "VPN DNS server %s failed", server)
 			}
 
+			// Explicit VPN DNS routes are authoritative for their suffix. If all
+			// routed servers fail at the transport layer while Windows is serving
+			// retained VPN DNS state, fail closed instead of leaking VPN/internal
+			// names to normal upstreams.
+			if gotTransportFailure && p.vpnDNS.ShouldFailClosedAfterVPNDNSTransportFailure(domain, vpnServers) {
+				ctrld.Log(ctx, mainLog.Load().Debug(),
+					"All VPN DNS servers had transport failures for %s; returning SERVFAIL while retained VPN DNS state is active", domain)
+				answer := new(dns.Msg)
+				answer.SetRcode(req.msg, dns.RcodeServerFailure)
+				return &proxyResponse{answer: answer}
+			}
+
 			ctrld.Log(ctx, mainLog.Load().Debug(), "All VPN DNS servers failed, falling back to normal upstreams")
 		}
 	}
@@ -589,13 +604,15 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 	// polluting captive portal / DHCP flows.
 	if dnsIntercept && p.vpnDNS != nil && req.ufr.matched &&
 		len(upstreams) > 0 && upstreams[0] == upstreamOS &&
-		len(req.msg.Question) > 0 && !p.isAdDomainQuery(req.msg) {
+		len(req.msg.Question) > 0 {
 		if dlServers := p.vpnDNS.DomainlessServers(); len(dlServers) > 0 {
 			domain := req.msg.Question[0].Name
 			ctrld.Log(ctx, mainLog.Load().Debug(),
 				"Split-rule query %s going to upstream.os, trying %d domain-less VPN DNS servers first: %v",
 				domain, len(dlServers), dlServers)
 
+			var gotDNSAnswer bool
+			var gotTransportFailure bool
 			for _, server := range dlServers {
 				upstreamCfg := p.vpnDNS.upstreamConfigFor(server)
 				ctrld.Log(ctx, mainLog.Load().Debug(), "Querying domain-less VPN DNS server: %s", server)
@@ -608,6 +625,10 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 				resolveCtx, cancel := upstreamCfg.Context(ctx)
 				answer, err := dnsResolver.Resolve(resolveCtx, req.msg)
 				cancel()
+				if answer != nil {
+					gotDNSAnswer = true
+					p.vpnDNS.VPNDNSReachable()
+				}
 				if answer != nil && answer.Rcode == dns.RcodeSuccess {
 					ctrld.Log(ctx, mainLog.Load().Debug(),
 						"Domain-less VPN DNS server %s answered %s successfully", server, domain)
@@ -618,10 +639,25 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 						"Domain-less VPN DNS server %s returned %s for %s, trying next",
 						server, dns.RcodeToString[answer.Rcode], domain)
 				} else {
+					gotTransportFailure = true
 					ctrld.Log(ctx, mainLog.Load().Debug().Err(err),
 						"Domain-less VPN DNS server %s failed for %s", server, domain)
 				}
 			}
+
+			// If every domainless VPN DNS attempt failed before receiving a DNS
+			// packet while Windows is serving retained VPN DNS state, fail closed
+			// instead of asking LAN/public DNS about internal split-rule names and
+			// caching false negatives. Reachable negative DNS responses still fall
+			// through to the old OS fallback behavior below.
+			if !gotDNSAnswer && gotTransportFailure && p.vpnDNS.ShouldFailClosedAfterVPNDNSTransportFailure(domain, dlServers) {
+				ctrld.Log(ctx, mainLog.Load().Debug(),
+					"All domain-less VPN DNS servers had transport failures for %s; returning SERVFAIL while retained VPN DNS state is active", domain)
+				answer := new(dns.Msg)
+				answer.SetRcode(req.msg, dns.RcodeServerFailure)
+				return &proxyResponse{answer: answer}
+			}
+
 			ctrld.Log(ctx, mainLog.Load().Debug(),
 				"All domain-less VPN DNS servers failed for %s, falling back to OS resolver", domain)
 		}

cmd/cli/main_test.go

@@ -2,6 +2,7 @@ package cli
 
 import (
 	"os"
+	"os/exec"
 	"strings"
 	"testing"
 
@@ -13,5 +14,20 @@ var logOutput strings.Builder
 func TestMain(m *testing.M) {
 	l := zerolog.New(&logOutput)
 	mainLog.Store(&l)
+
+	// Stub the self-upgrade command builder for the whole test binary. The real
+	// builder execs os.Executable() — which under `go test` IS this test binary
+	// — with positional args ("upgrade", ...). `go test` stops flag parsing at
+	// the first positional arg and ignores the rest, so the child just re-runs
+	// the entire suite, hits the upgrade tests again, and spawns more children:
+	// a fork bomb of detached processes that stalls the host and (on Windows)
+	// holds the test binary's image locked, breaking CI artifact cleanup.
+	// Point it at the test binary with a no-match -test.run so any test that
+	// reaches performUpgrade still exercises the cmd.Start() success path while
+	// the child exits immediately without recursing.
+	newUpgradeCmd = func(exe string) *exec.Cmd {
+		return exec.Command(exe, "-test.run=^$")
+	}
+
 	os.Exit(m.Run())
 }

cmd/cli/prog.go

@@ -1651,6 +1651,19 @@ func shouldUpgrade(vt string, cv *semver.Version, logger *zerolog.Logger) bool {
 	return true
 }
 
+// newUpgradeCmd builds the detached command used to self-upgrade. It is a
+// package-level variable so tests can stub it. With the real implementation a
+// *test* binary would re-exec itself — os.Executable() is the test binary, and
+// because `go test` stops flag parsing at the first positional arg ("upgrade")
+// it ignores the args and re-runs the entire suite. That child hits the same
+// upgrade test and spawns another child, recursively: a fork bomb of detached
+// processes that pins the host and locks the test binary's image file.
+var newUpgradeCmd = func(exe string) *exec.Cmd {
+	cmd := exec.Command(exe, "upgrade", "prod", "-vv")
+	cmd.SysProcAttr = sysProcAttrForDetachedChildProcess()
+	return cmd
+}
+
 // performUpgrade executes the self-upgrade command.
 // Returns true if upgrade was initiated successfully, false otherwise.
 func performUpgrade(vt string) bool {
@@ -1659,8 +1672,7 @@ func performUpgrade(vt string) bool {
 		mainLog.Load().Error().Err(err).Msg("failed to get executable path, skipped self-upgrade")
 		return false
 	}
-	cmd := exec.Command(exe, "upgrade", "prod", "-vv")
+	cmd := newUpgradeCmd(exe)
-	cmd.SysProcAttr = sysProcAttrForDetachedChildProcess()
 	if err := cmd.Start(); err != nil {
 		mainLog.Load().Error().Err(err).Msg("failed to start self-upgrade")
 		return false

cmd/cli/prog_linux.go

@@ -14,6 +14,9 @@ import (
 )
 
 func init() {
+	if isAndroid() {
+		return
+	}
 	if r, err := newLoopbackOSConfigurator(); err == nil {
 		useSystemdResolved = r.Mode() == "systemd-resolved"
 	}

cmd/cli/prog_test.go

@@ -262,6 +262,8 @@ func Test_performUpgrade(t *testing.T) {
 		},
 	}
 
+	// newUpgradeCmd is stubbed in TestMain so performUpgrade does not re-exec
+	// (and fork-bomb) the test binary; see the comment there.
 	for _, tc := range tests {
 		tc := tc
 		t.Run(tc.name, func(t *testing.T) {

cmd/cli/vpn_dns.go

@@ -3,14 +3,18 @@ package cli
 import (
 	"context"
 	"net"
+	"runtime"
 	"strings"
 	"sync"
 
+	"github.com/rs/zerolog"
 	"tailscale.com/net/netmon"
 
 	"github.com/Control-D-Inc/ctrld"
 )
 
+var vpnDNSSettlingEnabled = runtime.GOOS == "windows"
+
 // vpnDNSExemption represents a VPN DNS server that needs pf/WFP exemption,
 // including the interface it was discovered on. The interface is used on macOS
 // to create interface-scoped pf exemptions that allow the VPN's local DNS
@@ -38,6 +42,14 @@ type vpnDNSManager struct {
 	// as additional nameservers for queries that match split-DNS rules
 	// (from ctrld config, AD domain, or VPN suffix config).
 	domainlessServers []string
+	// retainedAfterEmptyDiscovery means Windows reported an empty VPN DNS
+	// snapshot once while previous VPN DNS state existed. We keep that last-known
+	// state for one guarded refresh cycle because Windows can briefly report an
+	// intermediate empty adapter/DNS state after sleep/wake or reconnect.
+	retainedAfterEmptyDiscovery bool
+	// discoverVPNDNS is injected for tests so Refresh does not depend on the
+	// runner host's real VPN/virtual adapter state.
+	discoverVPNDNS func(context.Context) []ctrld.VPNDNSConfig
 	// Called when VPN DNS server list changes, to update intercept exemptions.
 	onServersChanged vpnDNSExemptFunc
 }
@@ -48,6 +60,7 @@ type vpnDNSManager struct {
 func newVPNDNSManager(exemptFunc vpnDNSExemptFunc) *vpnDNSManager {
 	return &vpnDNSManager{
 		routes:           make(map[string][]string),
+		discoverVPNDNS:   ctrld.DiscoverVPNDNS,
 		onServersChanged: exemptFunc,
 	}
 }
@@ -58,7 +71,11 @@ func (m *vpnDNSManager) Refresh(guardAgainstNoNameservers bool) {
 	logger := mainLog.Load()
 
 	logger.Debug().Msg("Refreshing VPN DNS configurations")
-	configs := ctrld.DiscoverVPNDNS(context.Background())
+	discoverVPNDNS := m.discoverVPNDNS
+	if discoverVPNDNS == nil {
+		discoverVPNDNS = ctrld.DiscoverVPNDNS
+	}
+	configs := discoverVPNDNS(context.Background())
 
 	// Detect exit mode: if the default route goes through a VPN DNS interface,
 	// the VPN is routing ALL traffic (exit node / full tunnel). This is more
@@ -78,6 +95,31 @@ func (m *vpnDNSManager) Refresh(guardAgainstNoNameservers bool) {
 	m.mu.Lock()
 	defer m.mu.Unlock()
 
+	previousExemptions := m.currentExemptionsLocked()
+
+	if vpnDNSSettlingEnabled && len(configs) == 0 && guardAgainstNoNameservers && m.hasVPNDNSStateLocked() {
+		if !m.retainedAfterEmptyDiscovery {
+			exemptions := m.currentExemptionsLocked()
+			m.retainedAfterEmptyDiscovery = true
+			logger.Debug().Msgf(
+				"VPN DNS discovery empty; retaining last-known VPN DNS state for one guarded refresh (%d domainless servers, %d exemptions)",
+				len(m.domainlessServers), len(exemptions))
+			if m.onServersChanged != nil {
+				if err := m.onServersChanged(exemptions); err != nil {
+					logger.Error().Err(err).Msg("Failed to re-apply retained VPN DNS exemptions")
+				}
+			}
+			return
+		}
+		logger.Debug().Msgf(
+			"VPN DNS discovery still empty on next guarded refresh; clearing retained VPN DNS state (%d domainless servers)",
+			len(m.domainlessServers))
+	}
+
+	// Any discovery path that does not return with retained state clears the
+	// settling marker: non-empty discovery replaces old servers immediately, and
+	// an unguarded/second empty discovery clears stale state below.
+	m.retainedAfterEmptyDiscovery = false
 	m.configs = configs
 	m.routes = make(map[string][]string)
 
