tcp: RFC7413 option support for Fast Open client

Fast Open has been using an experimental option with a magic number
(RFC6994). This patch makes the client by default use the RFC7413
option (34) to get and send Fast Open cookies.  This patch makes
the client solicit cookies from a given server first with the
RFC7413 option. If that fails to elicit a cookie, then it tries
the RFC6994 experimental option. If that also fails, it uses the
RFC7413 option on all subsequent connect attempts.  If the server
returns a Fast Open cookie then the client caches the form of the
option that successfully elicited a cookie, and uses that form on
later connects when it presents that cookie.

The idea is to gradually obsolete the use of experimental options as
the servers and clients upgrade, while keeping the interoperability
meanwhile.

Signed-off-by: Daniel Lee <Longinus00@gmail.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 36 insertions, 14 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 24f1630b2afb..031cf72cd05c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5378,8 +5378,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL;
-	u16 mss = tp->rx_opt.mss_clamp;
-	bool syn_drop;
+	u16 mss = tp->rx_opt.mss_clamp, try_exp = 0;
+	bool syn_drop = false;
 
 	if (mss == tp->rx_opt.user_mss) {
 		struct tcp_options_received opt;
@@ -5391,16 +5391,25 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 		mss = opt.mss_clamp;
 	}
 
-	if (!tp->syn_fastopen)  /* Ignore an unsolicited cookie */
+	if (!tp->syn_fastopen) {
+		/* Ignore an unsolicited cookie */
 		cookie->len = -1;
+	} else if (tp->total_retrans) {
+		/* SYN timed out and the SYN-ACK neither has a cookie nor
+		 * acknowledges data. Presumably the remote received only
+		 * the retransmitted (regular) SYNs: either the original
+		 * SYN-data or the corresponding SYN-ACK was dropped.
+		 */
+		syn_drop = (cookie->len < 0 && data);
+	} else if (cookie->len < 0 && !tp->syn_data) {
+		/* We requested a cookie but didn't get it. If we did not use
+		 * the (old) exp opt format then try so next time (try_exp=1).
+		 * Otherwise we go back to use the RFC7413 opt (try_exp=2).
+		 */
+		try_exp = tp->syn_fastopen_exp ? 2 : 1;
+	}
 
-	/* The SYN-ACK neither has cookie nor acknowledges the data. Presumably
-	 * the remote receives only the retransmitted (regular) SYNs: either
-	 * the original SYN-data or the corresponding SYN-ACK is lost.
-	 */
-	syn_drop = (cookie->len <= 0 && data && tp->total_retrans);
-
-	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop);
+	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
 
 	if (data) { /* Retransmit unacked data in SYN */
 		tcp_for_write_queue_from(data, sk) {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 78ecc4a01712..a51d63a43e33 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -28,7 +28,8 @@ static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *s
 
 struct tcp_fastopen_metrics {
 	u16	mss;
-	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
+	u16	syn_loss:10,		/* Recurring Fast Open SYN losses */
+		try_exp:2;		/* Request w/ exp. option (once) */
 	unsigned long	last_syn_loss;	/* Last Fast Open SYN loss */
 	struct	tcp_fastopen_cookie	cookie;
 };
@@ -131,6 +132,8 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
 	if (fastopen_clear) {
 		tm->tcpm_fastopen.mss = 0;
 		tm->tcpm_fastopen.syn_loss = 0;
+		tm->tcpm_fastopen.try_exp = 0;
+		tm->tcpm_fastopen.cookie.exp = false;
 		tm->tcpm_fastopen.cookie.len = 0;
 	}
 }
@@ -713,6 +716,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
 			if (tfom->mss)
 				*mss = tfom->mss;
 			*cookie = tfom->cookie;
+			if (cookie->len <= 0 && tfom->try_exp == 1)
+				cookie->exp = true;
 			*syn_loss = tfom->syn_loss;
 			*last_syn_loss = *syn_loss ? tfom->last_syn_loss : 0;
 		} while (read_seqretry(&fastopen_seqlock, seq));
@@ -721,7 +726,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
 }
 
 void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
-			    struct tcp_fastopen_cookie *cookie, bool syn_lost)
+			    struct tcp_fastopen_cookie *cookie, bool syn_lost,
+			    u16 try_exp)
 {
 	struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_metrics_block *tm;
@@ -738,6 +744,9 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
 			tfom->mss = mss;
 		if (cookie && cookie->len > 0)
 			tfom->cookie = *cookie;
+		else if (try_exp > tfom->try_exp &&
+			 tfom->cookie.len <= 0 && !tfom->cookie.exp)
+			tfom->try_exp = try_exp;
 		if (syn_lost) {
 			++tfom->syn_loss;
 			tfom->last_syn_loss = jiffies;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 464bd8c5de69..e662d85d1635 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -592,13 +592,17 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	}
 
 	if (fastopen && fastopen->cookie.len >= 0) {
-		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len;
+		u32 need = fastopen->cookie.len;
+
+		need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE :
+					       TCPOLEN_FASTOPEN_BASE;
 		need = (need + 3) & ~3U;  /* Align to 32 bits */
 		if (remaining >= need) {
 			opts->options |= OPTION_FAST_OPEN_COOKIE;
 			opts->fastopen_cookie = &fastopen->cookie;
 			remaining -= need;
 			tp->syn_fastopen = 1;
+			tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0;
 		}
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 2568fd282873..8c65dc147d8b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -167,7 +167,7 @@ static int tcp_write_timeout(struct sock *sk)
 		if (icsk->icsk_retransmits) {
 			dst_negative_advice(sk);
 			if (tp->syn_fastopen || tp->syn_data)
-				tcp_fastopen_cache_set(sk, 0, NULL, true);
+				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
 			if (tp->syn_data)
 				NET_INC_STATS_BH(sock_net(sk),
 						 LINUX_MIB_TCPFASTOPENACTIVEFAIL);