summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
authorRicardo Dias <rdias@singlestore.com>2020-11-20 11:11:33 +0000
committerJakub Kicinski <kuba@kernel.org>2020-11-23 16:32:33 -0800
commit01770a166165738a6e05c3d911fb4609cc4eb416 (patch)
tree5e59edcbd3e772a9cb1a81b82625f375f371c3cb /net/ipv6
parent1eae77bfad7a0ded0f70d56f360ca59571a8cf4d (diff)
tcp: fix race condition when creating child sockets from syncookies
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 drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/tcp_ipv6.c13
1 files changed, 12 insertions, 1 deletions
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3d49e8d0afee..d2502911b7fa 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1193,6 +1193,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct ipv6_txoptions *opt;
struct inet_sock *newinet;
+ bool found_dup_sk = false;
struct tcp_sock *newtp;
struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
@@ -1368,7 +1369,8 @@ 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),
+ &found_dup_sk);
if (*own_req) {
tcp_move_syn(newtp, req);
@@ -1383,6 +1385,15 @@ 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 && found_dup_sk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ bh_unlock_sock(newsk);
+ sock_put(newsk);
+ newsk = NULL;
+ }
}
return newsk;