tcp: fix cwnd limited checking to improve congestion control

Yuchung discovered tcp_is_cwnd_limited() was returning false in
slow start phase even if the application filled the socket write queue.

All congestion modules take into account tcp_is_cwnd_limited()
before increasing cwnd, so this behavior limits slow start from
probing the bandwidth at full speed.

The problem is that even if write queue is full (aka we are _not_
application limited), cwnd can be under utilized if TSO should auto
defer or TCP Small queues decided to hold packets.

So the in_flight can be kept to smaller value, and we can get to the
point tcp_is_cwnd_limited() returns false.

With TCP Small Queues and FQ/pacing, this issue is more visible.

We fix this by having tcp_cwnd_validate(), which is supposed to track
such things, take into account unsent_segs, the number of segs that we
are not sending at the moment due to TSO or TSQ, but intend to send
real soon. Then when we are cwnd-limited, remember this fact while we
are processing the window of ACKs that comes back.

For example, suppose we have a brand new connection with cwnd=10; we
are in slow start, and we send a flight of 9 packets. By the time we
have received ACKs for all 9 packets we want our cwnd to be 18.
We implement this by setting tp->lsnd_pending to 9, and
considering ourselves to be cwnd-limited while cwnd is less than
twice tp->lsnd_pending (2*9 -> 18).

This makes tcp_is_cwnd_limited() more understandable, by removing
the GSO/TSO kludge, that tried to work around the issue.

Note the in_flight parameter can be removed in a followup cleanup
patch.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 14 insertions, 7 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 20847de991ea..f9181a133462 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1402,12 +1402,13 @@ static void tcp_cwnd_application_limited(struct sock *sk)
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 }
 
-/* Congestion window validation. (RFC2861) */
-static void tcp_cwnd_validate(struct sock *sk)
+static void tcp_cwnd_validate(struct sock *sk, u32 unsent_segs)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tp->packets_out >= tp->snd_cwnd) {
+	tp->lsnd_pending = tp->packets_out + unsent_segs;
+
+	if (tcp_is_cwnd_limited(sk, 0)) {
 		/* Network is feed fully. */
 		tp->snd_cwnd_used = 0;
 		tp->snd_cwnd_stamp = tcp_time_stamp;
@@ -1880,7 +1881,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	unsigned int tso_segs, sent_pkts;
+	unsigned int tso_segs, sent_pkts, unsent_segs = 0;
 	int cwnd_quota;
 	int result;
 
@@ -1924,7 +1925,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		} else {
 			if (!push_one && tcp_tso_should_defer(sk, skb))
-				break;
+				goto compute_unsent_segs;
 		}
 
 		/* TCP Small Queues :
@@ -1949,8 +1950,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			 * there is no smp_mb__after_set_bit() yet
 			 */
 			smp_mb__after_clear_bit();
-			if (atomic_read(&sk->sk_wmem_alloc) > limit)
+			if (atomic_read(&sk->sk_wmem_alloc) > limit) {
+				u32 unsent_bytes;
+
+compute_unsent_segs:
+				unsent_bytes = tp->write_seq - tp->snd_nxt;
+				unsent_segs = DIV_ROUND_UP(unsent_bytes, mss_now);
 				break;
+			}
 		}
 
 		limit = mss_now;
@@ -1990,7 +1997,7 @@ repair:
 		/* Send one loss probe per tail loss episode. */
 		if (push_one != 2)
 			tcp_schedule_loss_probe(sk);
-		tcp_cwnd_validate(sk);
+		tcp_cwnd_validate(sk, unsent_segs);
 		return false;
 	}
 	return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));