android_kernel_motorola_sm6225/net/ipv4/tcp_diag.c
Eric Dumazet 67f028acac tcp: annotate tp->rcv_nxt lockless reads
[ Upstream commit dba7d9b8c739df27ff3a234c81d6c6b23e3986fa ]

There are few places where we fetch tp->rcv_nxt while
this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make
sure write sides use corresponding WRITE_ONCE() to avoid
store-tearing.

Note that tcp_inq_hint() was already using READ_ONCE(tp->rcv_nxt)

syzbot reported :

BUG: KCSAN: data-race in tcp_poll / tcp_queue_rcv

write to 0xffff888120425770 of 4 bytes by interrupt on cpu 0:
 tcp_rcv_nxt_update net/ipv4/tcp_input.c:3365 [inline]
 tcp_queue_rcv+0x180/0x380 net/ipv4/tcp_input.c:4638
 tcp_rcv_established+0xbf1/0xf50 net/ipv4/tcp_input.c:5616
 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1542
 tcp_v4_rcv+0x1a03/0x1bf0 net/ipv4/tcp_ipv4.c:1923
 ip_protocol_deliver_rcu+0x51/0x470 net/ipv4/ip_input.c:204
 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231
 NF_HOOK include/linux/netfilter.h:305 [inline]
 NF_HOOK include/linux/netfilter.h:299 [inline]
 ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252
 dst_input include/net/dst.h:442 [inline]
 ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413
 NF_HOOK include/linux/netfilter.h:305 [inline]
 NF_HOOK include/linux/netfilter.h:299 [inline]
 ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523
 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004
 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118
 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208
 napi_skb_finish net/core/dev.c:5671 [inline]
 napi_gro_receive+0x28f/0x330 net/core/dev.c:5704
 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061

read to 0xffff888120425770 of 4 bytes by task 7254 on cpu 1:
 tcp_stream_is_readable net/ipv4/tcp.c:480 [inline]
 tcp_poll+0x204/0x6b0 net/ipv4/tcp.c:554
 sock_poll+0xed/0x250 net/socket.c:1256
 vfs_poll include/linux/poll.h:90 [inline]
 ep_item_poll.isra.0+0x90/0x190 fs/eventpoll.c:892
 ep_send_events_proc+0x113/0x5c0 fs/eventpoll.c:1749
 ep_scan_ready_list.constprop.0+0x189/0x500 fs/eventpoll.c:704
 ep_send_events fs/eventpoll.c:1793 [inline]
 ep_poll+0xe3/0x900 fs/eventpoll.c:1930
 do_epoll_wait+0x162/0x180 fs/eventpoll.c:2294
 __do_sys_epoll_pwait fs/eventpoll.c:2325 [inline]
 __se_sys_epoll_pwait fs/eventpoll.c:2311 [inline]
 __x64_sys_epoll_pwait+0xcd/0x170 fs/eventpoll.c:2311
 do_syscall_64+0xcf/0x2f0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 7254 Comm: syz-fuzzer Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-01-09 10:19:08 +01:00

