Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Conflicts:
	net/netfilter/core.c
	net/netfilter/nf_tables_netdev.c

Resolve two conflicts before pull request for David's net-next tree:

1) Between c73c24849011 ("netfilter: nf_tables_netdev: remove redundant
   ip_hdr assignment") from the net tree and commit ddc8b6027ad0
   ("netfilter: introduce nft_set_pktinfo_{ipv4, ipv6}_validate()").

2) Between e8bffe0cf964 ("net: Add _nf_(un)register_hooks symbols") and
   Aaron Conole's patches to replace list_head with single linked list.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

20 files changed, 271 insertions, 106 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f418d2eaeddd..2f1f5d439788 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -778,7 +778,14 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
 	}
 
 	if (p == &net->ipv6.devconf_all->forwarding) {
+		int old_dflt = net->ipv6.devconf_dflt->forwarding;
+
 		net->ipv6.devconf_dflt->forwarding = newf;
+		if ((!newf) ^ (!old_dflt))
+			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+						     NETCONFA_IFINDEX_DEFAULT,
+						     net->ipv6.devconf_dflt);
+
 		addrconf_forward_change(net, newf);
 		if ((!newf) ^ (!old))
 			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
@@ -1941,6 +1948,7 @@ errdad:
 	spin_unlock_bh(&ifp->lock);
 
 	addrconf_mod_dad_work(ifp, 0);
+	in6_ifa_put(ifp);
 }
 
 /* Join to solicited addr multicast group.
@@ -3850,6 +3858,7 @@ static void addrconf_dad_work(struct work_struct *w)
 		addrconf_dad_begin(ifp);
 		goto out;
 	} else if (action == DAD_ABORT) {
+		in6_ifa_hold(ifp);
 		addrconf_dad_stop(ifp, 1);
 		if (disable_ipv6)
 			addrconf_ifdown(idev->dev, 0);
@@ -6025,7 +6034,7 @@ static const struct ctl_table addrconf_sysctl[] = {
 static int __addrconf_sysctl_register(struct net *net, char *dev_name,
 		struct inet6_dev *idev, struct ipv6_devconf *p)
 {
-	int i;
+	int i, ifindex;
 	struct ctl_table *table;
 	char path[sizeof("net/ipv6/conf/") + IFNAMSIZ];
 
@@ -6045,6 +6054,13 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
 	if (!p->sysctl_header)
 		goto free;
 
+	if (!strcmp(dev_name, "all"))
+		ifindex = NETCONFA_IFINDEX_ALL;
+	else if (!strcmp(dev_name, "default"))
+		ifindex = NETCONFA_IFINDEX_DEFAULT;
+	else
+		ifindex = idev->dev->ifindex;
+	inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
 	return 0;
 
 free:
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 5857c1fc8b67..eea23b57c6a5 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -38,6 +38,9 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 		.flags = FIB_LOOKUP_NOREF,
 	};
 
+	/* update flow if oif or iif point to device enslaved to l3mdev */
+	l3mdev_update_flow(net, flowi6_to_flowi(fl6));
+
 	fib_rules_lookup(net->ipv6.fib6_rules_ops,
 			 flowi6_to_flowi(fl6), flags, &arg);
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 771be1fa4176..ef5485204522 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -743,6 +743,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 		   (info->nlh->nlmsg_flags & NLM_F_CREATE));
 	int found = 0;
 	bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
+	u16 nlflags = NLM_F_EXCL;
 	int err;
 
 	ins = &fn->leaf;
@@ -759,6 +760,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			if (info->nlh &&
 			    (info->nlh->nlmsg_flags & NLM_F_EXCL))
 				return -EEXIST;
+
+			nlflags &= ~NLM_F_EXCL;
 			if (replace) {
 				if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
 					found++;
@@ -856,6 +859,7 @@ next_iter:
 			pr_warn("NLM_F_CREATE should be set when creating new route\n");
 
 add:
+		nlflags |= NLM_F_CREATE;
 		err = fib6_commit_metrics(&rt->dst, mxc);
 		if (err)
 			return err;
@@ -864,7 +868,7 @@ add:
 		*ins = rt;
 		rt->rt6i_node = fn;
 		atomic_inc(&rt->rt6i_ref);
-		inet6_rt_notify(RTM_NEWROUTE, rt, info, 0);
+		inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
 		info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
 
