[PATCH v2 3/7] net-tcp: Fast Open client - sending SYN-data

[Yuchung Cheng <ycheng@google.com>]

This patch implements sending SYN-data in tcp_connect(). The data is
from tcp_sendmsg() with flag MSG_FASTOPEN (implemented in a later patch).

The length of the cookie in tcp_fastopen_req, init'd to 0, controls the
type of the SYN. If the cookie is not cached (len==0), the host sends
data-less SYN with Fast Open cookie request option to solicit a cookie
from the remote. If cookie is not available (len > 0), the host sends
a SYN-data with Fast Open cookie option. If cookie length is negative,
  the SYN will not include any Fast Open option (for fall back operations).

To deal with middleboxes that may drop SYN with data or experimental TCP
option, the SYN-data is only sent once. SYN retransmits do not include
data or Fast Open options. The connection will fall back to regular TCP
handshake.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
 include/linux/snmp.h  |    1 +
 include/linux/tcp.h   |    6 ++-
 include/net/tcp.h     |    9 ++++
 net/ipv4/af_inet.c    |    7 +++
 net/ipv4/proc.c       |    1 +
 net/ipv4/tcp_output.c |  115 +++++++++++++++++++++++++++++++++++++++++++++----
 6 files changed, 129 insertions(+), 10 deletions(-)

diff --git a/include/linux/snmp.h b/include/linux/snmp.h
index e5fcbd0..00bc189 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -238,6 +238,7 @@ enum
 	LINUX_MIB_TCPOFOMERGE,			/* TCPOFOMerge */
 	LINUX_MIB_TCPCHALLENGEACK,		/* TCPChallengeACK */
 	LINUX_MIB_TCPSYNCHALLENGE,		/* TCPSYNChallenge */
+	LINUX_MIB_TCPFASTOPENACTIVE,		/* TCPFastOpenActive */
 	__LINUX_MIB_MAX
 };
 
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 12948f5..1edf96a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -386,7 +386,8 @@ struct tcp_sock {
 		unused      : 1;
 	u8	repair_queue;
 	u8	do_early_retrans:1,/* Enable RFC5827 early-retransmit  */
-		early_retrans_delayed:1; /* Delayed ER timer installed */
+		early_retrans_delayed:1, /* Delayed ER timer installed */
+		syn_fastopen:1;	/* SYN includes Fast Open option */
 
 /* RTT measurement */
 	u32	srtt;		/* smoothed round trip time << 3	*/
@@ -500,6 +501,9 @@ struct tcp_sock {
 	struct tcp_md5sig_info	__rcu *md5sig_info;
 #endif
 
+/* TCP fastopen related information */
+	struct tcp_fastopen_request *fastopen_req;
+
 	/* When the cookie options are generated and exchanged, then this
 	 * object holds a reference to them (cookie_values->kref).  Also
 	 * contains related tcp_cookie_transactions fields.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e601da1..867557b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1289,6 +1289,15 @@ extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff
 extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
 			    const struct tcp_md5sig_key *key);
 
+struct tcp_fastopen_request {
+	/* Fast Open cookie. Size 0 means a cookie request */
+	struct tcp_fastopen_cookie	cookie;
+	struct msghdr			*data;  /* data in MSG_FASTOPEN */
+	u16				copied;	/* queued in tcp_connect() */
+};
+
+void tcp_free_fastopen_req(struct tcp_sock *tp);
+
 /* write queue abstraction */
 static inline void tcp_write_queue_purge(struct sock *sk)
 {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 07a02f6..6ef67b7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -558,9 +558,14 @@ EXPORT_SYMBOL(inet_dgram_connect);
 
 static long inet_wait_for_connect(struct sock *sk, long timeo)
 {
+	const bool write = (sk->sk_protocol == IPPROTO_TCP) &&
+			   tcp_sk(sk)->fastopen_req &&
+			   tcp_sk(sk)->fastopen_req->data;
 	DEFINE_WAIT(wait);
 
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+	if (write)
+		sk->sk_write_pending++;
 
 	/* Basic assumption: if someone sets sk->sk_err, he _must_
 	 * change state of the socket from TCP_SYN_*.
@@ -576,6 +581,8 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	}
 	finish_wait(sk_sleep(sk), &wait);
+	if (write)
+		sk->sk_write_pending--;
 	return timeo;
 }
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 2a5240b..957acd1 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -262,6 +262,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE),
 	SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
 	SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE),
+	SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4849be7..8869328 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -596,6 +596,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
 			 tcp_cookie_size_check(cvp->cookie_desired) :
 			 0;
+	struct tcp_fastopen_request *fastopen = tp->fastopen_req;
 
