feat(localdb): fail-closed bearer interceptor for the sync endpoint

2026-07-20 10:28:39 -04:00
parent 3b65c24bfb
commit 3d29be834e
2 changed files with 334 additions and 0 deletions
@@ -0,0 +1,162 @@
+using System.Security.Cryptography;
+using System.Text;
+using Grpc.Core;
+using Grpc.Core.Interceptors;
+using Microsoft.Extensions.Logging;
+using Microsoft.Extensions.Options;
+using ZB.MOM.WW.LocalDb.Replication;
+
+namespace ZB.MOM.WW.OtOpcUa.Host.Configuration;
+
+/// <summary>
+///     Gates the LocalDb passive sync endpoint. The replication library deliberately leaves inbound
+///     authentication to the host — its <c>LocalDbSyncService</c> verifies nothing — so without this
+///     interceptor anything that can reach a driver node's sync port could stream arbitrary rows
+///     into that node's deployment-artifact cache.
+/// </summary>
+/// <remarks>
+///     <para>
+///         <b>Why that matters here specifically.</b> The cached artifact is what a driver node
+///         boots from when central SQL is unreachable. An attacker able to write it could choose
+///         the configuration a node comes up on during exactly the outage nobody is watching.
+///     </para>
+///     <para>
+///         <b>Scoped by method path.</b> Only calls under <c>/localdb_sync.v1.LocalDbSync/</c> are
+///         gated; every other method on the shared gRPC pipeline passes through untouched.
+///     </para>
+///     <para>
+///         <b>Fail-closed.</b> With no <c>LocalDb:Replication:ApiKey</c> configured, NO sync stream
+///         is accepted, authenticated or not. That is the deliberate choice: the alternative —
+///         treating "no key" as "no auth required" — would silently expose the endpoint on exactly
+///         the default configuration every node ships with. An operator enabling replication must
+///         set the same key on both nodes of the pair, which is already required for the initiator
+///         to dial out (<c>SyncBackgroundService</c> sends <c>Authorization: Bearer &lt;key&gt;</c>).
+///         A key typo therefore stops convergence outright rather than degrading to unauthenticated.
+///     </para>
+///     <para>
+///         Comparison is <see cref="CryptographicOperations.FixedTimeEquals"/> over UTF-8 bytes, so
+///         a wrong key cannot be recovered byte-by-byte from response timing. Length differences are
+///         unavoidably observable and are not sensitive.
+///     </para>
+/// </remarks>
+public sealed class LocalDbSyncAuthInterceptor : Interceptor
+{
+    private const string ServicePrefix = "/localdb_sync.v1.LocalDbSync/";
+    private const string AuthorizationHeader = "authorization";
+    private const string BearerPrefix = "Bearer ";
+
+    private readonly IOptions<ReplicationOptions> _options;
+    private readonly ILogger<LocalDbSyncAuthInterceptor> _logger;
+
+    /// <summary>Creates the interceptor.</summary>
+    /// <param name="options">Replication options; <c>ApiKey</c> is the expected bearer token.</param>
+    /// <param name="logger">Logger for denial diagnostics.</param>
+    public LocalDbSyncAuthInterceptor(
+        IOptions<ReplicationOptions> options,
+        ILogger<LocalDbSyncAuthInterceptor> logger)
+    {
+        ArgumentNullException.ThrowIfNull(options);
+        ArgumentNullException.ThrowIfNull(logger);
+
+        _options = options;
+        _logger = logger;
+    }
+
+    /// <inheritdoc />
+    public override Task<TResponse> UnaryServerHandler<TRequest, TResponse>(
+        TRequest request,
+        ServerCallContext context,
+        UnaryServerMethod<TRequest, TResponse> continuation)
+    {
+        Authorize(context);
+        return continuation(request, context);
+    }
+
+    /// <inheritdoc />
+    public override Task DuplexStreamingServerHandler<TRequest, TResponse>(
+        IAsyncStreamReader<TRequest> requestStream,
+        IServerStreamWriter<TResponse> responseStream,
+        ServerCallContext context,
+        DuplexStreamingServerMethod<TRequest, TResponse> continuation)
+    {
+        Authorize(context);
+        return continuation(requestStream, responseStream, context);
+    }
+
+    /// <inheritdoc />
+    public override Task<TResponse> ClientStreamingServerHandler<TRequest, TResponse>(
+        IAsyncStreamReader<TRequest> requestStream,
+        ServerCallContext context,
+        ClientStreamingServerMethod<TRequest, TResponse> continuation)
+    {
+        Authorize(context);
+        return continuation(requestStream, context);
+    }
+
+    /// <inheritdoc />
+    public override Task ServerStreamingServerHandler<TRequest, TResponse>(
+        TRequest request,
+        IServerStreamWriter<TResponse> responseStream,
+        ServerCallContext context,
+        ServerStreamingServerMethod<TRequest, TResponse> continuation)
+    {
+        Authorize(context);
+        return continuation(request, responseStream, context);
+    }
+
+    /// <summary>
+    ///     Throws <see cref="RpcException"/> with <see cref="StatusCode.PermissionDenied"/> if this
+    ///     is a sync call that does not carry the configured bearer token. Non-sync calls return
+    ///     immediately.
+    /// </summary>
+    private void Authorize(ServerCallContext context)
+    {
+        if (!context.Method.StartsWith(ServicePrefix, StringComparison.Ordinal))
+            return;
+
+        var expected = _options.Value.ApiKey;
+        if (string.IsNullOrEmpty(expected))
+        {
+            _logger.LogWarning(
+                "Rejected a LocalDb sync call to {Method}: no LocalDb:Replication:ApiKey is configured, " +
+                "so the passive sync endpoint is closed. Configure the same key on both nodes of the pair.",
+                context.Method);
+            throw new RpcException(new Status(
+                StatusCode.PermissionDenied,
+                "LocalDb sync is not accepting connections: no API key is configured on this node."));
+        }
+
+        var presented = ExtractBearerToken(context.RequestHeaders);
+        if (presented is null || !FixedTimeEquals(presented, expected))
+        {
+            _logger.LogWarning(
+                "Rejected a LocalDb sync call to {Method}: {Reason}.",
+                context.Method,
+                presented is null ? "no bearer token presented" : "bearer token did not match");
+            throw new RpcException(new Status(
+                StatusCode.PermissionDenied,
+                "LocalDb sync authentication failed."));
+        }
+    }
+
+    private static string? ExtractBearerToken(Metadata headers)
+    {
+        // gRPC lowercases header keys on the wire; compare case-insensitively anyway so a
+        // hand-built Metadata in a test behaves the same as a real request.
+        foreach (var entry in headers)
+        {
+            if (!string.Equals(entry.Key, AuthorizationHeader, StringComparison.OrdinalIgnoreCase))
+                continue;
+
+            var value = entry.Value;
+            if (value is not null && value.StartsWith(BearerPrefix, StringComparison.OrdinalIgnoreCase))
+                return value[BearerPrefix.Length..];
+        }
+
+        return null;
+    }
+
+    private static bool FixedTimeEquals(string presented, string expected)
+        => CryptographicOperations.FixedTimeEquals(
+            Encoding.UTF8.GetBytes(presented), Encoding.UTF8.GetBytes(expected));
+}