Merge branch 'tcp_conn_request_unification'

Octavian Purdila says:

====================
tcp: remove code duplication in tcp_v[46]_conn_request

This patch series unifies the TCPv4 and TCPv6 connection request flow
in a single new function (tcp_conn_request).

The first 3 patches are small cleanups and fixes found during the code
merge process.

The next patches add new methods in tcp_request_sock_ops to abstract
the IPv4/IPv6 operations and keep the TCP connection request flow
common.

To identify potential performance issues this patch has been tested
by measuring the connection per second rate with nginx and a httperf
like client (to allow for concurrent connection requests - 256 CC were
used during testing) using the loopback interface. A dual-core i5 Ivy
Bridge processor was used and each process was bounded to a different
core to make results consistent.

Results for IPv4, unit is connections per second, higher is better, 20
measurements have been collected:

		before		after
min		27917		27962
max		28262		28366
avg		28094.1		28212.75
stdev		87.35		97.26

Results for IPv6, unit is connections per second, higher is better, 20
measurements have been collected:

		before		after
min		24813		24877
max		25029		25119
avg		24935.5		25017
stdev		64.13		62.93

Changes since v1:

 * add benchmarking datapoints

 * fix a few issues in the last patch (IPv6 related)
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/ipv6.h

@@ -256,16 +256,6 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 	return inet_sk(__sk)->pinet6;
 }
 
-static inline struct request_sock *inet6_reqsk_alloc(struct request_sock_ops *ops)
-{
-	struct request_sock *req = reqsk_alloc(ops);
-
-	if (req)
-		inet_rsk(req)->pktopts = NULL;
-
-	return req;
-}
-
 static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 {
 	return (struct raw6_sock *)sk;

include/linux/tcp.h

@@ -111,10 +111,7 @@ 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
 	struct sock			*listener; /* needed for TFO */
 	u32				rcv_isn;
 	u32				snt_isn;

include/net/inet_sock.h

@@ -88,8 +88,10 @@ struct inet_request_sock {
 				acked	   : 1,
 				no_srccheck: 1;
 	kmemcheck_bitfield_end(flags);
-	struct ip_options_rcu	*opt;
-	struct sk_buff		*pktopts;
+	union {
+		struct ip_options_rcu	*opt;
+		struct sk_buff		*pktopts;
+	};
 	u32                     ir_mark;
 };
 

include/net/tcp.h

@@ -493,14 +493,8 @@ static inline u32 tcp_cookie_time(void)
 
 u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
 			      u16 *mssp);
-__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mss);
-#else
-static inline __u32 cookie_v4_init_sequence(struct sock *sk,
-					    struct sk_buff *skb,
-					    __u16 *mss)
-{
-	return 0;
-}
+__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb,
+			      __u16 *mss);
 #endif
 
 __u32 cookie_init_timestamp(struct request_sock *req);
@@ -516,13 +510,6 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
 			      const struct tcphdr *th, u16 *mssp);
 __u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb,
 			      __u16 *mss);
-#else
-static inline __u32 cookie_v6_init_sequence(struct sock *sk,
-					    struct sk_buff *skb,
-					    __u16 *mss)
-{
-	return 0;
-}
 #endif
 /* tcp_output.c */
 
@@ -1586,6 +1573,11 @@ int tcp4_proc_init(void);
 void tcp4_proc_exit(void);
 #endif
 
