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 follows every target they gave with ResolveIPAddresses
and saves all addresses found as cnameAddresses in the hostname state,
so nameservers disagreeing on the target do not change them between
checks. Port and TLS checks use them. A change, also from or to none,
is notified as a CNAME address change; the first check from a state
file without them sends none. When a target cannot be followed, 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 +1,336 @@
+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"
+)
+
+// TestCNAMEIntoAnotherZonePortAndTLSChecks runs the port and TLS
+// checks on hostname state built here: the name's nameserver answered
+// with a CNAME into another zone, and following it found ip1. Both
+// checks must use ip1. They look nothing up, so the watcher has no
+// resolver.
+func TestCNAMEIntoAnotherZonePortAndTLSChecks(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.Hostnames = []string{host}
+
+	deps := newTestDeps(t, cfg)
+	w := watcher.NewForTest(
+		cfg, deps.state, nil,
+		deps.portChecker, deps.tlsChecker, deps.notifier,
+	)
+
+	deps.state.SetHostnameState(host, cnameState(ip1))
+
+	w.CheckAllPorts(t.Context())
+	w.RunTLSChecks(t.Context())
+
+	snap := deps.state.GetSnapshot()
+
+	ps, ok := snap.Ports[ip1+":443"]
+	if !ok || !slices.Contains(ps.Hostnames, host) {
+		t.Errorf("no port state for %s at %s:443", host, ip1)
+	}
+
+	certKey := ip1 + ":443:" + host
+	if _, ok := snap.Certificates[certKey]; !ok {
+		t.Errorf("no certificate state %s", certKey)
+	}
+}
+
+// TestCNAMEThatCannotBeFollowedKeepsPrevious runs a check of a name, not
+// the watcher's first, from the point where its records have been looked
+// up: they hold a CNAME to a target under .invalid, whose lookup fails.
+// The previous check found the same records, and oldIP at the end of the
+// CNAME. The check must keep oldIP and send nothing.
+func TestCNAMEThatCannotBeFollowedKeepsPrevious(t *testing.T) {
+	t.Parallel()
+
+	w, deps := newTestWatcher(t, defaultTestConfig(t))
+	w.SetFirstRun(false)
+
+	records := map[string]map[string][]string{
+		nsA: cnameTo("target.example.invalid."),
+	}
+
+	prev := hostnameState(records)
+	prev.CNAMEAddresses = []string{oldIP}
+	deps.state.SetHostnameState(host, prev)
+
+	// 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.UpdateHostnameState(ctx, host, hostnameState(records))
+
+		return nil
+	})
+
+	hs, _ := deps.state.GetHostnameState(host)
+	if !slices.Equal(hs.CNAMEAddresses, prev.CNAMEAddresses) {
+		t.Errorf(
+			"saved %v, want %v",
+			hs.CNAMEAddresses, prev.CNAMEAddresses,
+		)
+	}
+
+	notifications := deps.notifier.getNotifications()
+	if len(notifications) != 0 {
+		t.Errorf("sent %v, want no notifications", notifications)
+	}
+}
+
+// followLive follows in live DNS the CNAMEs in a name's records, built
+// from records, and returns the addresses saved for the name. The
+// previous check saved oldIP, which is kept when a target cannot be
+// followed; that is retried. The tests point CNAMEs only at names in
+// zones with two nameservers, to keep queries few (see the top of
+// watcher_test.go).
+func followLive(
+	t *testing.T,
+	records map[string]map[string][]string,
+) []string {
+	t.Helper()
+
+	w := watcher.NewForTest(
+		nil, nil, resolver.NewFromLogger(slog.Default()), nil, nil, nil,
+	)
+	prev := cnameState(oldIP)
+
+	var current *state.HostnameState
+
+	livednstest.Retry(t, "following CNAMEs", func(ctx context.Context) error {
+		current = hostnameState(records)
+
+		w.ResolveCNAMEAddresses(ctx, host, current, prev)
+
+		if slices.Equal(current.CNAMEAddresses, prev.CNAMEAddresses) {
+			return livednstest.ErrNoAnswer
+		}
+
+		return nil
+	})
+
+	return current.CNAMEAddresses
+}
+
+// TestCNAMEAddressesOfEveryTarget gives a name's two nameservers
+// different CNAME targets, as when a secondary still serves an old one.
+// The addresses at the end of both are saved, whichever answer is read
+// first: one.one.one.one has 1.1.1.1, and dns.adguard-dns.com has
+// 94.140.14.14.
+func TestCNAMEAddressesOfEveryTarget(t *testing.T) {
+	t.Parallel()
+
+	found := followLive(t, map[string]map[string][]string{
+		nsA: cnameTo("one.one.one.one."),
+		nsB: cnameTo("dns.adguard-dns.com."),
+	})
+
+	for _, ip := range []string{"1.1.1.1", "94.140.14.14"} {
+		if !slices.Contains(found, ip) {
+			t.Errorf("saved %v, want %s among them", found, ip)
+		}
+	}
+}
+
+// TestCNAMEChainEndingInNoAddressSavesEmptyList follows a CNAME to a
+// name live DNS answers with NXDOMAIN. An empty list is saved, not nil,
+// which would mean the addresses are not known.
+func TestCNAMEChainEndingInNoAddressSavesEmptyList(t *testing.T) {
+	t.Parallel()
+
+	found := followLive(t, map[string]map[string][]string{
+		nsA: cnameTo("this-surely-does-not-exist-xyz.example.org."),
+	})
+
+	if found == nil || len(found) != 0 {
+		t.Errorf("saved %#v, want an empty list", found)
+	}
+}
+
+// TestCNAMEBesideAnAddressNotFollowed gives one nameserver of a name an
+// address and another a CNAME. The CNAME is not followed: an empty list
+// is saved, not nil, and nothing is looked up, the watcher having no
+// resolver.
+func TestCNAMEBesideAnAddressNotFollowed(t *testing.T) {
+	t.Parallel()
+
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, nil)
+
+	current := hostnameState(map[string]map[string][]string{
+		nsA: {"A": {ip1}},
+		nsB: cnameTo("target.example.org."),
+	})
+
+	w.ResolveCNAMEAddresses(t.Context(), host, current, nil)
+
+	if current.CNAMEAddresses == nil || len(current.CNAMEAddresses) != 0 {
+		t.Errorf("saved %#v, want an empty list", current.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,
+		)
+	}
+}
+
+// cnameTo builds the records of a nameserver that answered with a CNAME
+// to target and no address.
+func cnameTo(target string) map[string][]string {
+	return map[string][]string{"CNAME": {target}}
+}
+
+// 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: cnameTo("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

