Files
selfpost/internal/store/sendercheck.go
T
mixandClaude Opus 5.5 60c7b85f84
test / test (push) Canceled after 0s
findings of the reviews of audit stage 1
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>
2026-10-14 15:21:52 +03:00

170 lines
5.5 KiB
Go

package store
import (
"fmt"
"time"
)
// Why a send-log row with status "rejected" was refused (send_log.reason).
// A row written before the reason was recorded has "".
const (
ReasonLimit = "limit" // a level-2 rate limit
ReasonClient = "client" // the application's list of client addresses
ReasonFrom = "from" // the From: line is not the application's
)
// Who decided a "bounced" row the log did not (send_log.reason).
const (
// ReasonReconcile: the reconcile sweep closed the row - its message left
// Postfix's queue with no delivery line ever read for it.
ReasonReconcile = "reconcile"
// ReasonReconcileContradicted: the sweep closed it and a delivery line
// read afterwards gave the status the row now has.
ReasonReconcileContradicted = "reconcile-contradicted"
)
// Settings keys of the sender check's statistics.
const (
// settingSenderCheckSince is the first UTC day the statistics cover.
settingSenderCheckSince = "sender_check_since"
// settingSenderCheckDeferredAt is when a message was last deferred because
// the check did not answer (RFC3339 UTC).
settingSenderCheckDeferredAt = "sender_check_deferred_at"
)
// senderCheckKeepDays is how long a day of the statistics is kept.
const senderCheckKeepDays = 366
const dayLayout = "2006-01-02"
// SenderCheckTotals is what the strict sender check has cost over a period.
type SenderCheckTotals struct {
Down time.Duration // the panel not answering while Postfix was running
Deferred int64 // messages Postfix deferred because of it
}
// SenderCheckStats is the card of Server > Health.
type SenderCheckStats struct {
Today, Month, Year SenderCheckTotals
// Since is the first day counted; zero before anything was.
Since time.Time
// DeferredAt is when a message was last deferred; zero if never.
DeferredAt time.Time
}
// StartSenderCheckStats records the first day the statistics cover, once.
func (s *Store) StartSenderCheckStats(now time.Time) error {
v, err := s.GetSetting(settingSenderCheckSince)
if err != nil || v != "" {
return err
}
return s.SetSetting(settingSenderCheckSince, now.UTC().Format(dayLayout))
}
// AddSenderCheckDown adds to the day of at the time the panel did not answer
// while Postfix was running.
func (s *Store) AddSenderCheckDown(at time.Time, d time.Duration) error {
secs := int64(d / time.Second)
if secs <= 0 {
return nil
}
_, err := s.db.Exec(
`INSERT INTO sender_check_days (day, down_seconds) VALUES (?, ?)
ON CONFLICT (day) DO UPDATE SET down_seconds = down_seconds + excluded.down_seconds`,
at.UTC().Format(dayLayout), secs,
)
if err != nil {
return fmt.Errorf("sender check downtime: %w", err)
}
return nil
}
// AddSenderCheckDeferred counts, on the day of at, n messages deferred because
// the check did not answer, and remembers at as the last such moment.
func (s *Store) AddSenderCheckDeferred(at time.Time, n int64) error {
if n <= 0 {
return nil
}
_, err := s.db.Exec(
`INSERT INTO sender_check_days (day, deferred) VALUES (?, ?)
ON CONFLICT (day) DO UPDATE SET deferred = deferred + excluded.deferred`,
at.UTC().Format(dayLayout), n,
)
if err != nil {
return fmt.Errorf("sender check deferred: %w", err)
}
// Lines are read in order, but a re-read log must not move the mark back.
last, err := s.GetSetting(settingSenderCheckDeferredAt)
if err != nil {
return err
}
// To the fraction of a second the log gives, and of a fixed width so that
// the strings compare as the times do.
stamp := at.UTC().Format("2006-01-02T15:04:05.000000Z")
if stamp > last {
return s.SetSetting(settingSenderCheckDeferredAt, stamp)
}
return nil
}
// SenderCheckDeferredAt is when a message was last counted as deferred; zero
// if none was.
func (s *Store) SenderCheckDeferredAt() (time.Time, error) {
v, err := s.GetSetting(settingSenderCheckDeferredAt)
if err != nil || v == "" {
return time.Time{}, err
}
at, _ := time.Parse(time.RFC3339Nano, v)
return at, nil
}
// SenderCheckStats sums the days up to now: today, the last 30 days and the
// last 12 months, each including today.
func (s *Store) SenderCheckStats(now time.Time) (SenderCheckStats, error) {
now = now.UTC()
var out SenderCheckStats
sum := func(days int) (SenderCheckTotals, error) {
var secs, deferred int64
err := s.db.QueryRow(
`SELECT COALESCE(SUM(down_seconds), 0), COALESCE(SUM(deferred), 0)
FROM sender_check_days WHERE day > ? AND day <= ?`,
now.AddDate(0, 0, -days).Format(dayLayout), now.Format(dayLayout),
).Scan(&secs, &deferred)
if err != nil {
return SenderCheckTotals{}, fmt.Errorf("sender check stats: %w", err)
}
return SenderCheckTotals{Down: time.Duration(secs) * time.Second, Deferred: deferred}, nil
}
var err error
if out.Today, err = sum(1); err != nil {
return out, err
}
if out.Month, err = sum(30); err != nil {
return out, err
}
if out.Year, err = sum(365); err != nil {
return out, err
}
since, err := s.GetSetting(settingSenderCheckSince)
if err != nil {
return out, err
}
out.Since, _ = time.Parse(dayLayout, since)
deferredAt, err := s.GetSetting(settingSenderCheckDeferredAt)
if err != nil {
return out, err
}
out.DeferredAt, _ = time.Parse(time.RFC3339, deferredAt)
return out, nil
}
// PruneSenderCheckDays deletes the days older than a year.
func (s *Store) PruneSenderCheckDays(now time.Time) error {
_, err := s.db.Exec(`DELETE FROM sender_check_days WHERE day < ?`,
now.UTC().AddDate(0, 0, -senderCheckKeepDays).Format(dayLayout))
if err != nil {
return fmt.Errorf("prune sender check days: %w", err)
}
return nil
}