191 lines
4.6 KiB
C

/*
* tcp_diag.c Module for monitoring TCP transport protocols sockets.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
#include <linux/net.h>
#include <linux/sock_diag.h>
#include <linux/inet_diag.h>
#include <linux/tcp.h>
#include <net/netlink.h>
#include <net/tcp.h>
static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
void *_info)
{
struct tcp_info *info = _info;
if (inet_sk_state_load(sk) == TCP_LISTEN) {
r->idiag_rqueue = sk->sk_ack_backlog;
r->idiag_wqueue = sk->sk_max_ack_backlog;
} else if (sk->sk_type == SOCK_STREAM) {
const struct tcp_sock *tp = tcp_sk(sk);
r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - tp->copied_seq, 0);
r->idiag_wqueue = tp->write_seq - tp->snd_una;
}
if (info)
tcp_get_info(sk, info);
}
#ifdef CONFIG_TCP_MD5SIG
static void tcp_diag_md5sig_fill(struct tcp_diag_md5sig *info,
const struct tcp_md5sig_key *key)
{
info->tcpm_family = key->family;
info->tcpm_prefixlen = key->prefixlen;
info->tcpm_keylen = key->keylen;
memcpy(info->tcpm_key, key->key, key->keylen);
if (key->family == AF_INET)
info->tcpm_addr[0] = key->addr.a4.s_addr;
#if IS_ENABLED(CONFIG_IPV6)
else if (key->family == AF_INET6)
memcpy(&info->tcpm_addr, &key->addr.a6,
sizeof(info->tcpm_addr));
#endif
}
static int tcp_diag_put_md5sig(struct sk_buff *skb,
const struct tcp_md5sig_info *md5sig)
{
const struct tcp_md5sig_key *key;
struct tcp_diag_md5sig *info;
struct nlattr *attr;
int md5sig_count = 0;
hlist_for_each_entry_rcu(key, &md5sig->head, node)
md5sig_count++;
if (md5sig_count == 0)
return 0;
attr = nla_reserve(skb, INET_DIAG_MD5SIG,
md5sig_count * sizeof(struct tcp_diag_md5sig));
if (!attr)
return -EMSGSIZE;
info = nla_data(attr);
memset(info, 0, md5sig_count * sizeof(struct tcp_diag_md5sig));
hlist_for_each_entry_rcu(key, &md5sig->head, node) {
tcp_diag_md5sig_fill(info++, key);
if (--md5sig_count == 0)
break;
}
return 0;
}
#endif
static int tcp_diag_get_aux(struct sock *sk, bool net_admin,
struct sk_buff *skb)
{
#ifdef CONFIG_TCP_MD5SIG
if (net_admin) {
struct tcp_md5sig_info *md5sig;
int err = 0;
rcu_read_lock();
md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info);
if (md5sig)
err = tcp_diag_put_md5sig(skb, md5sig);
rcu_read_unlock();
if (err < 0)
return err;
}
#endif
return 0;
}
static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin)
{
size_t size = 0;
#ifdef CONFIG_TCP_MD5SIG
if (net_admin && sk_fullsock(sk)) {
const struct tcp_md5sig_info *md5sig;
const struct tcp_md5sig_key *key;
size_t md5sig_count = 0;
rcu_read_lock();
md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info);
if (md5sig) {
hlist_for_each_entry_rcu(key, &md5sig->head, node)
md5sig_count++;
}
rcu_read_unlock();
size += nla_total_size(md5sig_count *
sizeof(struct tcp_diag_md5sig));
}
#endif
return size;
}
static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
const struct inet_diag_req_v2 *r, struct nlattr *bc)
{
inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc);
}
static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req);
}
#ifdef CONFIG_INET_DIAG_DESTROY
static int tcp_diag_destroy(struct sk_buff *in_skb,
const struct inet_diag_req_v2 *req)
{
struct net *net = sock_net(in_skb->sk);
struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req);
int err;
if (IS_ERR(sk))
return PTR_ERR(sk);
err = sock_diag_destroy(sk, ECONNABORTED);
sock_gen_put(sk);
return err;
}
#endif
static const struct inet_diag_handler tcp_diag_handler = {
.dump = tcp_diag_dump,
.dump_one = tcp_diag_dump_one,
.idiag_get_info = tcp_diag_get_info,
.idiag_get_aux = tcp_diag_get_aux,
.idiag_get_aux_size = tcp_diag_get_aux_size,
.idiag_type = IPPROTO_TCP,
.idiag_info_size = sizeof(struct tcp_info),
#ifdef CONFIG_INET_DIAG_DESTROY
.destroy = tcp_diag_destroy,
#endif
};
static int __init tcp_diag_init(void)
{
return inet_diag_register(&tcp_diag_handler);
}
static void __exit tcp_diag_exit(void)
{
inet_diag_unregister(&tcp_diag_handler);
}
module_init(tcp_diag_init);
module_exit(tcp_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */);