1 files changed, 108 insertions, 58 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ad0aa6b0b86a..6c389300f4e9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -65,6 +65,12 @@
 #include <linux/sysctl.h>
 #endif
 
+enum rt6_nud_state {
+	RT6_NUD_FAIL_HARD = -2,
+	RT6_NUD_FAIL_SOFT = -1,
+	RT6_NUD_SUCCEED = 1
+};
+
 static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 				    const struct in6_addr *dest);
 static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
@@ -78,6 +84,8 @@ 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_prohibit(struct sk_buff *skb);
+static int		ip6_pkt_prohibit_out(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);
@@ -227,9 +235,6 @@ static const struct rt6_info ip6_null_entry_template = {
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 
-static int ip6_pkt_prohibit(struct sk_buff *skb);
-static int ip6_pkt_prohibit_out(struct sk_buff *skb);
-
 static const struct rt6_info ip6_prohibit_entry_template = {
 	.dst = {
 		.__refcnt	= ATOMIC_INIT(1),
@@ -467,6 +472,24 @@ out:
 }
 
 #ifdef CONFIG_IPV6_ROUTER_PREF
+struct __rt6_probe_work {
+	struct work_struct work;
+	struct in6_addr target;
+	struct net_device *dev;
+};
+
+static void rt6_probe_deferred(struct work_struct *w)
+{
+	struct in6_addr mcaddr;
+	struct __rt6_probe_work *work =
+		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);
+	dev_put(work->dev);
+	kfree(w);
+}
+
 static void rt6_probe(struct rt6_info *rt)
 {
 	struct neighbour *neigh;
@@ -490,17 +513,23 @@ static void rt6_probe(struct rt6_info *rt)
 
 	if (!neigh ||
 	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
-		struct in6_addr mcaddr;
-		struct in6_addr *target;
+		struct __rt6_probe_work *work;
+
+		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 
-		if (neigh) {
+		if (neigh && work)
 			neigh->updated = jiffies;
+
+		if (neigh)
 			write_unlock(&neigh->lock);
-		}
 
-		target = (struct in6_addr *)&rt->rt6i_gateway;
-		addrconf_addr_solict_mult(target, &mcaddr);
-		ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
+		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);
@@ -527,26 +556,29 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif)
 	return 0;
 }
 
-static inline bool rt6_check_neigh(struct rt6_info *rt)
+static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
 {
 	struct neighbour *neigh;
-	bool ret = false;
+	enum rt6_nud_state ret = RT6_NUD_FAIL_HARD;
 
 	if (rt->rt6i_flags & RTF_NONEXTHOP ||
 	    !(rt->rt6i_flags & RTF_GATEWAY))
-		return true;
+		return RT6_NUD_SUCCEED;
 
 	rcu_read_lock_bh();
 	neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
 	if (neigh) {
 		read_lock(&neigh->lock);
 		if (neigh->nud_state & NUD_VALID)
-			ret = true;
+			ret = RT6_NUD_SUCCEED;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 		else if (!(neigh->nud_state & NUD_FAILED))
-			ret = true;
+			ret = RT6_NUD_SUCCEED;
 #endif
 		read_unlock(&neigh->lock);
+	} else {
+		ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ?
+		      RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT;
 	}
 	rcu_read_unlock_bh();
 
@@ -560,43 +592,52 @@ static int rt6_score_route(struct rt6_info *rt, int oif,
 
 	m = rt6_check_dev(rt, oif);
 	if (!m && (strict & RT6_LOOKUP_F_IFACE))
-		return -1;
+		return RT6_NUD_FAIL_HARD;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
 #endif
-	if (!rt6_check_neigh(rt) && (strict & RT6_LOOKUP_F_REACHABLE))
-		return -1;
+	if (strict & RT6_LOOKUP_F_REACHABLE) {
+		int n = rt6_check_neigh(rt);
+		if (n < 0)
+			return n;
+	}
 	return m;
 }
 
 static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
-				   int *mpri, struct rt6_info *match)
+				   int *mpri, struct rt6_info *match,
+				   bool *do_rr)
 {
 	int m;
+	bool match_do_rr = false;
 
 	if (rt6_check_expired(rt))
 		goto out;
 
 	m = rt6_score_route(rt, oif, strict);
-	if (m < 0)
+	if (m == RT6_NUD_FAIL_SOFT && !IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) {
+		match_do_rr = true;
+		m = 0; /* lowest valid score */
+	} else if (m < 0) {
 		goto out;
+	}
+
+	if (strict & RT6_LOOKUP_F_REACHABLE)
+		rt6_probe(rt);
 
 	if (m > *mpri) {
-		if (strict & RT6_LOOKUP_F_REACHABLE)
-			rt6_probe(match);
+		*do_rr = match_do_rr;
 		*mpri = m;
 		match = rt;
-	} else if (strict & RT6_LOOKUP_F_REACHABLE) {
-		rt6_probe(rt);
 	}
-
 out:
 	return match;
 }
 
 static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 				     struct rt6_info *rr_head,
-				     u32 metric, int oif, int strict)
+				     u32 metric, int oif, int strict,
+				     bool *do_rr)
 {
 	struct rt6_info *rt, *match;
 	int mpri = -1;
@@ -604,10 +645,10 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 	match = NULL;
 	for (rt = rr_head; rt && rt->rt6i_metric == metric;
 	     rt = rt->dst.rt6_next)
-		match = find_match(rt, oif, strict, &mpri, match);
+		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 	for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
 	     rt = rt->dst.rt6_next)
-		match = find_match(rt, oif, strict, &mpri, match);
+		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 
 	return match;
 }
@@ -616,15 +657,16 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
 {
 	struct rt6_info *match, *rt0;
 	struct net *net;
+	bool do_rr = false;
 
 	rt0 = fn->rr_ptr;
 	if (!rt0)
 		fn->rr_ptr = rt0 = fn->leaf;
 