@@ -141,14 +183,142 @@ func (m *vpnDNSManager) Refresh(guardAgainstNoNameservers bool) {
 	logger.Debug().Msgf("VPN DNS refresh completed: %d configs, %d routes, %d domainless servers, %d unique exemptions",
 		len(m.configs), len(m.routes), len(m.domainlessServers), len(exemptions))
 
-	// Update intercept rules to permit VPN DNS traffic.
+	// Update intercept rules to permit VPN DNS traffic only when the exemption set
-	// Always call onServersChanged — including when exemptions is empty — so that
+	// actually changes. Network-change events can fire repeatedly while macOS/VPN
-	// stale exemptions from a previous VPN session get cleared on disconnect.
+	// state is otherwise identical; rewriting pf for identical exemptions can feed
-	if m.onServersChanged != nil {
+	// a self-triggering network-change loop. Empty exemptions are still applied
-		if err := m.onServersChanged(exemptions); err != nil {
+	// when they differ from the previous set, so stale VPN exemptions are cleared
-			logger.Error().Err(err).Msg("Failed to update intercept exemptions for VPN DNS servers")
+	// on disconnect.
+	m.updateInterceptExemptionsIfChanged(logger, previousExemptions, exemptions, "VPN DNS")
+}
+
+func (m *vpnDNSManager) updateInterceptExemptionsIfChanged(logger *zerolog.Logger, before, after []vpnDNSExemption, reason string) {
+	if m.onServersChanged == nil {
+		return
+	}
+	if vpnDNSExemptionsEqual(before, after) {
+		logger.Debug().Msgf("VPN DNS exemptions unchanged after %s refresh; skipping intercept rule update", reason)
+		return
+	}
+	if err := m.onServersChanged(after); err != nil {
+		logger.Error().Err(err).Msg("Failed to update intercept exemptions for VPN DNS servers")
+	}
+}
+
+// RefreshRoutesOnly re-discovers VPN DNS configs and updates only ctrld's
+// in-memory split-DNS routes. It intentionally does not call onServersChanged,
+// so it does not rewrite/reload pf/WFP rules. Use this for post-settle discovery
+// checks where we only need to learn late-published VPN search domains.
+func (m *vpnDNSManager) RefreshRoutesOnly() (routes, domainlessServers, exemptions int) {
+	logger := mainLog.Load()
+
+	logger.Debug().Msg("Refreshing VPN DNS route state only")
+	discoverVPNDNS := m.discoverVPNDNS
+	if discoverVPNDNS == nil {
+		discoverVPNDNS = ctrld.DiscoverVPNDNS
+	}
+	configs := discoverVPNDNS(context.Background())
+
+	if dri, err := netmon.DefaultRouteInterface(); err == nil && dri != "" {
+		for i := range configs {
+			if configs[i].InterfaceName == dri {
+				configs[i].IsExitMode = true
+			}
 		}
 	}
+
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	m.retainedAfterEmptyDiscovery = false
+	m.configs = configs
+	m.routes = make(map[string][]string)
+
+	for _, config := range configs {
+		for _, domain := range config.Domains {
+			domain = strings.TrimPrefix(domain, "~")
+			domain = strings.TrimPrefix(domain, ".")
+			domain = strings.ToLower(domain)
+			if domain != "" {
+				m.routes[domain] = append([]string{}, config.Servers...)
+			}
+		}
+	}
+
+	var domainless []string
+	seenDomainless := make(map[string]bool)
+	for _, config := range configs {
+		if len(config.Domains) == 0 && len(config.Servers) > 0 {
+			for _, server := range config.Servers {
+				if !seenDomainless[server] {
+					seenDomainless[server] = true
+					domainless = append(domainless, server)
+				}
+			}
+		}
+	}
+	m.domainlessServers = domainless
+
+	logger.Debug().Msgf("VPN DNS route-only refresh completed: %d configs, %d routes, %d domainless servers, %d exemptions",
+		len(m.configs), len(m.routes), len(m.domainlessServers), len(m.currentExemptionsLocked()))
+	return len(m.routes), len(m.domainlessServers), len(m.currentExemptionsLocked())
+}
+
+func (m *vpnDNSManager) hasVPNDNSStateLocked() bool {
+	return len(m.configs) > 0 || len(m.routes) > 0 || len(m.domainlessServers) > 0
+}
+
+func (m *vpnDNSManager) currentExemptionsLocked() []vpnDNSExemption {
+	type key struct{ server, iface string }
+	seen := make(map[key]bool)
+	var exemptions []vpnDNSExemption
+	for _, config := range m.configs {
+		for _, server := range config.Servers {
+			k := key{server, config.InterfaceName}
+			if seen[k] {
+				continue
+			}
+			seen[k] = true
+			exemptions = append(exemptions, vpnDNSExemption{
+				Server:     server,
+				Interface:  config.InterfaceName,
+				IsExitMode: config.IsExitMode,
+			})
+		}
+	}
+	return exemptions
+}
+
+// ShouldFailClosedAfterVPNDNSTransportFailure reports whether split-rule
+// queries should fail closed instead of falling back to OS/public DNS after
+// every candidate VPN DNS server failed before returning a DNS packet. This is
+// Windows-only and only active while serving retained VPN DNS state from a
+// guarded empty discovery, which is the short window where Windows can report
+// VPN DNS before routes to those servers are usable after wake/reconnect.
+func (m *vpnDNSManager) ShouldFailClosedAfterVPNDNSTransportFailure(domain string, servers []string) bool {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+
+	if !vpnDNSSettlingEnabled || len(servers) == 0 || !m.retainedAfterEmptyDiscovery || !m.hasVPNDNSStateLocked() {
+		return false
+	}
+
+	mainLog.Load().Debug().Msgf(
+		"VPN DNS transport failed for %s while retained VPN DNS state is active; suppressing OS fallback for this query (servers=%v)",
+		domain, servers)
+	return true
+}
+
+// VPNDNSReachable records that a VPN DNS server returned a DNS response. The
+// response may be negative (NXDOMAIN/SERVFAIL); the important signal is that
+// the VPN DNS transport is reachable again.
+func (m *vpnDNSManager) VPNDNSReachable() {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if m.retainedAfterEmptyDiscovery {
+		mainLog.Load().Debug().Msg("VPN DNS transport recovered; clearing retained-empty-discovery state")
+	}
+	m.retainedAfterEmptyDiscovery = false
 }
 
 // UpstreamForDomain checks if the domain matches any VPN search domain.
@@ -208,24 +378,7 @@ func (m *vpnDNSManager) CurrentServers() []string {
 func (m *vpnDNSManager) CurrentExemptions() []vpnDNSExemption {
 	m.mu.RLock()
 	defer m.mu.RUnlock()
-
+	return m.currentExemptionsLocked()
-	type key struct{ server, iface string }
-	seen := make(map[key]bool)
-	var exemptions []vpnDNSExemption
-	for _, config := range m.configs {
-		for _, server := range config.Servers {
-			k := key{server, config.InterfaceName}
-			if !seen[k] {
-				seen[k] = true
-				exemptions = append(exemptions, vpnDNSExemption{
-					Server:     server,
-					Interface:  config.InterfaceName,
-					IsExitMode: config.IsExitMode,
-				})
-			}
-		}
-	}
-	return exemptions
 }
 
 // Routes returns a copy of the current VPN DNS routes for debugging.

cmd/cli/vpn_dns_test.go

@@ -0,0 +1,115 @@
+package cli
+
+import (
+	"context"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func withVPNDNSSettlingEnabled(t *testing.T) {
+	t.Helper()
+	old := vpnDNSSettlingEnabled
+	vpnDNSSettlingEnabled = true
+	t.Cleanup(func() { vpnDNSSettlingEnabled = old })
+}
+
+func TestVPNDNSRefreshRetainsStateForOneGuardedEmptyDiscovery(t *testing.T) {
+	withVPNDNSSettlingEnabled(t)
+	var gotExemptions []vpnDNSExemption
+	m := newVPNDNSManager(func(exemptions []vpnDNSExemption) error {
+		gotExemptions = exemptions
+		return nil
+	})
+	m.discoverVPNDNS = func(context.Context) []ctrld.VPNDNSConfig { return nil }
+	m.configs = []ctrld.VPNDNSConfig{{
+		InterfaceName: "Ethernet 6",
+		Servers:       []string{"10.25.37.21", "10.25.37.22"},
+	}}
+	m.domainlessServers = []string{"10.25.37.21", "10.25.37.22"}
+
+	m.Refresh(true)
+
+	if got := m.DomainlessServers(); len(got) != 2 {
+		t.Fatalf("expected retained domainless servers, got %v", got)
+	}
+	if len(gotExemptions) != 2 {
+		t.Fatalf("expected retained exemptions to be re-applied, got %v", gotExemptions)
+	}
+	if !m.retainedAfterEmptyDiscovery {
+		t.Fatal("expected empty discovery retention to be marked")
+	}
+}
+
+func TestVPNDNSRefreshClearsOnSecondGuardedEmptyDiscovery(t *testing.T) {
+	withVPNDNSSettlingEnabled(t)
+	var gotExemptions []vpnDNSExemption
+	m := newVPNDNSManager(func(exemptions []vpnDNSExemption) error {
+		gotExemptions = exemptions
+		return nil
+	})
+	m.discoverVPNDNS = func(context.Context) []ctrld.VPNDNSConfig { return nil }
+	m.configs = []ctrld.VPNDNSConfig{{
+		InterfaceName: "Ethernet 6",
+		Servers:       []string{"10.25.37.21"},
+	}}
+	m.domainlessServers = []string{"10.25.37.21"}
+	m.retainedAfterEmptyDiscovery = true
+
+	m.Refresh(true)
+
+	if got := m.DomainlessServers(); len(got) != 0 {
+		t.Fatalf("expected domainless servers to be cleared on second empty discovery, got %v", got)
+	}
+	if len(gotExemptions) != 0 {
+		t.Fatalf("expected empty exemptions after clearing stale state, got %v", gotExemptions)
+	}
+	if m.retainedAfterEmptyDiscovery {
+		t.Fatal("expected retained empty-discovery marker to be cleared with stale state")
+	}
+}
+
+func TestVPNDNSRefreshSkipsUnchangedInterceptExemptions(t *testing.T) {
+	var updates [][]vpnDNSExemption
+	m := newVPNDNSManager(func(exemptions []vpnDNSExemption) error {
+		updates = append(updates, append([]vpnDNSExemption{}, exemptions...))
+		return nil
+	})
+	m.discoverVPNDNS = func(context.Context) []ctrld.VPNDNSConfig {
+		return []ctrld.VPNDNSConfig{{
+			InterfaceName: "utun-test",
+			Servers:       []string{"10.102.26.10"},
+			Domains:       []string{"example.internal"},
+		}}
+	}
+
+	m.Refresh(true)
+	m.Refresh(true)
+
+	if len(updates) != 1 {
+		t.Fatalf("expected exactly one intercept exemption update for unchanged VPN DNS state, got %d", len(updates))
+	}
+	if len(updates[0]) != 1 || updates[0][0].Server != "10.102.26.10" || updates[0][0].Interface != "utun-test" {
+		t.Fatalf("unexpected exemption update: %+v", updates[0])
+	}
+}
+
+func TestVPNDNSTransportFailureSuppressesFallbackOnlyWhileRetainingState(t *testing.T) {
+	withVPNDNSSettlingEnabled(t)
+	m := newVPNDNSManager(nil)
+	m.domainlessServers = []string{"10.25.37.21"}
+
+	if m.ShouldFailClosedAfterVPNDNSTransportFailure("splunk.aws.arena.net.", []string{"10.25.37.21"}) {
+		t.Fatal("did not expect transport failure to suppress OS fallback outside retained empty-discovery state")
+	}
+
+	m.retainedAfterEmptyDiscovery = true
+	if !m.ShouldFailClosedAfterVPNDNSTransportFailure("splunk.aws.arena.net.", []string{"10.25.37.21"}) {
+		t.Fatal("expected transport failure to suppress OS fallback while retained state is active")
+	}
+
+	m.VPNDNSReachable()
+	if m.retainedAfterEmptyDiscovery {
+		t.Fatal("expected reachable DNS response to clear retained empty-discovery state")
+	}
+}

