bpf: Fix wrong copied_seq calculation

'sk->copied_seq' was updated 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.

It 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 duplicate
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.

We do not want to add new proto_ops to implement a new version of
tcp_read_sock, as this would introduce code complexity [1].

We could have added noack and copied_seq to desc, and then called
ops->read_sock. However, unfortunately, other modules didn’t fully
initialize desc to zero. So, for now, we are directly calling
tcp_read_sock_noack() in tcp_bpf.c.

[1]: https://lore.kernel.org/bpf/[email protected]

Fixes: e5c6de5 ("bpf, sockmap: Incorrectly handling copied_seq")
Suggested-by: Jakub Sitnicki <[email protected]>
Signed-off-by: Jiayuan Chen <[email protected]>
Signed-off-by: Martin KaFai Lau <[email protected]>
Reviewed-by: Jakub Sitnicki <[email protected]>
Acked-by: John Fastabend <[email protected]>
Link: https://patch.msgid.link/[email protected]

Author: mrpre

include/linux/skmsg.h

@@ -91,6 +91,8 @@ struct sk_psock {
 	struct sk_psock_progs		progs;
 #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 	struct strparser		strp;
+	u32				copied_seq;
+	u32				ingress_bytes;
 #endif
 	struct sk_buff_head		ingress_skb;
 	struct list_head		ingress_msg;

include/net/tcp.h

@@ -729,6 +729,9 @@ void tcp_get_info(struct sock *, struct tcp_info *);
 /* Read 'sendfile()'-style from a TCP socket */
 int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		  sk_read_actor_t recv_actor);
+int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
+			sk_read_actor_t recv_actor, bool noack,
+			u32 *copied_seq);
 int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
 struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off);
 void tcp_read_done(struct sock *sk, size_t len);
@@ -2599,6 +2602,11 @@ struct sk_psock;
 #ifdef CONFIG_BPF_SYSCALL
 int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
 void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
+#ifdef CONFIG_BPF_STREAM_PARSER
+struct strparser;
+int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc,
+			   sk_read_actor_t recv_actor);
+#endif /* CONFIG_BPF_STREAM_PARSER */
 #endif /* CONFIG_BPF_SYSCALL */
 
 #ifdef CONFIG_INET

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;
 }
 

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;

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;