 		if (!(fn->fn_flags & RTN_RTINFO)) {
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 397e1ed3daa3..4ce74f86291b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1239,7 +1239,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 		parms->encap_limit = nla_get_u8(data[IFLA_GRE_ENCAP_LIMIT]);
 
 	if (data[IFLA_GRE_FLOWINFO])
-		parms->flowinfo = nla_get_u32(data[IFLA_GRE_FLOWINFO]);
+		parms->flowinfo = nla_get_be32(data[IFLA_GRE_FLOWINFO]);
 
 	if (data[IFLA_GRE_FLAGS])
 		parms->flags = nla_get_u32(data[IFLA_GRE_FLAGS]);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 22e90e56b5a9..e7bfd55899a3 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -69,6 +69,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	int offset = 0;
 	bool encap, udpfrag;
 	int nhoff;
+	bool gso_partial;
 
 	skb_reset_network_header(skb);
 	nhoff = skb_network_header(skb) - skb_mac_header(skb);
@@ -101,9 +102,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	if (IS_ERR(segs))
 		goto out;
 
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
-		if (skb_is_gso(skb))
+		if (gso_partial)
 			payload_len = skb_shinfo(skb)->gso_size +
 				      SKB_GSO_CB(skb)->data_offset +
 				      skb->head - (unsigned char *)(ipv6h + 1);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 993fd9666f1b..6001e781164e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -236,6 +236,14 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
 		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			      IPSTATS_MIB_OUT, skb->len);
+
+		/* if egress device is enslaved to an L3 master device pass the
+		 * skb to its handler for processing
+		 */
+		skb = l3mdev_ip6_out((struct sock *)sk, skb);
+		if (unlikely(!skb))
+			return 0;
+
 		/* hooks should never assume socket lock is held.
 		 * we promote our socket to non const
 		 */
@@ -918,13 +926,6 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 	int err;
 	int flags = 0;
 
-	if (ipv6_addr_any(&fl6->saddr) && fl6->flowi6_oif &&
-	    (!*dst || !(*dst)->error)) {
-		err = l3mdev_get_saddr6(net, sk, fl6);
-		if (err)
-			goto out_err;
-	}
-
 	/* The correct way to handle this would be to do
 	 * ip6_route_get_saddr, and then ip6_route_output; however,
 	 * the route-specific preferred source forces the
@@ -1016,7 +1017,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 out_err_release:
 	dst_release(*dst);
 	*dst = NULL;
-out_err:
+
 	if (err == -ENETUNREACH)
 		IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
 	return err;
@@ -1062,8 +1063,6 @@ struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
 		return ERR_PTR(err);
 	if (final_dst)
 		fl6->daddr = *final_dst;
-	if (!fl6->flowi6_oif)
-		fl6->flowi6_oif = l3mdev_fib_oif(dst->dev);
 
 	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 2050217df565..6a66adba0c22 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -57,6 +57,7 @@
 #include <net/inet_ecn.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/dst_metadata.h>
 
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
@@ -90,6 +91,7 @@ struct ip6_tnl_net {
 	struct ip6_tnl __rcu *tnls_r_l[IP6_TUNNEL_HASH_SIZE];
 	struct ip6_tnl __rcu *tnls_wc[1];
 	struct ip6_tnl __rcu **tnls[2];
+	struct ip6_tnl __rcu *collect_md_tun;
 };
 
 static struct net_device_stats *ip6_get_stats(struct net_device *dev)
@@ -166,6 +168,10 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 			return t;
 	}
 
+	t = rcu_dereference(ip6n->collect_md_tun);
+	if (t)
+		return t;
+
 	t = rcu_dereference(ip6n->tnls_wc[0]);
 	if (t && (t->dev->flags & IFF_UP))
 		return t;
@@ -209,6 +215,8 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
 {
 	struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms);
 
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ip6n->collect_md_tun, t);
 	rcu_assign_pointer(t->next , rtnl_dereference(*tp));
 	rcu_assign_pointer(*tp, t);
 }
@@ -224,6 +232,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
 	struct ip6_tnl __rcu **tp;
 	struct ip6_tnl *iter;
 