+int tcp_rtx_synack(struct sock *sk, struct request_sock *req);
+int tcp_conn_request(struct request_sock_ops *rsk_ops,
+		     const struct tcp_request_sock_ops *af_ops,
+		     struct sock *sk, struct sk_buff *skb);
+
 /* TCP af-specific functions */
 struct tcp_sock_af_ops {
 #ifdef CONFIG_TCP_MD5SIG
@@ -1603,6 +1595,7 @@ struct tcp_sock_af_ops {
 };
 
 struct tcp_request_sock_ops {
+	u16 mss_clamp;
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key	*(*md5_lookup) (struct sock *sk,
 						struct request_sock *req);
@@ -1612,8 +1605,39 @@ struct tcp_request_sock_ops {
 						  const struct request_sock *req,
 						  const struct sk_buff *skb);
 #endif
+	void (*init_req)(struct request_sock *req, struct sock *sk,
+			 struct sk_buff *skb);
+#ifdef CONFIG_SYN_COOKIES
+	__u32 (*cookie_init_seq)(struct sock *sk, const struct sk_buff *skb,
+				 __u16 *mss);
+#endif
+	struct dst_entry *(*route_req)(struct sock *sk, struct flowi *fl,
+				       const struct request_sock *req,
+				       bool *strict);
+	__u32 (*init_seq)(const struct sk_buff *skb);
+	int (*send_synack)(struct sock *sk, struct dst_entry *dst,
+			   struct flowi *fl, struct request_sock *req,
+			   u16 queue_mapping, struct tcp_fastopen_cookie *foc);
+	void (*queue_hash_add)(struct sock *sk, struct request_sock *req,
+			       const unsigned long timeout);
 };
 
+#ifdef CONFIG_SYN_COOKIES
+static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
+					 struct sock *sk, struct sk_buff *skb,
+					 __u16 *mss)
+{
+	return ops->cookie_init_seq(sk, skb, mss);
+}
+#else
+static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
+					 struct sock *sk, struct sk_buff *skb,
+					 __u16 *mss)
+{
+	return 0;
+}
+#endif
+
 int tcpv4_offload_init(void);
 
 void tcp_v4_init(void);

net/dccp/ipv6.c

@@ -386,7 +386,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
 		goto drop;
 
-	req = inet6_reqsk_alloc(&dccp6_request_sock_ops);
+	req = inet_reqsk_alloc(&dccp6_request_sock_ops);
 	if (req == NULL)
 		goto drop;
 

net/ipv4/syncookies.c

@@ -170,7 +170,8 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
 }
 EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
 
-__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
+__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb,
+			      __u16 *mssp)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	const struct tcphdr *th = tcp_hdr(skb);

