pqkem: recover from persistent rekey failure by re-bootstrapping over signal

OnRekeyFailed now re-runs the KEM bootstrap over Signal (conn.RequestReoffer ->
handshaker.SendOffer) instead of only logging: a fresh signalling offer starts a new
exchange that overwrites the stalled PSK on both sides, resyncing after a persistent
data-path desync. Chosen over a responder-side awaitingAck revert (which fights the
confirm-less ack timing) and a full tunnel teardown (heavier). The tunnel stays up on
the previous PSK meanwhile since Signal is independent of the broken data path.

.github/workflows/test-infrastructure-files.yml

@@ -249,35 +249,78 @@ jobs:
           docker compose exec management ls -l /var/lib/netbird/ | grep -i GeoLite2-City_[0-9]*.mmdb
           docker compose exec management ls -l /var/lib/netbird/ | grep -i geonames_[0-9]*.db
 
-  test-legacy-getting-started-scripts:
+  test-getting-started-script:
     runs-on: ubuntu-latest
     steps:
+      - name: Install jq
+        run: sudo apt-get install -y jq
+
       - name: Checkout code
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
         with:
           persist-credentials: false
 
-      - name: Verify Dex retirement notice
-        run: |
-          if infrastructure_files/getting-started-with-dex.sh >stdout.txt 2>stderr.txt; then
-            echo "Expected the retired Dex installer to fail"
-            exit 1
-          fi
-          test ! -s stdout.txt
-          grep -Fq "Dex support is not deprecated." stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/local" stderr.txt
-          grep -Fq "removed in NetBird v0.80" stderr.txt
+      - name: run script with Zitadel PostgreSQL
+        run: NETBIRD_DOMAIN=use-ip bash -x infrastructure_files/getting-started-with-zitadel.sh
 
-      - name: Verify Zitadel retirement notice
+      - name: test Caddy file gen postgres
+        run: test -f Caddyfile
+
+      - name: test docker-compose file gen postgres
+        run: test -f docker-compose.yml
+
+      - name: test management.json file gen postgres
+        run: test -f management.json
+
+      - name: test turnserver.conf file gen postgres
         run: |
-          if bash infrastructure_files/getting-started-with-zitadel.sh >stdout.txt 2>stderr.txt; then
-            echo "Expected the retired Zitadel installer to fail"
-            exit 1
-          fi
-          test ! -s stdout.txt
-          grep -Fq "Zitadel support and existing Zitadel deployments are not deprecated." stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/zitadel" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-guide" stderr.txt
-          grep -Fq "removed in NetBird v0.80" stderr.txt
+          set -x
+          test -f turnserver.conf
+          grep external-ip turnserver.conf
+
+      - name: test zitadel.env file gen postgres
+        run: test -f zitadel.env
+
+      - name: test dashboard.env file gen postgres
+        run: test -f dashboard.env
+
+      - name: test relay.env file gen postgres
+        run: test -f relay.env
+
+      - name: test zdb.env file gen postgres
+        run: test -f zdb.env
+
+      - name: Postgres run cleanup
+        run: |
+          docker compose down --volumes --rmi all
+          rm -rf docker-compose.yml Caddyfile zitadel.env dashboard.env machinekey/zitadel-admin-sa.token turnserver.conf management.json zdb.env
+
+      - name: run script with Zitadel CockroachDB
+        run: bash -x infrastructure_files/getting-started-with-zitadel.sh
+        env:
+          NETBIRD_DOMAIN: use-ip
+          ZITADEL_DATABASE: cockroach
+
+      - name: test Caddy file gen CockroachDB
+        run: test -f Caddyfile
+
+      - name: test docker-compose file gen CockroachDB
+        run: test -f docker-compose.yml
+
+      - name: test management.json file gen CockroachDB
+        run: test -f management.json
+
+      - name: test turnserver.conf file gen CockroachDB
+        run: |
+          set -x
+          test -f turnserver.conf
+          grep external-ip turnserver.conf
+
+      - name: test zitadel.env file gen CockroachDB
+        run: test -f zitadel.env
+
+      - name: test dashboard.env file gen CockroachDB
+        run: test -f dashboard.env
+
+      - name: test relay.env file gen CockroachDB
+        run: test -f relay.env

.goreleaser_ui.yaml

@@ -24,8 +24,6 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
   - id: netbird-ui-windows-amd64
     dir: client/ui
@@ -41,8 +39,6 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
   - id: netbird-ui-windows-arm64
     dir: client/ui
@@ -59,8 +55,6 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
 archives:
   - id: linux-arch

.goreleaser_ui_darwin.yaml

@@ -29,8 +29,6 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
 universal_binaries:
   - id: netbird-ui-darwin

CONTRIBUTING.md

@@ -234,22 +234,12 @@ cd client/ui
 task dev
 ```
 
-Pass daemon flags after `--`, pointing the UI at the socket the daemon serves:
+Pass daemon flags after `--`:
 
 ```
-task dev -- --daemon-addr=unix:///var/run/netbird.sock   # Linux, macOS
-task dev -- --daemon-addr=npipe://netbird                # Windows
+task dev -- --daemon-addr=tcp://127.0.0.1:41731
 ```
 
-On Windows the daemon serves a named pipe (`npipe://netbird`). Which path that
-ends up being depends on what the daemon may create: as a service or elevated it
-serves `\\.\pipe\ProtectedPrefix\Administrators\netbird`, which no unprivileged
-process can take from it, and otherwise it falls back to `\\.\pipe\netbird`.
-Clients try both and check who owns the pipe before using the plain one. Avoid
-`tcp://127.0.0.1:41731`: loopback TCP carries no caller identity, so the daemon
-refuses the operations that require an administrator and you will not exercise
-those paths.
-
 Production build (frontend assets embedded into the binary, output in `client/ui/bin/`):
 
 ```

SECURITY.md

@@ -1,70 +1,12 @@
 # Security Policy
 
-NetBird's goal is to provide a secure network. The client runs as a privileged service on every machine it is installed on,
-so we take reports about it seriously and we publish what we fix.
+NetBird's goal is to provide a secure network. If you find a vulnerability or bug, please report it by opening an issue [here](https://github.com/netbirdio/netbird/issues/new?assignees=&labels=&template=bug-issue-report.md&title=) or by contacting us by email.
+
+There has yet to be an official bug bounty program for the NetBird project.
+
+## Supported Versions
+- We currently support only the latest version
 
 ## Reporting a Vulnerability
 
-**Please do not open a public issue for a security vulnerability.** Public issues are visible to everyone, including before
-a fix is available.
-
-Report security issues one of these two ways:
-
-- **GitHub private vulnerability reporting** — [open a private report](https://github.com/netbirdio/netbird/security/advisories/new)
-  on this repository. This is the preferred route: it keeps the discussion, the draft advisory, and the credit in one place.
-- **Email** — `security@netbird.io`.
-
-If the finding affects NetBird Cloud or our hosted infrastructure rather than the open-source code, email us rather than
-filing a repository report.
-
-### What to include
-
-A report is easier to act on when it contains:
-
-- The affected component (client, management, signal, relay, dashboard) and the version or commit you tested
-- The platform and configuration, where relevant — operating system, self-hosted or NetBird Cloud, container or host install
-- What an attacker needs before they can exploit it: network position, an account, local access, a specific privilege level
-- Steps to reproduce, and a proof of concept if you have one
-- The impact you believe it has
-
-Partial reports are still welcome. If you are unsure whether something is a security issue, send it to `security@netbird.io`
-and let us make that call.
-
-## What to expect from us
-
-- **We acknowledge your report** and tell you whether we can reproduce it.
-- **We work with you on severity and scope.** If we assess it differently than you do, we will explain why rather than
-  silently downgrade it.
-- **We fix and release**, then publish a [GitHub Security Advisory](https://github.com/netbirdio/netbird/security/advisories)
-  naming the affected version range and the patched version.
-- **We credit reporters who want to be credited.** Tell us the name or handle you would like used, or that you would rather
-  stay anonymous.
-- **We keep you in the loop** until the advisory is published.
-
-We ask that you give us a reasonable opportunity to ship a fix before disclosing the issue publicly, and that you avoid
-accessing, modifying, or exfiltrating data belonging to other people while testing. Testing against your own installation
-or your own account is always fine.
-
-## Supported Versions
-
-We support the latest release. Security fixes ship in the next version rather than as backports to older releases, so
-upgrading to the current release is how you get them.
-
-Release notifications are available by watching [releases](https://github.com/netbirdio/netbird/releases).
-
-## Published advisories
-
-Every vulnerability we fix is published as a GitHub Security Advisory on the
-[advisories page](https://github.com/netbirdio/netbird/security/advisories), including the affected version range, the
-patched version, and the reporter's credit. Advisories for the Go module are also distributed through the Go vulnerability
-database, so `govulncheck` will report them against your dependencies.
-
-## Bug bounty
-
-There is no official bug bounty program for the NetBird project. We credit reporters in advisories, and we are grateful for
-the work, but we cannot currently offer payment for reports.
-
-## Non-security bugs
-
-For bugs that are not security issues, please use the
-[issue tracker](https://github.com/netbirdio/netbird/discussions/new/choose).
+Please report security issues to `security@netbird.io`

client/android/client.go

@@ -7,7 +7,6 @@ import (
 	"fmt"
 	"os"
 	"slices"
-	"strings"
 	"sync"
 	"time"
 
@@ -76,24 +75,6 @@ type Client struct {
 	connectClient *internal.ConnectClient
 	config        *profilemanager.Config
 	cacheDir      string
-
-	stateChangeMu    sync.Mutex
-	stateChangeSubID string
-	eventSub         *peer.EventSubscription
-	// Closed to stop the watch goroutines from delivering buffered items to a
-	// listener that has been removed or replaced. See stopStateChangeWatchLocked.
-	stateChangeDone chan struct{}
-
-	// Latched "the server wants an interactive login": survives the engine
-	// restarts that replace the run loop's context state. See Client.Status.
-	// Guarded by loginRequiredMu together with loginCleared, which counts
-	// clears so a stale observation cannot re-latch over one.
-	loginRequiredMu sync.Mutex
-	loginRequired   bool
-	loginCleared    uint64
-
-	extendMu     sync.Mutex
-	extendCancel context.CancelFunc
 }
 
 func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cc *internal.ConnectClient) {
@@ -167,16 +148,11 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	if err != nil {
 		return err
 	}
+
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
 	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
 	c.setState(cfg, cacheDir, connectClient)
-	// This path runs the interactive SSO flow, so reaching here means the peer
-	// is authenticated again — release the latch Status() reports from. Clear
-	// only once the fresh connect client is installed: until then Status()
-	// still reads the previous run's context state, which holds the NeedsLogin
-	// that prompted this login, and would re-latch what was just cleared.
-	c.clearLoginRequired()
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
 
@@ -323,13 +299,6 @@ func (c *Client) SetInfoLogLevel() {
 // PeersList return with the list of the PeerInfos
 func (c *Client) PeersList() *PeerInfoArray {
 
-	// The recorder only caches transfer counters and handshake times; nothing
-	// refreshes them on its own, so without this they read as zero. The desktop
-	// daemon does the same before serving a full peer status.
-	if err := c.recorder.RefreshWireGuardStats(); err != nil {
-		log.Debugf("failed to refresh WireGuard stats: %v", err)
-	}
-
 	fullStatus := c.recorder.GetFullStatus()
 
 	peerInfos := make([]PeerInfo, len(fullStatus.Peers))
@@ -340,20 +309,6 @@ func (c *Client) PeersList() *PeerInfoArray {
 			FQDN:       p.FQDN,
 			ConnStatus: int(p.ConnStatus),
 			Routes:     PeerRoutes{routes: maps.Keys(p.GetRoutes())},
-
-			PubKey:                     p.PubKey,
-			Latency:                    formatDuration(p.Latency),
-			LatencyMs:                  p.Latency.Milliseconds(),
-			BytesRx:                    p.BytesRx,
-			BytesTx:                    p.BytesTx,
-			ConnStatusUpdate:           formatTime(p.ConnStatusUpdate),
-			Relayed:                    p.Relayed,
-			RosenpassEnabled:           p.RosenpassEnabled,
-			LastWireguardHandshake:     formatTime(p.LastWireguardHandshake),
-			LocalIceCandidateType:      p.LocalIceCandidateType,
-			RemoteIceCandidateType:     p.RemoteIceCandidateType,
-			LocalIceCandidateEndpoint:  p.LocalIceCandidateEndpoint,
-			RemoteIceCandidateEndpoint: p.RemoteIceCandidateEndpoint,
 		}
 		peerInfos[n] = pi
 	}
@@ -484,6 +439,10 @@ func (c *Client) RemoveConnectionListener() {
 	c.recorder.RemoveConnectionListener()
 }
 
+func (c *Client) toggleRoute(command routeCommand) error {
+	return command.toggleRoute()
+}
+
 func (c *Client) getRouteManager() (routemanager.Manager, error) {
 	client := c.getConnectClient()
 	if client == nil {
@@ -503,22 +462,22 @@ func (c *Client) getRouteManager() (routemanager.Manager, error) {
 	return manager, nil
 }
 
-func (c *Client) SelectRoute(id string) error {
+func (c *Client) SelectRoute(route string) error {
 	manager, err := c.getRouteManager()
 	if err != nil {
 		return err
 	}
 
-	return manager.SelectRoutes([]route.NetID{route.NetID(id)}, true)
+	return c.toggleRoute(selectRouteCommand{route: route, manager: manager})
 }
 
-func (c *Client) DeselectRoute(id string) error {
+func (c *Client) DeselectRoute(route string) error {
 	manager, err := c.getRouteManager()
 	if err != nil {
 		return err
 	}
 
-	return manager.DeselectRoutes([]route.NetID{route.NetID(id)})
+	return c.toggleRoute(deselectRouteCommand{route: route, manager: manager})
 }
 
 // getNetworkDomainsFromRoute extracts domains from a route and enriches each domain
@@ -553,28 +512,3 @@ func exportEnvList(list *EnvList) {
 		}
 	}
 }
-
-// formatDuration renders a duration for display, trimming the fractional part
-// to two digits so latencies read as "12.34ms" rather than "12.345678ms".
-func formatDuration(d time.Duration) string {
-	ds := d.String()
-	dotIndex := strings.Index(ds, ".")
-	if dotIndex == -1 {
-		return ds
-	}
-
-	endIndex := min(dotIndex+3, len(ds))
-
-	// Skip the remaining digits so only the unit suffix is appended back.
-	unitStart := endIndex
-	for unitStart < len(ds) && ds[unitStart] >= '0' && ds[unitStart] <= '9' {
-		unitStart++
-	}
-	return ds[:endIndex] + ds[unitStart:]
-}
-
-// formatTime renders a timestamp in UTC using a fixed layout. The zero time is
-// passed through as-is so the UI can recognise it and show "never" instead.
-func formatTime(t time.Time) string {
-	return t.UTC().Format("2006-01-02 15:04:05")
-}

client/android/peer_notifier.go

@@ -12,30 +12,12 @@ const (
 )
 
 // PeerInfo describe information about the peers. It designed for the UI usage
-//
-// The fields below ConnStatus back the peer detail screen. Durations and times
-// are pre-formatted into strings so the UI does not have to know Go's layouts;
-// Latency is additionally exposed as LatencyMs for colour coding.
 type PeerInfo struct {
 	IP         string
 	IPv6       string
 	FQDN       string
 	ConnStatus int
 	Routes     PeerRoutes
-
-	PubKey                     string
-	Latency                    string
-	LatencyMs                  int64
-	BytesRx                    int64
-	BytesTx                    int64
-	ConnStatusUpdate           string
-	Relayed                    bool
-	RosenpassEnabled           bool
-	LastWireguardHandshake     string
-	LocalIceCandidateType      string
-	RemoteIceCandidateType     string
-	LocalIceCandidateEndpoint  string
-	RemoteIceCandidateEndpoint string
 }
 
 func (p *PeerInfo) GetPeerRoutes() *PeerRoutes {

client/android/profile_manager.go

@@ -189,19 +189,6 @@ func (pm *ProfileManager) LogoutProfile(id string) error {
 	return nil
 }
 
-// RenameProfile changes a profile's display name. The profile ID, and therefore
-// its on-disk filename, is left untouched: only the "name" field of the config
-// is rewritten. This works for the default profile too, whose config lives in
-// netbird.cfg rather than under profiles/.
-func (pm *ProfileManager) RenameProfile(id string, newName string) error {
-	if err := pm.serviceMgr.RenameProfile(profilemanager.ID(id), androidUsername, newName); err != nil {
-		return fmt.Errorf("failed to rename profile: %w", err)
-	}
-
-	log.Infof("renamed profile %s to: %s", id, newName)
-	return nil
-}
-
 // RemoveProfile deletes a profile
 func (pm *ProfileManager) RemoveProfile(id string) error {
 	// Use ServiceManager (removes profile from profiles/ directory)

client/android/route_command.go

@@ -0,0 +1,70 @@
+//go:build android
+
+package android
+
+import (
+	"fmt"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/exp/maps"
+
+	"github.com/netbirdio/netbird/client/internal/routemanager"
+	"github.com/netbirdio/netbird/route"
+)
+
+func executeRouteToggle(id string, manager routemanager.Manager,
+	operationName string,
+	routeOperation func(routes []route.NetID, allRoutes []route.NetID) error) error {
+	netID := route.NetID(id)
+	routes := []route.NetID{netID}
+
+	routesMap := manager.GetClientRoutesWithNetID()
+	routes = route.ExpandV6ExitPairs(routes, routesMap)
+
+	log.Debugf("%s with ids: %v", operationName, routes)
+
+	if err := routeOperation(routes, maps.Keys(routesMap)); err != nil {
+		log.Debugf("error when %s: %s", operationName, err)
+		return fmt.Errorf("error %s: %w", operationName, err)
+	}
+
+	manager.TriggerSelection(manager.GetClientRoutes())
+
+	return nil
+}
+
+type routeCommand interface {
+	toggleRoute() error
+}
+
+type selectRouteCommand struct {
+	route   string
+	manager routemanager.Manager
+}
+
+func (s selectRouteCommand) toggleRoute() error {
+	routeSelector := s.manager.GetRouteSelector()
+	if routeSelector == nil {
+		return fmt.Errorf("no route selector available")
+	}
+
+	routeOperation := func(routes []route.NetID, allRoutes []route.NetID) error {
+		return routeSelector.SelectRoutes(routes, true, allRoutes)
+	}
+
+	return executeRouteToggle(s.route, s.manager, "selecting route", routeOperation)
+}
+
+type deselectRouteCommand struct {
+	route   string
+	manager routemanager.Manager
+}
+
+func (d deselectRouteCommand) toggleRoute() error {
+	routeSelector := d.manager.GetRouteSelector()
+	if routeSelector == nil {
+		return fmt.Errorf("no route selector available")
+	}
+
+	return executeRouteToggle(d.route, d.manager, "deselecting route", routeSelector.DeselectRoutes)
+}

client/android/session.go

@@ -1,309 +0,0 @@
-//go:build android
-
-package android
-
-import (
-	"context"
-	"fmt"
-
-	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/internal/auth"
-	"github.com/netbirdio/netbird/client/internal/auth/sessionwatch"
-	"github.com/netbirdio/netbird/client/internal/peer"
-	cProto "github.com/netbirdio/netbird/client/proto"
-)
-
-// StateChangeListener receives client state notifications.
-//
-// OnStateChanged is a payload-free wake-up whenever the state snapshot
-// changed: connection state, the run-loop status label (e.g. NeedsLogin) or
-// the session deadline. It mirrors the daemon's SubscribeStatus stream
-// trigger — on each signal the consumer pulls the fresh values via
-// Status() / SessionExpiresAtUnix().
-//
-// OnSessionExpiring forwards the engine's session-expiry warnings, fired at
-// sessionwatch.WarningLead before the deadline and again at FinalWarningLead
-// (finalWarning true). The second one is suppressed when the user dismissed
-// the first via DismissSessionWarning. The daemon turns the same events into
-// its tray notification.
-type StateChangeListener interface {
-	OnStateChanged()
-	OnSessionExpiring(expiresAtUnix int64, leadMinutes int64, finalWarning bool)
-}
-
-// Status returns the connect run-loop's status label — the same value the
-// desktop daemon serves in StatusResponse.Status. "NeedsLogin" means the
-// management server rejected the peer and an interactive login is required.
-//
-// The label is latched: the run loop keeps its status in a per-run context
-// state, which a restart replaces with a fresh Idle one, so an engine restart
-// (network change, always-on) would otherwise erase the fact that the peer
-// still needs to log in. Only a successful interactive login or extend clears
-// it — see clearLoginRequired.
-func (c *Client) Status() string {
-	latched, generation := c.loginRequiredState()
-	if latched {
-		return string(internal.StatusNeedsLogin)
-	}
-	cc := c.getConnectClient()
-	if cc == nil {
-		return string(internal.StatusIdle)
-	}
-	status := cc.Status()
-	if status == internal.StatusNeedsLogin {
-		c.latchLoginRequired(generation)
-	}
-	return string(status)
-}
-
-func (c *Client) loginRequiredState() (bool, uint64) {
-	c.loginRequiredMu.Lock()
-	defer c.loginRequiredMu.Unlock()
-	return c.loginRequired, c.loginCleared
-}
-
-// latchLoginRequired records a NeedsLogin observation, unless a clear landed
-// while the caller was reading the run loop's status: cc.Status() is read
-// outside the lock, so a login or extend completing in that window would
-// otherwise be undone by this stale observation, stranding the UI on
-// "login required" over a healthy session.
-func (c *Client) latchLoginRequired(observedGeneration uint64) {
-	c.loginRequiredMu.Lock()
-	defer c.loginRequiredMu.Unlock()
-	if c.loginCleared != observedGeneration {
-		return
-	}
-	c.loginRequired = true
-}
-
-// clearLoginRequired releases the latch after a successful interactive login
-// or session extend, and invalidates any observation already in flight.
-func (c *Client) clearLoginRequired() {
-	c.loginRequiredMu.Lock()
-	defer c.loginRequiredMu.Unlock()
-	c.loginRequired = false
-	c.loginCleared++
-}
-
-// SessionExpiresAtUnix returns the SSO session deadline as unix seconds, or 0
-// when no deadline is known (not SSO-registered, expiry disabled, or the
-// engine has not received one yet). A past value means the session expired.
-// Mirror of StatusResponse.sessionExpiresAt on the desktop daemon.
-func (c *Client) SessionExpiresAtUnix() int64 {
-	deadline := c.recorder.GetSessionExpiresAt()
-	if deadline.IsZero() {
-		return 0
-	}
-	return deadline.Unix()
-}
-
-// SetStateChangeListener registers the state notification listener.
-// Replaces any previously registered listener; remove it with
-// RemoveStateChangeListener.
-func (c *Client) SetStateChangeListener(listener StateChangeListener) {
-	c.stateChangeMu.Lock()
-	defer c.stateChangeMu.Unlock()
-	c.stopStateChangeWatchLocked()
-	if listener == nil {
-		return
-	}
-
-	// Both subscriptions are buffered (one pending tick, ten pending events),
-	// so unsubscribing is not enough to stop callbacks: the loops would drain
-	// what is already queued and deliver it to a listener the caller has
-	// already removed or replaced. Gate every callback on this registration's
-	// own signal, which is closed before unsubscribing.
-	done := make(chan struct{})
-	c.stateChangeDone = done
-
-	id, ch := c.recorder.SubscribeToStateChanges()
-	c.stateChangeSubID = id
-	// The channel is closed by UnsubscribeFromStateChanges, which ends the
-	// goroutine. Ticks are coalesced (buffer of one), so a burst of changes
-	// wakes the listener once.
-	go func() {
-		for range ch {
-			select {
-			case <-done:
-				return
-			default:
-			}
-			listener.OnStateChanged()
-		}
-	}()
-
-	c.eventSub = c.recorder.SubscribeToEvents()
-	go watchSessionWarnings(c.eventSub, listener, done)
-}
-
-// RemoveStateChangeListener unregisters the state notification listener.
-func (c *Client) RemoveStateChangeListener() {
-	c.stateChangeMu.Lock()
-	defer c.stateChangeMu.Unlock()
-	c.stopStateChangeWatchLocked()
-}
-
-// DismissSessionWarning records the user's "Dismiss" on the first expiry
-// warning and suppresses the final one for the current deadline. A refreshed
-// deadline re-arms both. No-op while the engine is not running.
-func (c *Client) DismissSessionWarning() {
-	cc := c.getConnectClient()
-	if cc == nil {
-		return
-	}
-	engine := cc.Engine()
-	if engine == nil {
-		return
-	}
-	engine.DismissSessionWarning()
-}
-
-// ExtendAuthSession runs the interactive SSO flow to obtain a fresh JWT and
-// asks the management server to extend the session deadline. The tunnel is
-// untouched: no resync, no reconnect. Async; the result arrives on the
-// listener. Mirror of the daemon's RequestExtendAuthSession /
-// WaitExtendAuthSession RPC pair, with URLOpener playing the "UI opens the
-// browser" role.
-//
-// Only one flow may be in flight: the PKCE step binds a fixed loopback port,
-// so a second concurrent flow would fail on that bind. Call
-// CancelExtendAuthSession when the user abandons the browser.
-func (c *Client) ExtendAuthSession(urlOpener URLOpener, isAndroidTV bool, resultListener ErrListener) {
-	ctx, err := c.beginExtend()
-	if err != nil {
-		resultListener.OnError(err)
-		return
-	}
-
-	go func() {
-		defer c.endExtend()
-		if err := c.extendAuthSession(ctx, urlOpener, isAndroidTV); err != nil {
-			resultListener.OnError(err)
-			return
-		}
-		resultListener.OnSuccess()
-	}()
-}
-
-// CancelExtendAuthSession aborts an in-flight ExtendAuthSession. The tunnel is
-// left alone — unlike the login flow, which cancels the whole client context
-// by stopping the engine. Without this the abandoned PKCE wait keeps its
-// loopback port for the full flow timeout and blocks every later attempt.
-// No-op when no flow is running.
-func (c *Client) CancelExtendAuthSession() {
-	c.extendMu.Lock()
-	defer c.extendMu.Unlock()
-	if c.extendCancel != nil {
-		c.extendCancel()
-	}
-}
-
-func (c *Client) stopStateChangeWatchLocked() {
-	// Signal first, unsubscribe second: closing the channels only stops new
-	// items, and the loops would still hand whatever is buffered to a listener
-	// that is no longer registered.
-	if c.stateChangeDone != nil {
-		close(c.stateChangeDone)
-		c.stateChangeDone = nil
-	}
-	if c.stateChangeSubID != "" {
-		c.recorder.UnsubscribeFromStateChanges(c.stateChangeSubID)
-		c.stateChangeSubID = ""
-	}
-	if c.eventSub != nil {
-		// Closes the channel, which ends watchSessionWarnings.
-		c.recorder.UnsubscribeFromEvents(c.eventSub)
-		c.eventSub = nil
-	}
-}
-
-// watchSessionWarnings forwards the engine's session-expiry warnings to the
-// listener. The event stream also carries unrelated traffic — network-map
-// updates on every sync, DNS and route errors — so everything but an
-// AUTHENTICATION event carrying the session-warning marker is dropped. Exits
-// when the subscription is closed by UnsubscribeFromEvents, or earlier when
-// done is closed — the stream buffers up to ten events, and a deregistered
-// listener must not receive the ones already queued.
-func watchSessionWarnings(sub *peer.EventSubscription, listener StateChangeListener, done <-chan struct{}) {
-	for ev := range sub.Events() {
-		select {
-		case <-done:
-			return
-		default:
-		}
-		if ev.GetCategory() != cProto.SystemEvent_AUTHENTICATION {
-			continue
-		}
-		meta := ev.GetMetadata()
-		if meta[sessionwatch.MetaSessionWarning] != "true" {
-			// Other AUTHENTICATION events exist (e.g. a deadline rejected as
-			// out of range); they carry no warning marker.
-			continue
-		}
-		deadline, err := sessionwatch.ParseExpiresAt(meta[sessionwatch.MetaSessionExpiresAt])
-		if err != nil {
-			log.Warnf("session warning event with unparsable deadline: %v", err)
-			continue
-		}
-		lead, err := sessionwatch.ParseLeadMinutes(meta[sessionwatch.MetaSessionLeadMinutes])
-		if err != nil {
-			// Informational only — the deadline above is what drives the UI.
-			lead = 0
-		}
-		listener.OnSessionExpiring(deadline.Unix(), int64(lead),
-			meta[sessionwatch.MetaSessionFinal] == "true")
-	}
-}
-
-func (c *Client) beginExtend() (context.Context, error) {
-	c.extendMu.Lock()
-	defer c.extendMu.Unlock()
-	if c.extendCancel != nil {
-		return nil, fmt.Errorf("session extend already in progress")
-	}
-	ctx, cancel := context.WithCancel(context.Background())
-	c.extendCancel = cancel
-	return ctx, nil
-}
-
-func (c *Client) endExtend() {
-	c.extendMu.Lock()
-	defer c.extendMu.Unlock()
-	if c.extendCancel != nil {
-		c.extendCancel()
-		c.extendCancel = nil
-	}
-}
-
-func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isAndroidTV bool) error {
-	cfg, _, cc := c.stateSnapshot()
-	if cfg == nil || cc == nil {
-		return fmt.Errorf("engine is not running")
-	}
-	engine := cc.Engine()
-	if engine == nil {
-		return fmt.Errorf("engine is not initialized")
-	}
-
-	authClient, err := auth.NewAuth(ctx, cfg.PrivateKey, cfg.ManagementURL, cfg)
-	if err != nil {
-		return fmt.Errorf("failed to create auth client: %v", err)
-	}
-	defer authClient.Close()
-
-	a := &Auth{ctx: ctx, config: cfg}
-	tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
-	if err != nil {
-		return fmt.Errorf("interactive sso login failed: %v", err)
-	}
-
-	if _, err := engine.ExtendAuthSession(ctx, tokenInfo.GetTokenToUse()); err != nil {
-		return err
-	}
-	c.clearLoginRequired()
-
-	go urlOpener.OnLoginSuccess()
-	return nil
-}

client/cmd/daemon_error.go

@@ -1,66 +0,0 @@
-package cmd
-
-import (
-	"errors"
-	"fmt"
-	"strings"
-
-	"google.golang.org/genproto/googleapis/rpc/errdetails"
-	gstatus "google.golang.org/grpc/status"
-
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-)
-
-// daemonCallError prepares a daemon error for display. A refusal the daemon
-// raised because the operation needs root/administrator is already guidance
-// written for the user, so it is surfaced on its own instead of buried under the
-// gRPC envelope and the name of the RPC that hit it. Anything else is wrapped
-// with context as usual.
-func daemonCallError(context string, err error) error {
-	if guidance, ok := privilegeGuidance(err); ok {
-		return errors.New(guidance)
-	}
-	return fmt.Errorf("%s: %w", context, err)
-}
-
-// privilegeGuidance renders the daemon's privilege refusal as a summary and the
-// command that performs the operation with the privileges it needs. It reports
-// false for any other error.
-func privilegeGuidance(err error) (string, bool) {
-	info, ok := privilegeErrorInfo(err)
-	if !ok {
-		return "", false
-	}
-
-	summary := info.GetMetadata()[ipcauth.ErrorMetaSummary]
-	command := info.GetMetadata()[ipcauth.ErrorMetaCommand]
-	if summary == "" {
-		// Detail without a summary: fall back to the status message, which
-		// carries the same text.
-		summary = strings.TrimSpace(gstatus.Convert(err).Message())
-	}
-	if command == "" {
-		return summary, true
-	}
-
-	return fmt.Sprintf("%s\n\n    %s\n", summary, command), true
-}
-
-// privilegeErrorInfo returns the daemon's privilege-refusal detail, if the error
-// carries one.
-func privilegeErrorInfo(err error) (*errdetails.ErrorInfo, bool) {
-	if err == nil {
-		return nil, false
-	}
-
-	for _, detail := range gstatus.Convert(err).Details() {
-		info, ok := detail.(*errdetails.ErrorInfo)
-		if !ok {
-			continue
-		}
-		if info.GetReason() == ipcauth.ErrorReasonPrivilegeRequired && info.GetDomain() == ipcauth.ErrorDomain {
-			return info, true
-		}
-	}
-	return nil, false
-}

client/cmd/logout.go

@@ -46,7 +46,7 @@ var logoutCmd = &cobra.Command{
 		}
 
 		if _, err := daemonClient.Logout(ctx, req); err != nil {
-			return daemonCallError("deregister", err)
+			return fmt.Errorf("deregister: %v", err)
 		}
 
 		cmd.Println("Deregistered successfully")

client/cmd/root.go

@@ -20,6 +20,7 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/pflag"
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
 
 	daddr "github.com/netbirdio/netbird/client/internal/daemonaddr"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
@@ -90,7 +91,6 @@ var (
 			// Don't resolve for service commands — they create the socket, not connect to it.
 			if !isServiceCmd(cmd) {
 				daemonAddr = daddr.ResolveUnixDaemonAddr(daemonAddr)
-				daemonAddr = daddr.ResolveDaemonAddr(daemonAddr)
 			}
 			return nil
 		},
@@ -143,10 +143,10 @@ func init() {
 
 	defaultDaemonAddr := "unix:///var/run/netbird.sock"
 	if runtime.GOOS == "windows" {
-		defaultDaemonAddr = daddr.WindowsPipeAddr
+		defaultDaemonAddr = "tcp://127.0.0.1:41731"
 	}
 
-	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp|npipe]://[path|host:port|name]")
+	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp]://[path|host:port]")
 	rootCmd.PersistentFlags().StringVarP(&managementURL, "management-url", "m", "", fmt.Sprintf("Management Service URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultManagementURL))
 	rootCmd.PersistentFlags().StringVar(&adminURL, "admin-url", "", fmt.Sprintf("Admin Panel URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultAdminURL))
 	rootCmd.PersistentFlags().StringVarP(&logLevel, "log-level", "l", "info", "sets NetBird log level")
@@ -269,10 +269,12 @@ func DialClientGRPCServer(ctx context.Context, addr string) (*grpc.ClientConn, e
 	ctx, cancel := context.WithTimeout(ctx, time.Second*10)
 	defer cancel()
 
-	target, opts := daddr.DialTarget(addr)
-	opts = append(opts, grpc.WithBlock())
-
-	return grpc.DialContext(ctx, target, opts...)
+	return grpc.DialContext(
+		ctx,
+		strings.TrimPrefix(addr, "tcp://"),
+		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithBlock(),
+	)
 }
 
 // WithBackOff execute function in backoff cycle.

client/cmd/service.go

@@ -33,15 +33,10 @@ var (
 )
 
 type program struct {
-	ctx      context.Context
-	cancel   context.CancelFunc
-	serv     *grpc.Server
-	jsonServ *http.Server
-	// jsonClient is the gateway's own connection to the daemon. It is held so
-	// shutting the gateway down also closes it: nothing else references it once
-	// the handlers are registered, so its transport goroutines would otherwise
-	// outlive the server.
-	jsonClient       *grpc.ClientConn
+	ctx              context.Context
+	cancel           context.CancelFunc
+	serv             *grpc.Server
+	jsonServ         *http.Server
 	jsonServMu       sync.Mutex
 	serverInstance   *server.Server
 	serverInstanceMu sync.Mutex

client/cmd/service_controller.go

@@ -5,7 +5,6 @@ package cmd
 import (
 	"context"
 	"fmt"
-	"runtime"
 	"time"
 
 	"github.com/kardianos/service"
@@ -14,8 +13,6 @@ import (
 	"github.com/spf13/cobra"
 	"google.golang.org/grpc"
 
-	"github.com/netbirdio/netbird/client/internal/daemonaddr"
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
 	"github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/server"
 	"github.com/netbirdio/netbird/client/system"
@@ -29,31 +26,6 @@ func validateJSONSocketFlags() error {
 	return nil
 }
 
-// daemonServerOptions installs the transport credentials that expose each
-// caller's kernel-authenticated identity to the handlers, which is what lets
-// the daemon require root/administrator for privileged operations.
-//
-// The handshake exchanges no bytes, so older CLI and UI binaries still
-// interoperate. Callers on a TCP socket carry no identity at all: the daemon
-// keeps serving them, and the privileged operations deny them, so a warning is
-// logged to make the loss of functionality visible.
-func daemonServerOptions(network string) []grpc.ServerOption {
-	if network == "tcp" {
-		log.Warnf("daemon is listening on TCP (%s): callers carry no verifiable identity over TCP, "+
-			"so privileged operations (SSH root login, SSH auth, enabling the SSH server, management URL changes, "+
-			"deregistration) will be denied. Use a unix socket, or npipe:// on Windows", daemonAddr)
-		return nil
-	}
-
-	creds := ipcauth.NewTransportCredentials()
-	if creds == nil {
-		log.Warnf("daemon IPC has no peer-identity primitive on %s: privileged operations will be denied", runtime.GOOS)
-		return nil
-	}
-
-	return []grpc.ServerOption{grpc.Creds(creds)}
-}
-
 func (p *program) Start(svc service.Service) error {
 	// Start should not block. Do the actual work async.
 	log.Info("starting NetBird service") //nolint
@@ -65,106 +37,68 @@ func (p *program) Start(svc service.Service) error {
 	// Collect static system and platform information
 	system.UpdateStaticInfoAsync()
 
-	// A daemon installed before named-pipe support has the loopback TCP address
-	// persisted. Move it to the named pipe so an upgraded daemon can identify
-	// its callers instead of silently serving an unauthenticated socket.
-	if migrated, ok := daemonaddr.MigrateLegacy(daemonAddr); ok {
-		log.Infof("daemon address %q predates named-pipe support, listening on %q so callers can be identified", daemonAddr, migrated)
-		daemonAddr = migrated
-	}
-
-	network, _, err := parseListenAddress(daemonAddr)
-	if err != nil {
-		return fmt.Errorf("parse daemon address: %w", err)
-	}
-
 	// in any case, even if configuration does not exists we run daemon to serve CLI gRPC API.
-	p.serv = grpc.NewServer(daemonServerOptions(network)...)
+	p.serv = grpc.NewServer()
 
-	daemonListener, jsonListener, err := listenDaemonSockets()
+	daemonListener, err := listenOnAddress(daemonAddr)
 	if err != nil {
-		return err
+		return fmt.Errorf("listen daemon interface: %w", err)
+	}
+
+	var jsonListener *socketListener
+	if enableJSONSocket {
+		jsonListener, err = listenOnAddress(jsonSocket)
+		if err != nil {
+			_ = daemonListener.Close()
+			return fmt.Errorf("listen daemon JSON interface: %w", err)
+		}
+	} else {
+		removeStaleUnixSocketForAddress(jsonSocket)
 	}
 
 	go func() {
-		// Fatal here rather than inside serve, so serve's deferred listener
-		// closes run before the process exits.
-		if err := p.serve(daemonListener, jsonListener); err != nil {
-			log.Fatalf("failed to %v", err)
+		defer daemonListener.Close()
+		if jsonListener != nil {
+			defer jsonListener.Close()
+		}
+
+		if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
+			log.Error(err)
+			return
+		}
+		if jsonListener != nil {
+			if err := jsonListener.chmodUnixSocket("daemon JSON"); err != nil {
+				log.Error(err)
+				return
+			}
+		}
+
+		serverInstance := server.New(p.ctx, util.FindFirstLogPath(logFiles), configPath, profilesDisabled, updateSettingsDisabled, captureEnabled, networksDisabled)
+		if err := serverInstance.Start(); err != nil {
+			log.Fatalf("failed to start daemon: %v", err)
+		}
+		proto.RegisterDaemonServiceServer(p.serv, serverInstance)
+
+		p.serverInstanceMu.Lock()
+		p.serverInstance = serverInstance
+		p.serverInstanceMu.Unlock()
+
+		if jsonListener != nil {
+			if err := p.startJSONGateway(jsonListener, daemonAddr); err != nil {
+				log.Fatalf("failed to start daemon JSON server: %v", err)
+			}
+		} else {
+			log.Debug("daemon JSON socket disabled")
+		}
+
+		log.Printf("started daemon server: %v", daemonListener.address)
+		if err := p.serv.Serve(daemonListener.Listener); err != nil {
+			log.Errorf("failed to serve daemon requests: %v", err)
 		}
 	}()
 	return nil
 }
 
-// listenDaemonSockets opens the daemon control socket and, when it is enabled, the
-// JSON gateway socket. The control socket is closed again if the second one fails,
-// so a failed start leaves nothing listening. The returned JSON listener is nil
-// when the socket is disabled.
-func listenDaemonSockets() (*socketListener, *socketListener, error) {
-	daemonListener, err := listenOnAddress(daemonAddr)
-	if err != nil {
-		return nil, nil, fmt.Errorf("listen daemon interface: %w", err)
-	}
-
-	if !enableJSONSocket {
-		removeStaleUnixSocketForAddress(jsonSocket)
-		return daemonListener, nil, nil
-	}
-
-	jsonListener, err := listenOnAddress(jsonSocket)
-	if err != nil {
-		if cerr := daemonListener.Close(); cerr != nil {
-			log.Debugf("close daemon listener: %v", cerr)
-		}
-		return nil, nil, fmt.Errorf("listen daemon JSON interface: %w", err)
-	}
-
-	return daemonListener, jsonListener, nil
-}
-
-// serve brings up the daemon server on an already-open control socket and blocks
-// until it stops. jsonListener is nil when the JSON socket is disabled. A returned
-// error means the daemon cannot run at all and the caller is expected to exit; the
-// failures it recovers from on its own are logged here.
-func (p *program) serve(daemonListener, jsonListener *socketListener) error {
-	defer daemonListener.Close()
-	if jsonListener != nil {
-		defer jsonListener.Close()
-	}
-
-	// chmodUnixSocket is a no-op for a nil listener and for a non-unix one.
-	if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
-		log.Error(err)
-		return nil
-	}
-	if err := jsonListener.chmodUnixSocket("daemon JSON"); err != nil {
-		log.Error(err)
-		return nil
-	}
-
-	serverInstance := server.New(p.ctx, util.FindFirstLogPath(logFiles), configPath, profilesDisabled, updateSettingsDisabled, captureEnabled, networksDisabled)
-	if err := serverInstance.Start(); err != nil {
-		return fmt.Errorf("start daemon: %w", err)
-	}
-	proto.RegisterDaemonServiceServer(p.serv, serverInstance)
-
-	p.serverInstanceMu.Lock()
-	p.serverInstance = serverInstance
-	p.serverInstanceMu.Unlock()
-
-	if jsonListener == nil {
-		log.Debug("daemon JSON socket disabled")
-	} else if err := p.startJSONGateway(jsonListener, daemonAddr); err != nil {
-		return fmt.Errorf("start daemon JSON server: %w", err)
-	}
-
-	log.Printf("started daemon server: %v", daemonListener.address)
-	if err := p.serv.Serve(daemonListener.Listener); err != nil {
-		log.Errorf("failed to serve daemon requests: %v", err)
-	}
-	return nil
-}
-
 func (p *program) Stop(srv service.Service) error {
 	p.serverInstanceMu.Lock()
 	if p.serverInstance != nil {
@@ -179,13 +113,8 @@ func (p *program) Stop(srv service.Service) error {
 	p.cancel()
 
 	p.jsonServMu.Lock()
-	jsonServ, jsonClient := p.jsonServ, p.jsonClient
+	jsonServ := p.jsonServ
 	p.jsonServMu.Unlock()
-	if jsonClient != nil {
-		if err := jsonClient.Close(); err != nil {
-			log.Debugf("close daemon JSON gateway client: %v", err)
-		}
-	}
 	if jsonServ != nil {
 		shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), 2*time.Second)
 		if err := jsonServ.Shutdown(shutdownCtx); err != nil {

client/cmd/service_json_gateway.go

@@ -5,123 +5,27 @@ package cmd
 import (
 	"context"
 	"errors"
-	"fmt"
 	"net"
 	"net/http"
-	"sync"
+	"strings"
 	"time"
 