+	if (t->parms.collect_md)
+		rcu_assign_pointer(ip6n->collect_md_tun, NULL);
+
 	for (tp = ip6_tnl_bucket(ip6n, &t->parms);
 	     (iter = rtnl_dereference(*tp)) != NULL;
 	     tp = &iter->next) {
@@ -829,6 +840,9 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev)));
 
+	if (tun_dst)
+		skb_dst_set(skb, (struct dst_entry *)tun_dst);
+
 	gro_cells_receive(&tunnel->gro_cells, skb);
 	return 0;
 
@@ -865,6 +879,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
 {
 	struct ip6_tnl *t;
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct metadata_dst *tun_dst = NULL;
 	int ret = -1;
 
 	rcu_read_lock();
@@ -881,7 +896,12 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
 			goto drop;
 		if (iptunnel_pull_header(skb, 0, tpi->proto, false))
 			goto drop;
-		ret = __ip6_tnl_rcv(t, skb, tpi, NULL, dscp_ecn_decapsulate,
+		if (t->parms.collect_md) {
+			tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0);
+			if (!tun_dst)
+				return 0;
+		}
+		ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
 				    log_ecn_error);
 	}
 
@@ -1012,8 +1032,16 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	int mtu;
 	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
 	unsigned int max_headroom = psh_hlen;
+	u8 hop_limit;
 	int err = -1;
 
+	if (t->parms.collect_md) {
+		hop_limit = skb_tunnel_info(skb)->key.ttl;
+		goto route_lookup;
+	} else {
+		hop_limit = t->parms.hop_limit;
+	}
+
 	/* NBMA tunnel */
 	if (ipv6_addr_any(&t->parms.raddr)) {
 		struct in6_addr *addr6;
@@ -1043,6 +1071,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		goto tx_err_link_failure;
 
 	if (!dst) {
+route_lookup:
 		dst = ip6_route_output(net, NULL, fl6);
 
 		if (dst->error)
@@ -1053,6 +1082,10 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 			dst = NULL;
 			goto tx_err_link_failure;
 		}
+		if (t->parms.collect_md &&
+		    ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
+				       &fl6->daddr, 0, &fl6->saddr))
+			goto tx_err_link_failure;
 		ndst = dst;
 	}
 
@@ -1071,7 +1104,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	}
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
-	if (skb_dst(skb))
+	if (skb_dst(skb) && !t->parms.collect_md)
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 	if (skb->len > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
@@ -1111,8 +1144,13 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		skb = new_skb;
 	}
 
-	if (!fl6->flowi6_mark && ndst)
-		dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr);
+	if (t->parms.collect_md) {
+		if (t->encap.type != TUNNEL_ENCAP_NONE)
+			goto tx_err_dst_release;
+	} else {
+		if (!fl6->flowi6_mark && ndst)
+			dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr);
+	}
 	skb_dst_set(skb, dst);
 
 	if (encap_limit >= 0) {
@@ -1137,7 +1175,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	ipv6h = ipv6_hdr(skb);
 	ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield),
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6));
-	ipv6h->hop_limit = t->parms.hop_limit;
+	ipv6h->hop_limit = hop_limit;
 	ipv6h->nexthdr = proto;
 	ipv6h->saddr = fl6->saddr;
 	ipv6h->daddr = fl6->daddr;
@@ -1170,18 +1208,34 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
 
-	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
-		encap_limit = t->parms.encap_limit;
+	dsfield = ipv4_get_dsfield(iph);
 
-	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+	if (t->parms.collect_md) {
+		struct ip_tunnel_info *tun_info;
+		const struct ip_tunnel_key *key;
 
-	dsfield = ipv4_get_dsfield(iph);
+		tun_info = skb_tunnel_info(skb);
+		if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+			     ip_tunnel_info_af(tun_info) != AF_INET6))
+			return -1;
+		key = &tun_info->key;
+		memset(&fl6, 0, sizeof(fl6));
+		fl6.flowi6_proto = IPPROTO_IPIP;
+		fl6.daddr = key->u.ipv6.dst;
+		fl6.flowlabel = key->label;
+	} else {
+		if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+			encap_limit = t->parms.encap_limit;
 
-	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-		fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
-					  & IPV6_TCLASS_MASK;
-	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
-		fl6.flowi6_mark = skb->mark;
+		memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+		fl6.flowi6_proto = IPPROTO_IPIP;
+
+		if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
+			fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
+					 & IPV6_TCLASS_MASK;
+		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
+			fl6.flowi6_mark = skb->mark;
+	}
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
@@ -1219,28 +1273,47 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	    ip6_tnl_addr_conflict(t, ipv6h))
 		return -1;
 