net/ipv4/tcp_input.c

@@ -5877,3 +5877,151 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	return 0;
 }
 EXPORT_SYMBOL(tcp_rcv_state_process);
+
+static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+
+	if (family == AF_INET)
+		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"),
+			       &ireq->ir_rmt_addr, port);
+	else
+		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI6/%u\n"),
+			       &ireq->ir_v6_rmt_addr, port);
+}
+
+int tcp_conn_request(struct request_sock_ops *rsk_ops,
+		     const struct tcp_request_sock_ops *af_ops,
+		     struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_options_received tmp_opt;
+	struct request_sock *req;
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct dst_entry *dst = NULL;
+	__u32 isn = TCP_SKB_CB(skb)->when;
+	bool want_cookie = false, fastopen;
+	struct flowi fl;
+	struct tcp_fastopen_cookie foc = { .len = -1 };
+	int err;
+
+
+	/* TW buckets are converted to open requests without
+	 * limitations, they conserve resources and peer is
+	 * evidently real one.
+	 */
+	if ((sysctl_tcp_syncookies == 2 ||
+	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
+		want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name);
+		if (!want_cookie)
+			goto drop;
+	}
+
+
+	/* Accept backlog is full. If we have already queued enough
+	 * of warm entries in syn queue, drop request. It is better than
+	 * clogging syn queue with openreqs with exponentially increasing
+	 * timeout.
+	 */
+	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+		goto drop;
+	}
+
+	req = inet_reqsk_alloc(rsk_ops);
+	if (!req)
+		goto drop;
+
+	tcp_rsk(req)->af_specific = af_ops;
+
+	tcp_clear_options(&tmp_opt);
+	tmp_opt.mss_clamp = af_ops->mss_clamp;
+	tmp_opt.user_mss  = tp->rx_opt.user_mss;
+	tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
+
+	if (want_cookie && !tmp_opt.saw_tstamp)
+		tcp_clear_options(&tmp_opt);
+
+	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
+	tcp_openreq_init(req, &tmp_opt, skb, sk);
+
+	af_ops->init_req(req, sk, skb);
+
+	if (security_inet_conn_request(sk, skb, req))
+		goto drop_and_free;
+
+	if (!want_cookie || tmp_opt.tstamp_ok)
+		TCP_ECN_create_request(req, skb, sock_net(sk));
+
+	if (want_cookie) {
+		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
+		req->cookie_ts = tmp_opt.tstamp_ok;
+	} else if (!isn) {
+		/* VJ's idea. We save last timestamp seen
+		 * from the destination in peer table, when entering
+		 * state TIME-WAIT, and check against it before
+		 * accepting new connection request.
+		 *
+		 * If "isn" is not zero, this request hit alive
+		 * timewait bucket, so that all the necessary checks
+		 * are made in the function processing timewait state.
+		 */
+		if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle) {
+			bool strict;
+
+			dst = af_ops->route_req(sk, &fl, req, &strict);
+			if (dst && strict &&
+			    !tcp_peer_is_proven(req, dst, true)) {
+				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
+				goto drop_and_release;
+			}
+		}
+		/* Kill the following clause, if you dislike this way. */
+		else if (!sysctl_tcp_syncookies &&
+			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+			  (sysctl_max_syn_backlog >> 2)) &&
+			 !tcp_peer_is_proven(req, dst, false)) {
+			/* Without syncookies last quarter of
+			 * backlog is filled with destinations,
+			 * proven to be alive.
+			 * It means that we continue to communicate
+			 * to destinations, already remembered
+			 * to the moment of synflood.
+			 */
+			pr_drop_req(req, ntohs(tcp_hdr(skb)->source),
+				    rsk_ops->family);
+			goto drop_and_release;
+		}
+
+		isn = af_ops->init_seq(skb);
+	}
+	if (!dst) {
+		dst = af_ops->route_req(sk, &fl, req, NULL);
+		if (!dst)
+			goto drop_and_free;
+	}
+
+	tcp_rsk(req)->snt_isn = isn;
+	tcp_openreq_init_rwin(req, sk, dst);
+	fastopen = !want_cookie &&
+		   tcp_try_fastopen(sk, skb, req, &foc, dst);
+	err = af_ops->send_synack(sk, dst, &fl, req,
+				  skb_get_queue_mapping(skb), &foc);
+	if (!fastopen) {
+		if (err || want_cookie)
+			goto drop_and_free;
+
+		tcp_rsk(req)->listener = NULL;
+		af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+	}
+
+	return 0;
+
+drop_and_release:
+	dst_release(dst);
+drop_and_free:
+	reqsk_free(req);
+drop:
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+	return 0;
+}
+EXPORT_SYMBOL(tcp_conn_request);

net/ipv4/tcp_ipv4.c

@@ -99,7 +99,7 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static inline __u32 tcp_v4_init_sequence(const struct sk_buff *skb)
+static  __u32 tcp_v4_init_sequence(const struct sk_buff *skb)
 {
 	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
 					  ip_hdr(skb)->saddr,
@@ -814,6 +814,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
  *	socket.
  */
 static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
+			      struct flowi *fl,
 			      struct request_sock *req,
 			      u16 queue_mapping,
 			      struct tcp_fastopen_cookie *foc)
@@ -844,17 +845,6 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 	return err;
 }
 
-static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req)
-{
-	int res = tcp_v4_send_synack(sk, NULL, req, 0, NULL);
-
-	if (!res) {
-		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
-	}
-	return res;
-}
-
 /*
  *	IPv4 request_sock destructor.
  */
@@ -1237,160 +1227,68 @@ static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
 