config.go

@@ -640,6 +640,7 @@ func (uc *UpstreamConfig) newDOHTransport(addrs []string) *http.Transport {
 	transport.TLSClientConfig = &tls.Config{
 		RootCAs:            uc.certPool,
 		ClientSessionCache: tls.NewLRUClientSessionCache(0),
+		MinVersion:         tls.VersionTLS12,
 	}
 
 	// Prevent bad tcp connection hanging the requests for too long.

config_quic.go

@@ -18,7 +18,7 @@ func (uc *UpstreamConfig) newDOH3Transport(addrs []string) http.RoundTripper {
 		return nil
 	}
 	rt := &http3.Transport{}
-	rt.TLSClientConfig = &tls.Config{RootCAs: uc.certPool}
+	rt.TLSClientConfig = &tls.Config{RootCAs: uc.certPool, MinVersion: tls.VersionTLS12}
 	rt.Dial = func(ctx context.Context, addr string, tlsCfg *tls.Config, cfg *quic.Config) (*quic.Conn, error) {
 		_, port, _ := net.SplitHostPort(addr)
 		// if we have a bootstrap ip set, use it to avoid DNS lookup
@@ -77,7 +77,17 @@ type parallelDialerResult struct {
 	err  error
 }
 
-type quicParallelDialer struct{}
+// quicParallelDialer races DialEarly across a list of remote addresses and
+// returns the first successful connection. When transport is non-nil, all
+// dials share that transport's UDP socket, which removes both the per-dial
+// socket allocation and the winner-path socket leak that an owner-of-the-conn
+// receiver cannot clean up. When transport is nil, the dialer falls back to a
+// fresh UDP socket per attempt (compat path used where no shared transport is
+// available yet); the loser paths close their sockets, and the winner path's
+// socket is owned by quic.DialEarly's internal transport.
+type quicParallelDialer struct {
+	transport *quic.Transport
+}
 
 // Dial performs parallel dialing to the given address list.
 func (d *quicParallelDialer) Dial(ctx context.Context, addrs []string, tlsCfg *tls.Config, cfg *quic.Config) (*quic.Conn, error) {
@@ -105,12 +115,24 @@ func (d *quicParallelDialer) Dial(ctx context.Context, addrs []string, tlsCfg *t
 				ch <- &parallelDialerResult{conn: nil, err: err}
 				return
 			}
-			udpConn, err := net.ListenUDP("udp", nil)
+			var (
-			if err != nil {
+				conn    *quic.Conn
-				ch <- &parallelDialerResult{conn: nil, err: err}
+				udpConn *net.UDPConn
-				return
+			)
+			if d.transport != nil {
+				conn, err = d.transport.DialEarly(ctx, remoteAddr, tlsCfg, cfg)
+			} else {
+				udpConn, err = net.ListenUDP("udp", nil)
+				if err != nil {
+					ch <- &parallelDialerResult{conn: nil, err: err}
+					return
+				}
+				conn, err = quic.DialEarly(ctx, udpConn, remoteAddr, tlsCfg, cfg)
+				if err != nil {
+					udpConn.Close()
+					udpConn = nil
+				}
 			}
-			conn, err := quic.DialEarly(ctx, udpConn, remoteAddr, tlsCfg, cfg)
 			select {
 			case ch <- &parallelDialerResult{conn: conn, err: err}:
 			case <-done:

docker/Dockerfile

@@ -1,4 +1,4 @@
-# Using Debian bullseye for building regular image.
+# Using Debian bookworm for building regular image.
 # Using scratch image for minimal image size.
 # The final image has:
 #
@@ -8,11 +8,12 @@
 # - Non-cgo ctrld binary.
 #
 # CI_COMMIT_TAG is used to set the version of ctrld binary.
-FROM golang:1.20-bullseye as base
+FROM golang:1.25-bookworm AS base
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y upx-ucl
+RUN echo "deb http://deb.debian.org/debian bookworm-backports main" | tee /etc/apt/sources.list.d/backports.list
+RUN apt update && apt install -t bookworm-backports upx-ucl
 
 COPY . .
 

docker/Dockerfile.debug

@@ -1,4 +1,4 @@
-# Using Debian bullseye for building regular image.
+# Using Debian bookworm for building regular image.
 # Using scratch image for minimal image size.
 # The final image has:
 #
@@ -8,11 +8,12 @@
 # - Non-cgo ctrld binary.
 #
 # CI_COMMIT_TAG is used to set the version of ctrld binary.
-FROM golang:bullseye as base
+FROM golang:1.25-bookworm AS base
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y upx-ucl
+RUN echo "deb http://deb.debian.org/debian bookworm-backports main" | tee /etc/apt/sources.list.d/backports.list
+RUN apt update && apt install -t bookworm-backports upx-ucl
 
 COPY . .
 

doh.go

@@ -25,6 +25,16 @@ const (
 	dohOsHeader           = "x-cd-os"
 	dohClientIDPrefHeader = "x-cd-cpref"
 	headerApplicationDNS  = "application/dns-message"
+
+	// dohMaxResponseSize caps the response body read from a DoH/DoH3
+	// upstream. A DNS message is bounded by the protocol's 16-bit length
+	// field; anything larger cannot be a valid response. The cap stops a
+	// malicious or compromised upstream from driving ctrld into unbounded
+	// memory growth via io.ReadAll on attacker-controlled bytes.
+	dohMaxResponseSize = dns.MaxMsgSize
+	// dohMaxErrorBodySize bounds how much of a non-200 response body is
+	// read for inclusion in the returned error.
+	dohMaxErrorBodySize = 1024
 )
 
 // EncodeOsNameMap provides mapping from OS name to a shorter string, used for encoding x-cd-os value.
@@ -130,13 +140,17 @@ func (r *dohResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, erro
 	}
 	defer resp.Body.Close()
 
-	buf, err := io.ReadAll(resp.Body)
+	if resp.StatusCode != http.StatusOK {
+		body, _ := io.ReadAll(io.LimitReader(resp.Body, dohMaxErrorBodySize))
+		return nil, fmt.Errorf("wrong response from DOH server, got: %s, status: %d", string(body), resp.StatusCode)
+	}
+
+	buf, err := io.ReadAll(io.LimitReader(resp.Body, dohMaxResponseSize+1))
 	if err != nil {
 		return nil, fmt.Errorf("could not read message from response: %w", err)
 	}
-
+	if len(buf) > dohMaxResponseSize {
-	if resp.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("DoH response exceeds %d-byte maximum DNS message size", dohMaxResponseSize)
-		return nil, fmt.Errorf("wrong response from DOH server, got: %s, status: %d", string(buf), resp.StatusCode)
 	}
 
 	answer := new(dns.Msg)

doh_test.go

@@ -12,6 +12,7 @@ import (
 	"net/url"
 	"runtime"
 	"strings"
+	"sync/atomic"
 	"testing"
 	"time"
 
@@ -196,6 +197,7 @@ func testTLSServer(t *testing.T, handler http.Handler) (*httptest.Server, *x509.
 	server := httptest.NewUnstartedServer(handler)
 	server.TLS = &tls.Config{
 		Certificates: []tls.Certificate{testCert.tlsCert},
+		MinVersion:   tls.VersionTLS12,
 	}
 	server.StartTLS()
 
@@ -232,6 +234,7 @@ func newTestHTTP3Server(t *testing.T, handler http.Handler) *testHTTP3Server {
 	tlsConfig := &tls.Config{
 		Certificates: []tls.Certificate{testCert.tlsCert},
 		NextProtos:   []string{"h3"}, // HTTP/3 protocol identifier
+		MinVersion:   tls.VersionTLS12,
 	}
 
