Since ehash lookups are lockless, if one CPU performs a lookup while
another concurrently deletes and inserts (removing reqsk and inserting sk),
the lookup may fail to find the socket, an RST may be sent.
The call trace map is drawn as follows:
CPU 0 CPU 1
----- -----
inet_ehash_insert()
spin_lock()
sk_nulls_del_node_init_rcu(osk)
__inet_lookup_established()
(lookup failed)
__sk_nulls_add_node_rcu(sk, list)
spin_unlock()
As both deletion and insertion operate on the same ehash chain, this patch
introduces a new sk_nulls_replace_node_init_rcu() helper functions to
implement atomic replacement.
Fixes: 5e0724d027f0 ("tcp/dccp: fix hashdance race for passive sessions")
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Signed-off-by: Xuanqiang Luo <luoxuanqiang@kylinos.cn>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251015020236.431822-3-xuanqiang.luo@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
return rc;
}
+static inline bool sk_nulls_replace_node_init_rcu(struct sock *old,
+ struct sock *new)
+{
+ if (sk_hashed(old)) {
+ hlist_nulls_replace_init_rcu(&old->sk_nulls_node,
+ &new->sk_nulls_node);
+ __sock_put(old);
+ return true;
+ }
+
+ return false;
+}
+
static inline void __sk_add_node(struct sock *sk, struct hlist_head *list)
{
hlist_add_head(&sk->sk_node, list);
spin_lock(lock);
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
- ret = sk_nulls_del_node_init_rcu(osk);
- } else if (found_dup_sk) {
+ ret = sk_nulls_replace_node_init_rcu(osk, sk);
+ goto unlock;
+ }
+
+ if (found_dup_sk) {
*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
if (*found_dup_sk)
ret = false;
if (ret)
__sk_nulls_add_node_rcu(sk, list);
+unlock:
spin_unlock(lock);
return ret;