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

Pull networking fixes from David Miller:
 "It looks like a sizeble collection but this is nearly 3 weeks of bug
  fixing while you were away.

   1) Fix crashes over IPSEC tunnels with NAT, the latter can reroute
      the packet through a non-IPSEC protected path and the code has to
      be able to handle SKBs attached to routes lacking an attached xfrm
      state.  From Steffen Klassert.

   2) Fix OOPSs in ipv4 and ipv6 ipsec layers for unsupported
      sub-protocols, also from Steffen Klassert.

   3) Set local_df on fragmented netfilter skbs otherwise we won't be
      able to forward successfully, from Florian Westphal.

   4) cdc_mbim ipv6 neighbour code does __vlan_find_dev_deep without
      holding RCU lock, from Bjorn Mork.

   5) local_df test in ip_may_fragment is inverted, from Florian
      Westphal.

   6) jme driver doesn't check for DMA mapping failures, from Neil
      Horman.

   7) qlogic driver doesn't calculate number of TX queues properly, from
      Shahed Shaikh.

   8) fib_info_cnt can drift irreversibly positive if we fail to
      allocate the fi->fib_metrics array, from Sergey Popovich.

   9) Fix use after free in ip6_route_me_harder(), also from Sergey
      Popovich.

  10) When SYSCTL is disabled, we don't handle local_port_range and
      ping_group_range defaults properly at all, from Cong Wang.

  11) Unaccelerated VLAN tagged frames improperly handled by cdc_mbim
      driver, fix from Bjorn Mork.

  12) cassini driver needs nested lock annotations for TX locking, from
      Emil Goode.

  13) On init error ipv6 VTI driver can unregister pernet ops twice,
      oops.  Fix from Mahtias Krause.

  14) If macvlan device is down, don't propagate IFF_ALLMULTI changes,
      from Peter Christensen.

  15) Missing NULL pointer check while parsing netlink config options in
      ip6_tnl_validate().  From Susant Sahani.

  16) Fix handling of neighbour entries during ipv6 router reachability
      probing, from Duan Jiong.

  17) x86 and s390 JIT address randomization has some address
      calculation bugs leading to crashes, from Alexei Starovoitov and
      Heiko Carstens.

  18) Clear up those uglies with nop patching and net_get_random_once(),
      from Hannes Frederic Sowa.

  19) Option length miscalculated in ip6_append_data(), fix also from
      Hannes Frederic Sowa.

  20) A while ago we fixed a race during device unregistry when a
      namespace went down, turns out there is a second place that needs
      similar protection.  From Cong Wang.

  21) In the new Altera TSE driver multicast filtering isn't working,
      disable it and just use promisc mode until the cause is found.
      From Vince Bridgers.

  22) When we disable router enabling in ipv6 we have to flush the
      cached routes explicitly, from Duan Jiong.

  23) NBMA tunnels should not cache routes on the tunnel object because
      the key is variable, from Timo Teräs.

  24) With stacked devices GRO information in skb->cb[] can be not setup
      properly, make sure it is in all code paths.  From Eric Dumazet.

  25) Really fix stacked vlan locking, multiple levels of nesting with
      intervening non-vlan devices are possible.  From Vlad Yasevich.

  26) Fallback ipip tunnel device's mtu is not setup properly, from
      Steffen Klassert.

  27) The packet scheduler's tcindex filter can crash because we
      structure copy objects with list_head's inside, oops.  From Cong
      Wang.

  28) Fix CHECKSUM_COMPLETE handling for ipv6 GRE tunnels, from Eric
      Dumazet.

  29) In some configurations 'itag' in __mkroute_input() can end up
      being used uninitialized because of how fib_validate_source()
      works.  Fix it by explitly initializing itag to zero like all the
      other fib_validate_source() callers do, from Li RongQing"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
  batman: fix a bogus warning from batadv_is_on_batman_iface()
  ipv4: initialise the itag variable in __mkroute_input
  bonding: Send ALB learning packets using the right source
  bonding: Don't assume 802.1Q when sending alb learning packets.
  net: doc: Update references to skb->rxhash
  stmmac: Remove unbalanced clk_disable call
  ipv6: gro: fix CHECKSUM_COMPLETE support
  net_sched: fix an oops in tcindex filter
  can: peak_pci: prevent use after free at netdev removal
  ip_tunnel: Initialize the fallback device properly
  vlan: Fix build error wth vlan_get_encap_level()
  can: c_can: remove obsolete STRICT_FRAME_ORDERING Kconfig option
  MAINTAINERS: Pravin Shelar is Open vSwitch maintainer.
  bnx2x: Convert return 0 to return rc
  bonding: Fix alb mode to only use first level vlans.
  bonding: Fix stacked device detection in arp monitoring
  macvlan: Fix lockdep warnings with stacked macvlan devices
  vlan: Fix lockdep warning with stacked vlan devices.
  net: Allow for more then a single subclass for netif_addr_lock
  net: Find the nesting level of a given device by type.
  ...