-	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
-	if (offset > 0) {
-		struct ipv6_tlv_tnl_enc_lim *tel;
-		tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
-		if (tel->encap_limit == 0) {
-			icmpv6_send(skb, ICMPV6_PARAMPROB,
-				    ICMPV6_HDR_FIELD, offset + 2);
+	dsfield = ipv6_get_dsfield(ipv6h);
+
+	if (t->parms.collect_md) {
+		struct ip_tunnel_info *tun_info;
+		const struct ip_tunnel_key *key;
+
+		tun_info = skb_tunnel_info(skb);
+		if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+			     ip_tunnel_info_af(tun_info) != AF_INET6))
 			return -1;
+		key = &tun_info->key;
+		memset(&fl6, 0, sizeof(fl6));
+		fl6.flowi6_proto = IPPROTO_IPV6;
+		fl6.daddr = key->u.ipv6.dst;
+		fl6.flowlabel = key->label;
+	} else {
+		offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+		if (offset > 0) {
+			struct ipv6_tlv_tnl_enc_lim *tel;
+
+			tel = (void *)&skb_network_header(skb)[offset];
+			if (tel->encap_limit == 0) {
+				icmpv6_send(skb, ICMPV6_PARAMPROB,
+					    ICMPV6_HDR_FIELD, offset + 2);
+				return -1;
+			}
+			encap_limit = tel->encap_limit - 1;
+		} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) {
+			encap_limit = t->parms.encap_limit;
 		}
-		encap_limit = tel->encap_limit - 1;
-	} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
-		encap_limit = t->parms.encap_limit;
 
-	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+		memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+		fl6.flowi6_proto = IPPROTO_IPV6;
 
-	dsfield = ipv6_get_dsfield(ipv6h);
-	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
-	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
-		fl6.flowlabel |= ip6_flowlabel(ipv6h);
-	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
-		fl6.flowi6_mark = skb->mark;
+		if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
+			fl6.flowlabel |= (*(__be32 *)ipv6h & IPV6_TCLASS_MASK);
+		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
+			fl6.flowlabel |= ip6_flowlabel(ipv6h);
+		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
+			fl6.flowi6_mark = skb->mark;
+	}
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
@@ -1739,6 +1812,10 @@ static int ip6_tnl_dev_init(struct net_device *dev)
 	if (err)
 		return err;
 	ip6_tnl_link_config(t);
+	if (t->parms.collect_md) {
+		dev->features |= NETIF_F_NETNS_LOCAL;
+		netif_keep_dst(dev);
+	}
 	return 0;
 }
 
@@ -1809,6 +1886,9 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[],
 
 	if (data[IFLA_IPTUN_PROTO])
 		parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
+
+	if (data[IFLA_IPTUN_COLLECT_METADATA])
+		parms->collect_md = true;
 }
 
 static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[],
@@ -1848,6 +1928,7 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
 			   struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net *net = dev_net(dev);
+	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct ip6_tnl *nt, *t;
 	struct ip_tunnel_encap ipencap;
 
@@ -1862,9 +1943,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
 
 	ip6_tnl_netlink_parms(data, &nt->parms);
 
-	t = ip6_tnl_locate(net, &nt->parms, 0);
-	if (!IS_ERR(t))
-		return -EEXIST;
+	if (nt->parms.collect_md) {
+		if (rtnl_dereference(ip6n->collect_md_tun))
+			return -EEXIST;
+	} else {
+		t = ip6_tnl_locate(net, &nt->parms, 0);
+		if (!IS_ERR(t))
+			return -EEXIST;
+	}
 
 	return ip6_tnl_create2(dev);
 }
@@ -1888,6 +1974,8 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 			return err;
 	}
 	ip6_tnl_netlink_parms(data, &p);
+	if (p.collect_md)
+		return -EINVAL;
 
 	t = ip6_tnl_locate(net, &p, 0);
 	if (!IS_ERR(t)) {
@@ -1935,6 +2023,8 @@ static size_t ip6_tnl_get_size(const struct net_device *dev)
 		nla_total_size(2) +
 		/* IFLA_IPTUN_ENCAP_DPORT */
 		nla_total_size(2) +
+		/* IFLA_IPTUN_COLLECT_METADATA */
+		nla_total_size(0) +
 		0;
 }
 
