resolver: ask again over TCP when a reply offers recursion (closes #300)

dnswatcher never asks for recursion, so a reply marked recursion
available comes from a resolver on the network answering in the
server's place, as on a network that sends all DNS to one resolver.
Such a resolver answers only from its cache, or with SERVFAIL or
REFUSED, which made make check fail there.

A reply over UDP marked so is now asked again over TCP, which many such
networks leave alone, and the TCP reply is used. A reply from a root
server's address still marked so is not used, and when every root
server refuses or gives one, the error is the existing "this network
intercepts DNS queries".

Model: opus-5-5

README.md

@@ -561,6 +561,17 @@ This approach ensures:
 - Ability to detect split-horizon or inconsistent responses across authoritative
   servers.
 
+dnswatcher never asks a server for recursion, so a reply marked "recursion
+available" did not come from the server it was sent to. It came from a recursive
+resolver on the network answering in that server's place, as on a network where
+a router rule, a VPN or a DNS filter sends all DNS to one resolver. Such a query
+is sent again over TCP, which many of those networks leave alone, and the reply
+over TCP is used; when that retry fails, the reply over UDP is kept. A root
+server never offers recursion, so a reply from a root server's address that is
+still marked so after that is passed over. When every root server refuses a
+query or gives such a reply, the lookup fails with the error "this network
+intercepts DNS queries".
+
 A watched name's records are stored as its nameservers return them, CNAME
 included. When they return a CNAME and no address, the chain of every CNAME
 target they gave is followed (with a depth limit to prevent loops) to the A and

TODO.md

@@ -19,6 +19,10 @@ milestone: https://git.eeqj.de/sneak/dnswatcher/milestone/7
 
 # Completed Steps
 
+- 2026-10-16: a reply over UDP marked "recursion available" is asked again over
+  TCP; such a reply from a root server's address is not used, and when every
+  root server refuses or gives one, the error is "this network intercepts DNS
+  queries" (closes #300).
 - 2026-10-15: a query its caller's context ends before it is sent records no
   reason about the nameserver, and a try the context's deadline cuts short is a
   timeout, so a nameserver whose only failures were timeouts is `timeout`, not a

internal/resolver/errors.go

@@ -53,9 +53,18 @@ var (
 		"reply truncated and its retry over TCP failed",
 	)
 
+	// ErrRecursionAvailable is the reason a reply from a root server
+	// marked recursion available is not used. Root servers offer no
+	// recursion, so the reply came from something on the network
+	// answering in their place.
+	ErrRecursionAvailable = errors.New(
+		"reply marked recursion available, so not from a root server",
+	)
+
 	// ErrIntercepted is returned when every root server refused a
-	// query. Root servers refuse no query, so the refusals came from
+	// query or gave a reply marked recursion available. Root servers do
-	// something on the network answering in their place.
+	// neither, so those replies came from something on the network
+	// answering in their place.
 	ErrIntercepted = errors.New("this network intercepts DNS queries")
 
 	// ErrCNAMEDepthExceeded is returned when a CNAME chain

internal/resolver/iterative.go

@@ -94,15 +94,18 @@ func (r *Resolver) tryExchange(
 }
 
 // retryTCP returns the reply to msg over TCP when resp, its reply over
-// UDP, is truncated. When that fails it returns resp, still truncated,
+// UDP, is truncated or marked recursion available. msg does not ask for
-// which holds only the records that fit.
+// recursion, so a reply marked so came from a recursive resolver on the
+// network answering in the server's place, and many networks that send
+// DNS to one do so only for UDP. When the retry fails it returns resp;
+// a truncated one holds only the records that fit.
 func (r *Resolver) retryTCP(
 	ctx context.Context,
 	msg *dns.Msg,
 	addr string,
 	resp *dns.Msg,
 ) *dns.Msg {
-	if !resp.Truncated {
+	if !resp.Truncated && !resp.RecursionAvailable {
 		return resp
 	}
 
@@ -115,7 +118,9 @@ func (r *Resolver) retryTCP(
 }
 
 // queryDNS sends a DNS query to a specific server IP, never asking it
-// for recursion. A reply of REFUSED is returned as ErrRefused.
+// for recursion. When the reply over UDP is truncated or marked
+// recursion available, the query is sent again over TCP (see retryTCP).
+// A reply of REFUSED is returned as ErrRefused.
 func (r *Resolver) queryDNS(
 	ctx context.Context,
 	serverIP string,
@@ -138,13 +143,15 @@ func (r *Resolver) queryDNS(
 		return nil, fmt.Errorf("query %s @%s: %w", name, serverIP, err)
 	}
 
+	resp = r.retryTCP(ctx, msg, addr, resp)
+
 	if resp.Rcode == dns.RcodeRefused {
 		return nil, fmt.Errorf(
 			"query %s @%s: %w", name, serverIP, ErrRefused,
 		)
 	}
 
-	return r.retryTCP(ctx, msg, addr, resp), nil
+	return resp, nil
 }
 
 func extractNSSet(rrs []dns.RR) []string {
@@ -284,10 +291,11 @@ func shuffled(
 }
 
