Commit 7f0c940b authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'mptcp-msg_fastopen-and-tfo-listener-side-support' 

Matthieu Baerts says:

====================
mptcp: MSG_FASTOPEN and TFO listener side support

Before this series, only the initiator of a connection was able to combine
both TCP FastOpen and MPTCP when using TCP_FASTOPEN_CONNECT socket option.

These new patches here add (in theory) the full support of TFO with MPTCP,
which means:

 - MSG_FASTOPEN sendmsg flag support (patch 1/8)
 - TFO support for the listener side (patches 2-5/8)
 - TCP_FASTOPEN socket option (patch 6/8)
 - TCP_FASTOPEN_KEY socket option (patch 7/8)

To support TFO for the server side, a few preparation patches are needed
(patches 2 to 5/8). Some of them were inspired by a previous work from
Benjamin Hesmans.

Note that TFO support with MPTCP has been validated with selftests
(patch 8/8) but also with Packetdrill tests running with a modified
but still very WIP version supporting MPTCP. Both the modified tool
and the tests are available online:

  https://github.com/multipath-tcp/packetdrill/
====================

Link: https://lore.kernel.org/r/20221125222958.958636-1-matthieu.baerts@tessares.net


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents f2bb566f ca7ae891

net/mptcp/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -2,7 +2,7 @@ 
obj-$(CONFIG_MPTCP) += mptcp.o



mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \

	   mib.o pm_netlink.o sockopt.o pm_userspace.o

	   mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o



obj-$(CONFIG_SYN_COOKIES) += syncookies.o

obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o

net/mptcp/fastopen.c

0 → 100644
+73 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0

/* MPTCP Fast Open Mechanism

 *

 * Copyright (c) 2021-2022, Dmytro SHYTYI

 */



#include "protocol.h"



void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,

					      struct request_sock *req)

{

	struct sock *ssk = subflow->tcp_sock;

	struct sock *sk = subflow->conn;

	struct sk_buff *skb;

	struct tcp_sock *tp;



	tp = tcp_sk(ssk);



	subflow->is_mptfo = 1;



	skb = skb_peek(&ssk->sk_receive_queue);

	if (WARN_ON_ONCE(!skb))

		return;



	/* dequeue the skb from sk receive queue */

	__skb_unlink(skb, &ssk->sk_receive_queue);

	skb_ext_reset(skb);

	skb_orphan(skb);



	/* We copy the fastopen data, but that don't belong to the mptcp sequence

	 * space, need to offset it in the subflow sequence, see mptcp_subflow_get_map_offset()

	 */

	tp->copied_seq += skb->len;

	subflow->ssn_offset += skb->len;



	/* initialize a dummy sequence number, we will update it at MPC

	 * completion, if needed

	 */

	MPTCP_SKB_CB(skb)->map_seq = -skb->len;

	MPTCP_SKB_CB(skb)->end_seq = 0;

	MPTCP_SKB_CB(skb)->offset = 0;

	MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;



	mptcp_data_lock(sk);



	mptcp_set_owner_r(skb, sk);

	__skb_queue_tail(&sk->sk_receive_queue, skb);



	sk->sk_data_ready(sk);



	mptcp_data_unlock(sk);

}



void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,

				   const struct mptcp_options_received *mp_opt)

{

	struct sock *sk = (struct sock *)msk;

	struct sk_buff *skb;



	mptcp_data_lock(sk);

	skb = skb_peek_tail(&sk->sk_receive_queue);

	if (skb) {

		WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);

		pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk,

			 MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq,

			 MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq);

		MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq;

		MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq;

	}



	pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);

	mptcp_data_unlock(sk);

}

net/mptcp/options.c

+17 −8
Original line number Diff line number Diff line
@@ -26,6 +26,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, 
{

	u8 subtype = *ptr >> 4;

	int expected_opsize;

	u16 subopt;

	u8 version;

	u8 flags;

	u8 i;
@@ -38,11 +39,15 @@ static void mptcp_parse_option(const struct sk_buff *skb, 
				expected_opsize = TCPOLEN_MPTCP_MPC_ACK_DATA;

			else

				expected_opsize = TCPOLEN_MPTCP_MPC_ACK;

			subopt = OPTION_MPTCP_MPC_ACK;

		} else {

			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)

			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) {

				expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK;

			else

				subopt = OPTION_MPTCP_MPC_SYNACK;

			} else {

				expected_opsize = TCPOLEN_MPTCP_MPC_SYN;

				subopt = OPTION_MPTCP_MPC_SYN;

			}

		}



		/* Cfr RFC 8684 Section 3.3.0:
@@ -85,7 +90,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, 


		mp_opt->deny_join_id0 = !!(flags & MPTCP_CAP_DENY_JOIN_ID0);



		mp_opt->suboptions |= OPTIONS_MPTCP_MPC;

		mp_opt->suboptions |= subopt;

		if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) {

			mp_opt->sndr_key = get_unaligned_be64(ptr);

			ptr += 8;
@@ -934,7 +939,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, 
		    subflow->mp_join && (mp_opt->suboptions & OPTIONS_MPTCP_MPJ) &&

		    !subflow->request_join)

			tcp_send_ack(ssk);

		goto fully_established;

		goto check_notify;

	}



	/* we must process OoO packets before the first subflow is fully
@@ -945,17 +950,20 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, 
	if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) {

		if (subflow->mp_join)

			goto reset;

		if (subflow->is_mptfo && mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)

			goto set_fully_established;

		return subflow->mp_capable;

	}



	if (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) ||

	    ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo)) {

	if (subflow->remote_key_valid &&

	    (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) ||

	     ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) {

		/* subflows are fully established as soon as we get any

		 * additional ack, including ADD_ADDR.

