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.

cmd/cli/cli.go

@@ -451,18 +451,7 @@ func run(appCallback *AppCallback, stopCh chan struct{}) {
 	p.onStopped = append(p.onStopped, func() {
 		// restore static DNS settings or DHCP
 		p.resetDNS(false, true)
-		// Iterate over all physical interfaces and restore static DNS if a saved static config exists.
+		restoreSavedStaticDNS("", false)
-		withEachPhysicalInterfaces("", "restore static DNS", func(i *net.Interface) error {
-			file := savedStaticDnsSettingsFilePath(i)
-			if _, err := os.Stat(file); err == nil {
-				if err := restoreDNS(i); err != nil {
-					mainLog.Load().Error().Err(err).Msgf("Could not restore static DNS on interface %s", i.Name)
-				} else {
-					mainLog.Load().Debug().Msgf("Restored static DNS on interface %s successfully", i.Name)
-				}
-			}
-			return nil
-		})
 	})
 
 	close(waitCh)
@@ -826,7 +815,7 @@ func processLogAndCacheFlags(v *viper.Viper, cfg *ctrld.Config) {
 }
 
 func netInterface(ifaceName string) (*net.Interface, error) {
-	if ifaceName == "auto" {
+	if ifaceName == autoIface {
 		ifaceName = defaultIfaceName()
 	}
 	var iface *net.Interface
@@ -1112,23 +1101,7 @@ func uninstall(p *prog, s service.Service) {
 		}
 		// restore static DNS settings or DHCP
 		p.resetDNS(false, true)
-
+		restoreSavedStaticDNS(p.runningIface, true)
-		// Iterate over all physical interfaces and restore DNS if a saved static config exists.
-		withEachPhysicalInterfaces(p.runningIface, "restore static DNS", func(i *net.Interface) error {
-			file := savedStaticDnsSettingsFilePath(i)
-			if _, err := os.Stat(file); err == nil {
-				if err := restoreDNS(i); err != nil {
-					mainLog.Load().Error().Err(err).Msgf("Could not restore static DNS on interface %s", i.Name)
-				} else {
-					mainLog.Load().Debug().Msgf("Restored static DNS on interface %s successfully", i.Name)
-					err = os.Remove(file)
-					if err != nil {
-						mainLog.Load().Debug().Err(err).Msgf("Could not remove saved static DNS file for interface %s", i.Name)
-					}
-				}
-			}
-			return nil
-		})
 
 		if router.Name() != "" {
 			mainLog.Load().Debug().Msg("Router cleanup")
@@ -1141,6 +1114,26 @@ func uninstall(p *prog, s service.Service) {
 	}
 }
 
+// restoreSavedStaticDNS restores DNS from saved static config files on physical interfaces.
+func restoreSavedStaticDNS(excludeIfaceName string, removeSaved bool) {
+	withEachPhysicalInterfaces(excludeIfaceName, "restore static DNS", func(i *net.Interface) error {
+		file := savedStaticDnsSettingsFilePath(i)
+		if _, err := os.Stat(file); err == nil {
+			if err := restoreDNS(i); err != nil {
+				mainLog.Load().Error().Err(err).Msgf("Could not restore static DNS on interface %s", i.Name)
+			} else {
+				mainLog.Load().Debug().Msgf("Restored static DNS on interface %s successfully", i.Name)
+				if removeSaved {
+					if err := os.Remove(file); err != nil {
+						mainLog.Load().Debug().Err(err).Msgf("Could not remove saved static DNS file for interface %s", i.Name)
+					}
+				}
+			}
+		}
+		return nil
+	})
+}
+
 func validateConfig(cfg *ctrld.Config) error {
 	if err := ctrld.ValidateConfig(validator.New(), cfg); err != nil {
 		var ve validator.ValidationErrors
@@ -2069,6 +2062,23 @@ func doValidateCdRemoteConfig(cdUID string, fatal bool) error {
 	return nil
 }
 
+// ensureRunningIfaceForInvalidUninstall populates p.runningIface before the
+// invalid-device self-uninstall resets DNS. This path can run early during
+// service startup (e.g. right after a reboot) before the running interface is
+// otherwise known. resetDNS, via resetDNSForRunningIface, silently skips DNS
+// restoration when p.runningIface is empty, which would leave the OS pointed at
+// ctrld's local listener after the service is removed. See issue-556.
+func ensureRunningIfaceForInvalidUninstall(p *prog, s service.Service) {
+	if iface == "" {
+		iface = autoIface
+	}
+	p.preRun()
+	if ir := runningIface(s); ir != nil {
+		p.runningIface = ir.Name
+		p.requiredMultiNICsConfig = ir.All
+	}
+}
+
 // uninstallInvalidCdUID performs self-uninstallation because the ControlD device does not exist.
 func uninstallInvalidCdUID(p *prog, logger zerolog.Logger, doStop bool) bool {
 	s, err := newService(p, svcConfig)
@@ -2076,8 +2086,13 @@ func uninstallInvalidCdUID(p *prog, logger zerolog.Logger, doStop bool) bool {
 		logger.Warn().Err(err).Msg("failed to create new service")
 		return false
 	}
+	ensureRunningIfaceForInvalidUninstall(p, s)
 	// restore static DNS settings or DHCP
 	p.resetDNS(false, true)
+	// The invalid-device path may run early during service startup before runningIface
+	// is known. Restore every saved static DNS file so uninstalling does not leave the
+	// OS pointed at ctrld's local listener after the service is removed.
+	restoreSavedStaticDNS("", true)
 
 	tasks := []task{{s.Uninstall, true, "Uninstall"}}
 	if doTasks(tasks) {

cmd/cli/cli_intercept_listener_test.go

@@ -1,6 +1,10 @@
 package cli
 
-import "testing"
+import (
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
 
 func TestIsExplicitInterceptListener(t *testing.T) {
 	tests := []struct {
@@ -26,3 +30,87 @@ func TestIsExplicitInterceptListener(t *testing.T) {
 		})
 	}
 }
+
+// TestPreserveBoundListeners is a regression test for #551: on reload, the on-disk
+// generated config still declares 127.0.0.1:53, but the running listener has fallen back
+// to 127.0.0.1:5354. preserveBoundListeners must keep the in-memory config on the actual
+// bound port so pf rdr rules and probes do not target the dead default port.
+func TestPreserveBoundListeners(t *testing.T) {
+	// cur = actual running listener (fell back to 5354); newCfg = freshly read from disk (53).
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 53}}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].Port; got != 5354 {
+		t.Errorf("listener port after reload = %d, want 5354 (actual bound port)", got)
+	}
+	if got := newListeners["0"].IP; got != "127.0.0.1" {
+		t.Errorf("listener IP after reload = %q, want 127.0.0.1", got)
+	}
+}
+
+// TestPreserveBoundListeners_NoChange verifies that when the on-disk config matches the
+// running listener, the config is left untouched (a legitimate reload with the same port).
+func TestPreserveBoundListeners_NoChange(t *testing.T) {
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].Port; got != 5354 {
+		t.Errorf("listener port = %d, want 5354", got)
+	}
+}
+
+// TestPreserveBoundListeners_MissingCurrent verifies that a listener present on disk but not
+// in the current running set (e.g. newly added) is left as configured.
+func TestPreserveBoundListeners_MissingCurrent(t *testing.T) {
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{
+		"0": {IP: "127.0.0.1", Port: 53},
+		"1": {IP: "127.0.0.1", Port: 5355},
+	}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].Port; got != 5354 {
+		t.Errorf("listener 0 port = %d, want 5354 (preserved)", got)
+	}
+	if got := newListeners["1"].Port; got != 5355 {
+		t.Errorf("listener 1 port = %d, want 5355 (unchanged, no current binding)", got)
+	}
+}
+
+// TestPreserveBoundListeners_ExplicitChangeNotMasked verifies that an explicit, non-default
+// listener in the reloaded config is applied rather than reverted to the old bound listener.
+// Reverting an explicit change would make the control-server reload comparison return 200
+// instead of 201, silently dropping the new listener. Regression guard for #551 review.
+func TestPreserveBoundListeners_ExplicitChangeNotMasked(t *testing.T) {
+	// Running listener fell back to 5354; user reloads with an explicit new listener.
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.2", Port: 5399}}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].IP; got != "127.0.0.2" {
+		t.Errorf("explicit listener IP = %q, want 127.0.0.2 (not reverted)", got)
+	}
+	if got := newListeners["0"].Port; got != 5399 {
+		t.Errorf("explicit listener port = %d, want 5399 (not reverted)", got)
+	}
+}
+
+// TestPreserveBoundListeners_ExplicitDefaultPreserved verifies that the default
+// 127.0.0.1:53 listener remains fallback-eligible: when it diverges from the running
+// fallback port it is still preserved (isExplicitInterceptListener treats :53 as non-explicit).
+func TestPreserveBoundListeners_ExplicitDefaultPreserved(t *testing.T) {
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 53}}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].Port; got != 5354 {
+		t.Errorf("default listener port = %d, want 5354 (preserved fallback)", got)
+	}
+}

