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

Pull networking changes from David Miller:

 1) GRE now works over ipv6, from Dmitry Kozlov.

 2) Make SCTP more network namespace aware, from Eric Biederman.

 3) TEAM driver now works with non-ethernet devices, from Jiri Pirko.

 4) Make openvswitch network namespace aware, from Pravin B Shelar.

 5) IPV6 NAT implementation, from Patrick McHardy.

 6) Server side support for TCP Fast Open, from Jerry Chu and others.

 7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel
    Borkmann.

 8) Increate the loopback default MTU to 64K, from Eric Dumazet.

 9) Use a per-task rather than per-socket page fragment allocator for
    outgoing networking traffic.  This benefits processes that have very
    many mostly idle sockets, which is quite common.

    From Eric Dumazet.

10) Use up to 32K for page fragment allocations, with fallbacks to
    smaller sizes when higher order page allocations fail.  Benefits are
    a) less segments for driver to process b) less calls to page
    allocator c) less waste of space.

    From Eric Dumazet.

11) Allow GRO to be used on GRE tunnels, from Eric Dumazet.

12) VXLAN device driver, one way to handle VLAN issues such as the
    limitation of 4096 VLAN IDs yet still have some level of isolation.
    From Stephen Hemminger.

13) As usual there is a large boatload of driver changes, with the scale
    perhaps tilted towards the wireless side this time around.

Fix up various fairly trivial conflicts, mostly caused by the user
namespace changes.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits)
  hyperv: Add buffer for extended info after the RNDIS response message.
  hyperv: Report actual status in receive completion packet
  hyperv: Remove extra allocated space for recv_pkt_list elements
  hyperv: Fix page buffer handling in rndis_filter_send_request()
  hyperv: Fix the missing return value in rndis_filter_set_packet_filter()
  hyperv: Fix the max_xfer_size in RNDIS initialization
  vxlan: put UDP socket in correct namespace
  vxlan: Depend on CONFIG_INET
  sfc: Fix the reported priorities of different filter types
  sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP
  sfc: Fix loopback self-test with separate_tx_channels=1
  sfc: Fix MCDI structure field lookup
  sfc: Add parentheses around use of bitfield macro arguments
  sfc: Fix null function pointer in efx_sriov_channel_type
  vxlan: virtual extensible lan
  igmp: export symbol ip_mc_leave_group
  netlink: add attributes to fdb interface
  tg3: unconditionally select HWMON support when tg3 is enabled.
  Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT"
  gre: fix sparse warning
  ...

1 files changed, 19 insertions, 8 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d04632673a9e..cfe6ffe1c177 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -702,7 +702,8 @@ static unsigned int tcp_synack_options(struct sock *sk,
                                    unsigned int mss, struct sk_buff *skb,
                                    struct tcp_out_options *opts,
                                    struct tcp_md5sig_key **md5,
-                                   struct tcp_extend_values *xvp)
+                                   struct tcp_extend_values *xvp,
+                                   struct tcp_fastopen_cookie *foc)
 {
         struct inet_request_sock *ireq = inet_rsk(req);
         unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -747,7 +748,15 @@ static unsigned int tcp_synack_options(struct sock *sk,
                 if (unlikely(!ireq->tstamp_ok))
                         remaining -= TCPOLEN_SACKPERM_ALIGNED;
         }
-
+        if (foc != NULL) {
+                u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
+                need = (need + 3) & ~3U;  /* Align to 32 bits */
+                if (remaining >= need) {
+                        opts->options |= OPTION_FAST_OPEN_COOKIE;
+                        opts->fastopen_cookie = foc;
+                        remaining -= need;
+                }
+        }
         /* Similar rationale to tcp_syn_options() applies here, too.
          * If the <SYN> options fit, the same options should fit now!
          */
@@ -2028,10 +2037,10 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
                 if (push_one)
                         break;
         }
-        if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery)
-                tp->prr_out += sent_pkts;
 
         if (likely(sent_pkts)) {
+                if (tcp_in_cwnd_reduction(sk))
+                        tp->prr_out += sent_pkts;
                 tcp_cwnd_validate(sk);
                 return false;
         }
@@ -2533,7 +2542,7 @@ begin_fwd:
                 }
                 NET_INC_STATS_BH(sock_net(sk), mib_idx);
 
-                if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery)
+                if (tcp_in_cwnd_reduction(sk))
                         tp->prr_out += tcp_skb_pcount(skb);
 
                 if (skb == tcp_write_queue_head(sk))
@@ -2658,7 +2667,8 @@ int tcp_send_synack(struct sock *sk)
  */
 struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
                                 struct request_sock *req,
-                                struct request_values *rvp)
+                                struct request_values *rvp,
+                                struct tcp_fastopen_cookie *foc)
 {
         struct tcp_out_options opts;
         struct tcp_extend_values *xvp = tcp_xv(rvp);
@@ -2718,7 +2728,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 #endif
         TCP_SKB_CB(skb)->when = tcp_time_stamp;
         tcp_header_size = tcp_synack_options(sk, req, mss,
-                                             skb, &opts, &md5, xvp)
+                                             skb, &opts, &md5, xvp, foc)
                         + sizeof(*th);
 
         skb_push(skb, tcp_header_size);
@@ -2772,7 +2782,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
         }
 
         th->seq = htonl(TCP_SKB_CB(skb)->seq);
-        th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
+        /* XXX data is queued and acked as is. No buffer/window check */
+        th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 
         /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
         th->window = htons(min(req->rcv_wnd, 65535U));