1 files changed, 276 insertions, 67 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d15586490cec..53617d715188 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -54,10 +54,13 @@
 #include <net/tcp.h>
 #include <linux/rtnetlink.h>
 #include <net/dst.h>
+#include <net/dst_metadata.h>
 #include <net/xfrm.h>
 #include <net/netevent.h>
 #include <net/netlink.h>
 #include <net/nexthop.h>
+#include <net/lwtunnel.h>
+#include <net/ip_tunnels.h>
 
 #include <asm/uaccess.h>
 
@@ -535,13 +538,14 @@ static void rt6_probe_deferred(struct work_struct *w)
 		container_of(w, struct __rt6_probe_work, work);
 
 	addrconf_addr_solict_mult(&work->target, &mcaddr);
-	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
+	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL);
 	dev_put(work->dev);
 	kfree(work);
 }
 
 static void rt6_probe(struct rt6_info *rt)
 {
+	struct __rt6_probe_work *work;
 	struct neighbour *neigh;
 	/*
 	 * Okay, this does not seem to be appropriate
@@ -556,34 +560,33 @@ static void rt6_probe(struct rt6_info *rt)
 	rcu_read_lock_bh();
 	neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
 	if (neigh) {
-		write_lock(&neigh->lock);
 		if (neigh->nud_state & NUD_VALID)
 			goto out;
-	}
-
-	if (!neigh ||
-	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
-		struct __rt6_probe_work *work;
 
+		work = NULL;
+		write_lock(&neigh->lock);
+		if (!(neigh->nud_state & NUD_VALID) &&
+		    time_after(jiffies,
+			       neigh->updated +
+			       rt->rt6i_idev->cnf.rtr_probe_interval)) {
+			work = kmalloc(sizeof(*work), GFP_ATOMIC);
+			if (work)
+				__neigh_set_probe_once(neigh);
+		}
+		write_unlock(&neigh->lock);
+	} else {
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	}
 
-		if (neigh && work)
-			__neigh_set_probe_once(neigh);
-
-		if (neigh)
-			write_unlock(&neigh->lock);
+	if (work) {
+		INIT_WORK(&work->work, rt6_probe_deferred);
+		work->target = rt->rt6i_gateway;
+		dev_hold(rt->dst.dev);
+		work->dev = rt->dst.dev;
+		schedule_work(&work->work);
+	}
 
-		if (work) {
-			INIT_WORK(&work->work, rt6_probe_deferred);
-			work->target = rt->rt6i_gateway;
-			dev_hold(rt->dst.dev);
-			work->dev = rt->dst.dev;
-			schedule_work(&work->work);
-		}
-	} else {
 out:
-		write_unlock(&neigh->lock);
-	}
 	rcu_read_unlock_bh();
 }
 #else
@@ -662,6 +665,12 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
 {
 	int m;
 	bool match_do_rr = false;
+	struct inet6_dev *idev = rt->rt6i_idev;
+	struct net_device *dev = rt->dst.dev;
+
+	if (dev && !netif_carrier_ok(dev) &&
+	    idev->cnf.ignore_routes_with_linkdown)
+		goto out;
 
 	if (rt6_check_expired(rt))
 		goto out;
@@ -1154,6 +1163,7 @@ void ip6_route_input(struct sk_buff *skb)
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct net *net = dev_net(skb->dev);
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
+	struct ip_tunnel_info *tun_info;
 	struct flowi6 fl6 = {
 		.flowi6_iif = skb->dev->ifindex,
 		.daddr = iph->daddr,
@@ -1163,6 +1173,10 @@ void ip6_route_input(struct sk_buff *skb)
 		.flowi6_proto = iph->nexthdr,
 	};
 
+	tun_info = skb_tunnel_info(skb);
+	if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX))
+		fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id;
+	skb_dst_drop(skb);
 	skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags));
 }
 
@@ -1684,6 +1698,7 @@ out:
 static int ip6_convert_metrics(struct mx6_config *mxc,
 			       const struct fib6_config *cfg)
 {
+	bool ecn_ca = false;
 	struct nlattr *nla;
 	int remaining;
 	u32 *mp;
@@ -1697,37 +1712,43 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 
 	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
 		int type = nla_type(nla);
+		u32 val;
 
