tcp: Remove TCPCT

TCPCT uses option-number 253, reserved for experimental use and should
not be used in production environments.
Further, TCPCT does not fully implement RFC 6013.

As a nice side-effect, removing TCPCT increases TCP's performance for
very short flows:

Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests
for files of 1KB size.

before this patch:
	average (among 7 runs) of 20845.5 Requests/Second
after:
	average (among 7 runs) of 21403.6 Requests/Second

Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/ip-sysctl.txt

@@ -175,14 +175,6 @@ tcp_congestion_control - STRING
 	is inherited.
 	[see setsockopt(listenfd, SOL_TCP, TCP_CONGESTION, "name" ...) ]
 
-tcp_cookie_size - INTEGER
-	Default size of TCP Cookie Transactions (TCPCT) option, that may be
-	overridden on a per socket basis by the TCPCT socket option.
-	Values greater than the maximum (16) are interpreted as the maximum.
-	Values greater than zero and less than the minimum (8) are interpreted
-	as the minimum.  Odd values are interpreted as the next even value.
-	Default: 0 (off).
-
 tcp_dsack - BOOLEAN
 	Allows TCP to send "duplicate" SACKs.
 

drivers/infiniband/hw/cxgb4/cm.c

@@ -2915,7 +2915,7 @@ static void build_cpl_pass_accept_req(struct sk_buff *skb, int stid , u8 tos)
 	 */
 	memset(&tmp_opt, 0, sizeof(tmp_opt));
 	tcp_clear_options(&tmp_opt);
-	tcp_parse_options(skb, &tmp_opt, NULL, 0, NULL);
+	tcp_parse_options(skb, &tmp_opt, 0, NULL);
 
 	req = (struct cpl_pass_accept_req *)__skb_push(skb, sizeof(*req));
 	memset(req, 0, sizeof(*req));

include/linux/tcp.h

@@ -90,9 +90,6 @@ struct tcp_options_received {
 		sack_ok : 4,	/* SACK seen on SYN packet		*/
 		snd_wscale : 4,	/* Window scaling received from sender	*/
 		rcv_wscale : 4;	/* Window scaling to send to receiver	*/
-	u8	cookie_plus:6,	/* bytes in authenticator/cookie option	*/
-		cookie_out_never:1,
-		cookie_in_always:1;
 	u8	num_sacks;	/* Number of SACK blocks		*/
 	u16	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
@@ -102,7 +99,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 {
 	rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
 	rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
-	rx_opt->cookie_plus = 0;
 }
 
 /* This is the max number of SACKS that we'll generate and process. It's safe
@@ -320,12 +316,6 @@ struct tcp_sock {
 	struct tcp_md5sig_info	__rcu *md5sig_info;
 #endif
 
-	/* 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.
-	 */
-	struct tcp_cookie_values  *cookie_values;
-
 /* TCP fastopen related information */
 	struct tcp_fastopen_request *fastopen_req;
 	/* fastopen_rsk points to request_sock that resulted in this big

include/net/request_sock.h

@@ -27,19 +27,13 @@ struct sk_buff;
 struct dst_entry;
 struct proto;
 
-/* empty to "strongly type" an otherwise void parameter.
- */
-struct request_values {
-};
-
 struct request_sock_ops {
 	int		family;
 	int		obj_size;
 	struct kmem_cache	*slab;
 	char		*slab_name;
 	int		(*rtx_syn_ack)(struct sock *sk,
-				       struct request_sock *req,
-				       struct request_values *rvp);
+				       struct request_sock *req);
 	void		(*send_ack)(struct sock *sk, struct sk_buff *skb,
 				    struct request_sock *req);
 	void		(*send_reset)(struct sock *sk,