cmd/cli/commands.go

@@ -399,7 +399,7 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 			reportSetDnsOk := func(sockDir string) {
 				if cc := newSocketControlClient(ctx, s, sockDir); cc != nil {
 					if resp, _ := cc.post(ifacePath, nil); resp != nil && resp.StatusCode == http.StatusOK {
-						if iface == "auto" {
+						if iface == autoIface {
 							iface = defaultIfaceName()
 						}
 						res := &ifaceResponse{}
@@ -748,7 +748,7 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 			startCmd.Run(cmd, args)
 		},
 	}
-	startCmdAlias.Flags().StringVarP(&ifaceStartStop, "iface", "", "auto", `Update DNS setting for iface, "auto" means the default interface gateway`)
+	startCmdAlias.Flags().StringVarP(&ifaceStartStop, "iface", "", autoIface, `Update DNS setting for iface, "auto" means the default interface gateway`)
 	startCmdAlias.Flags().AddFlagSet(startCmd.Flags())
 	rootCmd.AddCommand(startCmdAlias)
 
@@ -833,7 +833,7 @@ func initStopCmd() *cobra.Command {
 			stopCmd.Run(cmd, args)
 		},
 	}
-	stopCmdAlias.Flags().StringVarP(&ifaceStartStop, "iface", "", "auto", `Reset DNS setting for iface, "auto" means the default interface gateway`)
+	stopCmdAlias.Flags().StringVarP(&ifaceStartStop, "iface", "", autoIface, `Reset DNS setting for iface, "auto" means the default interface gateway`)
 	stopCmdAlias.Flags().AddFlagSet(stopCmd.Flags())
 	rootCmd.AddCommand(stopCmdAlias)
 
@@ -865,7 +865,7 @@ func initRestartCmd() *cobra.Command {
 				return
 			}
 			if iface == "" {
-				iface = "auto"
+				iface = autoIface
 			}
 			p.preRun()
 			if ir := runningIface(s); ir != nil {
@@ -1111,7 +1111,7 @@ NOTE: Uninstalling will set DNS to values provided by DHCP.`,
 				return
 			}
 			if iface == "" {
-				iface = "auto"
+				iface = autoIface
 			}
 			p.preRun()
 			if ir := runningIface(s); ir != nil {
@@ -1207,7 +1207,7 @@ NOTE: Uninstalling will set DNS to values provided by DHCP.`,
 			uninstallCmd.Run(cmd, args)
 		},
 	}
-	uninstallCmdAlias.Flags().StringVarP(&ifaceStartStop, "iface", "", "auto", `Reset DNS setting for iface, "auto" means the default interface gateway`)
+	uninstallCmdAlias.Flags().StringVarP(&ifaceStartStop, "iface", "", autoIface, `Reset DNS setting for iface, "auto" means the default interface gateway`)
 	uninstallCmdAlias.Flags().AddFlagSet(uninstallCmd.Flags())
 	rootCmd.AddCommand(uninstallCmdAlias)
 
@@ -1400,7 +1400,7 @@ func initUpgradeCmd() *cobra.Command {
 				return
 			}
 			if iface == "" {
-				iface = "auto"
+				iface = autoIface
 			}
 			p.preRun()
 			if ir := runningIface(s); ir != nil {
@@ -1595,7 +1595,7 @@ func onlyInterceptFlags(args []string) bool {
 			} else {
 				return false
 			}
-		case arg == "--iface=auto" || arg == "--iface" || arg == "auto":
+		case arg == "--iface="+autoIface || arg == "--iface" || arg == autoIface:
 			// Auto-added by startCmdAlias or its value; safe to ignore.
 			continue
 		default:

cmd/cli/dns_intercept_darwin_test.go

@@ -123,6 +123,35 @@ func TestPFBuildAnchorRules_Ordering(t *testing.T) {
 	}
 }
 
+// TestPFBuildAnchorRules_FallbackPort verifies that when the listener falls back
+// to an alternate local port (e.g. 5354 because mDNSResponder owns *:53), the pf
+// rdr rules redirect DNS to the ACTUAL bound port, not the configured default 53.
+// Regression test for #551: pf redirected to a dead port after listener fallback.
+func TestPFBuildAnchorRules_FallbackPort(t *testing.T) {
+	// Configured/generated listener is 127.0.0.1:53, but the runtime bound port is 5354.
+	p := &prog{cfg: &ctrld.Config{Listener: map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}}}
+	rules := p.buildPFAnchorRules(nil)
+
+	// rdr must redirect to the actual bound port 5354.
+	if !strings.Contains(rules, "rdr on lo0 inet proto udp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 5354") {
+		t.Errorf("UDP rdr must redirect to bound port 5354, got:\n%s", rules)
+	}
+	if !strings.Contains(rules, "rdr on lo0 inet proto tcp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 5354") {
+		t.Errorf("TCP rdr must redirect to bound port 5354, got:\n%s", rules)
+	}
+
+	// The rdr redirect target must NOT point at the dead default port 53.
+	// Match the exact port at line end so "port 5354" is not a false positive.
+	if strings.Contains(rules, "-> 127.0.0.1 port 53\n") {
+		t.Errorf("rdr must not redirect to dead port 53 after fallback, got:\n%s", rules)
+	}
+
+	// The inbound accept rule must also target the actual bound port.
+	if !strings.Contains(rules, "127.0.0.1 port 5354") {
+		t.Errorf("pass in rule must reference bound port 5354, got:\n%s", rules)
+	}
+}
+
 // TestPFAddressFamily tests the pfAddressFamily helper.
 func TestPFAddressFamily(t *testing.T) {
 	tests := []struct {

cmd/cli/dns_proxy.go

@@ -736,6 +736,17 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 			}
 			continue
 		}
+		// Reject an answer whose question does not match the request before it
+		// can be served or cached. A mismatched question means the upstream
+		// answered a different name/type than asked; caching it would poison
+		// the shared cache with wrong-domain records for the requested name.
+		// See github.com/Control-D-Inc/ctrld/issues/322.
+		if !sameQuestion(req.msg, answer) {
+			ctrld.Log(ctx, mainLog.Load().Debug(),
+				"discarding answer from %s: question mismatch (asked %q, got %q)",
+				upstreams[n], questionString(req.msg), questionString(answer))
+			continue
+		}
 		// We are doing LAN/PTR lookup using private resolver, so always process next one.
 		// Except for the last, we want to send response instead of saying all upstream failed.
 		if answer.Rcode != dns.RcodeSuccess && isLanOrPtrQuery && n != len(upstreamConfigs)-1 {
@@ -899,6 +910,33 @@ func containRcode(rcodes []int, rcode int) bool {
 	return false
 }
 
+// sameQuestion reports whether the upstream answer echoes the request's
+// question. A well-behaved resolver always copies the question section from
+// the query (RFC 1035 section 4.1.2); names are compared case-insensitively
+// because DNS names are case-insensitive. A mismatch means the upstream
+// answered a different name/type than asked - malformed or malicious - and the
+// answer must not be served or cached, or it would poison the shared cache with
+// wrong-domain records. See github.com/Control-D-Inc/ctrld/issues/322.
+func sameQuestion(req, answer *dns.Msg) bool {
+	if req == nil || answer == nil {
+		return false
+	}
+	if len(req.Question) == 0 || len(answer.Question) == 0 {
+		return false
+	}
+	rq, aq := req.Question[0], answer.Question[0]
+	return rq.Qtype == aq.Qtype && rq.Qclass == aq.Qclass && strings.EqualFold(rq.Name, aq.Name)
+}
+
+// questionString renders a message's first question as "name/type" for logging.
+func questionString(msg *dns.Msg) string {
+	if msg == nil || len(msg.Question) == 0 {
+		return "<none>"
+	}
+	q := msg.Question[0]
+	return q.Name + "/" + dns.TypeToString[q.Qtype]
+}
+
 func setCachedAnswerTTL(answer *dns.Msg, now, expiredTime time.Time) {
 	ttlSecs := expiredTime.Sub(now).Seconds()
 	if ttlSecs < 0 {
@@ -1299,7 +1337,8 @@ func isPrivatePtrLookup(m *dns.Msg) bool {
 			return addr.IsPrivate() ||
 				addr.IsLoopback() ||
 				addr.IsLinkLocalUnicast() ||
-				tsaddr.CGNATRange().Contains(addr)
+				tsaddr.CGNATRange().Contains(addr) ||
+				isServiceContinuityAddr(addr)
 		}
 	}
 	return false
@@ -1337,6 +1376,20 @@ func isLanHostname(name string) bool {
 		strings.HasSuffix(name, ".local")
 }
 
