feat(acl): keys + ACLs reach driver-only nodes via the artifact (#520 stage 4)
A driver-only node has had no ConfigDb since per-cluster mesh Phase 4, so it registered NullOpcUaUserAuthenticator and denied every UserName token. Its keys now ride the deployment artifact instead. - ConfigComposer snapshots ApiKeys alongside the NodeAcls it already carried. Only the peppered HMAC ships, never a secret, and the pepper is node config that is deliberately not in the artifact. - DeploymentArtifact.ParseDataPlaneAuthority decodes both node-side. Grants are scoped to the node's own cluster; keys are not, because ApiKey carries no ClusterId — a key is a fleet-wide credential and the ACL rows are what bind it. - OpcUaPublishActor installs them on DataPlaneAuthorityState on every apply, BEFORE its plan.IsEmpty early-return: an artifact that only revokes a key produces an empty address-space plan, so feeding after that return would leave the revoked key working until an unrelated structural change redeployed. - ArtifactApiKeyStore serves them to session activation; a node with a ConfigDb keeps ConfigDbApiKeyStore, whose per-request read is what makes revocation immediate there. - OtOpcUaNodeManager gains DataPlaneAuthority — the cluster identity blocker #4 named. NodeScope.ClusterId is required and the evaluator fails closed on a mismatch, so until now no scope it built could have evaluated. Nothing reads it until stages 5/6. The generation is a node-local COUNTER driven by the RevisionHash, not derived from its bits. PermissionTrieCache treats the highest GenerationId as current, so a generation taken from hash bytes would install a lower number about half the time and the cache would go on serving the previous deployment's ACLs, silently. Sessions are not stamped with it yet — that belongs with the first seam that reads a UserAuthorizationState, in stage 5, rather than being built now and consulted by nothing. Live-gated on docker-dev against site-a-1 (driver-only, no ConfigDb): key authenticates, wrong secret denied, both halves of the revocation asymmetry observed, and a SITE-A grant confirmed not to reach site-b-1. Key minted with an independent Python HMAC so the verifier was checked against something other than itself. Rig left clean. Claude-Session: https://claude.ai/code/session_015p7wGqy3YpZNCpDzTpGMKo
This commit is contained in:
Joseph Doherty
@@ -9,6 +9,7 @@ using ZB.MOM.WW.OtOpcUa.Commons.Observability;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Types;
|
||||
using ZB.MOM.WW.OtOpcUa.Configuration;
|
||||
using ZB.MOM.WW.OtOpcUa.Core.Authorization;
|
||||
using ZB.MOM.WW.OtOpcUa.OpcUaServer;
|
||||
using ZB.MOM.WW.OtOpcUa.Runtime.Drivers;
|
||||
using ZB.MOM.WW.OtOpcUa.Runtime.Health;
|
||||
@@ -95,6 +96,10 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
|
||||
private readonly NodeId? _localNode;
|
||||
private readonly IDbContextFactory<OtOpcUaConfigDbContext>? _dbFactory;
|
||||
private readonly AddressSpaceApplier? _applier;
|
||||
/// <summary>#520 stage 4 — receives the API keys + ACL grants carried by each applied artifact, so
|
||||
/// OPC UA session activation can authenticate. Null when nothing consumes it (tests, and any node
|
||||
/// that is not serving an OPC UA data plane).</summary>
|
||||
private readonly IDataPlaneAuthoritySink? _dataPlaneAuthority;
|
||||
private readonly IActorRef? _dbHealthProbe;
|
||||
/// <summary>Per-cluster mesh Phase 4: this is a driver-only node with NO ConfigDb (LocalDb is its
|
||||
/// config store). There is no DB to probe, so the ServiceLevel DB-reachability input is retired —
|
||||
@@ -166,7 +171,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
|
||||
TimeSpan? staleWindow = null,
|
||||
TimeSpan? probeFreshnessWindow = null,
|
||||
TimeSpan? healthTickInterval = null,
|
||||
bool dbLess = false) =>
|
||||
bool dbLess = false,
|
||||
IDataPlaneAuthoritySink? dataPlaneAuthority = null) =>
|
||||
Akka.Actor.Props.Create(() => new OpcUaPublishActor(
|
||||
sink ?? NullOpcUaAddressSpaceSink.Instance,
|
||||
serviceLevel ?? NullServiceLevelPublisher.Instance,
|
||||
@@ -178,7 +184,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
|
||||
staleWindow,
|
||||
probeFreshnessWindow,
|
||||
healthTickInterval,
|
||||
dbLess)).WithDispatcher(DispatcherId);
|
||||
dbLess,
|
||||
dataPlaneAuthority)).WithDispatcher(DispatcherId);
|
||||
|
||||
/// <summary>Test-only Props that omits the pinned-dispatcher requirement and skips the
|
||||
/// DPS subscribe so unit tests can spin up the actor on a vanilla TestKit cluster.</summary>
|
||||
@@ -214,7 +221,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
|
||||
TimeSpan? staleWindow = null,
|
||||