 	"github.com/grpc-ecosystem/grpc-gateway/v2/runtime"
 	log "github.com/sirupsen/logrus"
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
 
-	"github.com/netbirdio/netbird/client/internal/daemonaddr"
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
 	"github.com/netbirdio/netbird/client/proto"
 )
 
-// jsonPeerIdentity is the context key under which the connecting HTTP client's
-// identity is stashed for the lifetime of its connection.
-type jsonPeerIdentity struct{}
-
-// jsonPeerIdentityValue pairs the identity with whether it could be read at
-// all, so an unreadable identity is forwarded as "unknown" rather than omitted.
-type jsonPeerIdentityValue struct {
-	id    ipcauth.Identity
-	known bool
-}
-
-// jsonConnContext reads the identity of the client connecting to the JSON
-// socket and stashes it on the connection's context. The gateway re-dials the
-// daemon in-process, so the daemon would otherwise see every JSON request as
-// coming from the daemon itself.
-func jsonConnContext(ctx context.Context, c net.Conn) context.Context {
-	value := jsonPeerIdentityValue{}
-	id, err := ipcauth.ConnIdentity(c)
-	if err != nil {
-		log.Warnf("json gateway: cannot read HTTP client identity, privileged operations will be denied for this connection: %v", err)
-	} else {
-		value.id = id
-		value.known = true
-	}
-	return context.WithValue(ctx, jsonPeerIdentity{}, value)
-}
-
-// forwardIdentity stamps the HTTP client's identity onto every call the gateway
-// makes to the daemon.
-//
-// It is an interceptor on the gateway's client connection rather than a
-// runtime.WithMetadata annotator because grpc-gateway skips annotators when no
-// request header maps to metadata, which an HTTP/1.0 request with no Host header
-// over a unix socket achieves. The daemon would then receive no marker, see its own
-// identity as the transport peer, and authorize the request as the daemon itself.
-// An interceptor runs for every RPC whatever the request looked like.
-func forwardIdentity(ctx context.Context) context.Context {
-	value, ok := ctx.Value(jsonPeerIdentity{}).(jsonPeerIdentityValue)
-	if !ok {
-		// No ConnContext ran for this request, so forward an unknown identity:
-		// the daemon must not mistake its own identity for the client's.
-		return ipcauth.WithForwardedIdentity(ctx, ipcauth.Identity{}, false)
-	}
-	return ipcauth.WithForwardedIdentity(ctx, value.id, value.known)
-}
-
-func forwardIdentityUnary(ctx context.Context, method string, req, reply any, cc *grpc.ClientConn, invoker grpc.UnaryInvoker, opts ...grpc.CallOption) error {
-	return invoker(forwardIdentity(ctx), method, req, reply, cc, opts...)
-}
-
-func forwardIdentityStream(ctx context.Context, desc *grpc.StreamDesc, cc *grpc.ClientConn, method string, streamer grpc.Streamer, opts ...grpc.CallOption) (grpc.ClientStream, error) {
-	return streamer(forwardIdentity(ctx), desc, cc, method, opts...)
-}
-
-// reservedHeaderWarning limits the dropped-header warning to the first occurrence.
-var reservedHeaderWarning sync.Once
-
-// jsonIncomingHeaderMatcher keeps an HTTP client from supplying the metadata the
-// gateway uses to forward its identity. grpc-gateway turns "Grpc-Metadata-<key>"
-// headers into gRPC metadata and joins them ahead of what its annotators add, so
-// without this filter a JSON client could send its own x-netbird-fwd-uid and the
-// daemon would authorize that instead of the client's real identity.
-func jsonIncomingHeaderMatcher(key string) (string, bool) {
-	mapped, ok := runtime.DefaultHeaderMatcher(key)
-	if !ok {
-		return "", false
-	}
-	if ipcauth.IsReservedForwardKey(mapped) {
-		// Warn once: any client can send these on every request, so warning each
-		// time hands it a way to fill the log. The rest are debug-level.
-		reservedHeaderWarning.Do(func() {
-			log.Warnf("json gateway: dropping reserved header %q from a request: only the gateway may set the caller's identity", key)
-		})
-		log.Debugf("json gateway: dropping reserved header %q", key)
-		return "", false
-	}
-	return mapped, true
+func grpcGatewayEndpoint(addr string) string {
+	return strings.TrimPrefix(addr, "tcp://")
 }
 
 func (p *program) startJSONGateway(jsonListener *socketListener, daemonEndpoint string) error {
-	if jsonListener.network == "tcp" {
-		log.Warnf("daemon JSON socket is listening on TCP (%s): callers carry no verifiable identity over TCP, "+
-			"so privileged operations will be denied for JSON clients", jsonListener.address)
-	}
-
-	mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
-
-	// grpc.NewClient does not connect until the first request, so registering
-	// the handler here cannot block daemon startup.
-	target, opts := daemonaddr.DialTarget(daemonEndpoint)
-	opts = append(opts,
-		grpc.WithChainUnaryInterceptor(forwardIdentityUnary),
-		grpc.WithChainStreamInterceptor(forwardIdentityStream),
-	)
-	conn, err := grpc.NewClient(target, opts...)
-	if err != nil {
-		return fmt.Errorf("create daemon client for JSON gateway: %w", err)
-	}
-	if err := proto.RegisterDaemonServiceHandler(p.ctx, mux, conn); err != nil {
-		if cerr := conn.Close(); cerr != nil {
-			log.Debugf("close daemon client after failed JSON gateway registration: %v", cerr)
-		}
+	mux := runtime.NewServeMux()
+	opts := []grpc.DialOption{grpc.WithTransportCredentials(insecure.NewCredentials())}
+	if err := proto.RegisterDaemonServiceHandlerFromEndpoint(p.ctx, mux, grpcGatewayEndpoint(daemonEndpoint), opts); err != nil {
 		return err
 	}
 
@@ -131,12 +35,10 @@ func (p *program) startJSONGateway(jsonListener *socketListener, daemonEndpoint
 		BaseContext: func(net.Listener) context.Context {
 			return p.ctx
 		},
-		ConnContext: jsonConnContext,
 	}
 
 	p.jsonServMu.Lock()
 	p.jsonServ = jsonServer
-	p.jsonClient = conn
 	p.jsonServMu.Unlock()
 
 	go func() {

client/cmd/service_json_gateway_test.go

@@ -1,261 +0,0 @@
-//go:build !windows && !ios && !android
-
-package cmd
-
-import (
-	"context"
-	"net"
-	"net/http"
-	"path/filepath"
-	"testing"
-	"time"
-
-	"github.com/grpc-ecosystem/grpc-gateway/v2/runtime"
-	"google.golang.org/grpc/credentials"
-	"google.golang.org/grpc/metadata"
-	"google.golang.org/grpc/peer"
-
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-)
-
-// The JSON gateway runs inside the daemon and re-dials it locally, so every JSON
-// request reaches a handler with the daemon's own identity as the transport peer.
-// The gateway therefore forwards its HTTP client's identity as metadata, and the
-// daemon authorizes that instead of itself. These tests drive the real wiring
-// (jsonConnContext, forwardIdentity, jsonIncomingHeaderMatcher) and check the
-// identity a handler would end up authorizing.
-
-// daemonSideCtx is what a handler sees for a gateway-relayed call. The transport
-// peer must be this process's own identity: the gateway is the daemon, so the two
-// cannot differ, and hardcoding root here instead would describe a state that
-// never occurs.
-func daemonSideCtx(t *testing.T, md metadata.MD) context.Context {
-	t.Helper()
-	self, err := ipcauth.CurrentProcessIdentity()
-	if err != nil {
-		t.Skipf("cannot read this process's identity: %v", err)
-	}
-	ctx := peer.NewContext(context.Background(), &peer.Peer{
-		AuthInfo: ipcauth.AuthInfo{
-			CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
-			Identity:       self,
-		},
-	})
-	return metadata.NewIncomingContext(ctx, md)
-}
-
-// gatewayMetadata reproduces what the daemon receives for a JSON request: the
-// mux annotates the context from the request's headers, then the interceptor on the
-// gateway's client connection stamps the caller's identity. The order matters,
-// since the interceptor must win over anything a header put there.
-func gatewayMetadata(t *testing.T, req *http.Request, ctx context.Context) metadata.MD {
-	t.Helper()
-	mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
-	annotated, err := runtime.AnnotateContext(ctx, mux, req,
-		"/daemon.DaemonService/SetConfig",
-		runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
-	if err != nil {
-		t.Fatalf("annotate: %v", err)
-	}
-
-	md, ok := metadata.FromOutgoingContext(forwardIdentity(annotated))
-	if !ok {
-		t.Fatal("the interceptor produced no metadata")
-	}
-	return md
-}
-
-// clientCtx is the connection context jsonConnContext would have produced for an
-// HTTP client whose identity the gateway could read.
-func clientCtx(id ipcauth.Identity, known bool) context.Context {
-	return context.WithValue(context.Background(), jsonPeerIdentity{},
-		jsonPeerIdentityValue{id: id, known: known})
-}
-
-// An HTTP client must not be able to name its own identity. grpc-gateway turns
-// Grpc-Metadata-<key> headers into gRPC metadata, so without the header filter and
-// the interceptor overwriting the reserved keys, this request would authorize as
-// uid 0.
-func TestJSONGateway_ForgedIdentityHeaderIsDropped(t *testing.T) {
-	req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Uid", "0")
-	req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Gid", "0")
-	req.Header.Set("Grpc-Metadata-X-Netbird-Fwd", "1")
-	req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Sid", "S-1-5-18")
-
-	caller := ipcauth.Identity{UID: 31000, GID: 31000}
-	md := gatewayMetadata(t, req, clientCtx(caller, true))
-
-	id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md))
-	if !ok {
-		t.Fatal("the forwarded identity should be usable")
-	}
-	if id.IsPrivileged() {
-		t.Errorf("forged header was believed: authorized as %v", id)
-	}
-	if id.UID != caller.UID {
-		t.Errorf("authorized as uid %d, want the real client %d", id.UID, caller.UID)
-	}
-}
-
-// A request with no headers at all (HTTP/1.0 needs no Host, and a unix socket
-// yields no host:port) makes grpc-gateway produce no metadata whatsoever and skip
-// its annotators: "if len(pairs) == 0 { return ctx, nil, nil }" in
-// runtime/context.go. That is why the identity is stamped by an interceptor
-// instead. This is the case that previously reached the gate as the daemon itself.
-func TestJSONGateway_HeaderlessRequestIsStillMarkedForwarded(t *testing.T) {
-	req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	req.Header = http.Header{}
-	req.Host = ""
-
-	caller := ipcauth.Identity{UID: 31000, GID: 31000}
-	ctx := clientCtx(caller, true)
-
-	// Pin the skip path itself: if grpc-gateway ever produced a pair here, this
-	// test would still pass below while no longer covering what it was written for.
-	mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
-	annotated, err := runtime.AnnotateContext(ctx, mux, req,
-		"/daemon.DaemonService/SetConfig",
-		runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
-	if err != nil {
-		t.Fatalf("annotate: %v", err)
-	}
-	if md, ok := metadata.FromOutgoingContext(annotated); ok {
-		t.Fatalf("grpc-gateway produced metadata %v for a headerless request; "+
-			"this test no longer covers the annotator-skip path", md)
-	}
-
-	md := gatewayMetadata(t, req, ctx)
-
-	id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md))
-	if !ok {
-		t.Fatal("the forwarded identity should be usable")
-	}
-	if id.UID != caller.UID || id.IsPrivileged() {
-		t.Errorf("authorized as %v, want the real client uid %d", id, caller.UID)
-	}
-}
-
-// When the gateway cannot read its client's identity (a TCP JSON socket, say) it
-// forwards the marker alone. The daemon must then report "unidentified" so the
-// privileged operations refuse, rather than falling back to the gateway's own
-// identity.
-func TestJSONGateway_UnreadableClientIdentityIsUnidentified(t *testing.T) {
-	req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	md := gatewayMetadata(t, req, clientCtx(ipcauth.Identity{}, false))
-
-	if id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md)); ok {
-		t.Errorf("a request with no client identity was authorized as %v", id)
-	}
-}
-
-// A request that never passed through jsonConnContext (no stashed identity) must
-// also come out unidentified rather than as the daemon.
-func TestJSONGateway_MissingConnContextIsUnidentified(t *testing.T) {
-	req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	md := gatewayMetadata(t, req, context.Background())
-
-	if id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md)); ok {
-		t.Errorf("a request with no connection context was authorized as %v", id)
-	}
-}
-
-// End to end over a real unix socket: the gateway reads the connecting client's
-// identity from the socket itself, so a client cannot present anything else.
-func TestJSONGateway_IdentityComesFromTheSocket(t *testing.T) {
-	mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
-
-	type observed struct {
-		md metadata.MD
-	}
-	seen := make(chan observed, 1)
-
-	srv := &http.Server{
-		Handler: http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-			ctx, err := runtime.AnnotateContext(r.Context(), mux, r,
-				"/daemon.DaemonService/SetConfig",
-				runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
-			if err != nil {
-				t.Errorf("annotate: %v", err)
-				return
-			}
-			md, _ := metadata.FromOutgoingContext(forwardIdentity(ctx))
-			seen <- observed{md: md}
-			w.WriteHeader(http.StatusOK)
-		}),
-		ReadHeaderTimeout: 5 * time.Second,
-		ConnContext:       jsonConnContext,
-	}
-
-	sock := filepath.Join(t.TempDir(), "http.sock")
-	ln, err := net.Listen("unix", sock)
-	if err != nil {
-		t.Fatal(err)
-	}
-	t.Cleanup(func() {
-		if err := srv.Close(); err != nil {
-			t.Logf("close server: %v", err)
-		}
-	})
-	go func() {
-		if err := srv.Serve(ln); err != nil && err != http.ErrServerClosed {
-			t.Logf("serve: %v", err)
-		}
-	}()
-
-	conn, err := net.Dial("unix", sock)
-	if err != nil {
-		t.Fatal(err)
-	}
-	t.Cleanup(func() {
-		if err := conn.Close(); err != nil {
-			t.Logf("close conn: %v", err)
-		}
-	})
-
-	// Forge the identity headers on the wire as well.
-	request := "POST /daemon.DaemonService/SetConfig HTTP/1.1\r\n" +
-		"Host: localhost\r\n" +
-		"Grpc-Metadata-X-Netbird-Fwd: 1\r\n" +
-		"Grpc-Metadata-X-Netbird-Fwd-Uid: 0\r\n" +
-		"Content-Length: 0\r\n\r\n"
-	if _, err := conn.Write([]byte(request)); err != nil {
-		t.Fatal(err)
-	}
-
-	select {
-	case got := <-seen:
-		self, err := ipcauth.CurrentProcessIdentity()
-		if err != nil {
-			t.Skipf("cannot read this process's identity: %v", err)
-		}
-		// The socket peer is this test process, so that is the identity the
-		// gateway must forward, not the uid 0 the request asked for.
-		if uids := got.md.Get("x-netbird-fwd-uid"); len(uids) != 1 {
-			t.Fatalf("x-netbird-fwd-uid = %v, want exactly the gateway's own value", uids)
-		}
-		id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, got.md))
-		if !ok {
-			t.Fatal("the forwarded identity should be usable")
-		}
-		if id.UID != self.UID {
-			t.Errorf("authorized as uid %d, want the socket peer %d", id.UID, self.UID)
-		}
-	case <-time.After(5 * time.Second):
-		t.Fatal("the gateway never handled the request")
-	}
-}

client/cmd/service_params.go

@@ -13,7 +13,6 @@ import (
 	"github.com/spf13/cobra"
 
 	"github.com/netbirdio/netbird/client/configs"
-	"github.com/netbirdio/netbird/client/internal/daemonaddr"
 	"github.com/netbirdio/netbird/util"
 )
 
@@ -126,13 +125,6 @@ func applyServiceParams(cmd *cobra.Command, params *serviceParams) {
 
 	if !rootCmd.PersistentFlags().Changed("daemon-addr") && params.DaemonAddr != "" {
 		daemonAddr = params.DaemonAddr
-		// An install that predates named-pipe support has the loopback TCP
-		// address saved. Callers carry no identity over TCP, so move it to the
-		// pipe instead of restoring a socket the daemon cannot authorize on.
-		if migrated, ok := daemonaddr.MigrateLegacy(daemonAddr); ok {
-			cmd.Printf("Moving the saved daemon address from %s to %s so the daemon can identify its callers\n", daemonAddr, migrated)
-			daemonAddr = migrated
-		}
 	}
 
 	if !serviceCmd.PersistentFlags().Changed("json-socket") && params.JSONSocket != "" {

client/cmd/service_pipe_other.go

@@ -1,14 +0,0 @@
-//go:build !windows
-
-package cmd
-
-import (
-	"fmt"
-	"net"
-)
-
-// listenNamedPipe is Windows-only: no other platform serves the daemon on a
-// named pipe.
-func listenNamedPipe(string) (net.Listener, string, error) {
-	return nil, "", fmt.Errorf("named pipes are only supported on Windows")
-}

client/cmd/service_pipe_windows.go

@@ -1,41 +0,0 @@
-//go:build windows
-
-package cmd
-
-import (
-	"errors"
-	"fmt"
-	"net"
-
-	"github.com/Microsoft/go-winio"
-	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/client/internal/daemonaddr"
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-)
-
-// listenNamedPipe creates the daemon control pipe and reports the path it ended
-// up on. The security descriptor lets any local caller connect, as a Unix socket
-// at 0666 does, and the privileged operations are authorized separately from the
-// caller's token.
-//
-// The protected name comes first so that an unprivileged process cannot take the
-// name before the service does. Creating it requires being an administrator or
-// LocalSystem, so a daemon an ordinary user runs themselves, as in netstack mode,
-// falls back to the plain name; clients try both and check who serves them.
-func listenNamedPipe(name string) (net.Listener, string, error) {
-	var errs []error
-	for _, path := range daemonaddr.PipePaths(name) {
-		listener, err := winio.ListenPipe(path, &winio.PipeConfig{
-			SecurityDescriptor: ipcauth.DefaultPipeSDDL(),
-		})
-		if err != nil {
-			log.Debugf("not serving the daemon on %s: %v", path, err)
-			errs = append(errs, fmt.Errorf("%s: %w", path, err))
-			continue
-		}
-		return listener, path, nil
-	}
-
-	return nil, "", errors.Join(errs...)
-}

client/cmd/service_socket.go

@@ -26,14 +26,6 @@ func listenOnAddress(addr string) (*socketListener, error) {
 		return nil, err
 	}
 
-	if network == "npipe" {
-		listener, path, err := listenNamedPipe(address)
-		if err != nil {
-			return nil, err
-		}
-		return &socketListener{Listener: listener, network: network, address: path}, nil
-	}
-
 	if network == "unix" {
 		removeStaleUnixSocket(address)
 	}
@@ -49,11 +41,11 @@ func listenOnAddress(addr string) (*socketListener, error) {
 func parseListenAddress(addr string) (string, string, error) {
 	network, address, ok := strings.Cut(addr, "://")
 	if !ok || network == "" || address == "" {
-		return "", "", fmt.Errorf("address must be in [unix|tcp|npipe]://[path|host:port|name] format: %q", addr)
+		return "", "", fmt.Errorf("address must be in [unix|tcp]://[path|host:port] format: %q", addr)
 	}
 
 	switch network {
-	case "unix", "tcp", "npipe":
+	case "unix", "tcp":
 		return network, address, nil
 	default:
 		return "", "", fmt.Errorf("unsupported daemon address protocol: %v", network)

client/cmd/up.go

@@ -325,7 +325,7 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager
 		if st, ok := gstatus.FromError(err); ok && st.Code() == codes.Unavailable {
 			log.Warnf("setConfig method is not available in the daemon: %s", st.Message())
 		} else {
-			return daemonCallError("call service setConfig method", err)
+			return fmt.Errorf("call service setConfig method: %v", err)
 		}
 	}
 
@@ -379,7 +379,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
 	}
 
 	if loginErr != nil {
-		return daemonCallError("login failed", loginErr)
+		return fmt.Errorf("login failed: %v", loginErr)
 	}
 
 	if loginResp.NeedsSSOLogin {
@@ -392,7 +392,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
 		ProfileName: &profileID,
 		Username:    &username,
 	}); err != nil {
-		return daemonCallError("call service up method", err)
+		return fmt.Errorf("call service up method: %v", err)
 	}
 
 	return nil

client/internal/conn_mgr.go

@@ -385,20 +385,11 @@ func inactivityThresholdEnv() *time.Duration {
 		return nil
 	}
 
-	// Documented format: a Go duration such as "30m" or "1h".
-	if d, err := time.ParseDuration(envValue); err == nil {
-		if d <= 0 {
-			return nil
-		}
-		return &d
+	parsedMinutes, err := strconv.Atoi(envValue)
+	if err != nil || parsedMinutes <= 0 {
+		return nil
 	}
 
-	// Backwards compatibility: a bare integer used to be interpreted as minutes.
-	if parsedMinutes, err := strconv.Atoi(envValue); err == nil && parsedMinutes > 0 {
-		d := time.Duration(parsedMinutes) * time.Minute
-		return &d
-	}
-
-	log.Warnf("invalid %s value %q: expected a Go duration such as 30m or 1h", lazyconn.EnvInactivityThreshold, envValue)
-	return nil
+	d := time.Duration(parsedMinutes) * time.Minute
+	return &d
 }

client/internal/conn_mgr_test.go

@@ -104,38 +104,3 @@ func TestConnMgr_ActivatePeerConcurrentWithLifecycle(t *testing.T) {
 	close(done)
 	wg.Wait()
 }
-
-func TestInactivityThresholdEnv(t *testing.T) {
-	tests := []struct {
-		name string
-		val  string
-		want *time.Duration
-	}{
-		{name: "unset", val: "", want: nil},
-		{name: "go duration minutes", val: "30m", want: durPtr(30 * time.Minute)},
-		{name: "go duration hours", val: "1h", want: durPtr(time.Hour)},
-		{name: "go duration seconds", val: "90s", want: durPtr(90 * time.Second)},
-		{name: "bare integer is minutes (backwards compat)", val: "5", want: durPtr(5 * time.Minute)},
-		{name: "zero duration", val: "0s", want: nil},
-		{name: "zero integer", val: "0", want: nil},
-		{name: "negative duration", val: "-5m", want: nil},
-		{name: "garbage", val: "abc", want: nil},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv(lazyconn.EnvInactivityThreshold, tc.val)
-			got := inactivityThresholdEnv()
-			switch {
-			case tc.want == nil && got != nil:
-				t.Fatalf("want nil, got %v", *got)
-			case tc.want != nil && got == nil:
-				t.Fatalf("want %v, got nil", *tc.want)
-			case tc.want != nil && *got != *tc.want:
-				t.Fatalf("want %v, got %v", *tc.want, *got)
-			}
-		})
-	}
-}
-
-func durPtr(d time.Duration) *time.Duration { return &d }

client/internal/connect.go

@@ -34,7 +34,6 @@ import (
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
-	"github.com/netbirdio/netbird/client/internal/tunnelnotifier"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/internal/updater/installer"
 	nbnet "github.com/netbirdio/netbird/client/net"
@@ -137,13 +136,10 @@ func (c *ConnectClient) RunOniOS(
 	// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
 	debug.SetGCPercent(5)
 
-	notifier := tunnelnotifier.New(networkChangeListener, dnsManager)
-	defer notifier.Close()
-
 	mobileDependency := MobileDependency{
 		FileDescriptor:        fileDescriptor,
-		NetworkChangeListener: notifier,
-		DnsManager:            notifier,
+		NetworkChangeListener: networkChangeListener,
+		DnsManager:            dnsManager,
 		StateFilePath:         stateFilePath,
 		TempDir:               cacheDir,
 	}

client/internal/daemonaddr/owner.go

@@ -1,15 +0,0 @@
-package daemonaddr
-
-// DaemonRunsAsSelf reports whether the daemon listening at addr runs as this very
-// user. That is what makes an unprivileged daemon authorize this process for the
-// changes it otherwise restricts to root or an administrator, so a client can tell
-// up front whether those controls are usable instead of letting a save fail.
-//
-// It is answered from the ownership of the socket or pipe the daemon created, so it
-// costs no round trip and needs no cooperation from the daemon. Ownership that
-// cannot be read is reported as false, including for a TCP address, so a caller
-// reading this as "the daemon would allow it" fails closed. The daemon remains the
-// only thing that authorizes anything: this only decides what a client offers.
-func DaemonRunsAsSelf(addr string) bool {
-	return daemonRunsAsSelf(addr)
-}

client/internal/daemonaddr/owner_unix.go

@@ -1,40 +0,0 @@
-//go:build !windows
-
-package daemonaddr
-
-import (
-	"os"
-	"strings"
-	"syscall"
-
-	log "github.com/sirupsen/logrus"
-)
-
-// daemonRunsAsSelf compares the owner of the daemon's Unix socket with this
-// process's uid. Root is not treated specially here: a root caller is privileged
-// on its own merits, and a root-owned socket says nothing about the caller.
-func daemonRunsAsSelf(addr string) bool {
-	path, ok := strings.CutPrefix(addr, "unix://")
-	if !ok {
-		return false
-	}
-
-	info, err := os.Stat(path)
-	if err != nil {
-		log.Debugf("stat daemon socket %s: %v", path, err)
-		return false
-	}
-
-	// Only a socket says anything about a daemon. A directory or a leftover
-	// regular file at that path is not one, and reading it as "the daemon runs as
-	// us" would offer controls the daemon then refuses.
-	if info.Mode()&os.ModeSocket == 0 {
-		return false
-	}
-
-	stat, ok := info.Sys().(*syscall.Stat_t)
-	if !ok {
-		return false
-	}
-	return stat.Uid == uint32(os.Getuid())
-}

client/internal/daemonaddr/owner_unix_test.go

@@ -1,62 +0,0 @@
-//go:build !windows
-
-package daemonaddr
-
-import (
-	"net"
-	"os"
-	"path/filepath"
-	"testing"
-)
-
-// A socket this user created means the daemon runs as this user, which is the
-// rootless case where the daemon delegates its authority to its own identity.
-func TestDaemonRunsAsSelf_OwnSocket(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "netbird.sock")
-	ln, err := net.Listen("unix", path)
-	if err != nil {
-		t.Fatalf("listen: %v", err)
-	}
-	t.Cleanup(func() {
-		if err := ln.Close(); err != nil {
-			t.Logf("close listener: %v", err)
-		}
-	})
-
-	if !DaemonRunsAsSelf("unix://" + path) {
-		t.Error("a socket owned by this user must count as the daemon running as us")
-	}
-}
-
-// Everything that is not a readable socket of ours has to answer false, because
-// the caller reads a true as "the daemon would authorize me".
-func TestDaemonRunsAsSelf_FailsClosed(t *testing.T) {
-	dir := t.TempDir()
-
-	// A socket owned by another user, which is what a root-run daemon looks like
-	// to an unprivileged client. Only assertable when we are not root ourselves.
-	rootOwned := "unix:///var/run/netbird.sock"
-	if _, err := os.Stat("/var/run/netbird.sock"); err == nil && os.Getuid() != 0 {
-		if DaemonRunsAsSelf(rootOwned) {
-			t.Error("a socket owned by another user must not count as ours")
-		}
-	}
-
-	for name, addr := range map[string]string{
-		"missing socket":  "unix://" + filepath.Join(dir, "absent.sock"),
-		"tcp address":     "tcp://127.0.0.1:41731",
-		"named pipe":      "npipe://netbird",
-		"empty":           "",
-		"no scheme":       filepath.Join(dir, "absent.sock"),
-		"directory":       "unix://" + dir,
-		"unknown scheme":  "http://localhost:8080",
-		"scheme only":     "unix://",
-		"relative socket": "unix://netbird.sock",
-	} {
-		t.Run(name, func(t *testing.T) {
-			if DaemonRunsAsSelf(addr) {
-				t.Errorf("%q must not count as a daemon running as us", addr)
-			}
-		})
-	}
-}

client/internal/daemonaddr/owner_windows.go

@@ -1,42 +0,0 @@
-//go:build windows
-
-package daemonaddr
-
-import (
-	"context"
-	"strings"
-
-	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-)
-
-// daemonRunsAsSelf reads the owner of the daemon's pipe. A daemon running as the
-// service account owns its pipe as LocalSystem, and an elevated one as
-// BUILTIN\Administrators, so only a daemon the user started themselves matches.
-func daemonRunsAsSelf(addr string) bool {
-	name, ok := strings.CutPrefix(addr, pipeScheme)
-	if !ok {
-		return false
-	}
-
-	for _, path := range PipePaths(name) {
-		// Bounded: this runs on the UI's path for deciding which controls to
-		// offer, so a pipe that does not answer promptly must not stall it. A
-		// timeout leaves the caller unprivileged, which only disables controls.
-		ctx, cancel := context.WithTimeout(context.Background(), probeTimeout)
-		conn, err := dialPipe(ctx, path)
-		cancel()
-		if err != nil {
-			continue
-		}
-
-		owned := ipcauth.PipeOwnedBySelf(conn)
-		if cerr := conn.Close(); cerr != nil {
-			log.Debugf("close daemon pipe %s after ownership check: %v", path, cerr)
-		}
-		return owned
-	}
-
-	return false
-}

client/internal/daemonaddr/pipe.go

@@ -1,103 +0,0 @@
-package daemonaddr
-
-import (
-	"context"
-	"net"
-	"runtime"
-	"strings"
-
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/credentials/insecure"
-)
-
-const (
-	// WindowsPipeAddr is the default daemon address on Windows. A named pipe
-	// carries the connecting process's token, which loopback TCP does not, so
-	// it is the only Windows transport on which the daemon can tell who is
-	// calling it.
-	WindowsPipeAddr = "npipe://netbird"
-
-	// legacyWindowsAddr is the loopback-TCP address the Windows daemon used
-	// before named-pipe support.
-	legacyWindowsAddr = "tcp://127.0.0.1:41731"
-
-	pipeScheme = "npipe://"
-
-	// protectedPrefix is the NPFS namespace in which only LocalSystem and
-	// members of BUILTIN\Administrators may create a pipe. A daemon running as
-	// the service account creates its pipe there so that an unprivileged process
-	// cannot pre-create the name, which would keep the daemon from starting and
-	// leave callers talking to the squatter. Opening such a pipe needs no
-	// privilege, so unprivileged clients still reach the daemon.
-	protectedPrefix = `ProtectedPrefix\Administrators\`
-)
-
-// DialTarget returns the gRPC dial target and transport options for a daemon
-// address. The npipe scheme needs a context dialer because gRPC has no
-// named-pipe resolver; unix and tcp are handled by gRPC itself.
-func DialTarget(addr string) (string, []grpc.DialOption) {
-	opts := []grpc.DialOption{grpc.WithTransportCredentials(insecure.NewCredentials())}
-
-	if name, ok := strings.CutPrefix(addr, pipeScheme); ok {
-		paths := PipePaths(name)
-		opts = append(opts, grpc.WithContextDialer(func(ctx context.Context, _ string) (net.Conn, error) {
-			return dialPipePaths(ctx, paths)
-		}))
-		return "passthrough:///netbird-daemon-pipe", opts
-	}
-
-	return strings.TrimPrefix(addr, "tcp://"), opts
-}
-
-// PipePath maps an npipe address name ("netbird", from "npipe://netbird") to a
-// Windows named-pipe path (\\.\pipe\netbird). A fully qualified path is left as
-// is.
-func PipePath(name string) string {
-	if strings.HasPrefix(name, `\\`) {
-		return name
-	}
-	return `\\.\pipe\` + name
-}
-
-// PipePaths returns the paths a daemon control pipe may live at for an npipe
-// address name, in the order both sides must try them: the protected name first,
-// then the plain one.
-//
-// The daemon serves the first it can create, which is the protected name when it
-// runs as the service account and the plain one when it runs as an ordinary user,
-// as it does in netstack mode. Clients therefore have to try both, and because a
-// client cannot tell from the name alone who created the pipe, the plain name is
-// only usable once the server's identity has been checked: see
-// verifyPipeServer.
-//
-// A fully qualified path is what the operator asked for and is used as is.
-func PipePaths(name string) []string {
-	if strings.HasPrefix(name, `\\`) {
-		return []string{name}
-	}
-	return []string{PipePath(protectedPrefix + name), PipePath(name)}
-}
-
-// IsProtectedPipePath reports whether a pipe path is in the namespace only an
-// administrator or LocalSystem can create in, which is what lets a client trust
-// such a pipe from its name alone.
-func IsProtectedPipePath(path string) bool {
-	return strings.HasPrefix(path, `\\.\pipe\`+protectedPrefix)
-}
-
-// MigrateLegacy upgrades the pre-named-pipe Windows daemon address to the named
-// pipe, reporting whether it rewrote the address. Existing installs persist the
-// daemon address, so without this an upgraded daemon would keep listening on
-// loopback TCP, where callers carry no identity and privileged operations would
-// have to be refused for everyone. Only the exact legacy default is rewritten:
-// a deliberately chosen custom address is left alone.
-func MigrateLegacy(addr string) (string, bool) {
-	return migrateLegacyForOS(runtime.GOOS, addr)
-}
-
-func migrateLegacyForOS(goos, addr string) (string, bool) {
-	if goos == "windows" && addr == legacyWindowsAddr {
-		return WindowsPipeAddr, true
-	}
-	return addr, false
-}

client/internal/daemonaddr/pipe_other.go

@@ -1,15 +0,0 @@
-//go:build !windows
-
-package daemonaddr
-
-import (
-	"context"
-	"fmt"
-	"net"
-)
-
-// dialPipePaths is Windows-only: no other platform serves the daemon on a named
-// pipe.
-func dialPipePaths(context.Context, []string) (net.Conn, error) {
-	return nil, fmt.Errorf("named pipes are only supported on Windows")
-}

client/internal/daemonaddr/pipe_test.go

@@ -1,30 +0,0 @@
-package daemonaddr
-
-import (
-	"slices"
-	"testing"
-)
-
-// The protected name must be tried before the plain one on both sides: it is the
-// one an unprivileged process cannot create, so preferring it is what keeps a
-// squatter from owning the name the service daemon would otherwise use.
-func TestPipePaths_PrefersTheProtectedName(t *testing.T) {
-	got := PipePaths("netbird")
-	want := []string{
-		`\\.\pipe\ProtectedPrefix\Administrators\netbird`,
-		`\\.\pipe\netbird`,
-	}
-	if !slices.Equal(got, want) {
-		t.Errorf("PipePaths = %q, want %q", got, want)
-	}
-}
-
-// An operator who passes a full path chose exactly one pipe, so neither side may
-// look anywhere else.
-func TestPipePaths_QualifiedPathIsUsedAsIs(t *testing.T) {
-	path := `\\.\pipe\custom-netbird`
-	got := PipePaths(path)
-	if !slices.Equal(got, []string{path}) {
-		t.Errorf("PipePaths = %q, want just %q", got, path)
-	}
-}

client/internal/daemonaddr/pipe_windows.go

@@ -1,59 +0,0 @@
-//go:build windows
-
-package daemonaddr
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"net"
-
-	"github.com/Microsoft/go-winio"
-	log "github.com/sirupsen/logrus"
-	"golang.org/x/sys/windows"
-
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-)
-
-// dialPipePaths connects to the first path that answers with a pipe server this
-// client may trust, and returns the last error when none does.
-func dialPipePaths(ctx context.Context, paths []string) (net.Conn, error) {
-	var lastErr error
-	for _, path := range paths {
-		conn, err := dialPipe(ctx, path)
-		if err != nil {
-			log.Debugf("dial daemon pipe %s: %v", path, err)
-			lastErr = err
-			continue
-		}
-
-		// A pipe in the protected namespace could only have been created by an
-		// administrator or LocalSystem, so its name is the guarantee. Any other
-		// name has to be checked, because any local user can create one.
-		if !IsProtectedPipePath(path) {
-			if err := ipcauth.PipeServerTrusted(conn); err != nil {
-				if closeErr := conn.Close(); closeErr != nil {
-					log.Debugf("close untrusted pipe %s: %v", path, closeErr)
-				}
-				lastErr = fmt.Errorf("%s: %w", path, err)
-				continue
-			}
-		}
-
-		return conn, nil
-	}
-
-	if lastErr == nil {
-		lastErr = errors.New("no daemon pipe to connect to")
-	}
-	return nil, lastErr
-}
-
-// dialPipe connects to the daemon control pipe at SECURITY_IDENTIFICATION.
-// winio's plain DialPipe connects at SECURITY_ANONYMOUS, under which the daemon
-// cannot read the caller's token at all. Identification lets the daemon read the
-// caller's SID and groups without granting it the ability to act as the caller.
-func dialPipe(ctx context.Context, path string) (net.Conn, error) {
-	access := uint32(windows.GENERIC_READ | windows.GENERIC_WRITE)
-	return winio.DialPipeAccessImpLevel(ctx, path, access, winio.PipeImpLevelIdentification)
-}

client/internal/daemonaddr/resolve_pipe_other.go

@@ -1,9 +0,0 @@
-//go:build !windows
-
-package daemonaddr
-
-// ResolveDaemonAddr is a no-op off Windows, where there is no named-pipe
-// default to fall back from.
-func ResolveDaemonAddr(addr string) string {
-	return addr
-}

client/internal/daemonaddr/resolve_pipe_windows.go

@@ -1,82 +0,0 @@
-//go:build windows
-
-package daemonaddr
-
-import (
-	"net"
-	"strings"
-	"time"
-
-	"github.com/Microsoft/go-winio"
-	log "github.com/sirupsen/logrus"
-)
-
-// probeTimeout bounds each transport probe. Both are local, so a daemon that is
-// listening answers immediately and one that is not fails immediately.
-const probeTimeout = 300 * time.Millisecond
-
-// ResolveDaemonAddr keeps a client on the named pipe and never silently moves it
-// off. When the pipe does not answer it checks the legacy loopback TCP address, so
-// a client meeting a daemon that has not restarted since the upgrade can say what
-// is wrong, but it does not connect there.
-//
-// Using that address automatically would be a downgrade the user never asked for:
-// any local process can bind 127.0.0.1 while the daemon is not listening, and the
-// transport carries no caller identity, so a client that accepted whatever answered
-// would hand a setup key, a pre-shared key or an SSO prompt to a local impostor. An
-// operator who needs the legacy address during the upgrade window can still pass
-// --daemon-addr explicitly, which is a deliberate choice and still refuses the
-// privileged operations.
-//
-// Only the pipe address is resolved. A custom address is left alone, though passing
-// --daemon-addr npipe://netbird explicitly is indistinguishable from the default
-// here, so it is treated the same way.
-func ResolveDaemonAddr(addr string) string {
-	if addr != WindowsPipeAddr {
-		return addr
-	}
-
-	for _, path := range PipePaths("netbird") {
-		if pipeAvailable(path) {
-			return addr
-		}
-	}
-
-	if tcpAvailable(legacyWindowsAddr) {
-		log.Warnf("the daemon is not serving %s, but something is listening on the legacy %s. "+
-			"Restart the NetBird service so it serves the pipe. That address is not used automatically: "+
-			"any local user can bind it and it carries no caller identity, so pass --daemon-addr %s "+
-			"explicitly if you accept that",
-			WindowsPipeAddr, legacyWindowsAddr, legacyWindowsAddr)
-	}
-
-	return addr
-}
-
-func pipeAvailable(path string) bool {
-	timeout := probeTimeout
-	conn, err := winio.DialPipe(path, &timeout)
-	if err != nil {
-		return false
-	}
-	if err := conn.Close(); err != nil {
-		log.Debugf("close daemon pipe probe: %v", err)
-	}
-	return true
-}
-
-func tcpAvailable(addr string) bool {
-	host := addr
-	if _, after, ok := strings.Cut(addr, "://"); ok {
-		host = after
-	}
-
-	conn, err := net.DialTimeout("tcp", host, probeTimeout)
-	if err != nil {
-		return false
-	}
-	if err := conn.Close(); err != nil {
-		log.Debugf("close daemon TCP probe: %v", err)
-	}
-	return true
-}

client/internal/engine.go

@@ -50,6 +50,7 @@ import (
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
 	"github.com/netbirdio/netbird/client/internal/portforward"
+	"github.com/netbirdio/netbird/client/internal/pqkem"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/relay"
 	"github.com/netbirdio/netbird/client/internal/rosenpass"
@@ -197,6 +198,10 @@ type Engine struct {
 	// rpManager is a Rosenpass manager
 	rpManager *rosenpass.Manager
 
+	// pqkemManager runs the ML-KEM post-quantum PSK exchange (gated by NB_ENABLE_PQ_MLKEM).
+	// It owns the data-path transport and peer endpoint routing.
+	pqkemManager *pqkem.Manager
+
 	// syncMsgMux is used to guarantee sequential Management Service message processing
 	syncMsgMux *sync.Mutex
 
@@ -651,6 +656,30 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		e.rpManager.SetInterface(e.wgInterface)
 	}
 