+// ipv4ServiceContinuityPrefix is the RFC 7335 IPv4 Service Continuity Prefix
+// (192.0.0.0/29), used by the CLAT in 464XLAT/DS-Lite transition setups. On such
+// networks (common on IPv6-only cellular carriers and iPhone hotspots) the local
+// machine's DNS queries reach ctrld with a source in this range (e.g. 192.0.0.2),
+// so they must be treated as local, not WAN. Go's netip.IsPrivate does not cover
+// this range — the same reason the CGNAT range is special-cased below. See #552.
+var ipv4ServiceContinuityPrefix = netip.MustParsePrefix("192.0.0.0/29")
+
+// isServiceContinuityAddr reports whether ip is in the RFC 7335 IPv4 Service
+// Continuity Prefix (464XLAT/DS-Lite CLAT).
+func isServiceContinuityAddr(ip netip.Addr) bool {
+	return ipv4ServiceContinuityPrefix.Contains(ip)
+}
+
 // isWanClient reports whether the input is a WAN address.
 func isWanClient(na net.Addr) bool {
 	var ip netip.Addr
@@ -1347,7 +1400,8 @@ func isWanClient(na net.Addr) bool {
 		!ip.IsPrivate() &&
 		!ip.IsLinkLocalUnicast() &&
 		!ip.IsLinkLocalMulticast() &&
-		!tsaddr.CGNATRange().Contains(ip)
+		!tsaddr.CGNATRange().Contains(ip) &&
+		!isServiceContinuityAddr(ip)
 }
 
 // isIPv6LoopbackListener reports whether the listener address is [::1].

cmd/cli/dns_proxy_test.go

@@ -405,6 +405,8 @@ func Test_isPrivatePtrLookup(t *testing.T) {
 		{"CGNAT", newDnsMsgPtr("100.66.27.28", t), true},
 		{"Loopback", newDnsMsgPtr("127.0.0.1", t), true},
 		{"Link Local Unicast", newDnsMsgPtr("fe80::69f6:e16e:8bdb:433f", t), true},
+		// RFC 7335 IPv4 Service Continuity Prefix (464XLAT/DS-Lite CLAT), see #552.
+		{"464XLAT CLAT host", newDnsMsgPtr("192.0.0.2", t), true},
 		{"Public IP", newDnsMsgPtr("8.8.8.8", t), false},
 	}
 	for _, tc := range tests {
@@ -452,6 +454,11 @@ func Test_isWanClient(t *testing.T) {
 		{"CGNAT", &net.UDPAddr{IP: net.ParseIP("100.66.27.28")}, false},
 		{"Loopback", &net.UDPAddr{IP: net.ParseIP("127.0.0.1")}, false},
 		{"Link Local Unicast", &net.UDPAddr{IP: net.ParseIP("fe80::69f6:e16e:8bdb:433f")}, false},
+		// RFC 7335 IPv4 Service Continuity Prefix (464XLAT/DS-Lite CLAT), see #552.
+		{"464XLAT PLAT side", &net.UDPAddr{IP: net.ParseIP("192.0.0.1")}, false},
+		{"464XLAT CLAT host", &net.UDPAddr{IP: net.ParseIP("192.0.0.2")}, false},
+		// Outside the /29 but inside 192.0.0.0/24: still WAN (fix is scoped to /29).
+		{"192.0.0.0/24 outside /29", &net.UDPAddr{IP: net.ParseIP("192.0.0.100")}, true},
 		{"Public", &net.UDPAddr{IP: net.ParseIP("8.8.8.8")}, true},
 	}
 	for _, tc := range tests {
@@ -474,3 +481,33 @@ func Test_prog_queryFromSelf(t *testing.T) {
 		p.queryFromSelf("foo")
 	})
 }
+
+func Test_sameQuestion(t *testing.T) {
+	mk := func(name string, qtype uint16) *dns.Msg {
+		m := new(dns.Msg)
+		m.SetQuestion(name, qtype)
+		return m
+	}
+	tests := []struct {
+		name   string
+		req    *dns.Msg
+		answer *dns.Msg
+		want   bool
+	}{
+		{"identical", mk("example.com.", dns.TypeA), mk("example.com.", dns.TypeA), true},
+		{"case insensitive", mk("Example.COM.", dns.TypeA), mk("example.com.", dns.TypeA), true},
+		{"different name", mk("victim.example.", dns.TypeA), mk("attacker.example.", dns.TypeA), false},
+		{"different type", mk("example.com.", dns.TypeA), mk("example.com.", dns.TypeAAAA), false},
+		{"nil req", nil, mk("example.com.", dns.TypeA), false},
+		{"nil answer", mk("example.com.", dns.TypeA), nil, false},
+		{"empty answer question", mk("example.com.", dns.TypeA), new(dns.Msg), false},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			if got := sameQuestion(tc.req, tc.answer); got != tc.want {
+				t.Errorf("sameQuestion() = %v, want %v", got, tc.want)
+			}
+		})
+	}
+}

cmd/cli/log_writer.go

@@ -318,6 +318,12 @@ func (p *prog) initInternalLogging(writers []io.Writer) {
 
 // needInternalLogging reports whether prog needs to run internal logging.
 func (p *prog) needInternalLogging() bool {
+	// Do not run in silent mode: the user explicitly asked for no logging, so
+	// ctrld must not create or write the persisted internal log file (nor reset
+	// the global level back to debug). See https://github.com/Control-D-Inc/ctrld/issues/320.
+	if silent {
+		return false
+	}
 	// Do not run in non-cd mode.
 	if cdUID == "" {
 		return false

cmd/cli/log_writer_silent_test.go

@@ -0,0 +1,66 @@
+package cli
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+// Test_needInternalLogging_silent is a regression test for
+// https://github.com/Control-D-Inc/ctrld/issues/320: running with --silent must
+// not enable internal logging, otherwise ctrld creates and writes
+// <homedir>/ctrld.log (and, when verbose==0, resets the global level back to
+// debug) despite the user asking for silence.
+func Test_needInternalLogging_silent(t *testing.T) {
+	origSilent, origCdUID := silent, cdUID
+	t.Cleanup(func() { silent, cdUID = origSilent, origCdUID })
+
+	tests := []struct {
+		name    string
+		silent  bool
+		cdUID   string
+		logPath string
+		want    bool
+	}{
+		{"silent suppresses internal logging in cd mode", true, "test-uid", "", false},
+		{"cd mode enables internal logging", false, "test-uid", "", true},
+		{"non-cd mode disabled", false, "", "", false},
+		{"explicit log path disables internal logging", false, "test-uid", "/var/log/ctrld.log", false},
+	}
+	for _, tt := range tests {
+		tt := tt
+		t.Run(tt.name, func(t *testing.T) {
+			silent = tt.silent
+			cdUID = tt.cdUID
+			p := &prog{cfg: &ctrld.Config{}}
+			p.cfg.Service.LogPath = tt.logPath
+			if got := p.needInternalLogging(); got != tt.want {
+				t.Fatalf("needInternalLogging() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+// Test_initInternalLogging_silentCreatesNoFile drives the real initInternalLogging
+// path and asserts that a --silent --cd run does not create <homedir>/ctrld.log,
+// which is the observable failure reported in
+// https://github.com/Control-D-Inc/ctrld/issues/320.
+func Test_initInternalLogging_silentCreatesNoFile(t *testing.T) {
+	origSilent, origCdUID, origHomedir := silent, cdUID, homedir
+	t.Cleanup(func() { silent, cdUID, homedir = origSilent, origCdUID, origHomedir })
+
+	dir := t.TempDir()
+	homedir = dir
+	cdUID = "test-uid" // cd mode, which would otherwise enable internal logging
+	silent = true
+
+	p := &prog{cfg: &ctrld.Config{}}
+	p.initInternalLogging(nil)
+
+	logPath := filepath.Join(dir, logFileName)
+	if _, err := os.Stat(logPath); !os.IsNotExist(err) {
+		t.Fatalf("silent mode must not create %s (stat err = %v)", logPath, err)
+	}
+}

