tcp: Introduce tcp_read_skb()

This patch inroduces tcp_read_skb() based on tcp_read_sock(),
a preparation for the next patch which actually introduces
a new sock ops.

TCP is special here, because it has tcp_read_sock() which is
mainly used by splice(). tcp_read_sock() supports partial read
and arbitrary offset, neither of them is needed for sockmap.

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220615162014.89193-2-xiyou.wangcong@gmail.com

2 files changed, 49 insertions, 0 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c21a9b516f1e..7547d90fbb57 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -672,6 +672,8 @@ 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_skb(struct sock *sk, read_descriptor_t *desc,
+		 sk_read_actor_t recv_actor);
 
 void tcp_initialize_rcv_mss(struct sock *sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f7309452bdce..124f384f8695 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1734,6 +1734,53 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 }
 EXPORT_SYMBOL(tcp_read_sock);
 
+int tcp_read_skb(struct sock *sk, read_descriptor_t *desc,
+		 sk_read_actor_t recv_actor)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 seq = tp->copied_seq;
+	struct sk_buff *skb;
+	int copied = 0;
+	u32 offset;
+
+	if (sk->sk_state == TCP_LISTEN)
+		return -ENOTCONN;
+
+	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
+		int used;
+
+		__skb_unlink(skb, &sk->sk_receive_queue);
+		used = recv_actor(desc, skb, 0, skb->len);
+		if (used <= 0) {
+			if (!copied)
+				copied = used;
+			break;
+		}
+		seq += used;
+		copied += used;
+
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
+			consume_skb(skb);
+			++seq;
+			break;
+		}
+		consume_skb(skb);
+		if (!desc->count)
+			break;
+		WRITE_ONCE(tp->copied_seq, seq);
+	}
+	WRITE_ONCE(tp->copied_seq, seq);
+
+	tcp_rcv_space_adjust(sk);
+
+	/* Clean up data we have read: This will do ACK frames. */
+	if (copied > 0)
+		tcp_cleanup_rbuf(sk, copied);
+
+	return copied;
+}
+EXPORT_SYMBOL(tcp_read_skb);
+
 int tcp_peek_len(struct socket *sock)
 {
 	return tcp_inq(sock->sk);