panel-notifications: the notifier, its mail and the server's own DKIM key

internal/notify applies the owner's rules. Each subject has a row of state, so a thing is said once and a restart says nothing again: - DNS of a sending domain: said after two hourly checks in a row found a record wrong, said to be over after two found it right. A lookup that did not answer moves nothing; a warning (no DMARC record) is not a subject. - TLS certificate: at 14 days and at 3, per certificate. - Queue: a message older than three days, once; once more when none is. - Level-2 limit: from the rejected rows of the send log, every five minutes; at most once a day per domain and application. Global users are told everything, domain users about their domains; one message per recipient. With the instance switch off nothing is checked and no state moves. A message that could not be handed to Postfix is tried again at the next check. Mail leaves by sendmail(1) as postmaster@<hostname>, addresses after "--", no shell. For it to be believed the server's own name is signed like a sending domain: domain.Service keeps a key for it and a line in OpenDKIM's tables without a registry row, and non_smtpd_milters now names OpenDKIM. A sending domain of the same name shares its key with the server. dnscheck.ServerMail checks the name's DKIM and SPF records; postfix.QueueMessages reads postqueue -j for arrival times. The notifier is a sixth role of the panel process. Nothing in the panel shows or switches it yet. Checked on Windows: go vet clean; go test passes for notify, store, postfix, dnscheck, cmd, and domain apart from TestWriteLoadPrivateKeyRoundtrip, which fails there on file modes and always did. Not yet run in a container: whether the unprivileged panel may submit is for the e2e step. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 15:56:13 +03:00
parent 06ad174fb9
commit 50fd6b859f
17 changed files with 1547 additions and 9 deletions
@@ -100,6 +100,7 @@ type Checker struct {
 	servers map[string]cached[Server]
 	domains map[string]cached[Domain]
 	inbound map[string]cached[Result]
+	mail    map[string]cached[Mail]
 }

 type cached[T any] struct {
@@ -123,6 +124,7 @@ func newChecker(r resolver, timeout, srvTTL, domTTL time.Duration) *Checker {
 		servers:   make(map[string]cached[Server]),
 		domains:   make(map[string]cached[Domain]),
 		inbound:   make(map[string]cached[Result]),
+		mail:      make(map[string]cached[Mail]),
 	}
 }

@@ -170,6 +172,56 @@ func (c *Checker) Domain(q Query, force bool) Domain {
 	return d
 }