-		if (type) {
-			u32 val;
+		if (!type)
+			continue;
+		if (unlikely(type > RTAX_MAX))
+			goto err;
+
+		if (type == RTAX_CC_ALGO) {
+			char tmp[TCP_CA_NAME_MAX];
 
-			if (unlikely(type > RTAX_MAX))
+			nla_strlcpy(tmp, nla, sizeof(tmp));
+			val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
+			if (val == TCP_CA_UNSPEC)
 				goto err;
-			if (type == RTAX_CC_ALGO) {
-				char tmp[TCP_CA_NAME_MAX];
+		} else {
+			val = nla_get_u32(nla);
+		}
+		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
+			goto err;
 
-				nla_strlcpy(tmp, nla, sizeof(tmp));
-				val = tcp_ca_get_key_by_name(tmp);
-				if (val == TCP_CA_UNSPEC)
-					goto err;
-			} else {
-				val = nla_get_u32(nla);
-			}
+		mp[type - 1] = val;
+		__set_bit(type - 1, mxc->mx_valid);
+	}
 
-			mp[type - 1] = val;
-			__set_bit(type - 1, mxc->mx_valid);
-		}
+	if (ecn_ca) {
+		__set_bit(RTAX_FEATURES - 1, mxc->mx_valid);
+		mp[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
 	}
 
 	mxc->mx = mp;
-
 	return 0;
  err:
 	kfree(mp);
 	return -EINVAL;
 }
 
-int ip6_route_add(struct fib6_config *cfg)
+int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
 {
 	int err;
 	struct net *net = cfg->fc_nlinfo.nl_net;
@@ -1735,7 +1756,6 @@ int ip6_route_add(struct fib6_config *cfg)
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
-	struct mx6_config mxc = { .mx = NULL, };
 	int addr_type;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
@@ -1801,6 +1821,25 @@ int ip6_route_add(struct fib6_config *cfg)
 
 	rt->dst.output = ip6_output;
 
+	if (cfg->fc_encap) {
+		struct lwtunnel_state *lwtstate;
+
+		err = lwtunnel_build_state(dev, cfg->fc_encap_type,
+					   cfg->fc_encap, AF_INET6, cfg,
+					   &lwtstate);
+		if (err)
+			goto out;
+		rt->dst.lwtstate = lwtstate_get(lwtstate);
+		if (lwtunnel_output_redirect(rt->dst.lwtstate)) {
+			rt->dst.lwtstate->orig_output = rt->dst.output;
+			rt->dst.output = lwtunnel_output;
+		}
+		if (lwtunnel_input_redirect(rt->dst.lwtstate)) {
+			rt->dst.lwtstate->orig_input = rt->dst.input;
+			rt->dst.input = lwtunnel_input;
+		}
+	}
+
 	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
 	rt->rt6i_dst.plen = cfg->fc_dst_len;
 	if (rt->rt6i_dst.plen == 128)
@@ -1941,6 +1980,32 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
+	*rt_ret = rt;
+
+	return 0;
+out:
+	if (dev)
+		dev_put(dev);
+	if (idev)
+		in6_dev_put(idev);
+	if (rt)
+		dst_free(&rt->dst);
+
+	*rt_ret = NULL;
+
+	return err;
+}
+
+int ip6_route_add(struct fib6_config *cfg)
+{
+	struct mx6_config mxc = { .mx = NULL, };
+	struct rt6_info *rt = NULL;
+	int err;
+
+	err = ip6_route_info_create(cfg, &rt);
+	if (err)
+		goto out;
+
 	err = ip6_convert_metrics(&mxc, cfg);
 	if (err)
 		goto out;
@@ -1948,14 +2013,12 @@ install_route:
 	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc);
 
 	kfree(mxc.mx);
+
 	return err;
 out:
-	if (dev)
-		dev_put(dev);
-	if (idev)
-		in6_dev_put(idev);
 	if (rt)
 		dst_free(&rt->dst);
+
 	return err;
 }
 
@@ -2180,6 +2243,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
 #endif
 	rt->rt6i_prefsrc = ort->rt6i_prefsrc;
 	rt->rt6i_table = ort->rt6i_table;
+	rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate);
 }
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
@@ -2628,6 +2692,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_METRICS]           = { .type = NLA_NESTED },
 	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
 	[RTA_PREF]              = { .type = NLA_U8 },
+	[RTA_ENCAP_TYPE]	= { .type = NLA_U16 },
+	[RTA_ENCAP]		= { .type = NLA_NESTED },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2722,24 +2788,89 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_flags |= RTF_PREF(pref);
 	}
 
