TCPCT part 1: cookie option exchange

index c719084..c9b50eb 100644
@@ -27,13 +27,19 @@ 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_sock *req,
+				       struct request_values *rvp);
 	void		(*send_ack)(struct sock *sk, struct sk_buff *skb,
 				    struct request_sock *req);
 	void		(*send_reset)(struct sock *sk,

index 325bfcf..ec183fd 100644
@@ -440,7 +440,8 @@ 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_sock *req,
+						struct request_values *rvp);
 
 extern int			tcp_disconnect(struct sock *sk, int flags);
 

index 2423a08..efbcfdc 100644
@@ -477,7 +477,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 	return &rt->u.dst;
 }
 
-static int dccp_v4_send_response(struct sock *sk, struct request_sock *req)
+static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
+				 struct request_values *rv_unused)
 {
 	int err = -1;
 	struct sk_buff *skb;

@@ -626,7 +627,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	dreq->dreq_iss	   = dccp_v4_init_sequence(skb);
 	dreq->dreq_service = service;
 
-	if (dccp_v4_send_response(sk, req))
+	if (dccp_v4_send_response(sk, req, NULL))
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);

index 50ea91a..6574215 100644
@@ -241,7 +241,8 @@ out:
 }
 
 
-static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
+static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
+				 struct request_values *rv_unused)
 {
 	struct inet6_request_sock *ireq6 = inet6_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);

@@ -468,7 +469,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	dreq->dreq_iss	   = dccp_v6_init_sequence(skb);
 	dreq->dreq_service = service;
 
-	if (dccp_v6_send_response(sk, req))
+	if (dccp_v6_send_response(sk, req, NULL))
 		goto drop_and_free;
 
 	inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);

index 5ca49ce..af226a0 100644
@@ -184,7 +184,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 			 * counter (backoff, monitored by dccp_response_timer).
 			 */
 			req->retrans++;
-			req->rsk_ops->rtx_syn_ack(sk, req);
+			req->rsk_ops->rtx_syn_ack(sk, req, NULL);
 		}
 		/* Network Duplicate, discard packet */
 		return NULL;

index 9b35c56..ee16475 100644
@@ -531,7 +531,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 					       &expire, &resend);
 				if (!expire &&
 				    (!resend ||
-				     !req->rsk_ops->rtx_syn_ack(parent, req) ||
+				     !req->rsk_ops->rtx_syn_ack(parent, req, NULL) ||
 				     inet_rsk(req)->acked)) {
 					unsigned long timeo;
 

index df18ce0..649a36d 100644
@@ -742,8 +742,9 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
  *	This still operates on a request_sock only, not on a big
  *	socket.
  */
-static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
-				struct dst_entry *dst)
+static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
+				struct request_sock *req,
+				struct request_values *rvp)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	int err = -1;

@@ -753,7 +754,7 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
 	if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
 		return -1;
 
-	skb = tcp_make_synack(sk, dst, req);
+	skb = tcp_make_synack(sk, dst, req, rvp);
 
 	if (skb) {
 		struct tcphdr *th = tcp_hdr(skb);

@@ -774,9 +775,10 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
 	return err;
 }
 
-static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req)
+static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
+			      struct request_values *rvp)
 {
-	return __tcp_v4_send_synack(sk, req, NULL);
+	return __tcp_v4_send_synack(sk, NULL, req, rvp);
 }
 
 /*

@@ -1211,13 +1213,13 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
 
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
-	struct inet_request_sock *ireq;
 	struct tcp_options_received tmp_opt;
 	struct request_sock *req;
+	struct inet_request_sock *ireq;
+	struct dst_entry *dst = NULL;
 	__be32 saddr = ip_hdr(skb)->saddr;
 	__be32 daddr = ip_hdr(skb)->daddr;
 	__u32 isn = TCP_SKB_CB(skb)->when;
-	struct dst_entry *dst = NULL;
 #ifdef CONFIG_SYN_COOKIES
 	int want_cookie = 0;
 #else

@@ -1337,7 +1339,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	}
 	tcp_rsk(req)->snt_isn = isn;
 
-	if (__tcp_v4_send_synack(sk, req, dst) || want_cookie)
+	if (__tcp_v4_send_synack(sk, dst, req, NULL) || want_cookie)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);

index ab32c18..d3f6bbf 100644
@@ -531,7 +531,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		 * Enforce "SYN-ACK" according to figure 8, figure 6
 		 * of RFC793, fixed by RFC1122.
 		 */
-		req->rsk_ops->rtx_syn_ack(sk, req);
+		req->rsk_ops->rtx_syn_ack(sk, req, NULL);
 		return NULL;
 	}
 

index 875bc6d..b8b2504 100644
@@ -2224,7 +2224,8 @@ int tcp_send_synack(struct sock *sk)
 
 /* Prepare a SYN-ACK. */
 struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
-				struct request_sock *req)
+				struct request_sock *req,
+				struct request_values *rvp)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct tcp_sock *tp = tcp_sk(sk);

index de70909..da6e244 100644
@@ -461,7 +461,8 @@ out:
 }
 
 
-static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req)
+static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
+			      struct request_values *rvp)
 {
 	struct inet6_request_sock *treq = inet6_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);

@@ -499,7 +500,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req)
 	if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
 		goto done;
 
-	skb = tcp_make_synack(sk, dst, req);
+	skb = tcp_make_synack(sk, dst, req, rvp);
 	if (skb) {
 		struct tcphdr *th = tcp_hdr(skb);
 

@@ -1161,13 +1162,13 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
  */
 static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
+	struct tcp_options_received tmp_opt;
+	struct request_sock *req;
 	struct inet6_request_sock *treq;
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct tcp_options_received tmp_opt;
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct request_sock *req = NULL;
-	__u32 isn = TCP_SKB_CB(skb)->when;
 	struct dst_entry *dst = __sk_dst_get(sk);
+	__u32 isn = TCP_SKB_CB(skb)->when;
 #ifdef CONFIG_SYN_COOKIES
 	int want_cookie = 0;
 #else

@@ -1239,23 +1240,19 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 
 		isn = tcp_v6_init_sequence(skb);
 	}
-
 	tcp_rsk(req)->snt_isn = isn;
 
 	security_inet_conn_request(sk, skb, req);
 
-	if (tcp_v6_send_synack(sk, req))
-		goto drop;
+	if (tcp_v6_send_synack(sk, req, NULL) || want_cookie)
+		goto drop_and_free;
 
-	if (!want_cookie) {
-		inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
-		return 0;
-	}
+	inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+	return 0;
 
+drop_and_free:
+	reqsk_free(req);
 drop:
-	if (req)
-		reqsk_free(req);
-
 	return 0; /* don't send reset */
 }
 

index c118b2a..ec78a4b 100644
@@ -2,6 +2,7 @@
 #define __CRYPTOHASH_H
 
 #define SHA_DIGEST_WORDS 5
+#define SHA_MESSAGE_BYTES (512 /*bits*/ / 8)
 #define SHA_WORKSPACE_WORDS 80
 
 void sha_init(__u32 *buf);

index ec183fd..4a99a8e 100644
@@ -1478,6 +1478,14 @@ 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);
+
 extern void tcp_v4_init(void);
 extern void tcp_init(void);
 

164 lines not on this page · raw message

index 32d7d77..eaa3113 100644
@@ -102,7 +102,9 @@ 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 */
 
+/* for TCP_INFO socket option */
 #define TCPI_OPT_TIMESTAMPS	1
 #define TCPI_OPT_SACK		2
 #define TCPI_OPT_WSCALE		4

@@ -174,6 +176,30 @@ 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];
+};
+
 #ifdef __KERNEL__
 
 #include <linux/skbuff.h>

@@ -227,6 +253,11 @@ struct tcp_options_received {
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
 };
 
+static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
+{
+	rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+}
+
 /* This is the max number of SACKS that we'll generate and process. It's safe
  * to increse this, although since:
  *   size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8)

@@ -435,6 +466,6 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
 	return (struct tcp_timewait_sock *)sk;
 }
 
