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

Pull networking changes from David Miller:

 1) Multiply in netfilter IPVS can overflow when calculating destination
    weight.  From Simon Kirby.

 2) Use after free fixes in IPVS from Julian Anastasov.

 3) SFC driver bug fixes from Daniel Pieczko.

 4) Memory leak in pcan_usb_core failure paths, from Alexey Khoroshilov.

 5) Locking and encapsulation fixes to serial line CAN driver, from
    Andrew Naujoks.

 6) Duplex and VF handling fixes to bnx2x driver from Yaniv Rosner,
    Eilon Greenstein, and Ariel Elior.

 7) In lapb, if no other packets are outstanding, T1 timeouts actually
    stall things and no packet gets sent.  Fix from Josselin Costanzi.

 8) ICMP redirects should not make it to the socket error queues, from
    Duan Jiong.

 9) Fix bugs in skge DMA mapping error handling, from Nikulas Patocka.

10) Fix setting of VLAN priority field on via-rhine driver, from Roget
    Luethi.

11) Fix TX stalls and VLAN promisc programming in be2net driver from
    Ajit Khaparde.

12) Packet padding doesn't get handled correctly in new usbnet SG
    support code, from Ming Lei.

13) Fix races in netdevice teardown wrt.  network namespace closing.
    From Eric W.  Biederman.

14) Fix potential missed initialization of net_secret if not TCP
    connections are openned.  From Eric Dumazet.

15) Cinterion PLXX product ID in qmi_wwan driver is wrong, from
    Aleksander Morgado.

16) skb_cow_head() can change skb->data and thus packet header pointers,
    don't use stale ip_hdr reference in ip_tunnel code.

17) Backend state transition handling fixes in xen-netback, from Paul
    Durrant.

18) Packet offset for AH protocol is handled wrong in flow dissector,
    from Eric Dumazet.

19) Taking down an fq packet scheduler instance can leave stale packets
    in the queues, fix from Eric Dumazet.

20) Fix performance regressions introduced by TCP Small Queues.  From
    Eric Dumazet.

21) IPV6 GRE tunneling code calculates max_headroom incorrectly, from
    Hannes Frederic Sowa.

22) Multicast timer handlers in ipv4 and ipv6 can be the last and final
    reference to the ipv4/ipv6 specific network device state, so use the
    reference put that will check and release the object if the
    reference hits zero.  From Salam Noureddine.

23) Fix memory corruption in ip_tunnel driver, and use skb_push()
    instead of __skb_push() so that similar bugs are less hard to find.
    From Steffen Klassert.

24) Add forgotten hookup of rtnl_ops in SIT and ip6tnl drivers, from
    Nicolas Dichtel.

25) fq scheduler doesn't accurately rate limit in certain circumstances,
    from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (103 commits)
  pkt_sched: fq: rate limiting improvements
  ip6tnl: allow to use rtnl ops on fb tunnel
  sit: allow to use rtnl ops on fb tunnel
  ip_tunnel: Remove double unregister of the fallback device
  ip_tunnel_core: Change __skb_push back to skb_push
  ip_tunnel: Add fallback tunnels to the hash lists
  ip_tunnel: Fix a memory corruption in ip_tunnel_xmit
  qlcnic: Fix SR-IOV configuration
  ll_temac: Reset dma descriptors indexes on ndo_open
  skbuff: size of hole is wrong in a comment
  ipv6 mcast: use in6_dev_put in timer handlers instead of __in6_dev_put
  ipv4 igmp: use in_dev_put in timer handlers instead of __in_dev_put
  ethernet: moxa: fix incorrect placement of __initdata tag
  ipv6: gre: correct calculation of max_headroom
  powerpc/83xx: gianfar_ptp: select 1588 clock source through dts file
  Revert "powerpc/83xx: gianfar_ptp: select 1588 clock source through dts file"
  bonding: Fix broken promiscuity reference counting issue
  tcp: TSQ can use a dynamic limit
  dm9601: fix IFF_ALLMULTI handling
  pkt_sched: fq: qdisc dismantle fixes
  ...

8 files changed, 37 insertions, 28 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7a1874b7b8fd..cfeb85cff4f0 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -263,10 +263,8 @@ void build_ehash_secret(void)
 		get_random_bytes(&rnd, sizeof(rnd));
 	} while (rnd == 0);
 
-	if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) {
+	if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0)
 		get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
-		net_secret_init();
-	}
 }
 EXPORT_SYMBOL(build_ehash_secret);
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index dace87f06e5f..7defdc9ba167 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -736,7 +736,7 @@ static void igmp_gq_timer_expire(unsigned long data)
 
 	in_dev->mr_gq_running = 0;
 	igmpv3_send_report(in_dev, NULL);
-	__in_dev_put(in_dev);
+	in_dev_put(in_dev);
 }
 
 static void igmp_ifc_timer_expire(unsigned long data)
@@ -749,7 +749,7 @@ static void igmp_ifc_timer_expire(unsigned long data)
 		igmp_ifc_start_timer(in_dev,
 				     unsolicited_report_interval(in_dev));
 	}
-	__in_dev_put(in_dev);
+	in_dev_put(in_dev);
 }
 
 static void igmp_ifc_event(struct in_device *in_dev)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ac9fabe0300f..63a6d6d6b875 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -623,6 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			tunnel->err_count = 0;
 	}
 
