1 files changed, 273 insertions, 155 deletions

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b1a63b2c6b4..e68e0d4af6c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -5,8 +5,6 @@
  *
  *		Implementation of the Transmission Control Protocol(TCP).
  *
- * Version:	$Id: tcp_minisocks.c,v 1.15 2002/02/01 22:01:04 davem Exp $
- *
  * Authors:	Ross Biro
  *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
  *		Mark Evans, <evansmp@uhura.aston.ac.uk>
@@ -20,53 +18,47 @@
  *		Jorge Cwik, <jorge@laser.satlink.net>
  */
 
-#include <linux/config.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/sysctl.h>
 #include <linux/workqueue.h>
 #include <net/tcp.h>
 #include <net/inet_common.h>
 #include <net/xfrm.h>
 
-#ifdef CONFIG_SYSCTL
-#define SYNC_INIT 0 /* let the user enable it */
-#else
-#define SYNC_INIT 1
-#endif
+int sysctl_tcp_syncookies __read_mostly = 1;
+EXPORT_SYMBOL(sysctl_tcp_syncookies);
 
-int sysctl_tcp_syncookies = SYNC_INIT; 
-int sysctl_tcp_abort_on_overflow;
+int sysctl_tcp_abort_on_overflow __read_mostly;
 
 struct inet_timewait_death_row tcp_death_row = {
 	.sysctl_max_tw_buckets = NR_FILE * 2,
 	.period		= TCP_TIMEWAIT_LEN / INET_TWDR_TWKILL_SLOTS,
-	.death_lock	= SPIN_LOCK_UNLOCKED,
+	.death_lock	= __SPIN_LOCK_UNLOCKED(tcp_death_row.death_lock),
 	.hashinfo	= &tcp_hashinfo,
 	.tw_timer	= TIMER_INITIALIZER(inet_twdr_hangman, 0,
 					    (unsigned long)&tcp_death_row),
 	.twkill_work	= __WORK_INITIALIZER(tcp_death_row.twkill_work,
-					     inet_twdr_twkill_work,
-					     &tcp_death_row),
+					     inet_twdr_twkill_work),
 /* Short-time timewait calendar */
 
 	.twcal_hand	= -1,
 	.twcal_timer	= TIMER_INITIALIZER(inet_twdr_twcal_tick, 0,
 					    (unsigned long)&tcp_death_row),
 };
-
 EXPORT_SYMBOL_GPL(tcp_death_row);
 
-static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
+static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 {
 	if (seq == s_win)
-		return 1;
+		return true;
 	if (after(end_seq, s_win) && before(seq, e_win))
-		return 1;
-	return (seq == e_win && seq == end_seq);
+		return true;
+	return seq == e_win && seq == end_seq;
 }
 
-/* 
+/*
  * * Main purpose of TIME-WAIT state is to close connection gracefully,
  *   when one of ends sits in LAST-ACK or CLOSING retransmitting FIN
  *   (and, probably, tail of data) and one or more our ACKs are lost.
@@ -93,23 +85,26 @@ static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
  * spinlock it. I do not want! Well, probability of misbehaviour
  * is ridiculously low and, seems, we could use some mb() tricks
  * to avoid misread sequence numbers, states etc.  --ANK
+ *
+ * We don't need to initialize tmp_out.sack_ok as we don't use the results
  */
 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;
-	int paws_reject = 0;
+	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
+	bool paws_reject = false;
 
 	tmp_opt.saw_tstamp = 0;
 	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
-		tcp_parse_options(skb, &tmp_opt, 0);
+		tcp_parse_options(skb, &tmp_opt, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
+			tmp_opt.rcv_tsecr	-= tcptw->tw_ts_offset;
 			tmp_opt.ts_recent	= tcptw->tw_ts_recent;
 			tmp_opt.ts_recent_stamp	= tcptw->tw_ts_recent_stamp;
-			paws_reject = tcp_paws_check(&tmp_opt, th->rst);
+			paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
 		}
 	}
 
@@ -130,7 +125,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			goto kill_with_rst;
 
 		/* Dup ACK? */
-		if (!after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) ||
+		if (!th->ack ||
+		    !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) ||
 		    TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) {
 			inet_twsk_put(tw);
 			return TCP_TW_SUCCESS;
@@ -151,18 +147,13 @@ kill_with_rst:
 		tw->tw_substate	  = TCP_TIME_WAIT;
 		tcptw->tw_rcv_nxt = TCP_SKB_CB(skb)->end_seq;
 		if (tmp_opt.saw_tstamp) {
-			tcptw->tw_ts_recent_stamp = xtime.tv_sec;
+			tcptw->tw_ts_recent_stamp = get_seconds();
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
 		}
 
