Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 163 insertions, 122 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0185eea59342..00a41499d52c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -200,28 +200,25 @@ static inline bool tcp_in_quickack_mode(const struct sock *sk)
 	return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong;
 }
 
-static inline void TCP_ECN_queue_cwr(struct tcp_sock *tp)
+static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
 {
 	if (tp->ecn_flags & TCP_ECN_OK)
 		tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
 }
 
-static inline void TCP_ECN_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
+static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
 {
 	if (tcp_hdr(skb)->cwr)
 		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 }
 
-static inline void TCP_ECN_withdraw_cwr(struct tcp_sock *tp)
+static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 {
 	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 }
 
-static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 {
-	if (!(tp->ecn_flags & TCP_ECN_OK))
-		return;
-
 	switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) {
 	case INET_ECN_NOT_ECT:
 		/* Funny extension: if ECT is not set on a segment,
@@ -232,30 +229,43 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *s
 			tcp_enter_quickack_mode((struct sock *)tp);
 		break;
 	case INET_ECN_CE:
+		if (tcp_ca_needs_ecn((struct sock *)tp))
+			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
+
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
 			tcp_enter_quickack_mode((struct sock *)tp);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
-		/* fallinto */
+		tp->ecn_flags |= TCP_ECN_SEEN;
+		break;
 	default:
+		if (tcp_ca_needs_ecn((struct sock *)tp))
+			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
 		tp->ecn_flags |= TCP_ECN_SEEN;
+		break;
 	}
 }
 
-static inline void TCP_ECN_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
+static void tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+{
+	if (tp->ecn_flags & TCP_ECN_OK)
+		__tcp_ecn_check_ce(tp, skb);
+}
+
+static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
 {
 	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || th->cwr))
 		tp->ecn_flags &= ~TCP_ECN_OK;
 }
 
-static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th)
+static void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th)
 {
 	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || !th->cwr))
 		tp->ecn_flags &= ~TCP_ECN_OK;
 }
 
-static bool TCP_ECN_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th)
+static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th)
 {
 	if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK))
 		return true;
@@ -652,7 +662,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 	}
 	icsk->icsk_ack.lrcvtime = now;
 
-	TCP_ECN_check_ce(tp, skb);
+	tcp_ecn_check_ce(tp, skb);
 
 	if (skb->len >= 128)
 		tcp_grow_window(sk, skb);
@@ -1294,9 +1304,9 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	TCP_SKB_CB(prev)->end_seq += shifted;
 	TCP_SKB_CB(skb)->seq += shifted;
 
-	skb_shinfo(prev)->gso_segs += pcount;
-	BUG_ON(skb_shinfo(skb)->gso_segs < pcount);
-	skb_shinfo(skb)->gso_segs -= pcount;
+	tcp_skb_pcount_add(prev, pcount);
+	BUG_ON(tcp_skb_pcount(skb) < pcount);
+	tcp_skb_pcount_add(skb, -pcount);
 
 	/* When we're adding to gso_segs == 1, gso_size will be zero,
 	 * in theory this shouldn't be necessary but as long as DSACK
@@ -1309,7 +1319,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	}
 
 	/* CHECKME: To clear or not to clear? Mimics normal skb currently */
-	if (skb_shinfo(skb)->gso_segs <= 1) {
+	if (tcp_skb_pcount(skb) <= 1) {
 		skb_shinfo(skb)->gso_size = 0;
 		skb_shinfo(skb)->gso_type = 0;
 	}
@@ -1887,21 +1897,21 @@ static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
 	tp->sacked_out = 0;
 }
 
-static void tcp_clear_retrans_partial(struct tcp_sock *tp)
+void tcp_clear_retrans(struct tcp_sock *tp)
 {
 	tp->retrans_out = 0;
 	tp->lost_out = 0;
-
 	tp->undo_marker = 0;
 	tp->undo_retrans = -1;
+	tp->fackets_out = 0;
+	tp->sacked_out = 0;
 }
 
