1 files changed, 52 insertions, 21 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d62b05d33384..d9b40248b97f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -146,7 +146,6 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
 static void		 ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
 static int rt_garbage_collect(struct dst_ops *ops);
-static void rt_emergency_hash_rebuild(struct net *net);
 
 
 static struct dst_ops ipv4_dst_ops = {
@@ -287,12 +286,12 @@ static struct rtable *rt_cache_get_first(struct seq_file *seq)
 		if (!rt_hash_table[st->bucket].chain)
 			continue;
 		rcu_read_lock_bh();
-		r = rcu_dereference(rt_hash_table[st->bucket].chain);
+		r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
 		while (r) {
 			if (dev_net(r->u.dst.dev) == seq_file_net(seq) &&
 			    r->rt_genid == st->genid)
 				return r;
-			r = rcu_dereference(r->u.dst.rt_next);
+			r = rcu_dereference_bh(r->u.dst.rt_next);
 		}
 		rcu_read_unlock_bh();
 	}
@@ -314,7 +313,7 @@ static struct rtable *__rt_cache_get_next(struct seq_file *seq,
 		rcu_read_lock_bh();
 		r = rt_hash_table[st->bucket].chain;
 	}
-	return rcu_dereference(r);
+	return rcu_dereference_bh(r);
 }
 
 static struct rtable *rt_cache_get_next(struct seq_file *seq,
@@ -780,11 +779,30 @@ static void rt_do_flush(int process_context)
 #define FRACT_BITS 3
 #define ONE (1UL << FRACT_BITS)
 
+/*
+ * Given a hash chain and an item in this hash chain,
+ * find if a previous entry has the same hash_inputs
+ * (but differs on tos, mark or oif)
+ * Returns 0 if an alias is found.
+ * Returns ONE if rth has no alias before itself.
+ */
+static int has_noalias(const struct rtable *head, const struct rtable *rth)
+{
+	const struct rtable *aux = head;
+
+	while (aux != rth) {
+		if (compare_hash_inputs(&aux->fl, &rth->fl))
+			return 0;
+		aux = aux->u.dst.rt_next;
+	}
+	return ONE;
+}
+
 static void rt_check_expire(void)
 {
 	static unsigned int rover;
 	unsigned int i = rover, goal;
-	struct rtable *rth, *aux, **rthp;
+	struct rtable *rth, **rthp;
 	unsigned long samples = 0;
 	unsigned long sum = 0, sum2 = 0;
 	unsigned long delta;
@@ -835,15 +853,7 @@ nofree:
 					 * attributes don't unfairly skew
 					 * the length computation
 					 */
-					for (aux = rt_hash_table[i].chain;;) {
-						if (aux == rth) {
-							length += ONE;
-							break;
-						}
-						if (compare_hash_inputs(&aux->fl, &rth->fl))
-							break;
-						aux = aux->u.dst.rt_next;
-					}
+					length += has_noalias(rt_hash_table[i].chain, rth);
 					continue;
 				}
 			} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
@@ -1073,6 +1083,21 @@ work_done:
 out:	return 0;
 }
 
+/*
+ * Returns number of entries in a hash chain that have different hash_inputs
+ */
+static int slow_chain_length(const struct rtable *head)
+{
+	int length = 0;
+	const struct rtable *rth = head;
+
+	while (rth) {
+		length += has_noalias(head, rth);
+		rth = rth->u.dst.rt_next;
+	}
+	return length >> FRACT_BITS;
+}
+
 static int rt_intern_hash(unsigned hash, struct rtable *rt,
 			  struct rtable **rp, struct sk_buff *skb)
 {
@@ -1185,7 +1210,8 @@ restart:
 			rt_free(cand);
 		}
 	} else {
-		if (chain_length > rt_chain_length_max) {
+		if (chain_length > rt_chain_length_max &&
+		    slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {
 			struct net *net = dev_net(rt->u.dst.dev);
 			int num = ++net->ipv4.current_rt_cache_rebuild_count;
 			if (!rt_caching(dev_net(rt->u.dst.dev))) {
@@ -1990,8 +2016,13 @@ static int __mkroute_input(struct sk_buff *skb,
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
 		 * invalid for proxy arp. DNAT routes are always valid.
+		 *
+		 * Proxy arp feature have been extended to allow, ARP
+		 * replies back to the same interface, to support
+		 * Private VLAN switch technologies. See arp.c.
 		 */
-		if (out_dev == in_dev) {
+		if (out_dev == in_dev &&
+		    IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) {
 			err = -EINVAL;
 			goto cleanup;
 		}
@@ -2689,8 +2720,8 @@ int __ip_route_output_key(struct net *net, struct rtable **rp,
 	hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net));
 
 	rcu_read_lock_bh();
-	for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
-		rth = rcu_dereference(rth->u.dst.rt_next)) {
+	for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
+		rth = rcu_dereference_bh(rth->u.dst.rt_next)) {
 		if (rth->fl.fl4_dst == flp->fl4_dst &&
 		    rth->fl.fl4_src == flp->fl4_src &&
 		    rth->fl.iif == 0 &&
@@ -3008,8 +3039,8 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 		if (!rt_hash_table[h].chain)
 			continue;
 		rcu_read_lock_bh();
-		for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
-		     rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
+		for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
+		     rt = rcu_dereference_bh(rt->u.dst.rt_next), idx++) {
 			if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx)
 				continue;
 			if (rt_is_expired(rt))
@@ -3329,7 +3360,7 @@ static __net_initdata struct pernet_operations rt_secret_timer_ops = {
 
 
 #ifdef CONFIG_NET_CLS_ROUTE
-struct ip_rt_acct *ip_rt_acct __read_mostly;
+struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
 #endif /* CONFIG_NET_CLS_ROUTE */
 
 static __initdata unsigned long rhash_entries;