14 files changed, 157 insertions, 114 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8c54870db792..6d6dd345bc4d 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1650,6 +1650,39 @@ static int __init init_ipv4_mibs(void)
 	return register_pernet_subsys(&ipv4_mib_ops);
 }
 
+static __net_init int inet_init_net(struct net *net)
+{
+	/*
+	 * Set defaults for local port range
+	 */
+	seqlock_init(&net->ipv4.ip_local_ports.lock);
+	net->ipv4.ip_local_ports.range[0] =  32768;
+	net->ipv4.ip_local_ports.range[1] =  61000;
+
+	seqlock_init(&net->ipv4.ping_group_range.lock);
+	/*
+	 * Sane defaults - nobody may create ping sockets.
+	 * Boot scripts should set this to distro-specific group.
+	 */
+	net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1);
+	net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0);
+	return 0;
+}
+
+static __net_exit void inet_exit_net(struct net *net)
+{
+}
+
+static __net_initdata struct pernet_operations af_inet_ops = {
+	.init = inet_init_net,
+	.exit = inet_exit_net,
+};
+
+static int __init init_inet_pernet_ops(void)
+{
+	return register_pernet_subsys(&af_inet_ops);
+}
+
 static int ipv4_proc_init(void);
 
 /*
@@ -1794,6 +1827,9 @@ static int __init inet_init(void)
 	if (ip_mr_init())
 		pr_crit("%s: Cannot init ipv4 mroute\n", __func__);
 #endif
+
+	if (init_inet_pernet_ops())
+		pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
 	/*
 	 *	Initialise per-cpu ipv4 mibs
 	 */
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8a043f03c88e..b10cd43a4722 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -821,13 +821,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
+	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
 		if (!fi->fib_metrics)
 			goto failure;
 	} else
 		fi->fib_metrics = (u32 *) dst_default_metrics;
-	fib_info_cnt++;
 
 	fi->fib_net = hold_net(net);
 	fi->fib_protocol = cfg->fc_protocol;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0d1e2cb877ec..a56b8e6e866a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -37,11 +37,11 @@ void inet_get_local_port_range(struct net *net, int *low, int *high)
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
-		*low = net->ipv4.sysctl_local_ports.range[0];
-		*high = net->ipv4.sysctl_local_ports.range[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+		*low = net->ipv4.ip_local_ports.range[0];
+		*high = net->ipv4.ip_local_ports.range[1];
+	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index be8abe73bb9f..6f111e48e11c 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -42,12 +42,12 @@
 static bool ip_may_fragment(const struct sk_buff *skb)
 {
 	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
-	       !skb->local_df;
+		skb->local_df;
 }
 
 static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 {
-	if (skb->len <= mtu || skb->local_df)
+	if (skb->len <= mtu)
 		return false;
 
 	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
@@ -56,53 +56,6 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
-static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
-{
-	unsigned int mtu;
-
-	if (skb->local_df || !skb_is_gso(skb))
-		return false;
-
-	mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
-
-	/* if seglen > mtu, do software segmentation for IP fragmentation on
-	 * output.  DF bit cannot be set since ip_forward would have sent
-	 * icmp error.
-	 */
-	return skb_gso_network_seglen(skb) > mtu;
-}
-
-/* called if GSO skb needs to be fragmented on forward */
-static int ip_forward_finish_gso(struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-	netdev_features_t features;
-	struct sk_buff *segs;
-	int ret = 0;
-
-	features = netif_skb_dev_features(skb, dst->dev);
-	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
-	if (IS_ERR(segs)) {
-		kfree_skb(skb);
-		return -ENOMEM;
-	}
-
-	consume_skb(skb);
-
-	do {
-		struct sk_buff *nskb = segs->next;
-		int err;
-
-		segs->next = NULL;
-		err = dst_output(segs);
-
-		if (err && ret == 0)
-			ret = err;
-		segs = nskb;
-	} while (segs);
-
-	return ret;
-}
 
 static int ip_forward_finish(struct sk_buff *skb)
 {
@@ -114,9 +67,6 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
-	if (ip_gso_exceeds_dst_mtu(skb))
-		return ip_forward_finish_gso(skb);
-
 	return dst_output(skb);
 }
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index c10a3ce5cbff..ed32313e307c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -232,8 +232,9 @@ static void ip_expire(unsigned long arg)
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
 		if (qp->user == IP_DEFRAG_AF_PACKET ||
-		    (qp->user == IP_DEFRAG_CONNTRACK_IN &&
-		     skb_rtable(head)->rt_type != RTN_LOCAL))
+		    ((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
+		     (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
+		     (skb_rtable(head)->rt_type != RTN_LOCAL)))
 			goto out_rcu_unlock;
 
