linux/net/ipv4/datagram.c
Eric Dumazet f866fbc842 ipv4: fix data-races around inet->inet_id
UDP sendmsg() is lockless, so ip_select_ident_segs()
can very well be run from multiple cpus [1]

Convert inet->inet_id to an atomic_t, but implement
a dedicated path for TCP, avoiding cost of a locked
instruction (atomic_add_return())

Note that this patch will cause a trivial merge conflict
because we added inet->flags in net-next tree.

v2: added missing change in
drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
(David Ahern)

[1]

BUG: KCSAN: data-race in __ip_make_skb / __ip_make_skb

read-write to 0xffff888145af952a of 2 bytes by task 7803 on cpu 1:
ip_select_ident_segs include/net/ip.h:542 [inline]
ip_select_ident include/net/ip.h:556 [inline]
__ip_make_skb+0x844/0xc70 net/ipv4/ip_output.c:1446
ip_make_skb+0x233/0x2c0 net/ipv4/ip_output.c:1560
udp_sendmsg+0x1199/0x1250 net/ipv4/udp.c:1260
inet_sendmsg+0x63/0x80 net/ipv4/af_inet.c:830
sock_sendmsg_nosec net/socket.c:725 [inline]
sock_sendmsg net/socket.c:748 [inline]
____sys_sendmsg+0x37c/0x4d0 net/socket.c:2494
___sys_sendmsg net/socket.c:2548 [inline]
__sys_sendmmsg+0x269/0x500 net/socket.c:2634
__do_sys_sendmmsg net/socket.c:2663 [inline]
__se_sys_sendmmsg net/socket.c:2660 [inline]
__x64_sys_sendmmsg+0x57/0x60 net/socket.c:2660
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffff888145af952a of 2 bytes by task 7804 on cpu 0:
ip_select_ident_segs include/net/ip.h:541 [inline]
ip_select_ident include/net/ip.h:556 [inline]
__ip_make_skb+0x817/0xc70 net/ipv4/ip_output.c:1446
ip_make_skb+0x233/0x2c0 net/ipv4/ip_output.c:1560
udp_sendmsg+0x1199/0x1250 net/ipv4/udp.c:1260
inet_sendmsg+0x63/0x80 net/ipv4/af_inet.c:830
sock_sendmsg_nosec net/socket.c:725 [inline]
sock_sendmsg net/socket.c:748 [inline]
____sys_sendmsg+0x37c/0x4d0 net/socket.c:2494
___sys_sendmsg net/socket.c:2548 [inline]
__sys_sendmmsg+0x269/0x500 net/socket.c:2634
__do_sys_sendmmsg net/socket.c:2663 [inline]
__se_sys_sendmmsg net/socket.c:2660 [inline]
__x64_sys_sendmmsg+0x57/0x60 net/socket.c:2660
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x184d -> 0x184e

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 7804 Comm: syz-executor.1 Not tainted 6.5.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
==================================================================

Fixes: 23f57406b8 ("ipv4: avoid using shared IP generator for connected sockets")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2023-08-20 11:40:49 +01:00

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/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;
} else if (!oif) {
oif = inet->uc_index;
}
fl4 = &inet->cork.fl.u.ip4;
rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, 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);
atomic_set(&inet->inet_id, get_random_u16());
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);