tcp: add annotations around sk->sk_shutdown accesses

Now sk->sk_shutdown is no longer a bitfield, we can add
standard READ_ONCE()/WRITE_ONCE() annotations to silence
KCSAN reports like the following:

BUG: KCSAN: data-race in tcp_disconnect / tcp_poll

write to 0xffff88814588582c of 1 bytes by task 3404 on cpu 1:
tcp_disconnect+0x4d6/0xdb0 net/ipv4/tcp.c:3121
__inet_stream_connect+0x5dd/0x6e0 net/ipv4/af_inet.c:715
inet_stream_connect+0x48/0x70 net/ipv4/af_inet.c:727
__sys_connect_file net/socket.c:2001 [inline]
__sys_connect+0x19b/0x1b0 net/socket.c:2018
__do_sys_connect net/socket.c:2028 [inline]
__se_sys_connect net/socket.c:2025 [inline]
__x64_sys_connect+0x41/0x50 net/socket.c:2025
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 0xffff88814588582c of 1 bytes by task 3374 on cpu 0:
tcp_poll+0x2e6/0x7d0 net/ipv4/tcp.c:562
sock_poll+0x253/0x270 net/socket.c:1383
vfs_poll include/linux/poll.h:88 [inline]
io_poll_check_events io_uring/poll.c:281 [inline]
io_poll_task_func+0x15a/0x820 io_uring/poll.c:333
handle_tw_list io_uring/io_uring.c:1184 [inline]
tctx_task_work+0x1fe/0x4d0 io_uring/io_uring.c:1246
task_work_run+0x123/0x160 kernel/task_work.c:179
get_signal+0xe64/0xff0 kernel/signal.c:2635
arch_do_signal_or_restart+0x89/0x2a0 arch/x86/kernel/signal.c:306
exit_to_user_mode_loop+0x6f/0xe0 kernel/entry/common.c:168
exit_to_user_mode_prepare+0x6c/0xb0 kernel/entry/common.c:204
__syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline]
syscall_exit_to_user_mode+0x26/0x140 kernel/entry/common.c:297
do_syscall_64+0x4d/0xc0 arch/x86/entry/common.c:86
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x03 -> 0x00

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 940062e08f574fbfeed42f72fa8a4b5ce763110c..c4aab3aacbd89e35520583ab5e17b4e15e53b87e 100644 (file)
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -894,7 +894,7 @@ int inet_shutdown(struct socket *sock, int how)
                   EPOLLHUP, even on eg. unconnected UDP sockets -- RR */
                fallthrough;
        default:
-               sk->sk_shutdown |= how;
+               WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how);
                if (sk->sk_prot->shutdown)
                        sk->sk_prot->shutdown(sk, how);
                break;

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 20db115c38c492c010733d5a0a3efbb7dbbea13e..4d6392c16b7a5a9a853c27e3a4b258d000738304 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -498,6 +498,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
        __poll_t mask;
        struct sock *sk = sock->sk;
        const struct tcp_sock *tp = tcp_sk(sk);
+       u8 shutdown;
        int state;
 
        sock_poll_wait(file, sock, wait);
@@ -540,9 +541,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
         * NOTE. Check for TCP_CLOSE is added. The goal is to prevent
         * blocking on fresh not-connected or disconnected socket. --ANK
         */
-       if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
+       shutdown = READ_ONCE(sk->sk_shutdown);
+       if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
                mask |= EPOLLHUP;
-       if (sk->sk_shutdown & RCV_SHUTDOWN)
+       if (shutdown & RCV_SHUTDOWN)
                mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
 
        /* Connected or passive Fast Open socket? */
@@ -559,7 +561,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
                if (tcp_stream_is_readable(sk, target))
                        mask |= EPOLLIN | EPOLLRDNORM;
 
-               if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+               if (!(shutdown & SEND_SHUTDOWN)) {
                        if (__sk_stream_is_writeable(sk, 1)) {
                                mask |= EPOLLOUT | EPOLLWRNORM;
                        } else {  /* send SIGIO later */
@@ -2867,7 +2869,7 @@ void __tcp_close(struct sock *sk, long timeout)
        int data_was_unread = 0;
        int state;
 
-       sk->sk_shutdown = SHUTDOWN_MASK;
+       WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
        if (sk->sk_state == TCP_LISTEN) {
                tcp_set_state(sk, TCP_CLOSE);
@@ -3119,7 +3121,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
        inet_bhash2_reset_saddr(sk);
 
-       sk->sk_shutdown = 0;
+       WRITE_ONCE(sk->sk_shutdown, 0);
        sock_reset_flag(sk, SOCK_DONE);
        tp->srtt_us = 0;
        tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
@@ -4649,7 +4651,7 @@ void tcp_done(struct sock *sk)
        if (req)
                reqsk_fastopen_remove(sk, req, false);
 
-       sk->sk_shutdown = SHUTDOWN_MASK;
+       WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
        if (!sock_flag(sk, SOCK_DEAD))
                sk->sk_state_change(sk);

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a057330d6f59d693cdf634dbd22f1243f8171f58..61b6710f337a3a5c24b3f399cc77a404b7e012f9 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4362,7 +4362,7 @@ void tcp_fin(struct sock *sk)
 
        inet_csk_schedule_ack(sk);
 
-       sk->sk_shutdown |= RCV_SHUTDOWN;
+       WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
        sock_set_flag(sk, SOCK_DONE);
 
        switch (sk->sk_state) {
@@ -6599,7 +6599,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
                        break;
 
                tcp_set_state(sk, TCP_FIN_WAIT2);
-               sk->sk_shutdown |= SEND_SHUTDOWN;
+               WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN);
 
                sk_dst_confirm(sk);