+	// Start the ML-KEM PQ manager after the interface is up so its dedicated UDP
+	// transport can bind on the WG overlay IP.
+	if pqkem.Enabled() {
+		tr, pqErr := newPQTransport(e.config.WgAddr.IP)
+		if pqErr != nil {
+			log.Errorf("pqkem: transport bind failed, exchange disabled: %v", pqErr)
+		} else {
+			cbHandler := pqCallbackHandler{
+				wg: e.wgInterface,
+				// On a persistent rekey failure, re-bootstrap the KEM over Signal: a
+				// fresh signalling offer starts a new exchange that overwrites the
+				// stalled PSK on both sides, recovering from a data-path desync.
+				reoffer: func(remoteKey string) {
+					if conn, ok := e.peerStore.PeerConn(remoteKey); ok {
+						conn.RequestReoffer()
+					}
+				},
+			}
+			e.pqkemManager = pqkem.NewManager(pqkem.LocalID(publicKey.String()), cbHandler, pqkem.NewLogger())
+			e.pqkemManager.Start(tr)
+			log.Infof("pqkem: enabled (udp port %d on overlay %s)", e.pqkemManager.LocalPort(), e.config.WgAddr.IP)
+		}
+	}
+
 	// if inbound conns are blocked there is no need to create the ACL manager
 	if e.firewall != nil && !e.config.BlockInbound {
 		e.acl = acl.NewDefaultManager(e.firewall)
@@ -914,6 +943,10 @@ func (e *Engine) removePeer(peerKey string) error {
 
 	e.connMgr.RemovePeerConn(peerKey)
 
+	if e.pqkemManager != nil {
+		e.pqkemManager.RemovePeer(pqkem.RemoteID(peerKey))
+	}
+
 	err := e.statusRecorder.RemovePeer(peerKey)
 	if err != nil {
 		log.Warnf("received error when removing peer %s from status recorder: %v", peerKey, err)
@@ -1900,6 +1933,10 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 		},
 		ICEConfig: e.createICEConfig(),
 	}
+	if e.pqkemManager != nil {
+		config.PQ = pqHandshaker{mgr: e.pqkemManager}
+		config.PQStrict = pqkem.Strict()
+	}
 
 	serviceDependencies := peer.ServiceDependencies{
 		StatusRecorder:     e.statusRecorder,
@@ -2083,6 +2120,10 @@ func (e *Engine) close() {
 		_ = e.rpManager.Close()
 	}
 
+	if e.pqkemManager != nil {
+		e.pqkemManager.Stop()
+	}
+
 	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 	defer cancel()
 	if err := e.portForwardManager.GracefullyStop(ctx); err != nil {
@@ -2895,6 +2936,8 @@ func convertToOfferAnswer(msg *sProto.Message) (*peer.OfferAnswer, error) {
 		Version:         msg.GetBody().GetNetBirdVersion(),
 		RosenpassPubKey: rosenpassPubKey,
 		RosenpassAddr:   rosenpassAddr,
+		MlkemPayload:    msg.GetBody().GetMlkemPayload(),
+		MlkemPort:       int(msg.GetBody().GetMlkemPort()),
 		RelaySrvAddress: msg.GetBody().GetRelayServerAddress(),
 		RelaySrvIP:      relayIP,
 		SessionID:       sessionID,

client/internal/ipcauth/creds_stub.go

@@ -1,31 +0,0 @@
-//go:build !linux && !darwin && !freebsd && !windows
-
-package ipcauth
-
-import (
-	"errors"
-	"net"
-
-	"google.golang.org/grpc/credentials"
-)
-
-// errUnsupported is returned on platforms with no local peer-identity
-// primitive, so consumers fail closed instead of guessing an identity.
-var errUnsupported = errors.New("peer identity is not available on this platform")
-
-// NewTransportCredentials returns nil: without a peer-identity primitive the
-// daemon cannot authenticate local callers, and the caller must treat that as
-// "authorization cannot be enforced".
-func NewTransportCredentials() credentials.TransportCredentials {
-	return nil
-}
-
-// PeerIdentity always fails on this platform.
-func PeerIdentity(net.Conn) (Identity, error) {
-	return Identity{}, errUnsupported
-}
-
-// ConnIdentity always fails on this platform.
-func ConnIdentity(net.Conn) (Identity, error) {
-	return Identity{}, errUnsupported
-}

client/internal/ipcauth/creds_unix.go

@@ -1,56 +0,0 @@
-//go:build linux || darwin || freebsd
-
-package ipcauth
-
-import (
-	"context"
-	"net"
-
-	"google.golang.org/grpc/credentials"
-)
-
-// NewTransportCredentials returns gRPC transport credentials that expose the
-// caller's kernel-authenticated identity via IdentityFromContext. It returns
-// nil on platforms that have no peer-identity primitive, which the caller must
-// treat as "authorization cannot be enforced".
-//
-// The handshake exchanges no bytes on the wire, so a client dialing with
-// insecure credentials interoperates with a server using these. That keeps
-// older CLI and UI binaries working against an upgraded daemon.
-func NewTransportCredentials() credentials.TransportCredentials {
-	return unixCreds{}
-}
-
-// ConnIdentity extracts the caller's identity from an accepted local IPC
-// connection. It is shared by the gRPC transport credentials and by the JSON
-// gateway, which reads the identity of its own HTTP clients.
-func ConnIdentity(conn net.Conn) (Identity, error) {
-	return PeerIdentity(conn)
-}
-
-type unixCreds struct{}
-
-func (unixCreds) ClientHandshake(_ context.Context, _ string, conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
-	return conn, AuthInfo{}, nil
-}
-
-// ServerHandshake extracts the peer identity and fails closed when it cannot
-// be read, so a connection whose caller is unknown never reaches a handler.
-func (unixCreds) ServerHandshake(conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
-	id, err := ConnIdentity(conn)
-	if err != nil {
-		return nil, nil, err
-	}
-	return conn, AuthInfo{
-		CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
-		Identity:       id,
-	}, nil
-}
-
-func (unixCreds) Info() credentials.ProtocolInfo {
-	return credentials.ProtocolInfo{SecurityProtocol: AuthInfo{}.AuthType()}
-}
-
-func (unixCreds) Clone() credentials.TransportCredentials { return unixCreds{} }
-
-func (unixCreds) OverrideServerName(string) error { return nil }

client/internal/ipcauth/creds_windows.go

@@ -1,194 +0,0 @@
-//go:build windows
-
-package ipcauth
-
-import (
-	"context"
-	"fmt"
-	"net"
-	"runtime"
-
-	log "github.com/sirupsen/logrus"
-	"golang.org/x/sys/windows"
-	"google.golang.org/grpc/credentials"
-)
-
-var (
-	modadvapi32                    = windows.NewLazySystemDLL("advapi32.dll")
-	procImpersonateNamedPipeClient = modadvapi32.NewProc("ImpersonateNamedPipeClient")
-)
-
-// DefaultPipeSDDL is the security descriptor for the daemon control pipe.
-//
-//	D:P          protected DACL, no inheritance
-//	(A;;GA;;;SY) allow GENERIC_ALL to LocalSystem (the daemon's service account)
-//	(A;;GA;;;WD) allow GENERIC_ALL to Everyone
-//
-// Any local caller may connect, as with a Unix socket at 0666; what a caller may
-// actually do is decided from its token, not from the DACL. Remote callers are not
-// a concern here: winio.ListenPipe creates the pipe with
-// FILE_PIPE_REJECT_REMOTE_CLIENTS, so NPFS rejects connections from other machines
-// before the descriptor is consulted.
-//
-// A deny ACE on the NETWORK SID would not add anything and would break callers:
-// that SID is present in any network-logon token, which includes OpenSSH and WinRM
-// sessions, so it denies administrators driving the CLI over SSH and denies the
-// daemon itself when started from such a session.
-func DefaultPipeSDDL() string {
-	return "D:P(A;;GA;;;SY)(A;;GA;;;WD)"
-}
-
-// NewTransportCredentials returns gRPC transport credentials that derive the
-// caller's identity from the named-pipe client token.
-//
-// The client must connect at SECURITY_IDENTIFICATION for the daemon to be able
-// to read its token, which is what DialNamedPipe does.
-func NewTransportCredentials() credentials.TransportCredentials {
-	return winpipeCreds{}
-}
-
-// ConnIdentity extracts the caller's identity from an accepted named-pipe
-// connection by impersonating the pipe client and reading its token. It is
-// shared by the gRPC transport credentials and by the JSON gateway, which
-// reads the identity of its own HTTP clients.
-func ConnIdentity(conn net.Conn) (Identity, error) {
-	// go-winio's pipe connection embeds *win32File, which exposes Fd().
-	fdConn, ok := conn.(interface{ Fd() uintptr })
-	if !ok {
-		return Identity{}, fmt.Errorf("connection %T does not expose a pipe handle", conn)
-	}
-	return pipeClientIdentity(windows.Handle(fdConn.Fd()))
-}
-
-type winpipeCreds struct{}
-
-func (winpipeCreds) ClientHandshake(_ context.Context, _ string, conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
-	return conn, AuthInfo{}, nil
-}
-
-// ServerHandshake extracts the connecting client's identity and fails closed
-// when the handle or token cannot be read, so a connection whose caller is
-// unknown never reaches a handler.
-func (winpipeCreds) ServerHandshake(conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
-	id, err := ConnIdentity(conn)
-	if err != nil {
-		return nil, nil, err
-	}
-	return conn, AuthInfo{
-		CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
-		Identity:       id,
-	}, nil
-}
-
-func (winpipeCreds) Info() credentials.ProtocolInfo {
-	return credentials.ProtocolInfo{SecurityProtocol: AuthInfo{}.AuthType()}
-}
-
-func (winpipeCreds) Clone() credentials.TransportCredentials { return winpipeCreds{} }
-
-func (winpipeCreds) OverrideServerName(string) error { return nil }
-
-// pipeClientIdentity reads the connecting client's user SID, usable group
-// SIDs, and elevation state by impersonating the pipe client on this thread
-// and reading the resulting impersonation token.
-func pipeClientIdentity(handle windows.Handle) (id Identity, err error) {
-	// Impersonation is per-thread, so the goroutine must stay on this thread
-	// until RevertToSelf, otherwise an unrelated goroutine could inherit the
-	// impersonated context.
-	runtime.LockOSThread()
-
-	// The thread only goes back to the runtime's pool once it is provably no
-	// longer impersonating the client. If the revert fails, leaving it locked
-	// makes Go terminate it when this goroutine exits, which costs one thread
-	// and keeps a thread running as the client from ever being reused.
-	clean := false
-	defer func() {
-		if clean {
-			runtime.UnlockOSThread()
-		}
-	}()
-
-	if err = impersonateNamedPipeClient(handle); err != nil {
-		clean = true
-		return Identity{}, fmt.Errorf("impersonate named pipe client: %w", err)
-	}
-	defer func() {
-		// Surface the revert failure only when nothing else failed: leaving
-		// the thread impersonated is worse than the original error.
-		revErr := windows.RevertToSelf()
-		if revErr != nil {
-			if err == nil {
-				err = fmt.Errorf("revert impersonation: %w", revErr)
-			}
-			return
-		}
-		clean = true
-	}()
-
-	// openAsSelf=true opens the token with the daemon's own process context
-	// rather than the impersonated client's, so the open cannot fail because
-	// the client lacks access to its own token.
-	var token windows.Token
-	if err = windows.OpenThreadToken(windows.CurrentThread(), windows.TOKEN_QUERY, true, &token); err != nil {
-		return Identity{}, fmt.Errorf("open thread token: %w", err)
-	}
-	defer func() {
-		if cerr := token.Close(); cerr != nil {
-			log.Debugf("close client token: %v", cerr)
-		}
-	}()
-
-	return identityFromToken(token)
-}
-
-// identityFromToken reads the user SID, usable group SIDs and elevation state
-// out of a Windows token.
-func identityFromToken(token windows.Token) (Identity, error) {
-	user, err := token.GetTokenUser()
-	if err != nil {
-		return Identity{}, fmt.Errorf("read token user: %w", err)
-	}
-
-	groups, err := tokenGroupSIDs(token)
-	if err != nil {
-		return Identity{}, err
-	}
-
-	return Identity{
-		SID:      user.User.Sid.String(),
-		Groups:   groups,
-		Elevated: token.IsElevated(),
-	}, nil
-}
-
-// tokenGroupSIDs returns the SIDs of the groups the token can actually
-// exercise. Groups that are disabled or marked deny-only are skipped: a
-// UAC-filtered administrator carries BUILTIN\Administrators as deny-only, and
-// treating that as membership would hand every admin account privilege it
-// cannot currently use.
-func tokenGroupSIDs(token windows.Token) ([]string, error) {
-	tg, err := token.GetTokenGroups()
-	if err != nil {
-		return nil, fmt.Errorf("read token groups: %w", err)
-	}
-
-	var sids []string
-	for _, g := range tg.AllGroups() {
-		if g.Attributes&windows.SE_GROUP_ENABLED == 0 {
-			continue
-		}
-		if g.Attributes&windows.SE_GROUP_USE_FOR_DENY_ONLY != 0 {
-			continue
-		}
-		sids = append(sids, g.Sid.String())
-	}
-	return sids, nil
-}
-
-func impersonateNamedPipeClient(h windows.Handle) error {
-	r, _, e := procImpersonateNamedPipeClient.Call(uintptr(h))
-	if r == 0 {
-		return e
-	}
-	return nil
-}

client/internal/ipcauth/forward.go

@@ -1,272 +0,0 @@
-package ipcauth
-
-import (
-	"context"
-	"crypto/rand"
-	"crypto/subtle"
-	"encoding/hex"
-	"fmt"
-	"slices"
-	"strconv"
-	"strings"
-
-	"google.golang.org/grpc/metadata"
-)
-
-// Metadata keys the local JSON gateway uses to forward the identity of its own
-// HTTP client to the daemon. The gateway runs inside the daemon process and
-// re-dials the daemon over the control socket, so without forwarding every
-// JSON request would appear to come from the daemon itself.
-const (
-	// mdFwd marks a request as forwarded by the JSON gateway. It is always
-	// set, even when the gateway could not read its client's identity, so the
-	// daemon can tell "no identity available" apart from "not forwarded".
-	mdFwd         = "x-netbird-fwd"
-	mdFwdUID      = "x-netbird-fwd-uid"      // Unix user ID
-	mdFwdGID      = "x-netbird-fwd-gid"      // Unix primary group ID
-	mdFwdSID      = "x-netbird-fwd-sid"      // Windows user SID
-	mdFwdGroup    = "x-netbird-fwd-group"    // Windows group SID, repeated
-	mdFwdElevated = "x-netbird-fwd-elevated" // Windows, "1" when elevated
-
-	// mdFwdProof proves the forwarded identity was stamped by this process. The
-	// gateway runs inside the daemon, so a secret held in memory is available to
-	// the only legitimate producer and to nothing else.
-	mdFwdProof = "x-netbird-fwd-proof"
-)
-
-// forwardKeys is every metadata key the gateway sets. An HTTP client must never
-// be able to supply one itself: see IsReservedForwardKey.
-var forwardKeys = []string{mdFwd, mdFwdUID, mdFwdGID, mdFwdSID, mdFwdGroup, mdFwdElevated, mdFwdProof}
-
-// forwardProof authenticates the gateway's forwarding metadata. It is generated
-// once per daemon process and never leaves it: it is not written to disk, not
-// logged, and not sent anywhere except over the daemon's own control socket to
-// itself.
-//
-// Without it, trusting a forwarded identity rests on every layer in front of it
-// stripping incoming forwarding keys, and on each key's value shape being
-// distinguishable from an injected one. A single injected group SID or an
-// injected "elevated" flag has the same shape as a legitimate one, so no
-// cardinality rule can catch it. Requiring the proof means metadata that did not
-// come from this process is refused whatever it contains.
-var forwardProof = mustForwardProof()
-
-func mustForwardProof() string {
-	var buf [32]byte
-	if _, err := rand.Read(buf[:]); err != nil {
-		// Continuing would leave the forwarded path authenticated by a
-		// predictable value, which is worse than not starting.
-		panic(fmt.Sprintf("generate identity forwarding proof: %v", err))
-	}
-	return hex.EncodeToString(buf[:])
-}
-
-// IsReservedForwardKey reports whether a gRPC metadata key belongs to the
-// gateway's identity forwarding, and therefore must be dropped when it arrives
-// from outside.
-//
-// grpc-gateway maps "Grpc-Metadata-<key>" request headers into gRPC metadata and
-// joins them ahead of the values its own annotators add. Without dropping these,
-// an HTTP client could hand the daemon "x-netbird-fwd-uid: 0" and be believed,
-// because the daemon trusts forwarded metadata when the transport peer is the
-// (privileged) gateway.
-func IsReservedForwardKey(key string) bool {
-	key = strings.ToLower(key)
-	return slices.Contains(forwardKeys, key)
-}
-
-// ForwardIdentityMetadata encodes an HTTP client's identity for the JSON
-// gateway to forward to the daemon. When known is false only the marker is
-// set, which makes the daemon treat the caller as unidentified rather than as
-// the daemon itself.
-func ForwardIdentityMetadata(id Identity, known bool) metadata.MD {
-	md := metadata.MD{}
-	md.Set(mdFwd, "1")
-	md.Set(mdFwdProof, forwardProof)
-	if !known {
-		return md
-	}
-
-	if id.IsWindows() {
-		md.Set(mdFwdSID, id.SID)
-		if len(id.Groups) > 0 {
-			md.Set(mdFwdGroup, id.Groups...)
-		}
-		if id.Elevated {
-			md.Set(mdFwdElevated, "1")
-		}
-		return md
-	}
-
-	md.Set(mdFwdUID, strconv.FormatUint(uint64(id.UID), 10))
-	md.Set(mdFwdGID, strconv.FormatUint(uint64(id.GID), 10))
-	return md
-}
-
-// CallerIdentity returns the identity to authorize a request against. For a
-// direct connection that is the transport peer's kernel identity. For a
-// request relayed by the local JSON gateway it is the identity the gateway
-// forwarded, since the transport peer is then the daemon itself.
-//
-// A forwarded identity is only honoured when the transport peer is the daemon's
-// own identity and the metadata carries this process's forwarding proof, so
-// forged forwarding metadata gains a caller nothing. A forwarded request that
-// carries no identity is reported as unidentified, never as the daemon.
-//
-// The second return value is false when no identity could be established, and
-// callers MUST fail closed in that case.
-func CallerIdentity(ctx context.Context) (Identity, bool) {
-	id, ok := IdentityFromContext(ctx)
-	if !ok {
-		return Identity{}, false
-	}
-
-	// A forwarding key that arrives more than once did not come from the gateway
-	// alone, so nothing about the request can be trusted to describe its caller.
-	// Refusing outright matters because the alternative reading, "not forwarded",
-	// would authorize the request as the transport peer, which on the gateway's
-	// connection is the daemon itself.
-	if duplicatedForwardKey(ctx) {
-		return Identity{}, false
-	}
-
-	forwarded := isForwarded(ctx)
-
-	// Our own process on the other end of the socket is the JSON gateway, the only
-	// thing that dials the daemon from inside it. Such a call must carry a
-	// forwarded identity; without one there is no caller to authorize, and
-	// treating it as the daemon would authorize whatever reached the JSON socket.
-	// Only Linux reports the peer PID, so this is a belt on top of the gateway's
-	// interceptor rather than the sole guarantee.
-	if id.PID != 0 && int(id.PID) == selfPID && !forwarded {
-		return Identity{}, false
-	}
-
-	// Only the gateway's own connection may speak for someone else. Being
-	// privileged is not enough and not the point: the gateway runs inside the
-	// daemon, so it dials as the daemon's identity whatever user that is, which
-	// also covers a rootless container.
-	if !forwarded || !IsDaemonSelf(id) {
-		return id, true
-	}
-
-	// Speaking for someone else additionally requires the proof only this process
-	// holds. Refusing is the only safe reading: the transport peer here is the
-	// daemon itself, so falling back to it would authorize the request as the
-	// daemon. This is also what makes the forwarded values trustworthy once
-	// accepted, so they need no shape checks of their own.
-	if !authenticForward(ctx) {
-		return Identity{}, false
-	}
-
-	return forwardedIdentity(ctx)
-}
-
-// duplicatedForwardKey reports whether any forwarding key carries more than one
-// value. The gateway's interceptor sets each key exactly once and replaces what
-// was already there, so a repeat means a second source supplied it.
-func duplicatedForwardKey(ctx context.Context) bool {
-	md, ok := metadata.FromIncomingContext(ctx)
-	if !ok {
-		return false
-	}
-	for _, key := range forwardKeys {
-		// Group SIDs are legitimately repeated; the rest identify the caller.
-		if key == mdFwdGroup {
-			continue
-		}
-		if len(md.Get(key)) > 1 {
-			return true
-		}
-	}
-	return false
-}
-
-// authenticForward reports whether the request carries this process's forwarding
-// proof, which only the in-process JSON gateway can supply.
-func authenticForward(ctx context.Context) bool {
-	md, ok := metadata.FromIncomingContext(ctx)
-	if !ok {
-		return false
-	}
-	got := mdSingle(md, mdFwdProof)
-	return subtle.ConstantTimeCompare([]byte(got), []byte(forwardProof)) == 1
-}
-
-// isForwarded reports whether the request carries the JSON gateway marker.
-func isForwarded(ctx context.Context) bool {
-	md, ok := metadata.FromIncomingContext(ctx)
-	if !ok {
-		return false
-	}
-	return mdSingle(md, mdFwd) != ""
-}
-
-// forwardedIdentity decodes the identity the JSON gateway attached.
-func forwardedIdentity(ctx context.Context) (Identity, bool) {
-	md, ok := metadata.FromIncomingContext(ctx)
-	if !ok {
-		return Identity{}, false
-	}
-
-	if sid := mdSingle(md, mdFwdSID); sid != "" {
-		return Identity{
-			SID: sid,
-			// Repeated by design, one value per group, and only reachable once
-			// the forwarding proof has been verified.
-			Groups:   md.Get(mdFwdGroup),
-			Elevated: mdSingle(md, mdFwdElevated) == "1",
-		}, true
-	}
-
-	uid, err := strconv.ParseUint(mdSingle(md, mdFwdUID), 10, 32)
-	if err != nil {
-		return Identity{}, false
-	}
-
-	id := Identity{UID: uint32(uid)}
-	if gid, err := strconv.ParseUint(mdSingle(md, mdFwdGID), 10, 32); err == nil {
-		id.GID = uint32(gid)
-	}
-	return id, true
-}
-
-// mdSingle returns the value of a forwarded key only when exactly one was
-// supplied. The gateway's interceptor sets each key exactly once, so more than one
-// value means something else also supplied it, and the whole identity is treated as
-// unknown rather than picking a winner. Defence in depth behind the gateway's
-// header filter.
-func mdSingle(md metadata.MD, key string) string {
-	if v := md.Get(key); len(v) == 1 {
-		return v[0]
-	}
-	return ""
-}
-
-// WithForwardedIdentity stamps id onto a context's outgoing metadata for the JSON
-// gateway's call to the daemon, replacing any forwarding keys already present so
-// values supplied from outside cannot survive alongside it.
-//
-// This is deliberately not done with runtime.WithMetadata: grpc-gateway skips its
-// annotators entirely when no request header maps to metadata ("if len(pairs) == 0
-// { return ctx, nil, nil }", runtime/context.go), which an HTTP/1.0 request with no
-// Host header over a unix socket achieves. The daemon would then see an unmarked
-// call whose transport peer is the daemon's own identity, and authorize it as the
-// daemon. A client interceptor runs for every RPC regardless of headers.
-func WithForwardedIdentity(ctx context.Context, id Identity, known bool) context.Context {
-	md, ok := metadata.FromOutgoingContext(ctx)
-	if !ok {
-		md = metadata.MD{}
-	} else {
-		md = md.Copy()
-	}
-
-	for _, key := range forwardKeys {
-		delete(md, key)
-	}
-	for key, values := range ForwardIdentityMetadata(id, known) {
-		md[key] = values
-	}
-
-	return metadata.NewOutgoingContext(ctx, md)
-}

client/internal/ipcauth/forward_test.go

@@ -1,214 +0,0 @@
-package ipcauth
-
-import (
-	"context"
-	"testing"
-
-	"google.golang.org/grpc/credentials"
-	"google.golang.org/grpc/metadata"
-	"google.golang.org/grpc/peer"
-)
-
-// transportCtx builds a request context as the daemon's transport credentials
-// would: the identity of whoever opened the socket, plus whatever metadata the
-// request carried.
-func transportCtx(id Identity, md metadata.MD) context.Context {
-	ctx := peer.NewContext(context.Background(), &peer.Peer{
-		AuthInfo: AuthInfo{
-			CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
-			Identity:       id,
-		},
-	})
-	if md != nil {
-		ctx = metadata.NewIncomingContext(ctx, md)
-	}
-	return ctx
-}
-
-var (
-	root       = Identity{UID: 0}
-	unprivUser = Identity{UID: 1000, GID: 1000}
-)
-
-// asDaemon pins which identity counts as this process for the duration of a test.
-// Without it the test binary's own uid decides, which silently changes what
-// "the gateway" means.
-func asDaemon(t *testing.T, id Identity) {
-	t.Helper()
-	prevID, prevKnown, prevDelegate := selfIdentity, selfKnown, selfMayDelegate
-	t.Cleanup(func() { selfIdentity, selfKnown, selfMayDelegate = prevID, prevKnown, prevDelegate })
-	selfIdentity, selfKnown = id, true
-	selfMayDelegate = !id.IsPrivileged()
-}
-
-func TestCallerIdentity_DirectConnections(t *testing.T) {
-	t.Run("no transport credentials is not an identity", func(t *testing.T) {
-		if _, ok := CallerIdentity(context.Background()); ok {
-			t.Fatal("a caller with no credentials must not be identified")
-		}
-	})
-
-	t.Run("a direct caller is its transport identity", func(t *testing.T) {
-		id, ok := CallerIdentity(transportCtx(unprivUser, nil))
-		if !ok || id.UID != 1000 {
-			t.Fatalf("got %v ok=%t, want uid 1000", id, ok)
-		}
-	})
-
-	// The whole point of honouring forwarded metadata only from a privileged
-	// transport peer: an unprivileged caller can set any metadata it likes on its
-	// own connection to the daemon socket.
-	t.Run("an unprivileged caller cannot forge an identity", func(t *testing.T) {
-		asDaemon(t, root)
-		forged := metadata.Pairs(mdFwd, "1", mdFwdUID, "0", mdFwdGID, "0")
-		id, ok := CallerIdentity(transportCtx(unprivUser, forged))
-		if !ok {
-			t.Fatal("caller should still be identified, as itself")
-		}
-		if id.IsPrivileged() || id.UID != 1000 {
-			t.Fatalf("forged metadata was believed: got %v", id)
-		}
-	})
-}
-
-func TestCallerIdentity_GatewayForwarding(t *testing.T) {
-	t.Run("the gateway's client identity is used, not the gateway's own", func(t *testing.T) {
-		asDaemon(t, root)
-		md := ForwardIdentityMetadata(unprivUser, true)
-		id, ok := CallerIdentity(transportCtx(root, md))
-		if !ok {
-			t.Fatal("forwarded identity should be usable")
-		}
-		if id.IsPrivileged() || id.UID != 1000 {
-			t.Fatalf("got %v, want the forwarded uid 1000 and not privileged", id)
-		}
-	})
-
-	t.Run("a privileged gateway client stays privileged", func(t *testing.T) {
-		asDaemon(t, root)
-		md := ForwardIdentityMetadata(root, true)
-		id, ok := CallerIdentity(transportCtx(root, md))
-		if !ok || !id.IsPrivileged() {
-			t.Fatalf("got %v ok=%t, want a privileged identity", id, ok)
-		}
-	})
-
-	// A JSON socket the gateway cannot read peer credentials from (a TCP socket,
-	// say) must not make every request look like the daemon itself.
-	t.Run("an unreadable client identity is unknown, not the daemon", func(t *testing.T) {
-		asDaemon(t, root)
-		md := ForwardIdentityMetadata(Identity{}, false)
-		if _, ok := CallerIdentity(transportCtx(root, md)); ok {
-			t.Fatal("a forwarded request with no identity must not be identified")
-		}
-	})
-
-	// grpc-gateway turns Grpc-Metadata-<key> headers into gRPC metadata and joins
-	// them ahead of its annotators' values. If an HTTP client's header survived
-	// that, this is the shape the daemon would see: the attacker's uid 0 first,
-	// the real uid second. The gateway filters those headers out, and reading a
-	// duplicated key as unknown makes the daemon safe even if it did not.
-	t.Run("a duplicated key from an injected header is not believed", func(t *testing.T) {
-		asDaemon(t, root)
-		md := metadata.MD{}
-		md.Append(mdFwd, "1")
-		md.Append(mdFwdUID, "0")    // injected by the HTTP client
-		md.Append(mdFwdUID, "1000") // appended by the gateway's annotator
-		if id, ok := CallerIdentity(transportCtx(root, md)); ok {
-			t.Fatalf("injected uid was accepted: got %v", id)
-		}
-	})
-
-	t.Run("a duplicated marker is not believed either", func(t *testing.T) {
-		asDaemon(t, root)
-		md := metadata.MD{}
-		md.Append(mdFwd, "1")
-		md.Append(mdFwd, "1")
-		md.Append(mdFwdUID, "1000")
-		// A repeated marker must not be read as "not forwarded": that would
-		// authorize the request as the transport peer, which on the gateway's
-		// connection is the daemon itself.
-		if id, ok := CallerIdentity(transportCtx(root, md)); ok {
-			t.Fatalf("a duplicated marker was believed: got %v", id)
-		}
-	})
-
-	// The layers in front of this (the gateway's header matcher, and its
-	// interceptor replacing every forwarding key) are what keep outside metadata
-	// from arriving at all. The proof is what the daemon can check for itself, and
-	// it is the only defence that works for a value whose legitimate shape is
-	// indistinguishable from an injected one: a lone group SID, or "elevated".
-	t.Run("forwarding metadata without this process's proof is refused", func(t *testing.T) {
-		asDaemon(t, root)
-		for name, md := range map[string]metadata.MD{
-			"no proof":    metadata.Pairs(mdFwd, "1", mdFwdUID, "0"),
-			"wrong proof": metadata.Pairs(mdFwd, "1", mdFwdUID, "0", mdFwdProof, "deadbeef"),
-			"windows identity without a proof": metadata.Pairs(mdFwd, "1",
-				mdFwdSID, "S-1-5-21-1-2-3-1001", mdFwdGroup, sidAdministrators, mdFwdElevated, "1"),
-		} {
-			t.Run(name, func(t *testing.T) {
-				if id, ok := CallerIdentity(transportCtx(root, md)); ok {
-					t.Fatalf("unstamped forwarding metadata was believed: got %v", id)
-				}
-			})
-		}
-	})
-
-	// A caller that reaches the gateway cannot see the proof, so it cannot append
-	// a group of its own to a genuine forwarded identity: doing so would have to
-	// go through the interceptor, which replaces the whole set.
-	t.Run("a group appended to a stamped identity does not survive the interceptor", func(t *testing.T) {
-		asDaemon(t, root)
-		injected := metadata.MD{}
-		injected.Append(mdFwdGroup, sidAdministrators)
-
-		ctx := WithForwardedIdentity(metadata.NewOutgoingContext(context.Background(), injected),
-			Identity{SID: "S-1-5-21-1-2-3-1001"}, true)
-		out, ok := metadata.FromOutgoingContext(ctx)
-		if !ok {
-			t.Fatal("no outgoing metadata")
-		}
-		if groups := out.Get(mdFwdGroup); len(groups) != 0 {
-			t.Fatalf("injected group survived: %v", groups)
-		}
-	})
-}
-
-func TestIsReservedForwardKey(t *testing.T) {
-	for _, key := range forwardKeys {
-		if !IsReservedForwardKey(key) {
-			t.Errorf("%q must be reserved", key)
-		}
-	}
-
-	// grpc-gateway canonicalises header names, so the check has to be
-	// case-insensitive.
-	if !IsReservedForwardKey("X-Netbird-Fwd-Uid") {
-		t.Error("the check must be case-insensitive")
-	}
-
-	for _, key := range []string{"authorization", "x-netbird", "x-netbird-fwd-uid-extra", ""} {
-		if IsReservedForwardKey(key) {
-			t.Errorf("%q must not be reserved", key)
-		}
-	}
-}
-
-func TestForwardIdentityMetadata_AlwaysMarksForwarded(t *testing.T) {
-	for _, tc := range []struct {
-		name  string
-		id    Identity
-		known bool
-	}{
-		{"known unix identity", unprivUser, true},
-		{"unknown identity", Identity{}, false},
-		{"windows identity", Identity{SID: "S-1-5-21-1-2-3-1001", Elevated: true}, true},
-	} {
-		t.Run(tc.name, func(t *testing.T) {
-			md := ForwardIdentityMetadata(tc.id, tc.known)
-			if got := md.Get(mdFwd); len(got) != 1 || got[0] != "1" {
-				t.Fatalf("marker = %v, want exactly one \"1\"", got)
-			}
-		})
-	}
-}

client/internal/ipcauth/identity.go

@@ -1,127 +0,0 @@
-// Package ipcauth provides the kernel-authenticated identity of a local IPC
-// (gRPC) caller and the transport credentials that surface it into the gRPC
-// context, so the daemon can authorize individual RPCs by caller identity.
-//
-// On Unix the identity is read from the kernel via SO_PEERCRED (Linux) or
-// LOCAL_PEERCRED (Darwin/FreeBSD). On Windows it is derived from the
-// named-pipe client token. Platforms without a peer-identity primitive get no
-// credentials, and every consumer must fail closed when no identity is
-// available.
-package ipcauth
-
-import (
-	"context"
-	"fmt"
-	"slices"
-
-	"google.golang.org/grpc/credentials"
-	"google.golang.org/grpc/peer"
-)
-
-// Well-known Windows SIDs that identify a fully privileged principal.
-const (
-	sidLocalSystem    = "S-1-5-18"     // NT AUTHORITY\SYSTEM
-	sidLocalService   = "S-1-5-19"     // NT AUTHORITY\LOCAL SERVICE
-	sidNetworkService = "S-1-5-20"     // NT AUTHORITY\NETWORK SERVICE
-	sidAdministrators = "S-1-5-32-544" // BUILTIN\Administrators
-)
-
-// Identity is the kernel-authenticated identity of a local IPC caller. The
-// zero value is not a valid identity: consumers must only use one obtained
-// with a true ok/nil error return.
-type Identity struct {
-	// UID and GID are the caller's Unix user ID and primary group ID. Both are
-	// zero on Windows, where SID is authoritative instead.
-	UID uint32
-	GID uint32
-
-	// SID is the caller's Windows security identifier, empty on Unix.
-	SID string
-
-	// Groups holds the caller's Windows group SIDs, captured from the client
-	// token at handshake time. Only groups that are enabled and not
-	// deny-only are captured, so a group listed here is one the caller can
-	// actually exercise. Empty on Unix.
-	Groups []string
-
-	// Elevated reports whether the Windows client token is elevated (running
-	// as administrator, or an administrator with UAC turned off). Always false
-	// on Unix, where privilege is uid 0.
-	Elevated bool
-
-	// PID is the caller's process ID where the platform reports it (Linux's
-	// SO_PEERCRED), and 0 where it does not. It identifies the daemon's own
-	// process dialling itself, which is what the JSON gateway does, and is never
-	// used to grant anything.
-	PID int32
-}
-
-// IsWindows reports whether this identity is a Windows principal (SID-based)
-// rather than a Unix uid/gid principal.
-func (i Identity) IsWindows() bool {
-	return i.SID != ""
-}
-
-// IsPrivileged reports whether the caller is the platform's administrative
-// principal, which is what the daemon requires for changes that cross the
-// user-to-root boundary.
-//
-// On Windows the decision comes from the caller's token rather than from
-// account names or group RIDs: an elevated token, one of the service accounts
-// the daemon itself may run as, or a token with BUILTIN\Administrators
-// enabled. A UAC-filtered administrator has that group marked deny-only, and
-// deny-only groups are dropped when the identity is captured, so such a
-// caller is correctly reported as unprivileged. Domain group memberships
-// (Domain Admins and friends) are deliberately not consulted: they say
-// nothing about what this token may do on this machine.
-func (i Identity) IsPrivileged() bool {
-	if !i.IsWindows() {
-		return i.UID == 0
-	}
-
-	if i.Elevated {
-		return true
-	}
-
-	switch i.SID {
-	case sidLocalSystem, sidLocalService, sidNetworkService:
-		return true
-	}
-
-	return slices.Contains(i.Groups, sidAdministrators)
-}
-
-// String renders the identity for audit logs and denial messages.
-func (i Identity) String() string {
-	if i.IsWindows() {
-		return fmt.Sprintf("sid=%s elevated=%t", i.SID, i.Elevated)
-	}
-	return fmt.Sprintf("uid=%d gid=%d", i.UID, i.GID)
-}
-
-// AuthInfo carries the peer Identity as a gRPC credentials.AuthInfo so
-// handlers can retrieve it from the request context via IdentityFromContext.
-type AuthInfo struct {
-	credentials.CommonAuthInfo
-	Identity Identity
-}
-
-// AuthType identifies the authentication scheme.
-func (AuthInfo) AuthType() string { return "netbird-ipc-peercred" }
-
-// IdentityFromContext extracts the caller's kernel-authenticated identity from
-// the gRPC peer context. The second return value is false when no IPC
-// transport credentials were negotiated, which happens on a TCP daemon socket
-// and on platforms without a peer-identity primitive. Callers MUST fail closed
-// in that case.
-func IdentityFromContext(ctx context.Context) (Identity, bool) {
-	p, ok := peer.FromContext(ctx)
-	if !ok {
-		return Identity{}, false
-	}
-	info, ok := p.AuthInfo.(AuthInfo)
-	if !ok {
-		return Identity{}, false
-	}
-	return info.Identity, true
-}

client/internal/ipcauth/peercred_bsd.go

@@ -1,43 +0,0 @@
-//go:build darwin || freebsd
-
-package ipcauth
-
-import (
-	"fmt"
-	"net"
-
-	"golang.org/x/sys/unix"
-)
-
-// PeerIdentity reads the kernel-authenticated identity of the process on the
-// other end of a Unix socket via LOCAL_PEERCRED. The xucred is recorded by the
-// kernel at connect() time and carries the peer's uid and its group list, of
-// which the first entry is the primary group.
-func PeerIdentity(conn net.Conn) (Identity, error) {
-	uc, ok := conn.(*net.UnixConn)
-	if !ok {
-		return Identity{}, fmt.Errorf("connection is not a unix socket: %T", conn)
-	}
-
-	raw, err := uc.SyscallConn()
-	if err != nil {
-		return Identity{}, fmt.Errorf("raw conn: %w", err)
-	}
-
-	var cred *unix.Xucred
-	var credErr error
-	if err := raw.Control(func(fd uintptr) {
-		cred, credErr = unix.GetsockoptXucred(int(fd), unix.SOL_LOCAL, unix.LOCAL_PEERCRED)
-	}); err != nil {
-		return Identity{}, fmt.Errorf("control raw conn: %w", err)
-	}
-	if credErr != nil {
-		return Identity{}, fmt.Errorf("read LOCAL_PEERCRED: %w", credErr)
-	}
-
-	id := Identity{UID: cred.Uid}
-	if cred.Ngroups > 0 {
-		id.GID = cred.Groups[0]
-	}
-	return id, nil
-}

client/internal/ipcauth/peercred_linux.go

@@ -1,39 +0,0 @@
-//go:build linux
-
-package ipcauth
-
-import (
-	"fmt"
-	"net"
-
-	"golang.org/x/sys/unix"
-)
-
-// PeerIdentity reads the kernel-authenticated identity of the process on the
-// other end of a Unix socket via SO_PEERCRED. The credentials are recorded by
-// the kernel at connect() time and cannot be changed for the life of the
-// connection, so they are not spoofable by the caller.
-func PeerIdentity(conn net.Conn) (Identity, error) {
-	uc, ok := conn.(*net.UnixConn)
-	if !ok {
-		return Identity{}, fmt.Errorf("connection is not a unix socket: %T", conn)
-	}
-
-	raw, err := uc.SyscallConn()
-	if err != nil {
-		return Identity{}, fmt.Errorf("raw conn: %w", err)
-	}
-
-	var cred *unix.Ucred
-	var credErr error
-	if err := raw.Control(func(fd uintptr) {
-		cred, credErr = unix.GetsockoptUcred(int(fd), unix.SOL_SOCKET, unix.SO_PEERCRED)
-	}); err != nil {
-		return Identity{}, fmt.Errorf("control raw conn: %w", err)
-	}
-	if credErr != nil {
-		return Identity{}, fmt.Errorf("read SO_PEERCRED: %w", credErr)
-	}
-
-	return Identity{UID: cred.Uid, GID: cred.Gid, PID: cred.Pid}, nil
-}

client/internal/ipcauth/pipeserver_windows.go

@@ -1,87 +0,0 @@
-//go:build windows
-
-package ipcauth
-
-import (
-	"fmt"
-	"net"
-
-	log "github.com/sirupsen/logrus"
-	"golang.org/x/sys/windows"
-)
-
-// PipeServerTrusted reports an error unless the pipe behind conn was created by a
-// principal this client may hand secrets to. Clients call it for a pipe whose name
-// carries no guarantee of its own, which is any name outside the
-// ProtectedPrefix\Administrators namespace: that namespace already restricts
-// creation to administrators and LocalSystem, while a plain name can be created by
-// any local user before the daemon gets there.
-//
-// The decision is made from the pipe object's owner, not from the serving process,
-// because a client cannot open a process running as another user at all, and the
-// legitimate case is precisely an unprivileged client talking to a privileged
-// daemon. Trusted owners are the service accounts, BUILTIN\Administrators, and
-// this client's own user, the last of which is the daemon a user runs themselves
-// as in netstack mode. A pipe owned by anyone else gets no setup key, pre-shared
-// key or SSO prompt out of this client.
-func PipeServerTrusted(conn net.Conn) error {
-	// go-winio's pipe connection embeds *win32File, which exposes Fd().
-	fdConn, ok := conn.(interface{ Fd() uintptr })
-	if !ok {
-		return fmt.Errorf("connection %T does not expose a pipe handle", conn)
-	}
-
-	owner, err := pipeOwnerSID(windows.Handle(fdConn.Fd()))
-	if err != nil {
-		return err
-	}
-
-	if !trustedPipeOwner(owner) {
-		return fmt.Errorf("pipe owned by %s, which is neither an administrator nor this user", owner)
-	}
-	return nil
-}
-
-// PipeOwnedBySelf reports whether the pipe behind conn was created by this very
-// user, which is how a client recognises a daemon running as itself. Ownership it
-// cannot read is reported as false.
-func PipeOwnedBySelf(conn net.Conn) bool {
-	fdConn, ok := conn.(interface{ Fd() uintptr })
-	if !ok {
-		return false
-	}
-
-	owner, err := pipeOwnerSID(windows.Handle(fdConn.Fd()))
-	if err != nil {
-		log.Debugf("read daemon pipe owner: %v", err)
-		return false
-	}
-	return selfKnown && selfIdentity.SID != "" && owner == selfIdentity.SID
-}
-
-// pipeOwnerSID reads the owner of the pipe object a client is connected to. The
-// handle was opened with GENERIC_READ, which includes READ_CONTROL, so no extra
-// access is needed.
-func pipeOwnerSID(handle windows.Handle) (string, error) {
-	sd, err := windows.GetSecurityInfo(handle, windows.SE_KERNEL_OBJECT, windows.OWNER_SECURITY_INFORMATION)
-	if err != nil {
-		return "", fmt.Errorf("read pipe security info: %w", err)
-	}
-
-	owner, _, err := sd.Owner()
-	if err != nil {
-		return "", fmt.Errorf("read pipe owner: %w", err)
-	}
-	return owner.String(), nil
-}
-
-// trustedPipeOwner reports whether a pipe's owner is a principal a client may
-// speak to. An elevated process's objects are owned by BUILTIN\Administrators by
-// default, an unelevated one's by the user, which is why both forms appear here.
-func trustedPipeOwner(owner string) bool {
-	switch owner {
-	case sidLocalSystem, sidLocalService, sidNetworkService, sidAdministrators:
-		return true
-	}
-	return selfKnown && selfIdentity.SID != "" && owner == selfIdentity.SID
-}

