diff mbox series

[bpf-next,v6,04/12] tcp_bpf: Don't let child socket inherit parent protocol ops on copy

Message ID 20200127131057.150941-5-jakub@cloudflare.com
State Awaiting Upstream
Delegated to: BPF Maintainers
Headers show
Series Extend SOCKMAP to store listening sockets | expand

Commit Message

Jakub Sitnicki Jan. 27, 2020, 1:10 p.m. UTC
Prepare for cloning listening sockets that have their protocol callbacks
overridden by sk_msg. Child sockets must not inherit parent callbacks that
access state stored in sk_user_data owned by the parent.

Restore the child socket protocol callbacks before it gets hashed and any
of the callbacks can get invoked.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
---
 include/net/tcp.h        |  7 +++++++
 net/ipv4/tcp_bpf.c       | 13 +++++++++++++
 net/ipv4/tcp_minisocks.c |  2 ++
 3 files changed, 22 insertions(+)
diff mbox series

Patch

diff --git a/include/net/tcp.h b/include/net/tcp.h
index a5ea27df3c2b..07f947cc80e6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2203,6 +2203,13 @@  int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len);
 int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 		      struct msghdr *msg, int len, int flags);
+#ifdef CONFIG_NET_SOCK_MSG
+void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
+#else
+static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
+{
+}
+#endif
 
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index dd183b050642..c0439c015341 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -579,6 +579,19 @@  static void tcp_bpf_close(struct sock *sk, long timeout)
 	saved_close(sk, timeout);
 }
 
+/* If a child got cloned from a listening socket that had tcp_bpf
+ * protocol callbacks installed, we need to restore the callbacks to
+ * the default ones because the child does not inherit the psock state
+ * that tcp_bpf callbacks expect.
+ */
+void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
+{
+	struct proto *prot = newsk->sk_prot;
+
+	if (prot->unhash == tcp_bpf_unhash)
+		newsk->sk_prot = sk->sk_prot_creator;
+}
+
 enum {
 	TCP_BPF_IPV4,
 	TCP_BPF_IPV6,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ad3b56d9fa71..c8274371c3d0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -548,6 +548,8 @@  struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->fastopen_req = NULL;
 	RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
 
+	tcp_bpf_clone(sk, newsk);
+
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
 
 	return newsk;