[PATCH v3] ipv6: Fix problem with expired dst cache

[Gao feng <gaofeng@cn.fujitsu.com>]

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.

In func rt6_check_expired check if rt6_info.dst.from is expired.

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

In func ip6_dst_destroy release the ort.

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

Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
 include/net/dst.h     |   11 ++++++++++-
 include/net/ip6_fib.h |   41 +++++++++++++++++++++++++++++++++++++++++
 net/ipv6/addrconf.c   |    9 +++------
 net/ipv6/ip6_fib.c    |    3 +--
 net/ipv6/route.c      |   49 +++++++++++++++++++++++++++++++------------------
 5 files changed, 86 insertions(+), 27 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 344c8dd..5147839 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -35,7 +35,16 @@ struct dst_entry {
 	struct net_device       *dev;
 	struct  dst_ops	        *ops;
 	unsigned long		_metrics;
-	unsigned long		expires;
+
+	union {
+		unsigned long		expires;
+		/*
+		 * from is used only for dst cache witch copy form
+		 * the dst generated by ipv6 RA.
+		 * from is set only when rt6_info has no RTF_EXPIRES flag.
+		 */
+		void			*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 b26bb81..86cf1ac 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -123,6 +123,47 @@ 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);
+
+	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);
+
+	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);
+
+	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)
+{
+	if (!(rt->rt6i_flags & RTF_EXPIRES) && rt->dst.from) {
+		if (from == rt->dst.from)
+			return;
+		else
+			dst_release((struct dst_entry *) &rt->dst.from);
+	}
+
+	rt->rt6i_flags &= ~RTF_EXPIRES;
+	rt->dst.from = (void *) from;
+	dst_hold(&from->dst);
+}
+
 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 c02280a..b5cb3b1 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -799,8 +799,7 @@ 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);
@@ -1883,11 +1882,9 @@ 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 b82bcde..9a4f51e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -675,8 +675,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 					return -EEXIST;
 				iter->dst.expires = rt->dst.expires;
 				if (!(rt->rt6i_flags & RTF_EXPIRES)) {
-					iter->rt6i_flags &= ~RTF_EXPIRES;
-					iter->dst.expires = 0;
+					rt6_clean_expires(iter);
 				}
 				return -EEXIST;
 			}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8c2e3ab..302a773 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);
@@ -272,6 +272,10 @@ 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((struct dst_entry *)dst->from);
+
 	if (peer) {
 		rt->rt6i_peer = NULL;
 		inet_putpeer(peer);
@@ -316,8 +320,18 @@ 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)
@@ -608,10 +622,9 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 
 	if (rt) {
 		if (!addrconf_finite_timeout(lifetime)) {
-			rt->rt6i_flags &= ~RTF_EXPIRES;
+			rt6_clean_expires(rt);
 		} else {
-			rt->dst.expires = jiffies + HZ * lifetime;
-			rt->rt6i_flags |= RTF_EXPIRES;
+			rt6_set_expires(rt, jiffies + HZ * lifetime);
 		}
 		dst_release(&rt->dst);
 	}
@@ -717,7 +730,7 @@ 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)
 {
@@ -934,10 +947,10 @@ 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));
@@ -1000,8 +1013,7 @@ 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;
+			rt6_update_expires(rt, 0);
 		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
 			rt->rt6i_node->fn_sernum = -1;
 	}
@@ -1716,8 +1728,8 @@ 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;
 	}
 
@@ -1745,8 +1757,8 @@ 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);
 	}
@@ -1779,7 +1791,7 @@ 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);
@@ -1799,10 +1811,11 @@ 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;
+		rt6_set_from(rt, ort);
+
 		rt->rt6i_metric = 0;
 
 #ifdef CONFIG_IPV6_SUBTREES
-- 
1.7.5.4