cmd/cli/main.go

@@ -56,6 +56,9 @@ const (
 	cdOrgFlagName          = "cd-org"
 	customHostnameFlagName = "custom-hostname"
 	nextdnsFlagName        = "nextdns"
+
+	// autoIface is the sentinel --iface value meaning "use the default gateway interface".
+	autoIface = "auto"
 )
 
 func init() {

cmd/cli/prog.go

@@ -337,6 +337,18 @@ func (p *prog) runWait() {
 
 		p.mu.Lock()
 		*p.cfg = *newCfg
+		// In DNS-intercept mode on macOS, the DNS listener is bound once at startup and is
+		// NOT re-bound on reload (see prog.run: serveDNS is started only when !reload). When
+		// the configured/generated port (e.g. 127.0.0.1:53) is unavailable at startup because
+		// mDNSResponder owns *:53, ctrld falls back to an alternate local port (e.g. 5354).
+		// The on-disk config still declares 53, so adopting it here would revert p.cfg to a
+		// port nothing is listening on, and the pf rdr rules/probes rebuilt from p.cfg would
+		// target a dead port. Since a reload cannot move the running listener anyway, keep
+		// p.cfg pointing at the actual bound listener. The on-disk config (written above) is
+		// left unchanged. See #551.
+		if dnsIntercept && runtime.GOOS == "darwin" {
+			preserveBoundListeners(p.cfg.Listener, curListener)
+		}
 		p.mu.Unlock()
 
 		logger.Notice().Msg("reloading config successfully")
@@ -348,8 +360,41 @@ func (p *prog) runWait() {
 	}
 }
 
+// preserveBoundListeners overrides the IP/Port of each listener in newListeners with the
+// actual bound address from curListeners when they differ, logging the divergence. It is used
+// on config reload in DNS-intercept mode where the running listener is never re-bound, so a
+// port change on disk (e.g. reverting a fallback 5354 back to the generated 53) must not be
+// applied to the in-memory config that drives pf rdr rules and probes.
+//
+// Preservation is limited to fallback-eligible (default/unset, i.e. 127.0.0.1:53) listeners.
+// An explicit, non-default listener in the reloaded config is an intentional change that must
+// be applied: tryUpdateListenerConfigIntercept binds explicit listeners exactly (no fallback),
+// and the control-server reload handler detects the IP/port diff to trigger a restart that
+// re-binds. Reverting an explicit change here would make that comparison return 200 instead of
+// 201, silently dropping the new listener. See #551.
+func preserveBoundListeners(newListeners, curListeners map[string]*ctrld.ListenerConfig) {
+	for n, curLc := range curListeners {
+		newLc := newListeners[n]
+		if newLc == nil || curLc == nil {
+			continue
+		}
+		if newLc.IP == curLc.IP && newLc.Port == curLc.Port {
+			continue
+		}
+		if isExplicitInterceptListener(newLc.IP, newLc.Port) {
+			continue
+		}
+		mainLog.Load().Info().
+			Str("configured", net.JoinHostPort(newLc.IP, strconv.Itoa(newLc.Port))).
+			Str("actual", net.JoinHostPort(curLc.IP, strconv.Itoa(curLc.Port))).
+			Msg("DNS intercept: preserving actual bound listener across reload; on-disk config port not applied to running listener")
+		newLc.IP = curLc.IP
+		newLc.Port = curLc.Port
+	}
+}
+
 func (p *prog) preRun() {
-	if iface == "auto" {
+	if iface == autoIface {
 		iface = defaultIfaceName()
 		p.requiredMultiNICsConfig = requiredMultiNICsConfig()
 	}

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/uninstall_invalid_test.go

@@ -0,0 +1,61 @@
+package cli
+
+import "testing"
+
+// Test_ensureRunningIfaceForInvalidUninstall is a regression test for issue-556:
+// after a reboot, the invalid-device self-uninstall path could run before the
+// running interface was known. Because resetDNS (via resetDNSForRunningIface)
+// silently skips DNS restoration when p.runningIface is empty, the OS was left
+// pointed at ctrld's local listener with no internet after the service was
+// removed. ensureRunningIfaceForInvalidUninstall must populate p.runningIface
+// before resetDNS runs.
+func Test_ensureRunningIfaceForInvalidUninstall(t *testing.T) {
+	// preRun mutates the package-level iface global; restore it after the test.
+	origIface := iface
+	t.Cleanup(func() { iface = origIface })
+
+	// newService needs the package service config; it is safe to build here
+	// because ensureRunningIfaceForInvalidUninstall only queries the (absent)
+	// control socket via runningIface, which returns nil when ctrld is not
+	// running, and performs no DNS or service mutation.
+	s, err := newService(&prog{}, svcConfig)
+	if err != nil {
+		t.Fatalf("newService: %v", err)
+	}
+
+	t.Run("iface flag already resolved but not yet copied", func(t *testing.T) {
+		iface = "eth-test"
+		p := &prog{}
+
+		// Precondition mirrors the buggy post-reboot state: an empty running
+		// interface would make resetDNS skip restoration entirely.
+		if p.runningIface != "" {
+			t.Fatalf("precondition: runningIface = %q, want empty", p.runningIface)
+		}
+
+		ensureRunningIfaceForInvalidUninstall(p, s)
+
+		if p.runningIface == "" {
+			t.Fatal("runningIface still empty after prepare: resetDNS would skip DNS " +
+				"restoration and leave the OS pointed at ctrld's local listener")
+		}
+		if p.runningIface != "eth-test" {
+			t.Fatalf("runningIface = %q, want the resolved iface %q", p.runningIface, "eth-test")
+		}
+	})
+
+	t.Run("iface unset falls back to auto-detected interface", func(t *testing.T) {
+		iface = ""
+		p := &prog{}
+
+		ensureRunningIfaceForInvalidUninstall(p, s)
+
+		// With iface unset the prep resolves "auto" to the default interface
+		// (defaultIfaceName never returns empty on the supported platforms), so
+		// resetDNS has a concrete interface to restore.
+		if p.runningIface == "" {
+			t.Fatal("runningIface still empty after prepare with iface unset: " +
+				"resetDNS would skip DNS restoration")
+		}
+	})
+}

dns.go

@@ -14,6 +14,12 @@ func SetCacheReply(answer, msg *dns.Msg, code int) {
 		// See https://datatracker.ietf.org/doc/html/rfc7873#section-4
 		sCookie.Cookie = cCookie.Cookie[:16] + sCookie.Cookie[16:]
 	}
+	// NOTE: the answer's EDNS Client Subnet (ECS) is intentionally left as the
+	// upstream returned it. Correctness across clients is guaranteed by
+	// partitioning the cache and singleflight keys by ECS (see
+	// dnscache.CanonicalECS), so a cache hit only ever serves an answer that was
+	// resolved for the requester's own subnet. Rewriting the ECS option here
+	// without re-scoping the Answer records would violate RFC 7871 §7.3.
 }
 
 // getEdns0Cookie returns Edns0 cookie from *dns.OPT if present.

dns_test.go

@@ -0,0 +1,57 @@
+package ctrld
+
+import (
+	"net"
+	"testing"
+
+	"github.com/miekg/dns"
+)
+
+// Test_SetCacheReply_DoesNotRewriteECS documents the post-#564 contract: cross-client
+// correctness is guaranteed by partitioning the cache/singleflight keys by ECS
+// (dnscache.CanonicalECS), NOT by rewriting the cached answer's ECS option. Rewriting the
+// ECS metadata while leaving the Answer records scoped to another subnet would violate
+// RFC 7871 §7.3 and make forwarders accept a wrong-subnet answer. SetCacheReply must
+// therefore leave the answer's ECS untouched.
+func Test_SetCacheReply_DoesNotRewriteECS(t *testing.T) {
+	answer := new(dns.Msg)
+	answer.SetQuestion(dns.Fqdn("controld.com"), dns.TypeA)
+	answer.SetEdns0(4096, false)
+	cachedSubnet := &dns.EDNS0_SUBNET{
+		Code:          dns.EDNS0SUBNET,
+		Family:        2,
+		SourceNetmask: 64,
+		SourceScope:   64,
+		Address:       net.ParseIP("2001:db8:1::"),
+	}
+	answer.IsEdns0().Option = append(answer.IsEdns0().Option, cachedSubnet)
+
+	req := new(dns.Msg)
+	req.SetQuestion(dns.Fqdn("controld.com"), dns.TypeA)
+	req.SetEdns0(4096, true)
+	req.IsEdns0().Option = append(req.IsEdns0().Option, &dns.EDNS0_SUBNET{
+		Code:          dns.EDNS0SUBNET,
+		Family:        2,
+		SourceNetmask: 64,
+		Address:       net.ParseIP("2001:db8:2::"),
+	})
+
+	SetCacheReply(answer, req, dns.RcodeSuccess)
+
+	var got *dns.EDNS0_SUBNET
+	for _, o := range answer.IsEdns0().Option {
+		if e, ok := o.(*dns.EDNS0_SUBNET); ok {
+			got = e
+			break
+		}
+	}
+	if got == nil {
+		t.Fatal("SetCacheReply dropped the answer's ECS option")
+	}
+	if want := net.ParseIP("2001:db8:1::"); !got.Address.Equal(want) {
+		t.Fatalf("SetCacheReply rewrote the answer ECS to the requester's subnet: got %v, want %v (unchanged)", got.Address, want)
+	}
+	if got.SourceScope != 64 {
+		t.Fatalf("SetCacheReply altered the answer ECS scope: got %d, want 64 (unchanged)", got.SourceScope)
+	}
+}

doh_test.go

@@ -12,7 +12,6 @@ import (
 	"net/url"
 	"runtime"
 	"strings"
-	"sync/atomic"
 	"testing"
 	"time"
 
