On 9/7/22 01:57, Eric Dumazet wrote:
On Mon, Sep 5, 2022 at 12:06 AM Leonard Crestez <cdleonard@xxxxxxxxx> wrote:
This commit adds support to add and remove keys but does not use them
further.
Similar to tcp md5 a single pointer to a struct tcp_authopt_info* struct
is added to struct tcp_sock, this avoids increasing memory usage. The
data structures related to tcp_authopt are initialized on setsockopt and
only freed on socket close.
Thanks Leonard.
Small points from my side, please find them attached.
...
+/* Free info and keys.
+ * Don't touch tp->authopt_info, it might not even be assigned yes.
+ */
+void tcp_authopt_free(struct sock *sk, struct tcp_authopt_info *info)
+{
+ kfree_rcu(info, rcu);
+}
+
+/* Free everything and clear tcp_sock.authopt_info to NULL */
+void tcp_authopt_clear(struct sock *sk)
+{
+ struct tcp_authopt_info *info;
+
+ info = rcu_dereference_protected(tcp_sk(sk)->authopt_info, lockdep_sock_is_held(sk));
+ if (info) {
+ tcp_authopt_free(sk, info);
+ tcp_sk(sk)->authopt_info = NULL;
RCU rules at deletion mandate that the pointer must be cleared before
the call_rcu()/kfree_rcu() call.
It is possible that current MD5 code has an issue here, let's not copy/paste it.
OK. Is there a need for some special form of assignment or is current
plain form enough?
+ }
+}
+
+/* checks that ipv4 or ipv6 addr matches. */
+static bool ipvx_addr_match(struct sockaddr_storage *a1,
+ struct sockaddr_storage *a2)
+{
+ if (a1->ss_family != a2->ss_family)
+ return false;
+ if (a1->ss_family == AF_INET &&
+ (((struct sockaddr_in *)a1)->sin_addr.s_addr !=
+ ((struct sockaddr_in *)a2)->sin_addr.s_addr))
+ return false;
+ if (a1->ss_family == AF_INET6 &&
+ !ipv6_addr_equal(&((struct sockaddr_in6 *)a1)->sin6_addr,
+ &((struct sockaddr_in6 *)a2)->sin6_addr))
+ return false;
+ return true;
+}
Always surprising to see this kind of generic helper being added in a patch.
I remember looking for an equivalent and not finding it. Many places
have distinct code paths for ipv4 and ipv6 and my use of
"sockaddr_storage" as ipv4/ipv6 union is uncommon.
It also wastes some memory.
+int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *opt)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_authopt_info *info;
+
+ memset(opt, 0, sizeof(*opt));
+ sock_owned_by_me(sk);
+
+ info = rcu_dereference_check(tp->authopt_info, lockdep_sock_is_held(sk));
Probably not a big deal, but it seems the prior sock_owned_by_me()
might be redundant.
The sock_owned_by_me call checks checks lockdep_sock_is_held
The rcu_dereference_check call checks lockdep_sock_is_held ||
rcu_read_lock_held()
This is a getsockopt so caller ensures socket locking but
rcu_read_lock_held() == 0.
The sock_owned_by_me is indeed redundant because it seems very unlikely
the sockopt calling conditions will be changes. It was mostly there to
clarify for myself because I had probably at one time with locking
warnings. I guess they can be removed.
+int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen)
+{
+ struct tcp_authopt_key opt;
+ struct tcp_authopt_info *info;
+ struct tcp_authopt_key_info *key_info, *old_key_info;
+ struct netns_tcp_authopt *net = sock_net_tcp_authopt(sk);
+ int err;
+
+ sock_owned_by_me(sk);
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+
+ err = _copy_from_sockptr_tolerant((u8 *)&opt, sizeof(opt), optval, optlen);
+ if (err)
+ return err;
+
+ if (opt.flags & ~TCP_AUTHOPT_KEY_KNOWN_FLAGS)
+ return -EINVAL;
+
+ if (opt.keylen > TCP_AUTHOPT_MAXKEYLEN)
+ return -EINVAL;
+
+ /* Delete is a special case: */
+ if (opt.flags & TCP_AUTHOPT_KEY_DEL) {
+ mutex_lock(&net->mutex);
+ key_info = tcp_authopt_key_lookup_exact(sk, net, &opt);
+ if (key_info) {
+ tcp_authopt_key_del(net, key_info);
+ err = 0;
+ } else {
+ err = -ENOENT;
+ }
+ mutex_unlock(&net->mutex);
+ return err;
+ }
+
+ /* check key family */
+ if (opt.flags & TCP_AUTHOPT_KEY_ADDR_BIND) {
+ if (sk->sk_family != opt.addr.ss_family)
+ return -EINVAL;
+ }
+
+ /* Initialize tcp_authopt_info if not already set */
+ info = __tcp_authopt_info_get_or_create(sk);
+ if (IS_ERR(info))
+ return PTR_ERR(info);
+
+ key_info = kmalloc(sizeof(*key_info), GFP_KERNEL | __GFP_ZERO);
kzalloc() ?
Yes
+static int tcp_authopt_init_net(struct net *full_net)
Hmmm... our convention is to use "struct net *net"
+{
+ struct netns_tcp_authopt *net = &full_net->tcp_authopt;
Here, you should use a different name ...
OK, will replace with net_ao
@@ -2267,10 +2268,11 @@ void tcp_v4_destroy_sock(struct sock *sk)
tcp_clear_md5_list(sk);
kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu);
tp->md5sig_info = NULL;
}
#endif
+ tcp_authopt_clear(sk);
Do we really own the socket lock at this point ?
Not sure how I would tell but there is a lockdep_sock_is_held check
inside tcp_authopt_clear. I also added sock_owned_by_me and there were
no warnings.