-void tcp_clear_retrans(struct tcp_sock *tp)
+static inline void tcp_init_undo(struct tcp_sock *tp)
 {
-	tcp_clear_retrans_partial(tp);
-
-	tp->fackets_out = 0;
-	tp->sacked_out = 0;
+	tp->undo_marker = tp->snd_una;
+	/* Retransmission still in flight may cause DSACKs later. */
+	tp->undo_retrans = tp->retrans_out ? : -1;
 }
 
 /* Enter Loss state. If we detect SACK reneging, forget all SACK information
@@ -1924,18 +1934,18 @@ void tcp_enter_loss(struct sock *sk)
 		tp->prior_ssthresh = tcp_current_ssthresh(sk);
 		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
 		tcp_ca_event(sk, CA_EVENT_LOSS);
+		tcp_init_undo(tp);
 	}
 	tp->snd_cwnd	   = 1;
 	tp->snd_cwnd_cnt   = 0;
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 
-	tcp_clear_retrans_partial(tp);
+	tp->retrans_out = 0;
+	tp->lost_out = 0;
 
 	if (tcp_is_reno(tp))
 		tcp_reset_reno_sack(tp);
 
-	tp->undo_marker = tp->snd_una;
-
 	skb = tcp_write_queue_head(sk);
 	is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
 	if (is_reneg) {
@@ -1949,9 +1959,6 @@ void tcp_enter_loss(struct sock *sk)
 		if (skb == tcp_send_head(sk))
 			break;
 
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
-			tp->undo_marker = 0;
-
 		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
 		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) {
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
@@ -1971,7 +1978,7 @@ void tcp_enter_loss(struct sock *sk)
 				       sysctl_tcp_reordering);
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
-	TCP_ECN_queue_cwr(tp);
+	tcp_ecn_queue_cwr(tp);
 
 	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
 	 * loss recovery is underway except recurring timeout(s) on
@@ -2363,7 +2370,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
 
 		if (tp->prior_ssthresh > tp->snd_ssthresh) {
 			tp->snd_ssthresh = tp->prior_ssthresh;
-			TCP_ECN_withdraw_cwr(tp);
+			tcp_ecn_withdraw_cwr(tp);
 		}
 	} else {
 		tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
@@ -2493,7 +2500,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk)
 	tp->prr_delivered = 0;
 	tp->prr_out = 0;
 	tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk);
-	TCP_ECN_queue_cwr(tp);
+	tcp_ecn_queue_cwr(tp);
 }
 
 static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked,
@@ -2670,8 +2677,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 	NET_INC_STATS_BH(sock_net(sk), mib_idx);
 
 	tp->prior_ssthresh = 0;
-	tp->undo_marker = tp->snd_una;
-	tp->undo_retrans = tp->retrans_out ? : -1;
+	tcp_init_undo(tp);
 
 	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
 		if (!ece_ack)
@@ -2970,7 +2976,8 @@ void tcp_rearm_rto(struct sock *sk)
 		if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
 		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 			struct sk_buff *skb = tcp_write_queue_head(sk);
-			const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto;
+			const u32 rto_time_stamp =
+				tcp_skb_timestamp(skb) + rto;
 			s32 delta = (s32)(rto_time_stamp - tcp_time_stamp);
 			/* delta may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
@@ -3210,9 +3217,10 @@ static void tcp_ack_probe(struct sock *sk)
 		 * This function is not for random using!
 		 */
 	} else {
+		unsigned long when = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
+
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
-					  TCP_RTO_MAX);
+					  when, TCP_RTO_MAX);
 	}
 }
 
@@ -3363,6 +3371,14 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	}
 }
 
+static inline void tcp_in_ack_event(struct sock *sk, u32 flags)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (icsk->icsk_ca_ops->in_ack_event)
+		icsk->icsk_ca_ops->in_ack_event(sk, flags);
+}
+
 /* This routine deals with incoming acks, but not outgoing ones. */
 static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 {
@@ -3422,10 +3438,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tp->snd_una = ack;
 		flag |= FLAG_WIN_UPDATE;
 
