Files
selfpost/test/e2e/delivery_log_test.go
T
mixandClaude Opus 5.5 22ce1bdfbb postfix: long, non-repeating queue ids
The owner, 2026-10-16, of three ways to stop a reused queue id reaching an
older row (found by the technical review of inbound-upstream-result, L6):
"1" - enable_long_queue_ids=yes. A short id is the microsecond of arrival
and the queue file's inode in hex (Postfix 3.10.13, src/global/mail_queue.h,
MQID_SH_*) and repeats once the inode comes round; a later message with no
send-log row of its own (port-25 mail, a bounce Postfix sends) could then
rewrite an older Outbound log row of the same id and recipient, its page
could show the later message's stored lines (security.md's known exposure,
"enable_long_queue_ids ... ends it"), and the inbound journal's rows needed
detaching. A long id adds the time in seconds and does not repeat
(MQID_LG_*; proto/postconf.proto: existing queue files keep their names,
postqueue -p gets a wider Queue ID column). Every pattern of the panel
takes both shapes (queueLineRe's long branch, the [0-9A-Za-z]+ of the
others, queueEntryRe) - checked one by one.

Tests: e2e reads a long id on an outbound send-log row
(testExpiredMessageIsClosed) and on an inbound journal row
(testInboundUpstreamDown). go vet + go test (26 packages) and make e2e on
the test server for this tree.

Docs: security.md (the collision bullet closed for new mail, the upstream
bullet), architecture § Log tailer, delivery-log-storage's note, the
ForgetInboundQueueID comment; CHANGELOG [Unreleased] § Fixed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 18:59:18 +03:00

