findings of the reviews of audit stage 1
test / test (push) Canceled after 0s

Technical review (Opus) and security review (Fable) of 9efc9c7..a59e3d4;
reports in the session's scratchpad. Fixed:

- B1 (verified bug): store.UpdateStatus read before writing in its
  transaction; a commit by another connection in between (the dmarc-ingest
  process opens the same file) failed it at once with "database is locked"
  and the delivery line was lost. The first statement is now a write.
- R3: a delivery line updated every row of its queue id and recipient; it
  now updates only the newest (Postfix reuses short ids). The sweep closes
  by row id (QueuedDelivery.ID, CloseUnreported(id)).
- R4: a contradicted sweep keeps a mark, reason "reconcile-contradicted",
  instead of losing which row it was.
- R1: contradicted cannot see a lost line (never read late). New counter
  reconcile_missed: at close, the sweep looks for the row's delivery line
  in mail.log and mail.log.1 (QueueLines). 0007 edited - it has run on no
  database but throwaway stands.
- R2: queued_over_lifetime cannot measure "what removing the sweep would
  leave" while the sweep runs; its text now says rows stuck despite the
  sweep, and the rule uses closed - missed - contradicted.
- cert-reload (R5, R6, R7, security medium/low): both files copied to .new
  and the copies checked as a pair before both are renamed; acts on the copy
  only when postconf says Postfix reads it; a failed reload is retried next
  pass; umask 077; says so when the mounted files cannot be read. The e2e
  case asserts Postfix reads the copy, the copy equals the mount, the key is
  600 root.
- Security low: a recipient with a quoted local part - the journal cut
  "a b"@x at the space, deliveryRe cut "a>b"@x at the ">" - matched no
  delivery line and was closed by the sweep. cleanAddress ends a bracketed
  address at the first ">" outside quotes; deliveryRe takes the recipient
  up to the ">, " before relay= (test fixtures given the relay= every real
  delivery line has).
- Security low: postqueue -p's error carries at most 512 bytes of output.
- Nits: addDeliveryLogDay refuses a column not on its list; the truncation
  test checks its message.
- To stage 2b (page wording, mockup-first): the history step of a bounced
  row says the receiving server refused it, false for a row the sweep
  closed. To the owner when stage 2b is reached: since M13 the "deferred"
  figure counts whole messages too, which "Connections turned away" would
  not name.

Found while verifying: the e2e's main positive path failed once with "553
not owned by user app1" - an smtpd idle from before the panel's reload took
the connection in the reload's second. Measured on the stand (one-off
probe, not committed): sending 0, 10, 40, 110 s after the save (two seconds
at the soonest) always met an smtpd started after the reload. The e2e now
waits for the sender map after each application it creates
(waitForSenderMap: AUTH, MAIL, RCPT, RSET - no message, no row), and the
level-1 case uses it instead of its own loop.

Docs: architecture § Queue reconcile, schema-migrations (rows 7 and 8,
chain head 8), CHANGELOG, audit plan (stage 1 note, the measured window,
a new stage 2b line: 62 lines), roadmap 15/62.

