[management, client, proxy] add expose NetBird-only services over tunnel peers (#6226)

Adds a new "private" service mode for the reverse proxy: services reachable exclusively over the embedded WireGuard tunnel, gated by per-peer group membership instead of operator auth schemes.

Wire contract
- ProxyMapping.private (field 13): the proxy MUST call ValidateTunnelPeer and fail closed; operator schemes are bypassed.
- ProxyCapabilities.private (4) + supports_private_service (5): capability gate. Management never streams private mappings to proxies that don't claim the capability; the broadcast path applies the same filter via filterMappingsForProxy.
- ValidateTunnelPeer RPC: resolves an inbound tunnel IP to a peer, checks the peer's groups against service.AccessGroups, and mints a session JWT on success. checkPeerGroupAccess fails closed when a private service has empty AccessGroups.
- ValidateSession/ValidateTunnelPeer responses now carry peer_group_ids + peer_group_names so the proxy can authorise policy-aware middlewares without an extra management round-trip.
- ProxyInboundListener + SendStatusUpdate.inbound_listener: per-account inbound listener state surfaced to dashboards.
- PathTargetOptions.direct_upstream (11): bypass the embedded NetBird client and dial the target via the proxy host's network stack for upstreams reachable without WireGuard.

Data model
- Service.Private (bool) + Service.AccessGroups ([]string, JSON- serialised). Validate() rejects bearer auth on private services. Copy() deep-copies AccessGroups. pgx getServices loads the columns.
- DomainConfig.Private threaded into the proxy auth middleware. Request handler routes private services through forwardWithTunnelPeer and returns 403 on validation failure.
- Account-level SynthesizePrivateServiceZones (synthetic DNS) and injectPrivateServicePolicies (synthetic ACL) gate on len(svc.AccessGroups) > 0.

Proxy
- /netbird proxy --private (embedded mode) flag; Config.Private in proxy/lifecycle.go.
- Per-account inbound listener (proxy/inbound.go) binding HTTP/HTTPS on the embedded NetBird client's WireGuard tunnel netstack.
- proxy/internal/auth/tunnel_cache: ValidateTunnelPeer response cache with single-flight de-duplication and per-account eviction.
- Local peerstore short-circuit: when the inbound IP isn't in the account roster, deny fast without an RPC.
- proxy/server.go reports SupportsPrivateService=true and redacts the full ProxyMapping JSON from info logs (auth_token + header-auth hashed values now only at debug level).

Identity forwarding
- ValidateSessionJWT returns user_id, email, method, groups, group_names. sessionkey.Claims carries Email + Groups + GroupNames so the proxy can stamp identity onto upstream requests without an extra management round-trip on every cookie-bearing request.
- CapturedData carries userEmail / userGroups / userGroupNames; the proxy stamps X-NetBird-User and X-NetBird-Groups on r.Out from the authenticated identity (strips client-supplied values first to prevent spoofing).
- AccessLog.UserGroups: access-log enrichment captures the user's group memberships at write time so the dashboard can render group context without reverse-resolving stale memberships.

