Merge branch 'bpf-fix-wrong-copied_seq-calculation-and-add-tests'

Jiayuan Chen says:

====================
A previous commit described in this topic
http://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com
directly updated 'sk->copied_seq' in the tcp_eat_skb() function when the
action of a BPF program was SK_REDIRECT. For other actions, like SK_PASS,
the update logic for 'sk->copied_seq' was moved to
tcp_bpf_recvmsg_parser() to ensure the accuracy of the 'fionread' feature.

That commit works for a single stream_verdict scenario, as it also
modified 'sk_data_ready->sk_psock_verdict_data_ready->tcp_read_skb'
to remove updating 'sk->copied_seq'.

However, for programs where both stream_parser and stream_verdict are
active (strparser purpose), tcp_read_sock() was used instead of
tcp_read_skb() (sk_data_ready->strp_data_ready->tcp_read_sock).
tcp_read_sock() now still updates 'sk->copied_seq', leading to duplicated
updates.

In summary, for strparser + SK_PASS, copied_seq is redundantly calculated
in both tcp_read_sock() and tcp_bpf_recvmsg_parser().

The issue causes incorrect copied_seq calculations, which prevent
correct data reads from the recv() interface in user-land.

Also we added test cases for bpf + strparser and separated them from
sockmap_basic, as strparser has more encapsulation and parsing
capabilities compared to sockmap.
====================

Link: https://patch.msgid.link/20250122100917.49845-1-mrpre@163.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

5 files changed, 80 insertions, 8 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 61f3f3d4e528..0ddc4c718833 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -549,6 +549,9 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 			return num_sge;
 	}
 
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+	psock->ingress_bytes += len;
+#endif
 	copied = len;
 	msg->sg.start = 0;
 	msg->sg.size = copied;
@@ -1144,6 +1147,10 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
 	if (!ret)
 		sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED);
 
+	if (sk_is_tcp(sk)) {
+		psock->strp.cb.read_sock = tcp_bpf_strp_read_sock;
+		psock->copied_seq = tcp_sk(sk)->copied_seq;
+	}
 	return ret;
 }
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index f1b9b3958792..3b0f59d9b4db 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -303,7 +303,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk)
 
 	write_lock_bh(&sk->sk_callback_lock);
 	if (stream_parser && stream_verdict && !psock->saved_data_ready) {
-		ret = sk_psock_init_strp(sk, psock);
+		if (sk_is_tcp(sk))
+			ret = sk_psock_init_strp(sk, psock);
+		else
+			ret = -EOPNOTSUPP;
 		if (ret) {
 			write_unlock_bh(&sk->sk_callback_lock);
 			sk_psock_put(sk, psock);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0d704bda6c41..285678d8ce07 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1565,12 +1565,13 @@ EXPORT_SYMBOL(tcp_recv_skb);
  *	  or for 'peeking' the socket using this routine
  *	  (although both would be easy to implement).
  */
-int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
-		  sk_read_actor_t recv_actor)
+static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+			   sk_read_actor_t recv_actor, bool noack,
+			   u32 *copied_seq)
 {
 	struct sk_buff *skb;
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 seq = tp->copied_seq;
+	u32 seq = *copied_seq;
 	u32 offset;
 	int copied = 0;
 
@@ -1624,9 +1625,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		tcp_eat_recv_skb(sk, skb);
 		if (!desc->count)
 			break;
-		WRITE_ONCE(tp->copied_seq, seq);
+		WRITE_ONCE(*copied_seq, seq);
 	}
-	WRITE_ONCE(tp->copied_seq, seq);
+	WRITE_ONCE(*copied_seq, seq);
+
+	if (noack)
+		goto out;
 
 	tcp_rcv_space_adjust(sk);
 
@@ -1635,10 +1639,25 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		tcp_recv_skb(sk, seq, &offset);
 		tcp_cleanup_rbuf(sk, copied);
 	}
+out:
 	return copied;
 }
+
+int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+		  sk_read_actor_t recv_actor)
+{
+	return __tcp_read_sock(sk, desc, recv_actor, false,
+			       &tcp_sk(sk)->copied_seq);
+}
 EXPORT_SYMBOL(tcp_read_sock);
 
+int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
+			sk_read_actor_t recv_actor, bool noack,
+			u32 *copied_seq)
+{
+	return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq);
+}
+
 int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
 	struct sk_buff *skb;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 47f65b1b70ca..ba581785adb4 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -646,6 +646,42 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
 	       ops->sendmsg  == tcp_sendmsg ? 0 : -ENOTSUPP;
 }
 
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc,
+			   sk_read_actor_t recv_actor)
+{
+	struct sock *sk = strp->sk;
+	struct sk_psock *psock;
+	struct tcp_sock *tp;
+	int copied = 0;
+
+	tp = tcp_sk(sk);
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (WARN_ON_ONCE(!psock)) {
+		desc->error = -EINVAL;
+		goto out;
+	}
+
+	psock->ingress_bytes = 0;
+	copied = tcp_read_sock_noack(sk, desc, recv_actor, true,
+				     &psock->copied_seq);
+	if (copied < 0)
+		goto out;
+	/* recv_actor may redirect skb to another socket (SK_REDIRECT) or
+	 * just put skb into ingress queue of current socket (SK_PASS).
+	 * For SK_REDIRECT, we need to ack the frame immediately but for
+	 * SK_PASS, we want to delay the ack until tcp_bpf_recvmsg_parser().
+	 */
+	tp->copied_seq = psock->copied_seq - psock->ingress_bytes;
+	tcp_rcv_space_adjust(sk);
+	__tcp_cleanup_rbuf(sk, copied - psock->ingress_bytes);
+out:
+	rcu_read_unlock();
+	return copied;
+}
+#endif /* CONFIG_BPF_STREAM_PARSER */
+
 int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 {
 	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 8299ceb3e373..95696f42647e 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -347,7 +347,10 @@ static int strp_read_sock(struct strparser *strp)
 	struct socket *sock = strp->sk->sk_socket;
 	read_descriptor_t desc;
 
-	if (unlikely(!sock || !sock->ops || !sock->ops->read_sock))
+	if (unlikely(!sock || !sock->ops))
+		return -EBUSY;
+
+	if (unlikely(!strp->cb.read_sock && !sock->ops->read_sock))
 		return -EBUSY;
 
 	desc.arg.data = strp;
@@ -355,7 +358,10 @@ static int strp_read_sock(struct strparser *strp)
 	desc.count = 1; /* give more than one skb per call */
 
 	/* sk should be locked here, so okay to do read_sock */
-	sock->ops->read_sock(strp->sk, &desc, strp_recv);
+	if (strp->cb.read_sock)
+		strp->cb.read_sock(strp, &desc, strp_recv);
+	else
+		sock->ops->read_sock(strp->sk, &desc, strp_recv);
 
 	desc.error = strp->cb.read_sock_done(strp, desc.error);
 
@@ -468,6 +474,7 @@ int strp_init(struct strparser *strp, struct sock *sk,
 	strp->cb.unlock = cb->unlock ? : strp_sock_unlock;
 	strp->cb.rcv_msg = cb->rcv_msg;
 	strp->cb.parse_msg = cb->parse_msg;
+	strp->cb.read_sock = cb->read_sock;
 	strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done;
 	strp->cb.abort_parser = cb->abort_parser ? : strp_abort_strp;