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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 42 insertions, 47 deletions

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index dab946554157..3d3092adf1d2 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -471,15 +471,16 @@ static int
 ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 	    u8 *type, u8 *code, int *msg, __u32 *info, int offset)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) skb->data;
-	struct ip6_tnl *t;
-	int rel_msg = 0;
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data;
+	struct net *net = dev_net(skb->dev);
 	u8 rel_type = ICMPV6_DEST_UNREACH;
 	u8 rel_code = ICMPV6_ADDR_UNREACH;
-	u8 tproto;
 	__u32 rel_info = 0;
-	__u16 len;
+	struct ip6_tnl *t;
 	int err = -ENOENT;
+	int rel_msg = 0;
+	u8 tproto;
+	__u16 len;
 
 	/* If the packet doesn't contain the original IPv6 header we are
 	   in trouble since we might need the source address for further
@@ -497,9 +498,8 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 	err = 0;
 
 	switch (*type) {
-		__u32 teli;
 		struct ipv6_tlv_tnl_enc_lim *tel;
-		__u32 mtu;
+		__u32 mtu, teli;
 	case ICMPV6_DEST_UNREACH:
 		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
 				    t->parms.name);
@@ -530,11 +530,11 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
+		ip6_update_pmtu(skb, net, htonl(*info), 0, 0,
+				sock_net_uid(net, NULL));
 		mtu = *info - offset;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
-		t->dev->mtu = mtu;
-
 		len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len);
 		if (len > mtu) {
 			rel_type = ICMPV6_PKT_TOOBIG;
@@ -543,6 +543,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 			rel_msg = 1;
 		}
 		break;
+	case NDISC_REDIRECT:
+		ip6_redirect(skb, net, skb->dev->ifindex, 0,
+			     sock_net_uid(net, NULL));
+		break;
 	}
 
 	*type = rel_type;
@@ -559,13 +563,12 @@ static int
 ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	   u8 type, u8 code, int offset, __be32 info)
 {
-	int rel_msg = 0;
-	u8 rel_type = type;
-	u8 rel_code = code;
 	__u32 rel_info = ntohl(info);
-	int err;
-	struct sk_buff *skb2;
 	const struct iphdr *eiph;
+	struct sk_buff *skb2;
+	int err, rel_msg = 0;
+	u8 rel_type = type;
+	u8 rel_code = code;
 	struct rtable *rt;
 	struct flowi4 fl4;
 
@@ -590,9 +593,6 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		rel_type = ICMP_DEST_UNREACH;
 		rel_code = ICMP_FRAG_NEEDED;
 		break;
-	case NDISC_REDIRECT:
-		rel_type = ICMP_REDIRECT;
-		rel_code = ICMP_REDIR_HOST;
 	default:
 		return 0;
 	}
@@ -611,33 +611,26 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	eiph = ip_hdr(skb2);
 
 	/* Try to guess incoming interface */
-	rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
-				   eiph->saddr, 0,
-				   0, 0,
-				   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
+	rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr,
+				   0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
 	if (IS_ERR(rt))
 		goto out;
 
 	skb2->dev = rt->dst.dev;
+	ip_rt_put(rt);
 
 	/* route "incoming" packet */
 	if (rt->rt_flags & RTCF_LOCAL) {
-		ip_rt_put(rt);
-		rt = NULL;
 		rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
-					   eiph->daddr, eiph->saddr,
-					   0, 0,
-					   IPPROTO_IPIP,
-					   RT_TOS(eiph->tos), 0);
-		if (IS_ERR(rt) ||
-		    rt->dst.dev->type != ARPHRD_TUNNEL) {
+					   eiph->daddr, eiph->saddr, 0, 0,
+					   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
+		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) {
 			if (!IS_ERR(rt))
 				ip_rt_put(rt);
 			goto out;
 		}
 		skb_dst_set(skb2, &rt->dst);
 	} else {
-		ip_rt_put(rt);
 		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
 				   skb2->dev) ||
 		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
@@ -649,10 +642,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info);
+		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2,
+						rel_info);
 	}
-	if (rel_type == ICMP_REDIRECT)
-		skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2);
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
 
@@ -665,11 +657,10 @@ static int
 ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	   u8 type, u8 code, int offset, __be32 info)
 {
-	int rel_msg = 0;
+	__u32 rel_info = ntohl(info);
+	int err, rel_msg = 0;
 	u8 rel_type = type;
 	u8 rel_code = code;
-	__u32 rel_info = ntohl(info);
-	int err;
 
 	err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code,
 			  &rel_msg, &rel_info, offset);
@@ -769,7 +760,8 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
 
 		if ((ipv6_addr_is_multicast(laddr) ||
 		     likely(ipv6_chk_addr(net, laddr, ldev, 0))) &&
-		    likely(!ipv6_chk_addr(net, raddr, NULL, 0)))
+		    ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) ||
+		     likely(!ipv6_chk_addr(net, raddr, NULL, 0))))
 			ret = 1;
 	}
 	return ret;
@@ -999,7 +991,8 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t,
 		if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0)))
 			pr_warn("%s xmit: Local address not yet configured!\n",
 				p->name);
-		else if (!ipv6_addr_is_multicast(raddr) &&
+		else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) &&
+			 !ipv6_addr_is_multicast(raddr) &&
 			 unlikely(ipv6_chk_addr(net, raddr, NULL, 0)))
 			pr_warn("%s xmit: Routing loop! Remote address found on this node!\n",
 				p->name);
@@ -2168,17 +2161,16 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
 	.priority	=	1,
 };
 
-static void __net_exit ip6_tnl_destroy_tunnels(struct net *net)
+static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list)
 {
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct net_device *dev, *aux;
 	int h;
 	struct ip6_tnl *t;
-	LIST_HEAD(list);
 
 	for_each_netdev_safe(net, dev, aux)
 		if (dev->rtnl_link_ops == &ip6_link_ops)
-			unregister_netdevice_queue(dev, &list);
+			unregister_netdevice_queue(dev, list);
 
 	for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) {
 		t = rtnl_dereference(ip6n->tnls_r_l[h]);
@@ -2187,12 +2179,10 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net)
 			 * been added to the list by the previous loop.
 			 */
 			if (!net_eq(dev_net(t->dev), net))
-				unregister_netdevice_queue(t->dev, &list);
+				unregister_netdevice_queue(t->dev, list);
 			t = rtnl_dereference(t->next);
 		}
 	}
-
-	unregister_netdevice_many(&list);
 }
 
 static int __net_init ip6_tnl_init_net(struct net *net)
@@ -2236,16 +2226,21 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit ip6_tnl_exit_net(struct net *net)
+static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list)
 {
+	struct net *net;
+	LIST_HEAD(list);
+
 	rtnl_lock();
-	ip6_tnl_destroy_tunnels(net);
+	list_for_each_entry(net, net_list, exit_list)
+		ip6_tnl_destroy_tunnels(net, &list);
+	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
 
 static struct pernet_operations ip6_tnl_net_ops = {
 	.init = ip6_tnl_init_net,
-	.exit = ip6_tnl_exit_net,
+	.exit_batch = ip6_tnl_exit_batch_net,
 	.id   = &ip6_tnl_net_id,
 	.size = sizeof(struct ip6_tnl_net),
 };