@@ -1953,16 +2043,15 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto))
 		goto nla_put_failure;
 
-	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
-			tunnel->encap.type) ||
-	nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
-		     tunnel->encap.sport) ||
-	nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
-		     tunnel->encap.dport) ||
-	nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
-		    tunnel->encap.flags))
+	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) ||
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) ||
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) ||
+	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags))
 		goto nla_put_failure;
 
+	if (parm->collect_md)
+		if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA))
+			goto nla_put_failure;
 	return 0;
 
 nla_put_failure:
@@ -1990,6 +2079,7 @@ static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_ENCAP_FLAGS]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_SPORT]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_DPORT]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_COLLECT_METADATA]	= { .type = NLA_FLAG },
 };
 
 static struct rtnl_link_ops ip6_link_ops __read_mostly = {
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index cc7e05898307..8a02ca8a11af 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -321,11 +321,9 @@ static int vti6_rcv(struct sk_buff *skb)
 			goto discard;
 		}
 
-		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
-
 		rcu_read_unlock();
 
-		return xfrm6_rcv(skb);
+		return xfrm6_rcv_tnl(skb, t);
 	}
 	rcu_read_unlock();
 	return -EINVAL;
@@ -340,6 +338,7 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
 	struct net_device *dev;
 	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
+	struct xfrm_mode *inner_mode;
 	struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
 	u32 orig_mark = skb->mark;
 	int ret;
@@ -357,7 +356,19 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
 	}
 
 	x = xfrm_input_state(skb);
-	family = x->inner_mode->afinfo->family;
+
+	inner_mode = x->inner_mode;
+
+	if (x->sel.family == AF_UNSPEC) {
+		inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
+		if (inner_mode == NULL) {
+			XFRM_INC_STATS(dev_net(skb->dev),
+				       LINUX_MIB_XFRMINSTATEMODEERROR);
+			return -EINVAL;
+		}
+	}
+
+	family = inner_mode->afinfo->family;
 
 	skb->mark = be32_to_cpu(t->parms.i_key);
 	ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 6122f9c5cc49..fccb5dd91902 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2239,6 +2239,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	struct rta_mfc_stats mfcs;
 	struct nlattr *mp_attr;
 	struct rtnexthop *nhp;
+	unsigned long lastuse;
 	int ct;
 
 	/* If cache is unresolved, don't try to parse IIF and OIF */
@@ -2269,12 +2270,14 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 
 	nla_nest_end(skb, mp_attr);
 
+	lastuse = READ_ONCE(c->mfc_un.res.lastuse);
+	lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
+
 	mfcs.mfcs_packets = c->mfc_un.res.pkt;
 	mfcs.mfcs_bytes = c->mfc_un.res.bytes;
 	mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
 	if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
-	    nla_put_u64_64bit(skb, RTA_EXPIRES,
-			      jiffies_to_clock_t(c->mfc_un.res.lastuse),
+	    nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
 			      RTA_PAD))
 		return -EMSGSIZE;
 
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index fe65cdc28a45..d8e671457d10 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -67,7 +67,6 @@
 #include <net/flow.h>
 #include <net/ip6_checksum.h>
 #include <net/inet_common.h>
-#include <net/l3mdev.h>
 #include <linux/proc_fs.h>
 
 #include <linux/netfilter.h>
@@ -457,11 +456,9 @@ static void ndisc_send_skb(struct sk_buff *skb,
 
 	if (!dst) {
 		struct flowi6 fl6;
-		int oif = l3mdev_fib_oif(skb->dev);
+		int oif = skb->dev->ifindex;
 
 		icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif);
-		if (oif != skb->dev->ifindex)
-			fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC;
 		dst = icmp6_dst_alloc(skb->dev, &fl6);
 		if (IS_ERR(dst)) {
 			kfree_skb(skb);
@@ -1538,7 +1535,6 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 	int rd_len;
 	u8 ha_buf[MAX_ADDR_LEN], *ha = NULL,
 	   ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
-	int oif = l3mdev_fib_oif(dev);
 	bool ret;
 
 	if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) {
@@ -1555,10 +1551,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 	}
 
 	icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT,
-			 &saddr_buf, &ipv6_hdr(skb)->saddr, oif);
-
-	if (oif != skb->dev->ifindex)
-		fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC;
+			 &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex);
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst->error) {
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index 01eb0f658366..f2727475895e 100644
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -31,6 +31,7 @@ static unsigned int nf_route_table_hook(void *priv,
 	struct in6_addr saddr, daddr;
 	u_int8_t hop_limit;
 	u32 mark, flowlabel;
+	int err;
 
 	nft_set_pktinfo_ipv6(&pkt, skb, state);
 
