Re: [PATCH mptcp-next v14 6/8] mptcp: implement .splice_read

[Mat Martineau <martineau@kernel.org>]

On Mon, 24 Nov 2025, Geliang Tang wrote:

> From: Geliang Tang <tanggeliang@kylinos.cn>
>
> This patch implements .splice_read interface of mptcp struct proto_ops
> as mptcp_splice_read() with reference to tcp_splice_read().
>
> Corresponding to __tcp_splice_read(), __mptcp_splice_read() is defined,
> invoking mptcp_read_sock() instead of tcp_read_sock().
>
> mptcp_splice_read() is almost the same as tcp_splice_read(), except for
> sock_rps_record_flow().
>
> Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
> ---
> net/mptcp/protocol.c | 96 ++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 96 insertions(+)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index 9302b372910e..abd0f44ad63f 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -4355,6 +4355,100 @@ static int mptcp_read_sock(struct sock *sk, read_descriptor_t *desc,
> 	return __mptcp_read_sock(sk, desc, recv_actor, false);
> }
>
> +static int __mptcp_splice_read(struct sock *sk, struct tcp_splice_state *tss)
> +{
> +	/* Store TCP splice context information in read_descriptor_t. */
> +	read_descriptor_t rd_desc = {
> +		.arg.data = tss,
> +		.count	  = tss->len,
> +	};
> +
> +	return mptcp_read_sock(sk, &rd_desc, tcp_splice_data_recv);
> +}
> +
> +/**
> + *  mptcp_splice_read - splice data from MPTCP socket to a pipe
> + * @sock:	socket to splice from
> + * @ppos:	position (not valid)
> + * @pipe:	pipe to splice to
> + * @len:	number of bytes to splice
> + * @flags:	splice modifier flags
> + *
> + * Description:
> + *    Will read pages from given socket and fill them into a pipe.
> + *
> + **/
> +static ssize_t mptcp_splice_read(struct socket *sock, loff_t *ppos,
> +				 struct pipe_inode_info *pipe, size_t len,
> +				 unsigned int flags)
> +{
> +	struct tcp_splice_state tss = {
> +		.pipe	= pipe,
> +		.len	= len,
> +		.flags	= flags,
> +	};
> +	struct sock *sk = sock->sk;
> +	ssize_t spliced = 0;
> +	int ret = 0;
> +	long timeo;
> +
> +	/*
> +	 * We can't seek on a socket input
> +	 */
> +	if (unlikely(*ppos))
> +		return -ESPIPE;
> +
> +	lock_sock(sk);
> +
> +	mptcp_rps_record_subflows(mptcp_sk(sk));
> +
> +	timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK);
> +	while (tss.len) {
> +		ret = __mptcp_splice_read(sk, &tss);
> +		if (ret < 0) {
> +			break;
> +		} else if (!ret) {
> +			int err;
> +
> +			if (spliced)
> +				break;
> +			err = tcp_recv_should_stop(sk, timeo);
> +			if (err < 0) {
> +				if (err != -ESHUTDOWN)
> +					ret = err;
> +				break;
> +			}
> +			/* if __mptcp_splice_read() got nothing while we have
> +			 * an skb in receive queue, we do not want to loop.
> +			 * This might happen with URG data.
> +			 */
> +			if (!skb_queue_empty(&sk->sk_receive_queue))
> +				break;

Hi Geliang -

This queue could also be non-empty due to the length limit in patch 2. 
Maybe another reason to remove that length limit.


- Mat


> +			ret = sk_wait_data(sk, &timeo, NULL);
> +			if (ret < 0)
> +				break;
> +			continue;
> +		}
> +		tss.len -= ret;
> +		spliced += ret;
> +
> +		if (!tss.len || !timeo)
> +			break;
> +		release_sock(sk);
> +		lock_sock(sk);
> +
> +		if (tcp_recv_should_stop(sk, timeo))
> +			break;
> +	}
> +
> +	release_sock(sk);
> +
> +	if (spliced)
> +		return spliced;
> +
> +	return ret;
> +}
> +
> static const struct proto_ops mptcp_stream_ops = {
> 	.family		   = PF_INET,
> 	.owner		   = THIS_MODULE,
> @@ -4376,6 +4470,7 @@ static const struct proto_ops mptcp_stream_ops = {
> 	.mmap		   = sock_no_mmap,
> 	.set_rcvlowat	   = mptcp_set_rcvlowat,
> 	.read_sock	   = mptcp_read_sock,
> +	.splice_read	   = mptcp_splice_read,
> };
>
> static struct inet_protosw mptcp_protosw = {
> @@ -4481,6 +4576,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
> #endif
> 	.set_rcvlowat	   = mptcp_set_rcvlowat,
> 	.read_sock	   = mptcp_read_sock,
> +	.splice_read	   = mptcp_splice_read,
> };
>
> static struct proto mptcp_v6_prot;
> -- 
> 2.43.0
>
>
>