@@ -268,33 +267,62 @@ func newTestHTTP3Server(t *testing.T, handler http.Handler) *testHTTP3Server {
 	return h3Server
 }
 
-// oversizedDoHHandler streams `bodyBytes` bytes of zeros with the given
+// blockingBodyHandler writes exactly nbytes of body with the given status,
-// HTTP status. The atomic counter records bytes the handler actually
+// flushes them, then blocks until release is closed WITHOUT ever returning.
-// wrote, so tests can confirm the client tore down the stream before
+// Because the handler does not return, the response stream is never terminated
-// consuming the whole attacker-controlled body.
+// (no EOF/FIN). A client that stops after a bounded prefix therefore completes,
-func oversizedDoHHandler(status int, bodyBytes int64, written *atomic.Int64) http.HandlerFunc {
+// while a client that reads to EOF blocks. Tests set nbytes to the exact read
+// cap so the client consumes the whole written body (no half-written frame is
+// left blocking on flow control) yet still never sees EOF.
+func blockingBodyHandler(status, nbytes int, release <-chan struct{}) http.HandlerFunc {
 	return func(w http.ResponseWriter, r *http.Request) {
 		w.Header().Set("Content-Type", headerApplicationDNS)
 		w.WriteHeader(status)
-		chunk := make([]byte, 64*1024)
+		if _, err := w.Write(make([]byte, nbytes)); err != nil {
-		var sent int64
+			return
-		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()
-			}
 		}
+		if f, ok := w.(http.Flusher); ok {
+			f.Flush()
+		}
+		<-release
+	}
+}
+
+// requireBoundedResolve asserts that r.Resolve returns the expected size/status
+// error while the server is still withholding EOF (the handler is blocked in
+// blockingBodyHandler). Returning under those conditions proves ctrld read only
+// a bounded prefix of the body: a resolver that instead read to EOF would block
+// on the withheld stream and trip the deadline. This is the deterministic
+// regression guard for the issue-312 OOM protections, replacing the earlier
+// flaky server-side byte counter (issue-561).
+func requireBoundedResolve(t *testing.T, r Resolver, msg *dns.Msg, wantErrSubstr string) {
+	t.Helper()
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	type result struct {
+		answer *dns.Msg
+		err    error
+	}
+	done := make(chan result, 1)
+	go func() {
+		answer, err := r.Resolve(ctx, msg)
+		done <- result{answer, err}
+	}()
+
+	select {
+	case res := <-done:
+		if res.err == nil {
+			t.Fatalf("Resolve unexpectedly succeeded; answer=%v", res.answer)
+		}
+		if !strings.Contains(res.err.Error(), wantErrSubstr) {
+			t.Fatalf("error %q does not contain %q", res.err, wantErrSubstr)
+		}
+		if res.answer != nil {
+			t.Fatalf("Resolve returned non-nil answer alongside error: %v", res.answer)
+		}
+	case <-time.After(5 * time.Second):
+		t.Fatal("Resolve did not return while the server withheld EOF: the body is being read to EOF instead of a bounded prefix (issue-312 OOM protection missing)")
 	}
 }
 
@@ -348,9 +376,12 @@ func doh3UpstreamForAddr(t *testing.T, addr string, cert *x509.Certificate) *Ups
 // 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)
+	// Write exactly the LimitReader cap, then withhold EOF. ctrld's bounded
-	var written atomic.Int64
+	// read (io.LimitReader of dohMaxResponseSize+1) returns after this prefix;
-	srv := httptest.NewUnstartedServer(oversizedDoHHandler(http.StatusOK, oversized, &written))
+	// an unbounded read would block on the missing EOF and trip the deadline.
+	release := make(chan struct{})
+	defer close(release)
+	srv := httptest.NewUnstartedServer(blockingBodyHandler(http.StatusOK, dohMaxResponseSize+1, release))
 	testCert := generateTestCertificate(t)
 	srv.TLS = &tls.Config{
 		Certificates: []tls.Certificate{testCert.tlsCert},
@@ -370,31 +401,19 @@ func TestDoHResolve_OversizedBody_Rejected(t *testing.T) {
 	msg.SetQuestion("example.com.", dns.TypeA)
 	msg.RecursionDesired = true
 
-	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	requireBoundedResolve(t, r, msg, "maximum DNS message size")
-	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
+	// Same synchronization as the oversized-body test, but at the error-body
-	var written atomic.Int64
+	// cap: the non-200 path reads through an io.LimitReader of
-	srv := httptest.NewUnstartedServer(oversizedDoHHandler(http.StatusBadGateway, huge, &written))
+	// dohMaxErrorBodySize, so it must return after this prefix without EOF.
+	release := make(chan struct{})
+	defer close(release)
+	srv := httptest.NewUnstartedServer(blockingBodyHandler(http.StatusBadGateway, dohMaxErrorBodySize, release))
 	testCert := generateTestCertificate(t)
 	srv.TLS = &tls.Config{
 		Certificates: []tls.Certificate{testCert.tlsCert},
@@ -414,36 +433,22 @@ func TestDoHResolve_NonOKStatus_BoundedErrorBody(t *testing.T) {
 	msg.SetQuestion("example.com.", dns.TypeA)
 	msg.RecursionDesired = true
 
-	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	requireBoundedResolve(t, r, msg, "status: 502")
-	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
+	release := make(chan struct{})
+	defer close(release)
 	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),
+		Handler: blockingBodyHandler(http.StatusOK, dohMaxResponseSize+1, release),
 		TLSConfig: &tls.Config{
 			Certificates: []tls.Certificate{testCert.tlsCert},
 			NextProtos:   []string{"h3"},
@@ -471,17 +476,5 @@ func TestDoHResolve_OversizedBody_DoH3(t *testing.T) {
 	msg.SetQuestion("example.com.", dns.TypeA)
 	msg.RecursionDesired = true
 
-	ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
+	requireBoundedResolve(t, r, msg, "maximum DNS message size")
-	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

@@ -242,7 +242,15 @@ func (p *doqConnPool) doResolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, er
 	if err := answer.Unpack(buf[2 : 2+respLen]); err != nil {
 		return nil, err
 	}
-	answer.SetReply(msg)
+	// RFC 9250 section 4.2.1 requires the DNS Message ID to be 0 on the wire,
+	// so restore the downstream transaction ID for the client. Do NOT use
+	// SetReply here: it rewrites the RCODE to NOERROR and overwrites the
+	// Question with the request's, which would mask upstream failures from the
+	// failover logic (a SERVFAIL would look like success) and let a
+	// wrong-question answer pass validation and poison the cache. Preserve the
+	// upstream RCODE, Question, and answer sections untouched so the proxy can
+	// evaluate them. See github.com/Control-D-Inc/ctrld/issues/322.
+	answer.Id = msg.Id
 	return answer, nil
 }
 