-		/* I am shamed, but failed to make it more elegant.
-		 * Yes, it is direct reference to IP, which is impossible
-		 * to generalize to IPv6. Taking into account that IPv6
-		 * do not undertsnad recycling in any case, it not
-		 * a big problem in practice. --ANK */
-		if (tw->tw_family == AF_INET &&
-		    tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp &&
-		    tcp_v4_tw_remember_stamp(tw))
+		if (tcp_death_row.sysctl_tw_recycle &&
+		    tcptw->tw_ts_recent_stamp &&
+		    tcp_tw_remember_stamp(tw))
 			inet_twsk_schedule(tw, &tcp_death_row, tw->tw_timeout,
 					   TCP_TIMEWAIT_LEN);
 		else
@@ -178,13 +169,13 @@ kill_with_rst:
 	 *	"When a connection is [...] on TIME-WAIT state [...]
 	 *	[a TCP] MAY accept a new SYN from the remote TCP to
 	 *	reopen the connection directly, if it:
-	 *	
+	 *
 	 *	(1)  assigns its initial sequence number for the new
 	 *	connection to be larger than the largest sequence
 	 *	number it used on the previous connection incarnation,
 	 *	and
 	 *
-	 *	(2)  returns to TIME-WAIT state if the SYN turns out 
+	 *	(2)  returns to TIME-WAIT state if the SYN turns out
 	 *	to be an old duplicate".
 	 */
 
@@ -194,7 +185,7 @@ kill_with_rst:
 		/* In window segment, it may be only reset or bare ack. */
 
 		if (th->rst) {
-			/* This is TIME_WAIT assasination, in two flavors.
+			/* This is TIME_WAIT assassination, in two flavors.
 			 * Oh well... nobody has a sufficient solution to this
 			 * protocol bug yet.
 			 */
@@ -210,7 +201,7 @@ kill:
 
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
-			tcptw->tw_ts_recent_stamp = xtime.tv_sec;
+			tcptw->tw_ts_recent_stamp = get_seconds();
 		}
 
 		inet_twsk_put(tw);
@@ -246,9 +237,9 @@ kill:
 	}
 
 	if (paws_reject)
-		NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED);
+		NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_PAWSESTABREJECTED);
 
-	if(!th->rst) {
+	if (!th->rst) {
 		/* In this case we must reset the TIMEWAIT timer.
 		 *
 		 * If it is ACKless SYN it may be both old duplicate
@@ -267,44 +258,69 @@ kill:
 	inet_twsk_put(tw);
 	return TCP_TW_SUCCESS;
 }
+EXPORT_SYMBOL(tcp_timewait_state_process);
 
-/* 
+/*
  * Move a socket to time-wait or dead fin-wait-2 state.
- */ 
+ */
 void tcp_time_wait(struct sock *sk, int state, int timeo)
 {
 	struct inet_timewait_sock *tw = NULL;
+	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
-	int recycle_ok = 0;
+	bool recycle_ok = false;
 
 	if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)
-		recycle_ok = tp->af_specific->remember_stamp(sk);
+		recycle_ok = tcp_remember_stamp(sk);
 
 	if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets)
 		tw = inet_twsk_alloc(sk, state);
 
 	if (tw != NULL) {
 		struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
-		const struct inet_connection_sock *icsk = inet_csk(sk);
 		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
+		struct inet_sock *inet = inet_sk(sk);
 
+		tw->tw_transparent	= inet->transparent;
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
 		tcptw->tw_rcv_nxt	= tp->rcv_nxt;
 		tcptw->tw_snd_nxt	= tp->snd_nxt;
 		tcptw->tw_rcv_wnd	= tcp_receive_window(tp);
 		tcptw->tw_ts_recent	= tp->rx_opt.ts_recent;
 		tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
+		tcptw->tw_ts_offset	= tp->tsoffset;
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(sk);
-			struct tcp6_timewait_sock *tcp6tw = tcp6_twsk((struct sock *)tw);
 