@@ -44,13 +45,16 @@ static unsigned int nf_route_table_hook(void *priv,
 	flowlabel = *((u32 *)ipv6_hdr(skb));
 
 	ret = nft_do_chain(&pkt, priv);
-	if (ret != NF_DROP && ret != NF_QUEUE &&
+	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
 	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
-	     flowlabel != *((u_int32_t *)ipv6_hdr(skb))))
-		return ip6_route_me_harder(state->net, skb) == 0 ? ret : NF_DROP;
+	     flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
+		err = ip6_route_me_harder(state->net, skb);
+		if (err < 0)
+			ret = NF_DROP_ERR(err);
+	}
 
 	return ret;
 }
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
index 533cd5719c59..92bda9908bb9 100644
--- a/net/ipv6/netfilter/nft_reject_ipv6.c
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -47,6 +47,7 @@ static const struct nft_expr_ops nft_reject_ipv6_ops = {
 	.eval		= nft_reject_ipv6_eval,
 	.init		= nft_reject_init,
 	.dump		= nft_reject_dump,
+	.validate	= nft_reject_validate,
 };
 
 static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 462f2a76b5c2..7cca8ac66fe9 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -148,6 +148,13 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 	ipv6_hdr(skb)->payload_len = htons(len);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
+	/* if egress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip6_out(sk, skb);
+	if (unlikely(!skb))
+		return 0;
+
 	return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
 		       net, sk, skb, NULL, skb_dst(skb)->dev,
 		       dst_output);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 0900352c924c..0e983b694ee8 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -126,8 +126,10 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	rt = (struct rt6_info *) dst;
 
 	np = inet6_sk(sk);
-	if (!np)
-		return -EBADF;
+	if (!np) {
+		err = -EBADF;
+		goto dst_err_out;
+	}
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
 		fl6.flowi6_oif = np->mcast_oif;
@@ -163,6 +165,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 	release_sock(sk);
 
+dst_err_out:
+	dst_release(dst);
+
 	if (err)
 		return err;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 590dd1f7746f..54404f08efcc 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -653,6 +653,13 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	if (err)
 		goto error_fault;
 
+	/* if egress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip6_out(sk, skb);
+	if (unlikely(!skb))
+		return 0;
+
 	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
 	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
 		      NULL, rt->dst.dev, dst_output);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 09d43ff11a8d..5a5aeb92b4ec 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1147,15 +1147,16 @@ static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *
 	return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags);
 }
 
-static struct dst_entry *ip6_route_input_lookup(struct net *net,
-						struct net_device *dev,
-						struct flowi6 *fl6, int flags)
+struct dst_entry *ip6_route_input_lookup(struct net *net,
+					 struct net_device *dev,
+					 struct flowi6 *fl6, int flags)
 {
 	if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG)
 		flags |= RT6_LOOKUP_F_IFACE;
 
 	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input);
 }
+EXPORT_SYMBOL_GPL(ip6_route_input_lookup);
 
 void ip6_route_input(struct sk_buff *skb)
 {
@@ -1164,7 +1165,7 @@ void ip6_route_input(struct sk_buff *skb)
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
 	struct ip_tunnel_info *tun_info;
 	struct flowi6 fl6 = {
-		.flowi6_iif = l3mdev_fib_oif(skb->dev),
+		.flowi6_iif = skb->dev->ifindex,
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 		.flowlabel = ip6_flowinfo(iph),
@@ -1188,12 +1189,15 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
 struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 					 struct flowi6 *fl6, int flags)
 {
-	struct dst_entry *dst;
 	bool any_src;
 