@@ -38,6 +38,21 @@ func NewlyDisagreeingPairs(
 	return newlyDisagreeingPairs(prev, current)
 }
 
+// SetFirstRun sets whether the watcher is on its first check, in which
+// nothing is compared with the previous check. NewForTest's watcher is.
+func (w *Watcher) SetFirstRun(firstRun bool) {
+	w.firstRun = firstRun
+}
+
+// UpdateHostnameState exports updateHostnameState for testing.
+func (w *Watcher) UpdateHostnameState(
+	ctx context.Context,
+	hostname string,
+	newState *state.HostnameState,
+) {
+	w.updateHostnameState(ctx, hostname, newState)
+}
+
 // DetectHostnameChanges exports detectHostnameChanges for testing.
 func (w *Watcher) DetectHostnameChanges(
 	ctx context.Context,
@@ -57,6 +72,15 @@ 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(
@@ -398,9 +379,23 @@ func (w *Watcher) checkHostname(
 		return
 	}
 
-	newState := buildHostnameState(results, time.Now().UTC())
+	w.updateHostnameState(
+		ctx, hostname, buildHostnameState(results, time.Now().UTC()),
+	)
+}
 
+// updateHostnameState finishes a check of hostname from newState, built
+// from its nameservers' answers: it follows the CNAME in them, notifies
+// what changed since the previous check, and saves newState.
+func (w *Watcher) updateHostnameState(
+	ctx context.Context,
+	hostname string,
+	newState *state.HostnameState,
+) {
 	prev, hasPrev := w.state.GetHostnameState(hostname)
+
+	w.resolveCNAMEAddresses(ctx, hostname, newState, prev)
+
 	if hasPrev && !w.firstRun {
 		w.detectHostnameChanges(ctx, hostname, prev, newState)
 	}
@@ -408,6 +403,76 @@ 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. Every CNAME
+// target the nameservers gave is followed with ResolveIPAddresses and
+// the addresses found for all of them are saved, so nameservers that
+// disagree on the target do not change the result from check to check.
+// The addresses saved in prev, which may be nil, are kept when none of
+// the name's nameservers answered, and when a target cannot be
+// followed, as when no nameserver of a zone in its chain 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
+	targets := make(map[string]bool)
+
+	for _, nsState := range current.RecordsByNameserver {
+		if nsState.Status != statusOK {
+			continue
+		}
+
+		answered = true
+
+		if len(nsState.Records["A"]) > 0 || len(nsState.Records["AAAA"]) > 0 {
+			return
+		}
+
+		for _, target := range nsState.Records["CNAME"] {
+			targets[target] = true
+		}
+	}
+
+	if !answered {
+		current.CNAMEAddresses = prevAddresses
+
+		return
+	}
+
+	for target := range targets {
+		ips, err := w.resolver.ResolveIPAddresses(ctx, target)
+		if err != nil {
+			w.log.Error(
+				"failed to follow CNAME",
+				"hostname", hostname,
+				"target", target,
+				"error", err,
+			)
+
+			current.CNAMEAddresses = prevAddresses
+
+			return
+		}
+
+		current.CNAMEAddresses = append(current.CNAMEAddresses, ips...)
+	}
+
+	// Still the empty list when every chain ends in no address.
+	slices.Sort(current.CNAMEAddresses)
+	current.CNAMEAddresses = slices.Compact(current.CNAMEAddresses)
+}
+
 // 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 +516,37 @@ 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 +843,9 @@ 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 +864,10 @@ 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

@@ -312,7 +312,8 @@ func lookupNameservers(t *testing.T, name 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
 
@@ -321,7 +322,7 @@ 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
@@ -371,6 +372,14 @@ func TestFirstRunBaseline(t *testing.T) {
 
 	assertNoNotifications(t, deps)
 	assertStatePopulated(t, deps)
+
+	// testHost answers with an address, so the check saves an empty list
+	// of CNAME addresses for it; nil would mean the check did not look
+	// at whether to follow a CNAME.
+	hs, _ := deps.state.GetHostnameState(testHost)
+	if hs.CNAMEAddresses == nil || len(hs.CNAMEAddresses) != 0 {
+		t.Errorf("saved CNAME addresses %#v, want []", hs.CNAMEAddresses)
+	}
 }
 
 func assertNoNotifications(