Merge remote-tracking branch 'origin/main' into refactor/permissions-manager

client/internal/engine.go

@@ -14,12 +14,14 @@ import (
 	"sort"
 	"strings"
 	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/hashicorp/go-multierror"
 	"github.com/pion/ice/v4"
 	"github.com/pion/stun/v3"
 	log "github.com/sirupsen/logrus"
+	wgdevice "golang.zx2c4.com/wireguard/device"
 	"golang.zx2c4.com/wireguard/tun/netstack"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
@@ -236,6 +238,12 @@ type Engine struct {
 
 	wgInterface WGIface
 
+	// wgDevice is a lock-free handle on the WireGuard device behind
+	// wgInterface. Reaching the device through wgInterface requires
+	// syncMsgMux, which handleSync holds while it adds and removes peers;
+	// SetPerformance must stay reachable exactly when that work is stuck.
+	wgDevice atomic.Pointer[wgdevice.Device]
+
 	udpMux *udpmux.UniversalUDPMuxDefault
 
 	// networkSerial is the latest CurrentSerial (state ID) of the network sent by the Management service
@@ -651,6 +659,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		log.Errorf("failed to pull up wgInterface [%s]: %s", e.wgInterface.Name(), err.Error())
 		return fmt.Errorf("up wg interface: %w", err)
 	}
+	e.wgDevice.Store(e.wgInterface.GetWGDevice())
 
 	// Set up notrack rules immediately after proxy is listening to prevent
 	// conntrack entries from being created before the rules are in place
@@ -2144,6 +2153,10 @@ func (e *Engine) close() {
 	log.Debugf("removing Netbird interface %s", e.config.WgIfaceName)
 
 	if e.wgInterface != nil {
+		// Drop the handle before the close starts: a retune that loads it
+		// afterwards would touch a device on its way out and report success
+		// for an engine that is already gone.
+		e.wgDevice.Store(nil)
 		if err := e.wgInterface.Close(); err != nil {
 			log.Errorf("failed closing Netbird interface %s %v", e.config.WgIfaceName, err)
 		}
@@ -2303,15 +2316,16 @@ type Performance struct {
 }
 
 // SetPerformance applies the given tuning to this engine's live Device.
+//
+// It deliberately does not take syncMsgMux. Raising the buffer pool cap is the
+// recovery path for a device whose pool is exhausted, and an exhausted pool
+// blocks peer removal inside handleSync, which holds syncMsgMux for as long as
+// it stays blocked. Taking the lock here would make the retune unreachable in
+// the one situation that needs it.
 func (e *Engine) SetPerformance(t Performance) error {
-	e.syncMsgMux.Lock()
-	defer e.syncMsgMux.Unlock()
-	if e.wgInterface == nil {
-		return fmt.Errorf("wg interface not initialized")
-	}
-	dev := e.wgInterface.GetWGDevice()
+	dev := e.wgDevice.Load()
 	if dev == nil {
-		return fmt.Errorf("wg device not initialized")
+		return errors.New("wg device not initialized")
 	}
 	if t.PreallocatedBuffersPerPool != nil {
 		dev.SetPreallocatedBuffersPerPool(*t.PreallocatedBuffersPerPool)

client/internal/peer/handshaker.go

@@ -116,7 +116,7 @@ func (h *Handshaker) Listen(ctx context.Context) {
 	for {
 		select {
 		case remoteOfferAnswer := <-h.remoteOffersCh:
-			h.log.Infof("received offer, running version %s, remote WireGuard listen port %d, session id: %s, remote ICE supported: %t", remoteOfferAnswer.Version, remoteOfferAnswer.WgListenPort, remoteOfferAnswer.SessionIDString(), remoteOfferAnswer.hasICECredentials())
+			h.log.Infof("received offer, running version %s, remote WireGuard listen port %d, session id: %s, remote ICE supported: %t, relay server: %s, relay IP: %s", remoteOfferAnswer.Version, remoteOfferAnswer.WgListenPort, remoteOfferAnswer.SessionIDString(), remoteOfferAnswer.hasICECredentials(), remoteOfferAnswer.RelaySrvAddress, remoteOfferAnswer.RelaySrvIP)
 
 			// Record signaling received for reconnection attempts
 			if h.metricsStages != nil {
@@ -138,7 +138,7 @@ func (h *Handshaker) Listen(ctx context.Context) {
 				continue
 			}
 		case remoteOfferAnswer := <-h.remoteAnswerCh:
-			h.log.Infof("received answer, running version %s, remote WireGuard listen port %d, session id: %s, remote ICE supported: %t", remoteOfferAnswer.Version, remoteOfferAnswer.WgListenPort, remoteOfferAnswer.SessionIDString(), remoteOfferAnswer.hasICECredentials())
+			h.log.Infof("received answer, running version %s, remote WireGuard listen port %d, session id: %s, remote ICE supported: %t, relay server: %s, relay IP: %s", remoteOfferAnswer.Version, remoteOfferAnswer.WgListenPort, remoteOfferAnswer.SessionIDString(), remoteOfferAnswer.hasICECredentials(), remoteOfferAnswer.RelaySrvAddress, remoteOfferAnswer.RelaySrvIP)
 
 			// Record signaling received for reconnection attempts
 			if h.metricsStages != nil {
@@ -209,14 +209,14 @@ func (h *Handshaker) sendOffer() error {
 	}
 
 	offer := h.buildOfferAnswer()
-	h.log.Debugf("sending offer with serial: %s", offer.SessionIDString())
+	h.log.Debugf("sending offer with serial: %s, relay server: %s, relay IP: %s", offer.SessionIDString(), offer.RelaySrvAddress, offer.RelaySrvIP)
 
 	return h.signaler.SignalOffer(offer, h.config.Key)
 }
 
 func (h *Handshaker) sendAnswer() error {
 	answer := h.buildOfferAnswer()
-	h.log.Debugf("sending answer with serial: %s", answer.SessionIDString())
+	h.log.Debugf("sending answer with serial: %s, relay server: %s, relay IP: %s", answer.SessionIDString(), answer.RelaySrvAddress, answer.RelaySrvIP)
 
 	return h.signaler.SignalAnswer(answer, h.config.Key)
 }