-#endif
+#endif	/* __KERNEL__ */
 
 #endif	/* _LINUX_TCP_H */

index 4a99a8e..738b65f 100644
@@ -234,6 +234,7 @@ extern int sysctl_tcp_base_mss;
 extern int sysctl_tcp_workaround_signed_windows;
 extern int sysctl_tcp_slow_start_after_idle;
 extern int sysctl_tcp_max_ssthresh;
+extern int sysctl_tcp_cookie_size;
 
 extern atomic_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;

@@ -340,11 +341,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk,
 
 extern void tcp_enter_quickack_mode(struct sock *sk);
 
-static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
-{
- 	rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
-}
-
 #define	TCP_ECN_OK		1
 #define	TCP_ECN_QUEUE_CWR	2
 #define	TCP_ECN_DEMAND_CWR	4

index c00323b..13f7ab6 100644
@@ -714,6 +714,14 @@ static struct ctl_table ipv4_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "tcp_cookie_size",
+		.data		= &sysctl_tcp_cookie_size,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "udp_mem",
 		.data		= &sysctl_udp_mem,
 		.maxlen		= sizeof(sysctl_udp_mem),

index b8b2504..307f318 100644
@@ -59,6 +59,9 @@ int sysctl_tcp_base_mss __read_mostly = 512;
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 
+int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */
+
+
 /* Account for new data that has been sent to the network. */
 static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 {

index eaa3113..7fee8a4 100644
@@ -247,31 +247,38 @@ 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	*/
-/*	SACKs data	*/
+	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	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
 };
 
 static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 {
-	rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+	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
- * to increse this, although since:
+ * to increase this, although since:
  *   size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8)
  * only four options will fit in a standard TCP header */
 #define TCP_NUM_SACKS 4
 
+struct tcp_cookie_values;
+struct tcp_request_sock_ops;
+
 struct tcp_request_sock {
 	struct inet_request_sock 	req;
 #ifdef CONFIG_TCP_MD5SIG
 	/* Only used by TCP MD5 Signature so far. */
 	const struct tcp_request_sock_ops *af_specific;
 #endif
-	u32			 	rcv_isn;
-	u32			 	snt_isn;
+	u32				rcv_isn;
+	u32				snt_isn;
 };
 
 static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)

@@ -441,6 +448,12 @@ struct tcp_sock {
 /* TCP MD5 Signature Option information */
 	struct tcp_md5sig_info	*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;
 };
 
 static inline struct tcp_sock *tcp_sk(const struct sock *sk)

@@ -459,6 +472,10 @@ struct tcp_timewait_sock {
 	u16			  tw_md5_keylen;
 	u8			  tw_md5_key[TCP_MD5SIG_MAXKEYLEN];
 #endif
+	/* Few sockets in timewait have cookies; in that case, then this
+	 * object holds a reference to them (tw_cookie_values->kref).
+	 */
+	struct tcp_cookie_values  *tw_cookie_values;
 };
 
 static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)

107 lines not on this page · raw message

index 649a36d..a2bcac9 100644
@@ -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);
 }
 

67 lines not on this page · raw message

index da6e244..f2ec382 100644
@@ -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];
 

index ba03ac8..c8666b7 100644
@@ -2085,8 +2085,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	int val;
 	int err = 0;
 
-	/* This is a string value all the others are int's */
-	if (optname == TCP_CONGESTION) {
+	/* These are data/string values, all the others are ints */
+	switch (optname) {
+	case TCP_CONGESTION: {
 		char name[TCP_CA_NAME_MAX];
 
 		if (optlen < 1)

