Commit 01770a16 authored by Ricardo Dias's avatar Ricardo Dias Committed by Jakub Kicinski
Browse files

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: default avatarRicardo Dias <rdias@singlestore.com>
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 1eae77bf

include/net/inet_hashtables.h

+3 −2
Original line number Diff line number Diff line
@@ -247,8 +247,9 @@ 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, bool *found_dup_sk);

bool inet_ehash_nolisten(struct sock *sk, struct sock *osk,

			 bool *found_dup_sk);

int __inet_hash(struct sock *sk, struct sock *osk);

int inet_hash(struct sock *sk);

void inet_unhash(struct sock *sk);

net/dccp/ipv4.c

+1 −1
Original line number Diff line number Diff line
@@ -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

net/dccp/ipv6.c

+1 −1
Original line number Diff line number Diff line
@@ -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);

net/ipv4/inet_connection_sock.c

+1 −1
Original line number Diff line number Diff line
@@ -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.

	 */

net/ipv4/inet_hashtables.c

+60 −8
Original line number Diff line number Diff line
@@ -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>
@@ -508,10 +511,52 @@ 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

/* Searches for an exsiting socket in the ehash bucket list.

 * Returns true if found, false otherwise.

 */

static bool inet_ehash_lookup_by_sk(struct sock *sk,

				    struct hlist_nulls_head *list)

{

	const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num);

	const int sdif = sk->sk_bound_dev_if;

	const int dif = sk->sk_bound_dev_if;

	const struct hlist_nulls_node *node;

	struct net *net = sock_net(sk);

	struct sock *esk;



	INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr);



	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))) {

				return true;

			}

		}

#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))) {

				return true;

			}

		}

#endif

	}

	return false;

}



/* 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, socket sk is not inserted,

 * and sets found_dup_sk parameter to true.

 */

bool inet_ehash_insert(struct sock *sk, struct sock *osk)

bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)

{

	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;

	struct hlist_nulls_head *list;
@@ -530,16 +575,23 @@ 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 (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);



	spin_unlock(lock);



	return ret;

}



bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)

bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk)

{

	bool ok = inet_ehash_insert(sk, osk);

	bool ok = inet_ehash_insert(sk, osk, found_dup_sk);



	if (ok) {

		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -583,7 +635,7 @@ 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));
@@ -679,7 +731,7 @@ 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;

		}
@@ -758,7 +810,7 @@ ok: 
	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);

CRA Git | Maintained and supported by SUSTech CRA and CCSE