include/net/tcp.h

@@ -179,7 +179,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOPT_SACK             5       /* SACK Block */
 #define TCPOPT_TIMESTAMP	8	/* Better RTT estimations/PAWS */
 #define TCPOPT_MD5SIG		19	/* MD5 Signature (RFC2385) */
-#define TCPOPT_COOKIE		253	/* Cookie extension (experimental) */
 #define TCPOPT_EXP		254	/* Experimental */
 /* Magic number to be after the option value for sharing TCP
  * experimental options. See draft-ietf-tcpm-experimental-options-00.txt
@@ -454,7 +453,7 @@ extern void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req);
 extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		       size_t len, int nonblock, int flags, int *addr_len);
 extern void tcp_parse_options(const struct sk_buff *skb,
-			      struct tcp_options_received *opt_rx, const u8 **hvpp,
+			      struct tcp_options_received *opt_rx,
 			      int estab, struct tcp_fastopen_cookie *foc);
 extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
@@ -476,7 +475,6 @@ extern int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr,
 extern int tcp_connect(struct sock *sk);
 extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 					struct request_sock *req,
-					struct request_values *rvp,
 					struct tcp_fastopen_cookie *foc);
 extern int tcp_disconnect(struct sock *sk, int flags);
 
@@ -1589,91 +1587,6 @@ struct tcp_request_sock_ops {
 #endif
 };
 
-/* Using SHA1 for now, define some constants.
- */
-#define COOKIE_DIGEST_WORDS (SHA_DIGEST_WORDS)
-#define COOKIE_MESSAGE_WORDS (SHA_MESSAGE_BYTES / 4)
-#define COOKIE_WORKSPACE_WORDS (COOKIE_DIGEST_WORDS + COOKIE_MESSAGE_WORDS)
-
-extern int tcp_cookie_generator(u32 *bakery);
-
-/**
- *	struct tcp_cookie_values - each socket needs extra space for the
- *	cookies, together with (optional) space for any SYN data.
- *
- *	A tcp_sock contains a pointer to the current value, and this is
- *	cloned to the tcp_timewait_sock.
- *
- * @cookie_pair:	variable data from the option exchange.
- *
- * @cookie_desired:	user specified tcpct_cookie_desired.  Zero
- *			indicates default (sysctl_tcp_cookie_size).
- *			After cookie sent, remembers size of cookie.
- *			Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX.
- *
- * @s_data_desired:	user specified tcpct_s_data_desired.  When the
- *			constant payload is specified (@s_data_constant),
- *			holds its length instead.
- *			Range 0 to TCP_MSS_DESIRED.
- *
- * @s_data_payload:	constant data that is to be included in the
- *			payload of SYN or SYNACK segments when the
- *			cookie option is present.
- */
-struct tcp_cookie_values {
-	struct kref	kref;
-	u8		cookie_pair[TCP_COOKIE_PAIR_SIZE];
-	u8		cookie_pair_size;
-	u8		cookie_desired;
-	u16		s_data_desired:11,
-			s_data_constant:1,
-			s_data_in:1,
-			s_data_out:1,
-			s_data_unused:2;
-	u8		s_data_payload[0];
-};
-
-static inline void tcp_cookie_values_release(struct kref *kref)
-{
-	kfree(container_of(kref, struct tcp_cookie_values, kref));
-}
-
-/* The length of constant payload data.  Note that s_data_desired is
- * overloaded, depending on s_data_constant: either the length of constant
- * data (returned here) or the limit on variable data.
- */
-static inline int tcp_s_data_size(const struct tcp_sock *tp)
-{
-	return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant)
-		? tp->cookie_values->s_data_desired
-		: 0;
-}
-
-/**
- *	struct tcp_extend_values - tcp_ipv?.c to tcp_output.c workspace.
- *
- *	As tcp_request_sock has already been extended in other places, the
- *	only remaining method is to pass stack values along as function
- *	parameters.  These parameters are not needed after sending SYNACK.
- *
- * @cookie_bakery:	cryptographic secret and message workspace.
- *
- * @cookie_plus:	bytes in authenticator/cookie option, copied from
- *			struct tcp_options_received (above).
- */
-struct tcp_extend_values {
-	struct request_values		rv;
-	u32				cookie_bakery[COOKIE_WORKSPACE_WORDS];
-	u8				cookie_plus:6,
-					cookie_out_never:1,
-					cookie_in_always:1;
-};
-
-static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp)
-{
-	return (struct tcp_extend_values *)rvp;
-}
-
 extern void tcp_v4_init(void);
 extern void tcp_init(void);
 