@@ -2103,6 +2104,93 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		release_sock(sk);
 		return err;
 	}
+	case TCP_COOKIE_TRANSACTIONS: {
+		struct tcp_cookie_transactions ctd;
+		struct tcp_cookie_values *cvp = NULL;
+
+		if (sizeof(ctd) > optlen)
+			return -EINVAL;
+		if (copy_from_user(&ctd, optval, sizeof(ctd)))
+			return -EFAULT;
+
+		if (ctd.tcpct_used > sizeof(ctd.tcpct_value) ||
+		    ctd.tcpct_s_data_desired > TCP_MSS_DESIRED)
+			return -EINVAL;
+
+		if (ctd.tcpct_cookie_desired == 0) {
+			/* default to global value */
+		} else if ((0x1 & ctd.tcpct_cookie_desired) ||
+			   ctd.tcpct_cookie_desired > TCP_COOKIE_MAX ||
+			   ctd.tcpct_cookie_desired < TCP_COOKIE_MIN) {
+			return -EINVAL;
+		}
+
+		if (TCP_COOKIE_OUT_NEVER & ctd.tcpct_flags) {
+			/* Supercedes all other values */
+			lock_sock(sk);
+			if (tp->cookie_values != NULL) {
+				kref_put(&tp->cookie_values->kref,
+					 tcp_cookie_values_release);
+				tp->cookie_values = NULL;
+			}
+			tp->rx_opt.cookie_in_always = 0; /* false */
+			tp->rx_opt.cookie_out_never = 1; /* true */
+			release_sock(sk);
+			return err;
+		}
+
+		/* Allocate ancillary memory before locking.
+		 */
+		if (ctd.tcpct_used > 0 ||
+		    (tp->cookie_values == NULL &&
+		     (sysctl_tcp_cookie_size > 0 ||
+		      ctd.tcpct_cookie_desired > 0 ||
+		      ctd.tcpct_s_data_desired > 0))) {
+			cvp = kzalloc(sizeof(*cvp) + ctd.tcpct_used,
+				      GFP_KERNEL);
+			if (cvp == NULL)
+				return -ENOMEM;
+		}
+		lock_sock(sk);
+		tp->rx_opt.cookie_in_always =
+			(TCP_COOKIE_IN_ALWAYS & ctd.tcpct_flags);
+		tp->rx_opt.cookie_out_never = 0; /* false */
+
+		if (tp->cookie_values != NULL) {
+			if (cvp != NULL) {
+				/* Changed values are recorded by a changed
+				 * pointer, ensuring the cookie will differ,
+				 * without separately hashing each value later.
+				 */
+				kref_put(&tp->cookie_values->kref,
+					 tcp_cookie_values_release);
+				kref_init(&cvp->kref);
+				tp->cookie_values = cvp;
+			} else {
+				cvp = tp->cookie_values;
+			}
+		}
+		if (cvp != NULL) {
+			cvp->cookie_desired = ctd.tcpct_cookie_desired;
+
+			if (ctd.tcpct_used > 0) {
+				memcpy(cvp->s_data_payload, ctd.tcpct_value,
+				       ctd.tcpct_used);
+				cvp->s_data_desired = ctd.tcpct_used;
+				cvp->s_data_constant = 1; /* true */
+			} else {
+				/* No constant payload data. */
+				cvp->s_data_desired = ctd.tcpct_s_data_desired;
+				cvp->s_data_constant = 0; /* false */
+			}
+		}
+		release_sock(sk);
+		return err;
+	}
+	default:
+		/* fallthru */
+		break;
+	};
 
 	if (optlen < sizeof(int))
 		return -EINVAL;

@@ -2427,6 +2515,47 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		if (copy_to_user(optval, icsk->icsk_ca_ops->name, len))
 			return -EFAULT;
 		return 0;
+
+	case TCP_COOKIE_TRANSACTIONS: {
+		struct tcp_cookie_transactions ctd;
+		struct tcp_cookie_values *cvp = tp->cookie_values;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+		if (len < sizeof(ctd))
+			return -EINVAL;
+
+		memset(&ctd, 0, sizeof(ctd));
+		ctd.tcpct_flags = (tp->rx_opt.cookie_in_always ?
+				   TCP_COOKIE_IN_ALWAYS : 0)
+				| (tp->rx_opt.cookie_out_never ?
+				   TCP_COOKIE_OUT_NEVER : 0);
+
+		if (cvp != NULL) {
+			ctd.tcpct_flags |= (cvp->s_data_in ?
+					    TCP_S_DATA_IN : 0)
+					 | (cvp->s_data_out ?
+					    TCP_S_DATA_OUT : 0);
+
+			ctd.tcpct_cookie_desired = cvp->cookie_desired;
+			ctd.tcpct_s_data_desired = cvp->s_data_desired;
+
+			/* Cookie(s) saved, return as nonce */
+			if (sizeof(ctd.tcpct_value) < cvp->cookie_pair_size) {
+				/* impossible? */
+				return -EINVAL;
+			}
+			memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0],
+			       cvp->cookie_pair_size);
+			ctd.tcpct_used = cvp->cookie_pair_size;
+		}
+
+		if (put_user(sizeof(ctd), optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, &ctd, sizeof(ctd)))
+			return -EFAULT;
+		return 0;
+	}
 	default:
 		return -ENOPROTOOPT;
 	}