-		tcp_ca_event(sk, CA_EVENT_FAST_ACK);
+		tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
 
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPACKS);
 	} else {
+		u32 ack_ev_flags = CA_ACK_SLOWPATH;
+
 		if (ack_seq != TCP_SKB_CB(skb)->end_seq)
 			flag |= FLAG_DATA;
 		else
@@ -3437,10 +3455,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 			flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
 							&sack_rtt_us);
 
-		if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
+		if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) {
 			flag |= FLAG_ECE;
+			ack_ev_flags |= CA_ACK_ECE;
+		}
+
+		if (flag & FLAG_WIN_UPDATE)
+			ack_ev_flags |= CA_ACK_WIN_UPDATE;
 
-		tcp_ca_event(sk, CA_EVENT_SLOW_ACK);
+		tcp_in_ack_event(sk, ack_ev_flags);
 	}
 
 	/* We passed data and got it acked, remove any soft error
@@ -4062,6 +4085,44 @@ static void tcp_sack_remove(struct tcp_sock *tp)
 	tp->rx_opt.num_sacks = num_sacks;
 }
 
+/**
+ * tcp_try_coalesce - try to merge skb to prior one
+ * @sk: socket
+ * @to: prior buffer
+ * @from: buffer to add in queue
+ * @fragstolen: pointer to boolean
+ *
+ * Before queueing skb @from after @to, try to merge them
+ * to reduce overall memory use and queue lengths, if cost is small.
+ * Packets in ofo or receive queues can stay a long time.
+ * Better try to coalesce them right now to avoid future collapses.
+ * Returns true if caller should free @from instead of queueing it
+ */
+static bool tcp_try_coalesce(struct sock *sk,
+			     struct sk_buff *to,
+			     struct sk_buff *from,
+			     bool *fragstolen)
+{
+	int delta;
+
+	*fragstolen = false;
+
+	/* Its possible this segment overlaps with prior segment in queue */
+	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
+		return false;
+
+	if (!skb_try_coalesce(to, from, fragstolen, &delta))
+		return false;
+
+	atomic_add(delta, &sk->sk_rmem_alloc);
+	sk_mem_charge(sk, delta);
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE);
+	TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
+	TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
+	TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags;
+	return true;
+}
+
 /* This one checks to see if we can put data from the
  * out_of_order queue into the receive_queue.
  */
@@ -4069,7 +4130,8 @@ static void tcp_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 dsack_high = tp->rcv_nxt;
-	struct sk_buff *skb;
+	struct sk_buff *skb, *tail;
+	bool fragstolen, eaten;
 
 	while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) {
 		if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
@@ -4082,9 +4144,9 @@ static void tcp_ofo_queue(struct sock *sk)
 			tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
 		}
 
+		__skb_unlink(skb, &tp->out_of_order_queue);
 		if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
 			SOCK_DEBUG(sk, "ofo packet was already received\n");
-			__skb_unlink(skb, &tp->out_of_order_queue);
 			__kfree_skb(skb);
 			continue;
 		}
@@ -4092,11 +4154,15 @@ static void tcp_ofo_queue(struct sock *sk)
 			   tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
 			   TCP_SKB_CB(skb)->end_seq);
 
-		__skb_unlink(skb, &tp->out_of_order_queue);
-		__skb_queue_tail(&sk->sk_receive_queue, skb);
+		tail = skb_peek_tail(&sk->sk_receive_queue);
+		eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
 		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-		if (tcp_hdr(skb)->fin)
+		if (!eaten)
+			__skb_queue_tail(&sk->sk_receive_queue, skb);
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			tcp_fin(sk);
+		if (eaten)
+			kfree_skb_partial(skb, fragstolen);
 	}
 }
 
@@ -4123,53 +4189,13 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
 	return 0;
 }
 
