fix(archreview): security authz+hub cluster (SEC-07/05/08/11) + validation hardening

SEC-07: add QueryActiveAlarmsRequest -> events:read scope arm; fix two tests that
  constructed StreamAlarmsRequest instead of QueryActiveAlarmsRequest.
SEC-05: shorten hub-token lifetime 30m -> 5m; document that the ?access_token= query
  carriage must never be request-logged.
SEC-08: gateway-side CachingApiKeyVerifier (short TTL, keyed on a hash of the presented
  secret) skips the per-call store read+last_used write; CoalescingMarkApiKeyStore bounds
  last_used writes to <=1/key/min; identity constraints are cached. Invalidation is wired
  at the gateway admin sites (revoke/rotate/delete); short TTL backstops out-of-process CLI.
SEC-11: fixed-window rate limit on POST /auth/login + a per-peer (key-id) failure limiter
  checked before VerifyAsync; new MxGateway:Security options bound + validated.

Also fixes regressions from the SEC-01/04/06 commit (c185f62) that a narrow test filter
missed (all now covered by a full-suite checkpoint):
- Rooting check is cross-platform: accepts Windows C:\/UNC forms on Unix so the shipped
  appsettings path validates on the macOS dev box, still rejecting bare filenames.
- AddGatewayConfiguration TryAdds a non-production IHostEnvironment fallback so the validator
  resolves in minimal test/tooling containers; the real host + apikey CLI register the actual
  environment first (TryAdd no-op there).
- Test assembly defaults ASPNETCORE_ENVIRONMENT=Development (ModuleInitializer) so full-host
  tests exercise wiring instead of tripping the SEC-04/06 production guards.
- GatewayOptionsTests asserts the SEC-01 CommonApplicationData-derived default (platform-correct).

