@@ -247,8 +247,8 @@ void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
unsigned long high_limit);
int inet_hashinfo2_init_mod(struct inet_hashinfo *h);
-bool inet_ehash_insert(struct sock *sk, struct sock *osk);
-bool inet_ehash_nolisten(struct sock *sk, struct sock *osk);
+bool inet_ehash_insert(struct sock *sk, struct sock *osk, struct sock **esk);
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, struct sock **esk);
int __inet_hash(struct sock *sk, struct sock *osk);
int inet_hash(struct sock *sk);
void inet_unhash(struct sock *sk);
@@ -427,7 +427,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
if (*own_req)
ireq->ireq_opt = NULL;
else
@@ -533,7 +533,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
dccp_done(newsk);
goto out;
}
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
/* Clone pktoptions received with SYN, if we own the req */
if (*own_req && ireq->pktopts) {
newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
@@ -787,7 +787,7 @@ static void reqsk_queue_hash_req(struct request_sock *req,
timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
mod_timer(&req->rsk_timer, jiffies + timeout);
- inet_ehash_insert(req_to_sk(req), NULL);
+ inet_ehash_insert(req_to_sk(req), NULL, NULL);
/* before letting lookups find us, make sure all req fields
* are committed to memory and refcnt initialized.
*/
@@ -20,6 +20,9 @@
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/inet6_hashtables.h>
+#endif
#include <net/secure_seq.h>
#include <net/ip.h>
#include <net/tcp.h>
@@ -510,14 +513,17 @@ static u32 inet_sk_port_offset(const struct sock *sk)
inet->inet_dport);
}
-/* insert a socket into ehash, and eventually remove another one
- * (The another one can be a SYN_RECV or TIMEWAIT
+/* Insert a socket into ehash, and eventually remove another one
+ * (The another one can be a SYN_RECV or TIMEWAIT)
+ * If an existing socket already exists, it returns that socket
+ * through the esk parameter.
*/
-bool inet_ehash_insert(struct sock *sk, struct sock *osk)
+bool inet_ehash_insert(struct sock *sk, struct sock *osk, struct sock **esk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_nulls_head *list;
struct inet_ehash_bucket *head;
+ struct sock *_esk;
spinlock_t *lock;
bool ret = true;
@@ -532,16 +538,58 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk)
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
ret = sk_nulls_del_node_init_rcu(osk);
+ } else if (esk) {
+ const struct hlist_nulls_node *node;
+ struct net *net = sock_net(sk);
+ const int dif = sk->sk_bound_dev_if;
+ const int sdif = sk->sk_bound_dev_if;
+
+ INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr);
+ const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport,
+ sk->sk_num);
+
+ sk_nulls_for_each_rcu(_esk, node, list) {
+ if (_esk->sk_hash != sk->sk_hash)
+ continue;
+ if (sk->sk_family == AF_INET) {
+ if (unlikely(INET_MATCH(_esk, net, acookie,
+ sk->sk_daddr,
+ sk->sk_rcv_saddr,
+ ports, dif, sdif))) {
+ refcount_inc(&_esk->sk_refcnt);
+ goto found;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (sk->sk_family == AF_INET6) {
+ if (unlikely(INET6_MATCH(_esk, net,
+ &sk->sk_v6_daddr,
+ &sk->sk_v6_rcv_saddr,
+ ports, dif, sdif))) {
+ refcount_inc(&_esk->sk_refcnt);
+ goto found;
+ }
+ }
+#endif
+ }
+
}
+ _esk = NULL;
if (ret)
__sk_nulls_add_node_rcu(sk, list);
+
+found:
spin_unlock(lock);
+ if (_esk) {
+ *esk = _esk;
+ ret = false;
+ }
return ret;
}
-bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, struct sock **esk)
{
- bool ok = inet_ehash_insert(sk, osk);
+ bool ok = inet_ehash_insert(sk, osk, esk);
if (ok) {
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -585,7 +633,7 @@ int __inet_hash(struct sock *sk, struct sock *osk)
int err = 0;
if (sk->sk_state != TCP_LISTEN) {
- inet_ehash_nolisten(sk, osk);
+ inet_ehash_nolisten(sk, osk, NULL);
return 0;
}
WARN_ON(!sk_unhashed(sk));
@@ -681,7 +729,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- inet_ehash_nolisten(sk, NULL);
+ inet_ehash_nolisten(sk, NULL, NULL);
spin_unlock_bh(&head->lock);
return 0;
}
@@ -760,7 +808,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
- inet_ehash_nolisten(sk, (struct sock *)tw);
+ inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
@@ -208,7 +208,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
NULL, &own_req);
- if (child) {
+ if (child && own_req) {
refcount_set(&req->rsk_refcnt, 1);
tcp_sk(child)->tsoffset = tsoff;
sock_rps_save_rxhash(child, skb);
@@ -223,6 +223,9 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
bh_unlock_sock(child);
sock_put(child);
+ } else if (child && !own_req) {
+ __reqsk_free(req);
+ return child;
}
__reqsk_free(req);
@@ -1501,6 +1501,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
int l3index;
#endif
struct ip_options_rcu *inet_opt;
+ struct sock *esk = NULL;
if (sk_acceptq_is_full(sk))
goto exit_overflow;
@@ -1565,11 +1566,17 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &esk);
if (likely(*own_req)) {
tcp_move_syn(newtp, req);
ireq->ireq_opt = NULL;
} else {
+ if (!req_unhash && esk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ newsk = esk;
+ }
newinet->inet_opt = NULL;
}
return newsk;
@@ -1190,6 +1190,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
+ struct sock *esk = NULL;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
int l3index;
@@ -1206,6 +1207,12 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
if (!newsk)
return NULL;
+ else if (!req_unhash && !own_req) {
+ /* We're returning an existing child socket, probably
+ * created by a previous syncookie ACK.
+ */
+ return newsk;
+ }
inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
@@ -1359,7 +1366,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
tcp_done(newsk);
goto out;
}
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &esk);
if (*own_req) {
tcp_move_syn(newtp, req);
@@ -1374,6 +1381,13 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
skb_set_owner_r(newnp->pktoptions, newsk);
}
}
+ } else {
+ if (!req_unhash && esk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ newsk = esk;
+ }
}
return newsk;
When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we return that socket and use it to process the TCP packet received, and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> --- include/net/inet_hashtables.h | 4 +-- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/inet_hashtables.c | 64 ++++++++++++++++++++++++++++----- net/ipv4/syncookies.c | 5 ++- net/ipv4/tcp_ipv4.c | 9 ++++- net/ipv6/tcp_ipv6.c | 16 ++++++++- 8 files changed, 88 insertions(+), 16 deletions(-)