From: Geliang Tang <tanggeliang@kylinos.cn>

nvme_tcp_try_recv() needs to call .read_sock interface of struct
proto_ops, but it's not implemented in MPTCP.

This patch implements it with reference to __tcp_read_sock() and
__mptcp_recvmsg_mskq().

Corresponding to tcp_recv_skb(), a new helper for MPTCP named
mptcp_recv_skb() is added to peek a skb from sk->sk_receive_queue.

Compared with __mptcp_recvmsg_mskq(), mptcp_read_sock() uses
sk->sk_rcvbuf as the max read length. The LISTEN status is checked
before the while loop, and mptcp_recv_skb() and mptcp_cleanup_rbuf()
are invoked after the loop. In the loop, all flags checks for
__mptcp_recvmsg_mskq() are removed.

Reviewed-by: Hannes Reinecke <hare@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/protocol.c | 74 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index df82584a6f7a..f55185410e5b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -4039,6 +4039,78 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	return mask;
 }
 
+static struct sk_buff *mptcp_recv_skb(struct sock *sk, u32 *off)
+{
+	struct sk_buff *skb;
+	u32 offset;
+
+	if (skb_queue_empty(&sk->sk_receive_queue))
+		__mptcp_move_skbs(sk);
+
+	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
+		offset = MPTCP_SKB_CB(skb)->offset;
+		if (offset < skb->len) {
+			*off = offset;
+			return skb;
+		}
+		mptcp_eat_recv_skb(sk, skb);
+	}
+	return NULL;
+}
+
+/*
+ * Note:
+ *	- It is assumed that the socket was locked by the caller.
+ */
+static int mptcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+			   sk_read_actor_t recv_actor)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	size_t len = sk->sk_rcvbuf;
+	struct sk_buff *skb;
+	int copied = 0;
+	u32 offset;
+
+	if (sk->sk_state == TCP_LISTEN)
+		return -ENOTCONN;
+	while ((skb = mptcp_recv_skb(sk, &offset)) != NULL) {
+		u32 data_len = skb->len - offset;
+		u32 size = min_t(size_t, len - copied, data_len);
+		int count;
+
+		count = recv_actor(desc, skb, offset, size);
+		if (count <= 0) {
+			if (!copied)
+				copied = count;
+			break;
+		}
+
+		copied += count;
+
+		if (count < data_len) {
+			MPTCP_SKB_CB(skb)->offset += count;
+			MPTCP_SKB_CB(skb)->map_seq += count;
+			msk->bytes_consumed += count;
+			break;
+		}
+
+		mptcp_eat_recv_skb(sk, skb);
+		msk->bytes_consumed += count;
+
+		if (copied >= len)
+			break;
+	}
+
+	mptcp_rcv_space_adjust(msk, copied);
+
+	if (copied > 0) {
+		mptcp_recv_skb(sk, &offset);
+		mptcp_cleanup_rbuf(msk, copied);
+	}
+
+	return copied;
+}
+
 static const struct proto_ops mptcp_stream_ops = {
 	.family		   = PF_INET,
 	.owner		   = THIS_MODULE,
@@ -4059,6 +4131,7 @@ static const struct proto_ops mptcp_stream_ops = {
 	.recvmsg	   = inet_recvmsg,
 	.mmap		   = sock_no_mmap,
 	.set_rcvlowat	   = mptcp_set_rcvlowat,
+	.read_sock	   = mptcp_read_sock,
 };
 
 static struct inet_protosw mptcp_protosw = {
@@ -4163,6 +4236,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
 	.compat_ioctl	   = inet6_compat_ioctl,
 #endif
 	.set_rcvlowat	   = mptcp_set_rcvlowat,
+	.read_sock	   = mptcp_read_sock,
 };
 
 static struct proto mptcp_v6_prot;
-- 
2.48.1