-			ipv6_addr_copy(&tcp6tw->tw_v6_daddr, &np->daddr);
-			ipv6_addr_copy(&tcp6tw->tw_v6_rcv_saddr, &np->rcv_saddr);
+			tw->tw_v6_daddr = sk->sk_v6_daddr;
+			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+			tw->tw_tclass = np->tclass;
+			tw->tw_flowlabel = np->flow_label >> 12;
 			tw->tw_ipv6only = np->ipv6only;
 		}
 #endif
+
+#ifdef CONFIG_TCP_MD5SIG
+		/*
+		 * The timewait bucket does not have the key DB from the
+		 * sock structure. We just make a quick copy of the
+		 * md5 key being used (if indeed we are using one)
+		 * so the timewait ack generating code has the key.
+		 */
+		do {
+			struct tcp_md5sig_key *key;
+			tcptw->tw_md5_key = NULL;
+			key = tp->af_specific->md5_lookup(sk, sk);
+			if (key != NULL) {
+				tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
+				if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool())
+					BUG();
+			}
+		} while (0);
+#endif
+
 		/* Linkage updates. */
 		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
 
@@ -328,14 +344,61 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		 * socket up.  We've got bigger problems than
 		 * non-graceful socket closings.
 		 */
-		if (net_ratelimit())
-			printk(KERN_INFO "TCP: time wait bucket table overflow\n");
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEWAITOVERFLOW);
 	}
 
 	tcp_update_metrics(sk);
 	tcp_done(sk);
 }
 
+void tcp_twsk_destructor(struct sock *sk)
+{
+#ifdef CONFIG_TCP_MD5SIG
+	struct tcp_timewait_sock *twsk = tcp_twsk(sk);
+
+	if (twsk->tw_md5_key)
+		kfree_rcu(twsk->tw_md5_key, rcu);
+#endif
+}
+EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
+
+void tcp_openreq_init_rwin(struct request_sock *req,
+			   struct sock *sk, struct dst_entry *dst)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+	struct tcp_sock *tp = tcp_sk(sk);
+	__u8 rcv_wscale;
+	int mss = dst_metric_advmss(dst);
+
+	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
+		mss = tp->rx_opt.user_mss;
+
+	/* Set this up on the first call only */
+	req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
+		req->window_clamp = tcp_full_space(sk);
+
+	/* tcp_full_space because it is guaranteed to be the first packet */
+	tcp_select_initial_window(tcp_full_space(sk),
+		mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
+		&req->rcv_wnd,
+		&req->window_clamp,
+		ireq->wscale_ok,
+		&rcv_wscale,
+		dst_metric(dst, RTAX_INITRWND));
+	ireq->rcv_wscale = rcv_wscale;
+}
+EXPORT_SYMBOL(tcp_openreq_init_rwin);
+
+static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
+					 struct request_sock *req)
+{
+	tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0;
+}
+
 /* This is not only more efficient than what we used to do, it eliminates
  * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
  *
@@ -344,62 +407,64 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
  */
 struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb)
 {
-	struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC);
+	struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
 
 	if (newsk != NULL) {
 		const struct inet_request_sock *ireq = inet_rsk(req);
 		struct tcp_request_sock *treq = tcp_rsk(req);
-		struct inet_connection_sock *newicsk = inet_csk(sk);
-		struct tcp_sock *newtp;
+		struct inet_connection_sock *newicsk = inet_csk(newsk);
+		struct tcp_sock *newtp = tcp_sk(newsk);
 
 		/* 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_nxt = newtp->snd_una = newtp->snd_sml = treq->snt_isn + 1;
+
+		newtp->snd_sml = newtp->snd_una =
+		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
 
 		tcp_prequeue_init(newtp);
+		INIT_LIST_HEAD(&newtp->tsq_node);
 
-		tcp_init_wl(newtp, treq->snt_isn, treq->rcv_isn);
+		tcp_init_wl(newtp, treq->rcv_isn);
 
-		newtp->srtt = 0;
-		newtp->mdev = TCP_TIMEOUT_INIT;
+		newtp->srtt_us = 0;
+		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
 
 		newtp->packets_out = 0;
-		newtp->left_out = 0;
 		newtp->retrans_out = 0;
 		newtp->sacked_out = 0;
 		newtp->fackets_out = 0;
-		newtp->snd_ssthresh = 0x7fffffff;
+		newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+		tcp_enable_early_retrans(newtp);
+		newtp->tlp_high_seq = 0;
+		newtp->lsndtime = treq->snt_synack;
+		newtp->total_retrans = req->num_retrans;
 