client/internal/ipcauth/privileged.go

@@ -1,125 +0,0 @@
-package ipcauth
-
-import (
-	"os"
-	"runtime"
-)
-
-// Fields of the ErrorInfo detail the daemon attaches to a PermissionDenied it
-// raises for an operation that requires root/administrator. Clients match on
-// Reason and Domain rather than on the message text, and render the summary and
-// command themselves so the user gets guidance instead of a gRPC error dump.
-const (
-	// ErrorReasonPrivilegeRequired identifies the detail.
-	ErrorReasonPrivilegeRequired = "PRIVILEGE_REQUIRED"
-	// ErrorDomain scopes the reason to the NetBird daemon.
-	ErrorDomain = "daemon.netbird.io"
-	// ErrorMetaSummary is the one-sentence explanation of what was refused.
-	ErrorMetaSummary = "summary"
-	// ErrorMetaCommand is the command that performs the same operation with the
-	// privileges it needs, ready to copy and run.
-	ErrorMetaCommand = "command"
-)
-
-// The identity of the process evaluating callers, captured once because it cannot
-// change. selfKnown is false when it could not be read, in which case nothing is
-// ever treated as this process. selfMayDelegate additionally requires this
-// process to be unprivileged: see IsPrivilegedCaller.
-var (
-	selfIdentity    Identity
-	selfKnown       bool
-	selfMayDelegate bool
-	// selfPID is this process's PID, used to recognise the daemon dialling itself.
-	selfPID = os.Getpid()
-)
-
-func init() {
-	id, err := CurrentProcessIdentity()
-	if err != nil {
-		return
-	}
-	selfIdentity, selfKnown = id, true
-	// Only an unprivileged daemon delegates its authority to its own identity.
-	// When it is root or LocalSystem, sharing its identity does not mean sharing
-	// its power: on Windows a filtered and a full token carry the same SID, so
-	// matching there would let a non-elevated shell of an administrator account
-	// act as an administrator, which is the boundary the token check exists to
-	// keep.
-	selfMayDelegate = !id.IsPrivileged()
-}
-
-// IsDaemonSelf reports whether an identity is this very process. The JSON gateway
-// runs inside the daemon and re-dials it locally, so this is what distinguishes
-// the gateway from any other caller, whatever user the daemon runs as.
-func IsDaemonSelf(id Identity) bool {
-	if !selfKnown || id.IsWindows() != selfIdentity.IsWindows() {
-		return false
-	}
-	if id.IsWindows() {
-		return id.SID != "" && id.SID == selfIdentity.SID
-	}
-	return id.UID == selfIdentity.UID
-}
-
-// IsPrivilegedCaller reports whether an identity may make the changes the daemon
-// restricts to the platform administrator. This is the daemon's own rule and
-// cannot be evaluated by a client, which does not know what the daemon runs as.
-//
-// Beyond root/administrator it accepts a caller running as the daemon's own
-// identity when the daemon is itself unprivileged. That keeps a rootless container
-// working, where there is no uid 0 at all, and a Windows daemon in netstack mode,
-// which needs no administrator rights. In those setups a caller sharing the
-// daemon's identity can already rewrite the config files it reads and replace the
-// binary it runs, so refusing it a config change would protect nothing; and an
-// unprivileged daemon cannot hand out a root shell in the first place.
-func IsPrivilegedCaller(id Identity) bool {
-	if id.IsPrivileged() {
-		return true
-	}
-	return selfMayDelegate && IsDaemonSelf(id)
-}
-
-// SelfDelegatesTo returns the identity this process delegates its authority to,
-// and whether it delegates at all. Only an unprivileged daemon does: see
-// IsPrivilegedCaller. It exists so a refusal can name who may actually perform the
-// operation, because on such a host root is neither required nor necessarily
-// available.
-func SelfDelegatesTo() (Identity, bool) {
-	if !selfKnown || !selfMayDelegate {
-		return Identity{}, false
-	}
-	return selfIdentity, true
-}
-
-// PrivilegedActor names the principal a privileged operation requires, for use
-// in messages shown to the user.
-func PrivilegedActor() string {
-	if runtime.GOOS == "windows" {
-		return "administrator privileges"
-	}
-	return "root"
-}
-
-// ElevatedCommand renders a command so that running it grants the privileges the
-// operation needs. Windows has no in-line equivalent of sudo, so the command is
-// returned unchanged and the user is expected to run it from an elevated
-// terminal.
-func ElevatedCommand(command string) string {
-	if runtime.GOOS == "windows" {
-		return command
-	}
-	return "sudo " + command
-}
-
-// UpCommand renders an elevated `netbird up` with the given flags, preceded by a
-// `down`. The down is what makes the command work on a connected client: `netbird
-// up` prints "Already connected" and returns without applying any config flag, so
-// on its own the command would appear to do nothing. It is a no-op, exit 0, when
-// the client is not connected.
-//
-// ";" rather than "&&" so the line can be pasted into any of the shells a user
-// might have: PowerShell 5.1, still the default on Windows Server, rejects "&&"
-// as a syntax error.
-func UpCommand(flags string) string {
-	return ElevatedCommand("netbird down") + "; " + ElevatedCommand("netbird up "+flags)
-}

client/internal/ipcauth/privileged_test.go

@@ -1,134 +0,0 @@
-package ipcauth
-
-import "testing"
-
-// The self rule is the one place privilege is granted to something other than the
-// platform administrator, so its two guards matter: it must apply only when the
-// daemon is itself unprivileged, and only to a caller with the daemon's identity.
-func TestIsPrivilegedCaller_SelfRule(t *testing.T) {
-	tests := []struct {
-		name string
-		// self stands in for the process the daemon runs as.
-		self      Identity
-		selfKnown bool
-		caller    Identity
-		want      bool
-	}{
-		{
-			name:      "root is privileged whatever the daemon runs as",
-			self:      Identity{UID: 1000},
-			selfKnown: true,
-			caller:    Identity{UID: 0},
-			want:      true,
-		},
-		{
-			name:      "an unprivileged daemon delegates to its own user (rootless container)",
-			self:      Identity{UID: 1000},
-			selfKnown: true,
-			caller:    Identity{UID: 1000},
-			want:      true,
-		},
-		{
-			name:      "an unprivileged daemon delegates to nobody else",
-			self:      Identity{UID: 1000},
-			selfKnown: true,
-			caller:    Identity{UID: 1001},
-			want:      false,
-		},
-		{
-			// The daemon is root on a normal install, so sharing its identity is
-			// already covered by being root; nothing else may match.
-			name:      "a root daemon delegates to nobody",
-			self:      Identity{UID: 0},
-			selfKnown: true,
-			caller:    Identity{UID: 1000},
-			want:      false,
-		},
-		{
-			// Windows netstack mode: the daemon needs no administrator rights.
-			name:      "an unprivileged windows daemon delegates to its own SID",
-			self:      Identity{SID: "S-1-5-21-1-2-3-1001"},
-			selfKnown: true,
-			caller:    Identity{SID: "S-1-5-21-1-2-3-1001"},
-			want:      true,
-		},
-		{
-			name:      "an unprivileged windows daemon delegates to no other SID",
-			self:      Identity{SID: "S-1-5-21-1-2-3-1001"},
-			selfKnown: true,
-			caller:    Identity{SID: "S-1-5-21-1-2-3-1002"},
-			want:      false,
-		},
-		{
-			// The UAC boundary: a filtered and a full token of the same account
-			// carry the same SID but not the same power, so an elevated daemon must
-			// never delegate to its own SID.
-			name:      "an elevated windows daemon does not delegate to its own SID",
-			self:      Identity{SID: "S-1-5-21-1-2-3-500", Elevated: true},
-			selfKnown: true,
-			caller:    Identity{SID: "S-1-5-21-1-2-3-500"},
-			want:      false,
-		},
-		{
-			name:      "LocalSystem is privileged on its own merits, not by delegation",
-			self:      Identity{SID: sidLocalSystem},
-			selfKnown: true,
-			caller:    Identity{SID: sidLocalSystem},
-			want:      true, // LocalSystem is privileged on its own merits
-		},
-		{
-			name:      "identities of different kinds never match",
-			self:      Identity{UID: 1000},
-			selfKnown: true,
-			caller:    Identity{SID: "S-1-5-21-1-2-3-1001"},
-			want:      false,
-		},
-		{
-			name:      "an unknown self identity delegates to nobody",
-			self:      Identity{},
-			selfKnown: false,
-			caller:    Identity{UID: 1000},
-			want:      false,
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			prevID, prevKnown, prevDelegate := selfIdentity, selfKnown, selfMayDelegate
-			t.Cleanup(func() { selfIdentity, selfKnown, selfMayDelegate = prevID, prevKnown, prevDelegate })
-
-			selfIdentity, selfKnown = tt.self, tt.selfKnown
-			selfMayDelegate = tt.selfKnown && !tt.self.IsPrivileged()
-
-			if got := IsPrivilegedCaller(tt.caller); got != tt.want {
-				t.Fatalf("IsPrivilegedCaller(%v) with daemon %v = %t, want %t",
-					tt.caller, tt.self, got, tt.want)
-			}
-		})
-	}
-}
-
-// The real process must never accidentally delegate: a test binary running as a
-// normal user is unprivileged, so it may match itself, but nothing else.
-func TestIsPrivilegedCaller_ThisProcess(t *testing.T) {
-	id, err := CurrentProcessIdentity()
-	if err != nil {
-		t.Skipf("cannot read this process's identity: %v", err)
-	}
-
-	// This process is always allowed to act as itself: either it is privileged, or
-	// it is unprivileged and therefore delegates to its own identity.
-	if !IsPrivilegedCaller(id) {
-		t.Errorf("this process %v was refused its own identity", id)
-	}
-
-	// A caller that is neither root nor this process must be refused, whatever
-	// this process happens to be.
-	other := Identity{UID: id.UID + 1}
-	if id.IsWindows() {
-		other = Identity{SID: id.SID + "9"}
-	}
-	if IsPrivilegedCaller(other) {
-		t.Errorf("an unrelated identity %v was treated as privileged", other)
-	}
-}

client/internal/ipcauth/self_unix.go

@@ -1,17 +0,0 @@
-//go:build !windows
-
-package ipcauth
-
-import "os"
-
-// CurrentProcessIdentity returns this process's identity as the daemon would
-// see it if this process connected to the local IPC. It lets a client (the UI)
-// decide up front whether a privileged operation can succeed, without a
-// round-trip and without duplicating the rules: the answer comes from the same
-// Identity.IsPrivileged the daemon applies.
-func CurrentProcessIdentity() (Identity, error) {
-	return Identity{
-		UID: uint32(os.Geteuid()),
-		GID: uint32(os.Getegid()),
-	}, nil
-}

client/internal/ipcauth/self_windows.go

@@ -1,35 +0,0 @@
-//go:build windows
-
-package ipcauth
-
-import (
-	"fmt"
-
-	"golang.org/x/sys/windows"
-)
-
-// CurrentProcessIdentity returns this process's identity as the daemon would see
-// it if this process connected to the local IPC. It lets a client (the UI)
-// decide up front whether a privileged operation can succeed, without a
-// round-trip and without duplicating the rules: the answer comes from the same
-// Identity.IsPrivileged the daemon applies to the token it reads off the pipe.
-func CurrentProcessIdentity() (Identity, error) {
-	// A pseudo-token, so it must not be closed.
-	token := windows.GetCurrentProcessToken()
-
-	user, err := token.GetTokenUser()
-	if err != nil {
-		return Identity{}, fmt.Errorf("read token user: %w", err)
-	}
-
-	groups, err := tokenGroupSIDs(token)
-	if err != nil {
-		return Identity{}, err
-	}
-
-	return Identity{
-		SID:      user.User.Sid.String(),
-		Groups:   groups,
-		Elevated: token.IsElevated(),
-	}, nil
-}

client/internal/mobile_dependency.go

@@ -11,14 +11,12 @@ import (
 
 // MobileDependency collect all dependencies for mobile platform
 type MobileDependency struct {
-	// Android and iOS
-	NetworkChangeListener listener.NetworkChangeListener
-
 	// Android only
-	TunAdapter       device.TunAdapter
-	IFaceDiscover    stdnet.ExternalIFaceDiscover
-	HostDNSAddresses []netip.AddrPort
-	DnsReadyListener dns.ReadyListener
+	TunAdapter            device.TunAdapter
+	IFaceDiscover         stdnet.ExternalIFaceDiscover
+	NetworkChangeListener listener.NetworkChangeListener
+	HostDNSAddresses      []netip.AddrPort
+	DnsReadyListener      dns.ReadyListener
 
 	//	iOS only
 	DnsManager     dns.IosDnsManager

client/internal/peer/conn.go

@@ -3,6 +3,7 @@ package peer
 import (
 	"context"
 	"fmt"
+	"math"
 	"net"
 	"net/netip"
 	"runtime"
@@ -26,6 +27,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/portforward"
 	"github.com/netbirdio/netbird/client/internal/rosenpass"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
+	"github.com/netbirdio/netbird/monotime"
 	"github.com/netbirdio/netbird/route"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 )
@@ -74,6 +76,34 @@ type RosenpassConfig struct {
 	PermissiveMode bool
 }
 
+// PQHandshaker attaches post-quantum ML-KEM material to signalling offers/answers and
+// feeds received material back. It is implemented by the engine over the pqkem
+// manager and is nil when the PQ exchange is disabled. remoteKey is the peer's
+// WireGuard public key.
+type PQHandshaker interface {
+	// OfferPayload returns the KEM offer to embed in an outgoing offer (nil if this
+	// peer is not the KEM initiator) and the local PQ data-path port to announce.
+	OfferPayload(remoteKey string) (payload []byte, port int)
+	// AnswerPayload processes a received KEM offer (nil if absent) and returns the KEM
+	// answer to embed in the outgoing answer (nil if none) and the local PQ port.
+	AnswerPayload(remoteKey string, recvOffer []byte) (payload []byte, port int)
+	// OnAnswer feeds a received KEM answer (nil if absent).
+	OnAnswer(remoteKey string, recvAnswer []byte)
+	// PSK returns the peer's latest derived post-quantum PSK to program at WG
+	// peer-config time (the pull path). ok is false until one has been derived.
+	PSK(remoteKey string) (wgtypes.Key, bool)
+	// SetRemoteAddr registers the peer's data-path endpoint learned from signalling:
+	// its WG overlay IP with the advertised pq UDP port.
+	SetRemoteAddr(remoteKey string, addr netip.AddrPort)
+	// OnDataPathRekeyed signals a fresh WireGuard handshake for the peer; it clocks the
+	// next chained PSK rotation pushed over the data path. sinceActivity is how long
+	// ago the peer last exchanged real user data, so the rotation can be skipped for
+	// idle tunnels.
+	OnDataPathRekeyed(remoteKey string, sinceActivity time.Duration)
+	// OnDataPathDown signals the peer's tunnel went down.
+	OnDataPathDown(remoteKey string)
+}
+
 // ConnConfig is a peer Connection configuration
 type ConnConfig struct {
 	// Key is a public key of a remote peer
@@ -91,6 +121,12 @@ type ConnConfig struct {
 
 	RosenpassConfig RosenpassConfig
 
+	// PQ carries post-quantum ML-KEM material on offers/answers; nil when disabled.
+	PQ PQHandshaker
+	// PQStrict fails closed: block peer traffic until the ML-KEM PSK is established,
+	// instead of letting the tunnel come up classically and upgrading to PQ later.
+	PQStrict bool
+
 	// ICEConfig ICE protocol configuration
 	ICEConfig icemaker.Config
 }
@@ -149,6 +185,11 @@ type Conn struct {
 	// pendingFirstPacket is the lazyconn-captured handshake init, replayed once the real
 	// transport is up.
 	pendingFirstPacket []byte
+
+	// pqBlockingKey is a per-conn random sentinel PSK used in PQ strict mode to fail
+	// closed: it is programmed until the real ML-KEM PSK is derived, so no session can
+	// form on a non-PQ key. Per-conn random so two strict peers never match by chance.
+	pqBlockingKey *wgtypes.Key
 }
 
 // injectPendingFirstPacket replays the captured handshake through the proxy if present, else
@@ -206,6 +247,14 @@ func NewConn(config ConnConfig, services ServiceDependencies) (*Conn, error) {
 		metricsRecorder:    services.MetricsRecorder,
 	}
 
+	if config.PQ != nil && config.PQStrict {
+		if k, err := wgtypes.GenerateKey(); err != nil {
+			connLog.Errorf("pqkem: failed to generate strict-mode sentinel key, strict fail-closed disabled for this peer: %v", err)
+		} else {
+			conn.pqBlockingKey = &k
+		}
+	}
+
 	return conn, nil
 }
 
@@ -670,6 +719,22 @@ func (conn *Conn) onGuardEvent() {
 	}
 }
 
+// RequestReoffer sends a fresh signalling offer for the peer, re-running the
+// post-quantum bootstrap over Signal. Used to recover from a persistent data-path
+// rekey failure: a new exchange overwrites the stalled PSK on both sides. No-op if the
+// connection is not open yet.
+func (conn *Conn) RequestReoffer() {
+	conn.mu.Lock()
+	h := conn.handshaker
+	conn.mu.Unlock()
+	if h == nil {
+		return
+	}
+	if err := h.SendOffer(); err != nil {
+		conn.Log.Debugf("pqkem: recovery re-offer failed: %v", err)
+	}
+}
+
 func (conn *Conn) onWGDisconnected(watcherCtx context.Context) {
 	conn.mu.Lock()
 	defer conn.mu.Unlock()
@@ -681,6 +746,10 @@ func (conn *Conn) onWGDisconnected(watcherCtx context.Context) {
 
 	conn.Log.Warnf("WireGuard handshake timeout detected, closing current connection")
 
+	if conn.config.PQ != nil {
+		conn.config.PQ.OnDataPathDown(conn.config.Key)
+	}
+
 	// Close the active connection based on current priority
 	switch conn.currentConnPriority {
 	case conntype.Relay:
@@ -723,7 +792,7 @@ func (conn *Conn) updateRelayStatus(relayServerAddr string, rosenpassPubKey []by
 		ConnStatus:         conn.evalStatus(),
 		Relayed:            conn.isRelayed(),
 		RelayServerAddress: relayServerAddr,
-		RosenpassEnabled:   isRosenpassEnabled(rosenpassPubKey),
+		RosenpassEnabled:   conn.quantumResistant(rosenpassPubKey),
 	}
 
 	err := conn.statusRecorder.UpdatePeerRelayedState(peerState)
@@ -742,7 +811,7 @@ func (conn *Conn) updateIceState(iceConnInfo ICEConnInfo, updateTime time.Time)
 		RemoteIceCandidateType:     iceConnInfo.RemoteIceCandidateType,
 		LocalIceCandidateEndpoint:  iceConnInfo.LocalIceCandidateEndpoint,
 		RemoteIceCandidateEndpoint: iceConnInfo.RemoteIceCandidateEndpoint,
-		RosenpassEnabled:           isRosenpassEnabled(iceConnInfo.RosenpassPubKey),
+		RosenpassEnabled:           conn.quantumResistant(iceConnInfo.RosenpassPubKey),
 	}
 
 	err := conn.statusRecorder.UpdatePeerICEState(peerState)
@@ -946,6 +1015,35 @@ func (conn *Conn) onWGCheckSuccess() {
 	conn.mu.Lock()
 	conn.wgTimeouts = 0
 	conn.mu.Unlock()
+
+	// A fresh WireGuard handshake clocks the post-quantum PSK rotation. Pass how long
+	// ago the peer last exchanged real user data (keepalives excluded) so the pqkem
+	// manager can skip rotation on idle tunnels — rotating then would push data-path
+	// traffic that keeps the lazy connection artificially active.
+	if conn.config.PQ != nil {
+		conn.config.PQ.OnDataPathRekeyed(conn.config.Key, conn.dataActivityAge())
+	}
+}
+
+// dataActivityAge returns how long ago the peer last exchanged real user data
+// (WireGuard keepalives excluded), per the same LastActivities signal the
+// lazy-connection inactivity monitor uses. It reports a very large duration when no
+// activity has ever been recorded, so the peer is treated as idle.
+//
+// In kernel mode there is no per-peer data-activity signal (LastActivities is
+// userspace-only), so we cannot tell active from idle. We report zero — always
+// "active" — so PSK rotation is not disabled in kernel mode. Lazy back-to-idle is
+// already limited there; the eBPF WG-activity detection (future) will supply a real
+// signal that excludes handshake/pqkem traffic.
+func (conn *Conn) dataActivityAge() time.Duration {
+	if !conn.config.WgConfig.WgInterface.IsUserspaceBind() {
+		return 0
+	}
+	last, ok := conn.config.WgConfig.WgInterface.LastActivities()[conn.config.WgConfig.RemoteKey]
+	if !ok {
+		return time.Duration(math.MaxInt64)
+	}
+	return monotime.Since(last)
 }
 
 // recordConnectionMetrics records connection stage timestamps as metrics
@@ -987,6 +1085,23 @@ func (conn *Conn) AgentVersionString() string {
 }
 
 func (conn *Conn) presharedKey(remoteRosenpassKey []byte) *wgtypes.Key {
+	// Post-quantum: once the ML-KEM exchange has derived a PSK for this peer, program
+	// it here so the peer's next WireGuard handshake adopts it. Applied at peer-config
+	// time (bootstrap / reconnect); steady-state rotation is pushed separately.
+	if conn.config.PQ != nil {
+		if psk, ok := conn.config.PQ.PSK(conn.config.Key); ok {
+			return &psk
+		}
+		if conn.config.PQStrict && conn.pqBlockingKey != nil {
+			// Fail closed: program a non-matching sentinel so no session forms on a
+			// non-PQ key until the ML-KEM exchange derives the real PSK (pushed via
+			// SetPresharedKey once it converges). "pending" — turns into a "stuck"
+			// warning from the manager if the exchange keeps failing (see raiseFailure).
+			conn.Log.Debugf("pqkem: strict mode — no PQ PSK yet, blocking peer traffic until the ML-KEM exchange converges")
+			return conn.pqBlockingKey
+		}
+	}
+
 	if conn.config.RosenpassConfig.PubKey == nil {
 		return conn.config.WgConfig.PreSharedKey
 	}
@@ -1026,6 +1141,21 @@ func isRosenpassEnabled(remoteRosenpassPubKey []byte) bool {
 	return remoteRosenpassPubKey != nil
 }
 
+// quantumResistant reports whether the peer's tunnel is post-quantum protected, for
+// the status "Quantum resistance" field: either Rosenpass (the remote advertised a
+// Rosenpass key) or the ML-KEM exchange (a PQ PSK has been derived for this peer).
+func (conn *Conn) quantumResistant(remoteRosenpassPubKey []byte) bool {
+	if isRosenpassEnabled(remoteRosenpassPubKey) {
+		return true
+	}
+	if conn.config.PQ != nil {
+		if _, ok := conn.config.PQ.PSK(conn.config.Key); ok {
+			return true
+		}
+	}
+	return false
+}
+
 func evalConnStatus(in connStatusInputs) guard.ConnStatus {
 	// "Relay up and needed" — the peer uses relay and the transport is connected.
 	relayUsedAndUp := in.peerUsesRelay && in.relayConnected

client/internal/peer/handshaker.go

@@ -39,6 +39,16 @@ type OfferAnswer struct {
 	// This value is the local Rosenpass server address when sending the message
 	RosenpassAddr string
 
+	// MlkemPayload carries the post-quantum X25519MLKEM768 handshake message
+	// (pqkem-framed offer on an OFFER, answer on an ANSWER) that seeds the
+	// WireGuard PSK. Opaque here — the pqkem library frames and parses it. Nil
+	// when the peer does not run the ML-KEM PQ exchange.
+	MlkemPayload []byte
+
+	// MlkemPort is the peer's ML-KEM PQ service UDP port (bound on its WG overlay
+	// IP) where data-path rekey messages are sent. Zero when not running the exchange.
+	MlkemPort int
+
 	// relay server address
 	RelaySrvAddress string
 	// RelaySrvIP is the IP the remote peer is connected to on its
@@ -81,14 +91,20 @@ type Handshaker struct {
 
 func NewHandshaker(log *log.Entry, config ConnConfig, signaler *Signaler, ice *WorkerICE, relay *WorkerRelay, metricsStages *MetricsStages) *Handshaker {
 	h := &Handshaker{
-		log:            log,
-		config:         config,
-		signaler:       signaler,
-		ice:            ice,
-		relay:          relay,
-		metricsStages:  metricsStages,
-		remoteOffersCh: make(chan OfferAnswer),
-		remoteAnswerCh: make(chan OfferAnswer),
+		log:           log,
+		config:        config,
+		signaler:      signaler,
+		ice:           ice,
+		relay:         relay,
+		metricsStages: metricsStages,
+		// Buffered by 1: the single Listen goroutine can be busy handling an offer
+		// (sendAnswer does a blocking signal send) exactly when the matching answer
+		// arrives on the other channel. Unbuffered, that answer would hit the
+		// non-blocking send's default and be dropped — fatal for the post-quantum
+		// exchange, which needs the answer to converge. A 1-slot cushion lets it wait
+		// until Listen loops back, without ever blocking the signal receiver.
+		remoteOffersCh: make(chan OfferAnswer, 1),
+		remoteAnswerCh: make(chan OfferAnswer, 1),
 	}
 	// assume remote supports ICE until we learn otherwise from received offers
 	h.remoteICESupported.Store(ice != nil)
@@ -120,6 +136,8 @@ func (h *Handshaker) Listen(ctx context.Context) {
 
 			h.updateRemoteICEState(&remoteOfferAnswer)
 
+			h.pqRegisterEndpoint(remoteOfferAnswer.MlkemPort)
+
 			if h.relayListener != nil {
 				h.relayListener.Notify(&remoteOfferAnswer)
 			}
@@ -128,7 +146,7 @@ func (h *Handshaker) Listen(ctx context.Context) {
 				h.iceListener(&remoteOfferAnswer)
 			}
 
-			if err := h.sendAnswer(); err != nil {
+			if err := h.sendAnswer(&remoteOfferAnswer); err != nil {
 				h.log.Errorf("failed to send remote offer confirmation: %s", err)
 				continue
 			}
@@ -142,6 +160,8 @@ func (h *Handshaker) Listen(ctx context.Context) {
 
 			h.updateRemoteICEState(&remoteOfferAnswer)
 
+			h.pqRegisterEndpoint(remoteOfferAnswer.MlkemPort)
+
 			if h.relayListener != nil {
 				h.relayListener.Notify(&remoteOfferAnswer)
 			}
@@ -149,6 +169,10 @@ func (h *Handshaker) Listen(ctx context.Context) {
 			if h.iceListener != nil && h.RemoteICESupported() {
 				h.iceListener(&remoteOfferAnswer)
 			}
+
+			if h.config.PQ != nil {
+				h.config.PQ.OnAnswer(h.config.Key, remoteOfferAnswer.MlkemPayload)
+			}
 		case <-ctx.Done():
 			h.log.Infof("stop listening for remote offers and answers")
 			return
@@ -156,6 +180,16 @@ func (h *Handshaker) Listen(ctx context.Context) {
 	}
 }
 
+// pqRegisterEndpoint feeds the post-quantum handshaker the peer's data-path endpoint
+// (its WG overlay IP plus the advertised pq UDP port) learned from a remote offer/answer.
+func (h *Handshaker) pqRegisterEndpoint(remotePort int) {
+	if h.config.PQ == nil || remotePort <= 0 || remotePort > 65535 || len(h.config.WgConfig.AllowedIps) == 0 {
+		return
+	}
+	addr := netip.AddrPortFrom(h.config.WgConfig.AllowedIps[0].Addr(), uint16(remotePort))
+	h.config.PQ.SetRemoteAddr(h.config.Key, addr)
+}
+
 func (h *Handshaker) SendOffer() error {
 	h.mu.Lock()
 	defer h.mu.Unlock()
@@ -195,13 +229,23 @@ func (h *Handshaker) sendOffer() error {
 	}
 
 	offer := h.buildOfferAnswer()
+	if h.config.PQ != nil {
+		offer.MlkemPayload, offer.MlkemPort = h.config.PQ.OfferPayload(h.config.Key)
+	}
 	h.log.Debugf("sending offer with serial: %s", offer.SessionIDString())
 
 	return h.signaler.SignalOffer(offer, h.config.Key)
 }
 
-func (h *Handshaker) sendAnswer() error {
+func (h *Handshaker) sendAnswer(remoteOffer *OfferAnswer) error {
 	answer := h.buildOfferAnswer()
+	if h.config.PQ != nil {
+		var recvOffer []byte
+		if remoteOffer != nil {
+			recvOffer = remoteOffer.MlkemPayload
+		}
+		answer.MlkemPayload, answer.MlkemPort = h.config.PQ.AnswerPayload(h.config.Key, recvOffer)
+	}
 	h.log.Debugf("sending answer with serial: %s", answer.SessionIDString())
 
 	return h.signaler.SignalAnswer(answer, h.config.Key)

client/internal/peer/iface.go

@@ -10,6 +10,7 @@ import (
 	"github.com/netbirdio/netbird/client/iface/configurer"
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/iface/wgproxy"
+	"github.com/netbirdio/netbird/monotime"
 )
 
 type WGIface interface {
@@ -19,4 +20,11 @@ type WGIface interface {
 	GetProxy() wgproxy.Proxy
 	Address() wgaddr.Address
 	RemoveEndpointAddress(key string) error
+	// LastActivities returns the last real-data activity time per peer (WireGuard
+	// keepalives excluded), used to gate post-quantum PSK rotation on active tunnels.
+	LastActivities() map[string]monotime.Time
+	// IsUserspaceBind reports whether WireGuard runs in userspace. Only there does
+	// LastActivities track per-peer data activity; in kernel mode it is unavailable,
+	// so PSK rotation cannot be gated on activity.
+	IsUserspaceBind() bool
 }

client/internal/peer/signaler.go

@@ -63,6 +63,8 @@ func (s *Signaler) signalOfferAnswer(offerAnswer OfferAnswer, remoteKey string,
 		},
 		RosenpassPubKey: offerAnswer.RosenpassPubKey,
 		RosenpassAddr:   offerAnswer.RosenpassAddr,
+		MlkemPayload:    offerAnswer.MlkemPayload,
+		MlkemPort:       offerAnswer.MlkemPort,
 		RelaySrvAddress: offerAnswer.RelaySrvAddress,
 		RelaySrvIP:      offerAnswer.RelaySrvIP,
 		SessionID:       sessionIDBytes,

client/internal/pqkem/bench_test.go

@@ -0,0 +1,59 @@
+package pqkem
+
+import (
+	"crypto/ecdh"
+	"crypto/mlkem"
+	"crypto/rand"
+	"testing"
+)
+
+func BenchmarkX25519Keygen(b *testing.B) {
+	c := ecdh.X25519()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		if _, err := c.GenerateKey(rand.Reader); err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkX25519ECDH(b *testing.B) {
+	c := ecdh.X25519()
+	a, _ := c.GenerateKey(rand.Reader)
+	p, _ := c.GenerateKey(rand.Reader)
+	pub := p.PublicKey()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		if _, err := a.ECDH(pub); err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkMLKEMKeygen(b *testing.B) {
+	for i := 0; i < b.N; i++ {
+		if _, err := mlkem.GenerateKey768(); err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkMLKEMEncaps(b *testing.B) {
+	dk, _ := mlkem.GenerateKey768()
+	ek := dk.EncapsulationKey()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, _ = ek.Encapsulate()
+	}
+}
+
+func BenchmarkMLKEMDecaps(b *testing.B) {
+	dk, _ := mlkem.GenerateKey768()
+	_, ct := dk.EncapsulationKey().Encapsulate()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		if _, err := dk.Decapsulate(ct); err != nil {
+			b.Fatal(err)
+		}
+	}
+}

client/internal/pqkem/callbacks.go

@@ -0,0 +1,18 @@
+package pqkem
+
+// CallbackHandler is implemented by the host and invoked by the library. The
+// library only reports events; the host owns the reaction. Keeping this an
+// interface — rather than touching the transport or keying directly — is what lets
+// the KEM code be extracted as a standalone library.
+type CallbackHandler interface {
+	// OnNewPSKReady fires when a fresh post-quantum PSK has been derived for a peer
+	// and must be programmed into the consumer's secure channel. It is invoked at
+	// the commit point of each side: the initiator on receiving the answer, the
+	// responder on receiving the confirm.
+	OnNewPSKReady(remoteID RemoteID, psk PSK) error
+
+	// OnRekeyFailed fires when an exchange fails to converge within the allotted
+	// time. The host should tear the peer connection down so it re-establishes, and
+	// log a WARN. The library reports the event; it does not dictate the reaction.
+	OnRekeyFailed(remoteID RemoteID) error
+}

client/internal/pqkem/convergence.go

@@ -0,0 +1,271 @@
+package pqkem
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"time"
+)
+
+// idHex renders an exchange ID for logs.
+func idHex(id ExchangeID) string { return hex.EncodeToString(id[:]) }
+
+// pskFingerprint is a short, non-secret digest of a derived PSK: identical on both
+// peers iff they derived the same key. Logged instead of the raw PSK so debug logs
+// never carry the actual WireGuard preshared key.
+func pskFingerprint(psk PSK) string {
+	sum := sha256.Sum256(psk[:])
+	return hex.EncodeToString(sum[:8])
+}
+
+// startExchange creates a fresh initiator exchange (acknowledging ackID, zero for a
+// bootstrap) and returns the framed offer for the caller to send — pushed over the
+// data path for a chained rekey, or handed to the host for signalling when viaSignal
+// is set. Any previous in-flight exchange for the peer is cancelled.
+func (m *Manager) startExchange(remoteID RemoteID, viaSignal bool, ackID ExchangeID) ([]byte, error) {
+	init, err := NewInitiator()
+	if err != nil {
+		return nil, err
+	}
+	id, err := newExchangeID()
+	if err != nil {
+		return nil, err
+	}
+	raw, err := (&OfferMsg{ExchangeID: id, AckID: ackID, KEMOffer: init.Offer()}).Encode()
+	if err != nil {
+		return nil, err
+	}
+
+	ctx, cancel := context.WithCancel(m.rootCtx)
+	m.mu.Lock()
+	if old := m.exchanges[remoteID]; old != nil && old.cancel != nil {
+		old.cancel()
+	}
+	m.exchanges[remoteID] = &exchangeCtl{
+		id:        id,
+		state:     stateAwaitingAnswer,
+		startedAt: time.Now(),
+		cancel:    cancel,
+		lastSent:  raw,
+		initiator: init,
+		viaSignal: viaSignal,
+	}
+	m.mu.Unlock()
+
+	m.wait.Add(1)
+	go m.initiatorLoop(ctx, remoteID, id)
+
+	via := "data-path"
+	if viaSignal {
+		via = "signal"
+	}
+	m.trace("pqkem: offer sent", "peer", remoteID, "exchange", idHex(id), "acks", idHex(ackID), "via", via)
+	return raw, nil
+}
+
+// processOffer (responder) first acknowledges the previous exchange the offer names
+// (that offer riding the data path under the freshly adopted key proves it worked),
+// then derives the PSK for the new offer, commits it optimistically, and returns the
+// framed answer. A duplicate offer returns the cached answer without re-deriving.
+func (m *Manager) processOffer(remoteID RemoteID, o *OfferMsg) ([]byte, error) {
+	m.trace("pqkem: offer received", "peer", remoteID, "exchange", idHex(o.ExchangeID), "acks", idHex(o.AckID))
+
+	if o.AckID != (ExchangeID{}) {
+		m.ackConverged(remoteID, o.AckID)
+	}
+
+	m.mu.Lock()
+	if ex := m.exchanges[remoteID]; ex != nil && ex.id == o.ExchangeID {
+		state, last := ex.state, ex.lastSent
+		m.mu.Unlock()
+		if state == stateReserved {
+			return nil, nil
+		}
+		m.trace("pqkem: duplicate offer, resending cached answer", "peer", remoteID, "exchange", idHex(o.ExchangeID))
+		return last, nil
+	}
+	// Reserve the slot so a concurrent duplicate offer bails.
+	m.exchanges[remoteID] = &exchangeCtl{id: o.ExchangeID, state: stateReserved, startedAt: time.Now()}
+	m.mu.Unlock()
+
+	answerBytes, psk, err := Respond(o.KEMOffer, m.binding(remoteID))
+	if err != nil {
+		return nil, err
+	}
+	raw, err := (&AnswerMsg{ExchangeID: o.ExchangeID, KEMAnswer: answerBytes}).Encode()
+	if err != nil {
+		return nil, err
+	}
+
+	m.mu.Lock()
+	ex := m.exchanges[remoteID]
+	if ex == nil || ex.id != o.ExchangeID {
+		m.mu.Unlock()
+		m.trace("pqkem: exchange superseded during respond, dropping answer", "peer", remoteID, "exchange", idHex(o.ExchangeID))
+		return nil, nil
+	}
+	ex.state = stateAwaitingAck
+	ex.lastSent = raw
+	ex.pendingPSK = psk
+	m.psks[remoteID] = psk
+	m.mu.Unlock()
+
+	m.trace("pqkem: new PSK derived", "peer", remoteID, "exchange", idHex(o.ExchangeID), "role", "responder", "psk_fp", pskFingerprint(psk))
+
+	// Commit optimistically so our data path can rekey to the new PSK.
+	if err := m.cbHandler.OnNewPSKReady(remoteID, psk); err != nil {
+		return nil, err
+	}
+	m.trace("pqkem: answer sent", "peer", remoteID, "exchange", idHex(o.ExchangeID))
+	return raw, nil
+}
+
+// processAnswer (initiator) derives and commits the PSK and parks in
+// stateAwaitingRekey; the next offer (chained from OnDataPathRekeyed) will acknowledge
+// this exchange. Only valid in stateAwaitingAnswer; advancing the state under the
+// lock makes a concurrent/duplicate answer bail.
+func (m *Manager) processAnswer(remoteID RemoteID, a *AnswerMsg) error {
+	m.mu.Lock()
+	ex := m.exchanges[remoteID]
+	if ex == nil || ex.id != a.ExchangeID || ex.state != stateAwaitingAnswer {
+		haveID := "none"
+		if ex != nil {
+			haveID = idHex(ex.id)
+		}
+		m.mu.Unlock()
+		m.trace("pqkem: unexpected answer dropped (inconsistency)", "peer", remoteID, "answer_for", idHex(a.ExchangeID), "have_exchange", haveID)
+		return nil
+	}
+	ex.state = stateAwaitingRekey
+	init := ex.initiator
+	ex.initiator = nil
+	m.mu.Unlock()
+
+	m.trace("pqkem: answer received", "peer", remoteID, "exchange", idHex(a.ExchangeID))
+
+	psk, err := init.Finish(a.KEMAnswer, m.binding(remoteID))
+	if err != nil {
+		return err
+	}
+
+	// The initiator has converged: the responder must have derived the key to answer.
+	m.mu.Lock()
+	m.established[remoteID] = true
+	m.failures[remoteID] = 0
+	m.psks[remoteID] = psk
+	m.mu.Unlock()
+
+	m.trace("pqkem: new PSK derived", "peer", remoteID, "exchange", idHex(a.ExchangeID), "role", "initiator", "psk_fp", pskFingerprint(psk))
+
+	return m.cbHandler.OnNewPSKReady(remoteID, psk)
+}
+
+// ackConverged (responder) records convergence of the exchange named by ackID: a
+// later offer acknowledging it proves both sides operate on that exchange's key. Only
+// acts on a matching stateAwaitingAck exchange; anything else is ignored.
+func (m *Manager) ackConverged(remoteID RemoteID, ackID ExchangeID) {
+	m.mu.Lock()
+	ex := m.exchanges[remoteID]
+	if ex == nil || ex.id != ackID || ex.state != stateAwaitingAck {
+		m.mu.Unlock()
+		m.trace("pqkem: ack for unknown/mismatched exchange, ignored (inconsistency)", "peer", remoteID, "acks", idHex(ackID))
+		return
+	}
+	delete(m.exchanges, remoteID)
+	m.established[remoteID] = true
+	m.failures[remoteID] = 0
+	_ = time.Since(ex.startedAt) // convergence latency (metrics hook, later step)
+	m.mu.Unlock()
+
+	m.trace("pqkem: previous exchange confirmed by ack", "peer", remoteID, "exchange", idHex(ackID))
+}
+
+// initiatorLoop enforces the offer->answer convergence deadline and retransmits the
+// initiator's outstanding data-path offer while awaiting the answer (a
+// signalling-bootstrapped offer is retransmitted by the host, so it is not resent
+// here). Exhausting the deadline before the answer arrives is a failure. Once the
+// answer is in (state past awaitingAnswer) the loop exits: the next rotation is driven
+// by OnDataPathRekeyed, and the idle wait for it has no deadline.
+func (m *Manager) initiatorLoop(ctx context.Context, remoteID RemoteID, id ExchangeID) {
+	defer m.wait.Done()
+	t := time.NewTicker(m.retryInterval)
+	defer t.Stop()
+
+	attempts := 0
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-t.C:
+			m.mu.Lock()
+			ex := m.exchanges[remoteID]
+			if ex == nil || ex.id != id {
+				m.mu.Unlock()
+				return
+			}
+
+			switch ex.state {
+			case stateAwaitingAnswer:
+				if attempts >= m.maxRetries {
+					delete(m.exchanges, remoteID)
+					initial := !m.established[remoteID]
+					fail := m.registerFailureLocked(remoteID)
+					m.mu.Unlock()
+					m.raiseFailure(remoteID, fail, initial)
+					return
+				}
+				viaSignal := ex.viaSignal
+				msg := ex.lastSent
+				attempts++
+				m.mu.Unlock()
+				if !viaSignal {
+					if err := m.pushDataPath(remoteID, msg); err != nil {
+						m.logger.Warn("pqkem: offer retransmit failed", "peer", remoteID, "err", err)
+					}
+				}
+
+			default:
+				// Past awaiting the answer (converged) or superseded: the loop's job
+				// is done. The next rotation is driven externally by OnDataPathRekeyed,
+				// so there is no deadline while idle-waiting for it (that wait can be
+				// as long as the transport's natural rekey interval).
+				m.mu.Unlock()
+				return
+			}
+		}
+	}
+}
+
+// registerFailureLocked applies policy B and reports whether OnRekeyFailed is due:
+// an initial exchange (peer never established) fails immediately; a rekey tolerates
+// up to maxRekeyFailures consecutive misses (we stay on the still-valid previous
+// PSK) before failing. Assumes m.mu is held.
+func (m *Manager) registerFailureLocked(remoteID RemoteID) bool {
+	if !m.established[remoteID] {
+		return true
+	}
+	m.failures[remoteID]++
+	if m.failures[remoteID] >= m.maxRekeyFailures {
+		m.failures[remoteID] = 0
+		return true
+	}
+	return false
+}
+
+// raiseFailure reports a convergence failure. initial distinguishes a never-established
+// peer (bootstrap failed → no PQ PSK at all; in strict mode the peer stays blocked =
+// "stuck") from a rekey failure (a previous PSK is still in force and traffic continues).
+func (m *Manager) raiseFailure(remoteID RemoteID, fail, initial bool) {
+	if !fail {
+		m.logger.Warn("pqkem: rekey attempt timed out, will retry next cycle", "peer", remoteID)
+		return
+	}
+	if initial {
+		m.logger.Warn("pqkem: initial exchange failed — no PQ PSK established for peer (strict mode keeps the peer blocked until it converges)", "peer", remoteID)
+	} else {
+		m.logger.Warn("pqkem: rekey failed after retries — staying on the previous PSK", "peer", remoteID)
+	}
+	if err := m.cbHandler.OnRekeyFailed(remoteID); err != nil {
+		m.logger.Error("pqkem: OnRekeyFailed handler error", "peer", remoteID, "err", err)
+	}
+}

