[PATCH bpf-next v2 02/11] net, sk_msg: Annotate lockless access to sk_prot on clone

[Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>]

sk_msg and ULP frameworks override protocol callbacks pointer in
sk->sk_prot, while TCP accesses it locklessly when cloning the listening
socket.

Once we enable use of listening sockets with sockmap (and hence sk_msg),
there can be shared access to sk->sk_prot if socket is getting cloned while
being inserted/deleted to/from the sockmap from another CPU. Mark the
shared access with READ_ONCE/WRITE_ONCE annotations.

Signed-off-by: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
---
 include/linux/skmsg.h | 2 +-
 net/core/sock.c       | 5 +++--
 net/ipv4/tcp_bpf.c    | 2 +-
 net/ipv4/tcp_ulp.c    | 2 +-
 net/tls/tls_main.c    | 2 +-
 5 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 41ea1258d15e..d2d39d108354 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -352,7 +352,7 @@ static inline void sk_psock_update_proto(struct sock *sk,
 	psock->saved_write_space = sk->sk_write_space;
 
 	psock->sk_proto = sk->sk_prot;
-	sk->sk_prot = ops;
+	WRITE_ONCE(sk->sk_prot, ops);
 }
 
 static inline void sk_psock_restore_proto(struct sock *sk,
diff --git a/net/core/sock.c b/net/core/sock.c
index 8459ad579f73..96b4e8820ae8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1792,16 +1792,17 @@ static void sk_init_common(struct sock *sk)
  */
 struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 {
+	struct proto *prot = READ_ONCE(sk->sk_prot);
 	struct sock *newsk;
 	bool is_charged = true;
 
-	newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family);
+	newsk = sk_prot_alloc(prot, priority, sk->sk_family);
 	if (newsk != NULL) {
 		struct sk_filter *filter;
 
 		sock_copy(newsk, sk);
 
-		newsk->sk_prot_creator = sk->sk_prot;
+		newsk->sk_prot_creator = prot;
 
 		/* SANITY */
 		if (likely(newsk->sk_net_refcnt))
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index e38705165ac9..e6ffdb47b619 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -649,7 +649,7 @@ static void tcp_bpf_reinit_sk_prot(struct sock *sk, struct sk_psock *psock)
 	 * or added requiring sk_prot hook updates. We keep original saved
 	 * hooks in this case.
 	 */
-	sk->sk_prot = &tcp_bpf_prots[family][config];
+	WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]);
 }
 
 static int tcp_bpf_assert_proto_ops(struct proto *ops)
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 12ab5db2b71c..211af9759732 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -104,7 +104,7 @@ void tcp_update_ulp(struct sock *sk, struct proto *proto)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (!icsk->icsk_ulp_ops) {
-		sk->sk_prot = proto;
+		WRITE_ONCE(sk->sk_prot, proto);
 		return;
 	}
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index dac24c7aa7d4..d466b43c7eb6 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -740,7 +740,7 @@ static void tls_update(struct sock *sk, struct proto *p)
 	if (likely(ctx))
 		ctx->sk_proto = p;
 	else
-		sk->sk_prot = p;
+		WRITE_ONCE(sk->sk_prot, p);
 }
 
 static int tls_get_info(const struct sock *sk, struct sk_buff *skb)
-- 
2.24.1