Merge branch 'tcp-better-receiver-autotuning'

Eric Dumazet says:

====================
tcp: better receiver autotuning

Now TCP senders no longer backoff when a drop is detected,
it appears we are very often receive window limited.

This series makes tcp_rcv_space_adjust() slightly more robust
and responsive.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 13 insertions, 20 deletions

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index ca4a6361389b..4f93f0953c41 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -344,7 +344,7 @@ struct tcp_sock {
 
 /* Receiver queue space */
 	struct {
-		int	space;
+		u32	space;
 		u32	seq;
 		u64	time;
 	} rcvq_space;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9550cc42de2d..fefb46c16de7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -576,8 +576,8 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 void tcp_rcv_space_adjust(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 copied;
 	int time;
-	int copied;
 
 	tcp_mstamp_refresh(tp);
 	time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
@@ -600,38 +600,31 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-		int rcvwin, rcvmem, rcvbuf;
+		int rcvmem, rcvbuf;
+		u64 rcvwin, grow;
 
 		/* minimal window to cope with packet losses, assuming
 		 * steady state. Add some cushion because of small variations.
 		 */
-		rcvwin = (copied << 1) + 16 * tp->advmss;
+		rcvwin = ((u64)copied << 1) + 16 * tp->advmss;
 
-		/* If rate increased by 25%,
-		 *	assume slow start, rcvwin = 3 * copied
-		 * If rate increased by 50%,
-		 *	assume sender can use 2x growth, rcvwin = 4 * copied
-		 */
-		if (copied >=
-		    tp->rcvq_space.space + (tp->rcvq_space.space >> 2)) {
-			if (copied >=
-			    tp->rcvq_space.space + (tp->rcvq_space.space >> 1))
-				rcvwin <<= 1;
-			else
-				rcvwin += (rcvwin >> 1);
-		}
+		/* Accommodate for sender rate increase (eg. slow start) */
+		grow = rcvwin * (copied - tp->rcvq_space.space);
+		do_div(grow, tp->rcvq_space.space);
+		rcvwin += (grow << 1);
 
 		rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
 		while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
 			rcvmem += 128;
 
-		rcvbuf = min(rcvwin / tp->advmss * rcvmem,
-			     sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+		do_div(rcvwin, tp->advmss);
+		rcvbuf = min_t(u64, rcvwin * rcvmem,
+			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		if (rcvbuf > sk->sk_rcvbuf) {
 			sk->sk_rcvbuf = rcvbuf;
 
 			/* Make the window clamp follow along.  */
-			tp->window_clamp = rcvwin;
+			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
 		}
 	}
 	tp->rcvq_space.space = copied;