doq_test.go

@@ -714,3 +714,105 @@ func TestDoQResolve_OversizedResponse_Rejected(t *testing.T) {
 		t.Fatalf("Resolve returned non-nil answer alongside error: %v", answer)
 	}
 }
+
+// frameDoQResponse packs msg and prepends the RFC 9250 2-octet length prefix,
+// producing the exact bytes a DoQ server writes on the wire.
+func frameDoQResponse(t *testing.T, msg *dns.Msg) []byte {
+	t.Helper()
+	b, err := msg.Pack()
+	if err != nil {
+		t.Fatalf("pack response: %v", err)
+	}
+	n := uint16(len(b))
+	return append([]byte{byte(n >> 8), byte(n & 0xFF)}, b...)
+}
+
+// TestDoQResolve_PreservesRcode locks in the fix for
+// github.com/Control-D-Inc/ctrld/issues/322: the DoQ resolver must not rewrite
+// an upstream response with SetReply, which would clobber a SERVFAIL into
+// NOERROR and hide the failure from the proxy's failover logic. The upstream
+// RCODE must survive; only the transaction ID is restored for the client.
+func TestDoQResolve_PreservesRcode(t *testing.T) {
+	t.Parallel()
+
+	// RFC 9250 puts the DNS Message ID at 0 on the wire.
+	resp := new(dns.Msg)
+	resp.SetQuestion("example.com.", dns.TypeA)
+	resp.Response = true
+	resp.Id = 0
+	resp.Rcode = dns.RcodeServerFailure
+
+	server := newMalformedDoQServer(t, frameDoQResponse(t, resp))
+	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 failed: %v", err)
+	}
+	if answer.Rcode != dns.RcodeServerFailure {
+		t.Fatalf("upstream SERVFAIL was rewritten to %s; failover would be bypassed",
+			dns.RcodeToString[answer.Rcode])
+	}
+	if answer.Id != msg.Id {
+		t.Fatalf("transaction ID not restored: got %d, want %d", answer.Id, msg.Id)
+	}
+}
+
+// TestDoQResolve_PreservesWrongQuestion locks in the fix for
+// github.com/Control-D-Inc/ctrld/issues/322: when an upstream answers a
+// different name than asked, the resolver must preserve the upstream's
+// question rather than rewriting it to the request's question (as SetReply
+// did). Rewriting would hide the mismatch and let wrong-domain records poison
+// the shared cache.
+func TestDoQResolve_PreservesWrongQuestion(t *testing.T) {
+	t.Parallel()
+
+	resp := new(dns.Msg)
+	resp.SetQuestion("attacker.example.", dns.TypeA)
+	resp.Response = true
+	resp.Id = 0
+	resp.Answer = append(resp.Answer, &dns.A{
+		Hdr: dns.RR_Header{
+			Name:   "attacker.example.",
+			Rrtype: dns.TypeA,
+			Class:  dns.ClassINET,
+			Ttl:    300,
+		},
+		A: net.ParseIP("192.0.2.1"),
+	})
+
+	server := newMalformedDoQServer(t, frameDoQResponse(t, resp))
+	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("victim.example.", dns.TypeA)
+	msg.RecursionDesired = true
+
+	answer, err := pool.Resolve(ctx, msg)
+	if err != nil {
+		t.Fatalf("Resolve failed: %v", err)
+	}
+	if len(answer.Question) == 0 || !strings.EqualFold(answer.Question[0].Name, "attacker.example.") {
+		t.Fatalf("upstream question was rewritten; got %v, want the upstream's attacker.example.",
+			answer.Question)
+	}
+	if answer.Id != msg.Id {
+		t.Fatalf("transaction ID not restored: got %d, want %d", answer.Id, msg.Id)
+	}
+}

go.mod

@@ -37,7 +37,7 @@ require (
 	github.com/stretchr/testify v1.11.1
 	github.com/vishvananda/netlink v1.3.1
 	golang.org/x/net v0.56.0
-	golang.org/x/sync v0.21.0
+	golang.org/x/sync v0.22.0
 	golang.org/x/sys v0.46.0
 	golang.zx2c4.com/wireguard/windows v0.5.3
 	tailscale.com v1.74.0
@@ -94,9 +94,9 @@ require (
 	go4.org/netipx v0.0.0-20231129151722-fdeea329fbba // indirect
 	golang.org/x/crypto v0.53.0 // indirect
 	golang.org/x/exp v0.0.0-20240119083558-1b970713d09a // indirect
-	golang.org/x/mod v0.36.0 // indirect
+	golang.org/x/mod v0.37.0 // indirect
-	golang.org/x/text v0.38.0 // indirect
+	golang.org/x/text v0.40.0 // indirect
-	golang.org/x/tools v0.45.0 // indirect
+	golang.org/x/tools v0.47.0 // 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

@@ -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 v0.36.0 h1:JJjpVx6myfUsUdAzZuOSTTmRE0PfZeNWzzvKrP7amb4=
+golang.org/x/mod v0.37.0 h1:vF1DjpVEshcIqoEaauuHebaLk1O1forxjxBaVn884JQ=
-golang.org/x/mod v0.36.0/go.mod h1:moc6ELqsWcOw5Ef3xVprK5ul/MvtVvkIXLziUOICjUQ=
+golang.org/x/mod v0.37.0/go.mod h1:m8S8VeM9r4dzDwjrKO0a1sZP3YjeMamRRlD+fmR2Q/0=
 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=
@@ -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 v0.21.0 h1:HLII4xRRTtCRkxYp4HNFF0Js/Og6q2i++KXbg0gHCwM=
+golang.org/x/sync v0.22.0 h1:SZjpbeLmrCk4xhRSZFNZW5gFUeCeFgjekvI/+gfScek=
-golang.org/x/sync v0.21.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
+golang.org/x/sync v0.22.0/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=
@@ -504,8 +504,8 @@ 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 v0.38.0 h1:sXmwo9DwP3OK9EZ7PqAdaooSGozfl/3a6/xJcbzPRhE=
+golang.org/x/text v0.40.0 h1:Ub2Z6/xjgF1WrYQz2nuITOEegKFtiIy+rieRJ5lHZKs=
-golang.org/x/text v0.38.0/go.mod h1:YXZt3QhHUKYT53r2lLKFIVi6Ao1jdzrTR/KQ09qyxF4=
+golang.org/x/text v0.40.0/go.mod h1:hpnzDAfGV753zIKo+wk3u1bVKCGPbrnF7+7LBF/UHVY=
 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=
@@ -556,8 +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 v0.45.0 h1:18qN3FAooORvApf5XjCXgsuayZOEtXf6JK18I3+ONa8=
+golang.org/x/tools v0.47.0 h1:7Kn5x/d1svx/PzryTsqeoZN4TZwqeH5pGWjefhLi/1Q=
-golang.org/x/tools v0.45.0/go.mod h1:LuUGqqaXcXMEFEruIVJVm5mgDD8vww/z/SR1gQ4uE/0=
+golang.org/x/tools v0.47.0/go.mod h1:dFHnyTvFWY212G+h7ZY4Vsp/K3U4/7W9TyVaAul8uCA=
 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/dnscache/cache.go

@@ -1,6 +1,8 @@
 package dnscache
 
 import (
+	"fmt"
+	"net"
 	"strings"
 	"time"
 
@@ -16,11 +18,17 @@ type Cacher interface {
 }
 
 // Key is the caching key for DNS message.
+//
+// ECS partitions the cache by EDNS Client Subnet so an answer resolved for one
+// subnet is never served to a client in a different subnet. Answer records are
+// scoped to the network that generated them (RFC 7871 §7.3), so they must not
+// be shared across subnets even when the question is otherwise identical.
 type Key struct {
 	Qtype    uint16
 	Qclass   uint16
 	Name     string
 	Upstream string
+	ECS      string
 }
 
 type Value struct {
@@ -60,7 +68,58 @@ func NewLRUCache(size int) (*LRUCache, error) {
 // NewKey creates a new cache key for given DNS message.
 func NewKey(msg *dns.Msg, upstream string) Key {
 	q := msg.Question[0]
-	return Key{Qtype: q.Qtype, Qclass: q.Qclass, Name: normalizeQname(q.Name), Upstream: upstream}
+	return Key{Qtype: q.Qtype, Qclass: q.Qclass, Name: normalizeQname(q.Name), Upstream: upstream, ECS: CanonicalECS(msg)}
+}
+
+// CanonicalECS returns a canonical string form of the EDNS Client Subnet (ECS,
+// EDNS option 8) carried by msg, suitable for partitioning cache and
+// singleflight keys. A request with no ECS option returns "", so all ECS-less
+// queries share one partition and behave as before.
+//
+// A request that DOES carry an ECS option is never mapped to "", even at SOURCE
+// PREFIX-LENGTH 0: the /0 query is forwarded with an ECS option, may draw
+// different upstream data than an ECS-less query, and its answer (with the
+// echoed option) must not be served to a client that sent no ECS — RFC 7871
+// §7.3.1 requires /0-cached data to remain distinguishable. The family is part
+// of the token, so an IPv4 /0 and an IPv6 /0 stay distinct too.
+//
+// The address is masked to its source prefix length so only the significant
+// subnet bits contribute to the key: two clients in the same subnet share a
+// partition, while different subnets (or address families) never do. The
+// response-only SCOPE PREFIX-LENGTH is deliberately excluded — it is not part of
+// what the client asked for.
+func CanonicalECS(msg *dns.Msg) string {
+	opt := msg.IsEdns0()
+	if opt == nil {
+		return ""
+	}
+	for _, o := range opt.Option {
+		e, ok := o.(*dns.EDNS0_SUBNET)
+		if !ok {
+			continue
+		}
+		bits := int(e.SourceNetmask)
+		total := 128
+		zero := net.IPv6zero
+		if e.Family == 1 {
+			total = 32
+			zero = net.IPv4zero
+		}
+		addr := e.Address
+		if len(addr) == 0 {
+			// A /0 request commonly carries an empty address; normalize it to
+			// the family zero so its token is stable regardless of encoding.
+			addr = zero
+		}
+		masked := addr
+		if bits <= total {
+			if m := addr.Mask(net.CIDRMask(bits, total)); m != nil {
+				masked = m
+			}
+		}
+		return fmt.Sprintf("%d/%d/%s", e.Family, e.SourceNetmask, masked.String())
+	}
+	return ""
 }
 