 	// Create HTTP/3 server
@@ -264,3 +267,221 @@ func newTestHTTP3Server(t *testing.T, handler http.Handler) *testHTTP3Server {
 
 	return h3Server
 }
+
+// oversizedDoHHandler streams `bodyBytes` bytes of zeros with the given
+// HTTP status. The atomic counter records bytes the handler actually
+// wrote, so tests can confirm the client tore down the stream before
+// consuming the whole attacker-controlled body.
+func oversizedDoHHandler(status int, bodyBytes int64, written *atomic.Int64) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", headerApplicationDNS)
+		w.WriteHeader(status)
+		chunk := make([]byte, 64*1024)
+		var sent int64
+		for sent < bodyBytes {
+			n := int64(len(chunk))
+			if remaining := bodyBytes - sent; remaining < n {
+				n = remaining
+			}
+			m, err := w.Write(chunk[:n])
+			if err != nil {
+				return
+			}
+			sent += int64(m)
+			if written != nil {
+				written.Add(int64(m))
+			}
+			if f, ok := w.(http.Flusher); ok {
+				f.Flush()
+			}
+		}
+	}
+}
+
+// dohUpstreamForTLSServer wires an UpstreamConfig at a local httptest TLS
+// server, trusting its self-signed certificate. BootstrapIP is set so no
+// real DNS lookup runs.
+func dohUpstreamForTLSServer(t *testing.T, srv *httptest.Server) *UpstreamConfig {
+	t.Helper()
+	pool := x509.NewCertPool()
+	pool.AddCert(srv.Certificate())
+	u, err := url.Parse(srv.URL)
+	if err != nil {
+		t.Fatalf("parse server URL: %v", err)
+	}
+	uc := &UpstreamConfig{
+		Name:        "doh-oversize",
+		Type:        ResolverTypeDOH,
+		Endpoint:    srv.URL + "/dns-query",
+		BootstrapIP: u.Hostname(),
+		Timeout:     2000,
+	}
+	uc.SetCertPool(pool)
+	uc.Init()
+	return uc
+}
+
+// doh3UpstreamForAddr wires an UpstreamConfig at a local HTTP/3 server,
+// trusting its self-signed certificate.
+func doh3UpstreamForAddr(t *testing.T, addr string, cert *x509.Certificate) *UpstreamConfig {
+	t.Helper()
+	pool := x509.NewCertPool()
+	pool.AddCert(cert)
+	host, _, err := net.SplitHostPort(addr)
+	if err != nil {
+		t.Fatalf("split host/port %q: %v", addr, err)
+	}
+	uc := &UpstreamConfig{
+		Name:        "doh3-oversize",
+		Type:        ResolverTypeDOH3,
+		Endpoint:    "h3://" + addr + "/dns-query",
+		BootstrapIP: host,
+		Timeout:     5000,
+	}
+	uc.SetCertPool(pool)
+	uc.Init()
+	return uc
+}
+
+// TestDoHResolve_OversizedBody_Rejected locks in the fix for
+// github.com/Control-D-Inc/ctrld/issues/312: a malicious DoH upstream
+// returning a body larger than the DNS protocol allows must be rejected
+// with an explicit size error rather than buffered into ctrld memory.
+func TestDoHResolve_OversizedBody_Rejected(t *testing.T) {
+	const oversized = 2 * 1024 * 1024 // far past dohMaxResponseSize (~64 KiB)
+	var written atomic.Int64
+	srv := httptest.NewUnstartedServer(oversizedDoHHandler(http.StatusOK, oversized, &written))
+	testCert := generateTestCertificate(t)
+	srv.TLS = &tls.Config{
+		Certificates: []tls.Certificate{testCert.tlsCert},
+		NextProtos:   []string{"h2", "http/1.1"},
+		MinVersion:   tls.VersionTLS12,
+	}
+	srv.StartTLS()
+	t.Cleanup(srv.Close)
+
+	uc := dohUpstreamForTLSServer(t, srv)
+	r, err := NewResolver(uc)
+	if err != nil {
+		t.Fatalf("NewResolver: %v", err)
+	}
+
+	msg := new(dns.Msg)
+	msg.SetQuestion("example.com.", dns.TypeA)
+	msg.RecursionDesired = true
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	answer, err := r.Resolve(ctx, msg)
+	if err == nil {
+		t.Fatalf("Resolve unexpectedly succeeded; answer=%v", answer)
+	}
+	if !strings.Contains(err.Error(), "maximum DNS message size") {
+		t.Fatalf("error %q does not mention the size cap", err)
+	}
+	if answer != nil {
+		t.Fatalf("Resolve returned non-nil answer alongside error: %v", answer)
+	}
+	if got := written.Load(); got >= int64(oversized) {
+		t.Fatalf("server wrote the entire %d-byte body before client tore down (wrote=%d) — cap not effective", oversized, got)
+	}
+}
+
+// TestDoHResolve_NonOKStatus_BoundedErrorBody locks in that a non-200
+// response with a huge body does not pull the body fully into ctrld
+// memory just to format an error string.
+func TestDoHResolve_NonOKStatus_BoundedErrorBody(t *testing.T) {
+	const huge = 8 * 1024 * 1024
+	var written atomic.Int64
+	srv := httptest.NewUnstartedServer(oversizedDoHHandler(http.StatusBadGateway, huge, &written))
+	testCert := generateTestCertificate(t)
+	srv.TLS = &tls.Config{
+		Certificates: []tls.Certificate{testCert.tlsCert},
+		NextProtos:   []string{"h2", "http/1.1"},
+		MinVersion:   tls.VersionTLS12,
+	}
+	srv.StartTLS()
+	t.Cleanup(srv.Close)
+
+	uc := dohUpstreamForTLSServer(t, srv)
+	r, err := NewResolver(uc)
+	if err != nil {
+		t.Fatalf("NewResolver: %v", err)
+	}
+
+	msg := new(dns.Msg)
+	msg.SetQuestion("example.com.", dns.TypeA)
+	msg.RecursionDesired = true
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	answer, err := r.Resolve(ctx, msg)
+	if err == nil {
+		t.Fatalf("Resolve unexpectedly succeeded; answer=%v", answer)
+	}
+	if !strings.Contains(err.Error(), "status: 502") {
+		t.Fatalf("error %q does not surface the upstream status", err)
+	}
+	if answer != nil {
+		t.Fatalf("Resolve returned non-nil answer alongside error: %v", answer)
+	}
+	if got := written.Load(); got > 1024*1024 {
+		t.Fatalf("server wrote %d bytes before client tore down — error path is reading too much body", got)
+	}
+}
+
+// TestDoHResolve_OversizedBody_DoH3 mirrors the DoH oversized-body check
+// on the HTTP/3 transport, since github-312 specifically reproduced the
+// OOM via DoH3.
+func TestDoHResolve_OversizedBody_DoH3(t *testing.T) {
+	const oversized = 2 * 1024 * 1024
+	testCert := generateTestCertificate(t)
+	udpConn, err := net.ListenUDP("udp", &net.UDPAddr{IP: net.ParseIP("127.0.0.1"), Port: 0})
+	if err != nil {
+		t.Fatalf("udp listen: %v", err)
+	}
+	h3 := &http3.Server{
+		Handler: oversizedDoHHandler(http.StatusOK, oversized, nil),
+		TLSConfig: &tls.Config{
+			Certificates: []tls.Certificate{testCert.tlsCert},
+			NextProtos:   []string{"h3"},
+			MinVersion:   tls.VersionTLS12,
+		},
+	}
+	go func() {
+		if err := h3.Serve(udpConn); err != nil && !errors.Is(err, http.ErrServerClosed) {
+			t.Logf("h3 server: %v", err)
+		}
+	}()
+	t.Cleanup(func() {
+		_ = h3.Close()
+		_ = udpConn.Close()
+	})
+	time.Sleep(100 * time.Millisecond)
+
+	uc := doh3UpstreamForAddr(t, udpConn.LocalAddr().String(), testCert.cert)
+	r, err := NewResolver(uc)
+	if err != nil {
+		t.Fatalf("NewResolver: %v", err)
+	}
+
+	msg := new(dns.Msg)
+	msg.SetQuestion("example.com.", dns.TypeA)
+	msg.RecursionDesired = true
+
+	ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
+	defer cancel()
+
+	answer, err := r.Resolve(ctx, msg)
+	if err == nil {
+		t.Fatalf("Resolve unexpectedly succeeded; answer=%v", answer)
+	}
+	if !strings.Contains(err.Error(), "maximum DNS message size") {
+		t.Fatalf("error %q does not mention the size cap", err)
+	}
+	if answer != nil {
+		t.Fatalf("Resolve returned non-nil answer alongside error: %v", answer)
+	}
+}

doq.go

@@ -6,15 +6,23 @@ import (
 	"context"
 	"crypto/tls"
 	"errors"
+	"fmt"
 	"io"
 	"net"
 	"runtime"
+	"sync"
 	"time"
 
 	"github.com/miekg/dns"
 	"github.com/quic-go/quic-go"
 )
 
+// doqMaxResponseSize caps the bytes read from a DoQ stream: a 2-byte
+// length prefix plus a DNS message bounded by dns.MaxMsgSize. Anything
+// larger cannot be a valid response and is rejected before buffering more
+// data from the upstream.
+const doqMaxResponseSize = 2 + dns.MaxMsgSize
+
 type doqResolver struct {
 	uc *UpstreamConfig
 }
@@ -41,6 +49,10 @@ func (r *doqResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, erro
 const doqPoolSize = 16
 
 // doqConnPool manages a pool of QUIC connections for DoQ queries using a buffered channel.
+// A single quic.Transport (and its UDP socket) is shared by every connection in the pool,
+// so the OS socket lifecycle is tied to the pool rather than to each dial. Without this
+// ownership model, a strict DoQ upstream that triggers reconnect churn would leak one
+// caller-owned UDP socket per dial — see github.com/Control-D-Inc/ctrld/issues/309.
 type doqConnPool struct {
 	uc         *UpstreamConfig
 	addrs      []string
@@ -48,6 +60,13 @@ type doqConnPool struct {
 	tlsConfig  *tls.Config
 	quicConfig *quic.Config
 	conns      chan *doqConn
+
+	transportMu   sync.Mutex
+	transport     *quic.Transport
+	transportConn *net.UDPConn
+	transportErr  error
+	transportInit bool
+	closed        bool
 }
 
 type doqConn struct {
@@ -64,6 +83,7 @@ func newDOQConnPool(uc *UpstreamConfig, addrs []string) *doqConnPool {
 		NextProtos: []string{"doq"},
 		RootCAs:    uc.certPool,
 		ServerName: uc.Domain,
+		MinVersion: tls.VersionTLS12,
 	}
 
 	quicConfig := &quic.Config{
@@ -167,26 +187,59 @@ func (p *doqConnPool) doResolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, er
 		return nil, err
 	}
 
-	// Read response
+	// RFC 9250 section 4.2 requires the client to indicate end-of-request by
-	buf, err := io.ReadAll(stream)
+	// closing the send side of the stream (STREAM FIN). Servers may defer
-	stream.Close()
+	// processing until FIN arrives, so the close must happen before reading.
-
+	// Stream.Close closes only the send direction; the receive direction
-	// Return connection to pool (mark as potentially bad if error occurred)
+	// remains open for the response.
-	isGood := err == nil && len(buf) > 0
+	if err := stream.Close(); err != nil {
-	p.putConn(conn, isGood)
+		p.putConn(conn, false)
-
-	if err != nil {
 		return nil, err
 	}
 
-	// io.ReadAll hides io.EOF error, so check for empty buffer
+	// A DoQ response is a 2-byte length prefix followed by a DNS message.
+	// The DNS message is bounded by the protocol at dns.MaxMsgSize, so a
+	// well-formed response is at most doqMaxResponseSize bytes. Read one
+	// byte past that cap to distinguish "at limit" from "over limit" and
+	// reject oversized responses before they can drive memory growth from
+	// a malicious or compromised upstream.
+	buf, err := io.ReadAll(io.LimitReader(stream, doqMaxResponseSize+1))
+	if err != nil {
+		p.putConn(conn, false)
+		return nil, err
+	}
+
+	// io.ReadAll hides io.EOF error, so check for empty buffer.
 	if len(buf) == 0 {
+		p.putConn(conn, false)
 		return nil, io.EOF
 	}
 