Evidence on the test server for this tree: go vet clean, go test ./... 23
packages ok, make e2e exit 0 (renewed certificate, hung panel, level 1 at
49/60).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
mix
2026-10-14 15:21:52 +03:00
co-authored by Claude Opus 5.5
parent f51f5db245
commit 60c7b85f84
26 changed files with 503 additions and 143 deletions
+62 -17
View File
@@ -116,6 +116,16 @@ func TestParseDelivery(t *testing.T) {
line: "host postfix/cleanup[12]: BEEF03: message-id=<x@example.com>",
wantOK: false,
},
{
// A quoted local part may hold ">": the recipient runs to the
// ">, " before relay=.
name: "a recipient with > in a quoted local part",
line: `host postfix/smtp[26]: C0FFEE: to=<"a>b"@example.net>, relay=mx[203.0.113.9]:25, dsn=2.0.0, status=sent (250 OK)`,
wantOK: true,
queueID: "C0FFEE",
recipient: `"a>b"@example.net`,
status: store.StatusSent,
},
{
// The stamp Postfix 3.7's postlogd writes, as on the stand.
name: "syslog stamp",
@@ -178,6 +188,7 @@ type captureStore struct {
// closed sums AddReconcileClosed; stuckCount is what CountQueuedOlderThan
// answers and stuck what SetQueuedOverLifetime was given.
closed int64
missed int64
stuckCount int64
stuck []int64
@@ -241,12 +252,18 @@ func (c *captureStore) UpdateStatus(queueID, recipient, status string) (int64, e
return 1, nil
}
// CloseUnreported records the sweep's close as "queue-id|recipient|reconcile".
func (c *captureStore) CloseUnreported(queueID, recipient string) (int64, error) {
// CloseUnreported records the sweep's close as "queue-id|recipient|reconcile",
// finding the row by its id among queued.
func (c *captureStore) CloseUnreported(id int64) (int64, error) {
c.mu.Lock()
defer c.mu.Unlock()
c.calls = append(c.calls, queueID+"|"+recipient+"|"+store.ReasonReconcile)
return 1, nil
for _, q := range c.queued {
if q.ID == id {
c.calls = append(c.calls, q.QueueID+"|"+q.To+"|"+store.ReasonReconcile)
return 1, nil
}
}
return 0, nil
}
func (c *captureStore) DeleteSendLogBefore(time.Time) (int64, error) { return 0, nil }
@@ -259,6 +276,12 @@ func (c *captureStore) AddReconcileClosed(_ time.Time, n int64) error {
c.closed += n
return nil
}
func (c *captureStore) AddReconcileMissed(_ time.Time, n int64) error {
c.mu.Lock()
defer c.mu.Unlock()
c.missed += n
return nil
}
func (c *captureStore) AddTailerBlind(time.Time, time.Duration) error { return nil }
func (c *captureStore) CountQueuedOlderThan(time.Time) (int64, error) {
c.mu.Lock()
@@ -332,7 +355,7 @@ func TestFollowTailsAndRotates(t *testing.T) {
// Give follow() time to open at EOF (it seeks to end immediately on start,
// so the seed line above is ignored), then append a delivery line.
time.Sleep(50 * time.Millisecond)
appendLine(t, path, "host postfix/smtp[1]: Q1: to=<a@example.net>, dsn=2.0.0, status=sent (ok)")
appendLine(t, path, "host postfix/smtp[1]: Q1: to=<a@example.net>, relay=x, dsn=2.0.0, status=sent (ok)")
waitFor(t, func() bool { return contains(cs.snapshot(), "Q1|a@example.net|sent") })
// Rotate: move the current file aside and create a fresh one (logrotate
@@ -343,7 +366,7 @@ func TestFollowTailsAndRotates(t *testing.T) {
if err := os.WriteFile(path, nil, 0o644); err != nil {
t.Fatalf("recreate: %v", err)
}
appendLine(t, path, "host postfix/smtp[1]: Q2: to=<b@example.net>, dsn=5.1.1, status=bounced (nope)")
appendLine(t, path, "host postfix/smtp[1]: Q2: to=<b@example.net>, relay=x, dsn=5.1.1, status=bounced (nope)")
waitFor(t, func() bool { return contains(cs.snapshot(), "Q2|b@example.net|bounced") })
cancel()
@@ -375,12 +398,12 @@ func TestFollowResumesAfterRestart(t *testing.T) {
cs := &captureStore{}
stop := startRun(t, path, cs)