TimeSpan? probeFreshnessWindow = null,
|
||||
TimeSpan? healthTickInterval = null,
|
||||
bool dbLess = false) =>
|
||||
bool dbLess = false,
|
||||
IDataPlaneAuthoritySink? dataPlaneAuthority = null) =>
|
||||
Akka.Actor.Props.Create(() => new OpcUaPublishActor(
|
||||
sink ?? NullOpcUaAddressSpaceSink.Instance,
|
||||
serviceLevel ?? NullServiceLevelPublisher.Instance,
|
||||
@@ -226,7 +234,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
|
||||
staleWindow,
|
||||
probeFreshnessWindow,
|
||||
healthTickInterval,
|
||||
dbLess));
|
||||
dbLess,
|
||||
dataPlaneAuthority));
|
||||
|
||||
/// <summary>Initializes a new instance of the <see cref="OpcUaPublishActor"/> class.</summary>
|
||||
/// <param name="sink">The OPC UA address space sink.</param>
|
||||
@@ -259,9 +268,11 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
|
||||
TimeSpan? staleWindow = null,
|
||||
TimeSpan? probeFreshnessWindow = null,
|
||||
TimeSpan? healthTickInterval = null,
|
||||
bool dbLess = false)
|
||||
bool dbLess = false,
|
||||
IDataPlaneAuthoritySink? dataPlaneAuthority = null)
|
||||
{
|
||||
_sink = sink;
|
||||
_dataPlaneAuthority = dataPlaneAuthority;
|
||||
_serviceLevel = serviceLevel;
|
||||
_subscribeRedundancyTopic = subscribeRedundancyTopic;
|
||||
_localNode = localNode;
|
||||
@@ -412,6 +423,14 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
|
||||
return;
|
||||
}
|
||||
|
||||
// #520 stage 4 — install this artifact's API keys + ACL grants BEFORE the address-space work
|
||||
// below, and deliberately ahead of the `plan.IsEmpty` early-return: an artifact that revokes a
|
||||
// key or edits a grant without touching a single node produces an EMPTY address-space plan, so
|
||||
// feeding this after that return would leave a revoked key authenticating until some unrelated
|
||||
// structural change happened to redeploy. Authorization and topology change on their own
|
||||
// schedules.
|
||||
FeedDataPlaneAuthority(artifact);
|
||||
|
||||
var composition = _localNode is { } ln
|
||||
? DeploymentArtifact.ParseComposition(artifact, ln.Value,
|
||||
inconsistency => _log.Warning("OpcUaPublish {Node}: cross-cluster binding — {Message}", ln, inconsistency))
|
||||
@@ -491,6 +510,43 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Decode the artifact's data-plane authorization inputs (API keys + this cluster's ACL grants)
|
||||
/// and install them for OPC UA session activation (#520 stage 4). No-op when nothing consumes
|
||||
/// them.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// Wrapped so a decode failure can never break a deploy — the same discipline as the historised-ref
|
||||
/// feed. The cost of that choice is explicit: the node keeps serving the PREVIOUS key set, which is
|
||||
/// the safe direction for availability but means a revocation carried by an artifact this node
|
||||
/// could not decode has not taken effect. It is logged at Error for exactly that reason.
|
||||
/// </remarks>
|
||||
private void FeedDataPlaneAuthority(byte[] artifact)
|
||||
{
|
||||
if (_dataPlaneAuthority is null) return;
|
||||
|
||||
try
|
||||
{
|
||||
var nodeId = _localNode?.Value ?? string.Empty;
|
||||
var projection = DeploymentArtifact.ParseDataPlaneAuthority(artifact, nodeId);
|
||||
// The revision hash is SHA-256 of the artifact bytes — the same derivation ConfigComposer uses,
|
||||
// which is what lets a node recognise a re-applied revision without the hash riding the wire.
|
||||
var revision = Convert.ToHexStringLower(System.Security.Cryptography.SHA256.HashData(artifact));
|
||||
var snapshot = _dataPlaneAuthority.Apply(
|
||||
projection.ClusterId, revision, projection.Keys, projection.Grants);
|
||||
|
||||
_log.Info(
|
||||
"OpcUaPublish: data-plane authority generation {Generation} installed (cluster={Cluster}, revision={Revision}, keys={Keys}, grants={Grants})",
|
||||
snapshot.GenerationId, projection.ClusterId ?? "(single-cluster)", revision[..12],
|
||||
projection.Keys.Count, projection.Grants.Count);
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
_log.Error(ex,
|
||||
"OpcUaPublish: failed to install data-plane authority from the applied artifact — the node keeps the PREVIOUS keys and grants, so any revocation in this deployment has NOT taken effect");
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>Read a specific deployment's artifact blob from ConfigDb (the one just applied,
|
||||
/// which may not be Sealed yet). Empty array on any failure — <see cref="HandleRebuild"/> treats that as
|
||||
/// "no answer" and abandons the rebuild, leaving the served address space untouched (issue #485).</summary>
|
||||
|
||||
Reference in New Issue
Block a user