Files
certctl/internal/service/revocation_svc.go
T
shankar0123 b0efdbe2f8 repo,service: introduce WithinTx and atomic audit rows for issue/renew/revoke
Closes the #3 acquisition-readiness blocker from the 2026-05-01 issuer
coverage audit (Part 1.5 finding #1: audit row not transactional with
issuance). AuditRepository.Create previously ran on the package-level
*sql.DB while the certificate insert / version insert / revocation
insert ran on independent connections — a failed audit INSERT after
a successful operation INSERT was silently lost. SOX §404 over IT
general controls, PCI-DSS §10 audit logging, HIPAA §164.312(b) audit
controls, and CA/B Forum Baseline Requirements §5.4.1 audit log
records all presume audit-with-operation atomicity.

Design — Option A (Querier abstraction). The chosen pattern: a shared
repository.Querier interface (subset of *sql.DB and *sql.Tx) plus a
postgres.WithinTx helper that begins a tx, runs fn, commits on nil
error, rolls back on error or panic, and returns the wrapped result.
Repository methods that participate in a service-layer transaction
expose a *WithTx variant taking repository.Querier; the bare methods
remain for stand-alone use. A repository.Transactor abstracts the
"begin tx, run fn, commit/rollback" lifecycle so service-layer code
runs multi-write operations atomically without holding *sql.DB
directly. Option B (UnitOfWork) was considered but adds boilerplate
without behavioral benefit for the current scope. Option C
(context-carried tx) was explicitly rejected — it hides the
transactional boundary from the type system, reproducing the class
of bug we're fixing.

This commit:
- Adds internal/repository/querier.go with the Querier interface
  (compile-time guards that *sql.DB and *sql.Tx satisfy it) and the
  Transactor interface for service-layer use.
- Adds internal/repository/postgres/tx.go with the WithinTx helper
  (begin/fn/commit/rollback with panic recovery) and a transactor
  type that satisfies repository.Transactor.
- Adds CreateWithTx variants on AuditRepository, CertificateRepository
  (Create + Update + CreateVersion), and RevocationRepository.
  Existing bare methods now delegate to the *WithTx variant using
  the package-level *sql.DB so existing call sites are
  behavior-preserving.
- Updates repository/interfaces.go: AuditRepository, CertificateRepository,
  and RevocationRepository declare the new *WithTx methods. Adds an
  atomicity contract doc-comment on AuditRepository pointing at
  WithinTx + the audit blocker.
- Adds AuditService.RecordEventWithTx, mirroring RecordEvent but
  routing through CreateWithTx so the audit row is part of the
  caller's transaction. Same redaction + marshalling contract.
- Refactors three audit-emitting service paths to use Transactor.WithinTx
  when SetTransactor was wired, with a legacy fallback for backward
  compat:
    * CertificateService.Create — cert insert + audit row in one tx.
    * RevocationSvc.RevokeCertificateWithActor — cert status update +
      revocation row + audit row in one tx. The OCSP cache invalidate
      remains best-effort (out of scope per the prompt).
    * RenewalService CompleteServerRenewal — cert version insert +
      cert update + audit row in one tx. Job status update stays
      outside the audit-atomicity scope (job state lives outside
      the operator-facing audit trail).
- Adds SetTransactor on CertificateService, RevocationSvc, and
  RenewalService. cmd/server/main.go wires a single Transactor
  instance shared across all three so all audit-emitting paths run
  their writes in transactions backed by the same *sql.DB handle.
- Updates 5 mock implementations to satisfy the new interface methods:
  mockCertRepo (testutil_test.go), mockCertRepoWithGetError
  (shortlived_test.go), fakeRevocationRepo (crl_cache_test.go),
  intuneE2EAuditRepo (scep_intune_e2e_test.go), and the integration-
  test mocks (lifecycle_test.go: mockCertificateRepository,
  mockAuditRepository, mockRevocationRepository). All *WithTx mocks
  ignore the Querier and delegate to the bare method (mocks have no
  DB; in-memory state is shared regardless of "tx").
- Adds a service-layer test mockTransactor with BeginTxErr and
  CommitErr knobs so the atomic-audit tests can assert error
  propagation through the transactional boundary.
- Adds internal/repository/postgres/tx_test.go: unit-level test that
  WithinTx surfaces "begin tx" wrap when BeginTx fails, and that
  Transactor.WithinTx delegates correctly. Real-Postgres rollback
  semantics are covered by the testcontainers tests in the postgres
  package — sandbox disk pressure prevented adding a sqlmock dep
  for the in-fn / commit-failure unit test, so those scenarios are
  exercised through atomic_audit_test.go using the mockTransactor's
  CommitErr / BeginTxErr fields.
- Adds internal/service/atomic_audit_test.go:
    * TestCertificateService_Create_AtomicWithTx — asserts audit
      insert failure inside the tx surfaces as the operation's error
      (closes the blocker contract).
    * TestCertificateService_Create_LegacyPathLogs — pins the
      backward-compat behavior when SetTransactor isn't wired:
      audit failure is logged-not-failed, matching pre-fix.
    * TestCertificateService_Create_TransactorBeginFailure — BeginTx
      error path: operation fails, no cert insert, no audit insert.
    * TestCertificateService_Create_TransactorCommitFailure —
      Commit error after successful in-fn writes surfaces as the
      operation's error. Real Postgres can fail Commit on
      serialization conflicts; the service must report this.