+// Mail is the published-DNS state of the server's own name as a sender: the
+// panel's notifications go out from postmaster@ the hostname, signed with a
+// key of that name.
+type Mail struct {
+	Name      string
+	DKIM      Result
+	SPF       Result
+	Overall   health.Status
+	CheckedAt time.Time
+}
+
+// ServerMailSPF is the SPF record to publish for the server's own name: its
+// address record is the one sender.
+const ServerMailSPF = "v=spf1 a -all"
+
+// ServerMail checks the DKIM and SPF records of the server's own name. q is as
+// for a domain, with Name the hostname. Cached like a domain; force skips the
+// cache.
+func (c *Checker) ServerMail(q Query, force bool) Mail {
+	key := "\x00mail\x00" + q.Name
+	if !force {
+		c.mu.Lock()
+		entry, ok := c.mail[key]
+		c.mu.Unlock()
+		if ok && time.Now().Before(entry.expires) {
+			return entry.value
+		}
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), c.timeout)
+	defer cancel()
+	m := Mail{Name: q.Name, CheckedAt: time.Now()}
+	var wg sync.WaitGroup
+	wg.Add(2)
+	go func() { defer wg.Done(); m.DKIM = c.checkDKIM(ctx, q) }()
+	go func() { defer wg.Done(); m.SPF = c.checkSPF(ctx, q) }()
+	wg.Wait()
+	// checkSPF words a missing record for a sending domain; for the server's
+	// own name the record to publish is a different one.
+	if m.SPF.Status == health.StatusError && len(m.SPF.Records) == 0 {
+		m.SPF.Detail = fmt.Sprintf("No SPF record is published for %s. Publish the TXT record %q - without it a receiver has nothing authorising this server to send as its own name.", q.Name, ServerMailSPF)
+	}
+	m.Overall = health.Worst(m.DKIM.Status, m.SPF.Status)
+
+	c.mu.Lock()
+	c.mail[key] = cached[Mail]{value: m, expires: m.CheckedAt.Add(c.domainTTL)}
+	c.mu.Unlock()
+	return m
+}
+
 // Forget drops a domain's cached result, so the next page view re-checks it.
 // Used when a domain is removed or re-imported.
 func (c *Checker) Forget(domainName string) {
@@ -0,0 +1,82 @@
+package dnscheck
+
+import (
+	"net"
+	"strings"
+	"testing"
+
+	"github.com/mixeme/selfpost/internal/health"
+)
+
+const serverDKIM = "v=DKIM1; k=rsa; p=MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAserverkey"
+
+func serverMailQuery() Query {
+	return Query{
+		Name:         "mail.example.org",
+		Selector:     "sp",
+		ExpectedDKIM: serverDKIM,
+		Hostname:     "mail.example.org",
+		ServerIPs:    []string{"203.0.113.25"},
+	}
+}
+
+// The server's own name passes with its key published and "v=spf1 a -all":
+// the name's address record is this server.
+func TestServerMailPublished(t *testing.T) {
+	f := &fakeResolver{
+		txt: map[string][]string{
+			"sp._domainkey.mail.example.org": {serverDKIM},
+			"mail.example.org":               {ServerMailSPF},
+		},
+		addr: map[string][]net.IPAddr{"mail.example.org": ipAddrs("203.0.113.25")},
+	}
+	c := newTestChecker(f)
+
+	m := c.ServerMail(serverMailQuery(), false)
+	if m.DKIM.Status != health.StatusOK || m.SPF.Status != health.StatusOK || m.Overall != health.StatusOK {
+		t.Fatalf("DKIM %s (%s), SPF %s (%s), overall %s", m.DKIM.Status, m.DKIM.Detail, m.SPF.Status, m.SPF.Detail, m.Overall)
+	}
+
+	// Cached like a domain, and re-read when forced.
+	before := f.lookups
+	c.ServerMail(serverMailQuery(), false)
+	if f.lookups != before {
+		t.Errorf("a second reading looked DNS up again (%d lookups)", f.lookups-before)
+	}
+	c.ServerMail(serverMailQuery(), true)
+	if f.lookups == before {
+		t.Error("a forced reading used the cache")
+	}
+}
+
+// With nothing published both records are errors, and the SPF advice names the
+// record for a server's own name, not the one for a sending domain.
+func TestServerMailMissing(t *testing.T) {
+	c := newTestChecker(&fakeResolver{})
+
+	m := c.ServerMail(serverMailQuery(), false)
+	if m.DKIM.Status != health.StatusError || m.SPF.Status != health.StatusError || m.Overall != health.StatusError {
+		t.Fatalf("DKIM %s, SPF %s, overall %s; want errors", m.DKIM.Status, m.SPF.Status, m.Overall)
+	}
+	if !strings.Contains(m.SPF.Detail, ServerMailSPF) || strings.Contains(m.SPF.Detail, "a:mail.example.org") {
+		t.Errorf("SPF advice: %s", m.SPF.Detail)
+	}
+}
+
+// A sending domain of the same name does not share the cache entry.
+func TestServerMailCacheIsItsOwn(t *testing.T) {
+	f := &fakeResolver{
+		txt: map[string][]string{
+			"sp._domainkey.mail.example.org": {serverDKIM},
+			"mail.example.org":               {ServerMailSPF},
+		},
+		addr: map[string][]net.IPAddr{"mail.example.org": ipAddrs("203.0.113.25")},
+	}
+	c := newTestChecker(f)
+	c.Domain(serverMailQuery(), false)
+	before := f.lookups
+	c.ServerMail(serverMailQuery(), false)
+	if f.lookups == before {
+		t.Error("the server's mail check was answered from the domain's cache entry")
+	}
+}