Merge branch 'master' into next

1 files changed, 69 insertions, 35 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b2ba5581d2ae..d413b57be9b3 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 = {
@@ -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))
@@ -922,10 +932,8 @@ static void rt_secret_rebuild_oneshot(struct net *net)
 {
 	del_timer_sync(&net->ipv4.rt_secret_timer);
 	rt_cache_invalidate(net);
-	if (ip_rt_secret_interval) {
-		net->ipv4.rt_secret_timer.expires += ip_rt_secret_interval;
-		add_timer(&net->ipv4.rt_secret_timer);
-	}
+	if (ip_rt_secret_interval)
+		mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
 }
 
 static void rt_emergency_hash_rebuild(struct net *net)
@@ -1073,8 +1081,23 @@ 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)
+			  struct rtable **rp, struct sk_buff *skb, int ifindex)
 {
 	struct rtable	*rth, **rthp;
 	unsigned long	now;
@@ -1185,14 +1208,20 @@ 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))) {
+			if (!rt_caching(net)) {
 				printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
 					rt->u.dst.dev->name, num);
 			}
-			rt_emergency_hash_rebuild(dev_net(rt->u.dst.dev));
+			rt_emergency_hash_rebuild(net);
+			spin_unlock_bh(rt_hash_lock_addr(hash));
+
+			hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
+					ifindex, rt_genid(net));
+			goto restart;
 		}
 	}
 
@@ -1417,7 +1446,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 					dev_hold(rt->u.dst.dev);
 				if (rt->idev)
 					in_dev_hold(rt->idev);
-				rt->u.dst.obsolete	= 0;
+				rt->u.dst.obsolete	= -1;
 				rt->u.dst.lastuse	= jiffies;
 				rt->u.dst.path		= &rt->u.dst;
 				rt->u.dst.neighbour	= NULL;
@@ -1453,7 +1482,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 							&netevent);
 
 				rt_del(hash, rth);
-				if (!rt_intern_hash(hash, rt, &rt, NULL))
+				if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif))
 					ip_rt_put(rt);
 				goto do_next;
 			}
@@ -1482,11 +1511,12 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 	struct dst_entry *ret = dst;
 
 	if (rt) {
-		if (dst->obsolete) {
+		if (dst->obsolete > 0) {
 			ip_rt_put(rt);
 			ret = NULL;
 		} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
-			   rt->u.dst.expires) {
+			   (rt->u.dst.expires &&
+			    time_after_eq(jiffies, rt->u.dst.expires))) {
 			unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
 						rt->fl.oif,
 						rt_genid(dev_net(dst->dev)));
@@ -1702,7 +1732,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 {
-	return NULL;
+	if (rt_is_expired((struct rtable *)dst))
+		return NULL;
+	return dst;
 }
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
@@ -1864,7 +1896,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (!rth)
 		goto e_nobufs;
 
-	rth->u.dst.output= ip_rt_bug;
+	rth->u.dst.output = ip_rt_bug;
+	rth->u.dst.obsolete = -1;
 
 	atomic_set(&rth->u.dst.__refcnt, 1);
 	rth->u.dst.flags= DST_HOST;
@@ -1903,7 +1936,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	in_dev_put(in_dev);
 	hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
-	return rt_intern_hash(hash, rth, NULL, skb);
+	return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
 
 e_nobufs:
 	in_dev_put(in_dev);
@@ -2030,6 +2063,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->fl.oif 	= 0;
 	rth->rt_spec_dst= spec_dst;
 
+	rth->u.dst.obsolete = -1;
 	rth->u.dst.input = ip_forward;
 	rth->u.dst.output = ip_output;
 	rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
@@ -2069,7 +2103,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
 	/* put it into the cache */
 	hash = rt_hash(daddr, saddr, fl->iif,
 		       rt_genid(dev_net(rth->u.dst.dev)));
-	return rt_intern_hash(hash, rth, NULL, skb);
+	return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
 }
 
 /*
@@ -2194,6 +2228,7 @@ local_input:
 		goto e_nobufs;
 
 	rth->u.dst.output= ip_rt_bug;
+	rth->u.dst.obsolete = -1;
 	rth->rt_genid = rt_genid(net);
 
 	atomic_set(&rth->u.dst.__refcnt, 1);
@@ -2225,7 +2260,7 @@ local_input:
 	}
 	rth->rt_type	= res.type;
 	hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
-	err = rt_intern_hash(hash, rth, NULL, skb);
+	err = rt_intern_hash(hash, rth, NULL, skb, fl.iif);
 	goto done;
 
 no_route:
@@ -2420,6 +2455,7 @@ static int __mkroute_output(struct rtable **result,
 	rth->rt_spec_dst= fl->fl4_src;
 
 	rth->u.dst.output=ip_output;
+	rth->u.dst.obsolete = -1;
 	rth->rt_genid = rt_genid(dev_net(dev_out));
 
 	RT_CACHE_STAT_INC(out_slow_tot);
@@ -2471,7 +2507,7 @@ static int ip_mkroute_output(struct rtable **rp,
 	if (err == 0) {
 		hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
 			       rt_genid(dev_net(dev_out)));
-		err = rt_intern_hash(hash, rth, rp, NULL);
+		err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif);
 	}
 
 	return err;
@@ -3077,22 +3113,20 @@ static void rt_secret_reschedule(int old)
 	rtnl_lock();
 	for_each_net(net) {
 		int deleted = del_timer_sync(&net->ipv4.rt_secret_timer);
+		long time;
 
 		if (!new)
 			continue;
 
 		if (deleted) {
-			long time = net->ipv4.rt_secret_timer.expires - jiffies;
+			time = net->ipv4.rt_secret_timer.expires - jiffies;
 
 			if (time <= 0 || (time += diff) <= 0)
 				time = 0;
-
-			net->ipv4.rt_secret_timer.expires = time;
 		} else
-			net->ipv4.rt_secret_timer.expires = new;
+			time = new;
 
-		net->ipv4.rt_secret_timer.expires += jiffies;
-		add_timer(&net->ipv4.rt_secret_timer);
+		mod_timer(&net->ipv4.rt_secret_timer, jiffies + time);
 	}
 	rtnl_unlock();
 }