1 files changed, 97 insertions, 84 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ddb9d41c8ee..f23fbd28a50 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -66,8 +66,9 @@
 #endif
 
 enum rt6_nud_state {
-	RT6_NUD_FAIL_HARD = -2,
-	RT6_NUD_FAIL_SOFT = -1,
+	RT6_NUD_FAIL_HARD = -3,
+	RT6_NUD_FAIL_PROBE = -2,
+	RT6_NUD_FAIL_DO_RR = -1,
 	RT6_NUD_SUCCEED = 1
 };
 
@@ -83,9 +84,9 @@ static void		ip6_dst_ifdown(struct dst_entry *,
 static int		 ip6_dst_gc(struct dst_ops *ops);
 
 static int		ip6_pkt_discard(struct sk_buff *skb);
-static int		ip6_pkt_discard_out(struct sk_buff *skb);
+static int		ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb);
 static int		ip6_pkt_prohibit(struct sk_buff *skb);
-static int		ip6_pkt_prohibit_out(struct sk_buff *skb);
+static int		ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 					   struct sk_buff *skb, u32 mtu);
@@ -103,6 +104,36 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 					   const struct in6_addr *gwaddr, int ifindex);
 #endif
 
+static void rt6_bind_peer(struct rt6_info *rt, int create)
+{
+	struct inet_peer_base *base;
+	struct inet_peer *peer;
+
+	base = inetpeer_base_ptr(rt->_rt6i_peer);
+	if (!base)
+		return;
+
+	peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
+	if (peer) {
+		if (!rt6_set_peer(rt, peer))
+			inet_putpeer(peer);
+	}
+}
+
+static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create)
+{
+	if (rt6_has_peer(rt))
+		return rt6_peer_ptr(rt);
+
+	rt6_bind_peer(rt, create);
+	return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL);
+}
+
+static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt)
+{
+	return __rt6_get_peer(rt, 1);
+}
+
 static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 {
 	struct rt6_info *rt = (struct rt6_info *) dst;
@@ -118,7 +149,8 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 		unsigned long prev, new;
 
 		p = peer->metrics;
-		if (inet_metrics_new(peer))
+		if (inet_metrics_new(peer) ||
+		    (old & DST_METRICS_FORCE_OVERWRITE))
 			memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
 
 		new = (unsigned long) p;
@@ -258,7 +290,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
 		.obsolete	= DST_OBSOLETE_FORCE_CHK,
 		.error		= -EINVAL,
 		.input		= dst_discard,
-		.output		= dst_discard,
+		.output		= dst_discard_sk,
 	},
 	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
 	.rt6i_protocol  = RTPROT_KERNEL,
@@ -311,22 +343,6 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 	}
 }
 
-void rt6_bind_peer(struct rt6_info *rt, int create)
-{
-	struct inet_peer_base *base;
-	struct inet_peer *peer;
-
-	base = inetpeer_base_ptr(rt->_rt6i_peer);
-	if (!base)
-		return;
-
-	peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
-	if (peer) {
-		if (!rt6_set_peer(rt, peer))
-			inet_putpeer(peer);
-	}
-}
-
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 			   int how)
 {
@@ -358,12 +374,6 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
-static bool rt6_need_strict(const struct in6_addr *daddr)
-{
-	return ipv6_addr_type(daddr) &
-		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
-}
-
 /* Multipath route selection:
  *   Hash based function using packet header and flowlabel.
  * Adapted from fib_info_hashfn()
@@ -521,7 +531,7 @@ static void rt6_probe(struct rt6_info *rt)
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 
 		if (neigh && work)
-			neigh->updated = jiffies;
+			__neigh_set_probe_once(neigh);
 
 		if (neigh)
 			write_unlock(&neigh->lock);
@@ -577,11 +587,13 @@ static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
 #ifdef CONFIG_IPV6_ROUTER_PREF
 		else if (!(neigh->nud_state & NUD_FAILED))
 			ret = RT6_NUD_SUCCEED;
+		else
+			ret = RT6_NUD_FAIL_PROBE;
 #endif
 		read_unlock(&neigh->lock);
 	} else {
 		ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ?
-		      RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT;
+		      RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR;
 	}
 	rcu_read_unlock_bh();
 
