Files
netbird/management/internals/modules/reverseproxy/proxy/manager/manager.go
mlsmaycon 167ee08e14 feat(private-service): expose NetBird-only services over tunnel peers
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.
2026-05-20 22:46:18 +02:00

187 lines
6.9 KiB
Go

package manager
import (
"context"
"time"
log "github.com/sirupsen/logrus"
"go.opentelemetry.io/otel/metric"
"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
)
// store defines the interface for proxy persistence operations
type store interface {
SaveProxy(ctx context.Context, p *proxy.Proxy) error
DisconnectProxy(ctx context.Context, proxyID, sessionID string) error
UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) error
GetActiveProxyClusterAddresses(ctx context.Context) ([]string, error)
GetActiveProxyClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error)
GetProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
CleanupStaleProxies(ctx context.Context, inactivityDuration time.Duration) error
GetProxyByAccountID(ctx context.Context, accountID string) (*proxy.Proxy, error)
CountProxiesByAccountID(ctx context.Context, accountID string) (int64, error)
IsClusterAddressConflicting(ctx context.Context, clusterAddress, accountID string) (bool, error)
DeleteAccountCluster(ctx context.Context, clusterAddress, accountID string) error
}
// Manager handles all proxy operations
type Manager struct {
store store
metrics *metrics
}
// NewManager creates a new proxy Manager
func NewManager(store store, meter metric.Meter) (*Manager, error) {
m, err := newMetrics(meter)
if err != nil {
return nil, err
}
return &Manager{
store: store,
metrics: m,
}, nil
}
// Connect registers a new proxy connection in the database.
// capabilities may be nil for old proxies that do not report them.
func (m *Manager) Connect(ctx context.Context, proxyID, sessionID, clusterAddress, ipAddress string, accountID *string, capabilities *proxy.Capabilities) (*proxy.Proxy, error) {
now := time.Now()
var caps proxy.Capabilities
if capabilities != nil {
caps = *capabilities
}
p := &proxy.Proxy{
ID: proxyID,
SessionID: sessionID,
ClusterAddress: clusterAddress,
IPAddress: ipAddress,
AccountID: accountID,
LastSeen: now,
ConnectedAt: &now,
Status: proxy.StatusConnected,
Capabilities: caps,
}
if err := m.store.SaveProxy(ctx, p); err != nil {
log.WithContext(ctx).Errorf("failed to register proxy %s: %v", proxyID, err)
return nil, err
}
log.WithContext(ctx).WithFields(log.Fields{
"proxyID": proxyID,
"sessionID": sessionID,
"clusterAddress": clusterAddress,
"ipAddress": ipAddress,
}).Info("proxy connected")
return p, nil
}
// Disconnect marks a proxy as disconnected in the database.
func (m *Manager) Disconnect(ctx context.Context, proxyID, sessionID string) error {
if err := m.store.DisconnectProxy(ctx, proxyID, sessionID); err != nil {
log.WithContext(ctx).Errorf("failed to disconnect proxy %s session %s: %v", proxyID, sessionID, err)
return err
}
log.WithContext(ctx).WithFields(log.Fields{
"proxyID": proxyID,
"sessionID": sessionID,
}).Info("proxy disconnected")
return nil
}
// Heartbeat updates the proxy's last seen timestamp.
func (m *Manager) Heartbeat(ctx context.Context, p *proxy.Proxy) error {
if err := m.store.UpdateProxyHeartbeat(ctx, p); err != nil {
log.WithContext(ctx).Debugf("failed to update proxy %s heartbeat: %v", p.ID, err)
return err
}
log.WithContext(ctx).Tracef("updated heartbeat for proxy %s session %s", p.ID, p.SessionID)
m.metrics.IncrementProxyHeartbeatCount()
return nil
}
// GetActiveClusterAddresses returns all unique cluster addresses for active proxies
func (m *Manager) GetActiveClusterAddresses(ctx context.Context) ([]string, error) {
addresses, err := m.store.GetActiveProxyClusterAddresses(ctx)
if err != nil {
log.WithContext(ctx).Errorf("failed to get active proxy cluster addresses: %v", err)
return nil, err
}
return addresses, nil
}
// ClusterSupportsCustomPorts returns whether any active proxy in the cluster
// supports custom ports. Returns nil when no proxy has reported capabilities.
func (m Manager) ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool {
return m.store.GetClusterSupportsCustomPorts(ctx, clusterAddr)
}
// ClusterRequireSubdomain returns whether any active proxy in the cluster
// requires a subdomain. Returns nil when no proxy has reported capabilities.
func (m Manager) ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool {
return m.store.GetClusterRequireSubdomain(ctx, clusterAddr)
}
// ClusterSupportsCrowdSec returns whether all active proxies in the cluster
// have CrowdSec configured (unanimous). Returns nil when no proxy has reported capabilities.
func (m Manager) ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool {
return m.store.GetClusterSupportsCrowdSec(ctx, clusterAddr)
}
// ClusterSupportsPrivate reports whether any active proxy claims the private capability (nil = unreported).
func (m Manager) ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
return m.store.GetClusterSupportsPrivate(ctx, clusterAddr)
}
// CleanupStale removes proxies that haven't sent heartbeat in the specified duration
func (m *Manager) CleanupStale(ctx context.Context, inactivityDuration time.Duration) error {
if err := m.store.CleanupStaleProxies(ctx, inactivityDuration); err != nil {
log.WithContext(ctx).Errorf("failed to cleanup stale proxies: %v", err)
return err
}
return nil
}
func (m *Manager) GetActiveClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error) {
addresses, err := m.store.GetActiveProxyClusterAddressesForAccount(ctx, accountID)
if err != nil {
log.WithContext(ctx).Errorf("failed to get active proxy cluster addresses for account %s: %v", accountID, err)
return nil, err
}
return addresses, nil
}
func (m *Manager) GetAccountProxy(ctx context.Context, accountID string) (*proxy.Proxy, error) {
return m.store.GetProxyByAccountID(ctx, accountID)
}
func (m *Manager) CountAccountProxies(ctx context.Context, accountID string) (int64, error) {
return m.store.CountProxiesByAccountID(ctx, accountID)
}
func (m *Manager) IsClusterAddressAvailable(ctx context.Context, clusterAddress, accountID string) (bool, error) {
conflicting, err := m.store.IsClusterAddressConflicting(ctx, clusterAddress, accountID)
if err != nil {
return false, err
}
return !conflicting, nil
}
func (m *Manager) DeleteAccountCluster(ctx context.Context, clusterAddress, accountID string) error {
if err := m.store.DeleteAccountCluster(ctx, clusterAddress, accountID); err != nil {
log.WithContext(ctx).Errorf("failed to delete cluster %s for account %s: %v", clusterAddress, accountID, err)
return err
}
return nil
}