-	// Unpack DNS response (skip 2-byte length prefix)
+	if len(buf) > doqMaxResponseSize {
+		p.putConn(conn, false)
+		return nil, fmt.Errorf("DoQ response exceeds %d-byte maximum", doqMaxResponseSize)
+	}
+
+	// RFC 9250: each DoQ DNS message is encoded as a 2-octet length field
+	// followed by the DNS message. Reject responses that are shorter than
+	// the prefix or whose prefix declares more bytes than were received,
+	// and retire the misbehaving connection. Without this guard, buf[2:]
+	// would panic when len(buf) < 2.
+	if len(buf) < 2 {
+		p.putConn(conn, false)
+		return nil, fmt.Errorf("malformed DoQ response: %d byte(s), need >= 2 for length prefix", len(buf))
+	}
+	respLen := int(buf[0])<<8 | int(buf[1])
+	if 2+respLen > len(buf) {
+		p.putConn(conn, false)
+		return nil, fmt.Errorf("malformed DoQ response: length prefix %d exceeds payload %d", respLen, len(buf)-2)
+	}
+
+	p.putConn(conn, true)
+
+	// Unpack DNS response (skip 2-byte length prefix).
 	answer := new(dns.Msg)
-	if err := answer.Unpack(buf[2:]); err != nil {
+	if err := answer.Unpack(buf[2 : 2+respLen]); err != nil {
 		return nil, err
 	}
 	answer.SetReply(msg)
@@ -233,25 +286,26 @@ func (p *doqConnPool) putConn(conn *quic.Conn, isGood bool) {
 }
 
 // dialConn creates a new QUIC connection using parallel dialing like DoH3.
+// All connections from the pool multiplex on a single pool-owned UDP socket,
+// so reconnect churn cannot grow the host's FD count.
 func (p *doqConnPool) dialConn(ctx context.Context) (string, *quic.Conn, error) {
 	logger := ProxyLogger.Load()
 
+	tr, err := p.getOrInitTransport()
+	if err != nil {
+		return "", nil, err
+	}
+
 	// If we have a bootstrap IP, use it directly
 	if p.uc.BootstrapIP != "" {
 		addr := net.JoinHostPort(p.uc.BootstrapIP, p.port)
 		Log(ctx, logger.Debug(), "Sending DoQ request to: %s", addr)
-		udpConn, err := net.ListenUDP("udp", nil)
-		if err != nil {
-			return "", nil, err
-		}
 		remoteAddr, err := net.ResolveUDPAddr("udp", addr)
 		if err != nil {
-			udpConn.Close()
 			return "", nil, err
 		}
-		conn, err := quic.DialEarly(ctx, udpConn, remoteAddr, p.tlsConfig, p.quicConfig)
+		conn, err := tr.DialEarly(ctx, remoteAddr, p.tlsConfig, p.quicConfig)
 		if err != nil {
-			udpConn.Close()
 			return "", nil, err
 		}
 		return addr, conn, nil
@@ -263,7 +317,7 @@ func (p *doqConnPool) dialConn(ctx context.Context) (string, *quic.Conn, error)
 		dialAddrs[i] = net.JoinHostPort(p.addrs[i], p.port)
 	}
 
-	pd := &quicParallelDialer{}
+	pd := &quicParallelDialer{transport: tr}
 	conn, err := pd.Dial(ctx, dialAddrs, p.tlsConfig, p.quicConfig)
 	if err != nil {
 		return "", nil, err
@@ -274,9 +328,35 @@ func (p *doqConnPool) dialConn(ctx context.Context) (string, *quic.Conn, error)
 	return addr, conn, nil
 }
 
-// CloseIdleConnections closes all connections in the pool.
+// getOrInitTransport returns the pool's shared quic.Transport, initialising it
-// Connections currently checked out (in use) are not closed.
+// on first call. Once the pool has been closed it permanently returns an error
+// so that callers cannot resurrect a dead pool.
+func (p *doqConnPool) getOrInitTransport() (*quic.Transport, error) {
+	p.transportMu.Lock()
+	defer p.transportMu.Unlock()
+	if p.closed {
+		return nil, errors.New("doq pool closed")
+	}
+	if p.transportInit {
+		return p.transport, p.transportErr
+	}
+	p.transportInit = true
+	udpConn, err := net.ListenUDP("udp", nil)
+	if err != nil {
+		p.transportErr = err
+		return nil, err
+	}
+	p.transportConn = udpConn
+	p.transport = &quic.Transport{Conn: udpConn}
+	return p.transport, nil
+}
+
+// CloseIdleConnections closes all idle connections, the shared quic.Transport,
+// and the pool's UDP socket. Connections currently checked out (in use) get
+// terminated by the transport close as well — without that, the OS socket
+// would remain bound to a goroutine that the caller cannot reach to clean up.
 func (p *doqConnPool) CloseIdleConnections() {
+drain:
 	for {
 		select {
 		case dc := <-p.conns:
@@ -284,7 +364,22 @@ func (p *doqConnPool) CloseIdleConnections() {
 				dc.conn.CloseWithError(quic.ApplicationErrorCode(quic.NoError), "")
 			}
 		default:
-			return
+			break drain
 		}
 	}
+	p.transportMu.Lock()
+	if p.closed {
+		p.transportMu.Unlock()
+		return
+	}
+	p.closed = true
+	tr := p.transport
+	udpConn := p.transportConn
+	p.transportMu.Unlock()
+	if tr != nil {
+		_ = tr.Close()
+	}
+	if udpConn != nil {
+		_ = udpConn.Close()
+	}
 }

doq_test.go

@@ -1,4 +1,3 @@
-// test_helpers.go
 package ctrld
 
 import (
@@ -8,8 +7,11 @@ import (
 	"crypto/tls"
 	"crypto/x509"
 	"crypto/x509/pkix"
+	"io"
 	"math/big"
 	"net"
+	"os"
+	"runtime"
 	"strings"
 	"testing"
 	"time"
@@ -99,6 +101,7 @@ func newTestQUICServer(t *testing.T) *testQUICServer {
 	tlsConfig := &tls.Config{
 		Certificates: []tls.Certificate{testCert.tlsCert},
 		NextProtos:   []string{"doq"},
+		MinVersion:   tls.VersionTLS12,
 	}
 
