1 files changed, 48 insertions, 13 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 77311a92275c..f253e5019d22 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -380,14 +380,14 @@ void tcp_init_sock(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	__skb_queue_head_init(&tp->out_of_order_queue);
+	tp->out_of_order_queue = RB_ROOT;
 	tcp_init_xmit_timers(sk);
 	tcp_prequeue_init(tp);
 	INIT_LIST_HEAD(&tp->tsq_node);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
-	tp->rtt_min[0].rtt = ~0U;
+	minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U);
 
 	/* So many TCP implementations out there (incorrectly) count the
 	 * initial SYN frame in their delayed-ACK and congestion control
@@ -396,6 +396,9 @@ void tcp_init_sock(struct sock *sk)
 	 */
 	tp->snd_cwnd = TCP_INIT_CWND;
 
+	/* There's a bubble in the pipe until at least the first ACK. */
+	tp->app_limited = ~0U;
+
 	/* See draft-stevens-tcpca-spec-01 for discussion of the
 	 * initialization of these values.
 	 */
@@ -1014,23 +1017,40 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset,
 					flags);
 
 	lock_sock(sk);
+
+	tcp_rate_check_app_limited(sk);  /* is sending application-limited? */
+
 	res = do_tcp_sendpages(sk, page, offset, size, flags);
 	release_sock(sk);
 	return res;
 }
 EXPORT_SYMBOL(tcp_sendpage);
 
-static inline int select_size(const struct sock *sk, bool sg)
+/* Do not bother using a page frag for very small frames.
+ * But use this heuristic only for the first skb in write queue.
+ *
+ * Having no payload in skb->head allows better SACK shifting
+ * in tcp_shift_skb_data(), reducing sack/rack overhead, because
+ * write queue has less skbs.
+ * Each skb can hold up to MAX_SKB_FRAGS * 32Kbytes, or ~0.5 MB.
+ * This also speeds up tso_fragment(), since it wont fallback
+ * to tcp_fragment().
+ */
+static int linear_payload_sz(bool first_skb)
+{
+	if (first_skb)
+		return SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER);
+	return 0;
+}
+
+static int select_size(const struct sock *sk, bool sg, bool first_skb)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int tmp = tp->mss_cache;
 
 	if (sg) {
 		if (sk_can_gso(sk)) {
-			/* Small frames wont use a full page:
-			 * Payload will immediately follow tcp header.
-			 */
-			tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER);
+			tmp = linear_payload_sz(first_skb);
 		} else {
 			int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
 
@@ -1101,6 +1121,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 
+	tcp_rate_check_app_limited(sk);  /* is sending application-limited? */
+
 	/* Wait for a connection to finish. One exception is TCP Fast Open
 	 * (passive side) where data is allowed to be sent before a connection
 	 * is fully established.
@@ -1161,6 +1183,8 @@ restart:
 		}
 
 		if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) {
+			bool first_skb;
+
 new_segment:
 			/* Allocate new segment. If the interface is SG,
 			 * allocate skb fitting to single page.
@@ -1172,10 +1196,11 @@ new_segment:
 				process_backlog = false;
 				goto restart;
 			}
+			first_skb = skb_queue_empty(&sk->sk_write_queue);
 			skb = sk_stream_alloc_skb(sk,
-						  select_size(sk, sg),
+						  select_size(sk, sg, first_skb),
 						  sk->sk_allocation,
-						  skb_queue_empty(&sk->sk_write_queue));
+						  first_skb);
 			if (!skb)
 				goto wait_for_memory;
 
@@ -2243,7 +2268,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_clear_xmit_timers(sk);
 	__skb_queue_purge(&sk->sk_receive_queue);
 	tcp_write_queue_purge(sk);
-	__skb_queue_purge(&tp->out_of_order_queue);
+	skb_rbtree_purge(&tp->out_of_order_queue);
 
 	inet->inet_dport = 0;
 
@@ -2687,7 +2712,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 {
 	const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 now = tcp_time_stamp;
+	u32 now = tcp_time_stamp, intv;
 	unsigned int start;
 	int notsent_bytes;
 	u64 rate64;
@@ -2777,6 +2802,15 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_min_rtt = tcp_min_rtt(tp);
 	info->tcpi_data_segs_in = tp->data_segs_in;
 	info->tcpi_data_segs_out = tp->data_segs_out;
+
+	info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0;
+	rate = READ_ONCE(tp->rate_delivered);
+	intv = READ_ONCE(tp->rate_interval_us);
+	if (rate && intv) {
+		rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC;
+		do_div(rate64, intv);
+		put_unaligned(rate64, &info->tcpi_delivery_rate);
+	}
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
@@ -3244,11 +3278,12 @@ static void __init tcp_init_mem(void)
 
 void __init tcp_init(void)
 {
-	unsigned long limit;
 	int max_rshare, max_wshare, cnt;
+	unsigned long limit;
 	unsigned int i;
 
-	sock_skb_cb_check_size(sizeof(struct tcp_skb_cb));
+	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
+		     FIELD_SIZEOF(struct sk_buff, cb));
 
 	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
 	percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);