ipv6: fix problem with expired dst cache

If the ipv6 dst cache which copy from the dst generated by ICMPV6 RA packet.
this dst cache will not check expire because it has no RTF_EXPIRES flag.
So this dst cache will always be used until the dst gc run.

Change the struct dst_entry,add a union contains new pointer from and expires.
When rt6_info.rt6i_flags has no RTF_EXPIRES flag,the dst.expires has no use.
we can use this field to point to where the dst cache copy from.
The dst.from is only used in IPV6.

rt6_check_expired check if rt6_info.dst.from is expired.

ip6_rt_copy only set dst.from when the ort has flag RTF_ADDRCONF
and RTF_DEFAULT.then hold the ort.

ip6_dst_destroy release the ort.

Add some functions to operate the RTF_EXPIRES flag and expires(from) together.
and change the code to use these new adding functions.

Changes from v5:
modify ip6_route_add and ndisc_router_discovery to use new adding functions.

Only set dst.from when the ort has flag RTF_ADDRCONF
and RTF_DEFAULT.then hold the ort.

Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 99 insertions, 41 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index 59c5d18cc385..ff4da42fcfc6 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -36,7 +36,11 @@ struct dst_entry {
 	struct net_device       *dev;
 	struct  dst_ops	        *ops;
 	unsigned long		_metrics;
-	unsigned long		expires;
+	union {
+		unsigned long           expires;
+		/* point to where the dst_entry copied from */
+		struct dst_entry        *from;
+	};
 	struct dst_entry	*path;
 	struct neighbour __rcu	*_neighbour;
 #ifdef CONFIG_XFRM
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index b26bb8101981..c64778fd5e13 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -123,6 +123,48 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
 	return ((struct rt6_info *)dst)->rt6i_idev;
 }
 
+static inline void rt6_clean_expires(struct rt6_info *rt)
+{
+	if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from)
+		dst_release(rt->dst.from);
+
+	rt->rt6i_flags &= ~RTF_EXPIRES;
+	rt->dst.expires = 0;
+}
+
+static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
+{
+	if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from)
+		dst_release(rt->dst.from);
+
+	rt->rt6i_flags |= RTF_EXPIRES;
+	rt->dst.expires = expires;
+}
+
+static inline void rt6_update_expires(struct rt6_info *rt, int timeout)
+{
+	if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from)
+		dst_release(rt->dst.from);
+
+	dst_set_expires(&rt->dst, timeout);
+	rt->rt6i_flags |= RTF_EXPIRES;
+}
+
+static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
+{
+	struct dst_entry *new = (struct dst_entry *) from;
+
+	if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from) {
+		if (new == rt->dst.from)
+			return;
+		dst_release(rt->dst.from);
+	}
+
+	rt->rt6i_flags &= ~RTF_EXPIRES;
+	rt->dst.from = new;
+	dst_hold(new);
+}
+
 struct fib6_walker_t {
 	struct list_head lh;
 	struct fib6_node *root, *node;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6a3bb6077e19..7d5cb975cc6f 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -803,8 +803,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 				ip6_del_rt(rt);
 				rt = NULL;
 			} else if (!(rt->rt6i_flags & RTF_EXPIRES)) {
-				rt->dst.expires = expires;
-				rt->rt6i_flags |= RTF_EXPIRES;
+				rt6_set_expires(rt, expires);
 			}
 		}
 		dst_release(&rt->dst);
@@ -1887,11 +1886,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 				rt = NULL;
 			} else if (addrconf_finite_timeout(rt_expires)) {
 				/* not infinity */
-				rt->dst.expires = jiffies + rt_expires;
-				rt->rt6i_flags |= RTF_EXPIRES;
+				rt6_set_expires(rt, jiffies + rt_expires);
 			} else {
-				rt->rt6i_flags &= ~RTF_EXPIRES;
-				rt->dst.expires = 0;
+				rt6_clean_expires(rt);
 			}
 		} else if (valid_lft) {
 			clock_t expires = 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 5b27fbcae346..93717435013e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -673,11 +673,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 					    &rt->rt6i_gateway)) {
 				if (!(iter->rt6i_flags & RTF_EXPIRES))
 					return -EEXIST;
-				iter->dst.expires = rt->dst.expires;
-				if (!(rt->rt6i_flags & RTF_EXPIRES)) {
-					iter->rt6i_flags &= ~RTF_EXPIRES;
-					iter->dst.expires = 0;
-				}
+				if (!(rt->rt6i_flags & RTF_EXPIRES))
+					rt6_clean_expires(iter);
+				else
+					rt6_set_expires(iter, rt->dst.expires);
 				return -EEXIST;
 			}
 		}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 3dcdb81ec3e8..176b469322ac 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1264,8 +1264,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	}
 
 	if (rt)
-		rt->dst.expires = jiffies + (HZ * lifetime);
-
+		rt6_set_expires(rt, jiffies + (HZ * lifetime));
 	if (ra_msg->icmph.icmp6_hop_limit) {
 		in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
 		if (rt)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3992e26a6039..bc4888d902b2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -62,7 +62,7 @@
 #include <linux/sysctl.h>
 #endif
 
