1 files changed, 77 insertions, 46 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 218235de8963..19f4150f4d4d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -41,6 +41,7 @@
 #include <net/ip.h>
 #include <net/tcp_states.h>
 #include <net/inet_ecn.h>
+#include <net/dst.h>
 
 #include <linux/seq_file.h>
 
@@ -265,6 +266,19 @@ static inline int tcp_too_many_orphans(struct sock *sk, int num)
 		 atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]);
 }
 
+/* syncookies: remember time of last synqueue overflow */
+static inline void tcp_synq_overflow(struct sock *sk)
+{
+	tcp_sk(sk)->rx_opt.ts_recent_stamp = jiffies;
+}
+
+/* syncookies: no recent synqueue overflow on this listening socket? */
+static inline int tcp_synq_no_recent_overflow(const struct sock *sk)
+{
+	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	return time_after(jiffies, last_overflow + TCP_TIMEOUT_INIT);
+}
+
 extern struct proto tcp_prot;
 
 #define TCP_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.tcp_statistics, field)
@@ -481,7 +495,16 @@ static inline void tcp_clear_xmit_timers(struct sock *sk)
 }
 
 extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
-extern unsigned int tcp_current_mss(struct sock *sk, int large);
+extern unsigned int tcp_current_mss(struct sock *sk);
+
+/* Bound MSS / TSO packet size with the half of the window */
+static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
+{
+	if (tp->max_window && pktsize > (tp->max_window >> 1))
+		return max(tp->max_window >> 1, 68U - tp->tcp_header_len);
+	else
+		return pktsize;
+}
 
 /* tcp.c */
 extern void tcp_get_info(struct sock *, struct tcp_info *);
@@ -521,6 +544,17 @@ static inline void tcp_fast_path_check(struct sock *sk)
 		tcp_fast_path_on(tp);
 }
 
+/* Compute the actual rto_min value */
+static inline u32 tcp_rto_min(struct sock *sk)
+{
+	struct dst_entry *dst = __sk_dst_get(sk);
+	u32 rto_min = TCP_RTO_MIN;
+
+	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
+		rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
+	return rto_min;
+}
+
 /* Compute the actual receive window we are currently advertising.
  * Rcv_nxt can be after the window if our peer push more data
  * than the offered window.
@@ -607,21 +641,6 @@ static inline int tcp_skb_mss(const struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_size;
 }
 
-static inline void tcp_dec_pcount_approx_int(__u32 *count, const int decr)
-{
-	if (*count) {
-		*count -= decr;
-		if ((int)*count < 0)
-			*count = 0;
-	}
-}
-
-static inline void tcp_dec_pcount_approx(__u32 *count,
-					 const struct sk_buff *skb)
-{
-	tcp_dec_pcount_approx_int(count, tcp_skb_pcount(skb));
-}
-
 /* Events passed to congestion control interface */
 enum tcp_ca_event {
 	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
@@ -685,6 +704,7 @@ extern void tcp_get_allowed_congestion_control(char *buf, size_t len);
 extern int tcp_set_allowed_congestion_control(char *allowed);
 extern int tcp_set_congestion_control(struct sock *sk, const char *name);
 extern void tcp_slow_start(struct tcp_sock *tp);
+extern void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
 
 extern struct tcp_congestion_ops tcp_init_congestion_ops;
 extern u32 tcp_reno_ssthresh(struct sock *sk);
@@ -821,15 +841,15 @@ static inline void tcp_push_pending_frames(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	__tcp_push_pending_frames(sk, tcp_current_mss(sk, 1), tp->nonagle);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle);
 }
 
-static inline void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
+static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
 {
 	tp->snd_wl1 = seq;
 }
 
-static inline void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
+static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq)
 {
 	tp->snd_wl1 = seq;
 }
@@ -882,30 +902,32 @@ static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (!sysctl_tcp_low_latency && tp->ucopy.task) {
-		__skb_queue_tail(&tp->ucopy.prequeue, skb);
-		tp->ucopy.memory += skb->truesize;
-		if (tp->ucopy.memory > sk->sk_rcvbuf) {
-			struct sk_buff *skb1;
-
-			BUG_ON(sock_owned_by_user(sk));
-
-			while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
-				sk_backlog_rcv(sk, skb1);
-				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED);
-			}
-
-			tp->ucopy.memory = 0;
-		} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
-			wake_up_interruptible(sk->sk_sleep);
-			if (!inet_csk_ack_scheduled(sk))
-				inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-						          (3 * TCP_RTO_MIN) / 4,
-							  TCP_RTO_MAX);
+	if (sysctl_tcp_low_latency || !tp->ucopy.task)
+		return 0;
+
+	__skb_queue_tail(&tp->ucopy.prequeue, skb);
+	tp->ucopy.memory += skb->truesize;
+	if (tp->ucopy.memory > sk->sk_rcvbuf) {
+		struct sk_buff *skb1;
+
+		BUG_ON(sock_owned_by_user(sk));
+
+		while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
+			sk_backlog_rcv(sk, skb1);
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPPREQUEUEDROPPED);
 		}
-		return 1;
+
+		tp->ucopy.memory = 0;
+	} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
+		wake_up_interruptible_poll(sk->sk_sleep,
+					   POLLIN | POLLRDNORM | POLLRDBAND);
+		if (!inet_csk_ack_scheduled(sk))
+			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+						  (3 * tcp_rto_min(sk)) / 4,
+						  TCP_RTO_MAX);
 	}
-	return 0;
+	return 1;
 }
 
 
@@ -925,7 +947,6 @@ extern void tcp_done(struct sock *sk);
 static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 {
 	rx_opt->dsack = 0;
-	rx_opt->eff_sacks = 0;
 	rx_opt->num_sacks = 0;
 }
 
@@ -997,11 +1018,21 @@ static inline int tcp_fin_time(const struct sock *sk)
 	return fin_timeout;
 }
 
-static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int rst)
+static inline int tcp_paws_check(const struct tcp_options_received *rx_opt,
+				 int paws_win)
 {
-	if ((s32)(rx_opt->rcv_tsval - rx_opt->ts_recent) >= 0)
-		return 0;
-	if (get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)
+	if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
+		return 1;
+	if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))
+		return 1;
+
+	return 0;
+}
+
+static inline int tcp_paws_reject(const struct tcp_options_received *rx_opt,
+				  int rst)
+{
+	if (tcp_paws_check(rx_opt, 0))
 		return 0;
 
 	/* RST segments are not recommended to carry timestamp,