-/**
- * tcp_try_coalesce - try to merge skb to prior one
- * @sk: socket
- * @to: prior buffer
- * @from: buffer to add in queue
- * @fragstolen: pointer to boolean
- *
- * Before queueing skb @from after @to, try to merge them
- * to reduce overall memory use and queue lengths, if cost is small.
- * Packets in ofo or receive queues can stay a long time.
- * Better try to coalesce them right now to avoid future collapses.
- * Returns true if caller should free @from instead of queueing it
- */
-static bool tcp_try_coalesce(struct sock *sk,
-			     struct sk_buff *to,
-			     struct sk_buff *from,
-			     bool *fragstolen)
-{
-	int delta;
-
-	*fragstolen = false;
-
-	if (tcp_hdr(from)->fin)
-		return false;
-
-	/* Its possible this segment overlaps with prior segment in queue */
-	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
-		return false;
-
-	if (!skb_try_coalesce(to, from, fragstolen, &delta))
-		return false;
-
-	atomic_add(delta, &sk->sk_rmem_alloc);
-	sk_mem_charge(sk, delta);
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE);
-	TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
-	TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
-	return true;
-}
-
 static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb1;
 	u32 seq, end_seq;
 
-	TCP_ECN_check_ce(tp, skb);
+	tcp_ecn_check_ce(tp, skb);
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP);
@@ -4308,24 +4334,19 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
-	struct sk_buff *skb = NULL;
-	struct tcphdr *th;
+	struct sk_buff *skb;
 	bool fragstolen;
 
 	if (size == 0)
 		return 0;
 
-	skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
+	skb = alloc_skb(size, sk->sk_allocation);
 	if (!skb)
 		goto err;
 
-	if (tcp_try_rmem_schedule(sk, skb, size + sizeof(*th)))
+	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	th = (struct tcphdr *)skb_put(skb, sizeof(*th));
-	skb_reset_transport_header(skb);
-	memset(th, 0, sizeof(*th));
-
 	if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
 		goto err_free;
 
@@ -4333,7 +4354,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
 	TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
 
-	if (tcp_queue_rcv(sk, skb, sizeof(*th), &fragstolen)) {
+	if (tcp_queue_rcv(sk, skb, 0, &fragstolen)) {
 		WARN_ON_ONCE(fragstolen); /* should not happen */
 		__kfree_skb(skb);
 	}
@@ -4347,7 +4368,6 @@ err:
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
-	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int eaten = -1;
 	bool fragstolen = false;
@@ -4356,9 +4376,9 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 		goto drop;
 
 	skb_dst_drop(skb);
-	__skb_pull(skb, th->doff * 4);
+	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
-	TCP_ECN_accept_cwr(tp, skb);
+	tcp_ecn_accept_cwr(tp, skb);
 
 	tp->rx_opt.dsack = 0;
 
@@ -4400,7 +4420,7 @@ queue_and_out:
 		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
 		if (skb->len)
 			tcp_event_data_recv(sk, skb);
-		if (th->fin)
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			tcp_fin(sk);
 
 		if (!skb_queue_empty(&tp->out_of_order_queue)) {
@@ -4515,7 +4535,7 @@ restart:
 		 * - bloated or contains data before "start" or
 		 *   overlaps to the next one.
 		 */
-		if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin &&
+		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
 		    (tcp_win_from_space(skb->truesize) > skb->len ||
 		     before(TCP_SKB_CB(skb)->seq, start))) {
 			end_of_skbs = false;
@@ -4534,30 +4554,18 @@ restart:
 		/* Decided to skip this, advance start seq. */
 		start = TCP_SKB_CB(skb)->end_seq;
 	}
-	if (end_of_skbs || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
+	if (end_of_skbs ||
+	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 		return;
 
 	while (before(start, end)) {
+		int copy = min_t(int, SKB_MAX_ORDER(0, 0), end - start);
 		struct sk_buff *nskb;
-		unsigned int header = skb_headroom(skb);
-		int copy = SKB_MAX_ORDER(header, 0);
 