@@ -618,16 +630,17 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
 		goto out;
 
 	m = rt6_score_route(rt, oif, strict);
-	if (m == RT6_NUD_FAIL_SOFT) {
+	if (m == RT6_NUD_FAIL_DO_RR) {
 		match_do_rr = true;
 		m = 0; /* lowest valid score */
-	} else if (m < 0) {
+	} else if (m == RT6_NUD_FAIL_HARD) {
 		goto out;
 	}
 
 	if (strict & RT6_LOOKUP_F_REACHABLE)
 		rt6_probe(rt);
 
+	/* note that m can be RT6_NUD_FAIL_PROBE at this point */
 	if (m > *mpri) {
 		*do_rr = match_do_rr;
 		*mpri = m;
@@ -839,14 +852,15 @@ EXPORT_SYMBOL(rt6_lookup);
    be destroyed.
  */
 
-static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
+static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
+			struct nlattr *mx, int mx_len)
 {
 	int err;
 	struct fib6_table *table;
 
 	table = rt->rt6i_table;
 	write_lock_bh(&table->tb6_lock);
-	err = fib6_add(&table->tb6_root, rt, info);
+	err = fib6_add(&table->tb6_root, rt, info, mx, mx_len);
 	write_unlock_bh(&table->tb6_lock);
 
 	return err;
@@ -857,7 +871,7 @@ int ip6_ins_rt(struct rt6_info *rt)
 	struct nl_info info = {
 		.nl_net = dev_net(rt->dst.dev),
 	};
-	return __ip6_ins_rt(rt, &info);
+	return __ip6_ins_rt(rt, &info, NULL, 0);
 }
 
 static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
@@ -1044,7 +1058,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 
 		new->__use = 1;
 		new->input = dst_discard;
-		new->output = dst_discard;
+		new->output = dst_discard_sk;
 
 		if (dst_metrics_read_only(&ort->dst))
 			new->_metrics = ort->dst._metrics;
@@ -1162,7 +1176,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = oif;
-	fl6.flowi6_mark = mark;
+	fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark);
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
@@ -1259,6 +1273,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
 	struct flowi6 fl6;
 
 	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_iif = LOOPBACK_IFINDEX;
 	fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = mark;
 	fl6.daddr = iph->daddr;
@@ -1280,6 +1295,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
 	struct flowi6 fl6;
 
 	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_iif = LOOPBACK_IFINDEX;
 	fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = mark;
 	fl6.daddr = msg->dest;
@@ -1324,7 +1340,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
 
 	if (mtu)
-		return mtu;
+		goto out;
 
 	mtu = IPV6_MIN_MTU;
 
@@ -1334,7 +1350,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 		mtu = idev->cnf.mtu6;
 	rcu_read_unlock();
 
-	return mtu;
+out:
+	return min_t(unsigned int, mtu, IP6_MAX_MTU);
 }
 
 static struct dst_entry *icmp6_dst_gc_list;
@@ -1438,7 +1455,7 @@ static int ip6_dst_gc(struct dst_ops *ops)
 		goto out;
 
 	net->ipv6.ip6_rt_gc_expire++;
-	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size);
+	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true);
 	entries = dst_entries_get_slow(ops);
 	if (entries < ops->gc_thresh)
 		net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
@@ -1495,7 +1512,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	if (!table)
 		goto out;
 
-	rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
+	rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
 
 	if (!rt) {
 		err = -ENOMEM;
@@ -1525,17 +1542,11 @@ int ip6_route_add(struct fib6_config *cfg)
 