index 307f318..35dd983 100644
@@ -365,15 +365,45 @@ static inline int tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_TS		(1 << 1)
 #define OPTION_MD5		(1 << 2)
 #define OPTION_WSCALE		(1 << 3)
+#define OPTION_COOKIE_EXTENSION	(1 << 4)
 
 struct tcp_out_options {
 	u8 options;		/* bit field of OPTION_* */
 	u8 ws;			/* window scale, 0 to disable */
 	u8 num_sack_blocks;	/* number of SACK blocks to include */
+	u8 hash_size;		/* bytes in hash_location */
 	u16 mss;		/* 0 to disable */
 	__u32 tsval, tsecr;	/* need to include OPTION_TS */
+	__u8 *hash_location;	/* temporary pointer, overloaded */
 };
 
+/* The sysctl int routines are generic, so check consistency here.
+ */
+static u8 tcp_cookie_size_check(u8 desired)
+{
+	if (desired > 0) {
+		/* previously specified */
+		return desired;
+	}
+	if (sysctl_tcp_cookie_size <= 0) {
+		/* no default specified */
+		return 0;
+	}
+	if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) {
+		/* value too small, specify minimum */
+		return TCP_COOKIE_MIN;
+	}
+	if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) {
+		/* value too large, specify maximum */
+		return TCP_COOKIE_MAX;
+	}
+	if (0x1 & sysctl_tcp_cookie_size) {
+		/* 8-bit multiple, illegal, fix it */
+		return (u8)(sysctl_tcp_cookie_size + 0x1);
+	}
+	return (u8)sysctl_tcp_cookie_size;
+}
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of

@@ -388,17 +418,34 @@ struct tcp_out_options {
  * (but it may well be that other scenarios fail similarly).
  */
 static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
-			      const struct tcp_out_options *opts,
-			      __u8 **md5_hash) {
-	if (unlikely(OPTION_MD5 & opts->options)) {
-		*ptr++ = htonl((TCPOPT_NOP << 24) |
-			       (TCPOPT_NOP << 16) |
-			       (TCPOPT_MD5SIG << 8) |
-			       TCPOLEN_MD5SIG);
-		*md5_hash = (__u8 *)ptr;
+			      struct tcp_out_options *opts)
+{
+	u8 options = opts->options;	/* mungable copy */
+
+	/* Having both authentication and cookies for security is redundant,
+	 * and there's certainly not enough room.  Instead, the cookie-less
+	 * extension variant is proposed.
+	 *
+	 * Consider the pessimal case with authentication.  The options
+	 * could look like:
+	 *   COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40
+	 */
+	if (unlikely(OPTION_MD5 & options)) {
+		if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
+			*ptr++ = htonl((TCPOPT_COOKIE << 24) |
+				       (TCPOLEN_COOKIE_BASE << 16) |
+				       (TCPOPT_MD5SIG << 8) |
+				       TCPOLEN_MD5SIG);
+		} else {
+			*ptr++ = htonl((TCPOPT_NOP << 24) |
+				       (TCPOPT_NOP << 16) |
+				       (TCPOPT_MD5SIG << 8) |
+				       TCPOLEN_MD5SIG);
+		}
+		options &= ~OPTION_COOKIE_EXTENSION;
+		/* overload cookie hash location */
+		opts->hash_location = (__u8 *)ptr;
 		ptr += 4;
-	} else {
-		*md5_hash = NULL;
 	}
 
 	if (unlikely(opts->mss)) {

@@ -407,12 +454,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 			       opts->mss);
 	}
 