 // NewValue creates a new cache value for given DNS message.

internal/dnscache/cache_test.go

@@ -0,0 +1,186 @@
+package dnscache
+
+import (
+	"net"
+	"testing"
+	"time"
+
+	"github.com/miekg/dns"
+)
+
+// msgWithECS builds an A query for name carrying an EDNS Client Subnet option, or none
+// when family == 0.
+func msgWithECS(name string, family uint16, prefix uint8, addr string) *dns.Msg {
+	m := new(dns.Msg)
+	m.SetQuestion(dns.Fqdn(name), dns.TypeA)
+	if family == 0 {
+		return m
+	}
+	m.SetEdns0(4096, true)
+	m.IsEdns0().Option = append(m.IsEdns0().Option, &dns.EDNS0_SUBNET{
+		Code:          dns.EDNS0SUBNET,
+		Family:        family,
+		SourceNetmask: prefix,
+		Address:       net.ParseIP(addr),
+	})
+	return m
+}
+
+// answerWithA builds a cached answer holding a single A record with the given address.
+func answerWithA(name, a string) *dns.Msg {
+	m := new(dns.Msg)
+	m.SetQuestion(dns.Fqdn(name), dns.TypeA)
+	rr, err := dns.NewRR(dns.Fqdn(name) + " 300 IN A " + a)
+	if err != nil {
+		panic(err)
+	}
+	m.Answer = []dns.RR{rr}
+	return m
+}
+
+func firstA(msg *dns.Msg) string {
+	for _, rr := range msg.Answer {
+		if a, ok := rr.(*dns.A); ok {
+			return a.A.String()
+		}
+	}
+	return ""
+}
+
+// TestCanonicalECS covers the key-partitioning helper: only a request with no ECS option
+// collapses to the shared empty partition, while a carried /0 keeps its own family-scoped
+// token (distinct from no-ECS, per RFC 7871 §7.3.1); host bits below the source prefix do
+// not fragment the key, and different subnets / families produce different keys.
+func TestCanonicalECS(t *testing.T) {
+	tests := []struct {
+		name string
+		msg  *dns.Msg
+		want string
+	}{
+		{"no ecs", msgWithECS("controld.com", 0, 0, ""), ""},
+		// A carried ECS option is never "" (RFC 7871 §7.3.1), and IPv4 /0 vs
+		// IPv6 /0 stay distinct; the address encoding must not change the token.
+		{"ipv4 /0", msgWithECS("controld.com", 1, 0, "0.0.0.0"), "1/0/0.0.0.0"},
+		{"ipv4 /0 empty addr", msgWithECS("controld.com", 1, 0, ""), "1/0/0.0.0.0"},
+		{"ipv6 /0", msgWithECS("controld.com", 2, 0, "::"), "2/0/::"},
+		{"ipv6 /0 empty addr", msgWithECS("controld.com", 2, 0, ""), "2/0/::"},
+		{"ipv4 /24", msgWithECS("controld.com", 1, 24, "203.0.113.0"), "1/24/203.0.113.0"},
+		{"ipv4 host bits masked", msgWithECS("controld.com", 1, 24, "203.0.113.7"), "1/24/203.0.113.0"},
+		{"ipv6 /64", msgWithECS("controld.com", 2, 64, "2001:db8:1::"), "2/64/2001:db8:1::"},
+		{"ipv6 host bits masked", msgWithECS("controld.com", 2, 64, "2001:db8:1::dead:beef"), "2/64/2001:db8:1::"},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := CanonicalECS(tt.msg); got != tt.want {
+				t.Fatalf("CanonicalECS = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+// TestNewKey_ECSPartition verifies the cache key distinguishes subnets while collapsing
+// same-subnet requests, so the LRU cache cannot serve one subnet's records to another.
+func TestNewKey_ECSPartition(t *testing.T) {
+	const up = "https://dns.example/dns-query"
+	subnetA := NewKey(msgWithECS("controld.com", 2, 64, "2001:db8:1::"), up)
+	subnetB := NewKey(msgWithECS("controld.com", 2, 64, "2001:db8:2::"), up)
+	subnetAHost := NewKey(msgWithECS("controld.com", 2, 64, "2001:db8:1::5"), up)
+	ipv4 := NewKey(msgWithECS("controld.com", 1, 24, "203.0.113.0"), up)
+	noECS := NewKey(msgWithECS("controld.com", 0, 0, ""), up)
+
+	if subnetA == subnetB {
+		t.Fatal("different subnets must not share a cache key")
+	}
+	if subnetA != subnetAHost {
+		t.Fatal("same subnet (different host bits) must share a cache key")
+	}
+	if subnetA == ipv4 || subnetA == noECS || ipv4 == noECS {
+		t.Fatal("different families / no-ECS must not collide")
+	}
+}
+
+// TestLRUCache_ECSZeroPrefixDistinctFromNoECS is the regression test for the /0-vs-no-ECS
+// collision (RFC 7871 §7.3.1). A query carrying an ECS /0 option is forwarded WITH ECS and
+// may draw different upstream data, so its cached answer must never be served to a client
+// that sent no ECS at all, nor may IPv4 /0 and IPv6 /0 cross-serve each other.
+func TestLRUCache_ECSZeroPrefixDistinctFromNoECS(t *testing.T) {
+	c, err := NewLRUCache(16)
+	if err != nil {
+		t.Fatalf("NewLRUCache: %v", err)
+	}
+	const up = "https://dns.example/dns-query"
+	expire := time.Now().Add(time.Minute)
+
+	noECS := msgWithECS("controld.com", 0, 0, "")
+	zeroV4 := msgWithECS("controld.com", 1, 0, "0.0.0.0")
+	zeroV6 := msgWithECS("controld.com", 2, 0, "::")
+
+	// Only the IPv4 /0 query's answer is cached.
+	c.Add(NewKey(zeroV4, up), NewValue(answerWithA("controld.com", "192.0.2.1"), expire))
+
+	// A no-ECS client must NOT receive the ECS /0 cached answer.
+	if got := c.Get(NewKey(noECS, up)); got != nil {
+		t.Fatalf("no-ECS client received the ECS /0 cached record %q", firstA(got.Msg))
+	}
+	// An IPv6 /0 client must NOT receive the IPv4 /0 answer.
+	if got := c.Get(NewKey(zeroV6, up)); got != nil {
+		t.Fatalf("IPv6 /0 client received the IPv4 /0 cached record %q", firstA(got.Msg))
+	}
+	// The IPv4 /0 client still hits its own entry.
+	if got := c.Get(NewKey(zeroV4, up)); got == nil || firstA(got.Msg) != "192.0.2.1" {
+		t.Fatalf("IPv4 /0 lost its own cached record: %v", got)
+	}
+
+	// The no-ECS partition is independent and does not corrupt the /0 entry.
+	c.Add(NewKey(noECS, up), NewValue(answerWithA("controld.com", "198.51.100.1"), expire))
+	if got := c.Get(NewKey(noECS, up)); got == nil || firstA(got.Msg) != "198.51.100.1" {
+		t.Fatalf("no-ECS partition wrong record: %v", got)
+	}
+	if got := c.Get(NewKey(zeroV4, up)); got == nil || firstA(got.Msg) != "192.0.2.1" {
+		t.Fatalf("IPv4 /0 record corrupted by no-ECS insert: %v", got)
+	}
+}
+
+// TestLRUCache_ECSNoCrossSubnetServe is the real cache-path regression test for #564:
+// an entry populated for subnet A must never be returned to a client in subnet B, even
+// though the question (name/type/class/upstream) is identical. The two subnets carry
+// different A records; the second client must get its own record or a miss, never A's.
+func TestLRUCache_ECSNoCrossSubnetServe(t *testing.T) {
+	c, err := NewLRUCache(16)
+	if err != nil {
+		t.Fatalf("NewLRUCache: %v", err)
+	}
+	const up = "https://dns.example/dns-query"
+	expire := time.Now().Add(time.Minute)
+
+	reqA := msgWithECS("controld.com", 2, 64, "2001:db8:1::")
+	reqB := msgWithECS("controld.com", 2, 64, "2001:db8:2::")
+
+	// Only subnet A's answer (A record 192.0.2.1) is cached.
+	c.Add(NewKey(reqA, up), NewValue(answerWithA("controld.com", "192.0.2.1"), expire))
+
+	// A client in subnet B must NOT hit subnet A's entry.
+	if got := c.Get(NewKey(reqB, up)); got != nil {
+		t.Fatalf("subnet B received subnet A's cached record %q; cache is not ECS-partitioned", firstA(got.Msg))
+	}
+
+	// Subnet A still hits its own entry.
+	if got := c.Get(NewKey(reqA, up)); got == nil || firstA(got.Msg) != "192.0.2.1" {
+		t.Fatalf("subnet A lost its own cached record: %+v", got)
+	}
+
+	// Now cache subnet B's distinct answer and confirm the two never cross.
+	c.Add(NewKey(reqB, up), NewValue(answerWithA("controld.com", "198.51.100.1"), expire))
+	if got := c.Get(NewKey(reqB, up)); got == nil || firstA(got.Msg) != "198.51.100.1" {
+		t.Fatalf("subnet B got the wrong record: %v", got)
+	}
+	if got := c.Get(NewKey(reqA, up)); got == nil || firstA(got.Msg) != "192.0.2.1" {
+		t.Fatalf("subnet A record corrupted by subnet B insert: %v", got)
+	}
+
+	// A second host within subnet A shares the partition (cache hit with A's record).
+	reqAHost := msgWithECS("controld.com", 2, 64, "2001:db8:1::9")
+	if got := c.Get(NewKey(reqAHost, up)); got == nil || firstA(got.Msg) != "192.0.2.1" {
+		t.Fatalf("same-subnet host missed the shared cache entry: %v", got)
+	}
+}

