net/tcp: Add TCP-AO SNE support

Add Sequence Number Extension (SNE) for TCP-AO.
This is needed to protect long-living TCP-AO connections from replaying
attacks after sequence number roll-over, see RFC5925 (6.2).

Co-developed-by: Francesco Ruggeri <fruggeri@arista.com>
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Co-developed-by: Salam Noureddine <noureddine@arista.com>
Signed-off-by: Salam Noureddine <noureddine@arista.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Acked-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 81 insertions, 11 deletions

diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 1097e99a9ad6..7e14bcd4dfd4 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -401,6 +401,21 @@ static int tcp_ao_hash_pseudoheader(unsigned short int family,
 	return -EAFNOSUPPORT;
 }
 
+u32 tcp_ao_compute_sne(u32 next_sne, u32 next_seq, u32 seq)
+{
+	u32 sne = next_sne;
+
+	if (before(seq, next_seq)) {
+		if (seq > next_seq)
+			sne--;
+	} else {
+		if (seq < next_seq)
+			sne++;
+	}
+
+	return sne;
+}
+
 /* tcp_ao_hash_sne(struct tcp_sigpool *hp)
  * @hp	- used for hashing
  * @sne - sne value
@@ -611,7 +626,7 @@ struct tcp_ao_key *tcp_v4_ao_lookup(const struct sock *sk, struct sock *addr_sk,
 }
 
 int tcp_ao_prepare_reset(const struct sock *sk, struct sk_buff *skb,
-			 const struct tcp_ao_hdr *aoh, int l3index,
+			 const struct tcp_ao_hdr *aoh, int l3index, u32 seq,
 			 struct tcp_ao_key **key, char **traffic_key,
 			 bool *allocated_traffic_key, u8 *keyid, u32 *sne)
 {
@@ -639,7 +654,7 @@ int tcp_ao_prepare_reset(const struct sock *sk, struct sk_buff *skb,
 
 			sisn = htonl(tcp_rsk(req)->rcv_isn);
 			disn = htonl(tcp_rsk(req)->snt_isn);
-			*sne = 0;
+			*sne = tcp_ao_compute_sne(0, tcp_rsk(req)->snt_isn, seq);
 		} else {
 			sisn = th->seq;
 			disn = 0;
@@ -670,11 +685,15 @@ int tcp_ao_prepare_reset(const struct sock *sk, struct sk_buff *skb,
 		*keyid = (*key)->rcvid;
 	} else {
 		struct tcp_ao_key *rnext_key;
+		u32 snd_basis;
 
-		if (sk->sk_state == TCP_TIME_WAIT)
+		if (sk->sk_state == TCP_TIME_WAIT) {
 			ao_info = rcu_dereference(tcp_twsk(sk)->ao_info);
-		else
+			snd_basis = tcp_twsk(sk)->tw_snd_nxt;
+		} else {
 			ao_info = rcu_dereference(tcp_sk(sk)->ao_info);
+			snd_basis = tcp_sk(sk)->snd_una;
+		}
 		if (!ao_info)
 			return -ENOENT;
 
@@ -684,7 +703,8 @@ int tcp_ao_prepare_reset(const struct sock *sk, struct sk_buff *skb,
 		*traffic_key = snd_other_key(*key);
 		rnext_key = READ_ONCE(ao_info->rnext_key);
 		*keyid = rnext_key->rcvid;
-		*sne = 0;
+		*sne = tcp_ao_compute_sne(READ_ONCE(ao_info->snd_sne),
+					  snd_basis, seq);
 	}
 	return 0;
 }
@@ -698,6 +718,7 @@ int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	struct tcp_ao_info *ao;
 	void *tkey_buf = NULL;
 	u8 *traffic_key;
+	u32 sne;
 
 	ao = rcu_dereference_protected(tcp_sk(sk)->ao_info,
 				       lockdep_sock_is_held(sk));
@@ -717,8 +738,10 @@ int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		tp->af_specific->ao_calc_key_sk(key, traffic_key,
 						sk, ao->lisn, disn, true);
 	}
+	sne = tcp_ao_compute_sne(READ_ONCE(ao->snd_sne), READ_ONCE(tp->snd_una),
+				 ntohl(th->seq));
 	tp->af_specific->calc_ao_hash(hash_location, key, sk, skb, traffic_key,
-				      hash_location - (u8 *)th, 0);
+				      hash_location - (u8 *)th, sne);
 	kfree(tkey_buf);
 	return 0;
 }
@@ -846,7 +869,8 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 		if (unlikely(th->syn && !th->ack))
 			goto verify_hash;
 