Out of scope (separate follow-up commits, same shape):
- Issuer CRUD audit atomicity.
- Target CRUD audit atomicity.
- Agent retire (already transactional via RetireAgentWithCascade;
  verified, not changed).
- Renewal-policy CRUD audit atomicity.
- Owner/team/agent-group CRUD audit atomicity.
- Discovery / health-check audit atomicity.

Verified locally:
- gofmt -l . clean
- go vet ./... clean
- staticcheck ./... clean
- golangci-lint run --timeout 5m ./... → 0 issues
- go test -short -count=1 ./internal/service/ green
- go test -short -count=1 ./internal/api/handler/ green
- go test -short -count=1 ./internal/integration/ green
- go test -short -count=1 ./internal/repository/postgres/ green
- go build ./... success

Audit reference: cowork/issuer-coverage-audit-2026-05-01/RESULTS.md
Top-10 fix #3 (Part 3, narrative section).
2026-05-02 00:29:09 +00:00

257 lines
9.3 KiB
Go

package service
import (
"context"
"fmt"
"log/slog"
"time"
"github.com/shankar0123/certctl/internal/domain"
"github.com/shankar0123/certctl/internal/repository"
)
// RevocationSvc provides revocation-related business logic.
// It handles certificate revocation, revocation notifications, and issuer coordination.
type RevocationSvc struct {
certRepo repository.CertificateRepository
revocationRepo repository.RevocationRepository
auditService *AuditService
notificationSvc *NotificationService
issuerRegistry *IssuerRegistry
// tx — when set, wraps the cert status update + revocation row
// insert + audit row in a single transaction. Closes the #3 audit-
// readiness blocker for the revocation path. Optional via
// SetTransactor; nil means legacy non-transactional behavior
// (cert.Update committed independently from revocation row +
// audit, with revocation insert + audit logged-but-not-failed).
tx repository.Transactor
// ocspCacheInvalidator — production hardening II Phase 2 load-
// bearing security wire. After a successful revocation, the
// service MUST invalidate the OCSP response cache for this
// (issuer, serial) so the next OCSP fetch returns the revoked
// status (not the stale "good" cached blob).
ocspCacheInvalidator OCSPCacheInvalidator
}
// SetTransactor wires a Transactor for atomic revocation (cert update
// + revocation row + audit row in a single transaction). Closes the
// #3 audit-readiness blocker for the revocation path. Optional —
// nil reverts to the legacy non-transactional behavior.
func (s *RevocationSvc) SetTransactor(tx repository.Transactor) {
s.tx = tx
}
// OCSPCacheInvalidator is the minimum surface RevocationSvc needs
// from the OCSP cache. The cache service implements this interface;
// the indirection keeps RevocationSvc from depending on the cache
// type and lets tests inject a fake invalidator.
type OCSPCacheInvalidator interface {
InvalidateOnRevoke(ctx context.Context, issuerID, serialHex string) error
}
// SetOCSPCacheInvalidator wires the OCSP cache for invalidate-on-
// revoke. Production hardening II Phase 2.
func (s *RevocationSvc) SetOCSPCacheInvalidator(c OCSPCacheInvalidator) {
s.ocspCacheInvalidator = c
}
// NewRevocationSvc creates a new revocation service.
func NewRevocationSvc(
certRepo repository.CertificateRepository,
revocationRepo repository.RevocationRepository,
auditService *AuditService,
) *RevocationSvc {
