Adapt `mptcp_rcv_space_adjust()` after the recent TCP modifications (`tcp: receive side improvements`)

[matttbe]

Description

Eric is currently suggesting some improvements on TCP side: tcp: receive side improvements. This series modifies tcp_rcv_space_adjust().

Solution

In MPTCP, we have code similar to tcp_rcv_space_adjust(), in mptcp_rcv_space_adjust(). It is very likely the same modifications can be applied to MPTCP receive side.

Considered alternatives

If I'm not mistaken, this would be an improvement, not a fix due to the modifications done on the TCP side. But it might be required for MPTCP sockets, after a fallback to TCP!

It is important to measure the different impacts:

• Before Eric's series
• After Eric's series
• After the future adaptations in mptcp_rcv_space_adjust()

These measurements should include cases with MPTCP → MPTCP and MPTCP → TCP (fallback to TCP)

[matttbe]

(Thanks to Paolo for having noticed that these recent changes can affect MPTCP)

[matttbe]

As pointed out by Paolo, the modifications might be required, especially after a fallback to TCP. (And possibly some other scenarios we could not think of)

[matttbe]

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 41206c3f289f..ecfa657491b4 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -340,7 +340,7 @@ struct tcp_sock {
 	} rcv_rtt_est;
 /* Receiver queue space */
 	struct {
-		u32	space;
+		int	space;
 		u32	seq;
 		u64	time;
 	} rcvq_space;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 88beb6d0f7b5..5d64a6ecfc8f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -747,6 +747,32 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 	}
 }
 
+static void tcp_rcvbuf_grow(struct sock *sk)
+{
+	const struct net *net = sock_net(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	int rcvwin, rcvbuf, cap;
+
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) ||
+	    (sk->sk_userlocks & SOCK_RCVBUF_LOCK))
+		return;
+
+	/* slow start: allow the sender to double its rate. */
+	rcvwin = tp->rcvq_space.space << 1;
+
+	if (!RB_EMPTY_ROOT(&tp->out_of_order_queue))
+		rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt;
+
+	cap = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
+
+	rcvbuf = min_t(u32, tcp_space_from_win(sk, rcvwin), cap);
+	if (rcvbuf > sk->sk_rcvbuf) {
+		WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+		/* Make the window clamp follow along.  */
+		WRITE_ONCE(tp->window_clamp,
+			   tcp_win_from_space(sk, rcvbuf));
+	}
+}
 /*
  * This function should be called every time data is copied to user space.
  * It calculates the appropriate TCP receive buffer space.
@@ -754,8 +780,7 @@ 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 time, inq, copied;
 
 	trace_tcp_rcv_space_adjust(sk);
 
@@ -766,47 +791,18 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 	/* Number of bytes copied to user in last RTT */
 	copied = tp->copied_seq - tp->rcvq_space.seq;
+	/* Number of bytes in receive queue. */
+	inq = tp->rcv_nxt - tp->copied_seq;
+	copied -= inq;
 	if (copied <= tp->rcvq_space.space)
 		goto new_measure;
 
 	trace_tcp_rcvbuf_grow(sk, time);
 
-	/* A bit of theory :
-	 * copied = bytes received in previous RTT, our base window
-	 * To cope with packet losses, we need a 2x factor
-	 * To cope with slow start, and sender growing its cwin by 100 %
-	 * every RTT, we need a 4x factor, because the ACK we are sending
-	 * now is for the next RTT, not the current one :
-	 * <prev RTT . ><current RTT .. ><next RTT .... >
-	 */
-
-	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
-	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-		u64 rcvwin, grow;
-		int rcvbuf;
-
-		/* minimal window to cope with packet losses, assuming
-		 * steady state. Add some cushion because of small variations.
-		 */
-		rcvwin = ((u64)copied << 1) + 16 * tp->advmss;
-
-		/* 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);
-
-		rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
-			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-		if (rcvbuf > sk->sk_rcvbuf) {
-			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
-
-			/* Make the window clamp follow along.  */
-			WRITE_ONCE(tp->window_clamp,
-				   tcp_win_from_space(sk, rcvbuf));
-		}
-	}
 	tp->rcvq_space.space = copied;
 
+	tcp_rcvbuf_grow(sk);
+
 new_measure:
 	tp->rcvq_space.seq = tp->copied_seq;
 	tp->rcvq_space.time = tp->tcp_mstamp;
@@ -5175,6 +5171,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		skb_condense(skb);
 		skb_set_owner_r(skb, sk);
 	}
+	tcp_rcvbuf_grow(sk);
 }
 
 static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb

Patches 2-4/11 from tcp: receive side improvements.