Merge branch 'tcp-ao-fixes'

Dmitry Safonov says:

====================
TCP-AO fixes

Changes from v4:
- Dropped 2 patches on which there's no consensus. They will require
  more work TBD if they may made acceptable. Those are:
  o "net/tcp: Allow removing current/rnext TCP-AO keys on TCP_LISTEN sockets"
  o "net/tcp: Store SNEs + SEQs on ao_info"

Changes from v3:
- Don't restrict adding any keys on TCP-AO connection in VRF, but only
  the ones that don't match l3index (David)

Changes from v2:
- rwlocks are problematic in net code (Paolo)
  Changed the SNE code to avoid spin/rw locks on RX/TX fastpath by
  double-accounting SEQ numbers for TCP-AO enabled connections.

Changes from v1:
- Use tcp_can_repair_sock() helper to limit TCP_AO_REPAIR (Eric)
- Instead of hook to listen() syscall, allow removing current/rnext keys
  on TCP_LISTEN (addressing Eric's objection)
- Add sne_lock to protect snd_sne/rcv_sne
- Don't move used_tcp_ao in struct tcp_request_sock (Eric)

I've been working on TCP-AO key-rotation selftests and as a result
exercised some corner-cases that are not usually met in production.

Here are a bunch of semi-related fixes:
- Documentation typo (reported by Markus Elfring)
- Proper alignment for TCP-AO option in TCP header that has MAC length
  of non 4 bytes (now a selftest with randomized maclen/algorithm/etc
  passes)
- 3 uAPI restricting patches that disallow more things to userspace in
  order to prevent it shooting itself in any parts of the body
- SNEs READ_ONCE()/WRITE_ONCE() that went missing by my human factor
- Avoid storing MAC length from SYN header as SYN-ACK will use
  rnext_key.maclen (drops an extra check that fails on new selftests)
====================

Link: https://lore.kernel.org/r/
Signed-off-by: Paolo Abeni <[email protected]>

Author: Paolo Abeni

Documentation/networking/tcp_ao.rst

@@ -99,7 +99,7 @@ also [6.1]::
    when it is no longer considered permitted.
 
 Linux TCP-AO will try its best to prevent you from removing a key that's
-being used, considering it a key management failure. But sine keeping
+being used, considering it a key management failure. But since keeping
 an outdated key may become a security issue and as a peer may
 unintentionally prevent the removal of an old key by always setting
 it as RNextKeyID - a forced key removal mechanism is provided, where

include/linux/tcp.h

@@ -169,7 +169,7 @@ struct tcp_request_sock {
 #ifdef CONFIG_TCP_AO
 	u8				ao_keyid;
 	u8				ao_rcv_next;
-	u8				maclen;
+	bool				used_tcp_ao;
 #endif
 };
 
@@ -180,14 +180,10 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 
 static inline bool tcp_rsk_used_ao(const struct request_sock *req)
 {
-	/* The real length of MAC is saved in the request socket,
-	 * signing anything with zero-length makes no sense, so here is
-	 * a little hack..
-	 */
 #ifndef CONFIG_TCP_AO
 	return false;
 #else
-	return tcp_rsk(req)->maclen != 0;
+	return tcp_rsk(req)->used_tcp_ao;
 #endif
 }
 

include/net/tcp_ao.h

@@ -62,11 +62,17 @@ static inline int tcp_ao_maclen(const struct tcp_ao_key *key)
 	return key->maclen;
 }
 
+/* Use tcp_ao_len_aligned() for TCP header calculations */
 static inline int tcp_ao_len(const struct tcp_ao_key *key)
 {
 	return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr);
 }
 
+static inline int tcp_ao_len_aligned(const struct tcp_ao_key *key)
+{
+	return round_up(tcp_ao_len(key), 4);
+}
+
 static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key)
 {
 	return key->digest_size;

net/ipv4/tcp.c

@@ -3610,6 +3610,10 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case TCP_AO_REPAIR:
+		if (!tcp_can_repair_sock(sk)) {
+			err = -EPERM;
+			break;
+		}
 		err = tcp_ao_set_repair(sk, optval, optlen);
 		break;
 #ifdef CONFIG_TCP_AO
@@ -4309,6 +4313,8 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	}
 #endif
 	case TCP_AO_REPAIR:
+		if (!tcp_can_repair_sock(sk))
+			return -EPERM;
 		return tcp_ao_get_repair(sk, optval, optlen);
 	case TCP_AO_GET_KEYS:
 	case TCP_AO_INFO: {

net/ipv4/tcp_ao.c

@@ -851,7 +851,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
 	const struct tcp_ao_hdr *aoh;
 	struct tcp_ao_key *key;
 
