1 files changed, 33 insertions, 36 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7c83cb8bf13..7820f3a7dd7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -637,6 +637,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 	unsigned int size = 0;
 	unsigned int eff_sacks;
 
+	opts->options = 0;
+
 #ifdef CONFIG_TCP_MD5SIG
 	*md5 = tp->af_specific->md5_lookup(sk, sk);
 	if (unlikely(*md5)) {
@@ -848,15 +850,15 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
 
-	/* If congestion control is doing timestamping, we must
-	 * take such a timestamp before we potentially clone/copy.
-	 */
-	if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP)
-		__net_timestamp(skb);
-
-	if (likely(clone_it)) {
+	if (clone_it) {
 		const struct sk_buff *fclone = skb + 1;
 
+		/* If congestion control is doing timestamping, we must
+		 * take such a timestamp before we potentially clone/copy.
+		 */
+		if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP)
+			__net_timestamp(skb);
+
 		if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
 			     fclone->fclone == SKB_FCLONE_CLONE))
 			NET_INC_STATS_BH(sock_net(sk),
@@ -895,8 +897,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	skb_orphan(skb);
 	skb->sk = sk;
-	skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
-			  tcp_wfree : sock_wfree;
+	skb->destructor = tcp_wfree;
 	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
 	/* Build TCP header and checksum it. */
@@ -985,8 +986,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
 				 unsigned int mss_now)
 {
-	if (skb->len <= mss_now || !sk_can_gso(sk) ||
-	    skb->ip_summed == CHECKSUM_NONE) {
+	/* Make sure we own this skb before messing gso_size/gso_segs */
+	WARN_ON_ONCE(skb_cloned(skb));
+
+	if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) {
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
@@ -1066,9 +1069,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (skb_cloned(skb) &&
-	    skb_is_nonlinear(skb) &&
-	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
 	/* Get a new skb... force flag on. */
@@ -1840,7 +1841,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
-
 		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
 		BUG_ON(!tso_segs);
 
@@ -1869,13 +1869,24 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
-		/* TSQ : sk_wmem_alloc accounts skb truesize,
-		 * including skb overhead. But thats OK.
+		/* TCP Small Queues :
+		 * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+		 * This allows for :
+		 *  - better RTT estimation and ACK scheduling
+		 *  - faster recovery
+		 *  - high rates
+		 * Alas, some drivers / subsystems require a fair amount
+		 * of queued bytes to ensure line rate.
+		 * One example is wifi aggregation (802.11 AMPDU)
 		 */
-		if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+		limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
+			      sk->sk_pacing_rate >> 10);
+
+		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
 			break;
 		}
+
 		limit = mss_now;
 		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
@@ -2337,6 +2348,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		int oldpcount = tcp_skb_pcount(skb);
 
 		if (unlikely(oldpcount > 1)) {
+			if (skb_unclone(skb, GFP_ATOMIC))
+				return -ENOMEM;
 			tcp_init_tso_segs(sk, skb, cur_mss);
 			tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
 		}
@@ -2344,21 +2357,6 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 
 	tcp_retrans_try_collapse(sk, skb, cur_mss);
 
-	/* Some Solaris stacks overoptimize and ignore the FIN on a
-	 * retransmit when old data is attached.  So strip it off
-	 * since it is cheap to do so and saves bytes on the network.
-	 */
-	if (skb->len > 0 &&
-	    (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) &&
-	    tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
-		if (!pskb_trim(skb, 0)) {
-			/* Reuse, even though it does some unnecessary work */
-			tcp_init_nondata_skb(skb, TCP_SKB_CB(skb)->end_seq - 1,
-					     TCP_SKB_CB(skb)->tcp_flags);
-			skb->ip_summed = CHECKSUM_NONE;
-		}
-	}
-
 	/* Make a copy, if the first transmission SKB clone we made
 	 * is still in somebody's hands, else make a clone.
 	 */
@@ -2727,8 +2725,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	th->syn = 1;
 	th->ack = 1;
 	TCP_ECN_make_synack(req, th);
-	th->source = ireq->loc_port;
-	th->dest = ireq->rmt_port;
+	th->source = htons(ireq->ir_num);
+	th->dest = ireq->ir_rmt_port;
 	/* Setting of flags are superfluous here for callers (and ECE is
 	 * not even correctly set)
 	 */
@@ -3099,7 +3097,6 @@ void tcp_send_window_probe(struct sock *sk)
 {
 	if (sk->sk_state == TCP_ESTABLISHED) {
 		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
-		tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
 		tcp_xmit_probe_skb(sk, 0);
 	}
 }