watcher: follow a watched name's CNAME for port and TLS checks (closes #203)

When a watched name's nameservers answer with a CNAME and no address,
the DNS check asks ResolveIPAddresses for the name, which looks it up
again and follows the chain, and saves the addresses at its end in the
hostname state as cnameAddresses. The port and TLS checks use them. A
change in them is notified as a CNAME address change, also from or to
none. A state file without the field loads them as not known (nil), so
its first check sends nothing for them. When following fails, or none
of the name's nameservers answered, the last check's addresses are
kept. The domain check now runs the hostname check for the apex
instead of a copy of it.

Model: opus-5-5

internal/watcher/cname_test.go

@@ -0,0 +1,238 @@
+package watcher_test
+
+import (
+	"context"
+	"log/slog"
+	"slices"
+	"testing"
+
+	"sneak.berlin/go/dnswatcher/internal/livednstest"
+	"sneak.berlin/go/dnswatcher/internal/resolver"
+	"sneak.berlin/go/dnswatcher/internal/state"
+	"sneak.berlin/go/dnswatcher/internal/watcher"
+)
+
+// cnameHost is a CNAME into another zone: its nameservers answer with
+// the CNAME and no address.
+const cnameHost = "www.python.org"
+
+// TestCNAMEIntoAnotherZonePortAndTLSChecks checks cnameHost against
+// live DNS. Its port and TLS checks must use the addresses at the end
+// of its CNAME chain.
+func TestCNAMEIntoAnotherZonePortAndTLSChecks(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.Hostnames = []string{cnameHost}
+
+	deps := runChecks(t, cfg, nil, nil)
+
+	snap := deps.state.GetSnapshot()
+	hs := snap.Hostnames[cnameHost]
+
+	if len(hs.CNAMEAddresses) == 0 {
+		t.Fatalf(
+			"%s: no addresses saved from following its CNAME; if it "+
+				"is no longer a CNAME into another zone, this test "+
+				"needs another name",
+			cnameHost,
+		)
+	}
+
+	for _, ip := range hs.CNAMEAddresses {
+		ps, ok := snap.Ports[ip+":443"]
+		if !ok || !slices.Contains(ps.Hostnames, cnameHost) {
+			t.Errorf("no port state for %s at %s:443", cnameHost, ip)
+		}
+
+		certKey := ip + ":443:" + cnameHost
+		if _, ok := snap.Certificates[certKey]; !ok {
+			t.Errorf("no certificate state %s", certKey)
+		}
+	}
+}
+
+// TestCNAMEThatCannotBeFollowedKeepsPrevious gives a name under
+// .invalid, whose lookup fails, answers with a CNAME and no address.
+// The addresses the previous check saved from following its CNAME are
+// kept.
+func TestCNAMEThatCannotBeFollowedKeepsPrevious(t *testing.T) {
+	t.Parallel()
+
+	const name = "www.example.invalid"
+
+	w := watcher.NewForTest(
+		nil, nil, resolver.NewFromLogger(slog.Default()), nil, nil, nil,
+	)
+
+	current := hostnameState(map[string]map[string][]string{
+		nsA: {"CNAME": {"target.example.invalid."}},
+	})
+	prev := &state.HostnameState{CNAMEAddresses: []string{oldIP}}
+
+	// The result is the same whether or not live DNS answers, so the
+	// lookup is not retried.
+	_ = livednstest.Run(func(ctx context.Context) error {
+		w.ResolveCNAMEAddresses(ctx, name, current, prev)
+
+		return nil
+	})
+
+	if !slices.Equal(current.CNAMEAddresses, prev.CNAMEAddresses) {
+		t.Errorf(
+			"saved %v, want %v",
+			current.CNAMEAddresses, prev.CNAMEAddresses,
+		)
+	}
+}
+
+// TestCNAMEWhoseNameserversAllFailedKeepsPrevious checks a name none of
+// whose nameservers answered. The addresses the previous check saved
+// from following its CNAME are kept, and nothing is looked up: the
+// watcher has no resolver.
+func TestCNAMEWhoseNameserversAllFailedKeepsPrevious(t *testing.T) {
+	t.Parallel()
+
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, nil)
+
+	current := saved(map[string]*state.NameserverRecordState{
+		nsA: failed(), nsB: failed(),