-	treq->maclen = 0;
+	treq->used_tcp_ao = false;
 
 	if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh)
 		return;
@@ -863,7 +863,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
 
 	treq->ao_rcv_next = aoh->keyid;
 	treq->ao_keyid = aoh->rnext_keyid;
-	treq->maclen = tcp_ao_maclen(key);
+	treq->used_tcp_ao = true;
 }
 
 static enum skb_drop_reason
@@ -1100,7 +1100,7 @@ void tcp_ao_connect_init(struct sock *sk)
 			ao_info->current_key = key;
 		if (!ao_info->rnext_key)
 			ao_info->rnext_key = key;
-		tp->tcp_header_len += tcp_ao_len(key);
+		tp->tcp_header_len += tcp_ao_len_aligned(key);
 
 		ao_info->lisn = htonl(tp->write_seq);
 		ao_info->snd_sne = 0;
@@ -1346,7 +1346,7 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key)
 	syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED;
 	syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED;
 	syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED;
-	if (tcp_ao_len(key) > syn_tcp_option_space) {
+	if (tcp_ao_len_aligned(key) > syn_tcp_option_space) {
 		err = -EMSGSIZE;
 		goto err_kfree;
 	}
@@ -1608,6 +1608,15 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family,
 		if (!dev || !l3index)
 			return -EINVAL;
 
+		if (!bound_dev_if || bound_dev_if != cmd.ifindex) {
+			/* tcp_ao_established_key() doesn't expect having
+			 * non peer-matching key on an established TCP-AO
+			 * connection.
+			 */
+			if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)))
+				return -EINVAL;
+		}
+
 		/* It's still possible to bind after adding keys or even
 		 * re-bind to a different dev (with CAP_NET_RAW).
 		 * So, no reason to return error here, rather try to be

net/ipv4/tcp_input.c

@@ -7182,11 +7182,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
 		goto drop_and_release; /* Invalid TCP options */
 	if (aoh) {
-		tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr);
+		tcp_rsk(req)->used_tcp_ao = true;
 		tcp_rsk(req)->ao_rcv_next = aoh->keyid;
 		tcp_rsk(req)->ao_keyid = aoh->rnext_keyid;
+
 	} else {
-		tcp_rsk(req)->maclen = 0;
+		tcp_rsk(req)->used_tcp_ao = false;
 	}
 #endif
 	tcp_rsk(req)->snt_isn = isn;

net/ipv4/tcp_ipv4.c

@@ -690,7 +690,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb,
 
 	reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) |
 				 (aoh->rnext_keyid << 8) | keyid);
-	arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4);
+	arg->iov[0].iov_len += tcp_ao_len_aligned(key);
 	reply->doff = arg->iov[0].iov_len / 4;
 
 	if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1],
@@ -978,7 +978,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 					  (tcp_ao_len(key->ao_key) << 16) |
 					  (key->ao_key->sndid << 8) |
 					  key->rcv_next);
-		arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4);
+		arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key);
 		rep.th.doff = arg.iov[0].iov_len / 4;
 
 		tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset],

net/ipv4/tcp_minisocks.c

@@ -615,7 +615,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	ao_key = treq->af_specific->ao_lookup(sk, req,
 				tcp_rsk(req)->ao_keyid, -1);
 	if (ao_key)
-		newtp->tcp_header_len += tcp_ao_len(ao_key);
+		newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
  #endif
 	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;

net/ipv4/tcp_output.c

@@ -825,7 +825,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps);
 		if (tcp_key_is_ao(key)) {
 			opts->options |= OPTION_AO;
-			remaining -= tcp_ao_len(key->ao_key);
+			remaining -= tcp_ao_len_aligned(key->ao_key);
 		}
 	}
 
@@ -915,7 +915,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 			ireq->tstamp_ok &= !ireq->sack_ok;
 	} else if (tcp_key_is_ao(key)) {
 		opts->options |= OPTION_AO;
-		remaining -= tcp_ao_len(key->ao_key);
+		remaining -= tcp_ao_len_aligned(key->ao_key);
 		ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 
@@ -982,7 +982,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 		size += TCPOLEN_MD5SIG_ALIGNED;
 	} else if (tcp_key_is_ao(key)) {
 		opts->options |= OPTION_AO;
-		size += tcp_ao_len(key->ao_key);
+		size += tcp_ao_len_aligned(key->ao_key);
 	}
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
@@ -3720,7 +3720,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	if (tcp_rsk_used_ao(req)) {
 #ifdef CONFIG_TCP_AO
 		struct tcp_ao_key *ao_key = NULL;
-		u8 maclen = tcp_rsk(req)->maclen;
 		u8 keyid = tcp_rsk(req)->ao_keyid;
 
 		ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req),
@@ -3730,13 +3729,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 		 * for another peer-matching key, but the peer has requested
 		 * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here.
 		 */
-		if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) {
-			u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0;
-
+		if (unlikely(!ao_key)) {
 			rcu_read_unlock();
 			kfree_skb(skb);
-			net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n",
-					     keyid, maclen, key_maclen);
+			net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n",
+					     keyid);
 			return NULL;
 		}
 		key.ao_key = ao_key;

net/ipv6/tcp_ipv6.c

@@ -881,7 +881,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	if (tcp_key_is_md5(key))
 		tot_len += TCPOLEN_MD5SIG_ALIGNED;
 	if (tcp_key_is_ao(key))
-		tot_len += tcp_ao_len(key->ao_key);
+		tot_len += tcp_ao_len_aligned(key->ao_key);
 
 #ifdef CONFIG_MPTCP
 	if (rst && !tcp_key_is_md5(key)) {