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

resolver.go

@@ -19,6 +19,8 @@ import (
 	"golang.org/x/sync/singleflight"
 	"tailscale.com/net/netmon"
 	"tailscale.com/net/tsaddr"
+
+	"github.com/Control-D-Inc/ctrld/internal/dnscache"
 )
 
 const (
@@ -378,8 +380,10 @@ func (o *osResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error
 	domain := strings.TrimSuffix(msg.Question[0].Name, ".")
 	qtype := msg.Question[0].Qtype
 
-	// Unique key for the singleflight group.
+	// Unique key for the singleflight group. The EDNS Client Subnet is part of
-	key := fmt.Sprintf("%s:%d:", domain, qtype)
+	// the key so subnet-specific answers are neither coalesced nor hot-cached
+	// across different subnets (RFC 7871 §7.3).
+	key := fmt.Sprintf("%s:%d:%s", domain, qtype, dnscache.CanonicalECS(msg))
 
 	// Checking the cache first.
 	if val, ok := o.cache.Load(key); ok {

resolver_test.go

@@ -282,6 +282,93 @@ func Test_Edns0_CacheReply(t *testing.T) {
 	}
 }
 
+// ecsAnswerHandler returns a distinct A record per EDNS Client Subnet, so a test can
+// prove one subnet never receives another subnet's cached record. It counts upstream
+// calls to confirm the hot cache/singleflight is partitioned by ECS rather than shared.
+func ecsAnswerHandler(call *atomic.Int64) dns.HandlerFunc {
+	return func(w dns.ResponseWriter, msg *dns.Msg) {
+		call.Add(1)
+		a := "203.0.113.1" // no/other subnet
+		if opt := msg.IsEdns0(); opt != nil {
+			for _, o := range opt.Option {
+				if e, ok := o.(*dns.EDNS0_SUBNET); ok {
+					switch {
+					case e.Address.Equal(net.ParseIP("2001:db8:1::")):
+						a = "192.0.2.1"
+					case e.Address.Equal(net.ParseIP("2001:db8:2::")):
+						a = "198.51.100.1"
+					}
+				}
+			}
+		}
+		m := new(dns.Msg)
+		m.SetReply(msg)
+		rr, _ := dns.NewRR(msg.Question[0].Name + " 300 IN A " + a)
+		m.Answer = []dns.RR{rr}
+		w.WriteMsg(m)
+	}
+}
+
+// Test_osResolver_HotCache_ECSPartition is the real cache-path regression test for #564 on
+// the osResolver hot cache / singleflight path: the upstream returns a different A record
+// per subnet, and a client in subnet B must never be served subnet A's hot-cached record.
+func Test_osResolver_HotCache_ECSPartition(t *testing.T) {
+	lanPC, err := net.ListenPacket("udp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatalf("failed to listen on LAN address: %v", err)
+	}
+	call := &atomic.Int64{}
+	lanServer, lanAddr, err := runLocalPacketConnTestServer(t, lanPC, ecsAnswerHandler(call))
+	if err != nil {
+		t.Fatalf("failed to run LAN test server: %v", err)
+	}
+	defer lanServer.Shutdown()
+
+	or := newResolverWithNameserver([]string{lanAddr})
+	query := func(subnet string) string {
+		m := new(dns.Msg)
+		m.SetQuestion(dns.Fqdn("controld.com"), dns.TypeA)
+		m.RecursionDesired = true
+		m.SetEdns0(4096, true)
+		m.IsEdns0().Option = append(m.IsEdns0().Option, &dns.EDNS0_SUBNET{
+			Code:          dns.EDNS0SUBNET,
+			Family:        2,
+			SourceNetmask: 64,
+			Address:       net.ParseIP(subnet),
+		})
+		answer, err := or.Resolve(context.Background(), m)
+		if err != nil {
+			t.Fatal(err)
+		}
+		for _, rr := range answer.Answer {
+			if a, ok := rr.(*dns.A); ok {
+				return a.A.String()
+			}
+		}
+		return ""
+	}
+
+	// Subnet A populates the hot cache; a repeat hits it (upstream called once).
+	if got := query("2001:db8:1::"); got != "192.0.2.1" {
+		t.Fatalf("subnet A: got %q, want 192.0.2.1", got)
+	}
+	if got := query("2001:db8:1::"); got != "192.0.2.1" {
+		t.Fatalf("subnet A repeat: got %q, want 192.0.2.1", got)
+	}
+	if call.Load() != 1 {
+		t.Fatalf("subnet A repeat did not hit the hot cache: %d upstream calls", call.Load())
+	}
+
+	// Subnet B must get ITS OWN record, not subnet A's hot-cached one, and this
+	// requires a fresh upstream call (the cache is partitioned, not shared).
+	if got := query("2001:db8:2::"); got != "198.51.100.1" {
+		t.Fatalf("subnet B was served the wrong record %q (want 198.51.100.1); hot cache is not ECS-partitioned", got)
+	}
+	if call.Load() != 2 {
+		t.Fatalf("subnet B unexpectedly served from subnet A's cache: %d upstream calls, want 2", call.Load())
+	}
+}
+
 // https://github.com/Control-D-Inc/ctrld/issues/255
 func Test_legacyResolverWithBigExtraSection(t *testing.T) {
 	lanPC, err := net.ListenPacket("udp", "127.0.0.1:0") // 127.0.0.1 is considered LAN (loopback)
@@ -383,6 +470,11 @@ func nonSuccessHandlerWithRcode(rcode int) dns.HandlerFunc {
 
 func countHandler(call *atomic.Int64) dns.HandlerFunc {
 	return func(w dns.ResponseWriter, msg *dns.Msg) {
+		// Count the call before writing the reply. The client returns as soon
+		// as it receives the response, so a caller that reads this counter right
+		// after Resolve returns would race an increment done after WriteMsg and
+		// could observe a stale zero.
+		call.Add(1)
 		m := new(dns.Msg)
 		m.SetRcode(msg, dns.RcodeSuccess)
 		if cookie := getEdns0Cookie(msg.IsEdns0()); cookie != nil {
@@ -395,7 +487,6 @@ func countHandler(call *atomic.Int64) dns.HandlerFunc {
 			m.IsEdns0().Option = append(m.IsEdns0().Option, cookieOption)
 		}
 		w.WriteMsg(m)
-		call.Add(1)
 	}
 }