-		sne = 0;
+		sne = tcp_ao_compute_sne(info->rcv_sne, tcp_sk(sk)->rcv_nxt,
+					 ntohl(th->seq));
 		/* Established socket, traffic key are cached */
 		traffic_key = rcv_other_key(key);
 		err = tcp_ao_verify_hash(sk, skb, family, info, aoh, key,
@@ -881,14 +905,16 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb,
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) {
 		/* Make the initial syn the likely case here */
 		if (unlikely(req)) {
-			sne = 0;
+			sne = tcp_ao_compute_sne(0, tcp_rsk(req)->rcv_isn,
+						 ntohl(th->seq));
 			sisn = htonl(tcp_rsk(req)->rcv_isn);
 			disn = htonl(tcp_rsk(req)->snt_isn);
 		} else if (unlikely(th->ack && !th->syn)) {
 			/* Possible syncookie packet */
 			sisn = htonl(ntohl(th->seq) - 1);
 			disn = htonl(ntohl(th->ack_seq) - 1);
-			sne = 0;
+			sne = tcp_ao_compute_sne(0, ntohl(sisn),
+						 ntohl(th->seq));
 		} else if (unlikely(!th->syn)) {
 			/* no way to figure out initial sisn/disn - drop */
 			return SKB_DROP_REASON_TCP_FLAGS;
@@ -986,6 +1012,7 @@ void tcp_ao_connect_init(struct sock *sk)
 		tp->tcp_header_len += tcp_ao_len(key);
 
 		ao_info->lisn = htonl(tp->write_seq);
+		ao_info->snd_sne = 0;
 	} else {
 		/* Can't happen: tcp_connect() verifies that there's
 		 * at least one tcp-ao key that matches the remote peer.
@@ -1021,6 +1048,7 @@ void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb)
 		return;
 
 	WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq);
+	ao->rcv_sne = 0;
 
 	hlist_for_each_entry_rcu(key, &ao->head, node)
 		tcp_ao_cache_traffic_keys(sk, ao, key);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index de64c0c2fb69..67ca72185f14 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3576,9 +3576,18 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp,
 static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
 {
 	u32 delta = ack - tp->snd_una;
+#ifdef CONFIG_TCP_AO
+	struct tcp_ao_info *ao;
+#endif
 
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_acked += delta;
+#ifdef CONFIG_TCP_AO
+	ao = rcu_dereference_protected(tp->ao_info,
+				       lockdep_sock_is_held((struct sock *)tp));
+	if (ao && ack < tp->snd_una)
+		ao->snd_sne++;
+#endif
 	tp->snd_una = ack;
 }
 
@@ -3586,9 +3595,18 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
 static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
 {
 	u32 delta = seq - tp->rcv_nxt;
+#ifdef CONFIG_TCP_AO
+	struct tcp_ao_info *ao;
+#endif
 
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_received += delta;
+#ifdef CONFIG_TCP_AO
+	ao = rcu_dereference_protected(tp->ao_info,
+				       lockdep_sock_is_held((struct sock *)tp));
+	if (ao && seq < tp->rcv_nxt)
+		ao->rcv_sne++;
+#endif
 	WRITE_ONCE(tp->rcv_nxt, seq);
 }
 
@@ -6456,6 +6474,16 @@ consume:
 		 * simultaneous connect with crossed SYNs.
 		 * Particularly, it can be connect to self.
 		 */
+#ifdef CONFIG_TCP_AO
+		struct tcp_ao_info *ao;
+
+		ao = rcu_dereference_protected(tp->ao_info,
+					       lockdep_sock_is_held(sk));
+		if (ao) {
+			WRITE_ONCE(ao->risn, th->seq);
+			ao->rcv_sne = 0;
+		}
+#endif
 		tcp_set_state(sk, TCP_SYN_RECV);
 
 		if (tp->rx_opt.saw_tstamp) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ece95d5138e1..bdec99707028 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -676,7 +676,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb,
 	u8 keyid;
 
 	rcu_read_lock();
-	if (tcp_ao_prepare_reset(sk, skb, aoh, l3index,
+	if (tcp_ao_prepare_reset(sk, skb, aoh, l3index, ntohl(reply->seq),
 				 &key, &traffic_key, &allocated_traffic_key,
 				 &keyid, &ao_sne))
 		goto out;
@@ -1034,6 +1034,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 		struct tcp_ao_key *rnext_key;
 
 		key.traffic_key = snd_other_key(key.ao_key);
+		key.sne = READ_ONCE(ao_info->snd_sne);
 		rnext_key = READ_ONCE(ao_info->rnext_key);
 		key.rcv_next = rnext_key->rcvid;
 		key.type = TCP_KEY_AO;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 8d941a6e066b..a9807eeb311c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -51,6 +51,18 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
 	return TCP_TW_SUCCESS;
 }
 
+static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq)
+{
+#ifdef CONFIG_TCP_AO
+	struct tcp_ao_info *ao;
+
+	ao = rcu_dereference(tcptw->ao_info);
+	if (unlikely(ao && seq < tcptw->tw_rcv_nxt))
+		WRITE_ONCE(ao->rcv_sne, ao->rcv_sne + 1);
+#endif
+	tcptw->tw_rcv_nxt = seq;
+}
+
 /*
  * * Main purpose of TIME-WAIT state is to close connection gracefully,
  *   when one of ends sits in LAST-ACK or CLOSING retransmitting FIN
@@ -136,7 +148,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 
 		/* FIN arrived, enter true time-wait state. */
 		tw->tw_substate	  = TCP_TIME_WAIT;
-		tcptw->tw_rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq);
+
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent_stamp = ktime_get_seconds();
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;