appendLine(t, path, "host postfix/smtp[1]: Q1: to=<a@example.net>, dsn=2.0.0, status=sent (ok)")
appendLine(t, path, "host postfix/smtp[1]: Q1: to=<a@example.net>, relay=x, dsn=2.0.0, status=sent (ok)")
waitFor(t, func() bool { return contains(cs.snapshot(), "Q1|a@example.net|sent") })
stop() // persists the offset past Q1
// Down: Postfix keeps delivering.
appendLine(t, path, "host postfix/smtp[1]: Q2: to=<b@example.net>, dsn=2.0.0, status=sent (ok)")
appendLine(t, path, "host postfix/smtp[1]: Q2: to=<b@example.net>, relay=x, dsn=2.0.0, status=sent (ok)")
cs.reset()
stop = startRun(t, path, cs)
@@ -394,7 +417,7 @@ func TestFollowResumesAfterRestart(t *testing.T) {
// The stored offset belongs to a file that no longer exists, so the new one
// must be read from the start.
if err := os.WriteFile(path, []byte(strings.Repeat("host postfix/qmgr[1]: fresh log after rotation\n", 20)+
"host postfix/smtp[1]: Q3: to=<c@example.net>, dsn=5.1.1, status=bounced (nope)\n"), 0o644); err != nil {
"host postfix/smtp[1]: Q3: to=<c@example.net>, relay=x, dsn=5.1.1, status=bounced (nope)\n"), 0o644); err != nil {
t.Fatalf("recreate log: %v", err)
}
@@ -490,17 +513,39 @@ func TestReconcileClosesOnlyWhatPostfixNoLongerHolds(t *testing.T) {
stubQueue(t, nil, "STILLQ")
cs := &captureStore{queued: []store.QueuedDelivery{
{QueueID: "STILLQ", To: "inflight@example.net"},
{QueueID: "GONEQ", To: "lost@example.net"},
{ID: 1, QueueID: "STILLQ", To: "inflight@example.net"},
{ID: 2, QueueID: "GONEQ", To: "lost@example.net"},
}}
reconcile(cs, time.Now().UTC())
reconcile(cs, time.Now().UTC(), "")
got := cs.snapshot()
if len(got) != 1 || got[0] != "GONEQ|lost@example.net|"+store.ReasonReconcile {
t.Fatalf("got %v, want only the message Postfix dropped closed by the sweep", got)
}
if cs.closed != 1 {
t.Fatalf("the day counts %d closed row(s), want 1", cs.closed)
if cs.closed != 1 || cs.missed != 0 {
t.Fatalf("the day counts %d closed and %d missed, want 1 and 0", cs.closed, cs.missed)
}
}
// A closed row whose delivery line is in the log after all - here in the file
// rotated last - is counted as missed: the tailer did not read it.
func TestReconcileCountsALineTheTailerMissed(t *testing.T) {
stubQueue(t, nil)
dir := t.TempDir()
path := filepath.Join(dir, "mail.log")
if err := os.WriteFile(path, []byte("Oct 14 11:00:00 mail postfix/qmgr[10]: OTHERQ: removed\n"), 0o644); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(path+".1", []byte("Oct 14 10:59:58 mail postfix/smtp[26]: SEENQ: to=<Seen@example.net>, relay=mx[203.0.113.9]:25, dsn=2.0.0, status=sent (250 OK)\n"), 0o644); err != nil {
t.Fatal(err)
}
cs := &captureStore{queued: []store.QueuedDelivery{
{ID: 1, QueueID: "SEENQ", To: "seen@example.net"},
{ID: 2, QueueID: "GONEQ", To: "lost@example.net"},
}}
reconcile(cs, time.Now().UTC(), path)
if cs.closed != 2 || cs.missed != 1 {
t.Fatalf("closed %d, missed %d; want 2 and 1", cs.closed, cs.missed)
}
}
@@ -560,9 +605,9 @@ func TestReconcileLeavesRowsAloneWhenTheQueueCannotBeRead(t *testing.T) {
stubQueue(t, errors.New("postqueue: Permission denied"))
cs := &captureStore{queued: []store.QueuedDelivery{
{QueueID: "GONEQ", To: "lost@example.net"},
{ID: 1, QueueID: "GONEQ", To: "lost@example.net"},
}}
reconcile(cs, time.Now().UTC())
reconcile(cs, time.Now().UTC(), "")
if got := cs.snapshot(); len(got) != 0 {
t.Fatalf("got %v, want no row touched", got)
@@ -574,7 +619,7 @@ func TestReconcileLeavesRowsAloneWhenTheQueueCannotBeRead(t *testing.T) {
func TestReconcileSkipsTheQueueWhenNoRowIsStuck(t *testing.T) {
calls := stubQueue(t, nil)
reconcile(&captureStore{}, time.Now().UTC())
reconcile(&captureStore{}, time.Now().UTC(), "")
if *calls != 0 {
t.Fatalf("queue listed %d time(s), want none", *calls)