netlink: annotate accesses to nlk->cb_running

Both netlink_recvmsg() and netlink_native_seq_show() read
nlk->cb_running locklessly. Use READ_ONCE() there.

Add corresponding WRITE_ONCE() to netlink_dump() and
__netlink_dump_start()

syzbot reported:
BUG: KCSAN: data-race in __netlink_dump_start / netlink_recvmsg

write to 0xffff88813ea4db59 of 1 bytes by task 28219 on cpu 0:
__netlink_dump_start+0x3af/0x4d0 net/netlink/af_netlink.c:2399
netlink_dump_start include/linux/netlink.h:308 [inline]
rtnetlink_rcv_msg+0x70f/0x8c0 net/core/rtnetlink.c:6130
netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2577
rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6192
netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline]
netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365
netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1942
sock_sendmsg_nosec net/socket.c:724 [inline]
sock_sendmsg net/socket.c:747 [inline]
sock_write_iter+0x1aa/0x230 net/socket.c:1138
call_write_iter include/linux/fs.h:1851 [inline]
new_sync_write fs/read_write.c:491 [inline]
vfs_write+0x463/0x760 fs/read_write.c:584
ksys_write+0xeb/0x1a0 fs/read_write.c:637
__do_sys_write fs/read_write.c:649 [inline]
__se_sys_write fs/read_write.c:646 [inline]
__x64_sys_write+0x42/0x50 fs/read_write.c:646
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 0xffff88813ea4db59 of 1 bytes by task 28222 on cpu 1:
netlink_recvmsg+0x3b4/0x730 net/netlink/af_netlink.c:2022
sock_recvmsg_nosec+0x4c/0x80 net/socket.c:1017
____sys_recvmsg+0x2db/0x310 net/socket.c:2718
___sys_recvmsg net/socket.c:2762 [inline]
do_recvmmsg+0x2e5/0x710 net/socket.c:2856
__sys_recvmmsg net/socket.c:2935 [inline]
__do_sys_recvmmsg net/socket.c:2958 [inline]
__se_sys_recvmmsg net/socket.c:2951 [inline]
__x64_sys_recvmmsg+0xe2/0x160 net/socket.c:2951
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: 0x00 -> 0x01

Fixes: 16b304f3 ("netlink: Eliminate kmalloc in netlink dump operation.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/netlink/af_netlink.c

@@ -1990,7 +1990,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	skb_free_datagram(sk, skb);
 
-	if (nlk->cb_running &&
+	if (READ_ONCE(nlk->cb_running) &&
 	    atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
 		ret = netlink_dump(sk);
 		if (ret) {
@@ -2302,7 +2302,7 @@ static int netlink_dump(struct sock *sk)
 	if (cb->done)
 		cb->done(cb);
 
-	nlk->cb_running = false;
+	WRITE_ONCE(nlk->cb_running, false);
 	module = cb->module;
 	skb = cb->skb;
 	mutex_unlock(nlk->cb_mutex);
@@ -2365,7 +2365,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 			goto error_put;
 	}
 
-	nlk->cb_running = true;
+	WRITE_ONCE(nlk->cb_running, true);
 	nlk->dump_done_errno = INT_MAX;
 
 	mutex_unlock(nlk->cb_mutex);
@@ -2703,7 +2703,7 @@ static int netlink_native_seq_show(struct seq_file *seq, void *v)
 			   nlk->groups ? (u32)nlk->groups[0] : 0,
 			   sk_rmem_alloc_get(s),
 			   sk_wmem_alloc_get(s),
-			   nlk->cb_running,
+			   READ_ONCE(nlk->cb_running),
 			   refcount_read(&s->sk_refcnt),
 			   atomic_read(&s->sk_drops),
 			   sock_i_ino(s)