inbound journal: one row per recipient, and every row counts to the cap (audit M3)

Security audit 2026-10-17, finding M3, stage 1. inboundSession.RcptTo
appended every RCPT (the outbound session de-duplicates), and the end of
the message inserted a row per recipient one statement at a time inside
Postfix's callback; the cut to 10 000 rows every 500 counted only the log
tailer's rows. Postfix accepts a repeated recipient up to
smtpd_recipient_limit (1 000) and sends each to the milter, so one message
was a thousand rows, uncut until the six-hourly prune.

Now: the inbound milter folds a repeated recipient (case-insensitive, as
cleanup's been_here() with BH_FLAG_FOLD does, and as session.RcptTo does);
a message's rows go in one transaction (store.InsertInboundSpamMessage,
which replaces InsertInboundSpam in milter.InboundStore); the count and the
cut moved from the tailer into the store (countInboundWrites, an atomic
counter on Store) so the milter's rows, the tailer's and the tailer's
start-up re-reads all count. store.InboundSpamLogMaxRows is the one cap.

Tests: TestInboundRecipientRepeatedIsOneRow (1 000 RCPT in two cases, one
row); TestInboundJournalIsCutWhicheverWriterWrites (a small cap: a message's
rows and refusals together cross the mark, the table is cut); the tailer's
own counting test went with its counter. go test ./internal/store
./internal/milter ./internal/logtail (Windows-only Follow failures aside).
Also gofmt of a test line from the M2 commit.