archreview: SEC-07/05/08/11 (P1). Verified: NonWindows build clean; full gateway suite
747 passed / 42 failed, where all 42 are the pre-existing macOS named-pipe-harness failures
(Unix-socket path limit) and 0 are validation/regression failures.
This commit is contained in:
Joseph Doherty
2026-07-09 07:31:35 -04:00
parent 970613eebd
commit 17f16ea181
29 changed files with 1521 additions and 18 deletions
@@ -0,0 +1,159 @@
using System.Collections.Concurrent;
using System.Security.Cryptography;
using System.Text;
using Microsoft.Extensions.Caching.Memory;
using ZB.MOM.WW.Auth.Abstractions.ApiKeys;
using ZB.MOM.WW.MxGateway.Server.Configuration;
namespace ZB.MOM.WW.MxGateway.Server.Security.Authentication;
/// <summary>
/// Lets gateway-side admin call sites drop a cached API-key verification when they revoke, rotate
/// or delete a key, so a mutation applied through the running gateway process takes effect
/// immediately rather than after the cache TTL elapses.
/// </summary>
public interface IApiKeyCacheInvalidator
{
/// <summary>Removes every cached verification for the given key id.</summary>
/// <param name="keyId">The key id whose cached verifications should be dropped.</param>
void Invalidate(string keyId);
}
/// <summary>
/// An <see cref="IApiKeyVerifier"/> decorator that caches successful verifications for a short,
/// configurable TTL (<see cref="SecurityOptions.ApiKeyVerificationCacheSeconds"/>), keyed on a
/// SHA-256 hash of the presented token. A cache hit returns the cached result without calling the
/// inner (library) verifier, so it avoids both the per-call SQLite read and the <c>last_used</c>
/// write the library verifier couples into <see cref="IApiKeyVerifier.VerifyAsync"/>.
/// </summary>
/// <remarks>
/// <para>
/// Only successful verifications are cached. Failures and unparseable headers always fall through
/// to the inner verifier — caching a failure risks pinning a transiently-wrong negative, and the
/// SEC-11 per-peer failure counter (not this cache) is what bounds brute-force cost.
/// </para>
/// <para>
/// The cache key is the hex SHA-256 of the presented token (which embeds both the key id and the
/// secret). Hashing means the plaintext secret is never stored in memory. The hash is a cache index
/// only; the authentic constant-time secret comparison remains inside the inner verifier, reached
/// on every cache miss.
/// </para>
/// <para>
/// Correctness on mutation is provided by two mechanisms: gateway-initiated revoke/rotate/delete
/// call <see cref="Invalidate"/> directly (see <c>DashboardApiKeyManagementService</c>), and the
/// short TTL is the backstop for out-of-band mutations (a direct DB edit, or a revoke issued by the
/// separate <c>apikey</c> CLI process, whose in-memory cache is not this process's cache).
/// </para>
/// </remarks>
public sealed class CachingApiKeyVerifier : IApiKeyVerifier, IApiKeyCacheInvalidator
{
private const string CacheKeyPrefix = "mxgw:apikeyverif:";
private readonly IApiKeyVerifier _inner;
private readonly IMemoryCache _cache;
private readonly TimeSpan _ttl;
// keyId -> set of cache keys currently held for that id, so a revoke/rotate can evict every
// secret variant (e.g. an old secret still within TTL after a rotate).
private readonly ConcurrentDictionary<string, ConcurrentDictionary<string, byte>> _keyIdIndex =
new(StringComparer.Ordinal);
/// <summary>Initializes a new instance of the <see cref="CachingApiKeyVerifier"/> class.</summary>
/// <param name="inner">The wrapped verifier (the library verifier) reached on a cache miss.</param>
/// <param name="cache">The shared memory cache.</param>
/// <param name="security">Security options carrying the verification-cache TTL.</param>
public CachingApiKeyVerifier(IApiKeyVerifier inner, IMemoryCache cache, SecurityOptions security)
: this(
inner,
cache,
TimeSpan.FromSeconds((security ?? throw new ArgumentNullException(nameof(security)))
.ApiKeyVerificationCacheSeconds))
{
}
// Test/explicit-TTL seam.
internal CachingApiKeyVerifier(IApiKeyVerifier inner, IMemoryCache cache, TimeSpan ttl)
{
ArgumentNullException.ThrowIfNull(inner);
ArgumentNullException.ThrowIfNull(cache);
_inner = inner;
_cache = cache;
_ttl = ttl;
}
/// <inheritdoc />
public async Task<ApiKeyVerification> VerifyAsync(string authorizationHeader, CancellationToken ct)
{
if (_ttl <= TimeSpan.Zero || !TryComputeCacheKey(authorizationHeader, out string cacheKey))
{
return await _inner.VerifyAsync(authorizationHeader, ct).ConfigureAwait(false);
}
if (_cache.TryGetValue(cacheKey, out ApiKeyVerification? cached) && cached is not null)
{
return cached;
}
ApiKeyVerification result = await _inner.VerifyAsync(authorizationHeader, ct).ConfigureAwait(false);
if (result.Succeeded && result.Identity is not null)
{
_cache.Set(cacheKey, result, new MemoryCacheEntryOptions
{
AbsoluteExpirationRelativeToNow = _ttl,
});
IndexCacheKey(result.Identity.KeyId, cacheKey);
}
return result;
}
/// <inheritdoc />
public void Invalidate(string keyId)
{
if (string.IsNullOrEmpty(keyId))
{
return;
}
if (_keyIdIndex.TryRemove(keyId, out ConcurrentDictionary<string, byte>? cacheKeys))
{
foreach (string cacheKey in cacheKeys.Keys)
{
_cache.Remove(cacheKey);
}
}
}
private void IndexCacheKey(string keyId, string cacheKey)
{
ConcurrentDictionary<string, byte> set = _keyIdIndex.GetOrAdd(
keyId,
static _ => new ConcurrentDictionary<string, byte>(StringComparer.Ordinal));
set.TryAdd(cacheKey, 0);
}
private static bool TryComputeCacheKey(string? authorizationHeader, out string cacheKey)
{
cacheKey = string.Empty;
if (string.IsNullOrEmpty(authorizationHeader))
{
return false;
}
ReadOnlySpan<char> header = authorizationHeader.AsSpan().Trim();
const string bearer = "Bearer ";
ReadOnlySpan<char> token = header.StartsWith(bearer, StringComparison.OrdinalIgnoreCase)
? header[bearer.Length..].Trim()
: header;
if (token.IsEmpty)
{
return false;
}
byte[] hash = SHA256.HashData(Encoding.UTF8.GetBytes(token.ToString()));
cacheKey = CacheKeyPrefix + Convert.ToHexString(hash);
return true;
}
}