tcp: add SACK compression

When TCP receives an out-of-order packet, it immediately sends
a SACK packet, generating network load but also forcing the
receiver to send 1-MSS pathological packets, increasing its
RTX queue length/depth, and thus processing time.

Wifi networks suffer from this aggressive behavior, but generally
speaking, all these SACK packets add fuel to the fire when networks
are under congestion.

This patch adds a high resolution timer and tp->compressed_ack counter.

Instead of sending a SACK, we program this timer with a small delay,
based on RTT and capped to 1 ms :

	delay = min ( 5 % of RTT, 1 ms)

If subsequent SACKs need to be sent while the timer has not yet
expired, we simply increment tp->compressed_ack.

When timer expires, a SACK is sent with the latest information.
Whenever an ACK is sent (if data is sent, or if in-order
data is received) timer is canceled.

Note that tcp_sack_new_ofo_skb() is able to force a SACK to be sent
if the sack blocks need to be shuffled, even if the timer has not
expired.

A new SNMP counter is added in the following patch.

Two other patches add sysctls to allow changing the 1,000,000 and 44
values that this commit hard-coded.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Acked-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NToke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/linux/tcp.h

@@ -218,6 +218,7 @@ struct tcp_sock {
 		   reord:1;	 /* reordering detected */
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
+	u8	compressed_ack;
 	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
@@ -297,6 +298,7 @@ struct tcp_sock {
 	u32	sacked_out;	/* SACK'd packets			*/
 
 	struct hrtimer	pacing_timer;
+	struct hrtimer	compressed_ack_timer;
 
 	/* from STCP, retrans queue hinting */
 	struct sk_buff* lost_skb_hint;

include/net/tcp.h

@@ -561,6 +561,9 @@ static inline void tcp_clear_xmit_timers(struct sock *sk)
 	if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1)
 		__sock_put(sk);
 
+	if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1)
+		__sock_put(sk);
+
 	inet_csk_clear_xmit_timers(sk);
 }
 

net/ipv4/tcp.c

@@ -2595,6 +2595,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	dst_release(sk->sk_rx_dst);
 	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
+	tp->compressed_ack = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);

net/ipv4/tcp_input.c

@@ -4249,6 +4249,8 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
 	 * If the sack array is full, forget about the last one.
 	 */
 	if (this_sack >= TCP_NUM_SACKS) {
+		if (tp->compressed_ack)
+			tcp_send_ack(sk);
 		this_sack--;
 		tp->rx_opt.num_sacks--;
 		sp--;
@@ -5081,6 +5083,7 @@ static inline void tcp_data_snd_check(struct sock *sk)
 static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	unsigned long rtt, delay;
 
 	    /* More than one full frame received... */
 	if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
@@ -5092,15 +5095,35 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	    (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
 	     __tcp_select_window(sk) >= tp->rcv_wnd)) ||
 	    /* We ACK each frame or... */
-	    tcp_in_quickack_mode(sk) ||
-	    /* We have out of order data. */
-	    (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) {
-		/* Then ack it now */
+	    tcp_in_quickack_mode(sk)) {
+send_now:
 		tcp_send_ack(sk);
-	} else {
-		/* Else, send delayed ack. */
+		return;
+	}
+
+	if (!ofo_possible || RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
 		tcp_send_delayed_ack(sk);
+		return;
 	}
+
+	if (!tcp_is_sack(tp) || tp->compressed_ack >= 44)
+		goto send_now;
+	tp->compressed_ack++;
+
+	if (hrtimer_is_queued(&tp->compressed_ack_timer))
+		return;
+
+	/* compress ack timer : 5 % of rtt, but no more than 1 ms */
+
+	rtt = tp->rcv_rtt_est.rtt_us;
+	if (tp->srtt_us && tp->srtt_us < rtt)
+		rtt = tp->srtt_us;
+
+	delay = min_t(unsigned long, NSEC_PER_MSEC,
+		      rtt * (NSEC_PER_USEC >> 3)/20);
+	sock_hold(sk);
+	hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
+		      HRTIMER_MODE_REL_PINNED_SOFT);
 }
 
 static inline void tcp_ack_snd_check(struct sock *sk)

net/ipv4/tcp_output.c

@@ -162,6 +162,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 /* Account for an ACK we sent. */
 static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (unlikely(tp->compressed_ack)) {
+		tp->compressed_ack = 0;
+		if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
+			__sock_put(sk);
+	}
 	tcp_dec_quickack_mode(sk, pkts);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }

net/ipv4/tcp_timer.c

@@ -708,6 +708,27 @@ static void tcp_keepalive_timer (struct timer_list *t)
 	sock_put(sk);
 }
 
+static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer)
+{
+	struct tcp_sock *tp = container_of(timer, struct tcp_sock, compressed_ack_timer);
+	struct sock *sk = (struct sock *)tp;
+
+	bh_lock_sock(sk);
+	if (!sock_owned_by_user(sk)) {
+		if (tp->compressed_ack)
+			tcp_send_ack(sk);
+	} else {
+		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
+				      &sk->sk_tsq_flags))
+			sock_hold(sk);
+	}
+	bh_unlock_sock(sk);
+
+	sock_put(sk);
+
+	return HRTIMER_NORESTART;
+}
+
 void tcp_init_xmit_timers(struct sock *sk)
 {
 	inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
@@ -715,4 +736,8 @@ void tcp_init_xmit_timers(struct sock *sk)
 	hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS_PINNED_SOFT);
 	tcp_sk(sk)->pacing_timer.function = tcp_pace_kick;
+
+	hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL_PINNED_SOFT);
+	tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick;
 }