-static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
+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);
 static unsigned int	 ip6_default_advmss(const struct dst_entry *dst);
@@ -285,6 +285,10 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		rt->rt6i_idev = NULL;
 		in6_dev_put(idev);
 	}
+
+	if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from)
+		dst_release(dst->from);
+
 	if (peer) {
 		rt->rt6i_peer = NULL;
 		inet_putpeer(peer);
@@ -329,8 +333,17 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 
 static __inline__ int rt6_check_expired(const struct rt6_info *rt)
 {
-	return (rt->rt6i_flags & RTF_EXPIRES) &&
-		time_after(jiffies, rt->dst.expires);
+	struct rt6_info *ort = NULL;
+
+	if (rt->rt6i_flags & RTF_EXPIRES) {
+		if (time_after(jiffies, rt->dst.expires))
+			return 1;
+	} else if (rt->dst.from) {
+		ort = (struct rt6_info *) rt->dst.from;
+		return (ort->rt6i_flags & RTF_EXPIRES) &&
+			time_after(jiffies, ort->dst.expires);
+	}
+	return 0;
 }
 
 static inline int rt6_need_strict(const struct in6_addr *daddr)
@@ -620,12 +633,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 				 (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
 
 	if (rt) {
-		if (!addrconf_finite_timeout(lifetime)) {
-			rt->rt6i_flags &= ~RTF_EXPIRES;
-		} else {
-			rt->dst.expires = jiffies + HZ * lifetime;
-			rt->rt6i_flags |= RTF_EXPIRES;
-		}
+		if (!addrconf_finite_timeout(lifetime))
+			rt6_clean_expires(rt);
+		else
+			rt6_set_expires(rt, jiffies + HZ * lifetime);
+
 		dst_release(&rt->dst);
 	}
 	return 0;
@@ -730,7 +742,7 @@ int ip6_ins_rt(struct rt6_info *rt)
 	return __ip6_ins_rt(rt, &info);
 }
 
-static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort,
+static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
 				      const struct in6_addr *daddr,
 				      const struct in6_addr *saddr)
 {
@@ -954,10 +966,10 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 		rt->rt6i_idev = ort->rt6i_idev;
 		if (rt->rt6i_idev)
 			in6_dev_hold(rt->rt6i_idev);
-		rt->dst.expires = 0;
 
 		rt->rt6i_gateway = ort->rt6i_gateway;
-		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
+		rt->rt6i_flags = ort->rt6i_flags;
+		rt6_clean_expires(rt);
 		rt->rt6i_metric = 0;
 
 		memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
@@ -1019,10 +1031,9 @@ static void ip6_link_failure(struct sk_buff *skb)
 
 	rt = (struct rt6_info *) skb_dst(skb);
 	if (rt) {
-		if (rt->rt6i_flags & RTF_CACHE) {
-			dst_set_expires(&rt->dst, 0);
-			rt->rt6i_flags |= RTF_EXPIRES;
-		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
+		if (rt->rt6i_flags & RTF_CACHE)
+			rt6_update_expires(rt, 0);
+		else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
 			rt->rt6i_node->fn_sernum = -1;
 	}
 }
@@ -1289,9 +1300,12 @@ int ip6_route_add(struct fib6_config *cfg)
 	}
 
 	rt->dst.obsolete = -1;
-	rt->dst.expires = (cfg->fc_flags & RTF_EXPIRES) ?
-				jiffies + clock_t_to_jiffies(cfg->fc_expires) :
-				0;
+
+	if (cfg->fc_flags & RTF_EXPIRES)
+		rt6_set_expires(rt, jiffies +
+				clock_t_to_jiffies(cfg->fc_expires));
+	else
+		rt6_clean_expires(rt);
 
 	if (cfg->fc_protocol == RTPROT_UNSPEC)
 		cfg->fc_protocol = RTPROT_BOOT;
@@ -1736,8 +1750,8 @@ again:
 			features |= RTAX_FEATURE_ALLFRAG;
 			dst_metric_set(&rt->dst, RTAX_FEATURES, features);
 		}
-		dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
-		rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
+		rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
+		rt->rt6i_flags |= RTF_MODIFIED;
 		goto out;
 	}
 
@@ -1765,9 +1779,8 @@ again:
 		 * which is 10 mins. After 10 mins the decreased pmtu is expired
 		 * and detecting PMTU increase will be automatically happened.
 		 */
-		dst_set_expires(&nrt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
-		nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;
-
+		rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires);
+		nrt->rt6i_flags |= RTF_DYNAMIC;
 		ip6_ins_rt(nrt);
 	}
 out:
@@ -1799,7 +1812,7 @@ void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *sad
  *	Misc support functions
  */
 
-static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
+static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 				    const struct in6_addr *dest)
 {
 	struct net *net = dev_net(ort->dst.dev);
@@ -1819,10 +1832,14 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
 		if (rt->rt6i_idev)
 			in6_dev_hold(rt->rt6i_idev);
 		rt->dst.lastuse = jiffies;
-		rt->dst.expires = 0;
 
 		rt->rt6i_gateway = ort->rt6i_gateway;
-		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
+		rt->rt6i_flags = ort->rt6i_flags;
+		if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
+		    (RTF_DEFAULT | RTF_ADDRCONF))
+			rt6_set_from(rt, ort);
+		else
+			rt6_clean_expires(rt);
 		rt->rt6i_metric = 0;
 
 #ifdef CONFIG_IPV6_SUBTREES