aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorBalazs Scheidler <bazsi@balabit.hu>2010-10-21 13:06:43 +0200
committerPatrick McHardy <kaber@trash.net>2010-10-21 13:06:43 +0200
commit093d282321daeb19c107e5f1f16d7f68484f3ade (patch)
tree36e9eed23573068819bf67a91caac6ebf60d0d7c /net/ipv4
parent6006db84a91838813cdad8a6622a4e39efe9ea47 (diff)
tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()
When __inet_inherit_port() is called on a tproxy connection the wrong locks are held for the inet_bind_bucket it is added to. __inet_inherit_port() made an implicit assumption that the listener's port number (and thus its bind bucket). Unfortunately, if you're using the TPROXY target to redirect skbs to a transparent proxy that assumption is not true anymore and things break. This patch adds code to __inet_inherit_port() so that it can handle this case by looking up or creating a new bind bucket for the child socket and updates callers of __inet_inherit_port() to gracefully handle __inet_inherit_port() failing. Reported by and original patch from Stephen Buck <stephen.buck@exinda.com>. See http://marc.info/?t=128169268200001&r=1&w=2 for the original discussion. Signed-off-by: KOVACS Krisztian <hidden@balabit.hu> Signed-off-by: Patrick McHardy <kaber@trash.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/inet_hashtables.c28
-rw-r--r--net/ipv4/tcp_ipv4.c10
2 files changed, 33 insertions, 5 deletions
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index fb7ad5a21ff..1b344f30b46 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -101,19 +101,43 @@ void inet_put_port(struct sock *sk)
}
EXPORT_SYMBOL(inet_put_port);
-void __inet_inherit_port(struct sock *sk, struct sock *child)
+int __inet_inherit_port(struct sock *sk, struct sock *child)
{
struct inet_hashinfo *table = sk->sk_prot->h.hashinfo;
- const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->inet_num,
+ unsigned short port = inet_sk(child)->inet_num;
+ const int bhash = inet_bhashfn(sock_net(sk), port,
table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
+ if (tb->port != port) {
+ /* NOTE: using tproxy and redirecting skbs to a proxy
+ * on a different listener port breaks the assumption
+ * that the listener socket's icsk_bind_hash is the same
+ * as that of the child socket. We have to look up or
+ * create a new bind bucket for the child here. */
+ struct hlist_node *node;
+ inet_bind_bucket_for_each(tb, node, &head->chain) {
+ if (net_eq(ib_net(tb), sock_net(sk)) &&
+ tb->port == port)
+ break;
+ }
+ if (!node) {
+ tb = inet_bind_bucket_create(table->bind_bucket_cachep,
+ sock_net(sk), head, port);
+ if (!tb) {
+ spin_unlock(&head->lock);
+ return -ENOMEM;
+ }
+ }
+ }
sk_add_bind_node(child, &tb->owners);
inet_csk(child)->icsk_bind_hash = tb;
spin_unlock(&head->lock);
+
+ return 0;
}
EXPORT_SYMBOL_GPL(__inet_inherit_port);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a0232f3a358..8f8527d4168 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1422,7 +1422,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
newsk = tcp_create_openreq_child(sk, req, skb);
if (!newsk)
- goto exit;
+ goto exit_nonewsk;
newsk->sk_gso_type = SKB_GSO_TCPV4;
sk_setup_caps(newsk, dst);
@@ -1469,16 +1469,20 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
}
#endif
+ if (__inet_inherit_port(sk, newsk) < 0) {
+ sock_put(newsk);
+ goto exit;
+ }
__inet_hash_nolisten(newsk, NULL);
- __inet_inherit_port(sk, newsk);
return newsk;
exit_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+exit_nonewsk:
+ dst_release(dst);
exit:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
- dst_release(dst);
return NULL;
}
EXPORT_SYMBOL(tcp_v4_syn_recv_sock);