 	// Create QUIC listener
@@ -221,3 +224,493 @@ func (s *testQUICServer) handleStream(t *testing.T, stream *quic.Stream) {
 		return
 	}
 }
+
+// malformedDoQServer is a test QUIC server that drains the client's DoQ
+// request and writes caller-supplied raw bytes back. The bytes are not
+// required to be a well-framed DoQ response, which is what lets the
+// regression tests exercise malformed-response handling.
+type malformedDoQServer struct {
+	listener *quic.Listener
+	cert     *x509.Certificate
+	addr     string
+	response []byte
+}
+
+func newMalformedDoQServer(t *testing.T, response []byte) *malformedDoQServer {
+	t.Helper()
+
+	testCert := generateTestCertificate(t)
+	tlsConfig := &tls.Config{
+		Certificates: []tls.Certificate{testCert.tlsCert},
+		NextProtos:   []string{"doq"},
+	}
+
+	listener, err := quic.ListenAddr("127.0.0.1:0", tlsConfig, nil)
+	if err != nil {
+		t.Fatalf("failed to create QUIC listener: %v", err)
+	}
+
+	s := &malformedDoQServer{
+		listener: listener,
+		cert:     testCert.cert,
+		addr:     listener.Addr().String(),
+		response: response,
+	}
+
+	go s.serve()
+	t.Cleanup(func() { _ = listener.Close() })
+	return s
+}
+
+func (s *malformedDoQServer) serve() {
+	for {
+		conn, err := s.listener.Accept(context.Background())
+		if err != nil {
+			return
+		}
+		go s.handleConn(conn)
+	}
+}
+
+func (s *malformedDoQServer) handleConn(conn *quic.Conn) {
+	for {
+		stream, err := conn.AcceptStream(context.Background())
+		if err != nil {
+			return
+		}
+		go s.handleStream(stream)
+	}
+}
+
+func (s *malformedDoQServer) handleStream(stream *quic.Stream) {
+	defer stream.Close()
+
+	// Drain the client's DoQ-framed request so the client's writes complete
+	// cleanly before we reply with our attacker-controlled bytes. Using
+	// io.ReadFull because a single Read on a QUIC stream may return short.
+	lenBuf := make([]byte, 2)
+	if _, err := io.ReadFull(stream, lenBuf); err != nil {
+		return
+	}
+	msgLen := uint16(lenBuf[0])<<8 | uint16(lenBuf[1])
+	if msgLen > 0 {
+		discard := make([]byte, msgLen)
+		if _, err := io.ReadFull(stream, discard); err != nil {
+			return
+		}
+	}
+
+	if len(s.response) > 0 {
+		_, _ = stream.Write(s.response)
+	}
+}
+
+// newMalformedDoQUpstream builds an UpstreamConfig wired to a local
+// malformed test server with the test certificate trusted via a custom
+// cert pool. We bypass SetupBootstrapIP by setting BootstrapIP directly,
+// so the pool dials 127.0.0.1 without any DNS lookup.
+func newMalformedDoQUpstream(t *testing.T, cert *x509.Certificate, addr string) *UpstreamConfig {
+	t.Helper()
+
+	pool := x509.NewCertPool()
+	pool.AddCert(cert)
+
+	host, _, err := net.SplitHostPort(addr)
+	if err != nil {
+		t.Fatalf("split host/port %q: %v", addr, err)
+	}
+
+	uc := &UpstreamConfig{
+		Name:        "doq-malformed",
+		Type:        ResolverTypeDOQ,
+		Endpoint:    addr,
+		Domain:      host,
+		BootstrapIP: host,
+		Timeout:     2000,
+	}
+	uc.SetCertPool(pool)
+	return uc
+}
+
+// TestDoQResolve_MalformedResponse verifies that DoQ upstream
+// responses violating RFC 9250 framing — fewer than 2 bytes, or a
+// length prefix declaring more payload than was received — return a
+// handled error instead of panicking on the length-prefix slice.
+func TestDoQResolve_MalformedResponse(t *testing.T) {
+	tests := []struct {
+		name     string
+		response []byte
+	}{
+		// Empty stream is already handled via io.EOF; locked in so a
+		// future change that drops that branch is caught.
+		{"empty response", nil},
+
+		// One byte: too short to hold the 2-octet length prefix.
+		{"single byte response", []byte{0x00}},
+
+		// Length prefix declares 16 bytes; payload is absent.
+		{"length prefix only", []byte{0x00, 0x10}},
+
+		// Length prefix declares 65535 bytes; only 1 byte of payload
+		// arrived.
+		{"length prefix larger than payload", []byte{0xFF, 0xFF, 0x00}},
+	}
+
+	for _, tt := range tests {
+		tt := tt
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			server := newMalformedDoQServer(t, tt.response)
+			uc := newMalformedDoQUpstream(t, server.cert, server.addr)
+
+			ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+			defer cancel()
+
+			pool := newDOQConnPool(uc, []string{"127.0.0.1"})
+			t.Cleanup(pool.CloseIdleConnections)
+
+			msg := new(dns.Msg)
+			msg.SetQuestion("example.com.", dns.TypeA)
+			msg.RecursionDesired = true
+
+			answer, err := pool.Resolve(ctx, msg)
+			if err == nil {
+				t.Fatalf("Resolve unexpectedly succeeded for malformed response %v; answer=%v", tt.response, answer)
+			}
+			if answer != nil {
+				t.Fatalf("Resolve returned non-nil answer alongside error: answer=%v err=%v", answer, err)
+			}
+		})
+	}
+}
+
+// strictDoQServer accepts DoQ queries but defers the response until the
+// client signals end-of-request with STREAM FIN, as required by RFC 9250
+// section 4.2. It exists to lock in the fix for
+// github.com/Control-D-Inc/ctrld/issues/309 where a client
+// that never closes its send side caused the server to wait forever and the
+// client to churn through reconnects.
+type strictDoQServer struct {
+	listener *quic.Listener
+	cert     *x509.Certificate
+	addr     string
+}
+
+func newStrictDoQServer(t *testing.T) *strictDoQServer {
+	t.Helper()
+
+	testCert := generateTestCertificate(t)
+	tlsConfig := &tls.Config{
+		Certificates: []tls.Certificate{testCert.tlsCert},
+		NextProtos:   []string{"doq"},
+		MinVersion:   tls.VersionTLS12,
+	}
+
+	listener, err := quic.ListenAddr("127.0.0.1:0", tlsConfig, nil)
+	if err != nil {
+		t.Fatalf("failed to create QUIC listener: %v", err)
+	}
+
+	s := &strictDoQServer{
+		listener: listener,
+		cert:     testCert.cert,
+		addr:     listener.Addr().String(),
+	}
+	go s.serve()
+	t.Cleanup(func() { _ = listener.Close() })
+	return s
+}
+
+func (s *strictDoQServer) serve() {
+	for {
+		conn, err := s.listener.Accept(context.Background())
+		if err != nil {
+			return
+		}
+		go s.handleConn(conn)
+	}
+}
+
+func (s *strictDoQServer) handleConn(conn *quic.Conn) {
+	for {
+		stream, err := conn.AcceptStream(context.Background())
+		if err != nil {
+			return
+		}
+		go s.handleStream(stream)
+	}
+}
+
+func (s *strictDoQServer) handleStream(stream *quic.Stream) {
+	defer stream.Close()
+
+	// Drain until the client closes the send side. This is the behaviour
+	// that triggered the bug: if the client never sends STREAM FIN, this
+	// read blocks until the stream's deadline fires.
+	body, err := io.ReadAll(stream)
+	if err != nil {
+		return
+	}
+	if len(body) < 2 {
+		return
+	}
+	msgLen := uint16(body[0])<<8 | uint16(body[1])
+	if int(msgLen) != len(body)-2 {
+		return
+	}
+
+	msg := new(dns.Msg)
+	if err := msg.Unpack(body[2:]); err != nil {
+		return
+	}
+
+	response := new(dns.Msg)
+	response.SetReply(msg)
+	response.Authoritative = true
+	if len(msg.Question) > 0 && msg.Question[0].Qtype == dns.TypeA {
+		response.Answer = append(response.Answer, &dns.A{
+			Hdr: dns.RR_Header{
+				Name:   msg.Question[0].Name,
+				Rrtype: dns.TypeA,
+				Class:  dns.ClassINET,
+				Ttl:    300,
+			},
+			A: net.ParseIP("192.0.2.1"),
+		})
+	}
+
+	respBytes, err := response.Pack()
+	if err != nil {
+		return
+	}
+	respLen := uint16(len(respBytes))
+	if _, err := stream.Write([]byte{byte(respLen >> 8), byte(respLen & 0xFF)}); err != nil {
+		return
+	}
+	if _, err := stream.Write(respBytes); err != nil {
+		return
+	}
+}
+
+func newStrictDoQUpstream(t *testing.T, cert *x509.Certificate, addr string, useBootstrap bool) *UpstreamConfig {
+	t.Helper()
+
+	pool := x509.NewCertPool()
+	pool.AddCert(cert)
+
+	host, _, err := net.SplitHostPort(addr)
+	if err != nil {
+		t.Fatalf("split host/port %q: %v", addr, err)
+	}
+
+	uc := &UpstreamConfig{
+		Name:     "doq-strict",
+		Type:     ResolverTypeDOQ,
+		Endpoint: addr,
+		Domain:   host,
+		Timeout:  3000,
+	}
+	if useBootstrap {
+		uc.BootstrapIP = host
+	}
+	uc.SetCertPool(pool)
+	return uc
+}
+
+// TestDoQResolve_StrictServerWaitsForFIN exercises the RFC 9250 client-FIN
+// requirement. With the bug present, the server's io.ReadAll blocks until
+// the stream deadline expires and the client sees a timeout, so a successful
+// resolve here proves that the client now sends STREAM FIN before reading.
+func TestDoQResolve_StrictServerWaitsForFIN(t *testing.T) {
+	t.Parallel()
+
+	server := newStrictDoQServer(t)
+	uc := newStrictDoQUpstream(t, server.cert, server.addr, true)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	host, _, _ := net.SplitHostPort(server.addr)
+	pool := newDOQConnPool(uc, []string{host})
+	t.Cleanup(pool.CloseIdleConnections)
+
+	msg := new(dns.Msg)
+	msg.SetQuestion("example.com.", dns.TypeA)
+	msg.RecursionDesired = true
+
+	answer, err := pool.Resolve(ctx, msg)
+	if err != nil {
+		t.Fatalf("Resolve failed against strict DoQ server: %v", err)
+	}
+	if answer == nil || len(answer.Answer) == 0 {
+		t.Fatalf("Resolve returned no answer records: %+v", answer)
+	}
+	a, ok := answer.Answer[0].(*dns.A)
+	if !ok || !a.A.Equal(net.ParseIP("192.0.2.1")) {
+		t.Fatalf("unexpected answer: %+v", answer.Answer[0])
+	}
+}
+
+// TestDoQResolve_ParallelDialPathStrictFIN exercises the parallel-dial path
+// (no BootstrapIP) against the same FIN-strict server, so that both the
+// single-dial branch and the parallel-dial branch are covered.
+func TestDoQResolve_ParallelDialPathStrictFIN(t *testing.T) {
+	t.Parallel()
+
+	server := newStrictDoQServer(t)
+	uc := newStrictDoQUpstream(t, server.cert, server.addr, false)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	host, _, _ := net.SplitHostPort(server.addr)
+	pool := newDOQConnPool(uc, []string{host})
+	t.Cleanup(pool.CloseIdleConnections)
+
+	msg := new(dns.Msg)
+	msg.SetQuestion("example.com.", dns.TypeA)
+	msg.RecursionDesired = true
+
+	answer, err := pool.Resolve(ctx, msg)
+	if err != nil {
+		t.Fatalf("Resolve (parallel-dial path) failed against strict DoQ server: %v", err)
+	}
+	if answer == nil || len(answer.Answer) == 0 {
+		t.Fatalf("Resolve (parallel-dial path) returned no answer records: %+v", answer)
+	}
+}
+
+// TestDoQPool_ChurnDoesNotGrowFDs exercises the reconnect-churn scenario
+// described in github.com/Control-D-Inc/ctrld/issues/309: repeated dials
+// against a server that closes existing connections must not grow the process
+// FD count, because the pool now shares one UDP socket via quic.Transport instead
+// of allocating one per dial. Linux-only because /proc/self/fd is the cheapest
+// portable proxy for "what's still open."
+func TestDoQPool_ChurnDoesNotGrowFDs(t *testing.T) {
+	if runtime.GOOS != "linux" {
+		t.Skip("FD accounting via /proc/self/fd is linux-only")
+	}
+	t.Parallel()
+
+	server := newStrictDoQServer(t)
+	uc := newStrictDoQUpstream(t, server.cert, server.addr, true)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	host, _, _ := net.SplitHostPort(server.addr)
+	pool := newDOQConnPool(uc, []string{host})
+	t.Cleanup(pool.CloseIdleConnections)
+
+	makeQuery := func(i int) *dns.Msg {
+		msg := new(dns.Msg)
+		// Vary the question so any caching layer cannot short-circuit.
+		msg.SetQuestion(dns.Fqdn(strings.Repeat("a", 1+i%8)+".example.com"), dns.TypeA)
+		msg.RecursionDesired = true
+		return msg
+	}
+
+	// Warm the pool so the steady-state transport and at least one
+	// connection are open. Without this, the first resolve in the measured
+	// loop would inflate the baseline.
+	if _, err := pool.Resolve(ctx, makeQuery(0)); err != nil {
+		t.Fatalf("warm-up Resolve failed: %v", err)
+	}
+
+	baseline := countOpenFDs(t)
+
+	// Force reconnect churn by closing the connection between each query.
+	// Without the fix this would leak one UDP socket per round; with the
+	// fix the pool's shared transport keeps a single socket open.
+	const rounds = 20
+	for i := 1; i <= rounds; i++ {
+		// Drain any pooled connection so the next Resolve has to redial.
+		drainPooledConns(pool)
+
+		if _, err := pool.Resolve(ctx, makeQuery(i)); err != nil {
+			t.Fatalf("Resolve in churn loop iteration %d failed: %v", i, err)
+		}
+	}
+
+	// Give quic-go a moment to drop any background goroutines that hold
+	// references to closed sockets.
+	time.Sleep(200 * time.Millisecond)
+
+	after := countOpenFDs(t)
+
+	// Allow a small slack for transient FDs (goroutine wake-ups, qlog,
+	// etc.) but reject anything that scales with the number of rounds.
+	const slack = 5
+	if after > baseline+slack {
+		t.Fatalf("FD count grew under DoQ churn: baseline=%d after=%d rounds=%d (slack=%d)", baseline, after, rounds, slack)
+	}
+}
+
+// drainPooledConns removes any idle pooled connections so the next Resolve
+// is forced to dial a fresh one. It does not close the pool's transport.
+func drainPooledConns(p *doqConnPool) {
+	for {
+		select {
+		case dc := <-p.conns:
+			if dc.conn != nil {
+				dc.conn.CloseWithError(quic.ApplicationErrorCode(quic.NoError), "")
+			}
+		default:
+			return
+		}
+	}
+}
+
+func countOpenFDs(t *testing.T) int {
+	t.Helper()
+	entries, err := os.ReadDir("/proc/self/fd")
+	if err != nil {
+		t.Fatalf("read /proc/self/fd: %v", err)
+	}
+	return len(entries)
+}
+
+// TestDoQResolve_OversizedResponse_Rejected locks in the fix for
+// github.com/Control-D-Inc/ctrld/issues/312 on the DoQ transport: a
+// malicious upstream that writes a response larger than the DNS protocol
+// allows must be rejected with an explicit size error, not buffered
+// without bound into ctrld memory.
+func TestDoQResolve_OversizedResponse_Rejected(t *testing.T) {
+	t.Parallel()
+
+	// doqMaxResponseSize is 2 + dns.MaxMsgSize. Send something well past
+	// that. 256 KiB is enough to exceed the cap while keeping the test
+	// fast on loopback.
+	response := make([]byte, 256*1024)
+	// A well-formed length prefix isn't required: the size cap should
+	// fire before any framing check runs. Use a non-zero prefix so the
+	// test also documents that the order of validation is "size first,
+	// framing later."
+	response[0] = 0xFF
+	response[1] = 0xFF
+
+	server := newMalformedDoQServer(t, response)
+	uc := newMalformedDoQUpstream(t, server.cert, server.addr)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	pool := newDOQConnPool(uc, []string{"127.0.0.1"})
+	t.Cleanup(pool.CloseIdleConnections)
+
+	msg := new(dns.Msg)
+	msg.SetQuestion("example.com.", dns.TypeA)
+	msg.RecursionDesired = true
+
+	answer, err := pool.Resolve(ctx, msg)
+	if err == nil {
+		t.Fatalf("Resolve unexpectedly succeeded for oversized response; answer=%v", answer)
+	}
+	if !strings.Contains(err.Error(), "exceeds") {
+		t.Fatalf("error %q does not surface the size cap", err)
+	}
+	if answer != nil {
+		t.Fatalf("Resolve returned non-nil answer alongside error: %v", answer)
+	}
+}

