1 files changed, 88 insertions, 64 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a3d453b..7f18262 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -333,10 +333,19 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
 static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+		       tcp_ca_needs_ecn(sk);
+
+	if (!use_ecn) {
+		const struct dst_entry *dst = __sk_dst_get(sk);
+
+		if (dst && dst_feature(dst, RTAX_FEATURE_ECN))
+			use_ecn = true;
+	}
 
 	tp->ecn_flags = 0;
-	if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
-	    tcp_ca_needs_ecn(sk)) {
+
+	if (use_ecn) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		tp->ecn_flags = TCP_ECN_OK;
 		if (tcp_ca_needs_ecn(sk))
@@ -1515,6 +1524,27 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
 		((nonagle & TCP_NAGLE_CORK) ||
 		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
 }
+
+/* Return how many segs we'd like on a TSO packet,
+ * to send one TSO packet per ms
+ */
+static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now)
+{
+	u32 bytes, segs;
+
+	bytes = min(sk->sk_pacing_rate >> 10,
+		    sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
+
+	/* Goal is to send at least one packet per ms,
+	 * not one big TSO packet every 100 ms.
+	 * This preserves ACK clocking and is consistent
+	 * with tcp_tso_should_defer() heuristic.
+	 */
+	segs = max_t(u32, bytes / mss_now, sysctl_tcp_min_tso_segs);
+
+	return min_t(u32, segs, sk->sk_gso_max_segs);
+}
+
 /* Returns the portion of skb which can be sent right away */
 static unsigned int tcp_mss_split_point(const struct sock *sk,
 					const struct sk_buff *skb,
@@ -1553,7 +1583,7 @@ static unsigned int tcp_mss_split_point(const struct sock *sk,
 static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
 					 const struct sk_buff *skb)
 {
-	u32 in_flight, cwnd;
+	u32 in_flight, cwnd, halfcwnd;
 
 	/* Don't be strict about the congestion window for the final FIN.  */
 	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) &&
@@ -1562,10 +1592,14 @@ static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
 
 	in_flight = tcp_packets_in_flight(tp);
 	cwnd = tp->snd_cwnd;
-	if (in_flight < cwnd)
-		return (cwnd - in_flight);
+	if (in_flight >= cwnd)
+		return 0;
 
-	return 0;
+	/* For better scheduling, ensure we have at least
+	 * 2 GSO packets in flight.
+	 */
+	halfcwnd = max(cwnd >> 1, 1U);
+	return min(halfcwnd, cwnd - in_flight);
 }
 
 /* Initialize TSO state of a skb.
@@ -1718,7 +1752,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
  * This algorithm is from John Heffner.
  */
 static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
-				 bool *is_cwnd_limited)
+				 bool *is_cwnd_limited, u32 max_segs)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1748,8 +1782,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	limit = min(send_win, cong_win);
 
 	/* If a full-sized TSO skb can be sent, do it. */
-	if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
-			   tp->xmit_size_goal_segs * tp->mss_cache))
+	if (limit >= max_segs * tp->mss_cache)
 		goto send_now;
 
 	/* Middle in queue won't get any more data, full sendable already? */
@@ -1946,6 +1979,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	int cwnd_quota;
 	int result;
 	bool is_cwnd_limited = false;
+	u32 max_segs;
 
 	sent_pkts = 0;
 
@@ -1959,6 +1993,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		}
 	}
 
+	max_segs = tcp_tso_autosize(sk, mss_now);
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
@@ -1991,10 +2026,23 @@ 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, &is_cwnd_limited))
+			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
+						 max_segs))
 				break;
 		}
 