-		/* Too big header? This can happen with IPv6. */
-		if (copy < 0)
-			return;
-		if (end - start < copy)
-			copy = end - start;
-		nskb = alloc_skb(copy + header, GFP_ATOMIC);
+		nskb = alloc_skb(copy, GFP_ATOMIC);
 		if (!nskb)
 			return;
 
-		skb_set_mac_header(nskb, skb_mac_header(skb) - skb->head);
-		skb_set_network_header(nskb, (skb_network_header(skb) -
-					      skb->head));
-		skb_set_transport_header(nskb, (skb_transport_header(skb) -
-						skb->head));
-		skb_reserve(nskb, header);
-		memcpy(nskb->head, skb->head, header);
 		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
 		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
 		__skb_queue_before(list, skb, nskb);
@@ -4581,8 +4589,7 @@ restart:
 				skb = tcp_collapse_one(sk, skb, list);
 				if (!skb ||
 				    skb == tail ||
-				    tcp_hdr(skb)->syn ||
-				    tcp_hdr(skb)->fin)
+				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 					return;
 			}
 		}
@@ -5386,7 +5393,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 *    state to ESTABLISHED..."
 		 */
 
-		TCP_ECN_rcv_synack(tp, th);
+		tcp_ecn_rcv_synack(tp, th);
 
 		tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
 		tcp_ack(sk, skb, FLAG_SLOWPATH);
@@ -5505,7 +5512,7 @@ discard:
 		tp->snd_wl1    = TCP_SKB_CB(skb)->seq;
 		tp->max_window = tp->snd_wnd;
 
-		TCP_ECN_rcv_syn(tp, th);
+		tcp_ecn_rcv_syn(tp, th);
 
 		tcp_mtup_init(sk);
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
@@ -5835,6 +5842,40 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
 #endif
 }
 
+/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
+ *
+ * If we receive a SYN packet with these bits set, it means a
+ * network is playing bad games with TOS bits. In order to
+ * avoid possible false congestion notifications, we disable
+ * TCP ECN negociation.
+ *
+ * Exception: tcp_ca wants ECN. This is required for DCTCP
+ * congestion control; it requires setting ECT on all packets,
+ * including SYN. We inverse the test in this case: If our
+ * local socket wants ECN, but peer only set ece/cwr (but not
+ * ECT in IP header) its probably a non-DCTCP aware sender.
+ */
+static void tcp_ecn_create_request(struct request_sock *req,
+				   const struct sk_buff *skb,
+				   const struct sock *listen_sk)
+{
+	const struct tcphdr *th = tcp_hdr(skb);
+	const struct net *net = sock_net(listen_sk);
+	bool th_ecn = th->ece && th->cwr;
+	bool ect, need_ecn;
+
+	if (!th_ecn)
+		return;
+
+	ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
+	need_ecn = tcp_ca_needs_ecn(listen_sk);
+
+	if (!ect && !need_ecn && net->ipv4.sysctl_tcp_ecn)
+		inet_rsk(req)->ecn_ok = 1;
+	else if (ect && need_ecn)
+		inet_rsk(req)->ecn_ok = 1;
+}
+
 int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		     const struct tcp_request_sock_ops *af_ops,
 		     struct sock *sk, struct sk_buff *skb)
@@ -5843,7 +5884,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	struct request_sock *req;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct dst_entry *dst = NULL;
-	__u32 isn = TCP_SKB_CB(skb)->when;
+	__u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
 	bool want_cookie = false, fastopen;
 	struct flowi fl;
 	struct tcp_fastopen_cookie foc = { .len = -1 };
@@ -5895,7 +5936,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		goto drop_and_free;
 
 	if (!want_cookie || tmp_opt.tstamp_ok)
-		TCP_ECN_create_request(req, skb, sock_net(sk));
+		tcp_ecn_create_request(req, skb, sk);
 
 	if (want_cookie) {
 		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);