1 files changed, 76 insertions, 64 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a3d453b94747..dc9f925b0cd5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1984,7 +1984,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
 			break;
 
-		if (tso_segs == 1) {
+		if (tso_segs == 1 || !sk->sk_gso_max_segs) {
 			if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
 						     (tcp_skb_is_last(sk, skb) ?
 						      nonagle : TCP_NAGLE_PUSH))))
@@ -2020,7 +2020,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		}
 
 		limit = mss_now;
-		if (tso_segs > 1 && !tcp_urg_mode(tp))
+		if (tso_segs > 1 && sk->sk_gso_max_segs && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
 						    min_t(unsigned int,
 							  cwnd_quota,
@@ -2717,43 +2717,65 @@ begin_fwd:
 	}
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
-
-		/* Reserve space for headers and prepare control bits. */
 		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
@@ -2899,6 +2921,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	}
 #endif
 
+	/* Do not fool tcpdump (if any), clean our debris */
+	skb->tstamp.tv64 = 0;
 	return skb;
 }
 EXPORT_SYMBOL(tcp_make_synack);
@@ -2998,9 +3022,9 @@ 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 +3055,40 @@ 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_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 +3097,6 @@ 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 +3116,10 @@ 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);