ipv6: prepare rt6_clean_tohost() for exception table

If we move all cached dst into the exception table under the main route,
current rt6_clean_tohost() will no longer be able to access them.
This commit makes fib6_clean_tohost() to also go through all cached
routes in exception table and removes cached gateway routes to the
passed in gateway.
This is a preparation in order to move all cached routes into the
exception table.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d9805a857809cb53d13823731efd1f1d5e61716d..e8e901589564960206b46f100e2d4720c67e8b53 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1491,6 +1491,43 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
        }
 }
 
+#define RTF_CACHE_GATEWAY      (RTF_GATEWAY | RTF_CACHE)
+
+static void rt6_exceptions_clean_tohost(struct rt6_info *rt,
+                                       struct in6_addr *gateway)
+{
+       struct rt6_exception_bucket *bucket;
+       struct rt6_exception *rt6_ex;
+       struct hlist_node *tmp;
+       int i;
+
+       if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+               return;
+
+       spin_lock_bh(&rt6_exception_lock);
+       bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+                                    lockdep_is_held(&rt6_exception_lock));
+
+       if (bucket) {
+               for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+                       hlist_for_each_entry_safe(rt6_ex, tmp,
+                                                 &bucket->chain, hlist) {
+                               struct rt6_info *entry = rt6_ex->rt6i;
+
+                               if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) ==
+                                   RTF_CACHE_GATEWAY &&
+                                   ipv6_addr_equal(gateway,
+                                                   &entry->rt6i_gateway)) {
+                                       rt6_remove_exception(bucket, rt6_ex);
+                               }
+                       }
+                       bucket++;
+               }
+       }
+
+       spin_unlock_bh(&rt6_exception_lock);
+}
+
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
                               int oif, struct flowi6 *fl6, int flags)
 {
@@ -3240,18 +3277,27 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 }
 
 #define RTF_RA_ROUTER          (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
-#define RTF_CACHE_GATEWAY      (RTF_GATEWAY | RTF_CACHE)
 
 /* Remove routers and update dst entries when gateway turn into host. */
 static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
 {
        struct in6_addr *gateway = (struct in6_addr *)arg;
 
+       /* RTF_CACHE_GATEWAY case will be removed once the exception
+        * table is hooked up to store all cached routes.
+        */
        if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) ||
             ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) &&
             ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
                return -1;
        }
+
+       /* Further clean up cached routes in exception table.
+        * This is needed because cached route may have a different
+        * gateway than its 'parent' in the case of an ip redirect.
+        */
+       rt6_exceptions_clean_tohost(rt, gateway);
+
        return 0;
 }