 #endif
 
+static void tcp_v4_init_req(struct request_sock *req, struct sock *sk,
+			    struct sk_buff *skb)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+
+	ireq->ir_loc_addr = ip_hdr(skb)->daddr;
+	ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
+	ireq->no_srccheck = inet_sk(sk)->transparent;
+	ireq->opt = tcp_v4_save_options(skb);
+}
+
+static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl,
+					  const struct request_sock *req,
+					  bool *strict)
+{
+	struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req);
+
+	if (strict) {
+		if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr)
+			*strict = true;
+		else
+			*strict = false;
+	}
+
+	return dst;
+}
+
 struct request_sock_ops tcp_request_sock_ops __read_mostly = {
 	.family		=	PF_INET,
 	.obj_size	=	sizeof(struct tcp_request_sock),
-	.rtx_syn_ack	=	tcp_v4_rtx_synack,
+	.rtx_syn_ack	=	tcp_rtx_synack,
 	.send_ack	=	tcp_v4_reqsk_send_ack,
 	.destructor	=	tcp_v4_reqsk_destructor,
 	.send_reset	=	tcp_v4_send_reset,
 	.syn_ack_timeout = 	tcp_syn_ack_timeout,
 };
 
-#ifdef CONFIG_TCP_MD5SIG
 static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
+	.mss_clamp	=	TCP_MSS_DEFAULT,
+#ifdef CONFIG_TCP_MD5SIG
 	.md5_lookup	=	tcp_v4_reqsk_md5_lookup,
 	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
-};
 #endif
+	.init_req	=	tcp_v4_init_req,
+#ifdef CONFIG_SYN_COOKIES
+	.cookie_init_seq =	cookie_v4_init_sequence,
+#endif
+	.route_req	=	tcp_v4_route_req,
+	.init_seq	=	tcp_v4_init_sequence,
+	.send_synack	=	tcp_v4_send_synack,
+	.queue_hash_add =	inet_csk_reqsk_queue_hash_add,
+};
 
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
-	struct tcp_options_received tmp_opt;
-	struct request_sock *req;
-	struct inet_request_sock *ireq;
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct dst_entry *dst = NULL;
-	__be32 saddr = ip_hdr(skb)->saddr;
-	__be32 daddr = ip_hdr(skb)->daddr;
-	__u32 isn = TCP_SKB_CB(skb)->when;
-	bool want_cookie = false, fastopen;
-	struct flowi4 fl4;
-	struct tcp_fastopen_cookie foc = { .len = -1 };
-	int err;
-
 	/* Never answer to SYNs send to broadcast or multicast */
 	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
 		goto drop;
 
-	/* TW buckets are converted to open requests without
-	 * limitations, they conserve resources and peer is
-	 * evidently real one.
-	 */
-	if ((sysctl_tcp_syncookies == 2 ||
-	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
-		want_cookie = tcp_syn_flood_action(sk, skb, "TCP");
-		if (!want_cookie)
-			goto drop;
-	}
+	return tcp_conn_request(&tcp_request_sock_ops,
+				&tcp_request_sock_ipv4_ops, sk, skb);
 