-	if (likely(OPTION_TS & opts->options)) {
-		if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) {
+	if (likely(OPTION_TS & options)) {
+		if (unlikely(OPTION_SACK_ADVERTISE & options)) {
 			*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
 				       (TCPOLEN_SACK_PERM << 16) |
 				       (TCPOPT_TIMESTAMP << 8) |
 				       TCPOLEN_TIMESTAMP);
+			options &= ~OPTION_SACK_ADVERTISE;
 		} else {
 			*ptr++ = htonl((TCPOPT_NOP << 24) |
 				       (TCPOPT_NOP << 16) |

@@ -423,15 +471,52 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 		*ptr++ = htonl(opts->tsecr);
 	}
 
-	if (unlikely(OPTION_SACK_ADVERTISE & opts->options &&
-		     !(OPTION_TS & opts->options))) {
+	/* Specification requires after timestamp, so do it now.
+	 *
+	 * Consider the pessimal case without authentication.  The options
+	 * could look like:
+	 *   MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40
+	 */
+	if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
+		__u8 *cookie_copy = opts->hash_location;
+		u8 cookie_size = opts->hash_size;
+
+		/* 8-bit multiple handled in tcp_cookie_size_check() above,
+		 * and elsewhere.
+		 */
+		if (0x2 & cookie_size) {
+			__u8 *p = (__u8 *)ptr;
+
+			/* 16-bit multiple */
+			*p++ = TCPOPT_COOKIE;
+			*p++ = TCPOLEN_COOKIE_BASE + cookie_size;
+			*p++ = *cookie_copy++;
+			*p++ = *cookie_copy++;
+			ptr++;
+			cookie_size -= 2;
+		} else {
+			/* 32-bit multiple */
+			*ptr++ = htonl(((TCPOPT_NOP << 24) |
+					(TCPOPT_NOP << 16) |
+					(TCPOPT_COOKIE << 8) |
+					TCPOLEN_COOKIE_BASE) +
+				       cookie_size);
+		}
+
+		if (cookie_size > 0) {
+			memcpy(ptr, cookie_copy, cookie_size);
+			ptr += (cookie_size / 4);
+		}
+	}
+
+	if (unlikely(OPTION_SACK_ADVERTISE & options)) {
 		*ptr++ = htonl((TCPOPT_NOP << 24) |
 			       (TCPOPT_NOP << 16) |
 			       (TCPOPT_SACK_PERM << 8) |
 			       TCPOLEN_SACK_PERM);
 	}
 
-	if (unlikely(OPTION_WSCALE & opts->options)) {
+	if (unlikely(OPTION_WSCALE & options)) {
 		*ptr++ = htonl((TCPOPT_NOP << 24) |
 			       (TCPOPT_WINDOW << 16) |
 			       (TCPOLEN_WINDOW << 8) |

@@ -466,14 +551,18 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 				struct tcp_out_options *opts,
 				struct tcp_md5sig_key **md5) {
 	struct tcp_sock *tp = tcp_sk(sk);
-	unsigned size = 0;
+	struct tcp_cookie_values *cvp = tp->cookie_values;
 	struct dst_entry *dst = __sk_dst_get(sk);
+	unsigned remaining = MAX_TCP_OPTION_SPACE;
+	u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
+			 tcp_cookie_size_check(cvp->cookie_desired) :
+			 0;
 
 #ifdef CONFIG_TCP_MD5SIG
 	*md5 = tp->af_specific->md5_lookup(sk, sk);
 	if (*md5) {
 		opts->options |= OPTION_MD5;
-		size += TCPOLEN_MD5SIG_ALIGNED;
+		remaining -= TCPOLEN_MD5SIG_ALIGNED;
 	}
 #else
 	*md5 = NULL;

@@ -489,7 +578,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	 * SACKs don't matter, we never delay an ACK when we have any of those
 	 * going out.  */
 	opts->mss = tcp_advertise_mss(sk);
-	size += TCPOLEN_MSS_ALIGNED;
+	remaining -= TCPOLEN_MSS_ALIGNED;
 
 	if (likely(sysctl_tcp_timestamps &&
 		   !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) &&