 		/* So many TCP implementations out there (incorrectly) count the
 		 * initial SYN frame in their delayed-ACK and congestion control
 		 * algorithms that we must have the following bandaid to talk
 		 * efficiently to them.  -DaveM
 		 */
-		newtp->snd_cwnd = 2;
+		newtp->snd_cwnd = TCP_INIT_CWND;
 		newtp->snd_cwnd_cnt = 0;
 
-		newtp->frto_counter = 0;
-		newtp->frto_highmark = 0;
-
-		newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
+		if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops &&
+		    !try_module_get(newicsk->icsk_ca_ops->owner))
+			newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
 
 		tcp_set_ca_state(newsk, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
-		skb_queue_head_init(&newtp->out_of_order_queue);
-		newtp->rcv_wup = treq->rcv_isn + 1;
-		newtp->write_seq = treq->snt_isn + 1;
-		newtp->pushed_seq = newtp->write_seq;
-		newtp->copied_seq = treq->rcv_isn + 1;
+		__skb_queue_head_init(&newtp->out_of_order_queue);
+		newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
 
 		newtp->rx_opt.saw_tstamp = 0;
 
 		newtp->rx_opt.dsack = 0;
-		newtp->rx_opt.eff_sacks = 0;
-
 		newtp->rx_opt.num_sacks = 0;
+
 		newtp->urg_data = 0;
 
 		if (sock_flag(newsk, SOCK_KEEPOPEN))
@@ -407,9 +472,9 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 						       keepalive_time_when(newtp));
 
 		newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
-		if((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
+		if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
 			if (sysctl_tcp_fack)
-				newtp->rx_opt.sack_ok |= 2;
+				tcp_enable_fack(newtp);
 		}
 		newtp->window_clamp = req->window_clamp;
 		newtp->rcv_ssthresh = req->rcv_wnd;
@@ -422,48 +487,64 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 			newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
 			newtp->window_clamp = min(newtp->window_clamp, 65535U);
 		}
-		newtp->snd_wnd = ntohs(skb->h.th->window) << newtp->rx_opt.snd_wscale;
+		newtp->snd_wnd = (ntohs(tcp_hdr(skb)->window) <<
+				  newtp->rx_opt.snd_wscale);
 		newtp->max_window = newtp->snd_wnd;
 
 		if (newtp->rx_opt.tstamp_ok) {
 			newtp->rx_opt.ts_recent = req->ts_recent;
-			newtp->rx_opt.ts_recent_stamp = xtime.tv_sec;
+			newtp->rx_opt.ts_recent_stamp = get_seconds();
 			newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
 		} else {
 			newtp->rx_opt.ts_recent_stamp = 0;
 			newtp->tcp_header_len = sizeof(struct tcphdr);
 		}
-		if (skb->len >= TCP_MIN_RCVMSS+newtp->tcp_header_len)
+		newtp->tsoffset = 0;
+#ifdef CONFIG_TCP_MD5SIG
+		newtp->md5sig_info = NULL;	/*XXX*/
+		if (newtp->af_specific->md5_lookup(sk, newsk))
+			newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
+#endif
+		if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 			newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
 		newtp->rx_opt.mss_clamp = req->mss;
 		TCP_ECN_openreq_child(newtp, req);
-		if (newtp->ecn_flags&TCP_ECN_OK)
-			sock_set_flag(newsk, SOCK_NO_LARGESEND);
+		newtp->fastopen_rsk = NULL;
+		newtp->syn_data_acked = 0;
 
-		TCP_INC_STATS_BH(TCP_MIB_PASSIVEOPENS);
+		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS);
 	}
 	return newsk;
 }
+EXPORT_SYMBOL(tcp_create_openreq_child);
 
-/* 
- *	Process an incoming packet for SYN_RECV sockets represented
- *	as a request_sock.
+/*
+ * Process an incoming packet for SYN_RECV sockets represented as a
+ * request_sock. Normally sk is the listener socket but for TFO it
+ * points to the child socket.
+ *
+ * XXX (TFO) - The current impl contains a special check for ack
+ * validation and inside tcp_v4_reqsk_send_ack(). Can we do better?
+ *
+ * We don't need to initialize tmp_opt.sack_ok as we don't use the results
  */
 
-struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
+struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			   struct request_sock *req,
-			   struct request_sock **prev)
+			   struct request_sock **prev,
+			   bool fastopen)
 {
-	struct tcphdr *th = skb->h.th;
-	struct tcp_sock *tp = tcp_sk(sk);
-	u32 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;
+	const struct tcphdr *th = tcp_hdr(skb);
+	__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
+	bool paws_reject = false;
+
+	BUG_ON(fastopen == (sk->sk_state == TCP_LISTEN));
 
 	tmp_opt.saw_tstamp = 0;
 	if (th->doff > (sizeof(struct tcphdr)>>2)) {
-		tcp_parse_options(skb, &tmp_opt, 0);
+		tcp_parse_options(skb, &tmp_opt, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent = req->ts_recent;
@@ -471,8 +552,8 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 			 * it can be estimated (approximately)
 			 * from another data.
 			 */
-			tmp_opt.ts_recent_stamp = xtime.tv_sec - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans);
-			paws_reject = tcp_paws_check(&tmp_opt, th->rst);
+			tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout);
+			paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
 		}
 	}
 
@@ -496,8 +577,16 @@ 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.
+		 *
+		 * Note that even if there is new data in the SYN packet
+		 * they will be thrown away too.
+		 *
+		 * Reset timer after retransmitting SYNACK, similar to
+		 * the idea of fast retransmit in recovery.
 		 */
-		req->rsk_ops->rtx_syn_ack(sk, req, NULL);
+		if (!inet_rtx_syn_ack(sk, req))
+			req->expires = min(TCP_TIMEOUT_INIT << req->num_timeout,
+					   TCP_RTO_MAX) + jiffies;
 		return NULL;
 	}
 
@@ -550,13 +639,17 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 
 	/* RFC793 page 36: "If the connection is in any non-synchronized state ...
 	 *                  and the incoming segment acknowledges something not yet
-	 *                  sent (the segment carries an unaccaptable ACK) ...
+	 *                  sent (the segment carries an unacceptable ACK) ...
 	 *                  a reset is sent."
 	 *
-	 * Invalid ACK: reset will be sent by listening socket
+	 * Invalid ACK: reset will be sent by listening socket.
+	 * Note that the ACK validity check for a Fast Open socket is done
+	 * elsewhere and is checked directly against the child socket rather
+	 * than req because user data may have been sent out.
 	 */
-	if ((flg & TCP_FLAG_ACK) &&
-	    (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1))
+	if ((flg & TCP_FLAG_ACK) && !fastopen &&
+	    (TCP_SKB_CB(skb)->ack_seq !=
+	     tcp_rsk(req)->snt_isn + 1))
 		return sk;
 
 	/* Also, it would be not so bad idea to check rcv_tsecr, which
@@ -567,80 +660,109 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 	/* RFC793: "first check sequence number". */
 
 	if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
-					  tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) {
+					  tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rcv_wnd)) {
 		/* Out of window: send ACK and drop. */
 		if (!(flg & TCP_FLAG_RST))
-			req->rsk_ops->send_ack(skb, req);
+			req->rsk_ops->send_ack(sk, skb, req);
 		if (paws_reject)
-			NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED);
+			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
 		return NULL;
 	}
 
 	/* In sequence, PAWS is OK. */
 
-	if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1))
-			req->ts_recent = tmp_opt.rcv_tsval;
+	if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
+		req->ts_recent = tmp_opt.rcv_tsval;
 
-		if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
-			/* Truncate SYN, it is out of window starting
-			   at tcp_rsk(req)->rcv_isn + 1. */
-			flg &= ~TCP_FLAG_SYN;
-		}
+	if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
+		/* Truncate SYN, it is out of window starting
+		   at tcp_rsk(req)->rcv_isn + 1. */
+		flg &= ~TCP_FLAG_SYN;
+	}
 
-		/* RFC793: "second check the RST bit" and
-		 *	   "fourth, check the SYN bit"
-		 */
-		if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN))
-			goto embryonic_reset;
+	/* RFC793: "second check the RST bit" and
+	 *	   "fourth, check the SYN bit"
+	 */
+	if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) {
+		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
+		goto embryonic_reset;
+	}
 
-		/* ACK sequence verified above, just make sure ACK is
-		 * set.  If ACK not set, just silently drop the packet.
-		 */
-		if (!(flg & TCP_FLAG_ACK))
-			return NULL;
-
-		/* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
-		if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
-		    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
-			inet_rsk(req)->acked = 1;
-			return NULL;
-		}
+	/* ACK sequence verified above, just make sure ACK is
+	 * set.  If ACK not set, just silently drop the packet.
+	 *
+	 * XXX (TFO) - if we ever allow "data after SYN", the
+	 * following check needs to be removed.
+	 */
+	if (!(flg & TCP_FLAG_ACK))
+		return NULL;
 
