tcp: avoid extra wakeups for SO_RCVLOWAT users

SO_RCVLOWAT is properly handled in tcp_poll(), so that POLLIN is only
generated when enough bytes are available in receive queue, after
David change (commit c7004482e8dc "tcp: Respect SO_RCVLOWAT in tcp_poll().")

But TCP still calls sk->sk_data_ready() for each chunk added in receive
queue, meaning thread is awaken, and goes back to sleep shortly after.

Tested:

tcp_mmap test program, receiving 32768 MB of data with SO_RCVLOWAT set to 512KB

-> Should get ~2 wakeups (c-switches) per MB, regardless of how many
(tiny or big) packets were received.

High speed (mostly full size GRO packets)

received 32768 MB (100 % mmap'ed) in 8.03112 s, 34.2266 Gbit,
  cpu usage user:0.037 sys:1.404, 43.9758 usec per MB, 65497 c-switches

received 32768 MB (99.9954 % mmap'ed) in 7.98453 s, 34.4263 Gbit,
  cpu usage user:0.03 sys:1.422, 44.3115 usec per MB, 65485 c-switches

Low speed (sender is ratelimited and sends 1-MSS at a time, so GRO is not helping)

received 22474.5 MB (100 % mmap'ed) in 6015.35 s, 0.0313414 Gbit,
  cpu usage user:0.05 sys:1.586, 72.7952 usec per MB, 44950 c-switches

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 18 insertions, 2 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b2318242cad8..0ee85c47c185 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -403,6 +403,7 @@ void tcp_syn_ack_timeout(const struct request_sock *req);
 int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		int flags, int *addr_len);
 int tcp_set_rcvlowat(struct sock *sk, int val);
+void tcp_data_ready(struct sock *sk);
 void tcp_parse_options(const struct net *net, const struct sk_buff *skb,
 		       struct tcp_options_received *opt_rx,
 		       int estab, struct tcp_fastopen_cookie *foc);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0abd8d1d3d1d..c768d306b657 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1705,6 +1705,10 @@ EXPORT_SYMBOL(tcp_peek_len);
 int tcp_set_rcvlowat(struct sock *sk, int val)
 {
 	sk->sk_rcvlowat = val ? : 1;
+
+	/* Check if we need to signal EPOLLIN right now */
+	tcp_data_ready(sk);
+
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		return 0;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d854363a4387..f93687f97d80 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4576,6 +4576,17 @@ err:
 
 }
 
+void tcp_data_ready(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	int avail = tp->rcv_nxt - tp->copied_seq;
+
+	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+		return;
+
+	sk->sk_data_ready(sk);
+}
+
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -4633,7 +4644,7 @@ queue_and_out:
 		if (eaten > 0)
 			kfree_skb_partial(skb, fragstolen);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk);
+			tcp_data_ready(sk);
 		return;
 	}
 
@@ -5434,7 +5445,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 no_ack:
 			if (eaten)
 				kfree_skb_partial(skb, fragstolen);
-			sk->sk_data_ready(sk);
+			tcp_data_ready(sk);
 			return;
 		}
 	}