4 files changed, 29 insertions, 27 deletions

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index aaeb5d16f0c9..158a30ae7c5f 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -568,20 +568,6 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	return 0;
 }
 
-static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom)
-{
-	/* we must cap headroom to some upperlimit, else pskb_expand_head
-	 * will overflow header offsets in skb_headers_offset_update().
-	 */
-	static const unsigned int max_allowed = 512;
-
-	if (headroom > max_allowed)
-		headroom = max_allowed;
-
-	if (headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, headroom);
-}
-
 void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		       u8 proto, int tunnel_hlen)
 {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 31ea5af49f2d..e4a979b75cc6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -891,18 +891,27 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 	}
 }
 
-void tcp_rcvbuf_grow(struct sock *sk)
+void tcp_rcvbuf_grow(struct sock *sk, u32 newval)
 {
 	const struct net *net = sock_net(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	int rcvwin, rcvbuf, cap;
+	u32 rcvwin, rcvbuf, cap, oldval;
+	u64 grow;
+
+	oldval = tp->rcvq_space.space;
+	tp->rcvq_space.space = newval;
 
 	if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) ||
 	    (sk->sk_userlocks & SOCK_RCVBUF_LOCK))
 		return;
 
+	/* DRS is always one RTT late. */
+	rcvwin = newval << 1;
+
 	/* slow start: allow the sender to double its rate. */
-	rcvwin = tp->rcvq_space.space << 1;
+	grow = (u64)rcvwin * (newval - oldval);
+	do_div(grow, oldval);
+	rcvwin += grow << 1;
 
 	if (!RB_EMPTY_ROOT(&tp->out_of_order_queue))
 		rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt;
@@ -943,9 +952,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 	trace_tcp_rcvbuf_grow(sk, time);
 
-	tp->rcvq_space.space = copied;
-
-	tcp_rcvbuf_grow(sk);
+	tcp_rcvbuf_grow(sk, copied);
 
 new_measure:
 	tp->rcvq_space.seq = tp->copied_seq;
@@ -5270,7 +5277,7 @@ end:
 	}
 	/* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */
 	if (sk->sk_socket)
-		tcp_rcvbuf_grow(sk);
+		tcp_rcvbuf_grow(sk, tp->rcvq_space.space);
 }
 
 static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bb3576ac0ad7..b94efb3050d2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2369,7 +2369,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 				 u32 max_segs)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 send_win, cong_win, limit, in_flight;
+	u32 send_win, cong_win, limit, in_flight, threshold;
+	u64 srtt_in_ns, expected_ack, how_far_is_the_ack;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *head;
 	int win_divisor;
@@ -2431,9 +2432,19 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	head = tcp_rtx_queue_head(sk);
 	if (!head)
 		goto send_now;
-	delta = tp->tcp_clock_cache - head->tstamp;
-	/* If next ACK is likely to come too late (half srtt), do not defer */
-	if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
+
+	srtt_in_ns = (u64)(NSEC_PER_USEC >> 3) * tp->srtt_us;
+	/* When is the ACK expected ? */
+	expected_ack = head->tstamp + srtt_in_ns;
+	/* How far from now is the ACK expected ? */
+	how_far_is_the_ack = expected_ack - tp->tcp_clock_cache;
+
+	/* If next ACK is likely to come too late,
+	 * ie in more than min(1ms, half srtt), do not defer.
+	 */
+	threshold = min(srtt_in_ns >> 1, NSEC_PER_MSEC);
+
+	if ((s64)(how_far_is_the_ack - threshold) > 0)
 		goto send_now;
 
 	/* Ok, it looks like it is advisable to defer.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 95241093b7f0..30dfbf73729d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1851,8 +1851,6 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		sk_peek_offset_bwd(sk, len);
 
 	if (!skb_shared(skb)) {
-		if (unlikely(udp_skb_has_head_state(skb)))
-			skb_release_head_state(skb);
 		skb_attempt_defer_free(skb);
 		return;
 	}