-	dst = l3mdev_get_rt6_dst(net, fl6);
-	if (dst)
-		return dst;
+	if (rt6_need_strict(&fl6->daddr)) {
+		struct dst_entry *dst;
+
+		dst = l3mdev_link_scope_lookup(net, fl6);
+		if (dst)
+			return dst;
+	}
 
 	fl6->flowi6_iif = LOOPBACK_IFINDEX;
 
@@ -1988,9 +1992,18 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 			if (!(gwa_type & IPV6_ADDR_UNICAST))
 				goto out;
 
-			if (cfg->fc_table)
+			if (cfg->fc_table) {
 				grt = ip6_nh_lookup_table(net, cfg, gw_addr);
 
+				if (grt) {
+					if (grt->rt6i_flags & RTF_GATEWAY ||
+					    (dev && dev != grt->dst.dev)) {
+						ip6_rt_put(grt);
+						grt = NULL;
+					}
+				}
+			}
+
 			if (!grt)
 				grt = rt6_lookup(net, gw_addr, NULL,
 						 cfg->fc_ifindex, 1);
@@ -2558,8 +2571,16 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 {
 	u32 tb_id;
 	struct net *net = dev_net(idev->dev);
-	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
-					    DST_NOCOUNT);
+	struct net_device *dev = net->loopback_dev;
+	struct rt6_info *rt;
+
+	/* use L3 Master device as loopback for host routes if device
+	 * is enslaved and address is not link local or multicast
+	 */
+	if (!rt6_need_strict(addr))
+		dev = l3mdev_master_dev_rcu(idev->dev) ? : dev;
+
+	rt = ip6_dst_alloc(net, dev, DST_NOCOUNT);
 	if (!rt)
 		return ERR_PTR(-ENOMEM);
 
@@ -3338,11 +3359,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	} else {
 		fl6.flowi6_oif = oif;
 
-		if (netif_index_is_l3_master(net, oif)) {
-			fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC |
-					   FLOWI_FLAG_SKIP_NH_OIF;
-		}
-
 		rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 04529a3d42cb..54cf7197c7ab 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -818,12 +818,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	fl6.flowi6_proto = IPPROTO_TCP;
 	if (rt6_need_strict(&fl6.daddr) && !oif)
 		fl6.flowi6_oif = tcp_v6_iif(skb);
-	else {
-		if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
-			oif = skb->skb_iif;
-
-		fl6.flowi6_oif = oif;
-	}
+	else
+		fl6.flowi6_oif = oif ? : skb->skb_iif;
 
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
 	fl6.fl6_dport = t1->dest;
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 0eaab1fa6be5..b5789562aded 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -21,8 +21,10 @@ int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb)
 	return xfrm6_extract_header(skb);
 }
 
-int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
+int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi,
+		  struct ip6_tnl *t)
 {
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
 	XFRM_SPI_SKB_CB(skb)->family = AF_INET6;
 	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
 	return xfrm_input(skb, nexthdr, spi, 0);
@@ -48,13 +50,18 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 	return -1;
 }
 
-int xfrm6_rcv(struct sk_buff *skb)
+int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t)
 {
 	return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
-			     0);
+			     0, t);
 }
-EXPORT_SYMBOL(xfrm6_rcv);
+EXPORT_SYMBOL(xfrm6_rcv_tnl);
 
+int xfrm6_rcv(struct sk_buff *skb)
+{
+	return xfrm6_rcv_tnl(skb, NULL);
+}
+EXPORT_SYMBOL(xfrm6_rcv);
 int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
 		     xfrm_address_t *saddr, u8 proto)
 {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 6cc97003e4a9..e0f71c01d728 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -36,7 +36,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
 	int err;
 
 	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_oif = oif;
+	fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif);
 	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
 	memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
 	if (saddr)
@@ -134,7 +134,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 	nexthdr = nh[nhoff];
 
 	if (skb_dst(skb))
-		oif = l3mdev_fib_oif(skb_dst(skb)->dev);
+		oif = skb_dst(skb)->dev->ifindex;
 
 	memset(fl6, 0, sizeof(struct flowi6));
 	fl6->flowi6_mark = skb->mark;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 5743044cd660..e1c0bbe7996c 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -236,7 +236,7 @@ static int xfrm6_tunnel_rcv(struct sk_buff *skb)
 	__be32 spi;
 
 	spi = xfrm6_tunnel_spi_lookup(net, (const xfrm_address_t *)&iph->saddr);
-	return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi);
+	return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL);
 }
 
 static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt,