Commit 071c8ed6 authored by Florian Westphal's avatar Florian Westphal Committed by David S. Miller
Browse files

tcp: mptcp: use mptcp receive buffer space to select rcv window 



In MPTCP, the receive window is shared across all subflows, because it
refers to the mptcp-level sequence space.

MPTCP receivers already place incoming packets on the mptcp socket
receive queue and will charge it to the mptcp socket rcvbuf until
userspace consumes the data.

Update __tcp_select_window to use the occupancy of the parent/mptcp
socket instead of the subflow socket in case the tcp socket is part
of a logical mptcp connection.

This commit doesn't change choice of initial window for passive or active
connections.
While it would be possible to change those as well, this adds complexity
(especially when handling MP_JOIN requests).  Furthermore, the MPTCP RFC
specifically says that a MPTCP sender 'MUST NOT use the RCV.WND field
of a TCP segment at the connection level if it does not also carry a DSS
option with a Data ACK field.'

SYN/SYNACK packets do not carry a DSS option with a Data ACK field.

Signed-off-by: default avatarFlorian Westphal <fw@strlen.de>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 460fd830

include/net/mptcp.h

+3 −0
Original line number Diff line number Diff line
@@ -68,6 +68,8 @@ static inline bool rsk_is_mptcp(const struct request_sock *req) 
	return tcp_rsk(req)->is_mptcp;

}



void mptcp_space(const struct sock *ssk, int *space, int *full_space);



void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,

			int opsize, struct tcp_options_received *opt_rx);

bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
@@ -197,6 +199,7 @@ static inline bool mptcp_sk_is_subflow(const struct sock *sk) 
	return false;

}



static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { }

static inline void mptcp_seq_show(struct seq_file *seq) { }

#endif /* CONFIG_MPTCP */

net/ipv4/tcp_output.c

+6 −2
Original line number Diff line number Diff line
@@ -2772,8 +2772,12 @@ u32 __tcp_select_window(struct sock *sk) 
	int mss = icsk->icsk_ack.rcv_mss;

	int free_space = tcp_space(sk);

	int allowed_space = tcp_full_space(sk);

	int full_space = min_t(int, tp->window_clamp, allowed_space);

	int window;

	int full_space, window;



	if (sk_is_mptcp(sk))

		mptcp_space(sk, &free_space, &allowed_space);



	full_space = min_t(int, tp->window_clamp, allowed_space);



	if (unlikely(mss > full_space)) {

		mss = full_space;

net/mptcp/subflow.c

+18 −0
Original line number Diff line number Diff line
@@ -821,6 +821,24 @@ bool mptcp_subflow_data_available(struct sock *sk) 
	return subflow->data_avail;

}



/* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy,

 * not the ssk one.

 *

 * In mptcp, rwin is about the mptcp-level connection data.

 *

 * Data that is still on the ssk rx queue can thus be ignored,

 * as far as mptcp peer is concerened that data is still inflight.

 * DSS ACK is updated when skb is moved to the mptcp rx queue.

 */

void mptcp_space(const struct sock *ssk, int *space, int *full_space)

{

	const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);

	const struct sock *sk = subflow->conn;



	*space = tcp_space(sk);

	*full_space = tcp_full_space(sk);

}



static void subflow_data_ready(struct sock *sk)

{

	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);

CRA Git | Maintained and supported by SUSTech CRA and CCSE