207 lines
8.4 KiB
Go

package e2e
import (
"fmt"
"html"
"regexp"
"strings"
"testing"
"time"
)
var sendLogDetailsRe = regexp.MustCompile(`href="(/outbound/log/\d+[^"]*)"`)
// firstDeliveryPage returns the address of the page of the newest row in the
// sender domain's send log.
func firstDeliveryPage(sc *scenario) (string, error) {
rows, err := sc.panel.sendLogRows(senderDomain, "")
if err != nil {
return "", fmt.Errorf("read the send log: %w", err)
}
m := sendLogDetailsRe.FindStringSubmatch(rows)
if m == nil {
return "", fmt.Errorf("no Details link in the send log:\n%s", rows)
}
return html.UnescapeString(m[1]), nil
}
// testDeliveryLogSurvivesRotation checks that a message's page still lists
// what Postfix wrote about it after mail.log has been rotated: the lines are
// kept in the database by the log tailer, not searched for in the current
// file (architecture.md § Log tailer, Stored lines). The message is the first
// one delivered, whose page send_verify_dkim_and_status noted.
func testDeliveryLogSurvivesRotation(t *testing.T, sc *scenario) {
page := sc.deliveryPage
// What the page has to show: the line that opened the queue id and the
// delivery line. The tailer has read both - the row is "sent" - but it
// writes them one at a time, so the page is polled rather than read once.
wanted := []string{"client=", "status=sent"}
shows := func() (bool, error) {
_, body, err := sc.panel.get(page)
if err != nil {
return false, err
}
for _, w := range wanted {
if !strings.Contains(body, w) {
return false, fmt.Errorf("%s does not show a %q line", page, w)
}
}
return true, nil
}
if err := waitFor("the message's page to list its log lines", 15*time.Second, 500*time.Millisecond, shows); err != nil {
t.Fatal(err)
}
// The rotation ends with `postfix reload`, which fails while Postfix is
// still starting - and this step follows one that restarts the container.
// (Postfix 3.10.13, conf/postfix-script: "reload" and "status" both test
// "master -t" and exit 1 while master does not hold its pid lock.)
if err := waitFor("Postfix to be running", 30*time.Second, 500*time.Millisecond, func() (bool, error) {
if _, err := h.execIn("selfpost", "postfix", "status"); err != nil {
return false, err
}
return true, nil
}); err != nil {
t.Fatal(err)
}
if _, err := h.execIn("selfpost", "logrotate", "-f", "/etc/logrotate.d/mail"); err != nil {
t.Fatalf("logrotate -f: %v", err)
}
// The current file must no longer hold the delivery line, or the page
// finding it there would prove nothing. grep exits 1 on no match.
if out, err := h.execIn("selfpost", "sh", "-c", "grep -c 'status=sent' /data/log/mail.log || true"); err != nil || strings.TrimSpace(out) != "0" {
t.Fatalf("mail.log still holds delivery lines after the rotation (count=%q err=%v)", strings.TrimSpace(out), err)
}
if ok, err := shows(); !ok {
t.Fatalf("after mail.log was rotated: %v", err)
}
}
// testExpiredMessageIsClosed: a message Postfix gives up on is closed as
// bounced. Postfix logs expiry once per message, "<id>: from=<..>,
// status=expired, returned to sender" (here "force-expired"), and no line per
// recipient (Postfix 3.10.13, src/qmgr/qmgr_active.c,
// qmgr_active_done_25_generic(); assumptions A-8). The queue lifetime cannot
// be waited out, so the message is deferred by hand - defer_transports=smtp,
// under which qmgr hands the recipient to the retry service, "4.3.2 deferred
// transport" (src/qmgr/qmgr_message.c, qmgr_message_resolve()) - and then
// forced to expire: postsuper -e marks it, postqueue -i has qmgr look at it
// at once (man/man1/postsuper.1, postqueue.1).
func testExpiredMessageIsClosed(t *testing.T, sc *scenario) {
exec := func(args ...string) {
t.Helper()
if out, err := h.execIn("selfpost", args...); err != nil {
t.Fatalf("%s: %v\n%s", strings.Join(args, " "), err, out)
}
}
exec("postconf", "-e", "defer_transports=smtp")
exec("postfix", "reload")
defer func() {
// The bounce to the sender waits behind the same setting.
h.execIn("selfpost", "postconf", "-e", "defer_transports=")
h.execIn("selfpost", "postfix", "reload")
h.execIn("selfpost", "postqueue", "-f")
}()
token := uniqueToken("expire")
if res := attemptSend(sendAttempt{
authLogin: sc.appLogin, authPassword: sc.appPassword,
from: "alerts@" + senderDomain, headerFrom: "alerts@" + senderDomain, to: recipient,
subject: "e2e " + token, body: "deferred, then expired",
}); !res.ok() {
t.Fatalf("send: %v", res.firstErr())
}
row := func() (string, error) {
return asPanel(`import sqlite3,sys
r=sqlite3.connect("/data/selfpost.db").execute("select queue_id, status from send_log where subject like ? order by id desc",("%"+sys.argv[1]+"%",)).fetchone()
print("" if r is None else r[0]+" "+r[1])`, token)
}
var queueID string
if err := waitFor("the row to be deferred", 30*time.Second, 500*time.Millisecond, func() (bool, error) {
out, err := row()
if err != nil {
return false, err
}
if f := strings.Fields(out); len(f) == 2 && f[1] == "deferred" {
queueID = f[0]
if !longQueueID.MatchString(queueID) {
return false, fmt.Errorf("queue id %q is not a long one (enable_long_queue_ids)", queueID)
}
return true, nil
}
return false, fmt.Errorf("row %q", out)
}); err != nil {
t.Fatal(err)
}
exec("postsuper", "-e", queueID)
exec("postqueue", "-i", queueID)
if err := waitFor("the expired message's row to be bounced", 30*time.Second, 500*time.Millisecond, func() (bool, error) {
out, err := row()
if err != nil {
return false, err
}
return out == queueID+" bounced", fmt.Errorf("row %q", out)
}); err != nil {
out, _ := h.execIn("selfpost", "grep", queueID, "/data/log/mail.log")
t.Fatalf("%v\nmail.log:\n%s", err, out)
}
out, err := h.execIn("selfpost", "grep", queueID+": from=<alerts@"+senderDomain+">, status=force-expired, returned to sender", "/data/log/mail.log")
if err != nil {
t.Fatalf("no expiry line in mail.log: %v\n%s", err, out)
}
}
// testRecipientsAsPostfixLogsThem: each recipient's row reaches "sent". The
// row holds the recipient as Postfix logs it - "a b" stays quoted, "ab" loses
// its quotes - and a recipient given again in other capitals is one row, as
// cleanup keeps one (Postfix 3.10.13, src/global/quote_822_local.c,
// src/cleanup/cleanup_out_recipient.c; assumptions B-G5, A-31). Before, the
// first was cut at its blank and its row closed as bounced by the sweep.
func testRecipientsAsPostfixLogsThem(t *testing.T, sc *scenario) {
token := uniqueToken("rcpt")
if res := attemptSend(sendAttempt{
authLogin: sc.appLogin, authPassword: sc.appPassword,
from: "alerts@" + senderDomain, headerFrom: "alerts@" + senderDomain,
to: `"x y"@sink.e2e.test`,
moreTo: []string{`"ab"@sink.e2e.test`, `"X Y"@sink.e2e.test`},
subject: "e2e " + token, body: "three RCPT TO, two recipients",
}); !res.ok() {
t.Fatalf("send: %v", res.firstErr())
}
want := `"x y"@sink.e2e.test sent; ab@sink.e2e.test sent`
if err := waitFor("both rows to be sent", 30*time.Second, 500*time.Millisecond, func() (bool, error) {
out, err := asPanel(`import sqlite3,sys
rows=sqlite3.connect("/data/selfpost.db").execute("select to_addr, status from send_log where subject like ? order by id",("%"+sys.argv[1]+"%",)).fetchall()
print("; ".join(r[0]+" "+r[1] for r in rows))`, token)
if err != nil {
return false, err
}
return out == want, fmt.Errorf("rows %q, want %q", out, want)
}); err != nil {
t.Fatal(err)
}
}
// testAddressLiteralIsNotLocal: an address literal of an interface the
// container listens on is a local destination to Postfix even with an empty
// mydestination (Postfix 3.10.13, src/global/resolve_local.c,
// resolve_local()). Local delivery is Postfix's refusal now
// (local_transport=error:..., assumptions C-P8), and smtpd refuses such a
// recipient at RCPT with its text: smtpd_reject_unlisted_recipient (on by
// default) runs check_rcpt_maps(), which rejects whatever resolves to the
// error transport (src/smtpd/smtpd_check.c). Before, the message was
// accepted and handed to local(8).
func testAddressLiteralIsNotLocal(t *testing.T, sc *scenario) {
res := attemptSend(sendAttempt{
authLogin: sc.appLogin, authPassword: sc.appPassword,
from: "alerts@" + senderDomain, headerFrom: "alerts@" + senderDomain,
to: "probe@[127.0.0.1]", subject: "e2e " + uniqueToken("literal"), body: "to an address literal of the container",
})
if err := res.refusedAt("RCPT", 550, "local mail delivery is disabled"); err != nil {
t.Fatalf("to probe@[127.0.0.1]: %v", err)
}
}