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

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

1 files changed, 48 insertions, 30 deletions

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 4c65ca1a86d1..cffd8f9ed1a9 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -125,6 +125,49 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 	return false;
 }
 
+
+/* If an incoming SYN or SYNACK frame contains a payload and/or FIN,
+ * queue this additional data / FIN.
+ */
+void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (TCP_SKB_CB(skb)->end_seq == tp->rcv_nxt)
+		return;
+
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	skb_dst_drop(skb);
+	/* segs_in has been initialized to 1 in tcp_create_openreq_child().
+	 * Hence, reset segs_in to 0 before calling tcp_segs_in()
+	 * to avoid double counting.  Also, tcp_segs_in() expects
+	 * skb->len to include the tcp_hdrlen.  Hence, it should
+	 * be called before __skb_pull().
+	 */
+	tp->segs_in = 0;
+	tcp_segs_in(tp, skb);
+	__skb_pull(skb, tcp_hdrlen(skb));
+	skb_set_owner_r(skb, sk);
+
+	TCP_SKB_CB(skb)->seq++;
+	TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+
+	tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	__skb_queue_tail(&sk->sk_receive_queue, skb);
+	tp->syn_data_acked = 1;
+
+	/* u64_stats_update_begin(&tp->syncp) not needed here,
+	 * as we certainly are not changing upper 32bit value (0)
+	 */
+	tp->bytes_received = skb->len;
+
+	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+		tcp_fin(sk);
+}
+
 static struct sock *tcp_fastopen_create_child(struct sock *sk,
 					      struct sk_buff *skb,
 					      struct dst_entry *dst,
@@ -133,7 +176,6 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	struct tcp_sock *tp;
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	struct sock *child;
-	u32 end_seq;
 	bool own_req;
 
 	req->num_retrans = 0;
@@ -179,35 +221,11 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	tcp_init_metrics(child);
 	tcp_init_buffer_space(child);
 
-	/* Queue the data carried in the SYN packet.
-	 * We used to play tricky games with skb_get().
-	 * With lockless listener, it is a dead end.
-	 * Do not think about it.
-	 *
-	 * XXX (TFO) - we honor a zero-payload TFO request for now,
-	 * (any reason not to?) but no need to queue the skb since
-	 * there is no data. How about SYN+FIN?
-	 */
-	end_seq = TCP_SKB_CB(skb)->end_seq;
-	if (end_seq != TCP_SKB_CB(skb)->seq + 1) {
-		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
-
-		if (likely(skb2)) {
-			skb_dst_drop(skb2);
-			__skb_pull(skb2, tcp_hdrlen(skb));
-			skb_set_owner_r(skb2, child);
-			__skb_queue_tail(&child->sk_receive_queue, skb2);
-			tp->syn_data_acked = 1;
-
-			/* u64_stats_update_begin(&tp->syncp) not needed here,
-			 * as we certainly are not changing upper 32bit value (0)
-			 */
-			tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
-		} else {
-			end_seq = TCP_SKB_CB(skb)->seq + 1;
-		}
-	}
-	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq;
+	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+
+	tcp_fastopen_add_skb(child, skb);
+
+	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt;
 	/* tcp_conn_request() is sending the SYNACK,
 	 * and queues the child into listener accept queue.
 	 */