include/uapi/linux/tcp.h

@@ -102,7 +102,6 @@ enum {
 #define TCP_QUICKACK		12	/* Block/reenable quick acks */
 #define TCP_CONGESTION		13	/* Congestion control algorithm */
 #define TCP_MD5SIG		14	/* TCP MD5 Signature (RFC2385) */
-#define TCP_COOKIE_TRANSACTIONS	15	/* TCP Cookie Transactions */
 #define TCP_THIN_LINEAR_TIMEOUTS 16      /* Use linear timeouts for thin streams*/
 #define TCP_THIN_DUPACK         17      /* Fast retrans. after 1 dupack */
 #define TCP_USER_TIMEOUT	18	/* How long for loss retry before timeout */
@@ -199,29 +198,4 @@ struct tcp_md5sig {
 	__u8	tcpm_key[TCP_MD5SIG_MAXKEYLEN];		/* key (binary) */
 };
 
-/* for TCP_COOKIE_TRANSACTIONS (TCPCT) socket option */
-#define TCP_COOKIE_MIN		 8		/*  64-bits */
-#define TCP_COOKIE_MAX		16		/* 128-bits */
-#define TCP_COOKIE_PAIR_SIZE	(2*TCP_COOKIE_MAX)
-
-/* Flags for both getsockopt and setsockopt */
-#define TCP_COOKIE_IN_ALWAYS	(1 << 0)	/* Discard SYN without cookie */
-#define TCP_COOKIE_OUT_NEVER	(1 << 1)	/* Prohibit outgoing cookies,
-						 * supercedes everything. */
-
-/* Flags for getsockopt */
-#define TCP_S_DATA_IN		(1 << 2)	/* Was data received? */
-#define TCP_S_DATA_OUT		(1 << 3)	/* Was data sent? */
-
-/* TCP_COOKIE_TRANSACTIONS data */
-struct tcp_cookie_transactions {
-	__u16	tcpct_flags;			/* see above */
-	__u8	__tcpct_pad1;			/* zero */
-	__u8	tcpct_cookie_desired;		/* bytes */
-	__u16	tcpct_s_data_desired;		/* bytes of variable data */
-	__u16	tcpct_used;			/* bytes in value */
-	__u8	tcpct_value[TCP_MSS_DEFAULT];
-};
-
-
 #endif /* _UAPI_LINUX_TCP_H */

net/dccp/ipv4.c

@@ -500,8 +500,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 	return &rt->dst;
 }
 
-static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
-				 struct request_values *rv_unused)
+static int dccp_v4_send_response(struct sock *sk, struct request_sock *req)
 {
 	int err = -1;
 	struct sk_buff *skb;
@@ -658,7 +657,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	dreq->dreq_gss     = dreq->dreq_iss;
 	dreq->dreq_service = service;
 
-	if (dccp_v4_send_response(sk, req, NULL))
+	if (dccp_v4_send_response(sk, req))
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);

net/dccp/ipv6.c

@@ -213,8 +213,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 }
 
 
-static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
-				 struct request_values *rv_unused)
+static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 {
 	struct inet6_request_sock *ireq6 = inet6_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -428,7 +427,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	dreq->dreq_gss     = dreq->dreq_iss;
 	dreq->dreq_service = service;
 
-	if (dccp_v6_send_response(sk, req, NULL))
+	if (dccp_v6_send_response(sk, req))
 		goto drop_and_free;
 
 	inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);

net/ipv4/inet_connection_sock.c

@@ -559,7 +559,7 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
 
 int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
 {
-	int err = req->rsk_ops->rtx_syn_ack(parent, req, NULL);
+	int err = req->rsk_ops->rtx_syn_ack(parent, req);
 
 	if (!err)
 		req->num_retrans++;

net/ipv4/syncookies.c

@@ -267,7 +267,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			     struct ip_options *opt)
 {
 	struct tcp_options_received tcp_opt;
-	const u8 *hash_location;
 	struct inet_request_sock *ireq;
 	struct tcp_request_sock *treq;
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -294,7 +293,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 
 	/* check for timestamp cookie support */
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
-	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
+	tcp_parse_options(skb, &tcp_opt, 0, NULL);
 
 	if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
 		goto out;

net/ipv4/sysctl_net_ipv4.c

@@ -732,13 +732,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "tcp_cookie_size",
-		.data		= &sysctl_tcp_cookie_size,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{
 		.procname       = "tcp_thin_linear_timeouts",
 		.data           = &sysctl_tcp_thin_linear_timeouts,