Docs: security.md § Mail path, architecture.md; CHANGELOG; plan.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
mix
2026-10-17 21:44:28 +03:00
co-authored by Claude Opus 5.5
parent d254a9952d
commit c50314fb4c
11 changed files with 216 additions and 53 deletions
+85 -5
View File
@@ -63,9 +63,86 @@ type InboundSpamEntry struct {
// inbound domain registered under the row's name now (audit 2026-10-12, L12).
const inboundDomainID = `(SELECT d.id FROM inbound_domains d WHERE d.name = ?)`
// InsertInboundSpam records one journal row. It is called from the inbound
// journal milter's hot path and from the log tailer, so it returns any error
// for the caller to log; neither of them may hold up mail over it.
// InboundSpamLogMaxRows is how many rows the journal keeps whatever their
// age: refusals are written at the rate strangers knock on port 25, and
// accepted mail at the rate they send recipients.
const InboundSpamLogMaxRows = 10000
// inboundCapRows and inboundCapEvery are the cap and how many rows - from
// either writer - are written before the journal is cut back to it, without
// waiting for the six-hourly prune. Postfix's one limit on the rate of RCPT
// TO, smtpd_client_recipient_rate_limit, is per client address and off by
// default (postconf(5), Postfix 3.10.13) and not set here. Until 2.14.4 only
// the log tailer counted its rows; the journal milter's - one per accepted
// recipient - were cut only every six hours (security audit 2026-10-17, M3).
// Variables so that a test can make them small.
var (
inboundCapRows = InboundSpamLogMaxRows
inboundCapEvery = int64(500)
)
// countInboundWrites adds n written rows to the count and, once it reaches
// inboundCapEvery, cuts the journal to its cap. Two writers crossing the mark
// together may both cut; the second finds nothing to do.
func (s *Store) countInboundWrites(n int) error {
if n <= 0 || s.inboundWrites.Add(int64(n)) < inboundCapEvery {
return nil
}
s.inboundWrites.Store(0)
// The zero time removes nothing by age: this is the cap alone.
if _, err := s.PruneInboundSpam(time.Time{}, inboundCapRows); err != nil {
return fmt.Errorf("cut inbound_spam_log to %d rows: %w", inboundCapRows, err)
}
return nil
}
// InboundRecipient is one recipient of an accepted message at an inbound
// domain: a row of InsertInboundSpamMessage.
type InboundRecipient struct {
Domain string
To string
}
// InsertInboundSpamMessage records the rows of one accepted message, one per
// recipient, e with InboundDomain and To taken from each, in one transaction:
// the journal milter writes inside Postfix's end-of-message callback on the
// panel's one connection, and a thousand recipients are one commit, not a
// thousand. It returns any error for the caller to log.
func (s *Store) InsertInboundSpamMessage(e InboundSpamEntry, rcpts []InboundRecipient) error {
if len(rcpts) == 0 {
return nil
}
at := e.At
if at.IsZero() {
at = time.Now()
}
tx, err := s.db.Begin()
if err != nil {
return fmt.Errorf("insert inbound_spam_log: begin: %w", err)
}
defer tx.Rollback() //nolint:errcheck // a no-op after Commit
for _, r := range rcpts {
if _, err := tx.Exec(
`INSERT INTO inbound_spam_log
(inbound_domain, client_ip, from_addr, to_addr, subject, decision, engine, detail, created_at, inbound_domain_id,
queue_id, upstream_status)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, `+inboundDomainID+`, ?, ?)`,
r.Domain, e.ClientIP, e.From, r.To, e.Subject, e.Decision, e.Engine, e.Detail,
at.UTC().Format(time.RFC3339), r.Domain, e.QueueID, e.Upstream,
); err != nil {
return fmt.Errorf("insert inbound_spam_log: %w", err)
}
}
if err := tx.Commit(); err != nil {
return fmt.Errorf("insert inbound_spam_log: commit: %w", err)
}
return s.countInboundWrites(len(rcpts))
}
// InsertInboundSpam records one journal row. It is called from the log
// tailer (and was from the journal milter, which now writes a message's rows
// at once), so it returns any error for the caller to log; it may not hold up
// mail over it.
func (s *Store) InsertInboundSpam(e InboundSpamEntry) error {
at := e.At
if at.IsZero() {
@@ -82,7 +159,7 @@ func (s *Store) InsertInboundSpam(e InboundSpamEntry) error {
if err != nil {
return fmt.Errorf("insert inbound_spam_log: %w", err)
}
return nil
return s.countInboundWrites(1)
}
// InsertInboundSpamOnce records a journal row unless the same row is there
@@ -109,7 +186,10 @@ func (s *Store) InsertInboundSpamOnce(e InboundSpamEntry) (bool, error) {
return false, fmt.Errorf("insert inbound_spam_log once: %w", err)
}
n, _ := res.RowsAffected()
return n > 0, nil
if n == 0 {
return false, nil
}
return true, s.countInboundWrites(1)
}
// updateUpstreamQuery puts one delivery attempt's result on the rows of a
+57
View File
@@ -1,6 +1,7 @@
package store
import (
"fmt"
"strings"
"testing"
"time"
@@ -495,3 +496,59 @@ func TestInboundUpstreamHeldAndReusedQueueID(t *testing.T) {
t.Errorf("ForgetInboundQueueID does not use idx_inbound_spam_log_queue_id:\n%s", plan)
}
}
// The journal is cut to its cap every so many rows, whichever writer wrote
// them: the journal milter's rows of accepted mail count as the tailer's
// refusals do (security audit 2026-10-17, M3). One message's rows are one
// call. Here the cap is 5 rows and the cut every 4.
func TestInboundJournalIsCutWhicheverWriterWrites(t *testing.T) {
st := openTestStore(t)
rowsBefore, everyBefore := inboundCapRows, inboundCapEvery
inboundCapRows, inboundCapEvery = 5, 4
t.Cleanup(func() { inboundCapRows, inboundCapEvery = rowsBefore, everyBefore })
if _, err := st.AddInboundDomain("in.example.com"); err != nil {
t.Fatal(err)
}
count := func() int {
var n int
if err := st.db.QueryRow("SELECT COUNT(*) FROM inbound_spam_log").Scan(&n); err != nil {
t.Fatal(err)
}
return n
}
accepted := InboundSpamEntry{ClientIP: "203.0.113.7", From: "a@example.net", Decision: SpamDecisionAccept, Engine: SpamEngineSelfPost}
var rcpts []InboundRecipient
for i := 0; i < 3; i++ {
rcpts = append(rcpts, InboundRecipient{Domain: "in.example.com", To: fmt.Sprintf("r%d@in.example.com", i)})
}
// Three rows of one message, then two refusals: the fourth row crosses
// the mark, and the journal is cut to five.
if err := st.InsertInboundSpamMessage(accepted, rcpts); err != nil {
t.Fatal(err)
}
for i := 0; i < 2; i++ {
if err := st.InsertInboundSpam(InboundSpamEntry{InboundDomain: "in.example.com", ClientIP: "203.0.113.9", To: "x@in.example.com",
Decision: SpamDecisionReject, Engine: SpamEnginePostfix}); err != nil {
t.Fatal(err)
}
}
if n := count(); n != 5 {
t.Fatalf("after 5 rows, %d (no cut yet past the cap)", n)
}
// A message of six more crosses the mark again: cut to five.
rcpts = nil
for i := 0; i < 6; i++ {
rcpts = append(rcpts, InboundRecipient{Domain: "in.example.com", To: fmt.Sprintf("m%d@in.example.com", i)})
}
if err := st.InsertInboundSpamMessage(accepted, rcpts); err != nil {
t.Fatal(err)
}
if n := count(); n != 5 {
t.Errorf("after a message of six over the mark, %d rows, want the cap of 5", n)
}
// The message's rows carry the domain by id, like the tailer's.
var missing int
if err := st.db.QueryRow("SELECT COUNT(*) FROM inbound_spam_log WHERE inbound_domain_id IS NULL").Scan(&missing); err != nil || missing != 0 {
t.Errorf("%d rows without a domain id (%v)", missing, err)
}
}
+5
View File
@@ -13,6 +13,7 @@ import (
"io/fs"
"os"
"sort"
"sync/atomic"
_ "modernc.org/sqlite" // pure-Go SQLite driver (no cgo), keeps the static build
)
@@ -23,6 +24,10 @@ var migrationsFS embed.FS
// Store wraps the database connection pool.
type Store struct {
db *sql.DB
// inboundWrites counts journal rows written since the journal was last
// cut to its row cap, by both of its writers (countInboundWrites).
inboundWrites atomic.Int64
}
// Open opens (creating if needed) the SQLite database at path, enables WAL and