net: annotate data-races around sock->ops

IPV6_ADDRFORM socket option is evil, because it can change sock->ops
while other threads might read it. Same issue for sk->sk_family
being set to AF_INET.

Adding READ_ONCE() over sock->ops reads is needed for sockets
that might be impacted by IPV6_ADDRFORM.

Note that mptcp_is_tcpsk() can also overwrite sock->ops.

Adding annotations for all sk->sk_family reads will require
more patches :/

BUG: KCSAN: data-race in ____sys_sendmsg / do_ipv6_setsockopt

write to 0xffff888109f24ca0 of 8 bytes by task 4470 on cpu 0:
do_ipv6_setsockopt+0x2c5e/0x2ce0 net/ipv6/ipv6_sockglue.c:491
ipv6_setsockopt+0x57/0x130 net/ipv6/ipv6_sockglue.c:1012
udpv6_setsockopt+0x95/0xa0 net/ipv6/udp.c:1690
sock_common_setsockopt+0x61/0x70 net/core/sock.c:3663
__sys_setsockopt+0x1c3/0x230 net/socket.c:2273
__do_sys_setsockopt net/socket.c:2284 [inline]
__se_sys_setsockopt net/socket.c:2281 [inline]
__x64_sys_setsockopt+0x66/0x80 net/socket.c:2281
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 0xffff888109f24ca0 of 8 bytes by task 4469 on cpu 1:
sock_sendmsg_nosec net/socket.c:724 [inline]
sock_sendmsg net/socket.c:747 [inline]
____sys_sendmsg+0x349/0x4c0 net/socket.c:2503
___sys_sendmsg net/socket.c:2557 [inline]
__sys_sendmmsg+0x263/0x500 net/socket.c:2643
__do_sys_sendmmsg net/socket.c:2672 [inline]
__se_sys_sendmmsg net/socket.c:2669 [inline]
__x64_sys_sendmmsg+0x57/0x60 net/socket.c:2669
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: 0xffffffff850e32b8 -> 0xffffffff850da890

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 4469 Comm: syz-executor.1 Not tainted 6.4.0-rc5-syzkaller-00313-g4c605260bc60 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230808135809.2300241-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 25 insertions, 10 deletions

diff --git a/net/core/scm.c b/net/core/scm.c
index 3cd7dd377e53..880027ecf516 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -130,6 +130,7 @@ EXPORT_SYMBOL(__scm_destroy);
 
 int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
 {
+	const struct proto_ops *ops = READ_ONCE(sock->ops);
 	struct cmsghdr *cmsg;
 	int err;
 
@@ -153,7 +154,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
 		switch (cmsg->cmsg_type)
 		{
 		case SCM_RIGHTS:
-			if (!sock->ops || sock->ops->family != PF_UNIX)
+			if (!ops || ops->family != PF_UNIX)
 				goto error;
 			err=scm_fp_copy(cmsg, &p->fp);
 			if (err<0)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index a29508e1ff35..e6dfc846018f 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1198,13 +1198,17 @@ out:
 static void sk_psock_verdict_data_ready(struct sock *sk)
 {
 	struct socket *sock = sk->sk_socket;
+	const struct proto_ops *ops;
 	int copied;
 
 	trace_sk_data_ready(sk);
 
-	if (unlikely(!sock || !sock->ops || !sock->ops->read_skb))
+	if (unlikely(!sock))
 		return;
-	copied = sock->ops->read_skb(sk, sk_psock_verdict_recv);
+	ops = READ_ONCE(sock->ops);
+	if (!ops || !ops->read_skb)
+		return;
+	copied = ops->read_skb(sk, sk_psock_verdict_recv);
 	if (copied >= 0) {
 		struct sk_psock *psock;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 49915801d53a..51f7d94eccf7 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1277,14 +1277,19 @@ set_sndbuf:
 		break;
 
 	case SO_RCVLOWAT:
+		{
+		int (*set_rcvlowat)(struct sock *sk, int val) = NULL;
+
 		if (val < 0)
 			val = INT_MAX;
-		if (sock && sock->ops->set_rcvlowat)
-			ret = sock->ops->set_rcvlowat(sk, val);
+		if (sock)
+			set_rcvlowat = READ_ONCE(sock->ops)->set_rcvlowat;
+		if (set_rcvlowat)
+			ret = set_rcvlowat(sk, val);
 		else
 			WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 		break;
-
+		}
 	case SO_RCVTIMEO_OLD:
 	case SO_RCVTIMEO_NEW:
 		ret = sock_set_timeout(&sk->sk_rcvtimeo, optval,
@@ -1379,11 +1384,16 @@ set_sndbuf:
 		break;
 
 	case SO_PEEK_OFF:
-		if (sock->ops->set_peek_off)
-			ret = sock->ops->set_peek_off(sk, val);
+		{
+		int (*set_peek_off)(struct sock *sk, int val);
+
+		set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
+		if (set_peek_off)
+			ret = set_peek_off(sk, val);
 		else
 			ret = -EOPNOTSUPP;
 		break;
+		}
 
 	case SO_NOFCS:
 		sock_valbool_flag(sk, SOCK_NOFCS, valbool);
@@ -1816,7 +1826,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 	{
 		struct sockaddr_storage address;
 
-		lv = sock->ops->getname(sock, (struct sockaddr *)&address, 2);
+		lv = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 2);
 		if (lv < 0)
 			return -ENOTCONN;
 		if (lv < len)
@@ -1858,7 +1868,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_PEEK_OFF:
-		if (!sock->ops->set_peek_off)
+		if (!READ_ONCE(sock->ops)->set_peek_off)
 			return -EOPNOTSUPP;
 
 		v.val = READ_ONCE(sk->sk_peek_off);