net: fix NULL dereferences in check_peer_redir()

Gergely Kalman reported crashes in check_peer_redir().

It appears commit f39925dbde778 (ipv4: Cache learned redirect
information in inetpeer.) added a race, leading to possible NULL ptr
dereference.

Since we can now change dst neighbour, we should make sure a reader can
safely use a neighbour.

Add RCU protection to dst neighbour, and make sure check_peer_redir()
can be called safely by different cpus in parallel.

As neighbours are already freed after one RCU grace period, this patch
should not add typical RCU penalty (cache cold effects)

Many thanks to Gergely for providing a pretty report pointing to the
bug.

Reported-by: Gergely Kalman <synapse@hippy.csoma.elte.hu>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 25 insertions, 10 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e8987da06667..9e69eb0ec6dd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -364,7 +364,7 @@ out:
 #ifdef CONFIG_IPV6_ROUTER_PREF
 static void rt6_probe(struct rt6_info *rt)
 {
-	struct neighbour *neigh = rt ? dst_get_neighbour(&rt->dst) : NULL;
+	struct neighbour *neigh;
 	/*
 	 * Okay, this does not seem to be appropriate
 	 * for now, however, we need to check if it
@@ -373,8 +373,10 @@ static void rt6_probe(struct rt6_info *rt)
 	 * Router Reachability Probe MUST be rate-limited
 	 * to no more than one per minute.
 	 */
+	rcu_read_lock();
+	neigh = rt ? dst_get_neighbour(&rt->dst) : NULL;
 	if (!neigh || (neigh->nud_state & NUD_VALID))
-		return;
+		goto out;
 	read_lock_bh(&neigh->lock);
 	if (!(neigh->nud_state & NUD_VALID) &&
 	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
@@ -387,8 +389,11 @@ static void rt6_probe(struct rt6_info *rt)
 		target = (struct in6_addr *)&neigh->primary_key;
 		addrconf_addr_solict_mult(target, &mcaddr);
 		ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL);
-	} else
+	} else {
 		read_unlock_bh(&neigh->lock);
+	}
+out:
+	rcu_read_unlock();
 }
 #else
 static inline void rt6_probe(struct rt6_info *rt)
@@ -412,8 +417,11 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif)
 
 static inline int rt6_check_neigh(struct rt6_info *rt)
 {
-	struct neighbour *neigh = dst_get_neighbour(&rt->dst);
+	struct neighbour *neigh;
 	int m;
+
+	rcu_read_lock();
+	neigh = dst_get_neighbour(&rt->dst);
 	if (rt->rt6i_flags & RTF_NONEXTHOP ||
 	    !(rt->rt6i_flags & RTF_GATEWAY))
 		m = 1;
@@ -430,6 +438,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt)
 		read_unlock_bh(&neigh->lock);
 	} else
 		m = 0;
+	rcu_read_unlock();
 	return m;
 }
 
@@ -769,7 +778,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
 		rt->rt6i_dst.plen = 128;
 		rt->rt6i_flags |= RTF_CACHE;
 		rt->dst.flags |= DST_HOST;
-		dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour(&ort->dst)));
+		dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_raw(&ort->dst)));
 	}
 	return rt;
 }
@@ -803,7 +812,7 @@ restart:
 	dst_hold(&rt->dst);
 	read_unlock_bh(&table->tb6_lock);
 
-	if (!dst_get_neighbour(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+	if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
 		nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
 	else if (!(rt->dst.flags & DST_HOST))
 		nrt = rt6_alloc_clone(rt, &fl6->daddr);
@@ -1587,7 +1596,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
 	dst_confirm(&rt->dst);
 
 	/* Duplicate redirect: silently ignore. */
-	if (neigh == dst_get_neighbour(&rt->dst))
+	if (neigh == dst_get_neighbour_raw(&rt->dst))
 		goto out;
 
 	nrt = ip6_rt_copy(rt, dest);
@@ -1682,7 +1691,7 @@ again:
 	   1. It is connected route. Action: COW
 	   2. It is gatewayed route or NONEXTHOP route. Action: clone it.
 	 */
-	if (!dst_get_neighbour(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+	if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
 		nrt = rt6_alloc_cow(rt, daddr, saddr);
 	else
 		nrt = rt6_alloc_clone(rt, daddr);
@@ -2326,6 +2335,7 @@ static int rt6_fill_node(struct net *net,
 	struct nlmsghdr *nlh;
 	long expires;
 	u32 table;
+	struct neighbour *n;
 
 	if (prefix) {	/* user wants prefix routes only */
 		if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
@@ -2414,8 +2424,11 @@ static int rt6_fill_node(struct net *net,
 	if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
 		goto nla_put_failure;
 
-	if (dst_get_neighbour(&rt->dst))
-		NLA_PUT(skb, RTA_GATEWAY, 16, &dst_get_neighbour(&rt->dst)->primary_key);
+	rcu_read_lock();
+	n = dst_get_neighbour(&rt->dst);
+	if (n)
+		NLA_PUT(skb, RTA_GATEWAY, 16, &n->primary_key);
+	rcu_read_unlock();
 
 	if (rt->dst.dev)
 		NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex);
@@ -2608,12 +2621,14 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
 #else
 	seq_puts(m, "00000000000000000000000000000000 00 ");
 #endif
+	rcu_read_lock();
 	n = dst_get_neighbour(&rt->dst);
 	if (n) {
 		seq_printf(m, "%pi6", n->primary_key);
 	} else {
 		seq_puts(m, "00000000000000000000000000000000");
 	}
+	rcu_read_unlock();
 	seq_printf(m, " %08x %08x %08x %08x %8s\n",
 		   rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
 		   rt->dst.__use, rt->rt6i_flags,