+	})
+	prev := cnameState(oldIP)
+
+	w.ResolveCNAMEAddresses(t.Context(), host, current, prev)
+
+	if !slices.Equal(current.CNAMEAddresses, prev.CNAMEAddresses) {
+		t.Errorf(
+			"saved %v, want %v",
+			current.CNAMEAddresses, prev.CNAMEAddresses,
+		)
+	}
+}
+
+// cnameState builds the state a check leaves behind for a name whose
+// nameserver answered with a CNAME and no address, when following the
+// CNAME found these addresses, which may be none.
+func cnameState(addresses ...string) *state.HostnameState {
+	hs := hostnameState(map[string]map[string][]string{
+		nsA: {"CNAME": {"target.example.org."}},
+	})
+
+	hs.CNAMEAddresses = append([]string{}, addresses...)
+
+	return hs
+}
+
+func TestCNAMEAddressChangeAlerts(t *testing.T) {
+	t.Parallel()
+
+	// A state file written before the addresses were saved loads with
+	// them nil.
+	olderStateFile := cnameState()
+	olderStateFile.CNAMEAddresses = nil
+
+	// Each case is the state saved by the previous check and by the
+	// current one. The name's records are the same in both.
+	tests := []struct {
+		name          string
+		prev, current *state.HostnameState
+		want          int
+	}{
+		{
+			"same addresses",
+			cnameState(ip1, ip2), cnameState(ip1, ip2), 0,
+		},
+		{
+			"same addresses in another order",
+			cnameState(ip2, ip1), cnameState(ip1, ip2), 0,
+		},
+		{
+			"address replaced",
+			cnameState(ip1), cnameState(ip2), 1,
+		},
+		{
+			"address added",
+			cnameState(ip1), cnameState(ip1, ip2), 1,
+		},
+		{
+			"no address at the end of the chain now",
+			cnameState(ip1), cnameState(), 1,
+		},
+		{
+			"addresses at the end of the chain again",
+			cnameState(), cnameState(ip1), 1,
+		},
+		{
+			"state file from before addresses were saved",
+			olderStateFile, cnameState(ip1), 0,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			notifier := &mockNotifier{}
+			w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+			w.DetectHostnameChanges(t.Context(), host, tt.prev, tt.current)
+
+			got := len(notifier.getNotifications())
+			if got != tt.want {
+				t.Errorf("sent %d notifications, want %d", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestCNAMEAddressChangeAlertNamesHostnameAndAddresses(t *testing.T) {
+	t.Parallel()
+
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+	w.DetectHostnameChanges(
+		t.Context(), host, cnameState(ip1), cnameState(ip2, ip3),
+	)
+
+	want := notification{
+		Title: "CNAME Address Change: " + host,
+		Message: "Hostname: " + host +
+			"\nOld: " + ip1 + "\nNew: " + ip2 + ", " + ip3,
+		Priority: "warning",
+	}
+
+	got := notifier.getNotifications()
+	if len(got) != 1 || got[0] != want {
+		t.Errorf("sent %v, want %v", got, want)
+	}
+}
+
+// TestNameMovedFromARecordsToCNAMEAlerts checks a name that answers
+// with an A record and then with a CNAME whose chain ends in ip2. The
+// second check is notified as a CNAME address change from no addresses,
+// beside the record change. Nothing is looked up: the watcher has no
+// resolver.
+func TestNameMovedFromARecordsToCNAMEAlerts(t *testing.T) {
+	t.Parallel()
+
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+	prev := hostnameState(map[string]map[string][]string{
+		nsA: {"A": {ip1}},
+	})
+	w.ResolveCNAMEAddresses(t.Context(), host, prev, nil)
+
+	w.DetectHostnameChanges(t.Context(), host, prev, cnameState(ip2))
+
+	title := "CNAME Address Change: " + host
+	message := "Hostname: " + host + "\nOld: \nNew: " + ip2
+
+	got := notifier.getNotifications()
+	if !slices.ContainsFunc(got, func(n notification) bool {
+		return n.Title == title && n.Message == message
+	}) {
+		t.Errorf("sent %v, want %q with %q among them", got, title, message)
+	}
+}

