1 files changed, 44 insertions, 28 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ec335fabd5cc..e6bb8256e59f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -65,6 +65,9 @@ int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 
+unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX;
+EXPORT_SYMBOL(sysctl_tcp_notsent_lowat);
+
 static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			   int push_one, gfp_t gfp);
 
@@ -160,6 +163,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const u32 now = tcp_time_stamp;
+	const struct dst_entry *dst = __sk_dst_get(sk);
 
 	if (sysctl_tcp_slow_start_after_idle &&
 	    (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto))
@@ -170,8 +174,9 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 	/* If it is a reply for ato after last received
 	 * packet, enter pingpong mode.
 	 */
-	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
-		icsk->icsk_ack.pingpong = 1;
+	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato &&
+	    (!dst || !dst_metric(dst, RTAX_QUICKACK)))
+			icsk->icsk_ack.pingpong = 1;
 }
 
 /* Account for an ACK we sent. */
@@ -181,6 +186,21 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
 
+
+u32 tcp_default_init_rwnd(u32 mss)
+{
+	/* Initial receive window should be twice of TCP_INIT_CWND to
+	 * enable proper sending of new unsent data during fast recovery
+	 * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a
+	 * limit when mss is larger than 1460.
+	 */
+	u32 init_rwnd = TCP_INIT_CWND * 2;
+
+	if (mss > 1460)
+		init_rwnd = max((1460 * init_rwnd) / mss, 2U);
+	return init_rwnd;
+}
+
 /* Determine a window scaling and initial window to offer.
  * Based on the assumption that the given amount of space
  * will be offered. Store the results in the tp structure.
@@ -230,22 +250,10 @@ void tcp_select_initial_window(int __space, __u32 mss,
 		}
 	}
 
-	/* Set initial window to a value enough for senders starting with
-	 * initial congestion window of TCP_DEFAULT_INIT_RCVWND. Place
-	 * a limit on the initial window when mss is larger than 1460.
-	 */
 	if (mss > (1 << *rcv_wscale)) {
-		int init_cwnd = TCP_DEFAULT_INIT_RCVWND;
-		if (mss > 1460)
-			init_cwnd =
-			max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
-		/* when initializing use the value from init_rcv_wnd
-		 * rather than the default from above
-		 */
-		if (init_rcv_wnd)
-			*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
-		else
-			*rcv_wnd = min(*rcv_wnd, init_cwnd * mss);
+		if (!init_rcv_wnd) /* Use default unless specified otherwise */
+			init_rcv_wnd = tcp_default_init_rwnd(mss);
+		*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
 	}
 
 	/* Set the clamp no higher than max representable value */
@@ -887,8 +895,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	skb_orphan(skb);
 	skb->sk = sk;
-	skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
-			  tcp_wfree : sock_wfree;
+	skb->destructor = tcp_wfree;
 	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
 	/* Build TCP header and checksum it. */
@@ -1623,7 +1630,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 
 	/* If a full-sized TSO skb can be sent, do it. */
 	if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
-			   sk->sk_gso_max_segs * tp->mss_cache))
+			   tp->xmit_size_goal_segs * tp->mss_cache))
 		goto send_now;
 
 	/* Middle in queue won't get any more data, full sendable already? */
@@ -1832,7 +1839,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
-
 		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
 		BUG_ON(!tso_segs);
 
@@ -1861,13 +1867,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
-		/* TSQ : sk_wmem_alloc accounts skb truesize,
-		 * including skb overhead. But thats OK.
+		/* TCP Small Queues :
+		 * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+		 * This allows for :
+		 *  - better RTT estimation and ACK scheduling
+		 *  - faster recovery
+		 *  - high rates
 		 */
-		if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+		limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
+
+		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
 			break;
 		}
+
 		limit = mss_now;
 		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
@@ -2402,6 +2415,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		 * see tcp_input.c tcp_sacktag_write_queue().
 		 */
 		TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
+	} else {
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
 	return err;
 }
@@ -2523,10 +2538,9 @@ begin_fwd:
 		if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))
 			continue;
 
-		if (tcp_retransmit_skb(sk, skb)) {
-			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
+		if (tcp_retransmit_skb(sk, skb))
 			return;
-		}
+
 		NET_INC_STATS_BH(sock_net(sk), mib_idx);
 
 		if (tcp_in_cwnd_reduction(sk))
@@ -2664,7 +2678,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	int tcp_header_size;
 	int mss;
 
-	skb = alloc_skb(MAX_TCP_HEADER + 15, sk_gfp_atomic(sk, GFP_ATOMIC));
+	skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
 	if (unlikely(!skb)) {
 		dst_release(dst);
 		return NULL;
@@ -2808,6 +2822,8 @@ void tcp_connect_init(struct sock *sk)
 
 	if (likely(!tp->repair))
 		tp->rcv_nxt = 0;
+	else
+		tp->rcv_tstamp = tcp_time_stamp;
 	tp->rcv_wup = tp->rcv_nxt;
 	tp->copied_seq = tp->rcv_nxt;