+	tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
 	ttl = tnl_params->ttl;
 	if (ttl == 0) {
 		if (skb->protocol == htons(ETH_P_IP))
@@ -641,18 +642,17 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len;
-	if (max_headroom > dev->needed_headroom) {
+	if (max_headroom > dev->needed_headroom)
 		dev->needed_headroom = max_headroom;
-		if (skb_cow_head(skb, dev->needed_headroom)) {
-			dev->stats.tx_dropped++;
-			dev_kfree_skb(skb);
-			return;
-		}
+
+	if (skb_cow_head(skb, dev->needed_headroom)) {
+		dev->stats.tx_dropped++;
+		dev_kfree_skb(skb);
+		return;
 	}
 
 	err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol,
-			    ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df,
-			    !net_eq(tunnel->net, dev_net(dev)));
+			    tos, ttl, df, !net_eq(tunnel->net, dev_net(dev)));
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 
 	return;
@@ -853,8 +853,10 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
-	if (!IS_ERR(itn->fb_tunnel_dev))
+	if (!IS_ERR(itn->fb_tunnel_dev)) {
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
+	}
 	rtnl_unlock();
 
 	return PTR_RET(itn->fb_tunnel_dev);
@@ -884,8 +886,6 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
 			if (!net_eq(dev_net(t->dev), net))
 				unregister_netdevice_queue(t->dev, head);
 	}
-	if (itn->fb_tunnel_dev)
-		unregister_netdevice_queue(itn->fb_tunnel_dev, head);
 }
 
 void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index d6c856b17fd4..c31e3ad98ef2 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -61,7 +61,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
 	/* Push down and install the IP header. */
-	__skb_push(skb, sizeof(struct iphdr));
+	skb_push(skb, sizeof(struct iphdr));
 	skb_reset_network_header(skb);
 
 	iph = ip_hdr(skb);
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 67e17dcda65e..b6346bf2fde3 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -267,7 +267,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	if (th == NULL)
 		return NF_DROP;
 
-	synproxy_parse_options(skb, par->thoff, th, &opts);
+	if (!synproxy_parse_options(skb, par->thoff, th, &opts))
+		return NF_DROP;
 
 	if (th->syn && !(th->ack || th->fin || th->rst)) {
 		/* Initial SYN from client */
@@ -350,7 +351,8 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum,
 
 		/* fall through */
 	case TCP_CONNTRACK_SYN_SENT:
-		synproxy_parse_options(skb, thoff, th, &opts);
+		if (!synproxy_parse_options(skb, thoff, th, &opts))
+			return NF_DROP;
 
 		if (!th->syn && th->ack &&
 		    CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
@@ -373,7 +375,9 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum,
 		if (!th->syn || !th->ack)
 			break;
 
-		synproxy_parse_options(skb, thoff, th, &opts);
+		if (!synproxy_parse_options(skb, thoff, th, &opts))
+			return NF_DROP;
+
 		if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
 			synproxy->tsoff = opts.tsval - synproxy->its;
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bfec521c717f..193db03540ad 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -218,8 +218,10 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
 		ipv4_sk_update_pmtu(skb, sk, info);
-	else if (type == ICMP_REDIRECT)
+	else if (type == ICMP_REDIRECT) {
 		ipv4_sk_redirect(skb, sk);
+		return;
+	}
 
 	/* Report error on raw socket, if:
 	   1. User requested ip_recverr.
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7c83cb8bf137..e6bb8256e59f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -895,8 +895,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	skb_orphan(skb);
 	skb->sk = sk;
-	skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
-			  tcp_wfree : sock_wfree;
+	skb->destructor = tcp_wfree;
 	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
 	/* Build TCP header and checksum it. */
@@ -1840,7 +1839,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
-
 		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
 		BUG_ON(!tso_segs);
 
@@ -1869,13 +1867,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
-		/* TSQ : sk_wmem_alloc accounts skb truesize,
-		 * including skb overhead. But thats OK.
+		/* TCP Small Queues :
+		 * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+		 * This allows for :
+		 *  - better RTT estimation and ACK scheduling
+		 *  - faster recovery
+		 *  - high rates
 		 */
-		if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+		limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
+
+		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
 			break;
 		}
+
 		limit = mss_now;
 		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 74d2c95db57f..0ca44df51ee9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -658,7 +658,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 		break;
 	case ICMP_REDIRECT:
 		ipv4_sk_redirect(skb, sk);
-		break;
+		goto out;
 	}
 
 	/*