-	/* Accept backlog is full. If we have already queued enough
-	 * of warm entries in syn queue, drop request. It is better than
-	 * clogging syn queue with openreqs with exponentially increasing
-	 * timeout.
-	 */
-	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
-		goto drop;
-	}
-
-	req = inet_reqsk_alloc(&tcp_request_sock_ops);
-	if (!req)
-		goto drop;
-
-#ifdef CONFIG_TCP_MD5SIG
-	tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops;
-#endif
-
-	tcp_clear_options(&tmp_opt);
-	tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
-	tmp_opt.user_mss  = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
-
-	if (want_cookie && !tmp_opt.saw_tstamp)
-		tcp_clear_options(&tmp_opt);
-
-	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
-	tcp_openreq_init(req, &tmp_opt, skb, sk);
-
-	ireq = inet_rsk(req);
-	ireq->ir_loc_addr = daddr;
-	ireq->ir_rmt_addr = saddr;
-	ireq->no_srccheck = inet_sk(sk)->transparent;
-	ireq->opt = tcp_v4_save_options(skb);
-
-	if (security_inet_conn_request(sk, skb, req))
-		goto drop_and_free;
-
-	if (!want_cookie || tmp_opt.tstamp_ok)
-		TCP_ECN_create_request(req, skb, sock_net(sk));
-
-	if (want_cookie) {
-		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
-		req->cookie_ts = tmp_opt.tstamp_ok;
-	} else if (!isn) {
-		/* VJ's idea. We save last timestamp seen
-		 * from the destination in peer table, when entering
-		 * state TIME-WAIT, and check against it before
-		 * accepting new connection request.
-		 *
-		 * If "isn" is not zero, this request hit alive
-		 * timewait bucket, so that all the necessary checks
-		 * are made in the function processing timewait state.
-		 */
-		if (tmp_opt.saw_tstamp &&
-		    tcp_death_row.sysctl_tw_recycle &&
-		    (dst = inet_csk_route_req(sk, &fl4, req)) != NULL &&
-		    fl4.daddr == saddr) {
-			if (!tcp_peer_is_proven(req, dst, true)) {
-				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
-				goto drop_and_release;
-			}
-		}
-		/* Kill the following clause, if you dislike this way. */
-		else if (!sysctl_tcp_syncookies &&
-			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
-			  (sysctl_max_syn_backlog >> 2)) &&
-			 !tcp_peer_is_proven(req, dst, false)) {
-			/* Without syncookies last quarter of
-			 * backlog is filled with destinations,
-			 * proven to be alive.
-			 * It means that we continue to communicate
-			 * to destinations, already remembered
-			 * to the moment of synflood.
-			 */
-			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"),
-				       &saddr, ntohs(tcp_hdr(skb)->source));
-			goto drop_and_release;
-		}
-
-		isn = tcp_v4_init_sequence(skb);
-	}
-	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
-		goto drop_and_free;
-
-	tcp_rsk(req)->snt_isn = isn;
-	tcp_rsk(req)->snt_synack = tcp_time_stamp;
-	tcp_openreq_init_rwin(req, sk, dst);
-	fastopen = !want_cookie &&
-		   tcp_try_fastopen(sk, skb, req, &foc, dst);
-	err = tcp_v4_send_synack(sk, dst, req,
-				 skb_get_queue_mapping(skb), &foc);
-	if (!fastopen) {
-		if (err || want_cookie)
-			goto drop_and_free;
-
-		tcp_rsk(req)->snt_synack = tcp_time_stamp;
-		tcp_rsk(req)->listener = NULL;
-		inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
-	}
-
-	return 0;
-
-drop_and_release:
-	dst_release(dst);
-drop_and_free:
-	reqsk_free(req);
 drop:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return 0;

net/ipv4/tcp_output.c

@@ -3299,3 +3299,18 @@ void tcp_send_probe0(struct sock *sk)
 					  TCP_RTO_MAX);
 	}
 }
+
+int tcp_rtx_synack(struct sock *sk, struct request_sock *req)
+{
+	const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific;
+	struct flowi fl;
+	int res;
+
+	res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL);
+	if (!res) {
+		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+	}
+	return res;
+}
+EXPORT_SYMBOL(tcp_rtx_synack);

net/ipv6/syncookies.c

@@ -187,7 +187,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		goto out;
 
 	ret = NULL;
-	req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
+	req = inet_reqsk_alloc(&tcp6_request_sock_ops);
 	if (!req)
 		goto out;
 

net/ipv6/tcp_ipv6.c

@@ -470,13 +470,14 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 
 static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
-			      struct flowi6 *fl6,
+			      struct flowi *fl,
 			      struct request_sock *req,
 			      u16 queue_mapping,
 			      struct tcp_fastopen_cookie *foc)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct flowi6 *fl6 = &fl->u.ip6;
 	struct sk_buff *skb;
 	int err = -ENOMEM;
 