@@ -497,22 +586,68 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		opts->options |= OPTION_TS;
 		opts->tsval = TCP_SKB_CB(skb)->when;
 		opts->tsecr = tp->rx_opt.ts_recent;
-		size += TCPOLEN_TSTAMP_ALIGNED;
+		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
 	if (likely(sysctl_tcp_window_scaling &&
 		   !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) {
 		opts->ws = tp->rx_opt.rcv_wscale;
 		opts->options |= OPTION_WSCALE;
-		size += TCPOLEN_WSCALE_ALIGNED;
+		remaining -= TCPOLEN_WSCALE_ALIGNED;
 	}
 	if (likely(sysctl_tcp_sack &&
 		   !dst_feature(dst, RTAX_FEATURE_NO_SACK))) {
 		opts->options |= OPTION_SACK_ADVERTISE;
 		if (unlikely(!(OPTION_TS & opts->options)))
-			size += TCPOLEN_SACKPERM_ALIGNED;
+			remaining -= TCPOLEN_SACKPERM_ALIGNED;
 	}
 
-	return size;
+	/* Note that timestamps are required by the specification.
+	 *
+	 * Odd numbers of bytes are prohibited by the specification, ensuring
+	 * that the cookie is 16-bit aligned, and the resulting cookie pair is
+	 * 32-bit aligned.
+	 */
+	if (*md5 == NULL &&
+	    (OPTION_TS & opts->options) &&
+	    cookie_size > 0) {
+		int need = TCPOLEN_COOKIE_BASE + cookie_size;
+
+		if (0x2 & need) {
+			/* 32-bit multiple */
+			need += 2; /* NOPs */
+
+			if (need > remaining) {
+				/* try shrinking cookie to fit */
+				cookie_size -= 2;
+				need -= 4;
+			}
+		}
+		while (need > remaining && TCP_COOKIE_MIN <= cookie_size) {
+			cookie_size -= 4;
+			need -= 4;
+		}
+		if (TCP_COOKIE_MIN <= cookie_size) {
+			opts->options |= OPTION_COOKIE_EXTENSION;
+			opts->hash_location = (__u8 *)&cvp->cookie_pair[0];
+			opts->hash_size = cookie_size;
+
+			/* Remember for future incarnations. */
+			cvp->cookie_desired = cookie_size;
+
+			if (cvp->cookie_desired != cvp->cookie_pair_size) {
+				/* Currently use random bytes as a nonce,
+				 * assuming these are completely unpredictable
+				 * by hostile users of the same system.
+				 */
+				get_random_bytes(&cvp->cookie_pair[0],
+						 cookie_size);
+				cvp->cookie_pair_size = cookie_size;
+			}
+
+			remaining -= need;
+		}
+	}
+	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
 /* Set up TCP options for SYN-ACKs. */

@@ -627,7 +762,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	struct tcp_out_options opts;
 	unsigned tcp_options_size, tcp_header_size;
 	struct tcp_md5sig_key *md5;
-	__u8 *md5_hash_location;
 	struct tcphdr *th;
 	int err;
 

@@ -698,7 +832,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		}
 	}
 
-	tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+	tcp_options_write((__be32 *)(th + 1), tp, &opts);
 	if (likely((tcb->flags & TCPCB_FLAG_SYN) == 0))
 		TCP_ECN_send(sk, skb, tcp_header_size);
 

@@ -706,7 +840,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	/* Calculate the MD5 hash, as we have all we need now */
 	if (md5) {
 		sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
-		tp->af_specific->calc_md5_hash(md5_hash_location,
+		tp->af_specific->calc_md5_hash(opts.hash_location,
 					       md5, sk, NULL, skb);
 	}
 #endif

@@ -2230,14 +2364,13 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
 				struct request_values *rvp)
 {
+	struct tcp_out_options opts;
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcphdr *th;
-	int tcp_header_size;
-	struct tcp_out_options opts;
 	struct sk_buff *skb;
 	struct tcp_md5sig_key *md5;
-	__u8 *md5_hash_location;
+	int tcp_header_size;
 	int mss;
 
 	skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);