+		limit = mss_now;
+		if (tso_segs > 1 && !tcp_urg_mode(tp))
+			limit = tcp_mss_split_point(sk, skb, mss_now,
+						    min_t(unsigned int,
+							  cwnd_quota,
+							  max_segs),
+						    nonagle);
+
+		if (skb->len > limit &&
+		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
+			break;
+
 		/* TCP Small Queues :
 		 * Control number of packets in qdisc/devices to two packets / or ~1 ms.
 		 * This allows for :
@@ -2005,8 +2053,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		 * of queued bytes to ensure line rate.
 		 * One example is wifi aggregation (802.11 AMPDU)
 		 */
-		limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
-			      sk->sk_pacing_rate >> 10);
+		limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
+		limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
@@ -2019,18 +2067,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
-		limit = mss_now;
-		if (tso_segs > 1 && !tcp_urg_mode(tp))
-			limit = tcp_mss_split_point(sk, skb, mss_now,
-						    min_t(unsigned int,
-							  cwnd_quota,
-							  sk->sk_gso_max_segs),
-						    nonagle);
-
-		if (skb->len > limit &&
-		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
-			break;
-
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
@@ -2998,9 +3034,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen;
-	struct sk_buff *syn_data = NULL, *data;
+	int syn_loss = 0, space, err = 0;
 	unsigned long last_syn_loss = 0;
+	struct sk_buff *syn_data;
 
 	tp->rx_opt.mss_clamp = tp->advmss;  /* If MSS is not cached */
 	tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
@@ -3031,48 +3067,40 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	/* limit to order-0 allocations */
 	space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
 
-	syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
-				   sk->sk_allocation);
-	if (syn_data == NULL)
+	syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation);
+	if (!syn_data)
+		goto fallback;
+	syn_data->ip_summed = CHECKSUM_PARTIAL;
+	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
+	if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
+					 fo->data->msg_iter.iov, 0, space))) {
+		kfree_skb(syn_data);
 		goto fallback;
+	}
 
-	for (i = 0; i < iovlen && syn_data->len < space; ++i) {
-		struct iovec *iov = &fo->data->msg_iov[i];
-		unsigned char __user *from = iov->iov_base;
-		int len = iov->iov_len;
+	/* No more data pending in inet_wait_for_connect() */
+	if (space == fo->size)
+		fo->data = NULL;
+	fo->copied = space;
 
-		if (syn_data->len + len > space)
-			len = space - syn_data->len;
-		else if (i + 1 == iovlen)
-			/* No more data pending in inet_wait_for_connect() */
-			fo->data = NULL;
+	tcp_connect_queue_skb(sk, syn_data);
 
-		if (skb_add_data(syn_data, from, len))
-			goto fallback;
-	}
+	err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
 
-	/* Queue a data-only packet after the regular SYN for retransmission */
-	data = pskb_copy(syn_data, sk->sk_allocation);
-	if (data == NULL)
-		goto fallback;
-	TCP_SKB_CB(data)->seq++;
-	TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN;
-	TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH);
-	tcp_connect_queue_skb(sk, data);
-	fo->copied = data->len;
-
-	/* syn_data is about to be sent, we need to take current time stamps
-	 * for the packets that are in write queue : SYN packet and DATA
-	 */
-	skb_mstamp_get(&syn->skb_mstamp);
-	data->skb_mstamp = syn->skb_mstamp;
+	syn->skb_mstamp = syn_data->skb_mstamp;
 
-	if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+	/* Now full SYN+DATA was cloned and sent (or not),
+	 * remove the SYN from the original skb (syn_data)
+	 * we keep in write queue in case of a retransmit, as we
+	 * also have the SYN packet (with no data) in the same queue.
+	 */
+	TCP_SKB_CB(syn_data)->seq++;
+	TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH;
+	if (!err) {
 		tp->syn_data = (fo->copied > 0);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
 		goto done;
 	}
-	syn_data = NULL;
 
 fallback:
 	/* Send a regular SYN with Fast Open cookie request option */
@@ -3081,7 +3109,6 @@ fallback:
 	err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation);
 	if (err)
 		tp->syn_fastopen = 0;
-	kfree_skb(syn_data);
 done:
 	fo->cookie.len = -1;  /* Exclude Fast Open option for SYN retries */
 	return err;
@@ -3101,13 +3128,10 @@ int tcp_connect(struct sock *sk)
 		return 0;
 	}
 
-	buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation);
-	if (unlikely(buff == NULL))
+	buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+	if (unlikely(!buff))
 		return -ENOBUFS;
 
-	/* Reserve space for headers. */
-	skb_reserve(buff, MAX_TCP_HEADER);
-
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
 	tp->retrans_stamp = tcp_time_stamp;
 	tcp_connect_queue_skb(sk, buff);