1 files changed, 71 insertions, 42 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 660c967ba84a..9ada5e4a28e5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -177,8 +177,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+				      u32 rcv_nxt)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (unlikely(rcv_nxt != tp->rcv_nxt))
+		return;  /* Special ACK sent by DCTCP to reflect ECN */
 	tcp_dec_quickack_mode(sk, pkts);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
@@ -191,7 +196,7 @@ u32 tcp_default_init_rwnd(u32 mss)
 	 * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a
 	 * limit when mss is larger than 1460.
 	 */
-	u32 init_rwnd = TCP_INIT_CWND * 2;
+	u32 init_rwnd = sysctl_tcp_default_init_rwnd;
 
 	if (mss > 1460)
 		init_rwnd = max((1460 * init_rwnd) / mss, 2U);
@@ -901,8 +906,8 @@ out:
  * We are working here with either a clone of the original
  * SKB, or a fresh unique copy made by the retransmit engine.
  */
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
-			    gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+			      int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet;
@@ -962,7 +967,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->source		= inet->inet_sport;
 	th->dest		= inet->inet_dport;
 	th->seq			= htonl(tcb->seq);
-	th->ack_seq		= htonl(tp->rcv_nxt);
+	th->ack_seq		= htonl(rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
 					tcb->tcp_flags);
 
@@ -1005,7 +1010,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	icsk->icsk_af_ops->send_check(sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
 
 	if (skb->len != tcp_header_size)
 		tcp_event_data_sent(tp, sk);
@@ -1036,6 +1041,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	return net_xmit_eval(err);
 }
 
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+			    gfp_t gfp_mask)
+{
+	return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+				  tcp_sk(sk)->rcv_nxt);
+}
+
 /* This routine just queues the buffer for sending.
  *
  * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -1221,7 +1233,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
  * eventually). The difference is that pulled data not copied, but
  * immediately discarded.
  */
-static void __pskb_trim_head(struct sk_buff *skb, int len)
+static int __pskb_trim_head(struct sk_buff *skb, int len)
 {
 	struct skb_shared_info *shinfo;
 	int i, k, eat;
@@ -1231,7 +1243,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 		__skb_pull(skb, eat);
 		len -= eat;
 		if (!len)
-			return;
+			return 0;
 	}
 	eat = len;
 	k = 0;
@@ -1257,23 +1269,28 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	skb_reset_tail_pointer(skb);
 	skb->data_len -= len;
 	skb->len = skb->data_len;
+	return len;
 }
 
 /* Remove acked data from a packet in the transmit queue. */
 int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 {
+	u32 delta_truesize;
+
 	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
-	__pskb_trim_head(skb, len);
+	delta_truesize = __pskb_trim_head(skb, len);
 
 	TCP_SKB_CB(skb)->seq += len;
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
-	skb->truesize	     -= len;
-	sk->sk_wmem_queued   -= len;
-	sk_mem_uncharge(sk, len);
-	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	if (delta_truesize) {
+		skb->truesize	   -= delta_truesize;
+		sk->sk_wmem_queued -= delta_truesize;
+		sk_mem_uncharge(sk, delta_truesize);
+		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
 	if (tcp_skb_pcount(skb) > 1)
@@ -1946,16 +1963,19 @@ static int tcp_mtu_probe(struct sock *sk)
 	nskb->ip_summed = skb->ip_summed;
 
 	tcp_insert_write_queue_before(nskb, skb, sk);
+	tcp_highest_sack_replace(sk, skb, nskb);
 
 	len = 0;
 	tcp_for_write_queue_from_safe(skb, next, sk) {
 		copy = min_t(int, skb->len, probe_size - len);
-		if (nskb->ip_summed)
+		if (nskb->ip_summed) {
 			skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
-		else
-			nskb->csum = skb_copy_and_csum_bits(skb, 0,
-							    skb_put(nskb, copy),
-							    copy, nskb->csum);
+		} else {
+			__wsum csum = skb_copy_and_csum_bits(skb, 0,
+							     skb_put(nskb, copy),
+							     copy, 0);
+			nskb->csum = csum_block_add(nskb->csum, csum, len);
+		}
 
 		if (skb->len <= copy) {
 			/* We've eaten all the data from this skb.
@@ -2243,14 +2263,18 @@ void tcp_send_loss_probe(struct sock *sk)
 		skb = tcp_write_queue_tail(sk);
 	}
 
+	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;
 
@@ -2381,9 +2405,11 @@ u32 __tcp_select_window(struct sock *sk)
 	int full_space = min_t(int, tp->window_clamp, allowed_space);
 	int window;
 
-	if (mss > full_space)
+	if (unlikely(mss > full_space)) {
 		mss = full_space;
-
+		if (mss <= 0)
+			return 0;
+	}
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
@@ -2455,7 +2481,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 
 	BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
 
-	tcp_highest_sack_combine(sk, next_skb, skb);
+	tcp_highest_sack_replace(sk, next_skb, skb);
 
 	tcp_unlink_write_queue(next_skb, sk);
 
@@ -2569,15 +2595,18 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 * copying overhead: fragmentation, tunneling, mangling etc.
 	 */
 	if (atomic_read(&sk->sk_wmem_alloc) >
-	    min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
+	    min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2),
+		  sk->sk_sndbuf))
 		return -EAGAIN;
 
 	if (skb_still_in_host_queue(sk, skb))
 		return -EBUSY;
 
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
-		if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
-			BUG();
+		if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
+			WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
 		if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
 			return -ENOMEM;
 	}
@@ -3007,13 +3036,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	tcp_ecn_make_synack(req, th);
 	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)
-	 */
-	tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
-			     TCPHDR_SYN | TCPHDR_ACK);
-
-	th->seq = htonl(TCP_SKB_CB(skb)->seq);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	th->seq = htonl(tcp_rsk(req)->snt_isn);
 	/* XXX data is queued and acked as is. No buffer/window check */
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 
@@ -3111,6 +3135,7 @@ static void tcp_connect_init(struct sock *sk)
 	sock_reset_flag(sk, SOCK_DONE);
 	tp->snd_wnd = 0;
 	tcp_init_wl(tp, 0);
+	tcp_write_queue_purge(sk);
 	tp->snd_una = tp->write_seq;
 	tp->snd_sml = tp->write_seq;
 	tp->snd_up = tp->write_seq;
@@ -3246,6 +3271,9 @@ int tcp_connect(struct sock *sk)
 	struct sk_buff *buff;
 	int err;
 
+	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
+		return -EHOSTUNREACH; /* Routing failure or similar. */
+
 	tcp_connect_init(sk);
 
 	if (unlikely(tp->repair)) {
@@ -3292,8 +3320,6 @@ void tcp_send_delayed_ack(struct sock *sk)
 	int ato = icsk->icsk_ack.ato;
 	unsigned long timeout;
 
-	tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
 	if (ato > TCP_DELACK_MIN) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 		int max_ato = HZ / 2;
@@ -3342,7 +3368,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 }
 
 /* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 {
 	struct sk_buff *buff;
 
@@ -3350,8 +3376,6 @@ void tcp_send_ack(struct sock *sk)
 	if (sk->sk_state == TCP_CLOSE)
 		return;
 
-	tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
 	/* We are not putting this on the write queue, so
 	 * tcp_transmit_skb() will set the ownership to this
 	 * sock.
@@ -3379,9 +3403,14 @@ void tcp_send_ack(struct sock *sk)
 
 	/* Send it off, this clears delayed acks for us. */
 	skb_mstamp_get(&buff->skb_mstamp);
-	tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
+	__tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC), rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
-EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.