return &RevocationSvc{
certRepo: certRepo,
revocationRepo: revocationRepo,
auditService: auditService,
}
}
// SetNotificationService sets the notification service for revocation alerts.
func (s *RevocationSvc) SetNotificationService(svc *NotificationService) {
s.notificationSvc = svc
}
// SetIssuerRegistry sets the issuer registry for issuer-level revocation.
func (s *RevocationSvc) SetIssuerRegistry(registry *IssuerRegistry) {
s.issuerRegistry = registry
}
// RevokeCertificateWithActor performs revocation with actor tracking.
// Steps:
// 1. Validate the certificate exists and is revocable
// 2. Get the latest certificate version (for serial number)
// 3. Update certificate status to Revoked
// 4. Record revocation in certificate_revocations table
// 5. Notify the issuer connector (best-effort)
// 6. Record audit event
// 7. Send revocation notification
func (s *RevocationSvc) RevokeCertificateWithActor(ctx context.Context, certID string, reason string, actor string) error {
// 1. Validate certificate exists and is revocable
cert, err := s.certRepo.Get(ctx, certID)
if err != nil {
return fmt.Errorf("failed to fetch certificate: %w", err)
}
if cert.Status == domain.CertificateStatusRevoked {
return fmt.Errorf("certificate is already revoked")
}
if cert.Status == domain.CertificateStatusArchived {
return fmt.Errorf("cannot revoke archived certificate")
}
// Validate reason code
if reason == "" {
reason = string(domain.RevocationReasonUnspecified)
}
if !domain.IsValidRevocationReason(reason) {
return fmt.Errorf("invalid revocation reason: %s", reason)
}
// 2. Get latest certificate version for serial number
version, err := s.certRepo.GetLatestVersion(ctx, certID)
if err != nil {
return fmt.Errorf("failed to get certificate version: %w", err)
}
// 3. + 4. + audit: cert status update + revocation row + audit row.
// Atomic path (when SetTransactor was wired) keeps these three
// writes consistent: a failure in any one rolls back the others.
// Closes the #3 audit-readiness blocker for the revocation path.
now := time.Now()
cert.Status = domain.CertificateStatusRevoked
cert.RevokedAt = &now
cert.RevocationReason = reason
cert.UpdatedAt = now
auditDetails := map[string]interface{}{
"common_name": cert.CommonName,
"serial": version.SerialNumber,
"reason": reason,
}
if s.tx != nil {
// Atomic three-write path.
if err := s.tx.WithinTx(ctx, func(q repository.Querier) error {
if err := s.certRepo.UpdateWithTx(ctx, q, cert); err != nil {
return fmt.Errorf("failed to update certificate status: %w", err)
}
if s.revocationRepo != nil {
revocation := &domain.CertificateRevocation{
ID: generateID("rev"),
CertificateID: certID,
SerialNumber: version.SerialNumber,
Reason: reason,
RevokedBy: actor,
RevokedAt: now,
IssuerID: cert.IssuerID,
CreatedAt: now,
}
if err := s.revocationRepo.CreateWithTx(ctx, q, revocation); err != nil {
return fmt.Errorf("failed to record revocation: %w", err)
}
}
if err := s.auditService.RecordEventWithTx(ctx, q, actor, domain.ActorTypeUser,
"certificate_revoked", "certificate", certID, auditDetails); err != nil {
return fmt.Errorf("failed to record audit event: %w", err)
}
return nil
}); err != nil {
return err
}
} else {
// Legacy non-transactional path. Pre-fix behavior preserved
// for backward compat with callers that haven't wired