dot.go

@@ -64,7 +64,8 @@ func newDOTClientPool(uc *UpstreamConfig, addrs []string) *dotConnPool {
 	dialer := newDialer(net.JoinHostPort(controldPublicDns, "53"))
 
 	tlsConfig := &tls.Config{
-		RootCAs: uc.certPool,
+		RootCAs:    uc.certPool,
+		MinVersion: tls.VersionTLS12,
 	}
 
 	if uc.BootstrapIP != "" {

go.mod

@@ -1,6 +1,6 @@
 module github.com/Control-D-Inc/ctrld
 
-go 1.24
+go 1.25.0
 
 require (
 	github.com/Masterminds/semver/v3 v3.2.1
@@ -29,16 +29,16 @@ require (
 	github.com/prometheus/client_golang v1.19.1
 	github.com/prometheus/client_model v0.5.0
 	github.com/prometheus/prom2json v1.3.3
-	github.com/quic-go/quic-go v0.57.1
+	github.com/quic-go/quic-go v0.59.1
 	github.com/rs/zerolog v1.28.0
 	github.com/spf13/cobra v1.9.1
 	github.com/spf13/pflag v1.0.6
 	github.com/spf13/viper v1.16.0
 	github.com/stretchr/testify v1.11.1
 	github.com/vishvananda/netlink v1.3.1
-	golang.org/x/net v0.43.0
+	golang.org/x/net v0.56.0
-	golang.org/x/sync v0.16.0
+	golang.org/x/sync v0.21.0
-	golang.org/x/sys v0.35.0
+	golang.org/x/sys v0.46.0
 	golang.zx2c4.com/wireguard/windows v0.5.3
 	tailscale.com v1.74.0
 )
@@ -92,11 +92,11 @@ require (
 	github.com/yusufpapurcu/wmi v1.2.4 // indirect
 	go4.org/mem v0.0.0-20220726221520-4f986261bf13 // indirect
 	go4.org/netipx v0.0.0-20231129151722-fdeea329fbba // indirect
-	golang.org/x/crypto v0.41.0 // indirect
+	golang.org/x/crypto v0.53.0 // indirect
-	golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842 // indirect
+	golang.org/x/exp v0.0.0-20240119083558-1b970713d09a // indirect
-	golang.org/x/mod v0.27.0 // indirect
+	golang.org/x/mod v0.36.0 // indirect
-	golang.org/x/text v0.28.0 // indirect
+	golang.org/x/text v0.38.0 // indirect
-	golang.org/x/tools v0.36.0 // indirect
+	golang.org/x/tools v0.45.0 // indirect
 	google.golang.org/protobuf v1.33.0 // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect

go.sum

@@ -271,8 +271,8 @@ github.com/prometheus/prom2json v1.3.3 h1:IYfSMiZ7sSOfliBoo89PcufjWO4eAR0gznGcET
 github.com/prometheus/prom2json v1.3.3/go.mod h1:Pv4yIPktEkK7btWsrUTWDDDrnpUrAELaOCj+oFwlgmc=
 github.com/quic-go/qpack v0.6.0 h1:g7W+BMYynC1LbYLSqRt8PBg5Tgwxn214ZZR34VIOjz8=
 github.com/quic-go/qpack v0.6.0/go.mod h1:lUpLKChi8njB4ty2bFLX2x4gzDqXwUpaO1DP9qMDZII=
-github.com/quic-go/quic-go v0.57.1 h1:25KAAR9QR8KZrCZRThWMKVAwGoiHIrNbT72ULHTuI10=
+github.com/quic-go/quic-go v0.59.1 h1:0Gmua0HW1Tv7ANR7hUYwRyD0MG5OJfgvYSZasGZzBic=
-github.com/quic-go/quic-go v0.57.1/go.mod h1:ly4QBAjHA2VhdnxhojRsCUOeJwKYg+taDlos92xb1+s=
+github.com/quic-go/quic-go v0.59.1/go.mod h1:upnsH4Ju1YkqpLXC305eW3yDZ4NfnNbmQRCMWS58IKU=
 github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.4.4 h1:8TfxU8dW6PdqD27gjM8MVNuicgxIjxpm4K7x4jp8sis=
 github.com/rivo/uniseg v0.4.4/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
@@ -349,8 +349,8 @@ golang.org/x/crypto v0.0.0-20210421170649-83a5a9bb288b/go.mod h1:T9bdIzuCu7OtxOm
 golang.org/x/crypto v0.0.0-20211209193657-4570a0811e8b/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20211215153901-e495a2d5b3d3/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20220722155217-630584e8d5aa/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
-golang.org/x/crypto v0.41.0 h1:WKYxWedPGCTVVl5+WHSSrOBT0O8lx32+zxmHxijgXp4=
+golang.org/x/crypto v0.53.0 h1:QZ4Muo8THX6CizN2vPPd5fBGHyogrdK9fG4wLPFUsto=
-golang.org/x/crypto v0.41.0/go.mod h1:pO5AFd7FA68rFak7rOAGVuygIISepHftHnr8dr6+sUc=
+golang.org/x/crypto v0.53.0/go.mod h1:DNLU434OwVakk9PzuwV8w62mAJpRJL3vsgcfp4Qnsio=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190510132918-efd6b22b2522/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
@@ -361,8 +361,8 @@ golang.org/x/exp v0.0.0-20191227195350-da58074b4299/go.mod h1:2RIsYlXP63K8oxa1u0
 golang.org/x/exp v0.0.0-20200119233911-0405dc783f0a/go.mod h1:2RIsYlXP63K8oxa1u096TMicItID8zy7Y6sNkU49FU4=
 golang.org/x/exp v0.0.0-20200207192155-f17229e696bd/go.mod h1:J/WKrq2StrnmMY6+EHIKF9dgMWnmCNThgcyBT1FY9mM=
 golang.org/x/exp v0.0.0-20200224162631-6cc2880d07d6/go.mod h1:3jZMyOhIsHpP37uCMkUooju7aAi5cS1Q23tOzKc+0MU=
-golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842 h1:vr/HnozRka3pE4EsMEg1lgkXJkTFJCVUX+S/ZT6wYzM=
+golang.org/x/exp v0.0.0-20240119083558-1b970713d09a h1:Q8/wZp0KX97QFTc2ywcOE0YRjZPVIx+MXInMzdvQqcA=
-golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842/go.mod h1:XtvwrStGgqGPLc4cjQfWqZHG1YFdYs6swckp8vpsjnc=
+golang.org/x/exp v0.0.0-20240119083558-1b970713d09a/go.mod h1:idGWGoKP1toJGkd5/ig9ZLuPcZBC3ewk7SzmH0uou08=
 golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
 golang.org/x/image v0.0.0-20190802002840-cff245a6509b/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
@@ -386,8 +386,8 @@ golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.1/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
-golang.org/x/mod v0.27.0 h1:kb+q2PyFnEADO2IEF935ehFUXlWiNjJWtRNgBLSfbxQ=
+golang.org/x/mod v0.36.0 h1:JJjpVx6myfUsUdAzZuOSTTmRE0PfZeNWzzvKrP7amb4=
-golang.org/x/mod v0.27.0/go.mod h1:rWI627Fq0DEoudcK+MBkNkCe0EetEaDSwJJkCcjpazc=
+golang.org/x/mod v0.36.0/go.mod h1:moc6ELqsWcOw5Ef3xVprK5ul/MvtVvkIXLziUOICjUQ=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190108225652-1e06a53dbb7e/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -420,8 +420,8 @@ golang.org/x/net v0.0.0-20201209123823-ac852fbbde11/go.mod h1:m0MpNAwzfU5UDzcl9v
 golang.org/x/net v0.0.0-20201224014010-6772e930b67b/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/net v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE=
+golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o=
-golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg=
+golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -441,8 +441,8 @@ golang.org/x/sync v0.0.0-20200317015054-43a5402ce75a/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201207232520-09787c993a3a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.16.0 h1:ycBJEhp9p4vXvUZNszeOq0kGTPghopOL8q0fq3vstxw=
+golang.org/x/sync v0.21.0 h1:HLII4xRRTtCRkxYp4HNFF0Js/Og6q2i++KXbg0gHCwM=
-golang.org/x/sync v0.16.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
+golang.org/x/sync v0.21.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -492,8 +492,8 @@ golang.org/x/sys v0.4.1-0.20230131160137-e7d7f63158de/go.mod h1:oPkhp1MJrh7nUepC
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.35.0 h1:vz1N37gP5bs89s7He8XuIYXpyY0+QlsKmzipCbUtyxI=
+golang.org/x/sys v0.46.0 h1:noSf2Fq6F8DBgS+LysIkx7rIExoNHJsxOAtPp4rthXw=
-golang.org/x/sys v0.35.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/sys v0.46.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
 golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -504,13 +504,11 @@ golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.4/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
-golang.org/x/text v0.28.0 h1:rhazDwis8INMIwQ4tpjLDzUhx6RlXqZNPEM0huQojng=
+golang.org/x/text v0.38.0 h1:sXmwo9DwP3OK9EZ7PqAdaooSGozfl/3a6/xJcbzPRhE=
-golang.org/x/text v0.28.0/go.mod h1:U8nCwOR8jO/marOQ0QbDiOngZVEBB7MAiitBuMjXiNU=
+golang.org/x/text v0.38.0/go.mod h1:YXZt3QhHUKYT53r2lLKFIVi6Ao1jdzrTR/KQ09qyxF4=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=
-golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -558,8 +556,8 @@ golang.org/x/tools v0.0.0-20201208233053-a543418bbed2/go.mod h1:emZCQorbCU4vsT4f
 golang.org/x/tools v0.0.0-20210105154028-b0ab187a4818/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20210108195828-e2f9c7f1fc8e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.1.0/go.mod h1:xkSsbof2nBLbhDlRMhhhyNLN/zl3eTqcnHD5viDpcZ0=
-golang.org/x/tools v0.36.0 h1:kWS0uv/zsvHEle1LbV5LE8QujrxB3wfQyxHfhOk0Qkg=
+golang.org/x/tools v0.45.0 h1:18qN3FAooORvApf5XjCXgsuayZOEtXf6JK18I3+ONa8=
-golang.org/x/tools v0.36.0/go.mod h1:WBDiHKJK8YgLHlcQPYQzNCkUxUypCaa5ZegCVutKm+s=
+golang.org/x/tools v0.45.0/go.mod h1:LuUGqqaXcXMEFEruIVJVm5mgDD8vww/z/SR1gQ4uE/0=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