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1cbeba5edff9..a52f50187b54 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -211,6 +211,48 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	return -EINVAL;
 }
 
+static int ip_finish_output_gso(struct sk_buff *skb)
+{
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	/* common case: locally created skb or seglen is <= mtu */
+	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
+	      skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
+		return ip_finish_output2(skb);
+
+	/* Slowpath -  GSO segment length is exceeding the dst MTU.
+	 *
+	 * This can happen in two cases:
+	 * 1) TCP GRO packet, DF bit not set
+	 * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
+	 * from host network stack.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = ip_fragment(segs, ip_finish_output2);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_finish_output(struct sk_buff *skb)
 {
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
@@ -220,10 +262,13 @@ static int ip_finish_output(struct sk_buff *skb)
 		return dst_output(skb);
 	}
 #endif
-	if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
+	if (skb_is_gso(skb))
+		return ip_finish_output_gso(skb);
+
+	if (skb->len > ip_skb_dst_mtu(skb))
 		return ip_fragment(skb, ip_finish_output2);
-	else
-		return ip_finish_output2(skb);
+
+	return ip_finish_output2(skb);
 }
 
 int ip_mc_output(struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index b3f859731c60..2acc2337d38b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -540,9 +540,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst;
 	int err;
-	bool connected = true;
+	bool connected;
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+	connected = (tunnel->parms.iph.daddr != 0);
 
 	dst = tnl_params->daddr;
 	if (dst == 0) {
@@ -882,6 +883,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 	 */
 	if (!IS_ERR(itn->fb_tunnel_dev)) {
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
 	}
 	rtnl_unlock();
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index afcee51b90ed..13ef00f1e17b 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -239,6 +239,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 static int vti4_err(struct sk_buff *skb, u32 info)
 {
 	__be32 spi;
+	__u32 mark;
 	struct xfrm_state *x;
 	struct ip_tunnel *tunnel;
 	struct ip_esp_hdr *esph;
@@ -254,6 +255,8 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 	if (!tunnel)
 		return -1;
 
+	mark = be32_to_cpu(tunnel->parms.o_key);
+
 	switch (protocol) {
 	case IPPROTO_ESP:
 		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
@@ -281,7 +284,7 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 		return 0;
 	}
 
-	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, protocol, AF_INET);
 	if (!x)
 		return 0;
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 12e13bd82b5b..f40f321b41fc 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,7 +22,6 @@
 #endif
 #include <net/netfilter/nf_conntrack_zones.h>
 
-/* Returns new sk_buff, or NULL */
 static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 {
 	int err;
@@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 	err = ip_defrag(skb, user);
 	local_bh_enable();
 
-	if (!err)
+	if (!err) {
 		ip_send_check(ip_hdr(skb));
+		skb->local_df = 1;
+	}
 
 	return err;
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8210964a9f19..044a0ddf6a79 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -236,15 +236,15 @@ exit:
 static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
 					  kgid_t *high)
 {
-	kgid_t *data = net->ipv4.sysctl_ping_group_range;
+	kgid_t *data = net->ipv4.ping_group_range.range;
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
 }
 
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index db1e0da871f4..5e676be3daeb 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1519,7 +1519,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct in_device *out_dev;
 	unsigned int flags = 0;
 	bool do_cache;
-	u32 itag;
+	u32 itag = 0;
 
 	/* get a working reference to the output device */
 	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 44eba052b43d..5cde8f263d40 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
 {
-	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
-	net->ipv4.sysctl_local_ports.range[0] = range[0];
-	net->ipv4.sysctl_local_ports.range[1] = range[1];
-	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	net->ipv4.ip_local_ports.range[0] = range[0];
+	net->ipv4.ip_local_ports.range[1] = range[1];
+	write_sequnlock(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -57,7 +57,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 				 size_t *lenp, loff_t *ppos)
 {
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
+		container_of(table->data, struct net, ipv4.ip_local_ports.range);
 	int ret;
 	int range[2];
 	struct ctl_table tmp = {
@@ -87,14 +87,14 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 {
 	kgid_t *data = table->data;
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+		container_of(table->data, struct net, ipv4.ping_group_range.range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
 }
 