client/internal/pqkem/convergence_test.go

@@ -0,0 +1,74 @@
+package pqkem
+
+import (
+	"net/netip"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+)
+
+// dropTransport is a pqkem.Transport that silently discards everything.
+type dropTransport struct{}
+
+func (dropTransport) Send(netip.AddrPort, []byte) error { return nil }
+func (dropTransport) LocalPort() int                    { return 0 }
+func (dropTransport) Run(func(netip.AddrPort, []byte))  {}
+func (dropTransport) Close() error                      { return nil }
+
+func failedCount(f *fakeWG) int {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return len(f.failed)
+}
+
+func TestManager_InitialTimeoutFailsImmediately(t *testing.T) {
+	wg := newFakeWG()
+	d := NewManager("bbbb", wg, nil) // bbbb > aaaa -> initiator
+	d.Start(dropTransport{})
+	d.retryInterval = 5 * time.Millisecond
+	d.maxRetries = 3
+	defer d.Stop()
+
+	// Bootstrap offer is produced for signalling; no answer ever comes back -> the
+	// initial exchange fails fast.
+	offer, err := d.SignalOffer("aaaa")
+	require.NoError(t, err)
+	require.NotNil(t, offer)
+
+	require.Eventually(t, func() bool { return failedCount(wg) == 1 }, time.Second, 5*time.Millisecond)
+}
+
+func TestManager_RekeyToleratesKFailures(t *testing.T) {
+	dA, dB, _, wgB, lbB := pair(t)
+	defer dA.Stop()
+	defer dB.Stop()
+
+	// Tighten B's timings before any exchange loop spawns (the loop reads these
+	// fields, so writing them after a loop is running would race).
+	dB.retryInterval = 5 * time.Millisecond
+	dB.maxRetries = 2
+
+	// Establish: bootstrap + data-path-rekeyed so B becomes established and its data
+	// path is usable.
+	bootstrap(t, dA, dB)
+	dA.OnDataPathRekeyed("bbbb", 0)
+	dB.OnDataPathRekeyed("aaaa", 0)
+	require.NotEqual(t, PSK{}, wgB.psk("aaaa"))
+
+	// Drop B's outbound so rekeys can no longer converge.
+	lbB.drop.Store(true)
+
+	// K-1 data-path rekeys must NOT raise OnRekeyFailed.
+	for i := 0; i < DefaultMaxRekeyFailures-1; i++ {
+		_, err := dB.startExchange("aaaa", false, ExchangeID{})
+		require.NoError(t, err)
+		time.Sleep(50 * time.Millisecond)
+	}
+	require.Equal(t, 0, failedCount(wgB), "no failure before K attempts")
+
+	// The K-th failure raises it once.
+	_, err := dB.startExchange("aaaa", false, ExchangeID{})
+	require.NoError(t, err)
+	require.Eventually(t, func() bool { return failedCount(wgB) == 1 }, time.Second, 5*time.Millisecond)
+}

client/internal/pqkem/env.go

@@ -0,0 +1,138 @@
+package pqkem
+
+import (
+	"context"
+	"log/slog"
+	"os"
+	"strconv"
+	"strings"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// EnvEnabled is the environment variable that turns the ML-KEM post-quantum
+// exchange on for this client. Accepts on/off aliases plus anything
+// strconv.ParseBool understands (true/false/1/0).
+const EnvEnabled = "NB_ENABLE_PQ_MLKEM"
+
+// Enabled reports whether the ML-KEM PQ exchange is enabled via the environment.
+// An empty or unrecognized value is treated as disabled.
+func Enabled() bool {
+	raw := strings.ToLower(strings.TrimSpace(os.Getenv(EnvEnabled)))
+	switch raw {
+	case "":
+		return false
+	case "on":
+		return true
+	case "off":
+		return false
+	}
+	enabled, err := strconv.ParseBool(raw)
+	if err != nil {
+		log.Warnf("failed to parse %s value %q: %v", EnvEnabled, raw, err)
+		return false
+	}
+	return enabled
+}
+
+// EnvStrict enables strict (fail-closed) mode: block peer traffic until the ML-KEM
+// PSK has been established, instead of the default opportunistic behaviour that lets
+// the tunnel come up classically and upgrades to PQ once the exchange converges.
+const EnvStrict = "NB_PQ_MLKEM_STRICT"
+
+// Strict reports whether strict (fail-closed) mode is enabled via the environment.
+// An empty or unrecognized value is treated as disabled (opportunistic).
+func Strict() bool {
+	switch strings.ToLower(strings.TrimSpace(os.Getenv(EnvStrict))) {
+	case "on":
+		return true
+	case "", "off":
+		return false
+	}
+	enabled, err := strconv.ParseBool(strings.TrimSpace(os.Getenv(EnvStrict)))
+	if err != nil {
+		log.Warnf("failed to parse %s value %q: %v", EnvStrict, os.Getenv(EnvStrict), err)
+		return false
+	}
+	return enabled
+}
+
+// EnvLogLevel overrides the ML-KEM manager's slog level (trace/debug/info/warn/error).
+// Defaults to info. The verbose per-exchange lifecycle logs are emitted at trace.
+const EnvLogLevel = "NB_PQ_MLKEM_LOG_LEVEL"
+
+// LevelTrace is a custom slog level below Debug for the verbose per-exchange lifecycle
+// logs, so they stay off unless NB_PQ_MLKEM_LOG_LEVEL=trace (and the daemon log level
+// is trace, since the records are forwarded to logrus).
+const LevelTrace = slog.LevelDebug - 4
+
+// NewLogger builds the slog logger for the ML-KEM manager. It forwards records to
+// logrus so PQ logs land in the same sink as the rest of the daemon (console +
+// client.log) rather than stdout. Verbosity is gated by EnvLogLevel.
+func NewLogger() *slog.Logger {
+	return slog.New(slogToLogrus{})
+}
+
+func logLevel() slog.Level {
+	switch strings.ToLower(strings.TrimSpace(os.Getenv(EnvLogLevel))) {
+	case "trace":
+		return LevelTrace
+	case "debug":
+		return slog.LevelDebug
+	case "warn":
+		return slog.LevelWarn
+	case "error":
+		return slog.LevelError
+	default:
+		return slog.LevelInfo
+	}
+}
+
+// slogToLogrus is a slog.Handler that forwards records to logrus, so the ML-KEM
+// manager's logs go wherever the daemon's logrus is configured (console + client.log)
+// instead of stdout. Verbosity is gated by EnvLogLevel via logLevel().
+type slogToLogrus struct {
+	fields log.Fields
+}
+
+func (h slogToLogrus) Enabled(_ context.Context, level slog.Level) bool {
+	return level >= logLevel()
+}
+
+func (h slogToLogrus) Handle(_ context.Context, r slog.Record) error {
+	fields := make(log.Fields, len(h.fields)+r.NumAttrs())
+	for k, v := range h.fields {
+		fields[k] = v
+	}
+	r.Attrs(func(a slog.Attr) bool {
+		fields[a.Key] = a.Value.Any()
+		return true
+	})
+	entry := log.WithFields(fields)
+	switch {
+	case r.Level >= slog.LevelError:
+		entry.Error(r.Message)
+	case r.Level >= slog.LevelWarn:
+		entry.Warn(r.Message)
+	case r.Level >= slog.LevelInfo:
+		entry.Info(r.Message)
+	case r.Level >= slog.LevelDebug:
+		entry.Debug(r.Message)
+	default:
+		entry.Trace(r.Message)
+	}
+	return nil
+}
+
+func (h slogToLogrus) WithAttrs(attrs []slog.Attr) slog.Handler {
+	fields := make(log.Fields, len(h.fields)+len(attrs))
+	for k, v := range h.fields {
+		fields[k] = v
+	}
+	for _, a := range attrs {
+		fields[a.Key] = a.Value.Any()
+	}
+	return slogToLogrus{fields: fields}
+}
+
+func (h slogToLogrus) WithGroup(_ string) slog.Handler { return h }

client/internal/pqkem/kem.go

@@ -0,0 +1,178 @@
+// Package pqkem is a spike (NET-1406) for a post-quantum pre-shared-key exchange
+// that could replace Rosenpass. It performs an X25519MLKEM768 hybrid key
+// encapsulation and derives a 32-byte pre-shared key (PSK).
+//
+// The exchange is a single round trip designed to ride the (already
+// authenticated) Signal offer/answer channel:
+//
+//	initiator --Offer(1216B)--> responder
+//	initiator <--Answer(1120B)-- responder
+//
+// Both sides then hold the same PSK, which is bound to the two peers' identities
+// (their peer identity keys) so the derived key cannot be transplanted
+// to a different peer pair even if the transport authentication were bypassed.
+//
+// Combiner note: this follows draft-ietf-tls-ecdhe-mlkem for X25519MLKEM768 — on
+// the wire ML-KEM ‖ X25519 (the draft deliberately reversed the share order for
+// this group), and ML-KEM_ss ‖ X25519_ss as the KDF input. The PSK is derived with
+// HKDF-SHA256 over that hybrid secret, salted with a domain-separation label and
+// bound (via the HKDF info) to the full transcript and the canonicalised peer
+// identities.
+package pqkem
+
+import (
+	"crypto/ecdh"
+	"crypto/hkdf"
+	"crypto/mlkem"
+	"crypto/rand"
+	"crypto/sha256"
+	"fmt"
+)
+
+const (
+	// OfferSize is the initiator message: ML-KEM-768 encapsulation key ‖ X25519 public key
+	// (share order per draft-ietf-tls-ecdhe-mlkem for X25519MLKEM768).
+	OfferSize = mlkem.EncapsulationKeySize768 + 32 // 1216
+	// AnswerSize is the responder message: ML-KEM-768 ciphertext ‖ X25519 public key.
+	AnswerSize = mlkem.CiphertextSize768 + 32 // 1120
+
+	pskLabel = "netbird-pq-psk-v1"
+)
+
+// PSK is the 32-byte derived pre-shared key handed to the consumer to key its channel.
+type PSK [32]byte
+
+// Binding identifies the peer pair the PSK is derived for. Callers set both
+// peer identity keys; the order does not matter (it is canonicalised).
+type Binding struct {
+	LocalID  []byte
+	RemoteID []byte
+}
+
+// Initiator holds the ephemeral secrets between Offer and Finish.
+type Initiator struct {
+	x25519  *ecdh.PrivateKey
+	mlkemDK *mlkem.DecapsulationKey768
+	offer   []byte
+}
+
+// NewInitiator generates the ephemeral X25519 + ML-KEM-768 keypairs.
+func NewInitiator() (*Initiator, error) {
+	x, err := ecdh.X25519().GenerateKey(rand.Reader)
+	if err != nil {
+		return nil, fmt.Errorf("x25519 keygen: %w", err)
+	}
+	dk, err := mlkem.GenerateKey768()
+	if err != nil {
+		return nil, fmt.Errorf("ml-kem keygen: %w", err)
+	}
+
+	offer := make([]byte, 0, OfferSize)
+	offer = append(offer, dk.EncapsulationKey().Bytes()...)
+	offer = append(offer, x.PublicKey().Bytes()...)
+
+	return &Initiator{x25519: x, mlkemDK: dk, offer: offer}, nil
+}
+
+// Offer returns the initiator message to send over Signal.
+func (i *Initiator) Offer() []byte {
+	return i.offer
+}
+
+// Finish consumes the responder's answer and derives the PSK.
+func (i *Initiator) Finish(answer []byte, b Binding) (PSK, error) {
+	if len(answer) != AnswerSize {
+		return PSK{}, fmt.Errorf("answer: got %d bytes, want %d", len(answer), AnswerSize)
+	}
+	ct := answer[:mlkem.CiphertextSize768]
+	peerX := answer[mlkem.CiphertextSize768:]
+
+	ssMLKEM, err := i.mlkemDK.Decapsulate(ct)
+	if err != nil {
+		return PSK{}, fmt.Errorf("ml-kem decapsulate: %w", err)
+	}
+	pub, err := ecdh.X25519().NewPublicKey(peerX)
+	if err != nil {
+		return PSK{}, fmt.Errorf("parse peer x25519: %w", err)
+	}
+	ssX, err := i.x25519.ECDH(pub)
+	if err != nil {
+		return PSK{}, fmt.Errorf("x25519 ecdh: %w", err)
+	}
+
+	return derivePSK(ssMLKEM, ssX, i.offer, answer, b)
+}
+
+// Respond consumes an initiator offer, produces the answer, and derives the PSK.
+func Respond(offer []byte, b Binding) (answer []byte, psk PSK, err error) {
+	if len(offer) != OfferSize {
+		return nil, PSK{}, fmt.Errorf("offer: got %d bytes, want %d", len(offer), OfferSize)
+	}
+	peerEK := offer[:mlkem.EncapsulationKeySize768]
+	peerX := offer[mlkem.EncapsulationKeySize768:]
+
+	ek, err := mlkem.NewEncapsulationKey768(peerEK)
+	if err != nil {
+		return nil, PSK{}, fmt.Errorf("parse peer ml-kem key: %w", err)
+	}
+	ssMLKEM, ct := ek.Encapsulate()
+
+	x, err := ecdh.X25519().GenerateKey(rand.Reader)
+	if err != nil {
+		return nil, PSK{}, fmt.Errorf("x25519 keygen: %w", err)
+	}
+	pub, err := ecdh.X25519().NewPublicKey(peerX)
+	if err != nil {
+		return nil, PSK{}, fmt.Errorf("parse peer x25519: %w", err)
+	}
+	ssX, err := x.ECDH(pub)
+	if err != nil {
+		return nil, PSK{}, fmt.Errorf("x25519 ecdh: %w", err)
+	}
+
+	answer = make([]byte, 0, AnswerSize)
+	answer = append(answer, ct...)
+	answer = append(answer, x.PublicKey().Bytes()...)
+
+	// derivePSK uses the same argument order on both sides; the responder's local
+	// binding is the mirror of the initiator's, canonicalised inside derivePSK.
+	psk, err = derivePSK(ssMLKEM, ssX, offer, answer, b)
+	if err != nil {
+		return nil, PSK{}, err
+	}
+	return answer, psk, nil
+}
+
+// derivePSK runs HKDF-SHA256 over the hybrid shared secret (ML-KEM_ss ‖ X25519_ss,
+// per draft-ietf-tls-ecdhe-mlkem), salted with the domain-separation label, and binds
+// the result — via the HKDF info — to the full transcript (offer ‖ answer) and the
+// canonicalised peer identities, so the PSK cannot be transplanted to another peer
+// pair or a different exchange.
+func derivePSK(ssMLKEM, ssX, offer, answer []byte, b Binding) (PSK, error) {
+	lo, hi := canonicalPair(b.LocalID, b.RemoteID)
+
+	ikm := make([]byte, 0, len(ssMLKEM)+len(ssX))
+	ikm = append(ikm, ssMLKEM...)
+	ikm = append(ikm, ssX...)
+
+	info := make([]byte, 0, len(offer)+len(answer)+len(lo)+len(hi))
+	info = append(info, offer...)
+	info = append(info, answer...)
+	info = append(info, lo...)
+	info = append(info, hi...)
+
+	var psk PSK
+	key, err := hkdf.Key(sha256.New, ikm, []byte(pskLabel), string(info), len(psk))
+	if err != nil {
+		return PSK{}, fmt.Errorf("hkdf derive psk: %w", err)
+	}
+	copy(psk[:], key)
+	return psk, nil
+}
+
+func canonicalPair(a, b []byte) (lo, hi []byte) {
+	if string(a) <= string(b) {
+		return a, b
+	}
+	return b, a
+}

client/internal/pqkem/kem_test.go

@@ -0,0 +1,89 @@
+package pqkem
+
+import (
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+)
+
+var (
+	wgA = []byte("peer-A-wireguard-pubkey-32bytes!")
+	wgB = []byte("peer-B-wireguard-pubkey-32bytes!")
+)
+
+func TestExchange_DerivesMatchingPSK(t *testing.T) {
+	init, err := NewInitiator()
+	require.NoError(t, err)
+
+	require.Len(t, init.Offer(), OfferSize)
+
+	answer, pskB, err := Respond(init.Offer(), Binding{LocalID: wgB, RemoteID: wgA})
+	require.NoError(t, err)
+	require.Len(t, answer, AnswerSize)
+
+	pskA, err := init.Finish(answer, Binding{LocalID: wgA, RemoteID: wgB})
+	require.NoError(t, err)
+
+	require.Equal(t, pskB, pskA, "both sides must derive the same PSK")
+	require.NotEqual(t, PSK{}, pskA, "PSK must not be zero")
+}
+
+func TestExchange_PSKBoundToPeerIdentities(t *testing.T) {
+	init, err := NewInitiator()
+	require.NoError(t, err)
+
+	// responder computes with the honest pair...
+	_, pskHonest, err := Respond(init.Offer(), Binding{LocalID: wgB, RemoteID: wgA})
+	require.NoError(t, err)
+
+	// ...a second responder run with a different peer identity yields a different PSK,
+	// even though the KEM material would otherwise combine identically.
+	wgC := []byte("peer-C-wireguard-pubkey-32bytes!")
+	_, pskWrong, err := Respond(init.Offer(), Binding{LocalID: wgC, RemoteID: wgA})
+	require.NoError(t, err)
+
+	require.NotEqual(t, pskHonest, pskWrong, "PSK must be bound to the peer pair")
+}
+
+func TestExchange_RejectsMalformedMessages(t *testing.T) {
+	init, err := NewInitiator()
+	require.NoError(t, err)
+
+	_, _, err = Respond(init.Offer()[:10], Binding{})
+	require.Error(t, err)
+
+	_, err = init.Finish([]byte("too short"), Binding{})
+	require.Error(t, err)
+}
+
+// TestExchange_ReportSizesAndTiming is a spike measurement, not a pass/fail gate.
+// Run with: go test -run TestExchange_ReportSizesAndTiming -v ./client/internal/pqkem/
+func TestExchange_ReportSizesAndTiming(t *testing.T) {
+	const iters = 200
+
+	var tInit, tResp, tFinish time.Duration
+	for i := 0; i < iters; i++ {
+		s0 := time.Now()
+		init, err := NewInitiator()
+		require.NoError(t, err)
+		tInit += time.Since(s0)
+
+		s1 := time.Now()
+		answer, _, err := Respond(init.Offer(), Binding{LocalID: wgB, RemoteID: wgA})
+		require.NoError(t, err)
+		tResp += time.Since(s1)
+
+		s2 := time.Now()
+		_, err = init.Finish(answer, Binding{LocalID: wgA, RemoteID: wgB})
+		require.NoError(t, err)
+		tFinish += time.Since(s2)
+	}
+
+	t.Logf("wire sizes:   offer=%d B   answer=%d B   (Rosenpass static pubkey ~524160 B)", OfferSize, AnswerSize)
+	t.Logf("total on-wire per handshake: %d B  (~%.0fx smaller than RP static key)", OfferSize+AnswerSize, 524160.0/float64(OfferSize+AnswerSize))
+	t.Logf("avg NewInitiator (keygen): %s", tInit/iters)
+	t.Logf("avg Respond (encaps+dh):   %s", tResp/iters)
+	t.Logf("avg Finish (decaps+dh):    %s", tFinish/iters)
+	t.Logf("avg full handshake CPU:    %s", (tInit+tResp+tFinish)/iters)
+}

client/internal/pqkem/manager.go

@@ -0,0 +1,399 @@
+package pqkem
+
+import (
+	"context"
+	"crypto/rand"
+	"fmt"
+	"log/slog"
+	"net/netip"
+	"sync"
+	"time"
+)
+
+const (
+	// DefaultRetryInterval is how often the initiator retransmits its outstanding
+	// data-path offer while awaiting the answer.
+	DefaultRetryInterval = 2 * time.Second
+	// DefaultMaxRetries bounds how many ticks an exchange may run before it is
+	// declared failed. The convergence deadline is thus MaxRetries * RetryInterval.
+	DefaultMaxRetries = 10
+	// DefaultMaxRekeyFailures is how many consecutive rekey (non-initial) failures
+	// are tolerated before OnRekeyFailed. The initial exchange fails immediately.
+	DefaultMaxRekeyFailures = 3
+
+	// rotationActivityWindow gates rotation on recent real-data activity: a rekey
+	// clocks a rotation only if the peer exchanged user data within this window. It
+	// must stay shorter than the data path's rekey interval (WireGuard
+	// REKEY_AFTER_TIME ~120s) so the rotation's own traffic — which itself renews the
+	// activity signal — ages out before the next rekey, letting an idle tunnel stop
+	// rotating instead of self-sustaining.
+	rotationActivityWindow = 90 * time.Second
+)
+
+// LocalID and RemoteID are peer identity keys (e.g. WireGuard public keys). They are
+// distinct types so the local and a remote identity cannot be mixed up.
+type (
+	LocalID  string
+	RemoteID string
+)
+
+// Transport is the data-path socket the Manager drives (the analogue of
+// go-rosenpass's Conn). It is a dumb mover of bytes to/from endpoints: the Manager
+// owns the remoteID<->endpoint routing and hands the transport a resolved endpoint
+// to Send, and reverse-resolves the source of each inbound datagram. Its lifecycle
+// belongs to the Manager (Run at Start, Close at Stop).
+type Transport interface {
+	// Send delivers msg to the given data-path endpoint.
+	Send(endpoint netip.AddrPort, msg []byte) error
+	// LocalPort is the bound local UDP port, announced to peers so they know where
+	// to send data-path messages.
+	LocalPort() int
+	// Run starts delivering inbound datagrams as (source endpoint, msg) to onInbound
+	// and returns immediately; it runs until Close.
+	Run(onInbound func(src netip.AddrPort, msg []byte))
+	// Close stops delivery and releases the socket.
+	Close() error
+}
+
+// exchangeState is the single source of truth for an exchange's role and phase.
+type exchangeState uint8
+
+const (
+	stateReserved       exchangeState = iota // responder: deriving the answer
+	stateAwaitingAnswer                      // initiator: offer sent, awaiting the answer
+	stateAwaitingRekey                       // initiator: PSK derived+set, awaiting OnDataPathRekeyed to chain the next offer
+	stateAwaitingAck                         // responder: answer sent, awaiting the next offer that acks this exchange
+)
+
+// exchangeCtl holds all state for one in-flight exchange with a peer, under the
+// Manager's single lock. state drives every decision. lastSent is the current
+// data-path retransmit payload (the offer, for the initiator). initiator is the
+// ephemeral handle used at Finish; pendingPSK is the responder's derived key.
+// viaSignal records that the offer went to the host for the signalling channel, so
+// the loop does not retransmit it on the data path. Only the initiator runs a
+// retransmit loop, so only it sets cancel.
+type exchangeCtl struct {
+	id         ExchangeID
+	state      exchangeState
+	startedAt  time.Time
+	cancel     context.CancelFunc
+	lastSent   []byte
+	initiator  *Initiator
+	pendingPSK PSK
+	viaSignal  bool
+}
+
+// Manager is the stateful orchestrator — the analogue of go-rosenpass's Server. It
+// drives the X25519MLKEM768 exchange, owns the peer endpoint routing and the data-path
+// transport, and surfaces the derived PSK and convergence to the host via
+// CallbackHandler. It is event-driven: the bootstrap is triggered by the host
+// (SignalOffer) and each rotation is clocked by OnDataPathRekeyed. The cryptography is
+// the pure kem.go primitives; all state lives here under one lock.
+type Manager struct {
+	localID   LocalID
+	cbHandler CallbackHandler
+	logger    *slog.Logger
+
+	retryInterval    time.Duration
+	maxRetries       int
+	maxRekeyFailures int
+
+	rootCtx    context.Context
+	rootCancel context.CancelFunc
+
+	mu          sync.Mutex
+	transport   Transport
+	exchanges   map[RemoteID]*exchangeCtl   // in-flight exchange per peer
+	established map[RemoteID]bool           // peer has completed at least one exchange
+	failures    map[RemoteID]int            // consecutive rekey failures per peer
+	psks        map[RemoteID]PSK            // latest derived PSK per peer (pulled at WG peer-config time)
+	peerAddrs   map[RemoteID]netip.AddrPort // remoteID -> data-path endpoint (send routing)
+	peersByAddr map[netip.AddrPort]RemoteID // reverse: source endpoint -> remoteID (inbound)
+	wait        sync.WaitGroup
+}
+
+// NewManager builds a manager for the local peer identified by its peer identity key
+// (used for the deterministic initiator role and the identity binding). A nil logger
+// falls back to slog.Default(). Install the data-path transport with Start.
+func NewManager(localID LocalID, h CallbackHandler, logger *slog.Logger) *Manager {
+	if logger == nil {
+		logger = slog.Default()
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	return &Manager{
+		localID:          localID,
+		cbHandler:        h,
+		logger:           logger,
+		retryInterval:    DefaultRetryInterval,
+		maxRetries:       DefaultMaxRetries,
+		maxRekeyFailures: DefaultMaxRekeyFailures,
+		rootCtx:          ctx,
+		rootCancel:       cancel,
+		exchanges:        make(map[RemoteID]*exchangeCtl),
+		established:      make(map[RemoteID]bool),
+		failures:         make(map[RemoteID]int),
+		psks:             make(map[RemoteID]PSK),
+		peerAddrs:        make(map[RemoteID]netip.AddrPort),
+		peersByAddr:      make(map[netip.AddrPort]RemoteID),
+	}
+}
+
+// Start installs the data-path transport and begins its inbound delivery. The Manager
+// owns it from here; Stop closes it. Start/Stop are the transport lifecycle pair.
+func (m *Manager) Start(t Transport) {
+	m.mu.Lock()
+	m.transport = t
+	m.mu.Unlock()
+	if t != nil {
+		t.Run(m.onDataPathInbound)
+	}
+}
+
+// LocalPort is the data-path transport's bound UDP port (0 if no transport), to be
+// announced to peers.
+func (m *Manager) LocalPort() int {
+	m.mu.Lock()
+	t := m.transport
+	m.mu.Unlock()
+	if t == nil {
+		return 0
+	}
+	return t.LocalPort()
+}
+
+// IsInitiator reports whether the local peer drives the exchange for this remote
+// peer. Roles are deterministic (lexicographic identity-key compare) so exactly one
+// side initiates, mirroring how Rosenpass picks its handshake initiator.
+func (m *Manager) IsInitiator(remoteID RemoteID) bool {
+	return string(m.localID) > string(remoteID)
+}
+
+// PSK returns the latest PSK derived for the peer, for the host to program at WG
+// peer-config time (the pull path). ok is false until an exchange has derived one.
+func (m *Manager) PSK(remoteID RemoteID) (PSK, bool) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	psk, ok := m.psks[remoteID]
+	return psk, ok
+}
+
+// trace logs at LevelTrace, the verbose per-exchange lifecycle level gated by
+// NB_PQ_MLKEM_LOG_LEVEL=trace.
+func (m *Manager) trace(msg string, args ...any) {
+	m.logger.Log(context.Background(), LevelTrace, msg, args...)
+}
+
+// AddPeer registers where a peer's data-path messages are sent and received: its
+// overlay endpoint (IP:port). Re-adding updates the endpoint.
+func (m *Manager) AddPeer(remoteID RemoteID, endpoint netip.AddrPort) {
+	if !endpoint.IsValid() {
+		return
+	}
+	m.mu.Lock()
+	if old, ok := m.peerAddrs[remoteID]; ok {
+		delete(m.peersByAddr, old)
+	}
+	m.peerAddrs[remoteID] = endpoint
+	m.peersByAddr[endpoint] = remoteID
+	m.mu.Unlock()
+}
+
+// RemovePeer stops any in-flight exchange for a peer and drops its state and routing.
+func (m *Manager) RemovePeer(remoteID RemoteID) {
+	m.mu.Lock()
+	if ex, ok := m.exchanges[remoteID]; ok {
+		if ex.cancel != nil {
+			ex.cancel()
+		}
+		delete(m.exchanges, remoteID)
+	}
+	delete(m.established, remoteID)
+	delete(m.failures, remoteID)
+	delete(m.psks, remoteID)
+	if ep, ok := m.peerAddrs[remoteID]; ok {
+		delete(m.peersByAddr, ep)
+		delete(m.peerAddrs, remoteID)
+	}
+	m.mu.Unlock()
+}
+
+// Stop cancels all in-flight exchanges, closes the transport, and waits for the
+// exchange goroutines to exit.
+func (m *Manager) Stop() {
+	m.rootCancel()
+	m.wait.Wait()
+	m.mu.Lock()
+	t := m.transport
+	m.transport = nil
+	m.exchanges = make(map[RemoteID]*exchangeCtl)
+	m.psks = make(map[RemoteID]PSK)
+	m.mu.Unlock()
+	if t != nil {
+		if err := t.Close(); err != nil {
+			m.logger.Warn("pqkem: closing data-path transport", "err", err)
+		}
+	}
+}
+
+// ---- Signalling channel (host-driven; rides the host's negotiation) ----
+
+// SignalOffer returns the KEM offer for the host to embed in its outgoing offer to
+// remoteID (bootstrap). It returns (nil, nil) when the local peer is not the
+// initiator. It is idempotent for an in-flight bootstrap: a repeat call returns the
+// same offer rather than starting a new exchange.
+func (m *Manager) SignalOffer(remoteID RemoteID) ([]byte, error) {
+	if !m.IsInitiator(remoteID) {
+		return nil, nil
+	}
+	m.mu.Lock()
+	if ex := m.exchanges[remoteID]; ex != nil && ex.viaSignal && ex.state == stateAwaitingAnswer {
+		last := ex.lastSent
+		m.mu.Unlock()
+		return last, nil
+	}
+	m.mu.Unlock()
+	// bootstrap offer acknowledges nothing (zero AckID).
+	return m.startExchange(remoteID, true, ExchangeID{})
+}
+
+// SignalOnOffer processes a KEM offer the host extracted from an incoming offer and
+// returns the KEM answer for the host to embed in its outgoing answer.
+func (m *Manager) SignalOnOffer(remoteID RemoteID, offer []byte) ([]byte, error) {
+	typ, msg, err := Decode(offer)
+	if err != nil {
+		return nil, fmt.Errorf("decode signal offer from %s: %w", remoteID, err)
+	}
+	if typ != MsgOffer {
+		return nil, fmt.Errorf("expected offer from %s, got type %d", remoteID, typ)
+	}
+	return m.processOffer(remoteID, msg.(*OfferMsg))
+}
+
+// SignalOnAnswer processes a KEM answer the host extracted from an incoming answer.
+// There is no reply: the next offer (over the data path) acknowledges this exchange.
+func (m *Manager) SignalOnAnswer(remoteID RemoteID, answer []byte) error {
+	typ, msg, err := Decode(answer)
+	if err != nil {
+		return fmt.Errorf("decode signal answer from %s: %w", remoteID, err)
+	}
+	if typ != MsgAnswer {
+		return fmt.Errorf("expected answer from %s, got type %d", remoteID, typ)
+	}
+	return m.processAnswer(remoteID, msg.(*AnswerMsg))
+}
+
+// ---- Data path ----
+
+// onDataPathInbound is the transport's inbound handler: it reverse-resolves the
+// source endpoint to a peer and dispatches. Unknown sources are dropped.
+func (m *Manager) onDataPathInbound(src netip.AddrPort, msg []byte) {
+	m.mu.Lock()
+	remoteID, ok := m.peersByAddr[src]
+	m.mu.Unlock()
+	if !ok {
+		return
+	}
+	if err := m.OnDataPathMessage(remoteID, msg); err != nil {
+		m.trace("pqkem: inbound", "peer", remoteID, "err", err)
+	}
+}
+
+// OnDataPathMessage handles a KEM message received over the data path from remoteID
+// and pushes any reply back over the data path.
+func (m *Manager) OnDataPathMessage(remoteID RemoteID, raw []byte) error {
+	typ, msg, err := Decode(raw)
+	if err != nil {
+		return fmt.Errorf("decode data-path msg from %s: %w", remoteID, err)
+	}
+	switch typ {
+	case MsgOffer:
+		answer, err := m.processOffer(remoteID, msg.(*OfferMsg))
+		if err != nil {
+			return err
+		}
+		if answer == nil {
+			return nil
+		}
+		return m.pushDataPath(remoteID, answer)
+	case MsgAnswer:
+		return m.processAnswer(remoteID, msg.(*AnswerMsg))
+	default:
+		return fmt.Errorf("unhandled data-path message type %d from %s", typ, remoteID)
+	}
+}
+
+// OnDataPathRekeyed notifies that the peer's data path is up and freshly keyed with
+// the latest PSK (fired on first establishment AND every rekey). If we are the
+// initiator that just derived a PSK, it chains the next exchange: a fresh offer over
+// the data path that acknowledges the just-completed one (its arrival under the new
+// key proves to the responder that the key works).
+// OnDataPathRekeyed clocks the next chained PSK rotation on a fresh data-path rekey.
+// sinceActivity is how long ago the peer last exchanged real user data; when it
+// exceeds rotationActivityWindow the tunnel is treated as idle and rotation is
+// skipped — an idle tunnel has nothing to protect, and rotating would emit data-path
+// traffic that keeps the peer artificially active (see conn.onWGCheckSuccess).
+func (m *Manager) OnDataPathRekeyed(remoteID RemoteID, sinceActivity time.Duration) {
+	if sinceActivity >= rotationActivityWindow {
+		m.trace("pqkem: peer idle, skipping data-path rotation", "peer", remoteID, "since_activity", sinceActivity)
+		return
+	}
+
+	m.mu.Lock()
+	ex := m.exchanges[remoteID]
+	chain := ex != nil && ex.state == stateAwaitingRekey
+	var ackID ExchangeID
+	if chain {
+		ackID = ex.id
+	}
+	m.mu.Unlock()
+
+	m.trace("pqkem: data-path rekey signal", "peer", remoteID, "chaining", chain)
+	if !chain {
+		return
+	}
+	offer, err := m.startExchange(remoteID, false, ackID)
+	if err != nil {
+		m.logger.Error("pqkem: chain offer failed to start", "peer", remoteID, "err", err)
+		return
+	}
+	if err := m.pushDataPath(remoteID, offer); err != nil {
+		m.logger.Warn("pqkem: send chain offer failed", "peer", remoteID, "err", err)
+		return
+	}
+	m.trace("pqkem: chain offer sent over data path", "peer", remoteID)
+}
+
+// OnDataPathDown notifies that the peer's data path went down. Rotations resume once
+// the host re-bootstraps over signalling on reconnect; in-flight data-path sends will
+// simply fail until then. Reserved as an explicit hook.
+func (m *Manager) OnDataPathDown(remoteID RemoteID) {}
+
+// ---- internals ----
+
+// pushDataPath resolves the peer's endpoint and sends over the data-path transport,
+// erroring if the peer is unknown or no transport is set.
+func (m *Manager) pushDataPath(remoteID RemoteID, msg []byte) error {
+	m.mu.Lock()
+	ep, ok := m.peerAddrs[remoteID]
+	t := m.transport
+	m.mu.Unlock()
+	if !ok {
+		return fmt.Errorf("no data-path endpoint for peer %s", remoteID)
+	}
+	if t == nil {
+		return fmt.Errorf("no data-path transport")
+	}
+	return t.Send(ep, msg)
+}
+
+func (m *Manager) binding(remoteID RemoteID) Binding {
+	return Binding{LocalID: []byte(m.localID), RemoteID: []byte(remoteID)}
+}
+
+func newExchangeID() (ExchangeID, error) {
+	var id ExchangeID
+	if _, err := rand.Read(id[:]); err != nil {
+		return ExchangeID{}, fmt.Errorf("generate exchange id: %w", err)
+	}
+	return id, nil
+}

client/internal/pqkem/manager_test.go

@@ -0,0 +1,193 @@
+package pqkem
+
+import (
+	"fmt"
+	"net/netip"
+	"sync"
+	"sync/atomic"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+// netSwitch is an in-memory UDP fabric: transports register their endpoint and get
+// datagrams delivered to their inbound handler.
+type netSwitch struct {
+	mu sync.Mutex
+	h  map[netip.AddrPort]func(netip.AddrPort, []byte)
+}
+
+func newSwitch() *netSwitch {
+	return &netSwitch{h: map[netip.AddrPort]func(netip.AddrPort, []byte){}}
+}
+
+func (s *netSwitch) register(ep netip.AddrPort, fn func(netip.AddrPort, []byte)) {
+	s.mu.Lock()
+	s.h[ep] = fn
+	s.mu.Unlock()
+}
+
+func (s *netSwitch) deliver(dst, src netip.AddrPort, msg []byte) error {
+	s.mu.Lock()
+	fn := s.h[dst]
+	s.mu.Unlock()
+	if fn == nil {
+		return fmt.Errorf("no route to %s", dst)
+	}
+	fn(src, msg)
+	return nil
+}
+
+// loopback is an endpoint-based pqkem.Transport over a netSwitch, with a switchable
+// drop flag.
+type loopback struct {
+	ep   netip.AddrPort
+	sw   *netSwitch
+	drop atomic.Bool
+}
+
+func (l *loopback) Send(dst netip.AddrPort, msg []byte) error {
+	if l.drop.Load() {
+		return nil
+	}
+	return l.sw.deliver(dst, l.ep, append([]byte(nil), msg...))
+}
+
+func (l *loopback) LocalPort() int                             { return int(l.ep.Port()) }
+func (l *loopback) Run(onInbound func(netip.AddrPort, []byte)) { l.sw.register(l.ep, onInbound) }
+func (l *loopback) Close() error                               { return nil }
+
+type fakeWG struct {
+	mu     sync.Mutex
+	psks   map[RemoteID]PSK
+	failed []RemoteID
+}
+
+func newFakeWG() *fakeWG { return &fakeWG{psks: map[RemoteID]PSK{}} }
+
+func (f *fakeWG) OnNewPSKReady(remoteID RemoteID, psk PSK) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	f.psks[remoteID] = psk
+	return nil
+}
+
+func (f *fakeWG) OnRekeyFailed(remoteID RemoteID) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	f.failed = append(f.failed, remoteID)
+	return nil
+}
+
+func (f *fakeWG) psk(peer RemoteID) PSK {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return f.psks[peer]
+}
+
+var (
+	epA = netip.MustParseAddrPort("100.64.0.1:51833")
+	epB = netip.MustParseAddrPort("100.64.0.2:51833")
+)
+
+// pair builds two wired managers (B is the initiator, "bbbb" > "aaaa") sharing a
+// netSwitch, with each peer's data-path endpoint registered. lbB is B's loopback
+// (for toggling drop).
+func pair(t *testing.T) (dA, dB *Manager, wgA, wgB *fakeWG, lbB *loopback) {
+	t.Helper()
+	sw := newSwitch()
+	wgA = newFakeWG()
+	wgB = newFakeWG()
+	dA = NewManager("aaaa", wgA, nil)
+	dB = NewManager("bbbb", wgB, nil)
+	dA.Start(&loopback{ep: epA, sw: sw})
+	lbB = &loopback{ep: epB, sw: sw}
+	dB.Start(lbB)
+	dA.AddPeer("bbbb", epB)
+	dB.AddPeer("aaaa", epA)
+	return dA, dB, wgA, wgB, lbB
+}
+
+// bootstrap runs the signalling offer/answer (the test plays the host carrying bytes).
+func bootstrap(t *testing.T, dA, dB *Manager) {
+	t.Helper()
+	offer, err := dB.SignalOffer("aaaa")
+	require.NoError(t, err)
+	require.NotNil(t, offer)
+	answer, err := dA.SignalOnOffer("bbbb", offer)
+	require.NoError(t, err)
+	require.NotNil(t, answer)
+	require.NoError(t, dB.SignalOnAnswer("aaaa", answer))
+}
+
+func TestManager_BootstrapDerivesSamePSK(t *testing.T) {
+	dA, dB, wgA, wgB, _ := pair(t)
+	defer dA.Stop()
+	defer dB.Stop()
+
+	bootstrap(t, dA, dB)
+
+	pskA := wgA.psk("bbbb")
+	pskB := wgB.psk("aaaa")
+	require.NotEqual(t, PSK{}, pskA)
+	require.Equal(t, pskB, pskA, "both sides derive the same PSK from the bootstrap exchange")
+}
+
+func TestManager_ChainRotatesAndAcks(t *testing.T) {
+	dA, dB, wgA, wgB, _ := pair(t)
+	defer dA.Stop()
+	defer dB.Stop()
+
+	bootstrap(t, dA, dB)
+	psk1 := wgB.psk("aaaa")
+
+	// Data path up: B (initiator) chains the next offer over the data path, which
+	// rotates both to a fresh PSK and acknowledges A.
+	dA.OnDataPathRekeyed("bbbb", 0)
+	dB.OnDataPathRekeyed("aaaa", 0)
+
+	psk2A := wgA.psk("bbbb")
+	psk2B := wgB.psk("aaaa")
+	require.Equal(t, psk2B, psk2A, "both sides converge on the rotated PSK")
+	require.NotEqual(t, psk1, psk2B, "the chain rotated to a new PSK")
+}
+
+func TestManager_RotationSkippedWhenIdle(t *testing.T) {
+	dA, dB, wgA, wgB, _ := pair(t)
+	defer dA.Stop()
+	defer dB.Stop()
+
+	bootstrap(t, dA, dB)
+	psk1 := wgB.psk("aaaa")
+	require.NotEqual(t, PSK{}, psk1)
+
+	// Idle: the peer's last real-data activity is older than the window, so a rekey
+	// must NOT clock a rotation.
+	dA.OnDataPathRekeyed("bbbb", rotationActivityWindow)
+	dB.OnDataPathRekeyed("aaaa", rotationActivityWindow)
+	require.Equal(t, psk1, wgB.psk("aaaa"), "idle peer must not rotate the PSK")
+	require.Equal(t, psk1, wgA.psk("bbbb"), "idle peer must not rotate the PSK")
+
+	// Active: activity within the window clocks the rotation as usual.
+	dA.OnDataPathRekeyed("bbbb", rotationActivityWindow-1)
+	dB.OnDataPathRekeyed("aaaa", rotationActivityWindow-1)
+	psk2 := wgB.psk("aaaa")
+	require.NotEqual(t, psk1, psk2, "recent activity must clock a rotation")
+	require.Equal(t, psk2, wgA.psk("bbbb"), "both sides converge on the rotated PSK")
+}
+
+func TestManager_NonInitiatorReturnsNoOffer(t *testing.T) {
+	dA := NewManager("aaaa", newFakeWG(), nil)
+	defer dA.Stop()
+
+	offer, err := dA.SignalOffer("bbbb") // not the initiator vs "bbbb"
+	require.NoError(t, err)
+	require.Nil(t, offer)
+}
+
+func TestManager_StopIsIdempotent(t *testing.T) {
+	dA := NewManager("aaaa", newFakeWG(), nil)
+	dA.Start(&loopback{ep: epA, sw: newSwitch()})
+	dA.Stop()
+	dA.Stop() // must not panic or hang
+}