@@ -2298,14 +2431,14 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
 	th->window = htons(min(req->rcv_wnd, 65535U));
-	tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+	tcp_options_write((__be32 *)(th + 1), tp, &opts);
 	th->doff = (tcp_header_size >> 2);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Okay, we have all we need - do the md5 hash if needed */
 	if (md5) {
-		tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location,
+		tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location,
 					       md5, NULL, req, skb);
 	}
 #endif

index f9abd9b..28b04ff 100644
@@ -407,6 +407,7 @@ extern int			tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
 
 extern void			tcp_parse_options(struct sk_buff *skb,
 						  struct tcp_options_received *opt_rx,
+						  u8 **hvpp,
 						  int estab,
 						  struct dst_entry *dst);
 

index 3146cc4..26399ad 100644
@@ -253,6 +253,8 @@ EXPORT_SYMBOL(cookie_check_timestamp);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			     struct ip_options *opt)
 {
+	struct tcp_options_received tcp_opt;
+	u8 *hash_location;
 	struct inet_request_sock *ireq;
 	struct tcp_request_sock *treq;
 	struct tcp_sock *tp = tcp_sk(sk);

@@ -263,7 +265,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	int mss;
 	struct rtable *rt;
 	__u8 rcv_wscale;
-	struct tcp_options_received tcp_opt;
 
 	if (!sysctl_tcp_syncookies || !th->ack)
 		goto out;

@@ -341,7 +342,7 @@ 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, 0, &rt->u.dst);
+	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst);
 
 	if (tcp_opt.saw_tstamp)
 		cookie_check_timestamp(&tcp_opt);

124 lines not on this page · raw message

74 lines not on this page · raw message

index 96852af..87accec 100644
@@ -90,13 +90,14 @@ enum tcp_tw_status
 tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			   const struct tcphdr *th)
 {
-	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 	struct tcp_options_received tmp_opt;
+	u8 *hash_location;
+	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 	int paws_reject = 0;
 
 	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
 		tmp_opt.tstamp_ok = 1;
-		tcp_parse_options(skb, &tmp_opt, 1, NULL);
+		tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent	= tcptw->tw_ts_recent;

@@ -518,15 +519,16 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			   struct request_sock *req,
 			   struct request_sock **prev)
 {
+	struct tcp_options_received tmp_opt;
+	u8 *hash_location;
+	struct sock *child;
 	const struct tcphdr *th = tcp_hdr(skb);
 	__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
 	int paws_reject = 0;
-	struct tcp_options_received tmp_opt;
-	struct sock *child;
 
-	if ((th->doff > (sizeof(struct tcphdr)>>2)) && (req->ts_recent)) {
+	if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) {
 		tmp_opt.tstamp_ok = 1;
-		tcp_parse_options(skb, &tmp_opt, 1, NULL);
+		tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent = req->ts_recent;

154 lines not on this page · raw message

index 612fc53..5b9af50 100644
@@ -159,6 +159,8 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
 
 struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 {
+	struct tcp_options_received tcp_opt;
+	u8 *hash_location;
 	struct inet_request_sock *ireq;
 	struct inet6_request_sock *ireq6;
 	struct tcp_request_sock *treq;

@@ -171,7 +173,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	int mss;
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
-	struct tcp_options_received tcp_opt;
 
 	if (!sysctl_tcp_syncookies || !th->ack)
 		goto out;

@@ -254,7 +255,7 @@ struct sock *cookie_v6_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, 0, dst);
+	tcp_parse_options(skb, &tcp_opt, &hash_location, 0, dst);
 
 	if (tcp_opt.saw_tstamp)
 		cookie_check_timestamp(&tcp_opt);

72 lines not on this page · raw message

index 2ac8bef..c08e06d 100644
@@ -2485,7 +2485,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
 			/* recommended */
 			*tail-- ^= ((th->dest << 16) | th->source);
-			*tail-- ^= (u32)cvp; /* per sockopt */
+			*tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */
 
 			sha_transform((__u32 *)&xvp->cookie_bakery[0],
 				      (char *)mess,

index c08e06d..93316a9 100644
@@ -60,6 +60,7 @@ int sysctl_tcp_base_mss __read_mostly = 512;
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 
 int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */
+EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size);
 
 
 /* Account for new data that has been sent to the network. */