TCPCT part 1d: define TCP cookie option, extend existing struct's

Data structures are carefully composed to require minimal additions.
For example, the struct tcp_options_received cookie_plus variable fits
between existing 16-bit and 8-bit variables, requiring no additional
space (taking alignment into consideration).  There are no additions to
tcp_request_sock, and only 1 pointer in tcp_sock.

This is a significantly revised implementation of an earlier (year-old)
patch that no longer applies cleanly, with permission of the original
author (Adam Langley):

    http://thread.gmane.org/gmane.linux.network/102586

The principle difference is using a TCP option to carry the cookie nonce,
instead of a user configured offset in the data.  This is more flexible and
less subject to user configuration error.  Such a cookie option has been
suggested for many years, and is also useful without SYN data, allowing
several related concepts to use the same extension option.

    "Re: SYN floods (was: does history repeat itself?)", September 9, 1996.
    http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html

    "Re: what a new TCP header might look like", May 12, 1998.
    ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail

These functions will also be used in subsequent patches that implement
additional features.

Requires:
   TCPCT part 1a: add request_values parameter for sending SYNACK
   TCPCT part 1b: generate Responder Cookie secret
   TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS

Signed-off-by: William.Allen.Simpson@gmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 71 insertions, 8 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 649a36d99c73..a2bcac9b388e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1833,6 +1833,19 @@ static int tcp_v4_init_sock(struct sock *sk)
 	tp->af_specific = &tcp_sock_ipv4_specific;
 #endif
 
+	/* TCP Cookie Transactions */
+	if (sysctl_tcp_cookie_size > 0) {
+		/* Default, cookies without s_data_payload. */
+		tp->cookie_values =
+			kzalloc(sizeof(*tp->cookie_values),
+				sk->sk_allocation);
+		if (tp->cookie_values != NULL)
+			kref_init(&tp->cookie_values->kref);
+	}
+	/* Presumed zeroed, in order of appearance:
+	 *	cookie_in_always, cookie_out_never,
+	 *	s_data_constant, s_data_in, s_data_out
+	 */
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
@@ -1886,6 +1899,13 @@ void tcp_v4_destroy_sock(struct sock *sk)
 		sk->sk_sndmsg_page = NULL;
 	}
 
+	/* TCP Cookie Transactions */
+	if (tp->cookie_values != NULL) {
+		kref_put(&tp->cookie_values->kref,
+			 tcp_cookie_values_release);
+		tp->cookie_values = NULL;
+	}
+
 	percpu_counter_dec(&tcp_sockets_allocated);
 }
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index d3f6bbfc76f0..96852af43ca7 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -383,14 +383,43 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		const struct inet_request_sock *ireq = inet_rsk(req);
 		struct tcp_request_sock *treq = tcp_rsk(req);
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
-		struct tcp_sock *newtp;
+		struct tcp_sock *newtp = tcp_sk(newsk);
+		struct tcp_sock *oldtp = tcp_sk(sk);
+		struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
+
+		/* TCP Cookie Transactions require space for the cookie pair,
+		 * as it differs for each connection.  There is no need to
+		 * copy any s_data_payload stored at the original socket.
+		 * Failure will prevent resuming the connection.
+		 *
+		 * Presumed copied, in order of appearance:
+		 *	cookie_in_always, cookie_out_never
+		 */
+		if (oldcvp != NULL) {
+			struct tcp_cookie_values *newcvp =
+				kzalloc(sizeof(*newtp->cookie_values),
+					GFP_ATOMIC);
+
+			if (newcvp != NULL) {
+				kref_init(&newcvp->kref);
+				newcvp->cookie_desired =
+						oldcvp->cookie_desired;
+				newtp->cookie_values = newcvp;
+			} else {
+				/* Not Yet Implemented */
+				newtp->cookie_values = NULL;
+			}
+		}
 
 		/* Now setup tcp_sock */
-		newtp = tcp_sk(newsk);
 		newtp->pred_flags = 0;
-		newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1;
-		newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1;
-		newtp->snd_up = treq->snt_isn + 1;
+
+		newtp->rcv_wup = newtp->copied_seq =
+		newtp->rcv_nxt = treq->rcv_isn + 1;
+
+		newtp->snd_sml = newtp->snd_una =
+		newtp->snd_nxt = newtp->snd_up =
+			treq->snt_isn + 1 + tcp_s_data_size(oldtp);
 
 		tcp_prequeue_init(newtp);
 
@@ -423,8 +452,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		tcp_set_ca_state(newsk, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
 		skb_queue_head_init(&newtp->out_of_order_queue);
-		newtp->write_seq = treq->snt_isn + 1;
-		newtp->pushed_seq = newtp->write_seq;
+		newtp->write_seq = newtp->pushed_seq =
+			treq->snt_isn + 1 + tcp_s_data_size(oldtp);
 
 		newtp->rx_opt.saw_tstamp = 0;
 
@@ -590,7 +619,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	 * Invalid ACK: reset will be sent by listening socket
 	 */
 	if ((flg & TCP_FLAG_ACK) &&
-	    (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1))
+	    (TCP_SKB_CB(skb)->ack_seq !=
+	     tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk))))
 		return sk;
 
 	/* Also, it would be not so bad idea to check rcv_tsecr, which
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index da6e24416d75..f2ec38289a4a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1864,6 +1864,19 @@ static int tcp_v6_init_sock(struct sock *sk)
 	tp->af_specific = &tcp_sock_ipv6_specific;
 #endif
 
+	/* TCP Cookie Transactions */
+	if (sysctl_tcp_cookie_size > 0) {
+		/* Default, cookies without s_data_payload. */
+		tp->cookie_values =
+			kzalloc(sizeof(*tp->cookie_values),
+				sk->sk_allocation);
+		if (tp->cookie_values != NULL)
+			kref_init(&tp->cookie_values->kref);
+	}
+	/* Presumed zeroed, in order of appearance:
+	 *	cookie_in_always, cookie_out_never,
+	 *	s_data_constant, s_data_in, s_data_out
+	 */
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];