net_sched: fix a race condition in tcindex_destroy()

(cherry picked from commit 8015d93e)

tcindex_destroy() invokes tcindex_destroy_element() via
a walker to delete each filter result in its perfect hash
table, and tcindex_destroy_element() calls tcindex_delete()
which schedules tcf RCU works to do the final deletion work.
Unfortunately this races with the RCU callback
__tcindex_destroy(), which could lead to use-after-free as
reported by Adrian.

Fix this by migrating this RCU callback to tcf RCU work too,
as that workqueue is ordered, we will not have use-after-free.

Note, we don't need to hold netns refcnt because we don't call
tcf_exts_destroy() here.

Fixes: 27ce4f05 ("net_sched: use tcf_queue_work() in tcindex filter")
Reported-by: Adrian <bugs@abtelecom.ro>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/sched/cls_tcindex.c

@@ -48,7 +48,7 @@ struct tcindex_data {
 	u32 hash;		/* hash table size; 0 if undefined */
 	u32 alloc_hash;		/* allocated size */
 	u32 fall_through;	/* 0: only classify if explicit match */
-	struct rcu_head rcu;
+	struct rcu_work rwork;
 };
 
 static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
@@ -229,9 +229,11 @@ static int tcindex_destroy_element(struct tcf_proto *tp,
 	return tcindex_delete(tp, arg, &last, false, NULL);
 }
 
-static void __tcindex_destroy(struct rcu_head *head)
+static void tcindex_destroy_work(struct work_struct *work)
 {
-	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+	struct tcindex_data *p = container_of(to_rcu_work(work),
+					      struct tcindex_data,
+					      rwork);
 
 	kfree(p->perfect);
 	kfree(p->h);
@@ -258,9 +260,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r)
 	return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 }
 
-static void __tcindex_partial_destroy(struct rcu_head *head)
+static void tcindex_partial_destroy_work(struct work_struct *work)
 {
-	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+	struct tcindex_data *p = container_of(to_rcu_work(work),
+					      struct tcindex_data,
+					      rwork);
 
 	kfree(p->perfect);
 	kfree(p);
@@ -480,7 +484,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (oldp)
-		call_rcu(&oldp->rcu, __tcindex_partial_destroy);
+		tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work);
 	return 0;
 
 errout_alloc:
@@ -572,7 +576,7 @@ static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
 	walker.fn = tcindex_destroy_element;
 	tcindex_walk(tp, &walker, true);
 
-	call_rcu(&p->rcu, __tcindex_destroy);
+	tcf_queue_work(&p->rwork, tcindex_destroy_work);
 }