 /* Update system visible IP port range */
@@ -102,11 +102,11 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 {
 	kgid_t *data = table->data;
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
-	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+		container_of(table->data, struct net, ipv4.ping_group_range.range);
+	write_seqlock(&net->ipv4.ip_local_ports.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+	write_sequnlock(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -805,7 +805,7 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ping_group_range",
-		.data		= &init_net.ipv4.sysctl_ping_group_range,
+		.data		= &init_net.ipv4.ping_group_range.range,
 		.maxlen		= sizeof(gid_t)*2,
 		.mode		= 0644,
 		.proc_handler	= ipv4_ping_group_range,
@@ -819,8 +819,8 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ip_local_port_range",
-		.maxlen		= sizeof(init_net.ipv4.sysctl_local_ports.range),
-		.data		= &init_net.ipv4.sysctl_local_ports.range,
+		.maxlen		= sizeof(init_net.ipv4.ip_local_ports.range),
+		.data		= &init_net.ipv4.ip_local_ports.range,
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
@@ -858,20 +858,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 			table[i].data += (void *)net - (void *)&init_net;
 	}
 
-	/*
-	 * Sane defaults - nobody may create ping sockets.
-	 * Boot scripts should set this to distro-specific group.
-	 */
-	net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
-	net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
-
-	/*
-	 * Set defaults for local port range
-	 */
-	seqlock_init(&net->ipv4.sysctl_local_ports.lock);
-	net->ipv4.sysctl_local_ports.range[0] =  32768;
-	net->ipv4.sysctl_local_ports.range[1] =  61000;
-
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
 	if (net->ipv4.ipv4_hdr == NULL)
 		goto err_reg;
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 40e701f2e1e0..186a8ecf92fa 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -62,10 +62,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED;
-
-	skb->protocol = htons(ETH_P_IP);
+	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -73,27 +70,34 @@ EXPORT_SYMBOL(xfrm4_prepare_output);
 
 int xfrm4_output_finish(struct sk_buff *skb)
 {
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+	skb->protocol = htons(ETH_P_IP);
+
+#ifdef CONFIG_NETFILTER
+	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
+#endif
+
+	return xfrm_output(skb);
+}
+
+static int __xfrm4_output(struct sk_buff *skb)
+{
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+
 #ifdef CONFIG_NETFILTER
-	if (!skb_dst(skb)->xfrm) {
+	if (!x) {
 		IPCB(skb)->flags |= IPSKB_REROUTED;
 		return dst_output(skb);
 	}
-
-	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
 #endif
 
-	skb->protocol = htons(ETH_P_IP);
-	return xfrm_output(skb);
+	return x->outer_mode->afinfo->output_finish(skb);
 }
 
 int xfrm4_output(struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct xfrm_state *x = dst->xfrm;
-
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
-			    NULL, dst->dev,
-			    x->outer_mode->afinfo->output_finish,
+			    NULL, skb_dst(skb)->dev, __xfrm4_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index 7f7b243e8139..a2ce0101eaac 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -50,8 +50,12 @@ int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 {
 	int ret;
 	struct xfrm4_protocol *handler;
+	struct xfrm4_protocol __rcu **head = proto_handlers(protocol);
 
-	for_each_protocol_rcu(*proto_handlers(protocol), handler)
+	if (!head)
+		return 0;
+
+	for_each_protocol_rcu(*head, handler)
 		if ((ret = handler->cb_handler(skb, err)) <= 0)
 			return ret;
 
@@ -64,15 +68,20 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 {
 	int ret;
 	struct xfrm4_protocol *handler;
+	struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr);
 
 	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
 	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
 	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
 
-	for_each_protocol_rcu(*proto_handlers(nexthdr), handler)
+	if (!head)
+		goto out;
+
+	for_each_protocol_rcu(*head, handler)
 		if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
 			return ret;
 
+out:
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
 
 	kfree_skb(skb);
@@ -208,6 +217,9 @@ int xfrm4_protocol_register(struct xfrm4_protocol *handler,
 	int ret = -EEXIST;
 	int priority = handler->priority;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm4_protocol_mutex);
 
 	if (!rcu_dereference_protected(*proto_handlers(protocol),
@@ -250,6 +262,9 @@ int xfrm4_protocol_deregister(struct xfrm4_protocol *handler,
 	struct xfrm4_protocol *t;
 	int ret = -ENOENT;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm4_protocol_mutex);
 
 	for (pprev = proto_handlers(protocol);