+	if (tb[RTA_ENCAP])
+		cfg->fc_encap = tb[RTA_ENCAP];
+
+	if (tb[RTA_ENCAP_TYPE])
+		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
+
 	err = 0;
 errout:
 	return err;
 }
 
-static int ip6_route_multipath(struct fib6_config *cfg, int add)
+struct rt6_nh {
+	struct rt6_info *rt6_info;
+	struct fib6_config r_cfg;
+	struct mx6_config mxc;
+	struct list_head next;
+};
+
+static void ip6_print_replace_route_err(struct list_head *rt6_nh_list)
+{
+	struct rt6_nh *nh;
+
+	list_for_each_entry(nh, rt6_nh_list, next) {
+		pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6 nexthop %pI6 ifi %d\n",
+		        &nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway,
+		        nh->r_cfg.fc_ifindex);
+	}
+}
+
+static int ip6_route_info_append(struct list_head *rt6_nh_list,
+				 struct rt6_info *rt, struct fib6_config *r_cfg)
+{
+	struct rt6_nh *nh;
+	struct rt6_info *rtnh;
+	int err = -EEXIST;
+
+	list_for_each_entry(nh, rt6_nh_list, next) {
+		/* check if rt6_info already exists */
+		rtnh = nh->rt6_info;
+
+		if (rtnh->dst.dev == rt->dst.dev &&
+		    rtnh->rt6i_idev == rt->rt6i_idev &&
+		    ipv6_addr_equal(&rtnh->rt6i_gateway,
+				    &rt->rt6i_gateway))
+			return err;
+	}
+
+	nh = kzalloc(sizeof(*nh), GFP_KERNEL);
+	if (!nh)
+		return -ENOMEM;
+	nh->rt6_info = rt;
+	err = ip6_convert_metrics(&nh->mxc, r_cfg);
+	if (err) {
+		kfree(nh);
+		return err;
+	}
+	memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg));
+	list_add_tail(&nh->next, rt6_nh_list);
+
+	return 0;
+}
+
+static int ip6_route_multipath_add(struct fib6_config *cfg)
 {
 	struct fib6_config r_cfg;
 	struct rtnexthop *rtnh;
+	struct rt6_info *rt;
+	struct rt6_nh *err_nh;
+	struct rt6_nh *nh, *nh_safe;
 	int remaining;
 	int attrlen;
-	int err = 0, last_err = 0;
+	int err = 1;
+	int nhn = 0;
+	int replace = (cfg->fc_nlinfo.nlh &&
+		       (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
+	LIST_HEAD(rt6_nh_list);
 
 	remaining = cfg->fc_mp_len;
-beginning:
 	rtnh = (struct rtnexthop *)cfg->fc_mp;
 