internal/watcher/export_test.go

@@ -57,6 +57,15 @@ func (w *Watcher) ResolveNameserverAddresses(
 	return w.resolveNameserverAddresses(ctx, nameservers, prev)
 }
 
+// ResolveCNAMEAddresses exports resolveCNAMEAddresses for testing.
+func (w *Watcher) ResolveCNAMEAddresses(
+	ctx context.Context,
+	hostname string,
+	current, prev *state.HostnameState,
+) {
+	w.resolveCNAMEAddresses(ctx, hostname, current, prev)
+}
+
 // DetectNSAddressChanges exports detectNSAddressChanges for testing.
 func (w *Watcher) DetectNSAddressChanges(
 	ctx context.Context,

internal/watcher/watcher.go

@@ -252,28 +252,9 @@ func (w *Watcher) checkDomain(
 		LastChecked:         now,
 	})
 
-	// Also look up A/AAAA records for the apex domain so that
-	// port and TLS checks (which read HostnameState) can find
-	// the domain's IP addresses.
-	results, err := w.resolver.LookupAllRecords(ctx, domain)
-	if err != nil {
-		w.log.Error(
-			"failed to lookup records for domain",
-			"domain", domain,
-			"error", err,
-		)
-
-		return
-	}
-
-	newState := buildHostnameState(results, now)
-
-	prevHS, hasPrevHS := w.state.GetHostnameState(domain)
-	if hasPrevHS && !w.firstRun {
-		w.detectHostnameChanges(ctx, domain, prevHS, newState)
-	}
-
-	w.state.SetHostnameState(domain, newState)
+	// The apex domain's records are also checked as a hostname's, so
+	// that the port and TLS checks find its addresses.
+	w.checkHostname(ctx, domain)
 }
 
 func (w *Watcher) detectNSChanges(
@@ -401,6 +382,9 @@ func (w *Watcher) checkHostname(
 	newState := buildHostnameState(results, time.Now().UTC())
 
 	prev, hasPrev := w.state.GetHostnameState(hostname)
+
+	w.resolveCNAMEAddresses(ctx, hostname, newState, prev)
+
 	if hasPrev && !w.firstRun {
 		w.detectHostnameChanges(ctx, hostname, prev, newState)
 	}
@@ -408,6 +392,73 @@ func (w *Watcher) checkHostname(
 	w.state.SetHostnameState(hostname, newState)
 }
 
