pkt_sched: gen_estimator: add a new lock

gen_kill_estimator() / gen_new_estimator() is not always called with
RTNL held.

net/netfilter/xt_RATEEST.c is one user of these API that do not hold
RTNL, so random corruptions can occur between "tc" and "iptables".

Add a new fine grained lock instead of trying to use RTNL in netfilter.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index cf8e70392fe0938acb4b8b88fa8bc74dbeaed584..785e5276a300e6f14c634e785eb1be8e0633c18e 100644 (file)
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -107,6 +107,7 @@ static DEFINE_RWLOCK(est_lock);
 
 /* Protects against soft lockup during large deletion */
 static struct rb_root est_root = RB_ROOT;
+static DEFINE_SPINLOCK(est_tree_lock);
 
 static void est_timer(unsigned long arg)
 {
@@ -201,7 +202,6 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats
  *
  * Returns 0 on success or a negative error code.
  *
- * NOTE: Called under rtnl_mutex
  */
 int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
                      struct gnet_stats_rate_est *rate_est,
@@ -232,6 +232,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
        est->last_packets = bstats->packets;
        est->avpps = rate_est->pps<<10;
 
+       spin_lock(&est_tree_lock);
        if (!elist[idx].timer.function) {
                INIT_LIST_HEAD(&elist[idx].list);
                setup_timer(&elist[idx].timer, est_timer, idx);
@@ -242,6 +243,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 
        list_add_rcu(&est->list, &elist[idx].list);
        gen_add_node(est);
+       spin_unlock(&est_tree_lock);
 
        return 0;
 }
@@ -261,13 +263,13 @@ static void __gen_kill_estimator(struct rcu_head *head)
  *
  * Removes the rate estimator specified by &bstats and &rate_est.
  *
- * NOTE: Called under rtnl_mutex
  */
 void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
                        struct gnet_stats_rate_est *rate_est)
 {
        struct gen_estimator *e;
 
+       spin_lock(&est_tree_lock);
        while ((e = gen_find_node(bstats, rate_est))) {
                rb_erase(&e->node, &est_root);
 
@@ -278,6 +280,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
                list_del_rcu(&e->list);
                call_rcu(&e->e_rcu, __gen_kill_estimator);
        }
+       spin_unlock(&est_tree_lock);
 }
 EXPORT_SYMBOL(gen_kill_estimator);
 
@@ -312,8 +315,14 @@ EXPORT_SYMBOL(gen_replace_estimator);
 bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
                          const struct gnet_stats_rate_est *rate_est)
 {
+       bool res;
+
        ASSERT_RTNL();
 
-       return gen_find_node(bstats, rate_est) != NULL;
+       spin_lock(&est_tree_lock);
+       res = gen_find_node(bstats, rate_est) != NULL;
+       spin_unlock(&est_tree_lock);
+
+       return res;
 }
 EXPORT_SYMBOL(gen_estimator_active);