client/internal/pqkem/message.go

@@ -0,0 +1,121 @@
+package pqkem
+
+import (
+	"crypto/mlkem"
+	"fmt"
+)
+
+// Wire framing for the PQ-KEM exchange. Messages are self-contained, versioned,
+// transport-agnostic byte blobs: the same bytes ride the signalling channel
+// (initial bootstrap) or a data-tunnel packet (rekey). The library only ever sees
+// opaque []byte at the transport seam.
+//
+// Layout (all messages): [type:1][version:1][exchangeID:16][payload...]
+//
+// There is no confirm message: an exchange is acknowledged by the NEXT offer, which
+// carries the acked exchange's id (see OfferMsg.AckID) and — riding the data path
+// under the freshly adopted key — proves that key works.
+
+const (
+	// ProtocolVersion is bumped on any wire-incompatible change; a peer rejects
+	// messages it does not understand rather than misparsing them.
+	ProtocolVersion uint8 = 1
+
+	// ExchangeIDSize identifies one exchange so answers/acks correlate and stale
+	// messages are dropped.
+	ExchangeIDSize = 16
+
+	headerSize = 1 + 1 + ExchangeIDSize
+)
+
+// MsgType tags the two message kinds of the exchange.
+type MsgType uint8
+
+const (
+	MsgOffer MsgType = iota + 1
+	MsgAnswer
+)
+
+// ExchangeID is the per-exchange correlator. The zero value means "none" (an offer
+// that acknowledges nothing, i.e. the first exchange of a connection).
+type ExchangeID [ExchangeIDSize]byte
+
+// OfferMsg carries the initiator's public material (X25519 pub ‖ ML-KEM encap key)
+// and AckID, the id of the previous exchange this offer acknowledges (zero if none).
+type OfferMsg struct {
+	ExchangeID ExchangeID
+	AckID      ExchangeID
+	// KEMOffer is the raw Initiator.Offer() blob (OfferSize bytes).
+	KEMOffer []byte
+}
+
+// AnswerMsg carries the responder's reply (ML-KEM ciphertext ‖ X25519 pub) for the
+// round identified by ExchangeID.
+type AnswerMsg struct {
+	ExchangeID ExchangeID
+	// KEMAnswer is the raw Respond() answer blob (AnswerSize bytes).
+	KEMAnswer []byte
+}
+
+// Encode serialises the offer with its framed header (payload = AckID ‖ KEMOffer).
+func (m *OfferMsg) Encode() ([]byte, error) {
+	if len(m.KEMOffer) != OfferSize {
+		return nil, fmt.Errorf("offer payload: got %d, want %d", len(m.KEMOffer), OfferSize)
+	}
+	payload := make([]byte, 0, ExchangeIDSize+OfferSize)
+	payload = append(payload, m.AckID[:]...)
+	payload = append(payload, m.KEMOffer...)
+	return frame(MsgOffer, m.ExchangeID, payload), nil
+}
+
+// Encode serialises the answer with its framed header.
+func (m *AnswerMsg) Encode() ([]byte, error) {
+	if len(m.KEMAnswer) != AnswerSize {
+		return nil, fmt.Errorf("answer payload: got %d, want %d", len(m.KEMAnswer), AnswerSize)
+	}
+	return frame(MsgAnswer, m.ExchangeID, m.KEMAnswer), nil
+}
+
+// Decode parses a framed message into one of *OfferMsg / *AnswerMsg.
+func Decode(buf []byte) (MsgType, any, error) {
+	if len(buf) < headerSize {
+		return 0, nil, fmt.Errorf("message too short: %d bytes", len(buf))
+	}
+	typ := MsgType(buf[0])
+	if ver := buf[1]; ver != ProtocolVersion {
+		return typ, nil, fmt.Errorf("unsupported protocol version %d (want %d)", ver, ProtocolVersion)
+	}
+
+	var id ExchangeID
+	copy(id[:], buf[2:headerSize])
+	payload := buf[headerSize:]
+
+	switch typ {
+	case MsgOffer:
+		if len(payload) != ExchangeIDSize+OfferSize {
+			return typ, nil, fmt.Errorf("offer payload: got %d, want %d", len(payload), ExchangeIDSize+OfferSize)
+		}
+		var ack ExchangeID
+		copy(ack[:], payload[:ExchangeIDSize])
+		return typ, &OfferMsg{ExchangeID: id, AckID: ack, KEMOffer: payload[ExchangeIDSize:]}, nil
+	case MsgAnswer:
+		if len(payload) != AnswerSize {
+			return typ, nil, fmt.Errorf("answer payload: got %d, want %d", len(payload), AnswerSize)
+		}
+		return typ, &AnswerMsg{ExchangeID: id, KEMAnswer: payload}, nil
+	default:
+		return typ, nil, fmt.Errorf("unknown message type %d", typ)
+	}
+}
+
+func frame(typ MsgType, id ExchangeID, payload []byte) []byte {
+	buf := make([]byte, headerSize+len(payload))
+	buf[0] = byte(typ)
+	buf[1] = ProtocolVersion
+	copy(buf[2:], id[:])
+	copy(buf[headerSize:], payload)
+	return buf
+}
+
+// compile-time assurance the KEM blob sizes referenced here stay in sync with kem.go.
+var _ = [1]struct{}{}[OfferSize-(32+mlkem.EncapsulationKeySize768)]

client/internal/pqkem/message_test.go

@@ -0,0 +1,57 @@
+package pqkem
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestMessageRoundTrip(t *testing.T) {
+	init, err := NewInitiator()
+	require.NoError(t, err)
+	answer, _, err := Respond(init.Offer(), Binding{LocalID: wgB, RemoteID: wgA})
+	require.NoError(t, err)
+
+	id := ExchangeID{1, 2, 3, 4}
+	ack := ExchangeID{9, 9, 9}
+
+	offBytes, err := (&OfferMsg{ExchangeID: id, AckID: ack, KEMOffer: init.Offer()}).Encode()
+	require.NoError(t, err)
+	typ, decoded, err := Decode(offBytes)
+	require.NoError(t, err)
+	require.Equal(t, MsgOffer, typ)
+	require.Equal(t, id, decoded.(*OfferMsg).ExchangeID)
+	require.Equal(t, ack, decoded.(*OfferMsg).AckID)
+	require.Equal(t, init.Offer(), decoded.(*OfferMsg).KEMOffer)
+
+	ansBytes, err := (&AnswerMsg{ExchangeID: id, KEMAnswer: answer}).Encode()
+	require.NoError(t, err)
+	typ, decoded, err = Decode(ansBytes)
+	require.NoError(t, err)
+	require.Equal(t, MsgAnswer, typ)
+	require.Equal(t, answer, decoded.(*AnswerMsg).KEMAnswer)
+}
+
+func TestDecodeRejects(t *testing.T) {
+	// too short
+	_, _, err := Decode([]byte{1, 1})
+	require.Error(t, err)
+
+	// wrong version
+	bad := make([]byte, headerSize+ExchangeIDSize+OfferSize)
+	bad[0] = byte(MsgOffer)
+	bad[1] = ProtocolVersion + 1
+	_, _, err = Decode(bad)
+	require.Error(t, err)
+
+	// unknown type
+	bad2 := make([]byte, headerSize)
+	bad2[0] = 99
+	bad2[1] = ProtocolVersion
+	_, _, err = Decode(bad2)
+	require.Error(t, err)
+
+	// offer with wrong payload size
+	_, err = (&OfferMsg{KEMOffer: []byte{1, 2, 3}}).Encode()
+	require.Error(t, err)
+}

client/internal/pqkem_adapter.go

@@ -0,0 +1,114 @@
+package internal
+
+import (
+	"net/netip"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+
+	"github.com/netbirdio/netbird/client/internal/pqkem"
+)
+
+// pqPresharedKeySetter is the subset of the WireGuard interface the ML-KEM callback
+// needs: programming a peer's preshared key. *iface.WGIface satisfies it.
+type pqPresharedKeySetter interface {
+	SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error
+}
+
+// pqCallbackHandler programs the derived PQ PSK onto the WireGuard peer. It is the
+// engine-side implementation of pqkem.CallbackHandler.
+type pqCallbackHandler struct {
+	wg pqPresharedKeySetter
+	// reoffer re-bootstraps the KEM over Signal for a peer (a fresh signalling offer)
+	// to recover from a persistent data-path rekey failure. Nil disables recovery.
+	reoffer func(remoteKey string)
+}
+
+// OnNewPSKReady programs the freshly derived PSK for the peer (updateOnly: a no-op
+// if the peer is not present, mirroring Rosenpass). remoteID is the peer's WG pubkey.
+func (h pqCallbackHandler) OnNewPSKReady(remoteID pqkem.RemoteID, psk pqkem.PSK) error {
+	// updateOnly: applies to an already-configured peer (rotation). At bootstrap the
+	// peer is not configured yet, so this is a no-op there and the PSK is instead
+	// pulled at peer-config time (pqHandshaker.PSK / conn.presharedKey).
+	log.Tracef("pqkem: programming PSK for peer %s", remoteID)
+	return h.wg.SetPresharedKey(string(remoteID), wgtypes.Key(psk), true)
+}
+
+// OnRekeyFailed reports a failed PQ (re)key convergence and re-bootstraps the KEM over
+// Signal to recover: a fresh signalling offer starts a new exchange that overwrites the
+// stalled PSK on both sides, resyncing after a persistent data-path desync. The tunnel
+// stays up on the previous PSK meanwhile (the Signal channel is independent of the
+// broken data path).
+func (h pqCallbackHandler) OnRekeyFailed(remoteID pqkem.RemoteID) error {
+	log.Warnf("pqkem: post-quantum rekey failed for peer %s, re-bootstrapping over signal", remoteID)
+	if h.reoffer != nil {
+		h.reoffer(string(remoteID))
+	}
+	return nil
+}
+
+// pqHandshaker adapts the pqkem manager to peer.PQHandshaker (string peer keys),
+// wiring the host's signalling offers/answers to the KEM exchange.
+type pqHandshaker struct {
+	mgr *pqkem.Manager
+}
+
+func (p pqHandshaker) OfferPayload(remoteKey string) ([]byte, int) {
+	payload, err := p.mgr.SignalOffer(pqkem.RemoteID(remoteKey))
+	if err != nil {
+		log.Warnf("pqkem: build offer for %s: %v", remoteKey, err)
+	}
+	return payload, p.mgr.LocalPort()
+}
+
+func (p pqHandshaker) AnswerPayload(remoteKey string, recvOffer []byte) ([]byte, int) {
+	if len(recvOffer) == 0 {
+		return nil, p.mgr.LocalPort()
+	}
+	payload, err := p.mgr.SignalOnOffer(pqkem.RemoteID(remoteKey), recvOffer)
+	if err != nil {
+		log.Warnf("pqkem: build answer for %s: %v", remoteKey, err)
+	}
+	return payload, p.mgr.LocalPort()
+}
+
+func (p pqHandshaker) OnAnswer(remoteKey string, recvAnswer []byte) {
+	if len(recvAnswer) == 0 {
+		return
+	}
+	if err := p.mgr.SignalOnAnswer(pqkem.RemoteID(remoteKey), recvAnswer); err != nil {
+		log.Warnf("pqkem: process answer from %s: %v", remoteKey, err)
+	}
+}
+
+// PSK exposes the peer's derived PSK for the conn to program at WG peer-config time.
+func (p pqHandshaker) PSK(remoteKey string) (wgtypes.Key, bool) {
+	psk, ok := p.mgr.PSK(pqkem.RemoteID(remoteKey))
+	if !ok {
+		return wgtypes.Key{}, false
+	}
+	return wgtypes.Key(psk), true
+}
+
+// SetRemoteAddr registers the peer's data-path endpoint (overlay IP + pq UDP port)
+// learned from signalling. Sends only ever fire once the tunnel is up (clocked by
+// OnDataPathRekeyed), so registering here is safe even before connection-up.
+func (p pqHandshaker) SetRemoteAddr(remoteKey string, addr netip.AddrPort) {
+	if !addr.IsValid() || addr.Port() == 0 {
+		return
+	}
+	p.mgr.AddPeer(pqkem.RemoteID(remoteKey), addr)
+}
+
+// OnDataPathRekeyed clocks the next chained PSK rotation on a fresh WG handshake.
+// sinceActivity is how long ago the peer last exchanged real user data; the manager
+// skips rotation for idle tunnels.
+func (p pqHandshaker) OnDataPathRekeyed(remoteKey string, sinceActivity time.Duration) {
+	p.mgr.OnDataPathRekeyed(pqkem.RemoteID(remoteKey), sinceActivity)
+}
+
+// OnDataPathDown signals the peer's tunnel went down.
+func (p pqHandshaker) OnDataPathDown(remoteKey string) {
+	p.mgr.OnDataPathDown(pqkem.RemoteID(remoteKey))
+}

client/internal/pqkem_transport.go

@@ -0,0 +1,72 @@
+package internal
+
+import (
+	"fmt"
+	"net"
+	"net/netip"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// DefaultPort is the preferred UDP port for the ML-KEM data-path service, bound on
+// the WG overlay IP. Since each client owns a distinct overlay IP, this port is
+// almost always free, so it need not be announced (peers assume it). A peer only
+// announces Body.mlkemPort when a collision forced it onto a different port.
+const DefaultPort = 51833
+
+// pqTransport is the ML-KEM data-path transport: a dumb UDP socket bound on the WG
+// overlay IP. It implements pqkem.Transport — the manager owns the remoteID<->endpoint
+// routing and drives this socket's lifecycle (Run / Close).
+type pqTransport struct {
+	conn *net.UDPConn
+	port int
+}
+
+// newPQTransport binds a UDP socket on the WG overlay IP, preferring DefaultPort and
+// falling back to an OS-assigned ephemeral port if it is in use. Call it after the WG
+// interface is up so the overlay IP is assigned; when the bound port is not
+// DefaultPort it must be announced to peers via Body.mlkemPort.
+func newPQTransport(overlayIP netip.Addr) (*pqTransport, error) {
+	if !overlayIP.IsValid() {
+		return nil, fmt.Errorf("invalid overlay IP for pqkem transport")
+	}
+	ip := net.IP(overlayIP.AsSlice())
+	conn, err := net.ListenUDP("udp4", &net.UDPAddr{IP: ip, Port: DefaultPort})
+	if err != nil {
+		log.Debugf("pqkem: default port %d unavailable on %s (%v), using an ephemeral port", DefaultPort, overlayIP, err)
+		conn, err = net.ListenUDP("udp4", &net.UDPAddr{IP: ip, Port: 0})
+		if err != nil {
+			return nil, fmt.Errorf("bind pqkem udp on overlay %s: %w", overlayIP, err)
+		}
+	}
+	return &pqTransport{conn: conn, port: conn.LocalAddr().(*net.UDPAddr).Port}, nil
+}
+
+// Send implements pqkem.Transport.
+func (t *pqTransport) Send(endpoint netip.AddrPort, msg []byte) error {
+	_, err := t.conn.WriteToUDPAddrPort(msg, endpoint)
+	return err
+}
+
+// LocalPort implements pqkem.Transport.
+func (t *pqTransport) LocalPort() int { return t.port }
+
+// Run implements pqkem.Transport: the receive loop, delivering each datagram as
+// (source endpoint, msg). Exits when the socket is closed.
+func (t *pqTransport) Run(onInbound func(src netip.AddrPort, msg []byte)) {
+	go func() {
+		buf := make([]byte, 2048)
+		for {
+			n, src, err := t.conn.ReadFromUDPAddrPort(buf)
+			if err != nil {
+				return
+			}
+			msg := make([]byte, n)
+			copy(msg, buf[:n])
+			onInbound(src, msg)
+		}
+	}()
+}
+
+// Close implements pqkem.Transport.
+func (t *pqTransport) Close() error { return t.conn.Close() }

client/internal/profilemanager/config.go

@@ -746,13 +746,6 @@ func (config *Config) applyMDMPolicy(policy *mdm.Policy) {
 // appended for https or ":80" for http. The serviceName parameter is
 // used to contextualise error messages. On success returns the parsed
 // *url.URL; on failure returns a non-nil error.
-// ParseServiceURL normalises a service URL exactly as the config layer does when
-// it stores one, so callers comparing a requested URL against a stored one do not
-// have to reimplement the scheme validation and default-port handling.
-func ParseServiceURL(serviceName, serviceURL string) (*url.URL, error) {
-	return parseURL(serviceName, serviceURL)
-}
-
 func parseURL(serviceName, serviceURL string) (*url.URL, error) {
 	parsedMgmtURL, err := url.ParseRequestURI(serviceURL)
 	if err != nil {

client/internal/routemanager/dnsinterceptor/handler.go

@@ -95,7 +95,7 @@ func (d *DnsInterceptor) RemoveRoute() error {
 
 			// AllowedIPs should use real IPs
 			if d.currentPeerKey != "" {
-				if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
+				if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
 					merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
 				}
 			}
@@ -172,7 +172,7 @@ func (d *DnsInterceptor) removeAllowedIP(realPrefix netip.Prefix) error {
 	}
 
 	// AllowedIPs use real IPs
-	if _, err := d.allowedIPsRefcounter.Decrement(realPrefix, d.currentPeerKey); err != nil {
+	if _, err := d.allowedIPsRefcounter.Decrement(realPrefix); err != nil {
 		return fmt.Errorf("remove allowed IP %s: %v", realPrefix, err)
 	}
 
@@ -205,7 +205,7 @@ func (d *DnsInterceptor) RemoveAllowedIPs() error {
 	for _, prefixes := range d.interceptedDomains {
 		for _, prefix := range prefixes {
 			// AllowedIPs use real IPs
-			if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
+			if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
 			}
 		}

client/internal/routemanager/dynamic/route.go

@@ -135,7 +135,7 @@ func (r *Route) RemoveAllowedIPs() error {
 	var merr *multierror.Error
 	for _, domainPrefixes := range r.dynamicDomains {
 		for _, prefix := range domainPrefixes {
-			if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
+			if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
 			}
 		}
@@ -320,7 +320,7 @@ func (r *Route) removeRoutes(prefixes []netip.Prefix) ([]netip.Prefix, error) {
 			merr = multierror.Append(merr, fmt.Errorf("remove dynamic route for IP %s: %w", prefix, err))
 		}
 		if r.currentPeerKey != "" {
-			if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
+			if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
 			}
 		}

client/internal/routemanager/manager.go

@@ -52,10 +52,6 @@ type Manager interface {
 	UpdateRoutes(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error
 	ClassifyRoutes(newRoutes []*route.Route) (map[route.ID]*route.Route, route.HAMap)
 	TriggerSelection(route.HAMap)
-	SelectRoutes(ids []route.NetID, appendRoute bool) error
-	DeselectRoutes(ids []route.NetID) error
-	SelectAllRoutes()
-	DeselectAllRoutes()
 	GetRouteSelector() *routeselector.RouteSelector
 	GetClientRoutes() route.HAMap
 	GetSelectedClientRoutes() route.HAMap
@@ -220,7 +216,7 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) {
 		)
 	}
 
-	m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
+	m.allowedIPsRefCounter = refcounter.New(
 		func(prefix netip.Prefix, peerKey string) (string, error) {
 			// save peerKey to use it in the remove function
 			return peerKey, m.wgInterface.AddAllowedIP(peerKey, prefix)
@@ -804,7 +800,7 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 	var info exitNodeInfo
 
 	for haID, routes := range clientRoutes {
-		if !isExitNodeRoutes(routes) {
+		if !m.isExitNodeRoute(routes) {
 			continue
 		}
 
@@ -824,6 +820,13 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 	return info
 }
 
+func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool {
+	if len(routes) == 0 {
+		return false
+	}
+	return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)
+}
+
 func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) {
 	if m.routeSelector.IsSelected(netID) {
 		info.userSelected = append(info.userSelected, netID)

client/internal/routemanager/mock.go

@@ -16,8 +16,6 @@ type MockManager struct {
 	ClassifyRoutesFunc           func(routes []*route.Route) (map[route.ID]*route.Route, route.HAMap)
 	UpdateRoutesFunc             func(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error
 	TriggerSelectionFunc         func(haMap route.HAMap)
-	SelectRoutesFunc             func(ids []route.NetID, appendRoute bool) error
-	DeselectRoutesFunc           func(ids []route.NetID) error
 	GetRouteSelectorFunc         func() *routeselector.RouteSelector
 	GetClientRoutesFunc          func() route.HAMap
 	GetSelectedClientRoutesFunc  func() route.HAMap
@@ -57,30 +55,6 @@ func (m *MockManager) TriggerSelection(networks route.HAMap) {
 	}
 }
 
-// SelectRoutes mock implementation of SelectRoutes from Manager interface
-func (m *MockManager) SelectRoutes(ids []route.NetID, appendRoute bool) error {
-	if m.SelectRoutesFunc != nil {
-		return m.SelectRoutesFunc(ids, appendRoute)
-	}
-	return nil
-}
-
-// DeselectRoutes mock implementation of DeselectRoutes from Manager interface
-func (m *MockManager) DeselectRoutes(ids []route.NetID) error {
-	if m.DeselectRoutesFunc != nil {
-		return m.DeselectRoutesFunc(ids)
-	}
-	return nil
-}
-
-// SelectAllRoutes mock implementation of SelectAllRoutes from Manager interface
-func (m *MockManager) SelectAllRoutes() {
-}
-
-// DeselectAllRoutes mock implementation of DeselectAllRoutes from Manager interface
-func (m *MockManager) DeselectAllRoutes() {
-}
-
 // GetRouteSelector mock implementation of GetRouteSelector from Manager interface
 func (m *MockManager) GetRouteSelector() *routeselector.RouteSelector {
 	if m.GetRouteSelectorFunc != nil {

client/internal/routemanager/notifier/notifier_ios.go

@@ -3,6 +3,7 @@
 package notifier
 
 import (
+	"container/list"
 	"net/netip"
 	"slices"
 	"sort"
@@ -15,12 +16,20 @@ import (
 
 type Notifier struct {
 	mu              sync.Mutex
+	cond            *sync.Cond
 	currentPrefixes []string
 	listener        listener.NetworkChangeListener
+	queue           *list.List
+	closed          bool
 }
 
 func NewNotifier() *Notifier {
-	return &Notifier{}
+	n := &Notifier{
+		queue: list.New(),
+	}
+	n.cond = sync.NewCond(&n.mu)
+	go n.deliverLoop()
+	return n
 }
 
 func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
@@ -50,19 +59,44 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) {
 	sort.Strings(newNets)
 
 	n.mu.Lock()
-	defer n.mu.Unlock()
 	if slices.Equal(n.currentPrefixes, newNets) {
+		n.mu.Unlock()
 		return
 	}
 	n.currentPrefixes = newNets
-	if n.listener != nil {
-		n.listener.OnNetworkChanged(strings.Join(n.currentPrefixes, ","))
-	}
+	routes := strings.Join(n.currentPrefixes, ",")
+	n.queue.PushBack(routes)
+	n.cond.Signal()
+	n.mu.Unlock()
 }
 
 func (n *Notifier) Close() {
+	n.mu.Lock()
+	n.closed = true
+	n.cond.Signal()
+	n.mu.Unlock()
 }
 
 func (n *Notifier) GetInitialRouteRanges() []string {
 	return nil
 }
+
+func (n *Notifier) deliverLoop() {
+	for {
+		n.mu.Lock()
+		for n.queue.Len() == 0 && !n.closed {
+			n.cond.Wait()
+		}
+		if n.closed && n.queue.Len() == 0 {
+			n.mu.Unlock()
+			return
+		}
+		routes := n.queue.Remove(n.queue.Front()).(string)
+		l := n.listener
+		n.mu.Unlock()
+
+		if l != nil {
+			l.OnNetworkChanged(routes)
+		}
+	}
+}

client/internal/routemanager/reconcile_test.go

@@ -54,7 +54,7 @@ func (m *reconcileWGMock) GetNet() *netstack.Net                      { return n
 func TestReconcilePeerAllowedIPs(t *testing.T) {
 	wg := &reconcileWGMock{}
 	m := &DefaultManager{wgInterface: wg}
-	m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
+	m.allowedIPsRefCounter = refcounter.New[netip.Prefix, string, string](
 		func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil },
 		func(netip.Prefix, string) error { return nil },
 	)

client/internal/routemanager/refcounter/allowedips.go

@@ -1,206 +0,0 @@
-package refcounter
-
-import (
-	"errors"
-	"fmt"
-	"net/netip"
-	"sort"
-	"sync"
-
-	"github.com/hashicorp/go-multierror"
-
-	nberrors "github.com/netbirdio/netbird/client/errors"
-)
-
-// allowedIPsEntry holds the per-peer reference counts for a single prefix and which peer is
-// currently installed in WireGuard. WireGuard allows a prefix on exactly one peer, so at most
-// one peer is active at a time even when several peers reference the prefix.
-type allowedIPsEntry struct {
-	// peers maps a peerKey to the number of references holding the prefix for that peer.
-	peers map[string]int
-	// active is the peerKey currently installed in WireGuard for this prefix ("" if none).
-	active string
-	// total is the sum of all per-peer reference counts (kept in sync with peers).
-	total int
-}
-
-// AllowedIPsRefCounter is a peer-aware reference counter for WireGuard AllowedIPs.
-//
-// The generic Counter keys only by prefix and remembers a single Out value set by the first
-// caller, which it never changes. That is wrong for AllowedIPs: two independent watchers (or
-// multiple resolved domains) can reference the same prefix through different peers, and when the
-// peer currently installed in WireGuard releases its last reference the prefix must be handed over
-// to a surviving peer instead of being left pointing at the released one.
-//
-// It calls add/remove (which program WireGuard) only on the transitions that matter:
-//   - add on the first reference for a prefix, or when swapping the active peer;
-//   - remove on the last reference for a prefix, or on the old peer during a swap.
-type AllowedIPsRefCounter struct {
-	mu      sync.Mutex
-	entries map[netip.Prefix]*allowedIPsEntry
-	add     AddFunc[netip.Prefix, string, string]
-	remove  RemoveFunc[netip.Prefix, string]
-}
-
-// NewAllowedIPs creates a new peer-aware AllowedIPs reference counter.
-// add programs a prefix on a peer in WireGuard and returns the peerKey to store as the active peer.
-// remove unprograms the prefix from the given peer.
-func NewAllowedIPs(add AddFunc[netip.Prefix, string, string], remove RemoveFunc[netip.Prefix, string]) *AllowedIPsRefCounter {
-	return &AllowedIPsRefCounter{
-		entries: map[netip.Prefix]*allowedIPsEntry{},
-		add:     add,
-		remove:  remove,
-	}
-}
-
-// Increment adds a reference to prefix for peerKey. WireGuard is programmed only for the first
-// reference to a prefix; while a different peer is already installed the prefix is left with it
-// (first peer wins, HA at the WireGuard layer is not possible) and only the reference count is kept.
-func (rm *AllowedIPsRefCounter) Increment(prefix netip.Prefix, peerKey string) (Ref[string], error) {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	e, ok := rm.entries[prefix]
-	if !ok {
-		e = &allowedIPsEntry{peers: map[string]int{}}
-		rm.entries[prefix] = e
-	}
-
-	logCallerF("Increasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
-		prefix, peerKey, e.peers[peerKey], e.peers[peerKey]+1, e.total, e.total+1, e.active)
-
-	// Program WireGuard only when nothing is installed yet for this prefix.
-	if e.active == "" {
-		out, err := rm.add(prefix, peerKey)
-		if errors.Is(err, ErrIgnore) {
-			if e.total == 0 {
-				delete(rm.entries, prefix)
-			}
-			return Ref[string]{Count: e.total, Out: e.active}, nil
-		}
-		if err != nil {
-			if e.total == 0 {
-				delete(rm.entries, prefix)
-			}
-			return Ref[string]{}, fmt.Errorf("failed to add allowed IP %v for peer %s: %w", prefix, peerKey, err)
-		}
-		e.active = out
-	}
-
-	e.peers[peerKey]++
-	e.total++
-
-	return Ref[string]{Count: e.total, Out: e.active}, nil
-}
-
-// Decrement removes a reference to prefix for peerKey. When the peer currently installed in
-// WireGuard releases its last reference, the prefix is swapped to a surviving peer if one exists,
-// otherwise it is removed from WireGuard.
-func (rm *AllowedIPsRefCounter) Decrement(prefix netip.Prefix, peerKey string) (Ref[string], error) {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	e, ok := rm.entries[prefix]
-	if !ok {
-		logCallerF("No allowed IP reference found for prefix %v", prefix)
-		return Ref[string]{}, nil
-	}
-
-	if e.peers[peerKey] > 0 {
-		logCallerF("Decreasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
-			prefix, peerKey, e.peers[peerKey], e.peers[peerKey]-1, e.total, e.total-1, e.active)
-		e.peers[peerKey]--
-		e.total--
-		if e.peers[peerKey] == 0 {
-			delete(e.peers, peerKey)
-		}
-	} else {
-		logCallerF("No allowed IP reference found for prefix %v peer %s", prefix, peerKey)
-	}
-
-	// If the peer currently installed in WireGuard still holds references, nothing to reprogram.
-	// Keying the check on the active peer (not the one just released) makes this self-healing:
-	// a prior swap whose remove/add failed leaves e.active pointing at a peer with no references,
-	// and this retries the hand-off on the next Decrement instead of getting stuck.
-	if e.active != "" && e.peers[e.active] > 0 {
-		return Ref[string]{Count: e.total, Out: e.active}, nil
-	}
-
-	// Detach the stale/gone active peer from WireGuard before reprogramming.
-	if e.active != "" {
-		if err := rm.remove(prefix, e.active); err != nil {
-			return Ref[string]{Count: e.total, Out: e.active}, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err)
-		}
-		e.active = ""
-	}
-
-	// Hand the prefix over to a surviving peer, or drop the entry when none remain.
-	if survivor, ok := pickSurvivor(e.peers); ok {
-		out, err := rm.add(prefix, survivor)
-		if err != nil {
-			return Ref[string]{Count: e.total, Out: ""}, fmt.Errorf("swap allowed IP %v to peer %s: %w", prefix, survivor, err)
-		}
-		e.active = out
-		return Ref[string]{Count: e.total, Out: e.active}, nil
-	}
-
-	delete(rm.entries, prefix)
-	return Ref[string]{Count: 0, Out: ""}, nil
-}
-
-// Flush removes all prefixes from WireGuard and clears the counter.
-func (rm *AllowedIPsRefCounter) Flush() error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for prefix, e := range rm.entries {
-		if e.active == "" {
-			continue
-		}
-		logCallerF("Flushing allowed IP for prefix %v peer %s", prefix, e.active)
-		if err := rm.remove(prefix, e.active); err != nil {
-			merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err))
-		}
-	}
-
-	clear(rm.entries)
-
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-// ReapplyMatching calls apply for every prefix whose currently installed (active) peer satisfies
-// pred, holding the lock for the whole pass. It is used to re-push allowed IPs onto a peer whose
-// WireGuard entry was rebuilt (e.g. a lazy connection cycling idle->wake) without a matching
-// refcounter change, which would otherwise leave the prefix installed in the counter but missing
-// on the device. Only the active peer is considered — a prefix that lost its installed peer to a
-// failed swap is skipped here and reconciled by the next Increment/Decrement.
-func (rm *AllowedIPsRefCounter) ReapplyMatching(pred func(out string) bool, apply func(key netip.Prefix) error) error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for prefix, e := range rm.entries {
-		if e.active != "" && pred(e.active) {
-			if err := apply(prefix); err != nil {
-				merr = multierror.Append(merr, err)
-			}
-		}
-	}
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-// pickSurvivor deterministically selects a peer still referencing the prefix. WireGuard cannot do
-// multipath for a single prefix, so any surviving peer is a valid winner; the choice is made stable
-// (lowest peerKey) for predictable behavior and testability.
-func pickSurvivor(peers map[string]int) (string, bool) {
-	if len(peers) == 0 {
-		return "", false
-	}
-	keys := make([]string, 0, len(peers))
-	for k := range peers {
-		keys = append(keys, k)
-	}
-	sort.Strings(keys)
-	return keys[0], true
-}

client/internal/routemanager/refcounter/allowedips_test.go

@@ -1,241 +0,0 @@
-package refcounter
-
-import (
-	"errors"
-	"net/netip"
-	"testing"
-)
-
-// fakeWG models WireGuard's cryptokey routing: a prefix can be installed on exactly one peer.
-// failAdd/failRemove make the next add/remove fail once, to exercise the self-healing error paths.
-type fakeWG struct {
-	installed  map[netip.Prefix]string
-	adds       int
-	removes    int
-	failAdd    bool
-	failRemove bool
-}
-
-func newFakeWG() *fakeWG {
-	return &fakeWG{installed: map[netip.Prefix]string{}}
-}
-
-func (f *fakeWG) counter() *AllowedIPsRefCounter {
-	return NewAllowedIPs(
-		func(prefix netip.Prefix, peerKey string) (string, error) {
-			if f.failAdd {
-				f.failAdd = false
-				return "", errors.New("add failed")
-			}
-			f.adds++
-			f.installed[prefix] = peerKey
-			return peerKey, nil
-		},
-		func(prefix netip.Prefix, peerKey string) error {
-			if f.failRemove {
-				f.failRemove = false
-				return errors.New("remove failed")
-			}
-			f.removes++
-			// only clear if this peer is the one installed, mirroring wg semantics
-			if f.installed[prefix] == peerKey {
-				delete(f.installed, prefix)
-			}
-			return nil
-		},
-	)
-}
-
-func mustPrefix(t *testing.T, s string) netip.Prefix {
-	t.Helper()
-	p, err := netip.ParsePrefix(s)
-	if err != nil {
-		t.Fatalf("parse prefix %q: %v", s, err)
-	}
-	return p
-}
-
-func mustIncrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
-	t.Helper()
-	ref, err := c.Increment(p, peer)
-	if err != nil {
-		t.Fatalf("Increment(%v, %s): %v", p, peer, err)
-	}
-	return ref
-}
-
-func mustDecrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
-	t.Helper()
-	ref, err := c.Decrement(p, peer)
-	if err != nil {
-		t.Fatalf("Decrement(%v, %s): %v", p, peer, err)
-	}
-	return ref
-}
-
-// TestAllowedIPs_SwapOnActivePeerRemoval reproduces the reported bug: two networks with the same
-// prefix routed by different peers. Removing the network whose peer is installed must hand the
-// prefix over to the surviving peer instead of leaving it on the removed one.
-func TestAllowedIPs_SwapOnActivePeerRemoval(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	// First peer wins while both are present.
-	if got := f.installed[p]; got != "peerA" {
-		t.Fatalf("expected peerA installed, got %q", got)
-	}
-
-	// Remove the active peer's network -> must swap to peerB.
-	mustDecrement(t, c, p, "peerA")
-	if got := f.installed[p]; got != "peerB" {
-		t.Fatalf("BUG: prefix stuck on removed peer, want peerB got %q", got)
-	}
-
-	// Remove the last one -> prefix gone.
-	mustDecrement(t, c, p, "peerB")
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("expected prefix removed, still installed on %q", f.installed[p])
-	}
-}
-
-// TestAllowedIPs_RemoveNonActivePeer removing a non-installed peer must not touch WireGuard.
-func TestAllowedIPs_RemoveNonActivePeer(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	removesBefore := f.removes
-
-	mustDecrement(t, c, p, "peerB")
-	if f.installed[p] != "peerA" {
-		t.Fatalf("active peer must stay peerA, got %q", f.installed[p])
-	}
-	if f.removes != removesBefore {
-		t.Fatalf("removing a non-active peer must not call wg remove")
-	}
-}
-
-// TestAllowedIPs_SamePeerMultipleRefs two references via the same peer must keep the prefix until
-// the last reference is released (the reason the per-peer count must be an int, not a set).
-func TestAllowedIPs_SamePeerMultipleRefs(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerA")
-	if f.adds != 1 {
-		t.Fatalf("expected a single wg add for the same peer, got %d", f.adds)
-	}
-
-	mustDecrement(t, c, p, "peerA")
-	if f.installed[p] != "peerA" {
-		t.Fatalf("prefix must stay while a reference remains, got %q", f.installed[p])
-	}
-	if f.removes != 0 {
-		t.Fatalf("no wg remove expected while a reference remains, got %d", f.removes)
-	}
-
-	mustDecrement(t, c, p, "peerA")
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("prefix must be removed after last reference")
-	}
-}
-
-// TestAllowedIPs_RefCountAndActive checks the Ref returned to callers (used for the HA-disabled log).
-func TestAllowedIPs_RefCountAndActive(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	ref := mustIncrement(t, c, p, "peerA")
-	if ref.Count != 1 || ref.Out != "peerA" {
-		t.Fatalf("want {1, peerA}, got {%d, %q}", ref.Count, ref.Out)
-	}
-	ref = mustIncrement(t, c, p, "peerB")
-	if ref.Count != 2 || ref.Out != "peerA" {
-		t.Fatalf("want {2, peerA}, got {%d, %q}", ref.Count, ref.Out)
-	}
-}
-
-// TestAllowedIPs_Flush removes everything installed and clears the counter.
-func TestAllowedIPs_Flush(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p1 := mustPrefix(t, "10.44.8.0/24")
-	p2 := mustPrefix(t, "10.44.9.0/24")
-
-	mustIncrement(t, c, p1, "peerA")
-	mustIncrement(t, c, p2, "peerB")
-
-	if err := c.Flush(); err != nil {
-		t.Fatal(err)
-	}
-	if len(f.installed) != 0 {
-		t.Fatalf("expected all prefixes removed, got %v", f.installed)
-	}
-	// After flush, a fresh increment must add again.
-	mustIncrement(t, c, p1, "peerC")
-	if f.installed[p1] != "peerC" {
-		t.Fatalf("counter not reset after flush")
-	}
-}
-
-// TestAllowedIPs_SelfHealAfterSwapAddError ensures a failed add during a swap does not permanently
-// strand the prefix: the next Decrement (or Increment) must retry and install a surviving peer.
-func TestAllowedIPs_SelfHealAfterSwapAddError(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	mustIncrement(t, c, p, "peerC")
-
-	// Removing the active peerA triggers a swap to a survivor; make the add fail once.
-	f.failAdd = true
-	if _, err := c.Decrement(p, "peerA"); err == nil {
-		t.Fatalf("expected error from failed swap add")
-	}
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("nothing should be installed after a failed swap add, got %q", f.installed[p])
-	}
-
-	// A later Decrement of a non-active survivor must retry the hand-off (self-heal), not stay stuck.
-	ref := mustDecrement(t, c, p, "peerC")
-	if got := f.installed[p]; got == "" {
-		t.Fatalf("self-heal failed: prefix left unrouted after add recovered")
-	}
-	if ref.Out == "" {
-		t.Fatalf("expected an active peer after self-heal, got empty")
-	}
-}
-
-// TestAllowedIPs_SelfHealAfterRemoveError ensures a failed remove during a swap is retried instead
-// of leaving e.active stuck on a peer that no longer holds references.
-func TestAllowedIPs_SelfHealAfterRemoveError(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-
-	// Releasing active peerA must detach it (remove) then add peerB; fail the remove once.
-	f.failRemove = true
-	if _, err := c.Decrement(p, "peerA"); err == nil {
-		t.Fatalf("expected error from failed remove")
-	}
-
-	// Next Decrement of the non-active survivor retries: removes stale peerA, installs peerB.
-	mustDecrement(t, c, p, "peerB")
-	// peerB had only one ref, so after retry the prefix is fully released.
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("expected prefix released after self-heal, still on %q", f.installed[p])
-	}
-}

client/internal/routemanager/refcounter/types.go

@@ -5,7 +5,5 @@ import "net/netip"
 // RouteRefCounter is a Counter for Route, it doesn't take any input on Increment and doesn't use any output on Decrement
 type RouteRefCounter = Counter[netip.Prefix, struct{}, struct{}]
 