@@ -497,24 +498,14 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 		skb_set_queue_mapping(skb, queue_mapping);
 		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
 		err = net_xmit_eval(err);
+		if (!tcp_rsk(req)->snt_synack && !err)
+			tcp_rsk(req)->snt_synack = tcp_time_stamp;
 	}
 
 done:
 	return err;
 }
 
-static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req)
-{
-	struct flowi6 fl6;
-	int res;
-
-	res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0, NULL);
-	if (!res) {
-		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
-	}
-	return res;
-}
 
 static void tcp_v6_reqsk_destructor(struct request_sock *req)
 {
@@ -718,22 +709,66 @@ static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
 }
 #endif
 
+static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
+			    struct sk_buff *skb)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+
+	ireq->ir_iif = sk->sk_bound_dev_if;
+
+	/* So that link locals have meaning */
+	if (!sk->sk_bound_dev_if &&
+	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+		ireq->ir_iif = inet6_iif(skb);
+
+	if (!TCP_SKB_CB(skb)->when &&
+	    (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo ||
+	     np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
+	     np->rxopt.bits.rxohlim || np->repflow)) {
+		atomic_inc(&skb->users);
+		ireq->pktopts = skb;
+	}
+}
+
+static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl,
+					  const struct request_sock *req,
+					  bool *strict)
+{
+	if (strict)
+		*strict = true;
+	return inet6_csk_route_req(sk, &fl->u.ip6, req);
+}
+
 struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
 	.family		=	AF_INET6,
 	.obj_size	=	sizeof(struct tcp6_request_sock),
-	.rtx_syn_ack	=	tcp_v6_rtx_synack,
+	.rtx_syn_ack	=	tcp_rtx_synack,
 	.send_ack	=	tcp_v6_reqsk_send_ack,
 	.destructor	=	tcp_v6_reqsk_destructor,
 	.send_reset	=	tcp_v6_send_reset,
 	.syn_ack_timeout =	tcp_syn_ack_timeout,
 };
 
-#ifdef CONFIG_TCP_MD5SIG
 static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
+	.mss_clamp	=	IPV6_MIN_MTU - sizeof(struct tcphdr) -
+				sizeof(struct ipv6hdr),
+#ifdef CONFIG_TCP_MD5SIG
 	.md5_lookup	=	tcp_v6_reqsk_md5_lookup,
 	.calc_md5_hash	=	tcp_v6_md5_hash_skb,
-};
 #endif
+	.init_req	=	tcp_v6_init_req,
+#ifdef CONFIG_SYN_COOKIES
+	.cookie_init_seq =	cookie_v6_init_sequence,
+#endif
+	.route_req	=	tcp_v6_route_req,
+	.init_seq	=	tcp_v6_init_sequence,
+	.send_synack	=	tcp_v6_send_synack,
+	.queue_hash_add =	inet6_csk_reqsk_queue_hash_add,
+};
 
 static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 				 u32 tsval, u32 tsecr, int oif,
@@ -973,152 +1008,17 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
 	return sk;
 }
 
-/* FIXME: this is substantially similar to the ipv4 code.
- * Can some kind of merge be done? -- erics
- */
 static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
-	struct tcp_options_received tmp_opt;
-	struct request_sock *req;
-	struct inet_request_sock *ireq;
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct tcp_sock *tp = tcp_sk(sk);
-	__u32 isn = TCP_SKB_CB(skb)->when;
-	struct dst_entry *dst = NULL;
-	struct tcp_fastopen_cookie foc = { .len = -1 };
-	bool want_cookie = false, fastopen;
-	struct flowi6 fl6;
-	int err;
-
 	if (skb->protocol == htons(ETH_P_IP))
 		return tcp_v4_conn_request(sk, skb);
 
 	if (!ipv6_unicast_destination(skb))
 		goto drop;
 