 	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)
-	       rt->dst.flags |= DST_HOST;
-
-	if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) {
-		u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
-		if (!metrics) {
-			err = -ENOMEM;
-			goto out;
-		}
-		dst_init_metrics(&rt->dst, metrics, 0);
+	if (rt->rt6i_dst.plen == 128) {
+		rt->dst.flags |= DST_HOST;
+		dst_metrics_set_force_overwrite(&rt->dst);
 	}
+
 #ifdef CONFIG_IPV6_SUBTREES
 	ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
 	rt->rt6i_src.plen = cfg->fc_src_len;
@@ -1568,7 +1579,7 @@ int ip6_route_add(struct fib6_config *cfg)
 		switch (cfg->fc_type) {
 		case RTN_BLACKHOLE:
 			rt->dst.error = -EINVAL;
-			rt->dst.output = dst_discard;
+			rt->dst.output = dst_discard_sk;
 			rt->dst.input = dst_discard;
 			break;
 		case RTN_PROHIBIT:
@@ -1654,31 +1665,13 @@ int ip6_route_add(struct fib6_config *cfg)
 	rt->rt6i_flags = cfg->fc_flags;
 
 install_route:
-	if (cfg->fc_mx) {
-		struct nlattr *nla;
-		int remaining;
-
-		nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
-			int type = nla_type(nla);
-
-			if (type) {
-				if (type > RTAX_MAX) {
-					err = -EINVAL;
-					goto out;
-				}
-
-				dst_metric_set(&rt->dst, type, nla_get_u32(nla));
-			}
-		}
-	}
-
 	rt->dst.dev = dev;
 	rt->rt6i_idev = idev;
 	rt->rt6i_table = table;
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
-	return __ip6_ins_rt(rt, &cfg->fc_nlinfo);
+	return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len);
 
 out:
 	if (dev)
@@ -1905,9 +1898,7 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 		else
 			rt->rt6i_gateway = *dest;
 		rt->rt6i_flags = ort->rt6i_flags;
-		if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
-		    (RTF_DEFAULT | RTF_ADDRCONF))
-			rt6_set_from(rt, ort);
+		rt6_set_from(rt, ort);
 		rt->rt6i_metric = 0;
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -2140,7 +2131,7 @@ static int ip6_pkt_discard(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
 }
 
-static int ip6_pkt_discard_out(struct sk_buff *skb)
+static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb)
 {
 	skb->dev = skb_dst(skb)->dev;
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
@@ -2151,7 +2142,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
 }
 
-static int ip6_pkt_prohibit_out(struct sk_buff *skb)
+static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb)
 {
 	skb->dev = skb_dst(skb)->dev;
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
@@ -2166,12 +2157,10 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    bool anycast)
 {
 	struct net *net = dev_net(idev->dev);
-	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL);
-
-	if (!rt) {
-		net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n");
+	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
+					    DST_NOCOUNT, NULL);
+	if (!rt)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	in6_dev_hold(idev);
 
@@ -2242,7 +2231,28 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 		.net = net,
 		.addr = &ifp->addr,
 	};
-	fib6_clean_all(net, fib6_remove_prefsrc, 0, &adni);
+	fib6_clean_all(net, fib6_remove_prefsrc, &adni);
+}
+
+#define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
+#define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
+
+/* Remove routers and update dst entries when gateway turn into host. */
+static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
+{
+	struct in6_addr *gateway = (struct in6_addr *)arg;
+
+	if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) ||
+	     ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) &&
+	     ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+		return -1;
+	}
+	return 0;
+}
+
+void rt6_clean_tohost(struct net *net, struct in6_addr *gateway)
+{
+	fib6_clean_all(net, fib6_clean_tohost, gateway);
 }
 
 struct arg_dev_net {
@@ -2269,7 +2279,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
 		.net = net,
 	};
 
-	fib6_clean_all(net, fib6_ifdown, 0, &adn);
+	fib6_clean_all(net, fib6_ifdown, &adn);
 	icmp6_clean_all(fib6_ifdown, &adn);
 }
 
@@ -2324,7 +2334,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
 		.mtu = mtu,
 	};
 
-	fib6_clean_all(dev_net(dev), rt6_mtu_change_route, 0, &arg);
+	fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg);
 }
 
 static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
@@ -2720,6 +2730,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
 	if (tb[RTA_OIF])
 		oif = nla_get_u32(tb[RTA_OIF]);
 
+	if (tb[RTA_MARK])
+		fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+
 	if (iif) {
 		struct net_device *dev;
 		int flags = 0;