[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
+55 -2
View File
@@ -1090,6 +1090,38 @@ func (s *SqlStore) GetCustomDomainsCounts(ctx context.Context) (int64, int64, er
return total, validated, nil
}
// GetProxyMetrics aggregates per-cluster + per-proxy counts for the
// self-hosted telemetry payload. Single round-trip via conditional
// aggregations so a large proxies table doesn't fan out into multiple
// queries.
func (s *SqlStore) GetProxyMetrics(ctx context.Context) (ProxyMetrics, error) {
var m ProxyMetrics
activeCutoff := time.Now().Add(-proxyActiveThreshold)
// COUNT(DISTINCT ... CASE WHEN ...) is portable across sqlite/postgres
// (MySQL too) and keeps the round-trip to one. proxy.StatusConnected
// is the same string the cluster-capability queries use; the active
// window matches the cluster-capability semantics (only proxies
// heartbeating within ~2 * heartbeat interval count as connected).
row := s.db.WithContext(ctx).
Model(&proxy.Proxy{}).
Select(
"COUNT(DISTINCT cluster_address) AS clusters, "+
"COUNT(DISTINCT CASE WHEN account_id IS NOT NULL THEN cluster_address END) AS clusters_byop, "+
"COUNT(DISTINCT CASE WHEN private = ? THEN cluster_address END) AS clusters_private, "+
"COUNT(*) AS proxies, "+
"COUNT(CASE WHEN status = ? AND last_seen > ? THEN 1 END) AS proxies_connected",
true,
proxy.StatusConnected,
activeCutoff,
).
Row()
if err := row.Scan(&m.Clusters, &m.ClustersBYOP, &m.ClustersPrivate, &m.Proxies, &m.ProxiesConnected); err != nil {
return ProxyMetrics{}, fmt.Errorf("scan proxy metrics: %w", err)
}
return m, nil
}
func (s *SqlStore) GetAllAccounts(ctx context.Context) (all []*types.Account) {
var accounts []types.Account
result := s.db.Find(&accounts)
@@ -2178,7 +2210,8 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
const serviceQuery = `SELECT id, account_id, name, domain, enabled, auth,
meta_created_at, meta_certificate_issued_at, meta_status, proxy_cluster,
pass_host_header, rewrite_redirects, session_private_key, session_public_key,
mode, listen_port, port_auto_assigned, source, source_peer, terminated
mode, listen_port, port_auto_assigned, source, source_peer, terminated,
private, access_groups
FROM services WHERE account_id = $1`
const targetsQuery = `SELECT id, account_id, service_id, path, host, port, protocol,
@@ -2193,10 +2226,11 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
services, err := pgx.CollectRows(serviceRows, func(row pgx.CollectableRow) (*rpservice.Service, error) {
var s rpservice.Service
var auth []byte
var accessGroups []byte
var createdAt, certIssuedAt sql.NullTime
var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
var mode, source, sourcePeer sql.NullString
var terminated, portAutoAssigned sql.NullBool
var terminated, portAutoAssigned, private sql.NullBool
var listenPort sql.NullInt64
err := row.Scan(
&s.ID,
@@ -2219,6 +2253,8 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
&source,
&sourcePeer,
&terminated,
&private,
&accessGroups,
)
if err != nil {
return nil, err
@@ -2230,6 +2266,16 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
}
}
if len(accessGroups) > 0 {
if err := json.Unmarshal(accessGroups, &s.AccessGroups); err != nil {
return nil, fmt.Errorf("unmarshal access_groups: %w", err)
}
}
if private.Valid {
s.Private = private.Bool
}
s.Meta = rpservice.Meta{}
if createdAt.Valid {
s.Meta.CreatedAt = createdAt.Time
@@ -5826,6 +5872,7 @@ var validCapabilityColumns = map[string]struct{}{
"supports_custom_ports": {},
"require_subdomain": {},
"supports_crowdsec": {},
"private": {},
}
// GetClusterSupportsCustomPorts returns whether any active proxy in the cluster
@@ -5840,6 +5887,12 @@ func (s *SqlStore) GetClusterRequireSubdomain(ctx context.Context, clusterAddr s
return s.getClusterCapability(ctx, clusterAddr, "require_subdomain")
}
// GetClusterSupportsPrivate reports whether any active proxy in the cluster
// has the private capability (nil = unreported).
func (s *SqlStore) GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
return s.getClusterCapability(ctx, clusterAddr, "private")
}
// GetClusterSupportsCrowdSec returns whether all active proxies in the cluster
// have CrowdSec configured. Returns nil when no proxy reported the capability.
// Unlike other capabilities that use ANY-true (for rolling upgrades), CrowdSec