 // queryServers asks servers, the servers of zone, about name in a random
-// order until one gives a usable reply. A server that times out, refuses
+// order until one gives a reply it uses (see replyError). A server that
-// or gives a reply that is not usable is passed over for the next. When
+// times out, refuses or gives a reply it does not use is passed over for
-// every server refused, the error says so, and when they are the root
+// the next. When every server refused, the error says so. When they are
-// servers it is ErrIntercepted.
+// the root servers and each one refused or gave a reply marked recursion
+// available, the error is ErrIntercepted.
 func (r *Resolver) queryServers(
 	ctx context.Context,
 	servers []string,
@@ -298,6 +306,7 @@ func (r *Resolver) queryServers(
 	var lastErr error
 
 	refused := 0
+	recursionAvailable := 0
 
 	for _, ip := range shuffled(servers, rand.Shuffle) {
 		if checkCtx(ctx) != nil {
@@ -305,10 +314,8 @@ func (r *Resolver) queryServers(
 		}
 
 		resp, err := r.queryDNS(ctx, ip, name, qtype)
-		if err == nil && !usableReply(resp, zone, name) {
+		if err == nil {
-			err = fmt.Errorf(
+			err = replyError(resp, ip, zone, name)
-				"query %s @%s: %w", name, ip, ErrUnusableReply,
-			)
 		}
 
 		if err == nil {
@@ -319,6 +326,10 @@ func (r *Resolver) queryServers(
 			refused++
 		}
 
+		if errors.Is(err, ErrRecursionAvailable) {
+			recursionAvailable++
+		}
+
 		lastErr = err
 	}
 
@@ -329,6 +340,14 @@ func (r *Resolver) queryServers(
 		)
 	}
 
+	if refused+recursionAvailable == len(servers) && zone == "." {
+		return nil, fmt.Errorf(
+			"every root server refused a query for %s or gave a reply "+
+				"marked recursion available: %w",
+			name, ErrIntercepted,
+		)
+	}
+
 	if refused == len(servers) {
 		return nil, fmt.Errorf(
 			"every server of %s refused a query for %s: %w",
@@ -339,6 +358,27 @@ func (r *Resolver) queryServers(
 	return nil, fmt.Errorf("all servers failed: %w", lastErr)
 }
 
+// replyError returns why resp, the reply of the server at ip, one of the
+// servers of zone, to a query about name, is not used, or nil when it
+// is. A reply that is not usable is not used. Nor is a reply from a root
+// server marked recursion available: root servers offer no recursion,
+// so it came from something on the network answering in their place.
+func replyError(resp *dns.Msg, ip string, zone string, name string) error {
+	if zone == "." && resp.RecursionAvailable {
+		return fmt.Errorf(
+			"query %s @%s: %w", name, ip, ErrRecursionAvailable,
+		)
+	}
+
+	if !usableReply(resp, zone, name) {
+		return fmt.Errorf(
+			"query %s @%s: %w", name, ip, ErrUnusableReply,
+		)
+	}
+
+	return nil
+}
+
 // isErrorReply reports whether msg is an error reply: one with any code
 // but NOERROR and NXDOMAIN, such as SERVFAIL, NOTIMP or FORMERR. An error
 // reply says nothing about the name's records.

internal/resolver/resolver_test.go

@@ -850,6 +850,55 @@ func TestQueryServers_NotEveryRootServerRefused(t *testing.T) {
 	require.NotContains(t, err.Error(), "refused a query for")
 }
 
+// TestQueryServers_RecursiveResolversAsRootServers passes public
+// recursive resolvers of four operators to QueryServers as the servers
+// of the root zone, as a network that sends every DNS query to a
+// resolver would. Over UDP and over TCP alike, they mark every reply
+// recursion available, which no root server does. Each refuses the
+// query, replies SERVFAIL, or answers from its cache, as 1.1.1.1 does
+// for com.: a reply that would be used if a root server gave it. Either
+// way the error is ErrIntercepted, and since 1.1.1.1 and 8.8.8.8 refuse
+// no such query, it says a reply was marked recursion available.
+func TestQueryServers_RecursiveResolversAsRootServers(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	resolvers := []string{
+		"1.1.1.1", "8.8.8.8", "9.9.9.9", "208.67.222.222",
+	}
+
+	for _, name := range []string{"com.", "desec.io."} {
+		var err error
+
+		livednstest.Retry(
+			t,
+			"QueryServers(public recursive resolvers as root servers, "+
+				name+")",
+			func(ctx context.Context) error {
+				_, err = r.QueryServers(ctx, resolvers, ".", name, dns.TypeNS)
+
+				// When the error is another, one resolver may have given
+				// no reply at all, so the attempt is tried again.
+				if err != nil && !errors.Is(err, resolver.ErrIntercepted) {
+					return fmt.Errorf(
+						"%w: %w", livednstest.ErrNoAnswer, err,
+					)
+				}
+
+				return nil
+			},
+		)
+
+		require.ErrorIs(t, err, resolver.ErrIntercepted)
+		require.EqualError(
+			t, err,
+			"every root server refused a query for "+name+" or gave a "+
+				"reply marked recursion available: "+
+				"this network intercepts DNS queries",
+		)
+	}
+}
+
 func TestQueryNameserver_RecordsSorted(t *testing.T) {
 	t.Parallel()