-		/* OK, ACK is valid, create big socket and
-		 * feed this segment to it. It will repeat all
-		 * the tests. THIS SEGMENT MUST MOVE SOCKET TO
-		 * ESTABLISHED STATE. If it will be dropped after
-		 * socket is created, wait for troubles.
-		 */
-		child = tp->af_specific->syn_recv_sock(sk, skb, req, NULL);
-		if (child == NULL)
-			goto listen_overflow;
+	/* For Fast Open no more processing is needed (sk is the
+	 * child socket).
+	 */
+	if (fastopen)
+		return sk;
 
-		inet_csk_reqsk_queue_unlink(sk, req, prev);
-		inet_csk_reqsk_queue_removed(sk, req);
+	/* While TCP_DEFER_ACCEPT is active, drop bare ACK. */
+	if (req->num_timeout < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+	    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
+		inet_rsk(req)->acked = 1;
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP);
+		return NULL;
+	}
 
-		inet_csk_reqsk_queue_add(sk, req, child);
-		return child;
+	/* OK, ACK is valid, create big socket and
+	 * feed this segment to it. It will repeat all
+	 * the tests. THIS SEGMENT MUST MOVE SOCKET TO
+	 * ESTABLISHED STATE. If it will be dropped after
+	 * socket is created, wait for troubles.
+	 */
+	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
+	if (child == NULL)
+		goto listen_overflow;
 
-	listen_overflow:
-		if (!sysctl_tcp_abort_on_overflow) {
-			inet_rsk(req)->acked = 1;
-			return NULL;
-		}
+	inet_csk_reqsk_queue_unlink(sk, req, prev);
+	inet_csk_reqsk_queue_removed(sk, req);
 
-	embryonic_reset:
-		NET_INC_STATS_BH(LINUX_MIB_EMBRYONICRSTS);
-		if (!(flg & TCP_FLAG_RST))
-			req->rsk_ops->send_reset(skb);
+	inet_csk_reqsk_queue_add(sk, req, child);
+	return child;
 
-		inet_csk_reqsk_queue_drop(sk, req, prev);
+listen_overflow:
+	if (!sysctl_tcp_abort_on_overflow) {
+		inet_rsk(req)->acked = 1;
 		return NULL;
+	}
+
+embryonic_reset:
+	if (!(flg & TCP_FLAG_RST)) {
+		/* Received a bad SYN pkt - for TFO We try not to reset
+		 * the local connection unless it's really necessary to
+		 * avoid becoming vulnerable to outside attack aiming at
+		 * resetting legit local connections.
+		 */
+		req->rsk_ops->send_reset(sk, skb);
+	} else if (fastopen) { /* received a valid RST pkt */
+		reqsk_fastopen_remove(sk, req, true);
+		tcp_reset(sk);
+	}
+	if (!fastopen) {
+		inet_csk_reqsk_queue_drop(sk, req, prev);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
+	}
+	return NULL;
 }
+EXPORT_SYMBOL(tcp_check_req);
 
 /*
  * Queue segment on the new socket if the new socket is active,
  * otherwise we just shortcircuit this and continue with
  * the new socket.
+ *
+ * For the vast majority of cases child->sk_state will be TCP_SYN_RECV
+ * when entering. But other states are possible due to a race condition
+ * where after __inet_lookup_established() fails but before the listener
+ * locked is obtained, other packets cause the same connection to
+ * be created.
  */
 
 int tcp_child_process(struct sock *parent, struct sock *child,
@@ -650,25 +772,21 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int state = child->sk_state;
 
 	if (!sock_owned_by_user(child)) {
-		ret = tcp_rcv_state_process(child, skb, skb->h.th, skb->len);
-
+		ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb),
+					    skb->len);
 		/* Wakeup parent, send SIGIO */
 		if (state == TCP_SYN_RECV && child->sk_state != state)
-			parent->sk_data_ready(parent, 0);
+			parent->sk_data_ready(parent);
 	} else {
 		/* Alas, it is possible again, because we do lookup
 		 * in main socket hash table and lock on listening
 		 * socket does not protect us more.
 		 */
-		sk_add_backlog(child, skb);
+		__sk_add_backlog(child, skb);
 	}
 
 	bh_unlock_sock(child);
 	sock_put(child);
 	return ret;
 }
-
-EXPORT_SYMBOL(tcp_check_req);
 EXPORT_SYMBOL(tcp_child_process);
-EXPORT_SYMBOL(tcp_create_openreq_child);
-EXPORT_SYMBOL(tcp_timewait_state_process);