a8df9d0428
[ Upstream commit 69421bf98482d089e50799f45e48b25ce4a8d154 ]
When we call connect() for a UDP socket in a reuseport group, we have
to update sk->sk_reuseport_cb->has_conns to 1. Otherwise, the kernel
could select a unconnected socket wrongly for packets sent to the
connected socket.
However, the current way to set has_conns is illegal and possible to
trigger that problem. reuseport_has_conns() changes has_conns under
rcu_read_lock(), which upgrades the RCU reader to the updater. Then,
it must do the update under the updater's lock, reuseport_lock, but
it doesn't for now.
For this reason, there is a race below where we fail to set has_conns
resulting in the wrong socket selection. To avoid the race, let's split
the reader and updater with proper locking.
cpu1 cpu2
+----+ +----+
__ip[46]_datagram_connect() reuseport_grow()
. .
|- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size)
| . |
| |- rcu_read_lock()
| |- reuse = rcu_dereference(sk->sk_reuseport_cb)
| |
| | | /* reuse->has_conns == 0 here */
| | |- more_reuse->has_conns = reuse->has_conns
| |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */
| | |
| | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb,
| | | more_reuse)
| `- rcu_read_unlock() `- kfree_rcu(reuse, rcu)
|
|- sk->sk_state = TCP_ESTABLISHED
Note the likely(reuse) in reuseport_has_conns_set() is always true,
but we put the test there for ease of review. [0]
For the record, usually, sk_reuseport_cb is changed under lock_sock().
The only exception is reuseport_grow() & TCP reqsk migration case.
1) shutdown() TCP listener, which is moved into the latter part of
reuse->socks[] to migrate reqsk.
2) New listen() overflows reuse->socks[] and call reuseport_grow().
3) reuse->max_socks overflows u16 with the new listener.
4) reuseport_grow() pops the old shutdown()ed listener from the array
and update its sk->sk_reuseport_cb as NULL without lock_sock().
shutdown()ed TCP sk->sk_reuseport_cb can be changed without lock_sock(),
but, reuseport_has_conns_set() is called only for UDP under lock_sock(),
so likely(reuse) never be false in reuseport_has_conns_set().
[0]: https://lore.kernel.org/netdev/CANn89iLja=eQHbsM_Ta2sQF0tOGU8vAGrh_izRuuHjuO1ouUag@mail.gmail.com/
Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20221014182625.89913-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
130 lines
3.1 KiB
C
130 lines
3.1 KiB
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_set(sk);
|
|
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);
|