// SetTransactor.
if err := s.certRepo.Update(ctx, cert); err != nil {
return fmt.Errorf("failed to update certificate status: %w", err)
}
if s.revocationRepo != nil {
revocation := &domain.CertificateRevocation{
ID: generateID("rev"),
CertificateID: certID,
SerialNumber: version.SerialNumber,
Reason: reason,
RevokedBy: actor,
RevokedAt: now,
IssuerID: cert.IssuerID,
CreatedAt: now,
}
if err := s.revocationRepo.Create(ctx, revocation); err != nil {
slog.Error("failed to record revocation for CRL", "error", err, "certificate_id", certID)
// Don't fail the overall revocation — the cert status is already updated
}
}
}
// 5. Notify the issuer connector (best-effort)
if s.issuerRegistry != nil {
if issuerConn, ok := s.issuerRegistry.Get(cert.IssuerID); ok {
if err := issuerConn.RevokeCertificate(ctx, version.SerialNumber, reason); err != nil {
slog.Error("failed to notify issuer of revocation",
"error", err,
"issuer_id", cert.IssuerID,
"serial", version.SerialNumber)
// Best-effort — don't fail the overall revocation
} else if s.revocationRepo != nil {
// Mark issuer as notified
revocations, _ := s.revocationRepo.ListByCertificate(ctx, certID)
for _, rev := range revocations {
if rev.SerialNumber == version.SerialNumber {
_ = s.revocationRepo.MarkIssuerNotified(ctx, rev.ID)
}
}
}
}
}
// 5.5. Invalidate the OCSP response cache for this (issuer, serial)
// so the next OCSP fetch returns the revoked status (not the stale
// "good" cached blob). Production hardening II Phase 2 LOAD-BEARING
// security wire — without this, a revoked cert keeps returning
// "good" until the next ocspCacheRefreshLoop tick.
//
// Failure is logged and swallowed: the revocation row is committed,
// the CRL will reflect the revocation on the next regen, and the
// admin can manually nuke the cache row if necessary. Failing the
// caller's revoke on cache-failure would leave the operator's
// intent unachieved (cert appears not-revoked); failing-soft +
// logging is the right tradeoff.
if s.ocspCacheInvalidator != nil {
if err := s.ocspCacheInvalidator.InvalidateOnRevoke(ctx, cert.IssuerID, version.SerialNumber); err != nil {
slog.Warn("failed to invalidate OCSP response cache after revocation (revocation still committed)",
"error", err,
"issuer_id", cert.IssuerID,
"serial", version.SerialNumber,
"certificate_id", certID)
}
}
// 6. Record audit event (legacy non-transactional path only — the
// atomic path already recorded the audit inside the tx above).
if s.tx == nil {
if err := s.auditService.RecordEvent(ctx, actor, domain.ActorTypeUser,
"certificate_revoked", "certificate", certID, auditDetails); err != nil {
slog.Error("failed to record audit event", "error", err)
}
}
// 7. Send revocation notification
if s.notificationSvc != nil {
if err := s.notificationSvc.SendRevocationNotification(ctx, cert, reason); err != nil {
slog.Error("failed to send revocation notification", "error", err, "certificate_id", certID)
}
}
return nil
}
// GetRevokedCertificates returns all revoked certificate records (for CRL generation).
func (s *RevocationSvc) GetRevokedCertificates(ctx context.Context) ([]*domain.CertificateRevocation, error) {
if s.revocationRepo == nil {
return nil, fmt.Errorf("revocation repository not configured")
}
return s.revocationRepo.ListAll(ctx)
}