feat(mesh-phase5): fail-closed bearer interceptor for the telemetry stream
Claude-Session: https://claude.ai/code/session_01GASWkNEi68FSCtvr6rLoEW
This commit is contained in:
Joseph Doherty
@@ -0,0 +1,165 @@
|
||||
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.OtOpcUa.Cluster;
|
||||
|
||||
namespace ZB.MOM.WW.OtOpcUa.Host.Configuration;
|
||||
|
||||
/// <summary>
|
||||
/// Gates the driver-node telemetry stream endpoint (per-cluster mesh Phase 5). The
|
||||
/// <c>TelemetryStreamService.Subscribe</c> RPC streams a node's live alerts / script-logs /
|
||||
/// driver-health / driver-resilience-status to whoever dials it; anything able to reach a driver
|
||||
/// node's telemetry port could otherwise pull that live feed out-of-band. This interceptor is the
|
||||
/// ONLY inbound auth on that endpoint.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// <para>
|
||||
/// <b>Scoped by method path.</b> Only calls under
|
||||
/// <c>/telemetry.v1.TelemetryStreamService/</c> are gated; every other method on the shared
|
||||
/// gRPC pipeline (config-serve, LocalDb sync) passes through untouched, so this can share one
|
||||
/// <c>AddGrpc</c> registration with <see cref="ConfigServeAuthInterceptor"/> and
|
||||
/// <see cref="LocalDbSyncAuthInterceptor"/>.
|
||||
/// </para>
|
||||
/// <para>
|
||||
/// <b>Fail-closed.</b> With no <c>Telemetry:ApiKey</c> configured, NO dial is accepted,
|
||||
/// authenticated or not. Treating "no key" as "no auth required" would expose the live
|
||||
/// telemetry feed on exactly the default shape most nodes ship with. The caller dialing in
|
||||
/// must present the same <c>TelemetryDial:ApiKey</c> (the shared node key), so a key typo
|
||||
/// stops telemetry delivery 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>
|
||||
/// <para>
|
||||
/// <b>Exactly one public constructor.</b> <c>Grpc.AspNetCore</c> silently stops invoking an
|
||||
/// interceptor that has more than one public ctor — see
|
||||
/// <c>TelemetryStreamAuthInterceptorTests.HasExactlyOnePublicConstructor</c>.
|
||||
/// </para>
|
||||
/// </remarks>
|
||||
public sealed class TelemetryStreamAuthInterceptor : Interceptor
|
||||
{
|
||||
private const string ServicePrefix = "/telemetry.v1.TelemetryStreamService/";
|
||||
private const string AuthorizationHeader = "authorization";
|
||||
private const string BearerPrefix = "Bearer ";
|
||||
|
||||
private readonly IOptions<TelemetryOptions> _options;
|
||||
private readonly ILogger<TelemetryStreamAuthInterceptor> _logger;
|
||||
|
||||
/// <summary>Creates the interceptor.</summary>
|
||||
/// <param name="options">Telemetry options; <c>ApiKey</c> is the expected bearer token.</param>
|
||||
/// <param name="logger">Logger for denial diagnostics.</param>
|
||||
public TelemetryStreamAuthInterceptor(
|
||||
IOptions<TelemetryOptions> options,
|
||||
ILogger<TelemetryStreamAuthInterceptor> 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 telemetry-stream call that does not carry the configured bearer token. Non-telemetry
|
||||
/// 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 telemetry stream call to {Method}: no Telemetry:ApiKey is configured, so " +
|
||||
"the telemetry endpoint is closed. Configure the shared node key on this node and every " +
|
||||
"dialing caller.",
|
||||
context.Method);
|
||||
throw new RpcException(new Status(
|
||||
StatusCode.PermissionDenied,
|
||||
"Telemetry stream 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 telemetry stream 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,
|
||||
"Telemetry stream 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));
|
||||
}
|
||||
Reference in New Issue
Block a user