-	/* Parse a Multipath Entry */
+	/* Parse a Multipath Entry and build a list (rt6_nh_list) of
+	 * rt6_info structs per nexthop
+	 */
 	while (rtnh_ok(rtnh, remaining)) {
 		memcpy(&r_cfg, cfg, sizeof(*cfg));
 		if (rtnh->rtnh_ifindex)
@@ -2754,23 +2885,37 @@ beginning:
 				r_cfg.fc_gateway = nla_get_in6_addr(nla);
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
+			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+			if (nla)
+				r_cfg.fc_encap_type = nla_get_u16(nla);
 		}
-		err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
+
+		err = ip6_route_info_create(&r_cfg, &rt);
+		if (err)
+			goto cleanup;
+
+		err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
 		if (err) {
-			last_err = err;
-			/* If we are trying to remove a route, do not stop the
-			 * loop when ip6_route_del() fails (because next hop is
-			 * already gone), we should try to remove all next hops.
-			 */
-			if (add) {
-				/* If add fails, we should try to delete all
-				 * next hops that have been already added.
-				 */
-				add = 0;
-				remaining = cfg->fc_mp_len - remaining;
-				goto beginning;
-			}
+			dst_free(&rt->dst);
+			goto cleanup;
+		}
+
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	err_nh = NULL;
+	list_for_each_entry(nh, &rt6_nh_list, next) {
+		err = __ip6_ins_rt(nh->rt6_info, &cfg->fc_nlinfo, &nh->mxc);
+		/* nh->rt6_info is used or freed at this point, reset to NULL*/
+		nh->rt6_info = NULL;
+		if (err) {
+			if (replace && nhn)
+				ip6_print_replace_route_err(&rt6_nh_list);
+			err_nh = nh;
+			goto add_errout;
 		}
+
 		/* Because each route is added like a single route we remove
 		 * these flags after the first nexthop: if there is a collision,
 		 * we have already failed to add the first nexthop:
@@ -2780,6 +2925,62 @@ beginning:
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
+		nhn++;
+	}
+
+	goto cleanup;
+
+add_errout:
+	/* Delete routes that were already added */
+	list_for_each_entry(nh, &rt6_nh_list, next) {
+		if (err_nh == nh)
+			break;
+		ip6_route_del(&nh->r_cfg);
+	}
+
+cleanup:
+	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
+		if (nh->rt6_info)
+			dst_free(&nh->rt6_info->dst);
+		kfree(nh->mxc.mx);
+		list_del(&nh->next);
+		kfree(nh);
+	}
+
+	return err;
+}
+
+static int ip6_route_multipath_del(struct fib6_config *cfg)
+{
+	struct fib6_config r_cfg;
+	struct rtnexthop *rtnh;
+	int remaining;
+	int attrlen;
+	int err = 1, last_err = 0;
+
+	remaining = cfg->fc_mp_len;
+	rtnh = (struct rtnexthop *)cfg->fc_mp;
+
+	/* Parse a Multipath Entry */
+	while (rtnh_ok(rtnh, remaining)) {
+		memcpy(&r_cfg, cfg, sizeof(*cfg));
+		if (rtnh->rtnh_ifindex)
+			r_cfg.fc_ifindex = rtnh->rtnh_ifindex;
+
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen > 0) {
+			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+
+			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			if (nla) {
+				nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+				r_cfg.fc_flags |= RTF_GATEWAY;
+			}
+		}
+		err = ip6_route_del(&r_cfg);
+		if (err)
+			last_err = err;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
@@ -2796,7 +2997,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 
 	if (cfg.fc_mp)
-		return ip6_route_multipath(&cfg, 0);
+		return ip6_route_multipath_del(&cfg);
 	else
 		return ip6_route_del(&cfg);
 }
@@ -2811,12 +3012,12 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 
 	if (cfg.fc_mp)
-		return ip6_route_multipath(&cfg, 1);
+		return ip6_route_multipath_add(&cfg);
 	else
 		return ip6_route_add(&cfg);
 }
 
-static inline size_t rt6_nlmsg_size(void)
+static inline size_t rt6_nlmsg_size(struct rt6_info *rt)
 {
 	return NLMSG_ALIGN(sizeof(struct rtmsg))
 	       + nla_total_size(16) /* RTA_SRC */
@@ -2830,7 +3031,8 @@ static inline size_t rt6_nlmsg_size(void)
 	       + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
 	       + nla_total_size(sizeof(struct rta_cacheinfo))
 	       + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
-	       + nla_total_size(1); /* RTA_PREF */
+	       + nla_total_size(1) /* RTA_PREF */
+	       + lwtunnel_get_encap_size(rt->dst.lwtstate);
 }
 
 static int rt6_fill_node(struct net *net,
@@ -2891,6 +3093,11 @@ static int rt6_fill_node(struct net *net,
 	else
 		rtm->rtm_type = RTN_UNICAST;
 	rtm->rtm_flags = 0;
+	if (!netif_carrier_ok(rt->dst.dev)) {
+		rtm->rtm_flags |= RTNH_F_LINKDOWN;
+		if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
+			rtm->rtm_flags |= RTNH_F_DEAD;
+	}
 	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
 	rtm->rtm_protocol = rt->rt6i_protocol;
 	if (rt->rt6i_flags & RTF_DYNAMIC)
@@ -2978,6 +3185,8 @@ static int rt6_fill_node(struct net *net,
 	if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
 		goto nla_put_failure;
 
+	lwtunnel_fill_encap(skb, rt->dst.lwtstate);
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -3104,7 +3313,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
 	err = -ENOBUFS;
 	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
-	skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
+	skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
 	if (!skb)
 		goto errout;