netlink: annotate lockless accesses to nlk->max_recvmsg_len

syzbot reported a data-race in data-race in netlink_recvmsg() [1]

Indeed, netlink_recvmsg() can be run concurrently,
and netlink_dump() also needs protection.

[1]
BUG: KCSAN: data-race in netlink_recvmsg / netlink_recvmsg

read to 0xffff888141840b38 of 8 bytes by task 23057 on cpu 0:
netlink_recvmsg+0xea/0x730 net/netlink/af_netlink.c:1988
sock_recvmsg_nosec net/socket.c:1017 [inline]
sock_recvmsg net/socket.c:1038 [inline]
__sys_recvfrom+0x1ee/0x2e0 net/socket.c:2194
__do_sys_recvfrom net/socket.c:2212 [inline]
__se_sys_recvfrom net/socket.c:2208 [inline]
__x64_sys_recvfrom+0x78/0x90 net/socket.c:2208
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

write to 0xffff888141840b38 of 8 bytes by task 23037 on cpu 1:
netlink_recvmsg+0x114/0x730 net/netlink/af_netlink.c:1989
sock_recvmsg_nosec net/socket.c:1017 [inline]
sock_recvmsg net/socket.c:1038 [inline]
____sys_recvmsg+0x156/0x310 net/socket.c:2720
___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: 0x0000000000000000 -> 0x0000000000001000

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 23037 Comm: syz-executor.2 Not tainted 6.3.0-rc4-syzkaller-00195-g5a57b48fdfcb #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023

Fixes: 9063e21fb026 ("netlink: autosize skb lengthes")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230403214643.768555-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c642776..f365dfd 100644 (file)
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1952,7 +1952,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
        struct scm_cookie scm;
        struct sock *sk = sock->sk;
        struct netlink_sock *nlk = nlk_sk(sk);
-       size_t copied;
+       size_t copied, max_recvmsg_len;
        struct sk_buff *skb, *data_skb;
        int err, ret;
 
@@ -1985,9 +1985,10 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 #endif
 
        /* Record the max length of recvmsg() calls for future allocations */
-       nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
-       nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
-                                    SKB_WITH_OVERHEAD(32768));
+       max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len);
+       max_recvmsg_len = min_t(size_t, max_recvmsg_len,
+                               SKB_WITH_OVERHEAD(32768));
+       WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len);
 
        copied = data_skb->len;
        if (len < copied) {
@@ -2236,6 +2237,7 @@ static int netlink_dump(struct sock *sk)
        struct netlink_ext_ack extack = {};
        struct netlink_callback *cb;
        struct sk_buff *skb = NULL;
+       size_t max_recvmsg_len;
        struct module *module;
        int err = -ENOBUFS;
        int alloc_min_size;
@@ -2258,8 +2260,9 @@ static int netlink_dump(struct sock *sk)
        cb = &nlk->cb;
        alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
 
-       if (alloc_min_size < nlk->max_recvmsg_len) {
-               alloc_size = nlk->max_recvmsg_len;
+       max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len);
+       if (alloc_min_size < max_recvmsg_len) {
+               alloc_size = max_recvmsg_len;
                skb = alloc_skb(alloc_size,
                                (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) |
                                __GFP_NOWARN | __GFP_NORETRY);