Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1436 commits)
  cassini: Use local-mac-address prom property for Cassini MAC address
  net: remove the duplicate #ifdef __KERNEL__
  net: bridge: check the length of skb after nf_bridge_maybe_copy_header()
  netconsole: clarify stopping message
  netconsole: don't announce stopping if nothing happened
  cnic: Fix the type field in SPQ messages
  netfilter: fix export secctx error handling
  netfilter: fix the race when initializing nf_ct_expect_hash_rnd
  ipv4: IP defragmentation must be ECN aware
  net: r6040: Return proper error for r6040_init_one
  dcb: use after free in dcb_flushapp()
  dcb: unlock on error in dcbnl_ieee_get()
  net: ixp4xx_eth: Return proper error for eth_init_one
  include/linux/if_ether.h: Add #define ETH_P_LINK_CTL for HPNA and wlan local tunnel
  net: add POLLPRI to sock_def_readable()
  af_unix: Avoid socket->sk NULL OOPS in stream connect security hooks.
  net_sched: pfifo_head_drop problem
  mac80211: remove stray extern
  mac80211: implement off-channel TX using hw r-o-c offload
  mac80211: implement hardware offload for remain-on-channel
  ...

1 files changed, 26 insertions, 11 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 61c2463e275..dc7c096ddfe 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -55,7 +55,7 @@ int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
 int sysctl_tcp_tso_win_divisor __read_mostly = 3;
 
 int sysctl_tcp_mtu_probing __read_mostly = 0;
-int sysctl_tcp_base_mss __read_mostly = 512;
+int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
 
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
@@ -119,9 +119,13 @@ static __u16 tcp_advertise_mss(struct sock *sk)
 	struct dst_entry *dst = __sk_dst_get(sk);
 	int mss = tp->advmss;
 
-	if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) {
-		mss = dst_metric(dst, RTAX_ADVMSS);
-		tp->advmss = mss;
+	if (dst) {
+		unsigned int metric = dst_metric_advmss(dst);
+
+		if (metric < mss) {
+			mss = metric;
+			tp->advmss = mss;
+		}
 	}
 
 	return (__u16)mss;
@@ -224,10 +228,15 @@ void tcp_select_initial_window(int __space, __u32 mss,
 		}
 	}
 
-	/* Set initial window to value enough for senders, following RFC5681. */
+	/* Set initial window to a value enough for senders starting with
+	 * initial congestion window of TCP_DEFAULT_INIT_RCVWND. Place
+	 * a limit on the initial window when mss is larger than 1460.
+	 */
 	if (mss > (1 << *rcv_wscale)) {
-		int init_cwnd = rfc3390_bytes_to_packets(mss);
-
+		int init_cwnd = TCP_DEFAULT_INIT_RCVWND;
+		if (mss > 1460)
+			init_cwnd =
+			max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
 		/* when initializing use the value from init_rcv_wnd
 		 * rather than the default from above
 		 */
@@ -824,8 +833,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 							   &md5);
 	tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
 
-	if (tcp_packets_in_flight(tp) == 0)
+	if (tcp_packets_in_flight(tp) == 0) {
 		tcp_ca_event(sk, CA_EVENT_TX_START);
+		skb->ooo_okay = 1;
+	} else
+		skb->ooo_okay = 0;
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -2419,7 +2431,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
 	skb_dst_set(skb, dst_clone(dst));
 
-	mss = dst_metric(dst, RTAX_ADVMSS);
+	mss = dst_metric_advmss(dst);
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
 		mss = tp->rx_opt.user_mss;
 
@@ -2553,7 +2565,7 @@ static void tcp_connect_init(struct sock *sk)
 
 	if (!tp->window_clamp)
 		tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
-	tp->advmss = dst_metric(dst, RTAX_ADVMSS);
+	tp->advmss = dst_metric_advmss(dst);
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->advmss)
 		tp->advmss = tp->rx_opt.user_mss;
 
@@ -2596,6 +2608,7 @@ int tcp_connect(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *buff;
+	int err;
 
 	tcp_connect_init(sk);
 
@@ -2618,7 +2631,9 @@ int tcp_connect(struct sock *sk)
 	sk->sk_wmem_queued += buff->truesize;
 	sk_mem_charge(sk, buff->truesize);
 	tp->packets_out += tcp_skb_pcount(buff);
-	tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
+	err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
+	if (err == -ECONNREFUSED)
+		return err;
 
 	/* We change tp->snd_nxt after the tcp_transmit_skb() call
 	 * in order to make this packet get counted in tcpOutSegs.