-	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);
+	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict,
+			     &do_rr);
 
-	if (!match &&
-	    (strict & RT6_LOOKUP_F_REACHABLE)) {
+	if (do_rr) {
 		struct rt6_info *next = rt0->dst.rt6_next;
 
 		/* no entries matched; do round-robin */
@@ -685,8 +727,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 		prefix = &prefix_buf;
 	}
 
-	rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr,
-				dev->ifindex);
+	if (rinfo->prefix_len == 0)
+		rt = rt6_get_dflt_router(gwaddr, dev);
+	else
+		rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
+					gwaddr, dev->ifindex);
 
 	if (rt && !lifetime) {
 		ip6_del_rt(rt);
@@ -829,7 +874,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
 			if (ort->rt6i_dst.plen != 128 &&
 			    ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
 				rt->rt6i_flags |= RTF_ANYCAST;
-			rt->rt6i_gateway = *daddr;
 		}
 
 		rt->rt6i_flags |= RTF_CACHE;
@@ -1042,10 +1086,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 	if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev)))
 		return NULL;
 
-	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
-		return dst;
+	if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+		return NULL;
 
-	return NULL;
+	if (rt6_check_expired(rt))
+		return NULL;
+
+	return dst;
 }
 
 static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
@@ -1074,10 +1121,13 @@ static void ip6_link_failure(struct sk_buff *skb)
 
 	rt = (struct rt6_info *) skb_dst(skb);
 	if (rt) {
-		if (rt->rt6i_flags & RTF_CACHE)
-			rt6_update_expires(rt, 0);
-		else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
+		if (rt->rt6i_flags & RTF_CACHE) {
+			dst_hold(&rt->dst);
+			if (ip6_del_rt(rt))
+				dst_free(&rt->dst);
+		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) {
 			rt->rt6i_node->fn_sernum = -1;
+		}
 	}
 }
 
@@ -1223,6 +1273,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	rt->dst.flags |= DST_HOST;
 	rt->dst.output  = ip6_output;
 	atomic_set(&rt->dst.__refcnt, 1);
+	rt->rt6i_gateway  = fl6->daddr;
 	rt->rt6i_dst.addr = fl6->daddr;
 	rt->rt6i_dst.plen = 128;
 	rt->rt6i_idev     = idev;
@@ -1446,21 +1497,24 @@ int ip6_route_add(struct fib6_config *cfg)
 				goto out;
 			}
 		}
-		rt->dst.output = ip6_pkt_discard_out;
-		rt->dst.input = ip6_pkt_discard;
 		rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
 		switch (cfg->fc_type) {
 		case RTN_BLACKHOLE:
 			rt->dst.error = -EINVAL;
+			rt->dst.output = dst_discard;
+			rt->dst.input = dst_discard;
 			break;
 		case RTN_PROHIBIT:
 			rt->dst.error = -EACCES;
+			rt->dst.output = ip6_pkt_prohibit_out;
+			rt->dst.input = ip6_pkt_prohibit;
 			break;
 		case RTN_THROW:
-			rt->dst.error = -EAGAIN;
-			break;
 		default:
-			rt->dst.error = -ENETUNREACH;
+			rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN
+					: -ENETUNREACH;
+			rt->dst.output = ip6_pkt_discard_out;
+			rt->dst.input = ip6_pkt_discard;
 			break;
 		}
 		goto install_route;
@@ -1779,11 +1833,12 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 			in6_dev_hold(rt->rt6i_idev);
 		rt->dst.lastuse = jiffies;
 
-		rt->rt6i_gateway = ort->rt6i_gateway;
+		if (ort->rt6i_flags & RTF_GATEWAY)
+			rt->rt6i_gateway = ort->rt6i_gateway;
+		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
@@ -2022,8 +2077,6 @@ static int ip6_pkt_discard_out(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
 }
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-
 static int ip6_pkt_prohibit(struct sk_buff *skb)
 {
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
@@ -2035,8 +2088,6 @@ static int ip6_pkt_prohibit_out(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
 }
 
-#endif
-
 /*
  *	Allocate a dst for local (unicast / anycast) address.
  */
@@ -2046,12 +2097,10 @@ 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);
 
@@ -2066,6 +2115,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	else
 		rt->rt6i_flags |= RTF_LOCAL;
 
+	rt->rt6i_gateway  = *addr;
 	rt->rt6i_dst.addr = *addr;
 	rt->rt6i_dst.plen = 128;
 	rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);