 #ifdef CONFIG_TCP_MD5SIG
 	*md5 = tp->af_specific->md5_lookup(sk, sk);
@@ -636,6 +637,16 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 			remaining -= TCPOLEN_SACKPERM_ALIGNED;
 	}
 
+	if (fastopen && fastopen->cookie.len >= 0) {
+		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len;
+		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;
+		}
+	}
 	/* Note that timestamps are required by the specification.
 	 *
 	 * Odd numbers of bytes are prohibited by the specification, ensuring
@@ -2824,6 +2835,96 @@ void tcp_connect_init(struct sock *sk)
 	tcp_clear_retrans(tp);
 }
 
+static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+
+	tcb->end_seq += skb->len;
+	skb_header_release(skb);
+	__tcp_add_write_queue_tail(sk, skb);
+	sk->sk_wmem_queued += skb->truesize;
+	sk_mem_charge(sk, skb->truesize);
+	tp->write_seq = tcb->end_seq;
+	tp->packets_out += tcp_skb_pcount(skb);
+}
+
+/* Build and send a SYN with data and (cached) Fast Open cookie. However,
+ * queue a data-only packet after the regular SYN, such that regular SYNs
+ * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges
+ * only the SYN sequence, the data are retransmitted in the first ACK.
+ * If cookie is not cached or other error occurs, falls back to send a
+ * regular SYN with Fast Open cookie request option.
+ */
+static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcp_fastopen_request *fo = tp->fastopen_req;
+	int space, i, err = 0, iovlen = fo->data->msg_iovlen;
+	struct sk_buff *syn_data = NULL, *data;
+
+	tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie);
+	if (fo->cookie.len <= 0)
+		goto fallback;
+
+	/* MSS for SYN-data is based on cached MSS and bounded by PMTU and
+	 * user-MSS. Reserve maximum option space for middleboxes that add
+	 * private TCP options. The cost is reduced data space in SYN :(
+	 */
+	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp)
+		tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
+	space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+		MAX_TCP_OPTION_SPACE;
+
+	syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+				   sk->sk_allocation);
+	if (syn_data == NULL)
+		goto fallback;
+
+	for (i = 0; i < iovlen && syn_data->len < space; ++i) {
+		struct iovec *iov = &fo->data->msg_iov[i];
+		unsigned char __user *from = iov->iov_base;
+		int len = iov->iov_len;
+
+		if (syn_data->len + len > space)
+			len = space - syn_data->len;
+		else if (i + 1 == iovlen)
+			/* No more data pending in inet_wait_for_connect() */
+			fo->data = NULL;
+
+		if (skb_add_data(syn_data, from, len))
+			goto fallback;
+	}
+
+	/* Queue a data-only packet after the regular SYN for retransmission */
+	data = pskb_copy(syn_data, sk->sk_allocation);
+	if (data == NULL)
+		goto fallback;
+	TCP_SKB_CB(data)->seq++;
+	TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN;
+	TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH);
+	tcp_connect_queue_skb(sk, data);
+	fo->copied = data->len;
+
+	if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
+		goto done;
+	}
+	syn_data = NULL;
+
+fallback:
+	/* Send a regular SYN with Fast Open cookie request option */
+	if (fo->cookie.len > 0)
+		fo->cookie.len = 0;
+	err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation);
+	if (err)
+		tp->syn_fastopen = 0;
+	kfree_skb(syn_data);
+done:
+	fo->cookie.len = -1;  /* Exclude Fast Open option for SYN retries */
+	return err;
+}
+
 /* Build a SYN and send it off. */
 int tcp_connect(struct sock *sk)
 {
@@ -2841,17 +2942,13 @@ int tcp_connect(struct sock *sk)
 	skb_reserve(buff, MAX_TCP_HEADER);
 
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
+	tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp;
+	tcp_connect_queue_skb(sk, buff);
 	TCP_ECN_send_syn(sk, buff);
 
-	/* Send it off. */
-	TCP_SKB_CB(buff)->when = tcp_time_stamp;
-	tp->retrans_stamp = TCP_SKB_CB(buff)->when;
-	skb_header_release(buff);
-	__tcp_add_write_queue_tail(sk, buff);
-	sk->sk_wmem_queued += buff->truesize;
-	sk_mem_charge(sk, buff->truesize);
-	tp->packets_out += tcp_skb_pcount(buff);
-	err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
+	/* Send off SYN; include data in Fast Open. */
+	err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) :
+	      tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
 	if (err == -ECONNREFUSED)
 		return err;
 
-- 
1.7.7.3