Skip to main content

Browse the archive

Revision 78c906e430b13d30a8cfbdef4ccbbe1686841a9e authored by Vlad Buslov on 31 August 2020, 13:17:29 UTC, committed by Saeed Mahameed on 05 November 2020, 20:17:05 UTC 
net/mlx5e: Protect encap route dev from concurrent release
 
In functions mlx5e_route_lookup_ipv{4|6}() route_dev can be arbitrary net
device and not necessary mlx5 eswitch port representor. As such, in order
to ensure that route_dev is not destroyed concurrent the code needs either
explicitly take reference to the device before releasing reference to
rtable instance or ensure that caller holds rtnl lock. First approach is
chosen as a fix since rtnl lock dependency was intentionally removed from
mlx5 TC layer.

To prevent unprotected usage of route_dev in encap code take a reference to
the device before releasing rt. Don't save direct pointer to the device in
mlx5_encap_entry structure and use ifindex instead. Modify users of
route_dev pointer to properly obtain the net device instance from its
ifindex.

Fixes: 61086f391044 ("net/mlx5e: Protect encap hash table with mutex")
Fixes: 6707f74be862 ("net/mlx5e: Update hw flows when encap source mac changed")
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
1 parent e68e28b
Raw File
datagram.c 
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	common UDP/RAW code
 *	Linux INET implementation
 *
 * Authors:
 * 	Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
 */

#include <linux/types.h>
#include <linux/module.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <net/ip.h>
#include <net/sock.h>
#include <net/route.h>
#include <net/tcp_states.h>
#include <net/sock_reuseport.h>

int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
	struct flowi4 *fl4;
	struct rtable *rt;
	__be32 saddr;
	int oif;
	int err;


	if (addr_len < sizeof(*usin))
		return -EINVAL;

	if (usin->sin_family != AF_INET)
		return -EAFNOSUPPORT;

	sk_dst_reset(sk);

	oif = sk->sk_bound_dev_if;
	saddr = inet->inet_saddr;
	if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
		if (!oif || netif_index_is_l3_master(sock_net(sk), oif))
			oif = inet->mc_index;
		if (!saddr)
			saddr = inet->mc_addr;
	}
	fl4 = &inet->cork.fl.u.ip4;
	rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr,
			      RT_CONN_FLAGS(sk), oif,
			      sk->sk_protocol,
			      inet->inet_sport, usin->sin_port, sk);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		if (err == -ENETUNREACH)
			IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
		goto out;
	}

	if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) {
		ip_rt_put(rt);
		err = -EACCES;
		goto out;
	}
	if (!inet->inet_saddr)
		inet->inet_saddr = fl4->saddr;	/* Update source address */
	if (!inet->inet_rcv_saddr) {
		inet->inet_rcv_saddr = fl4->saddr;
		if (sk->sk_prot->rehash)
			sk->sk_prot->rehash(sk);
	}
	inet->inet_daddr = fl4->daddr;
	inet->inet_dport = usin->sin_port;
	reuseport_has_conns(sk, true);
	sk->sk_state = TCP_ESTABLISHED;
	sk_set_txhash(sk);
	inet->inet_id = prandom_u32();

	sk_dst_set(sk, &rt->dst);
	err = 0;
out:
	return err;
}
EXPORT_SYMBOL(__ip4_datagram_connect);

int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	int res;

	lock_sock(sk);
	res = __ip4_datagram_connect(sk, uaddr, addr_len);
	release_sock(sk);
	return res;
}
EXPORT_SYMBOL(ip4_datagram_connect);

/* Because UDP xmit path can manipulate sk_dst_cache without holding
 * socket lock, we need to use sk_dst_set() here,
 * even if we own the socket lock.
 */
void ip4_datagram_release_cb(struct sock *sk)
{
	const struct inet_sock *inet = inet_sk(sk);
	const struct ip_options_rcu *inet_opt;
	__be32 daddr = inet->inet_daddr;
	struct dst_entry *dst;
	struct flowi4 fl4;
	struct rtable *rt;

	rcu_read_lock();

	dst = __sk_dst_get(sk);
	if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
		rcu_read_unlock();
		return;
	}
	inet_opt = rcu_dereference(inet->inet_opt);
	if (inet_opt && inet_opt->opt.srr)
		daddr = inet_opt->opt.faddr;
	rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr,
				   inet->inet_saddr, inet->inet_dport,
				   inet->inet_sport, sk->sk_protocol,
				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);

	dst = !IS_ERR(rt) ? &rt->dst : NULL;
	sk_dst_set(sk, dst);

	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
back to top