-	if ((sysctl_tcp_syncookies == 2 ||
-	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
-		want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6");
-		if (!want_cookie)
-			goto drop;
-	}
-
-	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
-		goto drop;
-	}
-
-	req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
-	if (req == NULL)
-		goto drop;
-
-#ifdef CONFIG_TCP_MD5SIG
-	tcp_rsk(req)->af_specific = &tcp_request_sock_ipv6_ops;
-#endif
-
-	tcp_clear_options(&tmp_opt);
-	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
-	tmp_opt.user_mss = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
-
-	if (want_cookie && !tmp_opt.saw_tstamp)
-		tcp_clear_options(&tmp_opt);
-
-	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
-	tcp_openreq_init(req, &tmp_opt, skb, sk);
-
-	ireq = inet_rsk(req);
-	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
-	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
-	if (!want_cookie || tmp_opt.tstamp_ok)
-		TCP_ECN_create_request(req, skb, sock_net(sk));
-
-	ireq->ir_iif = sk->sk_bound_dev_if;
-
-	/* So that link locals have meaning */
-	if (!sk->sk_bound_dev_if &&
-	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq->ir_iif = inet6_iif(skb);
-
-	if (!isn) {
-		if (ipv6_opt_accepted(sk, skb) ||
-		    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
-		    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim ||
-		    np->repflow) {
-			atomic_inc(&skb->users);
-			ireq->pktopts = skb;
-		}
-
-		if (want_cookie) {
-			isn = cookie_v6_init_sequence(sk, skb, &req->mss);
-			req->cookie_ts = tmp_opt.tstamp_ok;
-			goto have_isn;
-		}
+	return tcp_conn_request(&tcp6_request_sock_ops,
+				&tcp_request_sock_ipv6_ops, sk, skb);
 
-		/* VJ's idea. We save last timestamp seen
-		 * from the destination in peer table, when entering
-		 * state TIME-WAIT, and check against it before
-		 * accepting new connection request.
-		 *
-		 * If "isn" is not zero, this request hit alive
-		 * timewait bucket, so that all the necessary checks
-		 * are made in the function processing timewait state.
-		 */
-		if (tmp_opt.saw_tstamp &&
-		    tcp_death_row.sysctl_tw_recycle &&
-		    (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) {
-			if (!tcp_peer_is_proven(req, dst, true)) {
-				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
-				goto drop_and_release;
-			}
-		}
-		/* Kill the following clause, if you dislike this way. */
-		else if (!sysctl_tcp_syncookies &&
-			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
-			  (sysctl_max_syn_backlog >> 2)) &&
-			 !tcp_peer_is_proven(req, dst, false)) {
-			/* Without syncookies last quarter of
-			 * backlog is filled with destinations,
-			 * proven to be alive.
-			 * It means that we continue to communicate
-			 * to destinations, already remembered
-			 * to the moment of synflood.
-			 */
-			LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n",
-				       &ireq->ir_v6_rmt_addr, ntohs(tcp_hdr(skb)->source));
-			goto drop_and_release;
-		}
-
-		isn = tcp_v6_init_sequence(skb);
-	}
-have_isn:
-
-	if (security_inet_conn_request(sk, skb, req))
-		goto drop_and_release;
-
-	if (!dst && (dst = inet6_csk_route_req(sk, &fl6, req)) == NULL)
-		goto drop_and_free;
-
-	tcp_rsk(req)->snt_isn = isn;
-	tcp_rsk(req)->snt_synack = tcp_time_stamp;
-	tcp_openreq_init_rwin(req, sk, dst);
-	fastopen = !want_cookie &&
-		   tcp_try_fastopen(sk, skb, req, &foc, dst);
-	err = tcp_v6_send_synack(sk, dst, &fl6, req,
-				 skb_get_queue_mapping(skb), &foc);
-	if (!fastopen) {
-		if (err || want_cookie)
-			goto drop_and_free;
-
-		tcp_rsk(req)->listener = NULL;
-		inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
-	}
-	return 0;
-
-drop_and_release:
-	dst_release(dst);
-drop_and_free:
-	reqsk_free(req);
 drop:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return 0; /* don't send reset */