internal/certs/root_ca_test.go

@@ -11,7 +11,8 @@ func TestCACertPool(t *testing.T) {
 	c := &http.Client{
 		Transport: &http.Transport{
 			TLSClientConfig: &tls.Config{
-				RootCAs: CACertPool(),
+				RootCAs:    CACertPool(),
+				MinVersion: tls.VersionTLS12,
 			},
 		},
 		Timeout: 2 * time.Second,

internal/controld/config.go

@@ -293,7 +293,7 @@ func apiTransport(cdDev bool) *http.Transport {
 		return dial(ctx, "tcp6", addrsFromPort(apiIpsV6, port))
 	}
 	if router.Name() == ddwrt.Name || runtime.GOOS == "android" {
-		transport.TLSClientConfig = &tls.Config{RootCAs: certs.CACertPool()}
+		transport.TLSClientConfig = &tls.Config{RootCAs: certs.CACertPool(), MinVersion: tls.VersionTLS12}
 	}
 	return transport
 }

internal/router/dnsmasq/dnsmasq.go

@@ -2,11 +2,11 @@ package dnsmasq
 
 import (
 	"errors"
-	"html/template"
 	"net"
 	"os"
 	"path/filepath"
 	"strings"
+	"text/template"
 
 	"github.com/Control-D-Inc/ctrld"
 )

nameservers.go

@@ -1,7 +1,14 @@
 package ctrld
 
+import "runtime"
+
 type dnsFn func() []string
 
+// isMobile reports whether the current OS is a mobile platform.
+func isMobile() bool {
+	return runtime.GOOS == "android" || runtime.GOOS == "ios"
+}
+
 // nameservers returns DNS nameservers from system settings.
 func nameservers() []string {
 	var dns []string

nameservers_darwin.go

@@ -25,6 +25,12 @@ func dnsFns() []dnsFn {
 func getDNSFromScutil() []string {
 	logger := *ProxyLogger.Load()
 
+	// Skip scutil on mobile platforms - not available in sandbox
+	if isMobile() {
+		Log(context.Background(), logger.Debug(), "skipping scutil DNS discovery on mobile platform")
+		return nil
+	}
+
 	const (
 		maxRetries    = 10
 		retryInterval = 100 * time.Millisecond
@@ -89,6 +95,11 @@ func getDNSFromScutil() []string {
 }
 
 func getDHCPNameservers(iface string) ([]string, error) {
+	// Skip ipconfig on mobile platforms - not available in sandbox
+	if isMobile() {
+		return nil, fmt.Errorf("ipconfig not available on mobile")
+	}
+
 	// Run the ipconfig command for the given interface.
 	cmd := exec.Command("ipconfig", "getpacket", iface)
 	output, err := cmd.Output()
@@ -201,6 +212,11 @@ func getAllDHCPNameservers() []string {
 }
 
 func patchNetIfaceName(iface *net.Interface) (bool, error) {
+	// Skip networksetup on mobile platforms - not available in sandbox
+	if isMobile() {
+		return false, nil
+	}
+
 	b, err := exec.Command("networksetup", "-listnetworkserviceorder").Output()
 	if err != nil {
 		return false, err

nameservers_linux.go

@@ -7,6 +7,7 @@ import (
 	"net"
 	"net/netip"
 	"os"
+	"runtime"
 	"strings"
 
 	"tailscale.com/net/netmon"
@@ -24,6 +25,11 @@ func dnsFns() []dnsFn {
 }
 
 func dns4() []string {
+	// Skip route-based DNS discovery on Android
+	if runtime.GOOS == "android" {
+		return nil
+	}
+
 	f, err := os.Open(v4RouteFile)
 	if err != nil {
 		return nil
@@ -64,6 +70,11 @@ func dns4() []string {
 }
 
 func dns6() []string {
+	// Skip route-based DNS discovery on Android
+	if runtime.GOOS == "android" {
+		return nil
+	}
+
 	f, err := os.Open(v6RouteFile)
 	if err != nil {
 		return nil
@@ -98,6 +109,11 @@ func dns6() []string {
 }
 
 func dnsFromSystemdResolver() []string {
+	// Skip systemd resolver on Android
+	if runtime.GOOS == "android" {
+		return nil
+	}
+
 	c, err := resolvconffile.ParseFile("/run/systemd/resolve/resolv.conf")
 	if err != nil {
 		return nil

nameservers_windows.go

@@ -56,6 +56,8 @@ const (
 var (
 	dcRetryMu     sync.Mutex
 	dcRetryCancel context.CancelFunc
+	dcRetryDomain string
+	dcRetryID     uint64
 
 	// Lazy-loaded netapi32 for DsGetDcNameW calls.
 	netapi32DLL  = windows.NewLazySystemDLL("netapi32.dll")
@@ -133,9 +135,6 @@ func dnsFromAdapter() []string {
 func getDNSServers(ctx context.Context) ([]string, error) {
 	logger := *ProxyLogger.Load()
 
-	// Cancel any in-flight DC retry from a previous network state.
-	cancelDCRetry()
-
 	// Check context before making the call
 	if ctx.Err() != nil {
 		return nil, ctx.Err()
@@ -157,6 +156,9 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 	var dcServers []string
 	var adDomain string
 	isDomain := checkDomainJoined()
+	if !isDomain {
+		cancelDCRetry()
+	}
 	if isDomain {
 		domainName, err := system.GetActiveDirectoryDomain()
 		if err != nil {
@@ -164,6 +166,7 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 				"Failed to get local AD domain: %v", err)
 		} else {
 			adDomain = domainName
+			cancelDCRetryForOtherDomain(domainName)
 			// Load netapi32.dll
 			var info *DomainControllerInfo
 			flags := uint32(DS_RETURN_DNS_NAME | DS_IP_REQUIRED | DS_IS_DNS_NAME)
@@ -205,7 +208,7 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 					// Start background retry for transient DC errors.
 					if isTransientDCError(ret) {
 						Log(ctx, logger.Info(),
-							"AD DC detection failed with transient error %d for %s, starting background retry", ret, domainName)
+							"AD DC detection failed with retryable error %d for %s, ensuring background retry", ret, domainName)
 						startDCRetry(domainName)
 					}
 				} else if info != nil {
@@ -219,6 +222,7 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 
 						if ip := net.ParseIP(dcAddr); ip != nil {
 							dcServers = append(dcServers, ip.String())
+							cancelDCRetry()
 							Log(ctx, logger.Debug(),
 								"Added domain controller DNS servers: %v", dcServers)
 						}
@@ -387,10 +391,13 @@ func checkDomainJoined() bool {
 }
 
 // isTransientDCError returns true if the DsGetDcName error code indicates
-// a transient failure that may succeed on retry.
+// a transient failure that may succeed on retry. ERROR_NO_SUCH_DOMAIN is
+// retryable here because we only call this path after Windows already reported
+// the machine is domain joined and returned a local AD domain name; during VPN
+// DNS churn, DC locator can temporarily fail to resolve that known domain.
 func isTransientDCError(code uintptr) bool {
 	switch code {
-	case errConnReset, errRPCUnavailable, errNoLogonServers, errDCNotFound, errNetUnreachable:
+	case errNoSuchDomain, errConnReset, errRPCUnavailable, errNoLogonServers, errDCNotFound, errNetUnreachable:
 		return true
 	default:
 		return false
@@ -404,23 +411,49 @@ func cancelDCRetry() {
 	if dcRetryCancel != nil {
 		dcRetryCancel()
 		dcRetryCancel = nil
+		dcRetryDomain = ""
+		dcRetryID = 0
 	}
 }
 
+// cancelDCRetryForOtherDomain keeps an existing retry alive during noisy
+// network-change refreshes, but stops it if Windows reports a different AD
+// domain. This avoids the start/cancel storm seen when DsGetDcName briefly
+// returns ERROR_NO_SUCH_DOMAIN while VPN DNS is still settling.
+func cancelDCRetryForOtherDomain(domainName string) {
+	dcRetryMu.Lock()
+	defer dcRetryMu.Unlock()
+	if dcRetryCancel == nil || dcRetryDomain == "" || strings.EqualFold(dcRetryDomain, domainName) {
+		return
+	}
+	dcRetryCancel()
+	dcRetryCancel = nil
+	dcRetryDomain = ""
+	dcRetryID = 0
+}
+
 // startDCRetry spawns a background goroutine that retries DsGetDcName with
 // exponential backoff. On success it appends the DC IP to the OS resolver.
 func startDCRetry(domainName string) {
 	dcRetryMu.Lock()
-	// Cancel any previous retry.
+	if dcRetryCancel != nil && strings.EqualFold(dcRetryDomain, domainName) {
+		ProxyLogger.Load().Debug().Msgf("AD DC retry already running for domain %s", domainName)
+		dcRetryMu.Unlock()
+		return
+	}
 	if dcRetryCancel != nil {
 		dcRetryCancel()
 	}
 	ctx, cancel := context.WithCancel(context.Background())
+	dcRetryID++
+	retryID := dcRetryID
 	dcRetryCancel = cancel
+	dcRetryDomain = domainName
 	dcRetryMu.Unlock()
 
-	go func() {
+	go func(retryID uint64) {
 		logger := *ProxyLogger.Load()
+		defer clearDCRetryIfCurrent(domainName, retryID)
 		delay := dcRetryInitialDelay
 
 		for attempt := 1; attempt <= dcRetryMaxAttempts; attempt++ {
@@ -472,7 +505,17 @@ func startDCRetry(domainName string) {
 
 		Log(ctx, logger.Warn(),
 			"AD DC retry exhausted %d attempts for domain %s", dcRetryMaxAttempts, domainName)
-	}()
+	}(retryID)
+}
+
+func clearDCRetryIfCurrent(domainName string, retryID uint64) {
+	dcRetryMu.Lock()
+	defer dcRetryMu.Unlock()
+	if dcRetryCancel != nil && dcRetryID == retryID && strings.EqualFold(dcRetryDomain, domainName) {
+		dcRetryCancel = nil
+		dcRetryDomain = ""
+		dcRetryID = 0
+	}
 }
 
 // tryGetDCAddress attempts a single DsGetDcName call and returns the DC IP on success,