+// resolveCNAMEAddresses saves in current the addresses at the end of
+// hostname's CNAME chain, when the nameservers' answers in current hold
+// a CNAME and no address, and an empty list otherwise.
+// ResolveIPAddresses looks the name up again and follows the chain. The
+// addresses saved in prev, which may be nil, are kept when none of the
+// name's nameservers answered, and when the chain cannot be followed, as
+// when no nameserver of a zone in it answers.
+func (w *Watcher) resolveCNAMEAddresses(
+	ctx context.Context,
+	hostname string,
+	current, prev *state.HostnameState,
+) {
+	var prevAddresses []string
+	if prev != nil {
+		prevAddresses = prev.CNAMEAddresses
+	}
+
+	// Empty, not nil: nil means the addresses are not known.
+	current.CNAMEAddresses = []string{}
+
+	answered := false
+	hasCNAME := false
+
+	for _, nsState := range current.RecordsByNameserver {
+		if nsState.Status != statusOK {
+			continue
+		}
+
+		answered = true
+
+		if len(nsState.Records["A"]) > 0 || len(nsState.Records["AAAA"]) > 0 {
+			return
+		}
+
+		if len(nsState.Records["CNAME"]) > 0 {
+			hasCNAME = true
+		}
+	}
+
+	if !answered {
+		current.CNAMEAddresses = prevAddresses
+
+		return
+	}
+
+	if !hasCNAME {
+		return
+	}
+
+	ips, err := w.resolver.ResolveIPAddresses(ctx, hostname)
+	if err != nil {
+		w.log.Error(
+			"failed to follow CNAME",
+			"hostname", hostname,
+			"error", err,
+		)
+
+		current.CNAMEAddresses = prevAddresses
+
+		return
+	}
+
+	// Appended to the empty list, so a chain that ends in no address is
+	// saved as empty, not nil.
+	current.CNAMEAddresses = append(current.CNAMEAddresses, ips...)
+}
+
 // buildHostnameState saves each nameserver's response. A nameserver
 // that answered, even with NXDOMAIN or no records, is saved as ok; one
 // that timed out or failed is saved as error with the reason, and its
@@ -451,6 +502,37 @@ func (w *Watcher) detectHostnameChanges(
 	w.detectNSDisappearances(ctx, hostname, prev, current)
 	w.detectNSFailures(ctx, hostname, prev, current)
 	w.detectInconsistencies(ctx, hostname, prev, current)
+	w.detectCNAMEAddressChanges(ctx, hostname, prev, current)
+}
+
+// detectCNAMEAddressChanges notifies when the addresses at the end of
+// hostname's CNAME chain differ from those the previous check saved,
+// including a change from or to none. When the previous addresses are
+// not known (nil), as on the first check after loading a state file
+// written before they were saved, nothing is compared.
+func (w *Watcher) detectCNAMEAddressChanges(
+	ctx context.Context,
+	hostname string,
+	prev, current *state.HostnameState,
+) {
+	old, cur := prev.CNAMEAddresses, current.CNAMEAddresses
+	if old == nil || sliceEqual(old, cur) {
+		return
+	}
+
+	msg := fmt.Sprintf(
+		"Hostname: %s\nOld: %s\nNew: %s",
+		hostname,
+		strings.Join(old, ", "),
+		strings.Join(cur, ", "),
+	)
+
+	w.notify.SendNotification(
+		ctx,
+		"CNAME Address Change: "+hostname,
+		msg,
+		"warning",
+	)
 }
 
 // detectRecordChanges compares each nameserver's records with those of
@@ -747,6 +829,9 @@ func (w *Watcher) noNameserverAnswered(name string) bool {
 	return true
 }
 
+// collectIPs returns the addresses saved for hostname: those in its
+// nameservers' A and AAAA records, and those at the end of its CNAME
+// chain.
 func (w *Watcher) collectIPs(hostname string) []string {
 	hs, ok := w.state.GetHostnameState(hostname)
 	if !ok {
@@ -765,6 +850,10 @@ func (w *Watcher) collectIPs(hostname string) []string {
 		}
 	}
 
+	for _, ip := range hs.CNAMEAddresses {
+		ipSet[ip] = true
+	}
+
 	result := make([]string, 0, len(ipSet))
 	for ip := range ipSet {
 		result = append(result, ip)

internal/watcher/watcher_test.go

@@ -315,7 +315,8 @@ func lookupNameservers(t *testing.T, domain string) []string {
 	return nameservers
 }
 
-// addresses returns the A and AAAA values saved for a hostname.
+// addresses returns the A and AAAA values saved for a hostname, and the
+// addresses saved at the end of its CNAME chain.
 func addresses(hs *state.HostnameState) []string {
 	var ips []string
 
@@ -324,7 +325,7 @@ func addresses(hs *state.HostnameState) []string {
 		ips = append(ips, nsState.Records["AAAA"]...)
 	}
 
-	return ips
+	return append(ips, hs.CNAMEAddresses...)
 }
 
 // assertNotified checks that a notification with this title and