-// AllowedIPsRefCounter tracks WireGuard AllowedIPs per prefix. Unlike the generic Counter it is peer-aware:
-// a prefix can be claimed by several peers at once and WireGuard allows a given prefix on exactly one peer,
-// so the counter records the per-peer reference count and swaps the installed peer when the active one is released.
-// See allowedips.go.
+// AllowedIPsRefCounter is a Counter for AllowedIPs, it takes a peer key on Increment and passes it back to Decrement
+type AllowedIPsRefCounter = Counter[netip.Prefix, string, string]

client/internal/routemanager/selection.go

@@ -1,138 +0,0 @@
-package routemanager
-
-import (
-	"fmt"
-	"slices"
-
-	"github.com/hashicorp/go-multierror"
-	log "github.com/sirupsen/logrus"
-	"golang.org/x/exp/maps"
-
-	nberrors "github.com/netbirdio/netbird/client/errors"
-	"github.com/netbirdio/netbird/route"
-)
-
-// SelectRoutes selects the routes with the given network IDs and applies the
-// new selection. V4/v6 exit-node pairs are expanded automatically. Exit nodes
-// are mutually exclusive: if the selection activates an exit node, every other
-// available exit node is deselected so two can't be active at once. With
-// appendRoute=false the previous selection is replaced instead of extended.
-func (m *DefaultManager) SelectRoutes(ids []route.NetID, appendRoute bool) error {
-	if err := m.selectRoutes(ids, appendRoute); err != nil {
-		return err
-	}
-	m.TriggerSelection(m.GetClientRoutes())
-	return nil
-}
-
-// DeselectRoutes removes the routes with the given network IDs from the
-// selection and applies the change. V4/v6 exit-node pairs are expanded
-// automatically.
-func (m *DefaultManager) DeselectRoutes(ids []route.NetID) error {
-	if err := m.deselectRoutes(ids); err != nil {
-		return err
-	}
-	m.TriggerSelection(m.GetClientRoutes())
-	return nil
-}
-
-func (m *DefaultManager) deselectRoutes(ids []route.NetID) error {
-	routesMap := m.GetClientRoutesWithNetID()
-	routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap)
-
-	log.Debugf("deselecting routes with ids: %v", routes)
-
-	if err := m.routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil {
-		return fmt.Errorf("deselect routes: %w", err)
-	}
-
-	return nil
-}
-
-// SelectAllRoutes selects every available route and applies the selection.
-// Exit nodes stay mutually exclusive: at most one remains active.
-func (m *DefaultManager) SelectAllRoutes() {
-	m.selectAllRoutes()
-	m.TriggerSelection(m.GetClientRoutes())
-}
-
-func (m *DefaultManager) selectAllRoutes() {
-	m.routeSelector.SelectAllRoutes()
-
-	// Select-all wipes every explicit selection, so exit nodes fall back to
-	// management's auto-apply flags — which may mark several at once.
-	// Reconcile immediately so at most one exit node stays active instead of
-	// waiting for the next network map to enforce it.
-	m.mux.Lock()
-	defer m.mux.Unlock()
-	m.updateRouteSelectorFromManagement(m.clientRoutes)
-}
-
-// DeselectAllRoutes deselects every route and applies the change.
-func (m *DefaultManager) DeselectAllRoutes() {
-	m.routeSelector.DeselectAllRoutes()
-	m.TriggerSelection(m.GetClientRoutes())
-}
-
-func (m *DefaultManager) selectRoutes(ids []route.NetID, appendRoute bool) error {
-	routesMap := m.GetClientRoutesWithNetID()
-	routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap)
-	allIDs := maps.Keys(routesMap)
-
-	log.Debugf("selecting routes with ids: %v", routes)
-
-	// A partial failure (e.g. an unknown ID in the request) still selects the
-	// valid routes, so exclusivity below must run regardless of the error.
-	var merr *multierror.Error
-	if err := m.routeSelector.SelectRoutes(routes, appendRoute, allIDs); err != nil {
-		merr = multierror.Append(merr, fmt.Errorf("select routes: %w", err))
-	}
-
-	// Exit nodes are mutually exclusive: if this selection activates an
-	// exit node, deselect every other available exit node so two can't be
-	// selected at once. Non-exit route selections are left untouched.
-	if requestActivatesExitNode(routes, routesMap) {
-		if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 {
-			if err := m.routeSelector.DeselectRoutes(others, allIDs); err != nil {
-				merr = multierror.Append(merr, fmt.Errorf("deselect sibling exit nodes: %w", err))
-			}
-		}
-	}
-
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-func isExitNodeRoutes(routes []*route.Route) bool {
-	return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network))
-}
-
-// requestActivatesExitNode reports whether any requested NetID maps to an exit
-// node (default route) in the current route table.
-func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool {
-	for _, id := range requested {
-		if isExitNodeRoutes(routesMap[id]) {
-			return true
-		}
-	}
-	return false
-}
-
-// otherExitNodeIDs returns every available exit-node NetID that is not in the
-// requested set — the siblings to deselect so a single exit node stays active.
-func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID {
-	keep := make(map[route.NetID]struct{}, len(requested))
-	for _, id := range requested {
-		keep[id] = struct{}{}
-	}
-	var others []route.NetID
-	for id, routes := range routesMap {
-		if !isExitNodeRoutes(routes) {
-			continue
-		}
-		if _, ok := keep[id]; ok {
-			continue
-		}
-		others = append(others, id)
-	}
-	return others
-}

client/internal/routemanager/selection_test.go

@@ -1,129 +0,0 @@
-package routemanager
-
-import (
-	"net/netip"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal/routeselector"
-	"github.com/netbirdio/netbird/route"
-)
-
-func v6ExitRoute(netID, peer string) *route.Route {
-	return &route.Route{
-		NetID:   route.NetID(netID),
-		Network: netip.MustParsePrefix("::/0"),
-		Peer:    peer,
-	}
-}
-
-func newSelectionTestManager() *DefaultManager {
-	return &DefaultManager{
-		routeSelector: routeselector.NewRouteSelector(),
-		clientRoutes: route.HAMap{
-			"exitA|0.0.0.0/0":    {exitRoute("exitA", "p1", true)},
-			"exitA-v6|::/0":      {v6ExitRoute("exitA-v6", "p1")},
-			"exitB|0.0.0.0/0":    {exitRoute("exitB", "p2", true)},
-			"lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}},
-		},
-	}
-}
-
-func TestSelectRoutes_ExitNodeExclusivity(t *testing.T) {
-	m := newSelectionTestManager()
-
-	// Selecting an exit node selects its v6 pair and deselects the sibling.
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitA"), "exitA should be selected")
-	assert.True(t, m.routeSelector.IsSelected("exitA-v6"), "the v6 pair follows its v4 base")
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "the sibling exit node must be deselected")
-
-	// Switching to the sibling deselects the previous exit node and its v6 pair.
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitB"), "exitB should now be selected")
-	assert.False(t, m.routeSelector.IsSelected("exitA"), "the previous exit node must be deselected")
-	assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "the previous exit node's v6 pair must be deselected")
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched")
-
-	// Selecting a non-exit route leaves the active exit node alone.
-	require.NoError(t, m.selectRoutes([]route.NetID{"lan"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitB"), "selecting a non-exit route keeps the exit node")
-
-	// Deselecting the active exit node turns every exit node off.
-	require.NoError(t, m.deselectRoutes([]route.NetID{"exitB"}))
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "exitB should be deselected")
-	assert.False(t, m.routeSelector.IsSelected("exitA"), "exitA stays deselected")
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched")
-}
-
-func TestSelectRoutes_PartialErrorStillEnforcesExclusivity(t *testing.T) {
-	// The unknown ID must be reported, but the valid exit node in the same
-	// request is still selected — so its sibling must still be deselected.
-	// Both orderings are covered: processing must continue past the invalid
-	// ID wherever it sits in the request.
-	requests := map[string][]route.NetID{
-		"invalid id first": {"missing", "exitB"},
-		"invalid id last":  {"exitB", "missing"},
-	}
-
-	for name, ids := range requests {
-		t.Run(name, func(t *testing.T) {
-			m := newSelectionTestManager()
-
-			require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true))
-
-			err := m.selectRoutes(ids, true)
-			assert.Error(t, err, "unknown id must be reported")
-			assert.True(t, m.routeSelector.IsSelected("exitB"), "valid exit node from the request is selected")
-			assert.False(t, m.routeSelector.IsSelected("exitA"), "sibling exit node must be deselected despite the error")
-			assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "sibling's v6 pair must be deselected too")
-		})
-	}
-}
-
-func TestSelectAllRoutes_KeepsSingleExitNode(t *testing.T) {
-	// Both exit nodes are marked for auto-apply by management
-	// (SkipAutoApply=false), the state where select-all could turn on two at
-	// once without the immediate reconciliation.
-	m := &DefaultManager{
-		routeSelector: routeselector.NewRouteSelector(),
-		clientRoutes: route.HAMap{
-			"exitA|0.0.0.0/0":    {exitRoute("exitA", "p1", false)},
-			"exitB|0.0.0.0/0":    {exitRoute("exitB", "p2", false)},
-			"lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}},
-		},
-	}
-
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true))
-
-	m.selectAllRoutes()
-
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit routes are all selected")
-	assert.True(t, m.routeSelector.IsSelected("exitA"), "the deterministic management pick stays active")
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "select-all must not leave a second exit node active")
-}
-
-func TestSelectRoutes_UnknownRoute(t *testing.T) {
-	m := newSelectionTestManager()
-
-	assert.Error(t, m.selectRoutes([]route.NetID{"missing"}, true), "selecting an unavailable route must fail")
-	assert.Error(t, m.deselectRoutes([]route.NetID{"missing"}), "deselecting an unavailable route must fail")
-}
-
-func TestExitNodeSelectionHelpers(t *testing.T) {
-	routesMap := map[route.NetID][]*route.Route{
-		"exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}},
-		"exitB": {{Network: netip.MustParsePrefix("::/0")}},
-		"lan":   {{Network: netip.MustParsePrefix("192.168.0.0/16")}},
-	}
-
-	assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node")
-	assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node")
-	assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node")
-	assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node")
-
-	others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"})
-	assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored")
-}

client/internal/routemanager/static/route.go

@@ -15,11 +15,6 @@ type Route struct {
 	route                *route.Route
 	routeRefCounter      *refcounter.RouteRefCounter
 	allowedIPsRefcounter *refcounter.AllowedIPsRefCounter
-	// currentPeerKey is the routing peer this watcher currently has the prefix installed on
-	// (the HA winner elected by the watcher). It can differ from route.Peer and change on
-	// failover, so it is recorded on AddAllowedIPs and used on RemoveAllowedIPs to decrement
-	// the exact peer that was incremented.
-	currentPeerKey string
 }
 
 func NewRoute(params common.HandlerParams) *Route {
@@ -57,15 +52,12 @@ func (r *Route) AddAllowedIPs(peerKey string) error {
 			ref.Out,
 		)
 	}
-	r.currentPeerKey = peerKey
 	return nil
 }
 
 func (r *Route) RemoveAllowedIPs() error {
-	var err error
-	if _, decErr := r.allowedIPsRefcounter.Decrement(r.route.Network, r.currentPeerKey); decErr != nil {
-		err = fmt.Errorf("remove allowed IP %s: %w", r.route.Network, decErr)
+	if _, err := r.allowedIPsRefcounter.Decrement(r.route.Network); err != nil {
+		return err
 	}
-	r.currentPeerKey = ""
-	return err
+	return nil
 }

client/internal/routemanager/sysctl/sysctl_linux.go

@@ -20,8 +20,6 @@ const (
 	rpFilterPath          = "net.ipv4.conf.all.rp_filter"
 	rpFilterInterfacePath = "net.ipv4.conf.%s.rp_filter"
 	srcValidMarkPath      = "net.ipv4.conf.all.src_valid_mark"
-	percentEscape         = "%25"
-	dotEscape             = "%2E"
 )
 
 type iface interface {
@@ -58,11 +56,7 @@ func Setup(wgIface iface) (map[string]int, error) {
 			continue
 		}
 
-		// Escape '%' and '.' so they survive the dot-to-slash conversion in Set()
-		safeName := strings.ReplaceAll(intf.Name, "%", percentEscape)
-		safeName = strings.ReplaceAll(safeName, ".", dotEscape)
-
-		i := fmt.Sprintf(rpFilterInterfacePath, safeName)
+		i := fmt.Sprintf(rpFilterInterfacePath, intf.Name)
 		oldVal, err := Set(i, 2, true)
 		if err != nil {
 			result = multierror.Append(result, err)
@@ -76,11 +70,7 @@ func Setup(wgIface iface) (map[string]int, error) {
 
 // Set sets a sysctl configuration, if onlyIfOne is true it will only set the new value if it's set to 1
 func Set(key string, desiredValue int, onlyIfOne bool) (int, error) {
-	path := strings.ReplaceAll(key, ".", "/")
-	// Unescape interface dots and percent signs
-	path = strings.ReplaceAll(path, dotEscape, ".")
-	path = strings.ReplaceAll(path, percentEscape, "%")
-	path = fmt.Sprintf("/proc/sys/%s", path)
+	path := fmt.Sprintf("/proc/sys/%s", strings.ReplaceAll(key, ".", "/"))
 	currentValue, err := os.ReadFile(path)
 	if err != nil {
 		return -1, fmt.Errorf("read sysctl %s: %w", key, err)

client/internal/tunnelnotifier/notifier.go

@@ -1,124 +0,0 @@
-package tunnelnotifier
-
-import (
-	"container/list"
-	"sync"
-
-	"github.com/netbirdio/netbird/client/internal/dns"
-	"github.com/netbirdio/netbird/client/internal/listener"
-)
-
-type eventKind int
-
-const (
-	eventRoutes eventKind = iota
-	eventIfaceIP
-	eventIfaceIPv6
-	eventDNS
-)
-
-var (
-	_ listener.NetworkChangeListener = (*Notifier)(nil)
-	_ dns.IosDnsManager              = (*Notifier)(nil)
-)
-
-type event struct {
-	kind    eventKind
-	payload string
-}
-
-type Notifier struct {
-	mu     sync.Mutex
-	cond   *sync.Cond
-	queue  *list.List
-	closed bool
-	done   chan struct{}
-
-	listener   listener.NetworkChangeListener
-	dnsManager dns.IosDnsManager
-}
-
-func New(l listener.NetworkChangeListener, dm dns.IosDnsManager) *Notifier {
-	n := &Notifier{
-		queue:      list.New(),
-		done:       make(chan struct{}),
-		listener:   l,
-		dnsManager: dm,
-	}
-	n.cond = sync.NewCond(&n.mu)
-	go n.deliverLoop()
-	return n
-}
-
-func (n *Notifier) OnNetworkChanged(routes string) {
-	n.enqueue(event{kind: eventRoutes, payload: routes})
-}
-
-func (n *Notifier) SetInterfaceIP(ip string) {
-	n.enqueue(event{kind: eventIfaceIP, payload: ip})
-}
-
-func (n *Notifier) SetInterfaceIPv6(ip string) {
-	n.enqueue(event{kind: eventIfaceIPv6, payload: ip})
-}
-
-func (n *Notifier) ApplyDns(config string) {
-	n.enqueue(event{kind: eventDNS, payload: config})
-}
-
-// Close stops accepting new events and blocks until the delivery loop has
-// drained all queued events and exited.
-func (n *Notifier) Close() {
-	n.mu.Lock()
-	n.closed = true
-	n.cond.Signal()
-	n.mu.Unlock()
-	<-n.done
-}
-
-func (n *Notifier) enqueue(ev event) {
-	n.mu.Lock()
-	defer n.mu.Unlock()
-	if n.closed {
-		return
-	}
-	n.queue.PushBack(ev)
-	n.cond.Signal()
-}
-
-func (n *Notifier) deliverLoop() {
-	defer close(n.done)
-	for {
-		n.mu.Lock()
-		for n.queue.Len() == 0 && !n.closed {
-			n.cond.Wait()
-		}
-		if n.closed && n.queue.Len() == 0 {
-			n.mu.Unlock()
-			return
-		}
-		ev := n.queue.Remove(n.queue.Front()).(event)
-		l := n.listener
-		dm := n.dnsManager
-		n.mu.Unlock()
-
-		switch ev.kind {
-		case eventRoutes:
-			if l != nil {
-				l.OnNetworkChanged(ev.payload)
-			}
-		case eventIfaceIP:
-			if l != nil {
-				l.SetInterfaceIP(ev.payload)
-			}
-		case eventIfaceIPv6:
-			if l != nil {
-				l.SetInterfaceIPv6(ev.payload)
-			}
-		case eventDNS:
-			if dm != nil {
-				dm.ApplyDns(ev.payload)
-			}
-		}
-	}
-}

client/internal/tunnelnotifier/notifier_test.go

@@ -1,192 +0,0 @@
-package tunnelnotifier
-
-import (
-	"fmt"
-	"sync"
-	"sync/atomic"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-type call struct {
-	kind    string
-	payload string
-}
-
-type recorder struct {
-	mu       sync.Mutex
-	calls    []call
-	inFlight atomic.Int32
-	overlap  atomic.Bool
-	delay    time.Duration
-}
-
-func (r *recorder) record(kind, payload string) {
-	if r.inFlight.Add(1) != 1 {
-		r.overlap.Store(true)
-	}
-	if r.delay > 0 {
-		time.Sleep(r.delay)
-	}
-	r.mu.Lock()
-	r.calls = append(r.calls, call{kind: kind, payload: payload})
-	r.mu.Unlock()
-	r.inFlight.Add(-1)
-}
-
-func (r *recorder) count() int {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	return len(r.calls)
-}
-
-func (r *recorder) snapshot() []call {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	out := make([]call, len(r.calls))
-	copy(out, r.calls)
-	return out
-}
-
-type fakeListener struct {
-	rec *recorder
-}
-
-func (f *fakeListener) OnNetworkChanged(routes string) {
-	f.rec.record("routes", routes)
-}
-
-func (f *fakeListener) SetInterfaceIP(ip string) {
-	f.rec.record("ip", ip)
-}
-
-func (f *fakeListener) SetInterfaceIPv6(ip string) {
-	f.rec.record("ipv6", ip)
-}
-
-type fakeDNSManager struct {
-	rec *recorder
-}
-
-func (f *fakeDNSManager) ApplyDns(config string) {
-	f.rec.record("dns", config)
-}
-
-func TestFIFOOrder(t *testing.T) {
-	rec := &recorder{}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	n.SetInterfaceIP("10.0.0.1")
-	n.SetInterfaceIPv6("fd00::1")
-	n.ApplyDns(`{"domains":[]}`)
-	n.OnNetworkChanged("10.0.0.0/8,192.168.0.0/16")
-	n.ApplyDns(`{"domains":["example.com"]}`)
-
-	require.Eventually(t, func() bool { return rec.count() == 5 }, time.Second, time.Millisecond)
-
-	expected := []call{
-		{kind: "ip", payload: "10.0.0.1"},
-		{kind: "ipv6", payload: "fd00::1"},
-		{kind: "dns", payload: `{"domains":[]}`},
-		{kind: "routes", payload: "10.0.0.0/8,192.168.0.0/16"},
-		{kind: "dns", payload: `{"domains":["example.com"]}`},
-	}
-	assert.Equal(t, expected, rec.snapshot())
-}
-
-func TestNoOverlappingCalls(t *testing.T) {
-	rec := &recorder{delay: 100 * time.Microsecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	const producers = 8
-	const perProducer = 25
-
-	var wg sync.WaitGroup
-	for i := 0; i < producers; i++ {
-		wg.Add(1)
-		go func(id int) {
-			defer wg.Done()
-			for j := 0; j < perProducer; j++ {
-				payload := fmt.Sprintf("%d-%d", id, j)
-				switch j % 4 {
-				case 0:
-					n.OnNetworkChanged(payload)
-				case 1:
-					n.SetInterfaceIP(payload)
-				case 2:
-					n.SetInterfaceIPv6(payload)
-				case 3:
-					n.ApplyDns(payload)
-				}
-			}
-		}(i)
-	}
-	wg.Wait()
-
-	require.Eventually(t, func() bool { return rec.count() == producers*perProducer }, 5*time.Second, time.Millisecond)
-	assert.False(t, rec.overlap.Load())
-}
-
-func TestDNSAndRoutesInterleaved(t *testing.T) {
-	rec := &recorder{delay: 100 * time.Microsecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	const events = 50
-
-	var wg sync.WaitGroup
-	wg.Add(2)
-	go func() {
-		defer wg.Done()
-		for i := 0; i < events; i++ {
-			n.ApplyDns(fmt.Sprintf("dns-%d", i))
-		}
-	}()
-	go func() {
-		defer wg.Done()
-		for i := 0; i < events; i++ {
-			n.OnNetworkChanged(fmt.Sprintf("routes-%d", i))
-		}
-	}()
-	wg.Wait()
-
-	require.Eventually(t, func() bool { return rec.count() == 2*events }, 5*time.Second, time.Millisecond)
-	assert.False(t, rec.overlap.Load())
-
-	var dnsSeen, routesSeen int
-	for _, c := range rec.snapshot() {
-		switch c.kind {
-		case "dns":
-			assert.Equal(t, fmt.Sprintf("dns-%d", dnsSeen), c.payload)
-			dnsSeen++
-		case "routes":
-			assert.Equal(t, fmt.Sprintf("routes-%d", routesSeen), c.payload)
-			routesSeen++
-		}
-	}
-	assert.Equal(t, events, dnsSeen)
-	assert.Equal(t, events, routesSeen)
-}
-
-func TestCloseDrainsQueue(t *testing.T) {
-	rec := &recorder{delay: time.Millisecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-
-	const events = 20
-	for i := 0; i < events; i++ {
-		n.OnNetworkChanged(fmt.Sprintf("routes-%d", i))
-	}
-	n.Close()
-
-	require.Equal(t, events, rec.count(), "Close must not return before all queued events are delivered")
-
-	n.OnNetworkChanged("after-close")
-	n.ApplyDns("after-close")
-	time.Sleep(50 * time.Millisecond)
-	assert.Equal(t, events, rec.count())
-}

client/ios/NetBirdSDK/client.go

@@ -13,6 +13,7 @@ import (
 	"time"
 
 	log "github.com/sirupsen/logrus"
+	"golang.org/x/exp/maps"
 
 	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/auth"
@@ -636,18 +637,23 @@ func (c *Client) SelectRoute(id string) error {
 	}
 
 	routeManager := engine.GetRouteManager()
+	routeSelector := routeManager.GetRouteSelector()
 	if id == "All" {
 		log.Debugf("select all routes")
-		routeManager.SelectAllRoutes()
-		return nil
-	}
-
-	log.Debugf("select route with id: %s", id)
-	if err := routeManager.SelectRoutes(toNetIDs([]string{id}), true); err != nil {
-		log.Debugf("error when selecting routes: %s", err)
-		return err
+		routeSelector.SelectAllRoutes()
+	} else {
+		log.Debugf("select route with id: %s", id)
+		routes := toNetIDs([]string{id})
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		if err := routeSelector.SelectRoutes(routes, true, maps.Keys(routesMap)); err != nil {
+			log.Debugf("error when selecting routes: %s", err)
+			return fmt.Errorf("select routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 	return nil
+
 }
 
 func (c *Client) DeselectRoute(id string) error {
@@ -661,17 +667,21 @@ func (c *Client) DeselectRoute(id string) error {
 	}
 
 	routeManager := engine.GetRouteManager()
+	routeSelector := routeManager.GetRouteSelector()
 	if id == "All" {
 		log.Debugf("deselect all routes")
-		routeManager.DeselectAllRoutes()
-		return nil
-	}
-
-	log.Debugf("deselect route with id: %s", id)
-	if err := routeManager.DeselectRoutes(toNetIDs([]string{id})); err != nil {
-		log.Debugf("error when deselecting routes: %s", err)
-		return err
+		routeSelector.DeselectAllRoutes()
+	} else {
+		log.Debugf("deselect route with id: %s", id)
+		routes := toNetIDs([]string{id})
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		if err := routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil {
+			log.Debugf("error when deselecting routes: %s", err)
+			return fmt.Errorf("deselect routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 	return nil
 }
 

client/server/login_gate_test.go

@@ -1,127 +0,0 @@
-package server
-
-import (
-	"context"
-	"path/filepath"
-	"testing"
-
-	"github.com/stretchr/testify/require"
-	"google.golang.org/grpc/codes"
-	gstatus "google.golang.org/grpc/status"
-
-	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/internal/profilemanager"
-	"github.com/netbirdio/netbird/client/proto"
-)
-
-// A refused login must not leave the profile switched. Login can both switch
-// profiles and carry the guarded config fields, so the gate has to run before the
-// switch: otherwise a caller whose change is refused still gets the side effect of
-// activating whichever profile the request named.
-func TestLogin_RefusedChangeLeavesTheProfileAlone(t *testing.T) {
-	s, _, activeProfile, username, _ := setupServerWithProfile(t)
-
-	// Login reads process state off the daemon's root context.
-	s.rootCtx = internal.CtxInitState(context.Background())
-
-	// A second profile that runs the SSH server, which is what makes repointing
-	// its management binding a privileged change.
-	target := "ssh-enabled"
-	_, err := profilemanager.UpdateOrCreateConfig(profilemanager.ConfigInput{
-		ConfigPath:       filepath.Join(profilemanager.DefaultConfigPathDir, target+".json"),
-		ManagementURL:    "https://api.netbird.io:443",
-		ServerSSHAllowed: boolPtr(true),
-	})
-	require.NoError(t, err)
-
-	_, err = s.Login(userCtx(), &proto.LoginRequest{
-		ProfileName:   &target,
-		Username:      &username,
-		ManagementUrl: "https://mgmt.attacker.example:443",
-	})
-	require.Error(t, err, "an unprivileged caller must not move the management URL of an SSH-enabled profile")
-	require.Equal(t, codes.PermissionDenied, gstatus.Code(err), "want a privilege refusal, got %v", err)
-
-	active, err := s.profileManager.GetActiveProfileState()
-	require.NoError(t, err)
-	require.Equal(t, profilemanager.ID(activeProfile), active.ID,
-		"the refused login switched the active profile anyway")
-}
-
-// A caller whose change becomes privileged only after its first check must be
-// refused without having cancelled a login or switched profiles: the first check is
-// unsynchronized, so the SSH server can be enabled by a concurrent privileged
-// request in between, and the authoritative check happens before any side effect.
-func TestLogin_ChangeThatBecomesPrivilegedMidRequestHasNoSideEffects(t *testing.T) {
-	s, _, activeProfile, username, _ := setupServerWithProfile(t)
-	s.rootCtx = internal.CtxInitState(context.Background())
-
-	// The target profile has SSH off, so the first check lets the request through.
-	target := "ssh-later"
-	targetPath := filepath.Join(profilemanager.DefaultConfigPathDir, target+".json")
-	_, err := profilemanager.UpdateOrCreateConfig(profilemanager.ConfigInput{
-		ConfigPath:       targetPath,
-		ManagementURL:    "https://api.netbird.io:443",
-		ServerSSHAllowed: boolPtr(false),
-	})
-	require.NoError(t, err)
-
-	cancelled := false
-	s.actCancel = func() { cancelled = true }
-
-	// Stand in for a privileged SetConfig that enables the SSH server between the
-	// two checks, which is the interleaving the lock has to make safe.
-	afterLoginPreCheck = func() {
-		_, err := profilemanager.UpdateOrCreateConfig(profilemanager.ConfigInput{
-			ConfigPath:       targetPath,
-			ServerSSHAllowed: boolPtr(true),
-		})
-		require.NoError(t, err)
-	}
-	t.Cleanup(func() { afterLoginPreCheck = nil })
-
-	_, err = s.Login(userCtx(), &proto.LoginRequest{
-		ProfileName:   &target,
-		Username:      &username,
-		ManagementUrl: "https://mgmt.attacker.example:443",
-	})
-	require.Error(t, err)
-	require.Equal(t, codes.PermissionDenied, gstatus.Code(err), "want a privilege refusal, got %v", err)
-	require.False(t, cancelled, "the refused login cancelled the login already in progress")
-
-	active, err := s.profileManager.GetActiveProfileState()
-	require.NoError(t, err)
-	require.Equal(t, profilemanager.ID(activeProfile), active.ID, "the refused login switched the active profile anyway")
-
-	stored, err := profilemanager.ReadConfig(targetPath)
-	require.NoError(t, err)
-	require.Equal(t, "https://api.netbird.io:443", stored.ManagementURL.String(), "the refused login moved the management URL")
-}
-
-// Login cancels whatever login is already in progress before starting its own. A
-// refused caller must not get that far, otherwise anyone able to reach the socket
-// can abort someone else's login by sending a request that is denied.
-func TestLogin_RefusedChangeLeavesAnInProgressLoginAlone(t *testing.T) {
-	s, _, _, username, _ := setupServerWithProfile(t)
-	s.rootCtx = internal.CtxInitState(context.Background())
-
-	target := "ssh-enabled"
-	_, err := profilemanager.UpdateOrCreateConfig(profilemanager.ConfigInput{
-		ConfigPath:       filepath.Join(profilemanager.DefaultConfigPathDir, target+".json"),
-		ManagementURL:    "https://api.netbird.io:443",
-		ServerSSHAllowed: boolPtr(true),
-	})
-	require.NoError(t, err)
-
-	cancelled := false
-	s.actCancel = func() { cancelled = true }
-
-	_, err = s.Login(userCtx(), &proto.LoginRequest{
-		ProfileName:   &target,
-		Username:      &username,
-		ManagementUrl: "https://mgmt.attacker.example:443",
-	})
-	require.Error(t, err)
-	require.Equal(t, codes.PermissionDenied, gstatus.Code(err), "want a privilege refusal, got %v", err)
-	require.False(t, cancelled, "the refused login cancelled the login already in progress")
-}

client/server/network.go

@@ -8,6 +8,7 @@ import (
 	"sort"
 	"strings"
 
+	"golang.org/x/exp/maps"
 	"google.golang.org/grpc/codes"
 	gstatus "google.golang.org/grpc/status"
 
@@ -160,11 +161,30 @@ func (s *Server) SelectNetworks(_ context.Context, req *proto.SelectNetworksRequ
 		return nil, fmt.Errorf("no route manager")
 	}
 
+	routeSelector := routeManager.GetRouteSelector()
 	if req.GetAll() {
-		routeManager.SelectAllRoutes()
-	} else if err := routeManager.SelectRoutes(toNetIDs(req.GetNetworkIDs()), req.GetAppend()); err != nil {
-		return nil, err
+		routeSelector.SelectAllRoutes()
+	} else {
+		routes := toNetIDs(req.GetNetworkIDs())
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		netIdRoutes := maps.Keys(routesMap)
+		if err := routeSelector.SelectRoutes(routes, req.GetAppend(), netIdRoutes); err != nil {
+			return nil, fmt.Errorf("select routes: %w", err)
+		}
+
+		// Exit nodes are mutually exclusive: if this selection activates an
+		// exit node, deselect every other available exit node so two can't be
+		// selected at once. Non-exit route selections are left untouched.
+		if requestActivatesExitNode(routes, routesMap) {
+			if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 {
+				if err := routeSelector.DeselectRoutes(others, netIdRoutes); err != nil {
+					return nil, fmt.Errorf("deselect sibling exit nodes: %w", err)
+				}
+			}
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 
 	s.statusRecorder.PublishEvent(
 		proto.SystemEvent_INFO,
@@ -204,11 +224,19 @@ func (s *Server) DeselectNetworks(_ context.Context, req *proto.SelectNetworksRe
 		return nil, fmt.Errorf("no route manager")
 	}
 
+	routeSelector := routeManager.GetRouteSelector()
 	if req.GetAll() {
-		routeManager.DeselectAllRoutes()
-	} else if err := routeManager.DeselectRoutes(toNetIDs(req.GetNetworkIDs())); err != nil {
-		return nil, err
+		routeSelector.DeselectAllRoutes()
+	} else {
+		routes := toNetIDs(req.GetNetworkIDs())
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		netIdRoutes := maps.Keys(routesMap)
+		if err := routeSelector.DeselectRoutes(routes, netIdRoutes); err != nil {
+			return nil, fmt.Errorf("deselect routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 
 	s.statusRecorder.PublishEvent(
 		proto.SystemEvent_INFO,
@@ -233,3 +261,37 @@ func toNetIDs(routes []string) []route.NetID {
 	return netIDs
 }
 
+func isExitNodeRoutes(routes []*route.Route) bool {
+	return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network))
+}
+
+// requestActivatesExitNode reports whether any requested NetID maps to an exit
+// node (default route) in the current route table.
+func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool {
+	for _, id := range requested {
+		if isExitNodeRoutes(routesMap[id]) {
+			return true
+		}
+	}
+	return false
+}
+
+// otherExitNodeIDs returns every available exit-node NetID that is not in the
+// requested set — the siblings to deselect so a single exit node stays active.
+func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID {
+	keep := make(map[route.NetID]struct{}, len(requested))
+	for _, id := range requested {
+		keep[id] = struct{}{}
+	}
+	var others []route.NetID
+	for id, routes := range routesMap {
+		if !isExitNodeRoutes(routes) {
+			continue
+		}
+		if _, ok := keep[id]; ok {
+			continue
+		}
+		others = append(others, id)
+	}
+	return others
+}

client/server/network_exitnode_test.go

@@ -0,0 +1,26 @@
+package server
+
+import (
+	"net/netip"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/netbirdio/netbird/route"
+)
+
+func TestExitNodeSelectionHelpers(t *testing.T) {
+	routesMap := map[route.NetID][]*route.Route{
+		"exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}},
+		"exitB": {{Network: netip.MustParsePrefix("::/0")}},
+		"lan":   {{Network: netip.MustParsePrefix("192.168.0.0/16")}},
+	}
+
+	assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node")
+	assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node")
+	assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node")
+	assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node")
+
+	others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"})
+	assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored")
+}

client/server/server.go

@@ -82,12 +82,6 @@ type Server struct {
 	// extend flow or vice versa.
 	extendAuthSessionFlow *auth.PendingFlow
 
-	// guardedConfigMu serializes a privilege check against the write it
-	// authorizes. Without it the two are separate steps over the same file, and a
-	// change that was allowed because the profile had the SSH server disabled
-	// could land after a concurrent privileged request enabled it.
-	guardedConfigMu sync.Mutex
-
 	mutex  sync.Mutex
 	config *profilemanager.Config
 	proto.UnimplementedDaemonServiceServer
@@ -417,20 +411,6 @@ func (s *Server) SetConfig(callerCtx context.Context, msg *proto.SetConfigReques
 		return nil, err
 	}
 
-	// Privilege gate: refuse the parts of the request that would let a local
-	// user turn the root daemon into a root shell. Held across the write so the
-	// config cannot gain the SSH server between the decision and the update.
-	s.guardedConfigMu.Lock()
-	defer s.guardedConfigMu.Unlock()
-
-	stored, err := s.storedProfileConfig(msg.ProfileName, msg.Username)
-	if err != nil {
-		return nil, err
-	}
-	if err := requirePrivilegeForConfigChange(callerCtx, stored, privilegedChangeFromSetConfig(msg)); err != nil {
-		return nil, err
-	}
-
 	config, err := s.setConfigInputFromRequest(msg)
 	if err != nil {
 		return nil, err
@@ -557,23 +537,22 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 		}
 	}
 
-	activeProf, err := s.profileManager.GetActiveProfileState()
-	if err != nil {
-		log.Errorf("failed to get active profile state: %v", err)
-		return nil, fmt.Errorf("failed to get active profile state: %w", err)
+	s.mutex.Lock()
+	if s.actCancel != nil {
+		s.actCancel()
+	}
+	ctx, cancel := context.WithCancel(callerCtx)
+
+	md, ok := metadata.FromIncomingContext(callerCtx)
+	if ok {
+		ctx = metadata.NewOutgoingContext(ctx, md)
 	}
 
-	// Privilege gate: same restrictions as SetConfig, since LoginRequest can carry
-	// the same fields. It runs before anything here changes daemon state, so a
-	// refused login neither switches the profile nor cancels a login already in
-	// progress, and it reads the profile the request targets, which is the one the
-	// switch below would activate.
-	stored, err := s.storedLoginConfig(activeProf, msg)
-	if err != nil {
-		return nil, err
-	}
-	if err := requirePrivilegeForConfigChange(callerCtx, stored, privilegedChangeFromLogin(msg)); err != nil {
-		return nil, err
+	s.actCancel = cancel
+	s.mutex.Unlock()
+
+	if err := RestoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil {
+		log.Warnf(errRestoreResidualState, err)
 	}
 
 	state := internal.CtxGetState(s.rootCtx)
@@ -584,16 +563,23 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 		}
 	}()
 
-	ctx, activeProf, err := s.authorizeAndPrepareLogin(callerCtx, msg, activeProf)
+	activeProf, err := s.profileManager.GetActiveProfileState()
 	if err != nil {
-		// The RPC boundary is where this gets recorded: nothing logs handler
-		// errors for us, and a caller that retries would otherwise leave no
-		// trace in the daemon log. A refusal is skipped because the gate has
-		// already logged the decision, with the caller's identity.
-		if gstatus.Code(err) != codes.PermissionDenied {
-			log.Errorf("failed to prepare login: %v", err)
+		log.Errorf("failed to get active profile state: %v", err)
+		return nil, fmt.Errorf("failed to get active profile state: %w", err)
+	}
+
+	if msg.ProfileName != nil {
+		if _, err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil {
+			log.Errorf("failed to switch profile: %v", err)
+			return nil, err
 		}
-		return nil, err
+	}
+
+	activeProf, err = s.profileManager.GetActiveProfileState()
+	if err != nil {
+		log.Errorf("failed to get active profile state: %v", err)
+		return nil, fmt.Errorf("failed to get active profile state: %w", err)
 	}
 
 	log.Infof("active profile: %s for %s", activeProf.ID, activeProf.Username)
@@ -607,6 +593,11 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 
 	s.mutex.Unlock()
 
+	if err := persistLoginOverrides(activeProf, msg.ManagementUrl, msg.OptionalPreSharedKey); err != nil {
+		log.Errorf("failed to persist login overrides: %v", err)
+		return nil, fmt.Errorf("persist login overrides: %w", err)
+	}
+
 	config, _, err := s.getConfig(activeProf)
 	if err != nil {
 		log.Errorf("failed to get active profile config: %v", err)
@@ -989,63 +980,6 @@ func (s *Server) waitForUp(callerCtx context.Context) (*proto.UpResponse, error)
 	}
 }
 
-// storedProfileConfig loads the on-disk config of the profile a request
-// targets, so a privileged-change decision can be made against the values the
-// profile currently holds. A profile that has no config file yet yields nil,
-// which every caller must read as "nothing enabled yet".
-func (s *Server) storedProfileConfig(handle, username string) (*profilemanager.Config, error) {
-	resolved, err := s.resolveProfileHandle(handle, username)
-	if err != nil {
-		return nil, err
-	}
-
-	path := resolved.Path
-	if path == "" {
-		path = profilemanager.DefaultConfigPath
-	}
-
-	return s.storedConfigAtPath(path)
-}
-
-// storedLoginConfig loads the on-disk config of the profile a login request
-// targets: the one it names, or the active one when it names none. Used to decide
-// a privileged change before the request is allowed to switch profiles.
-func (s *Server) storedLoginConfig(activeProf *profilemanager.ActiveProfileState, msg *proto.LoginRequest) (*profilemanager.Config, error) {
-	if msg.ProfileName == nil {
-		cfgPath, err := activeProf.FilePath()
-		if err != nil {
-			return nil, fmt.Errorf("active profile file path: %w", err)
-		}
-		return s.storedConfigAtPath(cfgPath)
-	}
-
-	// Mirrors switchProfileIfNeeded: the default profile resolves without a
-	// username, so this reads the same profile the switch would activate.
-	handle := *msg.ProfileName
-	username := ""
-	if handle != profilemanager.DefaultProfileName {
-		username = msg.GetUsername()
-	}
-	return s.storedProfileConfig(handle, username)
-}
-
-// storedConfigAtPath reads a profile config file, yielding nil when it does not
-// exist yet.
-func (s *Server) storedConfigAtPath(path string) (*profilemanager.Config, error) {
-	if _, err := os.Stat(path); err != nil {
-		if os.IsNotExist(err) {
-			return nil, nil //nolint:nilnil
-		}
-		return nil, fmt.Errorf("stat profile config: %w", err)
-	}
-
-	cfg, err := profilemanager.GetConfig(path)
-	if err != nil {
-		return nil, fmt.Errorf("read profile config: %w", err)
-	}
-	return cfg, nil
-}
-
 // resolveProfileHandle resolves a wire-level profile handle (display
 // name, ID, or unique ID prefix) to a concrete profile. Returns gRPC
 // status errors so handlers can return them directly.
@@ -1263,12 +1197,6 @@ func (s *Server) handleProfileLogout(ctx context.Context, msg *proto.LogoutReque
 
 	if err := s.logoutFromProfile(ctx, resolved); err != nil {
 		log.Errorf("failed to logout from profile %s: %v", resolved.ID, err)
-		// A refused deregistration is already a status error carrying the reason
-		// and the command to run; rewrapping it as Internal would flatten both
-		// into a gRPC dump for the user.
-		if _, isStatus := gstatus.FromError(err); isStatus {
-			return nil, err
-		}
 		return nil, gstatus.Errorf(codes.Internal, "logout: %v", err)
 	}
 
@@ -1390,13 +1318,6 @@ func (s *Server) sendLogoutRequest(ctx context.Context) error {
 }
 
 func (s *Server) sendLogoutRequestWithConfig(ctx context.Context, config *profilemanager.Config) error {
-	// Privilege gate: deregistering frees this machine's key to be registered
-	// against another management server, which is only restricted while the SSH
-	// server makes that a privilege handover.
-	if err := requirePrivilegeForDeregistration(ctx, config); err != nil {
-		return err
-	}
-
 	key, err := wgtypes.ParseKey(config.PrivateKey)
 	if err != nil {
 		return fmt.Errorf("parse private key: %w", err)
@@ -2142,10 +2063,7 @@ func (s *Server) RemoveProfile(ctx context.Context, msg *proto.RemoveProfileRequ
 	}
 
 	if err := s.logoutFromProfile(ctx, resolved); err != nil {
-		// Deregistration is best-effort here: the local profile is removed
-		// either way, so an unprivileged caller leaves the peer registered on
-		// the management server rather than being blocked from removing it.
-		log.Warnf("removing profile %s locally without deregistering it: %v", resolved.ID, err)
+		log.Warnf("failed to logout from profile %s before removal: %v", resolved.ID, err)
 	}
 
 	if err := s.profileManager.RemoveProfile(resolved.ID, msg.Username); err != nil {
@@ -2442,69 +2360,6 @@ func sendTerminalNotification() error {
 
