ipv6: add rcu grace period before freeing fib6_node

commit c5cff8561d2d0006e972bd114afd51f082fee77c upstream.

We currently keep rt->rt6i_node pointing to the fib6_node for the route.
And some functions make use of this pointer to dereference the fib6_node
from rt structure, e.g. rt6_check(). However, as there is neither
refcount nor rcu taken when dereferencing rt->rt6i_node, it could
potentially cause crashes as rt->rt6i_node could be set to NULL by other
CPUs when doing a route deletion.
This patch introduces an rcu grace period before freeing fib6_node and
makes sure the functions that dereference it takes rcu_read_lock().

Note: there is no "Fixes" tag because this bug was there in a very
early stage.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index ac5cb6a45cefc7cd0343f9c8c0a84a52efd0dfd7..039e0265a48aef2e69ef0c4acb2491f6b78f6fcb 100644 (file)
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -63,6 +63,7 @@ struct fib6_node {
        __u16                   fn_flags;
        __u32                   fn_sernum;
        struct rt6_info         *rr_ptr;
+       struct rcu_head         rcu;
 };
 
 #ifndef CONFIG_IPV6_SUBTREES
@@ -126,9 +127,36 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
        return ((struct rt6_info *)dst)->rt6i_idev;
 }
 
+/* Function to safely get fn->sernum for passed in rt
+ * and store result in passed in cookie.
+ * Return true if we can get cookie safely
+ * Return false if not
+ */
+static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
+                                      u32 *cookie)
+{
+       struct fib6_node *fn;
+       bool status = false;
+
+       rcu_read_lock();
+       fn = rcu_dereference(rt->rt6i_node);
+
+       if (fn) {
+               *cookie = fn->fn_sernum;
+               status = true;
+       }
+
+       rcu_read_unlock();
+       return status;
+}
+
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
-       return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+       u32 cookie = 0;
+
+       rt6_get_cookie_safe(rt, &cookie);
+
+       return cookie;
 }
 
 struct fib6_walker_t {

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 785e62d90b39d85a9eda01d8e70d8bf01a6c75f5..96d4d1c9a619bc86506c9a5e430e896d2f9728a0 100644 (file)
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -153,11 +153,23 @@ static __inline__ struct fib6_node * node_alloc(void)
        return fn;
 }
 
-static __inline__ void node_free(struct fib6_node * fn)
+static void node_free_immediate(struct fib6_node *fn)
 {
        kmem_cache_free(fib6_node_kmem, fn);
 }
 
+static void node_free_rcu(struct rcu_head *head)
+{
+       struct fib6_node *fn = container_of(head, struct fib6_node, rcu);
+
+       kmem_cache_free(fib6_node_kmem, fn);
+}
+
+static void node_free(struct fib6_node *fn)
+{
+       call_rcu(&fn->rcu, node_free_rcu);
+}
+
 static __inline__ void rt6_release(struct rt6_info *rt)
 {
        if (atomic_dec_and_test(&rt->rt6i_ref))
@@ -529,9 +541,9 @@ insert_above:
 
                if (in == NULL || ln == NULL) {
                        if (in)
-                               node_free(in);
+                               node_free_immediate(in);
                        if (ln)
-                               node_free(ln);
+                               node_free_immediate(ln);
                        return NULL;
                }
 
@@ -743,7 +755,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
                                   root, and then (in st_failure) stale node
                                   in main tree.
                                 */
-                               node_free(sfn);
+                               node_free_immediate(sfn);
                                goto st_failure;
                        }
 

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cda5cfe92f6bb8b617d08ee2250ded2361910045..b1eb89c74ff637aeab19d1ad06fd4f2f5aef42f3 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -964,10 +964,11 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 {
        struct rt6_info *rt;
+       u32 rt_cookie;
 
        rt = (struct rt6_info *) dst;
 
-       if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
+       if (rt6_get_cookie_safe(rt, &rt_cookie) && rt_cookie == cookie) {
                if (rt->rt6i_peer_genid != rt6_peer_genid()) {
                        if (!rt->rt6i_peer)
                                rt6_bind_peer(rt, 0);
@@ -1007,8 +1008,15 @@ static void ip6_link_failure(struct sk_buff *skb)
                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))
-                       rt->rt6i_node->fn_sernum = -1;
+               } else {
+                       struct fib6_node *fn;
+
+                       rcu_read_lock();
+                       fn = rcu_dereference(rt->rt6i_node);
+                       if (fn && (rt->rt6i_flags & RTF_DEFAULT))
+                               fn->fn_sernum = -1;
+                       rcu_read_unlock();
+               }
        }
 }