1 files changed, 55 insertions, 30 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9c34b97d365d..730bc44dbad9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -180,10 +180,10 @@ 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)) {
+	if (unlikely(tp->compressed_ack > TCP_FASTRETRANS_THRESH)) {
 		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
-			      tp->compressed_ack);
-		tp->compressed_ack = 0;
+			      tp->compressed_ack - TCP_FASTRETRANS_THRESH);
+		tp->compressed_ack = TCP_FASTRETRANS_THRESH;
 		if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
 			__sock_put(sk);
 	}
@@ -233,16 +233,14 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	if (init_rcv_wnd)
 		*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
 
-	(*rcv_wscale) = 0;
+	*rcv_wscale = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
 		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
-		while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) {
-			space >>= 1;
-			(*rcv_wscale)++;
-		}
+		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
+				      0, TCP_MAX_WSCALE);
 	}
 	/* Set the clamp no higher than max representable value */
 	(*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp);
@@ -596,7 +594,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 
 	*md5 = NULL;
 #ifdef CONFIG_TCP_MD5SIG
-	if (unlikely(rcu_access_pointer(tp->md5sig_info))) {
+	if (static_key_false(&tcp_md5_needed) &&
+	    rcu_access_pointer(tp->md5sig_info)) {
 		*md5 = tp->af_specific->md5_lookup(sk, sk);
 		if (*md5) {
 			opts->options |= OPTION_MD5;
@@ -732,7 +731,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	*md5 = NULL;
 #ifdef CONFIG_TCP_MD5SIG
-	if (unlikely(rcu_access_pointer(tp->md5sig_info))) {
+	if (static_key_false(&tcp_md5_needed) &&
+	    rcu_access_pointer(tp->md5sig_info)) {
 		*md5 = tp->af_specific->md5_lookup(sk, sk);
 		if (*md5) {
 			opts->options |= OPTION_MD5;
@@ -1904,24 +1904,27 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
  * This algorithm is from John Heffner.
  */
 static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
-				 bool *is_cwnd_limited, u32 max_segs)
+				 bool *is_cwnd_limited,
+				 bool *is_rwnd_limited,
+				 u32 max_segs)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 age, send_win, cong_win, limit, in_flight;
+	u32 send_win, cong_win, limit, in_flight;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *head;
 	int win_divisor;
-
-	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
-		goto send_now;
+	s64 delta;
 
 	if (icsk->icsk_ca_state >= TCP_CA_Recovery)
 		goto send_now;
 
 	/* Avoid bursty behavior by allowing defer
-	 * only if the last write was recent.
+	 * only if the last write was recent (1 ms).
+	 * Note that tp->tcp_wstamp_ns can be in the future if we have
+	 * packets waiting in a qdisc or device for EDT delivery.
 	 */
-	if ((s32)(tcp_jiffies32 - tp->lsndtime) > 0)
+	delta = tp->tcp_clock_cache - tp->tcp_wstamp_ns - NSEC_PER_MSEC;
+	if (delta > 0)
 		goto send_now;
 
 	in_flight = tcp_packets_in_flight(tp);
@@ -1968,15 +1971,33 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	head = tcp_rtx_queue_head(sk);
 	if (!head)
 		goto send_now;
-	age = tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(head));
+	delta = tp->tcp_clock_cache - head->tstamp;
 	/* If next ACK is likely to come too late (half srtt), do not defer */
-	if (age < (tp->srtt_us >> 4))
+	if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
 		goto send_now;
 
-	/* Ok, it looks like it is advisable to defer. */
+	/* Ok, it looks like it is advisable to defer.
+	 * Three cases are tracked :
+	 * 1) We are cwnd-limited
+	 * 2) We are rwnd-limited
+	 * 3) We are application limited.
+	 */
+	if (cong_win < send_win) {
+		if (cong_win <= skb->len) {
+			*is_cwnd_limited = true;
+			return true;
+		}
+	} else {
+		if (send_win <= skb->len) {
+			*is_rwnd_limited = true;
+			return true;
+		}
+	}
 
-	if (cong_win < send_win && cong_win <= skb->len)
-		*is_cwnd_limited = true;
+	/* If this packet won't get more data, do not wait. */
+	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) ||
+	    TCP_SKB_CB(skb)->eor)
+		goto send_now;
 
 	return true;
 
@@ -2212,8 +2233,9 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 	limit = max_t(unsigned long,
 		      2 * skb->truesize,
 		      sk->sk_pacing_rate >> sk->sk_pacing_shift);
-	limit = min_t(unsigned long, limit,
-		      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+	if (sk->sk_pacing_status == SK_PACING_NONE)
+		limit = min_t(unsigned long, limit,
+			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
 	limit <<= factor;
 
 	if (refcount_read(&sk->sk_wmem_alloc) > limit) {
@@ -2356,7 +2378,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		} else {
 			if (!push_one &&
 			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
-						 max_segs))
+						 &is_rwnd_limited, max_segs))
 				break;
 		}
 
@@ -2494,15 +2516,18 @@ void tcp_send_loss_probe(struct sock *sk)
 		goto rearm_timer;
 	}
 	skb = skb_rb_last(&sk->tcp_rtx_queue);
+	if (unlikely(!skb)) {
+		WARN_ONCE(tp->packets_out,
+			  "invalid inflight: %u state %u cwnd %u mss %d\n",
+			  tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+		inet_csk(sk)->icsk_pending = 0;
+		return;
+	}
 
 	/* At most one outstanding TLP retransmission. */
 	if (tp->tlp_high_seq)
 		goto rearm_timer;
 
-	/* Retransmit last segment. */
-	if (WARN_ON(!skb))
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
@@ -2920,7 +2945,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
 		trace_tcp_retransmit_skb(sk, skb);
 	} else if (err != -EBUSY) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
+		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs);
 	}
 	return err;
 }