 // persistLoginOverrides writes management URL and pre-shared key from a LoginRequest to the
 // active profile config so that subsequent reads pick them up. Empty/nil values are ignored.
-// afterLoginPreCheck is a seam for tests to run a concurrent config change
-// between Login's first privilege check and the authoritative one.
-var afterLoginPreCheck func()
-
-// authorizeAndPrepareLogin makes the authoritative privilege decision for a login
-// and, when it passes, carries out every state change that decision authorizes:
-// cancelling an login already in progress, switching to the requested profile, and
-// persisting the config overrides the request carries.
-//
-// All of it happens under guardedConfigMu, which SetConfig also holds across its
-// own check and write. Login's earlier check refuses the ordinary case before any
-// of this is reached; this one exists because that check is not synchronized
-// against a concurrent privileged request that enables the SSH server, and a
-// caller refused here must not have cancelled or switched anything either.
-func (s *Server) authorizeAndPrepareLogin(callerCtx context.Context, msg *proto.LoginRequest, activeProf *profilemanager.ActiveProfileState) (context.Context, *profilemanager.ActiveProfileState, error) {
-	if afterLoginPreCheck != nil {
-		afterLoginPreCheck()
-	}
-
-	s.guardedConfigMu.Lock()
-	defer s.guardedConfigMu.Unlock()
-
-	stored, err := s.storedLoginConfig(activeProf, msg)
-	if err != nil {
-		return nil, nil, err
-	}
-	if err := requirePrivilegeForConfigChange(callerCtx, stored, privilegedChangeFromLogin(msg)); err != nil {
-		return nil, nil, err
-	}
-
-	s.mutex.Lock()
-	if s.actCancel != nil {
-		s.actCancel()
-	}
-	ctx, cancel := context.WithCancel(callerCtx)
-	if md, ok := metadata.FromIncomingContext(callerCtx); ok {
-		ctx = metadata.NewOutgoingContext(ctx, md)
-	}
-	s.actCancel = cancel
-	s.mutex.Unlock()
-
-	if err := RestoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil {
-		log.Warnf(errRestoreResidualState, err)
-	}
-
-	if msg.ProfileName != nil {
-		if _, err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil {
-			return nil, nil, fmt.Errorf("switch profile: %w", err)
-		}
-	}
-
-	activeProf, err = s.profileManager.GetActiveProfileState()
-	if err != nil {
-		return nil, nil, fmt.Errorf("active profile state: %w", err)
-	}
-
-	if err := persistLoginOverrides(activeProf, msg.ManagementUrl, msg.OptionalPreSharedKey); err != nil {
-		return nil, nil, fmt.Errorf("persist login overrides: %w", err)
-	}
-
-	return ctx, activeProf, nil
-}
-
 func persistLoginOverrides(activeProf *profilemanager.ActiveProfileState, managementURL string, preSharedKey *string) error {
 	if preSharedKey != nil && *preSharedKey == "" {
 		preSharedKey = nil

client/server/setconfig_mdm_test.go

@@ -66,11 +66,7 @@ func setupServerWithProfile(t *testing.T) (s *Server, ctx context.Context, profN
 		Username: currUser.Username,
 	}))
 
-	// The privileged-change gate reads the caller's kernel identity from the
-	// context, which a real caller gets from the daemon's transport credentials.
-	// This test drives the handler directly, so it stands in for a root caller;
-	// without an identity the gate would (correctly) refuse the SSH fields.
-	ctx = privilegedTestCtx()
+	ctx = context.Background()
 	s = New(ctx, "console", "", false, false, false, false)
 	return s, ctx, profName, currUser.Username, cfgPath
 }

client/server/setconfig_test.go

@@ -1,6 +1,7 @@
 package server
 
 import (
+	"context"
 	"os/user"
 	"path/filepath"
 	"reflect"
@@ -51,11 +52,7 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 	})
 	require.NoError(t, err)
 
-	// The privileged-change gate reads the caller's kernel identity from the
-	// context, which a real caller gets from the daemon's transport credentials.
-	// This test drives the handler directly, so it stands in for a root caller;
-	// without an identity the gate would (correctly) refuse the SSH fields.
-	ctx := privilegedTestCtx()
+	ctx := context.Background()
 	s := New(ctx, "console", "", false, false, false, false)
 
 	rosenpassEnabled := true

client/server/ssh_gate.go

@@ -1,282 +0,0 @@
-package server
-
-import (
-	"context"
-	"fmt"
-	"net/url"
-	"runtime"
-	"strings"
-
-	log "github.com/sirupsen/logrus"
-	"google.golang.org/genproto/googleapis/rpc/errdetails"
-	"google.golang.org/grpc/codes"
-	gstatus "google.golang.org/grpc/status"
-
-	"github.com/netbirdio/netbird/client/internal/daemonaddr"
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-	"github.com/netbirdio/netbird/client/internal/profilemanager"
-	"github.com/netbirdio/netbird/client/proto"
-	"github.com/netbirdio/netbird/util"
-)
-
-// The daemon runs as root/LocalSystem, so a handful of config changes cross the
-// user-to-root boundary and are restricted to privileged callers:
-//
-//   - Enabling SSH root login, or disabling SSH authentication, turns the
-//     daemon's SSH server into a root (or unauthenticated) shell.
-//   - Enabling the SSH server at all is what makes the above reachable, and a
-//     profile the caller owns is not a privilege they hold.
-//   - While the SSH server is enabled, repointing the profile at another
-//     management identity hands SSH authorization decisions, including which
-//     keys and users are accepted, to whoever controls that identity. Changing
-//     the management URL and deregistering the peer are both ways to do that.
-//
-// Everything else stays unauthenticated, so this is not an authorization model:
-// it only refuses the changes that would let a local user become root. A caller
-// whose identity cannot be established is refused as well.
-
-// privilegedConfigChange is the subset of a config request that crosses the
-// user-to-root boundary. Fields are nil or empty when the request leaves them
-// untouched.
-type privilegedConfigChange struct {
-	managementURL    string
-	serverSSHAllowed *bool
-	enableSSHRoot    *bool
-	disableSSHAuth   *bool
-}
-
-func privilegedChangeFromSetConfig(msg *proto.SetConfigRequest) privilegedConfigChange {
-	return privilegedConfigChange{
-		managementURL:    msg.GetManagementUrl(),
-		serverSSHAllowed: msg.ServerSSHAllowed,
-		enableSSHRoot:    msg.EnableSSHRoot,
-		disableSSHAuth:   msg.DisableSSHAuth,
-	}
-}
-
-func privilegedChangeFromLogin(msg *proto.LoginRequest) privilegedConfigChange {
-	return privilegedConfigChange{
-		managementURL:    msg.GetManagementUrl(),
-		serverSSHAllowed: msg.ServerSSHAllowed,
-		enableSSHRoot:    msg.EnableSSHRoot,
-		disableSSHAuth:   msg.DisableSSHAuth,
-	}
-}
-
-// requirePrivilegeForConfigChange refuses the privileged parts of a config
-// change when the caller is not root/administrator. stored is the profile's
-// current config, or nil when it has none yet.
-//
-// Each check compares against the stored value so that a request restating a
-// value it does not change is never refused: a UI that submits the whole
-// settings form must not start failing once an administrator has enabled SSH.
-func requirePrivilegeForConfigChange(ctx context.Context, stored *profilemanager.Config, change privilegedConfigChange) error {
-	if enables(storedFlag(stored, func(c *profilemanager.Config) *bool { return c.EnableSSHRoot }), change.enableSSHRoot) {
-		return denyPrivileged(ctx, "enabling SSH root login", ipcauth.UpCommand("--enable-ssh-root"))
-	}
-
-	if enables(storedFlag(stored, func(c *profilemanager.Config) *bool { return c.DisableSSHAuth }), change.disableSSHAuth) {
-		return denyPrivileged(ctx, "disabling SSH authentication", ipcauth.UpCommand("--disable-ssh-auth"))
-	}
-
-	if enables(sshServerCurrentlyAllowed(stored), change.serverSSHAllowed) {
-		return denyPrivileged(ctx, "enabling the NetBird SSH server", ipcauth.UpCommand("--allow-server-ssh"))
-	}
-
-	// Only guard the management binding while the SSH server is enabled: that is
-	// when the management identity decides who may open a shell here.
-	if !sshServerEnabled(stored) {
-		return nil
-	}
-
-	if change.managementURL != "" && !sameManagementURL(stored.ManagementURL, change.managementURL) {
-		return denyPrivileged(ctx,
-			"changing the management URL while the NetBird SSH server is enabled",
-			ipcauth.UpCommand("-m "+change.managementURL))
-	}
-
-	return nil
-}
-
-// requirePrivilegeForDeregistration refuses to deregister the peer from the
-// management server when the caller is not privileged and the profile has the
-// SSH server enabled. Deregistering frees the peer's key to be registered
-// against another management identity, which is the same handover the
-// management URL check refuses.
-//
-// Callers that treat deregistration as best-effort (profile removal) continue
-// without it; callers that were asked to deregister surface the error.
-func requirePrivilegeForDeregistration(ctx context.Context, cfg *profilemanager.Config) error {
-	if !sshServerEnabled(cfg) {
-		return nil
-	}
-
-	return denyPrivileged(ctx,
-		"deregistering this peer while the NetBird SSH server is enabled",
-		ipcauth.ElevatedCommand("netbird logout"))
-}
-
-// denyPrivileged returns nil when the caller is privileged, and otherwise a
-// PermissionDenied whose message names the action and the command that performs
-// it with the privileges it needs. The same summary and command ride along as an
-// ErrorInfo detail so the CLI and the UI can present them without parsing text.
-//
-// action reads as the subject of a sentence ("enabling SSH root login"), and
-// command is the equivalent command, already elevated for the platform.
-func denyPrivileged(ctx context.Context, action, command string) error {
-	id, ok := ipcauth.CallerIdentity(ctx)
-	if !ok {
-		log.Warnf("denying %s: the caller's identity cannot be verified on this control channel", action)
-		return privilegeError(unidentifiedSummary(action), reinstallCommand())
-	}
-
-	if ipcauth.IsPrivilegedCaller(id) {
-		log.Infof("allowing %s for privileged caller %s", action, id)
-		return nil
-	}
-
-	log.Warnf("denying %s for unprivileged caller %s", action, id)
-	actor, command := requiredActor(command)
-	return privilegeError(privilegeSummary(action, actor), command)
-}
-
-// requiredActor names who may perform the operation and adjusts the command to
-// match. A daemon that is not itself privileged delegates to its own identity, so
-// telling that host's user to become root is wrong twice over: root is not what the
-// daemon checks for, and a rootless container has neither root nor sudo.
-func requiredActor(command string) (string, string) {
-	self, delegates := ipcauth.SelfDelegatesTo()
-	if !delegates {
-		return ipcauth.PrivilegedActor(), command
-	}
-	return fmt.Sprintf("the user the daemon runs as (%s)", self), strings.ReplaceAll(command, "sudo ", "")
-}
-
-// privilegeError builds the PermissionDenied carrying summary and command.
-func privilegeError(summary, command string) error {
-	st := gstatus.New(codes.PermissionDenied, fmt.Sprintf("%s\n\n%s", summary, command))
-
-	detailed, err := st.WithDetails(&errdetails.ErrorInfo{
-		Reason: ipcauth.ErrorReasonPrivilegeRequired,
-		Domain: ipcauth.ErrorDomain,
-		Metadata: map[string]string{
-			ipcauth.ErrorMetaSummary: summary,
-			ipcauth.ErrorMetaCommand: command,
-		},
-	})
-	if err != nil {
-		log.Debugf("attach privilege error detail: %v", err)
-		return st.Err()
-	}
-	return detailed.Err()
-}
-
-// privilegeSummary states what is refused and what it needs, in one sentence
-// that reads the same in a dialog and in a terminal.
-func privilegeSummary(action, actor string) string {
-	return fmt.Sprintf("%s requires %s.", capitalize(action), actor)
-}
-
-// unidentifiedSummary covers a control channel that carries no caller identity.
-// Elevating does not help there, so it points at the daemon's socket instead.
-func unidentifiedSummary(action string) string {
-	return fmt.Sprintf("%s requires %s, and the daemon cannot verify who is calling over its current socket. "+
-		"Reinstall the service on a socket that carries the caller's identity.", capitalize(action), ipcauth.PrivilegedActor())
-}
-
-// reinstallCommand is the command that moves the daemon onto a socket whose
-// callers can be identified.
-func reinstallCommand() string {
-	if runtime.GOOS == "windows" {
-		return fmt.Sprintf("netbird service install --daemon-addr %s", daemonaddr.WindowsPipeAddr)
-	}
-	return "sudo netbird service install --daemon-addr unix:///var/run/netbird.sock"
-}
-
-func capitalize(s string) string {
-	if s == "" {
-		return s
-	}
-	return strings.ToUpper(s[:1]) + s[1:]
-}
-
-// enables reports whether requested turns a flag on that is currently off. A
-// request that restates the stored value, or turns the flag off, is not a
-// privileged change.
-func enables(stored, requested *bool) bool {
-	if requested == nil || !*requested {
-		return false
-	}
-	return stored == nil || !*stored
-}
-
-// storedFlag reads a flag from the stored config, tolerating a config that does
-// not exist yet.
-func storedFlag(cfg *profilemanager.Config, get func(*profilemanager.Config) *bool) *bool {
-	if cfg == nil {
-		return nil
-	}
-	return get(cfg)
-}
-
-// sshServerEnabled reports whether the profile currently runs the SSH server.
-//
-// A nil flag means ON, matching what the engine does with the same config
-// (util.ReturnBoolWithDefaultTrue in internal/connect.go, kept for configs written
-// before the flag existed). Reading it as OFF here would open the management-URL
-// and deregistration guards on exactly those legacy hosts, whose SSH server is
-// running. Configs loaded through profilemanager have already been materialised by
-// apply(), so this is the same answer by a route that does not depend on that.
-func sshServerEnabled(cfg *profilemanager.Config) bool {
-	if cfg == nil {
-		return false
-	}
-	return util.ReturnBoolWithDefaultTrue(cfg.ServerSSHAllowed)
-}
-
-// sshServerCurrentlyAllowed is the value an enable request is compared against. It
-// shares sshServerEnabled's nil-means-on default, so restating "on" for a legacy
-// config is correctly seen as no change.
-func sshServerCurrentlyAllowed(cfg *profilemanager.Config) *bool {
-	enabled := sshServerEnabled(cfg)
-	if cfg == nil {
-		return nil
-	}
-	return &enabled
-}
-
-// sameManagementURL reports whether requested addresses the same management
-// server as stored, comparing scheme, host and effective port so that an
-// equivalent spelling ("https://api.netbird.io" for a stored
-// "https://api.netbird.io:443") is not treated as a change. It fails closed:
-// anything unparseable counts as a change and therefore needs privilege.
-func sameManagementURL(stored *url.URL, requested string) bool {
-	if stored == nil {
-		return false
-	}
-
-	// Normalise the requested URL through the config layer's own parser, so the
-	// comparison cannot drift from how the value would actually be stored.
-	parsed, err := profilemanager.ParseServiceURL("Management URL", requested)
-	if err != nil {
-		return false
-	}
-
-	return stored.Scheme == parsed.Scheme &&
-		stored.Hostname() == parsed.Hostname() &&
-		effectivePort(stored) == effectivePort(parsed)
-}
-
-func effectivePort(u *url.URL) string {
-	if port := u.Port(); port != "" {
-		return port
-	}
-	switch u.Scheme {
-	case "https":
-		return "443"
-	case "http":
-		return "80"
-	default:
-		return ""
-	}
-}

client/server/ssh_gate_test.go

@@ -1,348 +0,0 @@
-package server
-
-import (
-	"context"
-	"net/url"
-	"os"
-	"runtime"
-	"strings"
-	"testing"
-
-	"google.golang.org/genproto/googleapis/rpc/errdetails"
-	"google.golang.org/grpc/codes"
-	"google.golang.org/grpc/credentials"
-	"google.golang.org/grpc/peer"
-	gstatus "google.golang.org/grpc/status"
-
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-	"github.com/netbirdio/netbird/client/internal/profilemanager"
-)
-
-// ctxWithIdentity builds a request context carrying the identity the transport
-// credentials would have attached.
-func ctxWithIdentity(id ipcauth.Identity) context.Context {
-	return peer.NewContext(context.Background(), &peer.Peer{
-		AuthInfo: ipcauth.AuthInfo{
-			CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
-			Identity:       id,
-		},
-	})
-}
-
-// unprivUID is deliberately not this process's own uid. An unprivileged daemon
-// treats a caller sharing its identity as privileged (rootless containers), and
-// the test binary would otherwise stand in for both the daemon and the caller.
-// os.Geteuid returns -1 on Windows, where identities are SIDs instead and this is
-// unused.
-var unprivUID = uint32(os.Geteuid() + 1)
-
-// The fabricated identities have to be shaped like the platform's: a uid says
-// nothing on Windows, and a zero uid there would read as root and be privileged.
-func rootCtx() context.Context { return ctxWithIdentity(privilegedIdentity()) }
-func userCtx() context.Context { return ctxWithIdentity(unprivilegedIdentity()) }
-
-func privilegedIdentity() ipcauth.Identity {
-	if runtime.GOOS == "windows" {
-		// LocalSystem, which is what the Windows service account is.
-		return ipcauth.Identity{SID: "S-1-5-18"}
-	}
-	return ipcauth.Identity{UID: 0}
-}
-
-func unprivilegedIdentity() ipcauth.Identity {
-	if runtime.GOOS == "windows" {
-		// A plain user SID: no groups, so no BUILTIN\Administrators, and not
-		// elevated.
-		return ipcauth.Identity{SID: "S-1-5-21-1-2-3-1001"}
-	}
-	return ipcauth.Identity{UID: unprivUID, GID: unprivUID}
-}
-func noIdentityCtx() context.Context { return context.Background() }
-
-func boolPtr(v bool) *bool { return &v }
-
-func mustURL(t *testing.T, raw string) *url.URL {
-	t.Helper()
-	u, err := url.Parse(raw)
-	if err != nil {
-		t.Fatalf("parse %q: %v", raw, err)
-	}
-	return u
-}
-
-func assertDenied(t *testing.T, err error) {
-	t.Helper()
-	if err == nil {
-		t.Fatal("expected the change to be refused, got nil")
-	}
-	st := gstatus.Convert(err)
-	if st.Code() != codes.PermissionDenied {
-		t.Fatalf("code = %v, want PermissionDenied", st.Code())
-	}
-	// The refusal must be machine-readable: the CLI and the UI render the
-	// summary and command from the detail rather than parsing the message.
-	var info *errdetails.ErrorInfo
-	for _, d := range st.Details() {
-		if got, ok := d.(*errdetails.ErrorInfo); ok {
-			info = got
-		}
-	}
-	if info == nil {
-		t.Fatal("refusal carries no ErrorInfo detail")
-	}
-	if info.GetReason() != ipcauth.ErrorReasonPrivilegeRequired || info.GetDomain() != ipcauth.ErrorDomain {
-		t.Fatalf("detail = %s/%s, want %s/%s", info.GetDomain(), info.GetReason(), ipcauth.ErrorDomain, ipcauth.ErrorReasonPrivilegeRequired)
-	}
-	if info.GetMetadata()[ipcauth.ErrorMetaSummary] == "" {
-		t.Error("detail carries no summary")
-	}
-	if info.GetMetadata()[ipcauth.ErrorMetaCommand] == "" {
-		t.Error("detail carries no command")
-	}
-}
-
-func assertAllowed(t *testing.T, err error) {
-	t.Helper()
-	if err != nil {
-		t.Fatalf("expected the change to be allowed, got %v", err)
-	}
-}
-
-func TestRequirePrivilegeForConfigChange_SSHFlags(t *testing.T) {
-	tests := []struct {
-		name       string
-		stored     *profilemanager.Config
-		change     privilegedConfigChange
-		privileged bool
-		wantDeny   bool
-	}{
-		{
-			name:     "enabling the ssh server unprivileged is refused",
-			stored:   &profilemanager.Config{ServerSSHAllowed: boolPtr(false)},
-			change:   privilegedConfigChange{serverSSHAllowed: boolPtr(true)},
-			wantDeny: true,
-		},
-		{
-			name:       "enabling the ssh server as root is allowed",
-			stored:     &profilemanager.Config{ServerSSHAllowed: boolPtr(false)},
-			change:     privilegedConfigChange{serverSSHAllowed: boolPtr(true)},
-			privileged: true,
-		},
-		{
-			name:   "restating an already enabled ssh server is not a change",
-			stored: &profilemanager.Config{ServerSSHAllowed: boolPtr(true)},
-			change: privilegedConfigChange{serverSSHAllowed: boolPtr(true)},
-		},
-		{
-			name:   "turning the ssh server off is not guarded",
-			stored: &profilemanager.Config{ServerSSHAllowed: boolPtr(true)},
-			change: privilegedConfigChange{serverSSHAllowed: boolPtr(false)},
-		},
-		{
-			name:     "a profile with no config yet counts as off, so enabling is refused",
-			stored:   nil,
-			change:   privilegedConfigChange{serverSSHAllowed: boolPtr(true)},
-			wantDeny: true,
-		},
-		{
-			name:     "enabling ssh root login unprivileged is refused",
-			stored:   &profilemanager.Config{EnableSSHRoot: boolPtr(false)},
-			change:   privilegedConfigChange{enableSSHRoot: boolPtr(true)},
-			wantDeny: true,
-		},
-		{
-			name:   "restating ssh root login is not a change",
-			stored: &profilemanager.Config{EnableSSHRoot: boolPtr(true)},
-			change: privilegedConfigChange{enableSSHRoot: boolPtr(true)},
-		},
-		{
-			name:   "turning ssh root login off is not guarded",
-			stored: &profilemanager.Config{EnableSSHRoot: boolPtr(true)},
-			change: privilegedConfigChange{enableSSHRoot: boolPtr(false)},
-		},
-		{
-			name:     "disabling ssh authentication unprivileged is refused",
-			stored:   &profilemanager.Config{DisableSSHAuth: boolPtr(false)},
-			change:   privilegedConfigChange{disableSSHAuth: boolPtr(true)},
-			wantDeny: true,
-		},
-		{
-			name:   "re-enabling ssh authentication is not guarded",
-			stored: &profilemanager.Config{DisableSSHAuth: boolPtr(true)},
-			change: privilegedConfigChange{disableSSHAuth: boolPtr(false)},
-		},
-		{
-			name:   "a request that touches none of the guarded fields is allowed",
-			stored: &profilemanager.Config{ServerSSHAllowed: boolPtr(false)},
-			change: privilegedConfigChange{},
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			ctx := userCtx()
-			if tt.privileged {
-				ctx = rootCtx()
-			}
-			err := requirePrivilegeForConfigChange(ctx, tt.stored, tt.change)
-			if tt.wantDeny {
-				assertDenied(t, err)
-				return
-			}
-			assertAllowed(t, err)
-		})
-	}
-}
-
-func TestRequirePrivilegeForConfigChange_ManagementURL(t *testing.T) {
-	sshOn := func(raw string) *profilemanager.Config {
-		return &profilemanager.Config{ServerSSHAllowed: boolPtr(true), ManagementURL: mustURL(t, raw)}
-	}
-	sshOff := func(raw string) *profilemanager.Config {
-		return &profilemanager.Config{ServerSSHAllowed: boolPtr(false), ManagementURL: mustURL(t, raw)}
-	}
-
-	tests := []struct {
-		name       string
-		stored     *profilemanager.Config
-		requested  string
-		privileged bool
-		wantDeny   bool
-	}{
-		{
-			name:      "moving the binding while ssh is enabled is refused",
-			stored:    sshOn("https://api.netbird.io:443"),
-			requested: "https://attacker.example.com:443",
-			wantDeny:  true,
-		},
-		{
-			name:       "moving the binding as root is allowed",
-			stored:     sshOn("https://api.netbird.io:443"),
-			requested:  "https://selfhosted.example.com:443",
-			privileged: true,
-		},
-		{
-			name:      "the same url restated is not a change",
-			stored:    sshOn("https://api.netbird.io:443"),
-			requested: "https://api.netbird.io:443",
-		},
-		{
-			name:      "an equivalent spelling of the same url is not a change",
-			stored:    sshOn("https://api.netbird.io:443"),
-			requested: "https://api.netbird.io",
-		},
-		{
-			name:      "an equivalent spelling with an explicit http port is not a change",
-			stored:    sshOn("http://mgmt.internal:80"),
-			requested: "http://mgmt.internal",
-		},
-		{
-			name:      "a different port on the same host is a change",
-			stored:    sshOn("https://api.netbird.io:443"),
-			requested: "https://api.netbird.io:8443",
-			wantDeny:  true,
-		},
-		{
-			name:      "a different scheme on the same host is a change",
-			stored:    sshOn("https://mgmt.internal:443"),
-			requested: "http://mgmt.internal:443",
-			wantDeny:  true,
-		},
-		{
-			name:      "with ssh disabled the binding is not guarded at all",
-			stored:    sshOff("https://api.netbird.io:443"),
-			requested: "https://attacker.example.com:443",
-		},
-		{
-			name:      "an unparseable url fails closed",
-			stored:    sshOn("https://api.netbird.io:443"),
-			requested: "ht tp://%zz",
-			wantDeny:  true,
-		},
-		{
-			name:      "an empty url leaves the binding alone",
-			stored:    sshOn("https://api.netbird.io:443"),
-			requested: "",
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			ctx := userCtx()
-			if tt.privileged {
-				ctx = rootCtx()
-			}
-			err := requirePrivilegeForConfigChange(ctx, tt.stored, privilegedConfigChange{managementURL: tt.requested})
-			if tt.wantDeny {
-				assertDenied(t, err)
-				return
-			}
-			assertAllowed(t, err)
-		})
-	}
-}
-
-// A caller the daemon cannot identify must be refused, not trusted: that is the
-// state on a TCP daemon socket, where no peer credentials exist.
-func TestRequirePrivilegeForConfigChange_UnidentifiedCallerIsRefused(t *testing.T) {
-	err := requirePrivilegeForConfigChange(noIdentityCtx(),
-		&profilemanager.Config{ServerSSHAllowed: boolPtr(false)},
-		privilegedConfigChange{serverSSHAllowed: boolPtr(true)})
-	assertDenied(t, err)
-
-	// The guidance must point at the socket rather than at sudo, since elevating
-	// would not help.
-	st := gstatus.Convert(err)
-	if !strings.Contains(st.Message(), "service install") {
-		t.Errorf("message %q does not tell the operator how to fix the socket", st.Message())
-	}
-}
-
-func TestRequirePrivilegeForDeregistration(t *testing.T) {
-	tests := []struct {
-		name       string
-		cfg        *profilemanager.Config
-		privileged bool
-		wantDeny   bool
-	}{
-		{
-			name:     "deregistering while ssh is enabled is refused",
-			cfg:      &profilemanager.Config{ServerSSHAllowed: boolPtr(true)},
-			wantDeny: true,
-		},
-		{
-			name:       "deregistering while ssh is enabled is allowed for root",
-			cfg:        &profilemanager.Config{ServerSSHAllowed: boolPtr(true)},
-			privileged: true,
-		},
-		{
-			name: "deregistering with ssh disabled is not guarded",
-			cfg:  &profilemanager.Config{ServerSSHAllowed: boolPtr(false)},
-		},
-		{
-			name: "deregistering a profile with no config is not guarded",
-			cfg:  nil,
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			ctx := userCtx()
-			if tt.privileged {
-				ctx = rootCtx()
-			}
-			err := requirePrivilegeForDeregistration(ctx, tt.cfg)
-			if tt.wantDeny {
-				assertDenied(t, err)
-				return
-			}
-			assertAllowed(t, err)
-		})
-	}
-}
-
-// privilegedTestCtx is the context a handler-level test should use when it is
-// standing in for a root/administrator caller. Tests that drive the handlers
-// directly have no transport credentials, and the privileged-change gate refuses
-// a caller it cannot identify.
-func privilegedTestCtx() context.Context { return rootCtx() }

client/ssh/client/client.go

@@ -9,6 +9,7 @@ import (
 	"path/filepath"
 	"runtime"
 	"strconv"
+	"strings"
 	"time"
 
 	log "github.com/sirupsen/logrus"
@@ -16,6 +17,7 @@ import (
 	"golang.org/x/crypto/ssh/knownhosts"
 	"golang.org/x/term"
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
 
 	"github.com/netbirdio/netbird/client/internal/daemonaddr"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
@@ -30,7 +32,7 @@ const (
 	// DefaultDaemonAddr is the default address for the NetBird daemon
 	DefaultDaemonAddr = "unix:///var/run/netbird.sock"
 	// DefaultDaemonAddrWindows is the default address for the NetBird daemon on Windows
-	DefaultDaemonAddrWindows = daemonaddr.WindowsPipeAddr
+	DefaultDaemonAddrWindows = "tcp://127.0.0.1:41731"
 )
 
 // Client wraps crypto/ssh Client for simplified SSH operations
@@ -266,7 +268,7 @@ func getDefaultDaemonAddr() string {
 		return addr
 	}
 	if runtime.GOOS == "windows" {
-		return daemonaddr.ResolveDaemonAddr(DefaultDaemonAddrWindows)
+		return DefaultDaemonAddrWindows
 	}
 	return daemonaddr.ResolveUnixDaemonAddr(DefaultDaemonAddr)
 }
@@ -408,9 +410,12 @@ func verifyHostKeyViaDaemon(hostname string, remote net.Addr, key ssh.PublicKey,
 }
 
 func connectToDaemon(daemonAddr string) (*grpc.ClientConn, error) {
-	target, opts := daemonaddr.DialTarget(daemonAddr)
+	addr := strings.TrimPrefix(daemonAddr, "tcp://")
 
-	conn, err := grpc.NewClient(target, opts...)
+	conn, err := grpc.NewClient(
+		addr,
+		grpc.WithTransportCredentials(insecure.NewCredentials()),
+	)
 	if err != nil {
 		log.Debugf("failed to create gRPC client for NetBird daemon at %s: %v", daemonAddr, err)
 		return nil, fmt.Errorf("failed to connect to NetBird daemon: %w", err)

client/ssh/proxy/proxy.go

@@ -9,6 +9,7 @@ import (
 	"net"
 	"os"
 	"strconv"
+	"strings"
 	"sync"
 	"time"
 
@@ -16,8 +17,8 @@ import (
 	log "github.com/sirupsen/logrus"
 	cryptossh "golang.org/x/crypto/ssh"
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
 
-	"github.com/netbirdio/netbird/client/internal/daemonaddr"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/proto"
 	nbssh "github.com/netbirdio/netbird/client/ssh"
@@ -54,8 +55,8 @@ type SSHProxy struct {
 }
 
 func New(daemonAddr, targetHost string, targetPort int, stderr io.Writer, browserOpener func(string) error) (*SSHProxy, error) {
-	target, opts := daemonaddr.DialTarget(daemonAddr)
-	grpcConn, err := grpc.NewClient(target, opts...)
+	grpcAddr := strings.TrimPrefix(daemonAddr, "tcp://")
+	grpcConn, err := grpc.NewClient(grpcAddr, grpc.WithTransportCredentials(insecure.NewCredentials()))
 	if err != nil {
 		return nil, fmt.Errorf("connect to daemon: %w", err)
 	}

client/ui/frontend/src/components/CopyToClipboard.tsx

@@ -18,9 +18,6 @@ type CopyToClipboardProps = {
     className?: string;
     iconClassName?: string;
     alwaysShowIcon?: boolean;
-    // wrap lets long content (a shell command, a path) break across lines
-    // instead of being truncated to one line.
-    wrap?: boolean;
     variant?: CopyToClipboardVariant;
     "aria-label"?: string;
     tabIndex?: number;
@@ -35,7 +32,6 @@ export const CopyToClipboard = ({
     className,
     iconClassName,
     alwaysShowIcon = false,
-    wrap = false,
     variant = "default",
     "aria-label": ariaLabel,
     tabIndex = 0,
@@ -87,8 +83,7 @@ export const CopyToClipboard = ({
         >
             <span
                 className={cn(
-                    "relative min-w-0",
-                    wrap ? "whitespace-pre-wrap break-all" : "truncate",
+                    "relative min-w-0 truncate",
                     "[&_*]:transition-colors",
                     VARIANT_HOVER[variant],
                 )}

client/ui/frontend/src/contexts/SettingsContext.tsx

@@ -14,7 +14,7 @@ import type { Config } from "@bindings/services/models.js";
 import i18next from "@/lib/i18n";
 import { useProfile } from "@/contexts/ProfileContext.tsx";
 import { SettingsSkeleton } from "@/modules/settings/SettingsSkeleton.tsx";
-import { errorCommand, errorDialog, formatErrorMessage as errorMessage } from "@/lib/errors.ts";
+import { errorDialog, formatErrorMessage as errorMessage } from "@/lib/errors.ts";
 
 const SAVE_DEBOUNCE_MS = 400;
 
@@ -68,21 +68,6 @@ const useSettingsState = () => {
         loadedRef.current = loaded;
     }, [loaded]);
 
-    // reload re-reads the daemon's config, which is authoritative. Used on
-    // mount, on the daemon's config_changed event, and to undo an optimistic
-    // update the daemon then rejected.
-    const reload = useCallback(
-        async (profileName: string) => {
-            try {
-                const data = await SettingsSvc.GetConfig({ profileName, username });
-                setLoaded({ profileName, data });
-            } catch (e) {
-                console.warn("[SettingsContext] reload after rejected save failed", e);
-            }
-        },
-        [username],
-    );
-
     useEffect(() => {
         if (!profileLoaded || !activeProfileId) return;
         let cancelled = false;
@@ -148,20 +133,13 @@ const useSettingsState = () => {
                     username,
                 });
             } catch (e) {
-                // The optimistic update is wrong now: the daemon refused it
-                // (a change that needs elevated privileges, an MDM-managed
-                // field, ...). Snap the controls back to what it actually
-                // holds before reporting, so the UI never shows a value the
-                // daemon does not have.
-                await reload(profileName);
                 await errorDialog({
                     Title: i18next.t("settings.error.saveTitle"),
                     Message: errorMessage(e),
-                    Command: errorCommand(e),
                 });
             }
         },
-        [username, reload],
+        [username],
     );
 
     const setField = useCallback(

client/ui/frontend/src/hooks/usePrivilege.ts

@@ -1,32 +0,0 @@
-import { useEffect, useState } from "react";
-import { Settings as SettingsSvc } from "@bindings/services";
-import { Privilege } from "@bindings/services/models.js";
-
-// usePrivilege reports whether this UI process may perform the changes the daemon
-// restricts to root/administrator. It is answered in-process from our own token
-// with the daemon's own rule, so there is no round-trip and it works while the
-// daemon is down.
-//
-// null means "not known yet", which includes the read having failed. Callers must
-// treat that as "do not restrict": the daemon enforces this regardless, so the
-// only thing a wrong guess here costs is a control that looks unavailable when it
-// is not, or a save that fails with the daemon's own guidance.
-export const usePrivilege = (): Privilege | null => {
-    const [privilege, setPrivilege] = useState<Privilege | null>(null);
-
-    useEffect(() => {
-        let cancelled = false;
-        SettingsSvc.Privilege()
-            .then((p) => {
-                if (!cancelled) setPrivilege(p);
-            })
-            .catch((e: unknown) => {
-                console.warn("[usePrivilege] read failed, not restricting controls", e);
-            });
-        return () => {
-            cancelled = true;
-        };
-    }, []);
-
-    return privilege;
-};

client/ui/frontend/src/lib/errors.ts

@@ -1,6 +1,6 @@
 import { WindowManager } from "@bindings/services";
 
-type ClassifiedError = { short: string; long: string; command: string };
+type ClassifiedError = { short: string; long: string };
 
 const asObject = (v: unknown): Record<string, unknown> | null =>
     v && typeof v === "object" ? (v as Record<string, unknown>) : null;
@@ -22,24 +22,20 @@ const toWailsEnvelope = (e: unknown): Record<string, unknown> | null => {
     return asObject(obj.cause) ?? parseJsonObject(obj.message);
 };
 
-// Read { short, long, command } from wherever the classified error sits in the envelope
+// Read { short, long } from wherever the classified error sits in the envelope
 const toClassifiedError = (v: unknown): ClassifiedError | null => {
     const o = asObject(v);
     if (!o) return null;
     const short = typeof o.short === "string" ? o.short : "";
     const long = typeof o.long === "string" ? o.long : "";
-    const command = typeof o.command === "string" ? o.command : "";
-    return short || long ? { short, long, command } : null;
-};
-
-const classify = (e: unknown): ClassifiedError | null => {
-    const envelope = toWailsEnvelope(e);
-    return toClassifiedError(envelope?.cause) ?? toClassifiedError(envelope);
+    return short || long ? { short, long } : null;
 };
 
 export const formatErrorMessage = (e: unknown): string => {
+    const envelope = toWailsEnvelope(e);
+
     // Prefer the structured { short, long } the daemon classifier produced.
-    const classified = classify(e);
+    const classified = toClassifiedError(envelope?.cause) ?? toClassifiedError(envelope);
     if (classified) {
         const { short, long } = classified;
         if (short && long && long !== short) return `${short} Details: ${long}`;
@@ -48,26 +44,17 @@ export const formatErrorMessage = (e: unknown): string => {
     }
 
     // Unclassified (a service returned the raw daemon error)
-    const envelope = toWailsEnvelope(e);
     const message = envelope?.message;
     if (typeof message === "string" && message) return message;
     if (e instanceof Error) return e.message;
     return String(e);
 };
 
-// errorCommand returns a command the user can run to complete an operation the
-// daemon refused, when the error carries one (a change that needs elevated
-// privileges). Empty for every other error.
-export const errorCommand = (e: unknown): string => classify(e)?.command ?? "";
-
 export type ErrorDialogOptions = {
     Title: string;
     Message: string;
-    // Command is shown for copying below the message. Defaults to the one the
-    // error carries, so callers only pass it to override.
-    Command?: string;
 };
 
 export function errorDialog(options: ErrorDialogOptions): Promise<void> {
-    return WindowManager.OpenError(options.Title, options.Message, options.Command ?? "");
+    return WindowManager.OpenError(options.Title, options.Message);
 }

client/ui/frontend/src/modules/auto-update/UpdateVersionCard.tsx

@@ -2,7 +2,6 @@ import { type ReactNode } from "react";
 import { useTranslation } from "react-i18next";
 import { Browser } from "@wailsio/runtime";
 import { DownloadIcon, NotepadText } from "lucide-react";
-import { Update as UpdateSvc } from "@bindings/services";
 import { Button } from "@/components/buttons/Button";
 import { useClientVersion } from "@/contexts/ClientVersionContext";
 import { cn } from "@/lib/cn";
@@ -15,12 +14,6 @@ function openUrl(url: string) {
     });
 }
 
-function openInstallerDownload() {
-    UpdateSvc.DownloadURL()
-        .then(openUrl)
-        .catch(() => openUrl(GITHUB_RELEASES));
-}
-
 export function UpdateVersionCard() {
     const { t } = useTranslation();
     const { updateVersion, enforced, triggerUpdate } = useClientVersion();
@@ -44,7 +37,11 @@ export function UpdateVersionCard() {
                         {t("update.card.installNow")}
                     </Button>
                 ) : (
-                    <Button variant={"primary"} size={"xs"} onClick={openInstallerDownload}>
+                    <Button
+                        variant={"primary"}
+                        size={"xs"}
+                        onClick={() => openUrl(GITHUB_RELEASES)}
+                    >
                         <DownloadIcon size={14} />
                         {t("update.card.getInstaller")}
                     </Button>

client/ui/frontend/src/modules/error/ErrorDialog.tsx

@@ -3,7 +3,6 @@ import { useTranslation } from "react-i18next";
 import { useSearchParams } from "react-router-dom";
 import { AlertCircleIcon } from "lucide-react";
 import { Button } from "@/components/buttons/Button";
-import { CopyToClipboard } from "@/components/CopyToClipboard";
 import { ConfirmDialog } from "@/components/dialog/ConfirmDialog";
 import { DialogActions } from "@/components/dialog/DialogActions";
 import { DialogDescription } from "@/components/dialog/DialogDescription";
@@ -13,22 +12,14 @@ import { WindowManager } from "@bindings/services";
 import { useAutoSizeWindow } from "@/hooks/useAutoSizeWindow";
 
 const WINDOW_WIDTH = 380;
-// A command needs the room to wrap at a sensible number of characters instead of
-// breaking every few words.
-const WINDOW_WIDTH_WITH_COMMAND = 460;
 
 export default function ErrorDialog() {
     const { t } = useTranslation();
+    const contentRef = useAutoSizeWindow<HTMLDivElement>(WINDOW_WIDTH);
     const [params] = useSearchParams();
 
     const title = params.get("title") || t("window.title.error");
     const message = params.get("message") || "";
-    // Set when the daemon refused an operation that needs elevated privileges:
-    // the command that performs it, offered for copying.
-    const command = params.get("command") || "";
-    const contentRef = useAutoSizeWindow<HTMLDivElement>(
-        command ? WINDOW_WIDTH_WITH_COMMAND : WINDOW_WIDTH,
-    );
 
     const close = useCallback(() => {
         WindowManager.CloseError().catch(console.error);
@@ -46,37 +37,15 @@ export default function ErrorDialog() {
         <ConfirmDialog ref={contentRef} aria-labelledby={"nb-error-dialog-title"}>
             <SquareIcon icon={AlertCircleIcon} variant={"danger"} />
 
-            <div className={"flex w-full flex-col items-center gap-1"}>
+            <div className={"flex flex-col items-center gap-1"}>
                 <DialogHeading id={"nb-error-dialog-title"} className={"text-balance"}>
                     {title}
                 </DialogHeading>
                 {message && (
                     <DialogDescription className={"text-balance"}>
-                        {/* select-text: the message often names a path, a flag or an
-                            address the user needs to act on. */}
-                        <span className={"select-text whitespace-pre-wrap break-words"}>
-                            {message}
-                        </span>
+                        <span className={"whitespace-pre-wrap break-words"}>{message}</span>
                     </DialogDescription>
                 )}
-                {command && (
-                    <CopyToClipboard
-                        message={command}
-                        alwaysShowIcon
-                        wrap
-                        variant={"bright"}
-                        className={
-                            "mt-2 w-full items-start gap-2 rounded-md bg-nb-gray-930 px-3 py-2 text-left"
-                        }
-                        aria-label={t("common.copy")}
-                    >
-                        <code
-                            className={"select-text break-all font-mono text-xs text-nb-gray-200"}
-                        >
-                            {command}
-                        </code>
-                    </CopyToClipboard>
-                )}
             </div>
 
             <DialogActions>