net/tcp: Add TCP-AO sign to outgoing packets

Using precalculated traffic keys, sign TCP segments as prescribed by
RFC5925. Per RFC, TCP header options are included in sign calculation:
"The TCP header, by default including options, and where the TCP
checksum and TCP-AO MAC fields are set to zero, all in network-
byte order." (5.1.3)

tcp_ao_hash_header() has exclude_options parameter to optionally exclude
TCP header from hash calculation, as described in RFC5925 (9.1), this is
needed for interaction with middleboxes that may change "some TCP
options". This is wired up to AO key flags and setsockopt() later.

Similarly to TCP-MD5 hash TCP segment fragments.

From this moment a user can start sending TCP-AO signed segments with
one of crypto ahash algorithms from supported by Linux kernel. It can
have a user-specified MAC length, to either save TCP option header space
or provide higher protection using a longer signature.
The inbound segments are not yet verified, TCP-AO option is ignored and
they are accepted.

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>

1 files changed, 74 insertions, 38 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9fbf1b2e2025..fa3a630f3629 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -422,6 +422,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_FAST_OPEN_COOKIE	BIT(8)
 #define OPTION_SMC		BIT(9)
 #define OPTION_MPTCP		BIT(10)
+#define OPTION_AO		BIT(11)
 
 static void smc_options_write(__be32 *ptr, u16 *options)
 {
@@ -614,19 +615,43 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
  * (but it may well be that other scenarios fail similarly).
  */
 static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
-			      struct tcp_out_options *opts)
+			      struct tcp_out_options *opts,
+			      struct tcp_key *key)
 {
 	__be32 *ptr = (__be32 *)(th + 1);
 	u16 options = opts->options;	/* mungable copy */
 
-	if (unlikely(OPTION_MD5 & options)) {
+	if (tcp_key_is_md5(key)) {
 		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
 			       (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
 		/* overload cookie hash location */
 		opts->hash_location = (__u8 *)ptr;
 		ptr += 4;
-	}
+	} else if (tcp_key_is_ao(key)) {
+#ifdef CONFIG_TCP_AO
+		struct tcp_ao_key *rnext_key;
+		struct tcp_ao_info *ao_info;
+		u8 maclen;
 
+		ao_info = rcu_dereference_check(tp->ao_info,
+				lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk));
+		rnext_key = READ_ONCE(ao_info->rnext_key);
+		if (WARN_ON_ONCE(!rnext_key))
+			goto out_ao;
+		maclen = tcp_ao_maclen(key->ao_key);
+		*ptr++ = htonl((TCPOPT_AO << 24) |
+				(tcp_ao_len(key->ao_key) << 16) |
+				(key->ao_key->sndid << 8) |
+				(rnext_key->rcvid));
+		opts->hash_location = (__u8 *)ptr;
+		ptr += maclen / sizeof(*ptr);
+		if (unlikely(maclen % sizeof(*ptr))) {
+			memset(ptr, TCPOPT_NOP, sizeof(*ptr));
+			ptr++;
+		}
+out_ao:
+#endif
+	}
 	if (unlikely(opts->mss)) {
 		*ptr++ = htonl((TCPOPT_MSS << 24) |
 			       (TCPOLEN_MSS << 16) |
@@ -767,23 +792,25 @@ static void mptcp_set_option_cond(const struct request_sock *req,
  */
 static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 				struct tcp_out_options *opts,
-				struct tcp_md5sig_key **md5)
+				struct tcp_key *key)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
 	struct tcp_fastopen_request *fastopen = tp->fastopen_req;
+	bool timestamps;
 
-	*md5 = NULL;
-#ifdef CONFIG_TCP_MD5SIG
-	if (static_branch_unlikely(&tcp_md5_needed.key) &&
-	    rcu_access_pointer(tp->md5sig_info)) {
-		*md5 = tp->af_specific->md5_lookup(sk, sk);
-		if (*md5) {
-			opts->options |= OPTION_MD5;
-			remaining -= TCPOLEN_MD5SIG_ALIGNED;
+	/* Better than switch (key.type) as it has static branches */
+	if (tcp_key_is_md5(key)) {
+		timestamps = false;
+		opts->options |= OPTION_MD5;
+		remaining -= TCPOLEN_MD5SIG_ALIGNED;
+	} else {
+		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);
 		}
 	}
-#endif
 
 	/* We always get an MSS option.  The option bytes which will be seen in
 	 * normal data packets should timestamps be used, must be in the MSS
@@ -797,7 +824,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	opts->mss = tcp_advertise_mss(sk);
 	remaining -= TCPOLEN_MSS_ALIGNED;
 
-	if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) {
+	if (likely(timestamps)) {
 		opts->options |= OPTION_TS;
 		opts->tsval = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
@@ -922,7 +949,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
  */
 static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb,
 					struct tcp_out_options *opts,
-					struct tcp_md5sig_key **md5)
+					struct tcp_key *key)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int size = 0;
@@ -930,17 +957,14 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	opts->options = 0;
 