OpenAPI/dashboard surface
- ReverseProxyService gains private + access_groups; ReverseProxyCluster gains private + supports_private. ReverseProxyTarget target_type enum gains "cluster". ServiceTargetOptions gains direct_upstream. ProxyAccessLog gains user_groups.
This commit is contained in:
Maycon Santos
2026-05-25 17:41:50 +02:00
committed by GitHub
parent 0358be2313
commit 7aebdd69dd
84 changed files with 7810 additions and 933 deletions
+52 -30
View File
@@ -185,9 +185,12 @@ func (s *StatusChangeSubscription) Events() chan map[string]RouterState {
return s.eventsChan
}
// Status holds a state of peers, signal, management connections and relays
// Status holds a state of peers, signal, management connections and relays.
// mux is an RWMutex so hot read paths (notably PeerStateByIP, called for
// every private-service request) don't contend against each other.
// Pure read methods take RLock; anything that mutates state takes Lock.
type Status struct {
mux sync.Mutex
mux sync.RWMutex
peers map[string]State
changeNotify map[string]map[string]*StatusChangeSubscription // map[peerID]map[subscriptionID]*StatusChangeSubscription
signalState bool
@@ -283,8 +286,8 @@ func (d *Status) AddPeer(peerPubKey string, fqdn string, ip string, ipv6 string)
// GetPeer adds peer to Daemon status map
func (d *Status) GetPeer(peerPubKey string) (State, error) {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
state, ok := d.peers[peerPubKey]
if !ok {
@@ -294,8 +297,8 @@ func (d *Status) GetPeer(peerPubKey string) (State, error) {
}
func (d *Status) PeerByIP(ip string) (string, bool) {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
for _, state := range d.peers {
if state.IP == ip {
@@ -305,6 +308,25 @@ func (d *Status) PeerByIP(ip string) (string, bool) {
return "", false
}
// PeerStateByIP returns the full peer State for the given tunnel IP.
// Matches against either the IPv4 (State.IP) or IPv6 (State.IPv6) tunnel
// address so dual-stack peers are reachable on either family. Returns the
// zero State and false when no peer matches or the input is empty.
func (d *Status) PeerStateByIP(ip string) (State, bool) {
if ip == "" {
return State{}, false
}
d.mux.RLock()
defer d.mux.RUnlock()
for _, state := range d.peers {
if (state.IP != "" && state.IP == ip) || (state.IPv6 != "" && state.IPv6 == ip) {
return state, true
}
}
return State{}, false
}
// RemovePeer removes peer from Daemon status map
func (d *Status) RemovePeer(peerPubKey string) error {
d.mux.Lock()
@@ -702,8 +724,8 @@ func (d *Status) UnsubscribePeerStateChanges(subscription *StatusChangeSubscript
// GetLocalPeerState returns the local peer state
func (d *Status) GetLocalPeerState() LocalPeerState {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
return d.localPeer.Clone()
}
@@ -909,8 +931,8 @@ func (d *Status) DeleteResolvedDomainsStates(domain domain.Domain) {
}
func (d *Status) GetRosenpassState() RosenpassState {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
return RosenpassState{
d.rosenpassEnabled,
d.rosenpassPermissive,
@@ -918,14 +940,14 @@ func (d *Status) GetRosenpassState() RosenpassState {
}
func (d *Status) GetLazyConnection() bool {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
return d.lazyConnectionEnabled
}
func (d *Status) GetManagementState() ManagementState {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
return ManagementState{
d.mgmAddress,
d.managementState,
@@ -951,8 +973,8 @@ func (d *Status) UpdateLatency(pubKey string, latency time.Duration) error {
// IsLoginRequired determines if a peer's login has expired.
func (d *Status) IsLoginRequired() bool {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
// if peer is connected to the management then login is not expired
if d.managementState {
@@ -967,8 +989,8 @@ func (d *Status) IsLoginRequired() bool {
}
func (d *Status) GetSignalState() SignalState {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
return SignalState{
d.signalAddress,
d.signalState,
@@ -978,8 +1000,8 @@ func (d *Status) GetSignalState() SignalState {
// GetRelayStates returns the stun/turn/permanent relay states
func (d *Status) GetRelayStates() []relay.ProbeResult {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
if d.relayMgr == nil {
return d.relayStates
}
@@ -1008,8 +1030,8 @@ func (d *Status) GetRelayStates() []relay.ProbeResult {
}
func (d *Status) ForwardingRules() []firewall.ForwardRule {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
if d.ingressGwMgr == nil {
return nil
}
@@ -1018,16 +1040,16 @@ func (d *Status) ForwardingRules() []firewall.ForwardRule {
}
func (d *Status) GetDNSStates() []NSGroupState {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
// shallow copy is good enough, as slices fields are currently not updated
return slices.Clone(d.nsGroupStates)
}
func (d *Status) GetResolvedDomainsStates() map[domain.Domain]ResolvedDomainInfo {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
return maps.Clone(d.resolvedDomainsStates)
}
@@ -1043,8 +1065,8 @@ func (d *Status) GetFullStatus() FullStatus {
LazyConnectionEnabled: d.GetLazyConnection(),
}
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
fullStatus.LocalPeerState = d.localPeer
@@ -1219,8 +1241,8 @@ func (d *Status) SetWgIface(wgInterface WGIfaceStatus) {
}
func (d *Status) PeersStatus() (*configurer.Stats, error) {
d.mux.Lock()
defer d.mux.Unlock()
d.mux.RLock()
defer d.mux.RUnlock()
if d.wgIface == nil {
return nil, fmt.Errorf("wgInterface is nil, cannot retrieve peers status")
}
+27
View File
@@ -63,6 +63,33 @@ func TestUpdatePeerState(t *testing.T) {
assert.Equal(t, ip, state.IP, "ip should be equal")
}
func TestStatus_PeerStateByIP(t *testing.T) {
status := NewRecorder("https://mgm")
req := require.New(t)
req.NoError(status.AddPeer("pk-1", "peer-1.netbird", "100.64.0.10", ""))
req.NoError(status.AddPeer("pk-2", "peer-2.netbird", "100.64.0.11", ""))
state, ok := status.PeerStateByIP("100.64.0.10")
req.True(ok, "known tunnel IP should resolve to a peer state")
req.Equal("pk-1", state.PubKey, "matching state must carry the right pub key")
req.Equal("peer-1.netbird", state.FQDN, "matching state must carry the right FQDN")
_, ok = status.PeerStateByIP("100.64.0.99")
req.False(ok, "unknown IP must report ok=false")
}
func TestStatus_PeerStateByIP_MatchesIPv6(t *testing.T) {
status := NewRecorder("https://mgm")
req := require.New(t)
req.NoError(status.AddPeer("pk-1", "peer-1.netbird", "100.64.0.10", "fd00::1"))
state, ok := status.PeerStateByIP("fd00::1")
req.True(ok, "IPv6-only match must resolve to the peer state")
req.Equal("pk-1", state.PubKey, "matching state must carry the right pub key")
}
func TestStatus_UpdatePeerFQDN(t *testing.T) {
key := "abc"
fqdn := "peer-a.netbird.local"