-	*md5 = NULL;
-#ifdef CONFIG_TCP_MD5SIG
-	if (static_branch_unlikely(&tcp_md5_needed.key) &&
-	    rcu_access_pointer(tp->md5sig_info)) {
-		*md5 = tp->af_specific->md5_lookup(sk, sk);
-		if (*md5) {
-			opts->options |= OPTION_MD5;
-			size += TCPOLEN_MD5SIG_ALIGNED;
-		}
+	/* Better than switch (key.type) as it has static branches */
+	if (tcp_key_is_md5(key)) {
+		opts->options |= OPTION_MD5;
+		size += TCPOLEN_MD5SIG_ALIGNED;
+	} else if (tcp_key_is_ao(key)) {
+		opts->options |= OPTION_AO;
+		size += tcp_ao_len(key->ao_key);
 	}
-#endif
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
 		opts->options |= OPTION_TS;
@@ -1245,7 +1269,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	struct tcp_out_options opts;
 	unsigned int tcp_options_size, tcp_header_size;
 	struct sk_buff *oskb = NULL;
-	struct tcp_md5sig_key *md5;
+	struct tcp_key key;
 	struct tcphdr *th;
 	u64 prior_wstamp;
 	int err;
@@ -1277,11 +1301,11 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	tcb = TCP_SKB_CB(skb);
 	memset(&opts, 0, sizeof(opts));
 
+	tcp_get_current_key(sk, &key);
 	if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) {
-		tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5);
+		tcp_options_size = tcp_syn_options(sk, skb, &opts, &key);
 	} else {
-		tcp_options_size = tcp_established_options(sk, skb, &opts,
-							   &md5);
+		tcp_options_size = tcp_established_options(sk, skb, &opts, &key);
 		/* Force a PSH flag on all (GSO) packets to expedite GRO flush
 		 * at receiver : This slightly improve GRO performance.
 		 * Note that we do not force the PSH flag for non GSO packets,
@@ -1362,16 +1386,25 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		th->window	= htons(min(tp->rcv_wnd, 65535U));
 	}
 
-	tcp_options_write(th, tp, &opts);
+	tcp_options_write(th, tp, &opts, &key);
 
+	if (tcp_key_is_md5(&key)) {
 #ifdef CONFIG_TCP_MD5SIG
-	/* Calculate the MD5 hash, as we have all we need now */
-	if (md5) {
+		/* Calculate the MD5 hash, as we have all we need now */
 		sk_gso_disable(sk);
 		tp->af_specific->calc_md5_hash(opts.hash_location,
-					       md5, sk, skb);
-	}
+					       key.md5_key, sk, skb);
 #endif
+	} else if (tcp_key_is_ao(&key)) {
+		int err;
+
+		err = tcp_ao_transmit_skb(sk, skb, key.ao_key, th,
+					  opts.hash_location);
+		if (err) {
+			kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED);
+			return -ENOMEM;
+		}
+	}
 
 	/* BPF prog is the last one writing header option */
 	bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts);
@@ -1804,7 +1837,7 @@ unsigned int tcp_current_mss(struct sock *sk)
 	u32 mss_now;
 	unsigned int header_len;
 	struct tcp_out_options opts;
-	struct tcp_md5sig_key *md5;
+	struct tcp_key key;
 
 	mss_now = tp->mss_cache;
 
@@ -1813,8 +1846,8 @@ unsigned int tcp_current_mss(struct sock *sk)
 		if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
 			mss_now = tcp_sync_mss(sk, mtu);
 	}
-
-	header_len = tcp_established_options(sk, NULL, &opts, &md5) +
+	tcp_get_current_key(sk, &key);
+	header_len = tcp_established_options(sk, NULL, &opts, &key) +
 		     sizeof(struct tcphdr);
 	/* The mss_cache is sized based on tp->tcp_header_len, which assumes
 	 * some common options. If this is an odd packet (because we have SACK
@@ -3613,6 +3646,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *md5 = NULL;
 	struct tcp_out_options opts;
+	struct tcp_key key = {};
 	struct sk_buff *skb;
 	int tcp_header_size;
 	struct tcphdr *th;
@@ -3667,6 +3701,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 #ifdef CONFIG_TCP_MD5SIG
 	rcu_read_lock();
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
+	if (md5)
+		key.type = TCP_KEY_MD5;
 #endif
 	skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4);
 	/* bpf program will be interested in the tcp_flags */
@@ -3693,7 +3729,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
 	th->window = htons(min(req->rsk_rcv_wnd, 65535U));
-	tcp_options_write(th, NULL, &opts);
+	tcp_options_write(th, NULL, &opts, &key);
 	th->doff = (tcp_header_size >> 2);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);