		 */

		subflow->fully_established = 1;

		WRITE_ONCE(msk->fully_established, true);

		goto fully_established;

		goto check_notify;

	}



	/* If the first established packet does not contain MP_CAPABLE + data
@@ -974,11 +982,12 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, 
	if (mp_opt->deny_join_id0)

		WRITE_ONCE(msk->pm.remote_deny_join_id0, true);



set_fully_established:

	if (unlikely(!READ_ONCE(msk->pm.server_side)))

		pr_warn_once("bogus mpc option on established client sk");

	mptcp_subflow_fully_established(subflow, mp_opt);



fully_established:

check_notify:

	/* if the subflow is not already linked into the conn_list, we can't

	 * notify the PM: this subflow is still on the listener queue

	 * and the PM possibly acquiring the subflow lock could race with

net/mptcp/protocol.c

+5 −34
Original line number Diff line number Diff line
@@ -36,15 +36,6 @@ struct mptcp6_sock { 
};

#endif



struct mptcp_skb_cb {

	u64 map_seq;

	u64 end_seq;

	u32 offset;

	u8  has_rxtstamp:1;

};



#define MPTCP_SKB_CB(__skb)	((struct mptcp_skb_cb *)&((__skb)->cb[0]))



enum {

	MPTCP_CMSG_TS = BIT(0),

	MPTCP_CMSG_INQ = BIT(1),
@@ -200,7 +191,7 @@ static void mptcp_rfree(struct sk_buff *skb) 
	mptcp_rmem_uncharge(sk, len);

}



static void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk)

void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk)

{

	skb_orphan(skb);

	skb->sk = sk;
@@ -1711,17 +1702,14 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 
	int ret = 0;

	long timeo;



	/* we don't support FASTOPEN yet */

	if (msg->msg_flags & MSG_FASTOPEN)

		return -EOPNOTSUPP;



	/* silently ignore everything else */

	msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL;

	msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_FASTOPEN;



	lock_sock(sk);



	ssock = __mptcp_nmpc_socket(msk);

	if (unlikely(ssock && inet_sk(ssock->sk)->defer_connect)) {

	if (unlikely(ssock && (inet_sk(ssock->sk)->defer_connect ||

			       msg->msg_flags & MSG_FASTOPEN))) {

		int copied_syn = 0;



		ret = mptcp_sendmsg_fastopen(sk, ssock->sk, msg, len, &copied_syn);
@@ -3048,7 +3036,6 @@ struct sock *mptcp_sk_clone(const struct sock *sk, 
	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);

	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);

	struct mptcp_sock *msk;

	u64 ack_seq;



	if (!nsk)

		return NULL;
@@ -3074,15 +3061,6 @@ struct sock *mptcp_sk_clone(const struct sock *sk, 
	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;

	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;



	if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) {

		msk->can_ack = true;

		msk->remote_key = mp_opt->sndr_key;

		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);

		ack_seq++;

		WRITE_ONCE(msk->ack_seq, ack_seq);

		atomic64_set(&msk->rcv_wnd_sent, ack_seq);

	}



	sock_reset_flag(nsk, SOCK_RCU_FREE);

	/* will be fully established after successful MPC subflow creation */

	inet_sk_state_store(nsk, TCP_SYN_RECV);
@@ -3355,7 +3333,6 @@ void mptcp_finish_connect(struct sock *ssk) 
	struct mptcp_subflow_context *subflow;

	struct mptcp_sock *msk;

	struct sock *sk;

	u64 ack_seq;



	subflow = mptcp_subflow_ctx(ssk);

	sk = subflow->conn;
@@ -3363,22 +3340,16 @@ void mptcp_finish_connect(struct sock *ssk) 


	pr_debug("msk=%p, token=%u", sk, subflow->token);



	mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq);

	ack_seq++;

	subflow->map_seq = ack_seq;

	subflow->map_seq = subflow->iasn;

	subflow->map_subflow_seq = 1;



	/* the socket is not connected yet, no msk/subflow ops can access/race

	 * accessing the field below

	 */

	WRITE_ONCE(msk->remote_key, subflow->remote_key);

	WRITE_ONCE(msk->local_key, subflow->local_key);

	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);

	WRITE_ONCE(msk->snd_nxt, msk->write_seq);

	WRITE_ONCE(msk->ack_seq, ack_seq);

	WRITE_ONCE(msk->can_ack, 1);

	WRITE_ONCE(msk->snd_una, msk->write_seq);

	atomic64_set(&msk->rcv_wnd_sent, ack_seq);



	mptcp_pm_new_connection(msk, ssk, 0);

net/mptcp/protocol.h

+24 −4
Original line number Diff line number Diff line
@@ -126,6 +126,15 @@ 
#define MPTCP_CONNECTED		6

#define MPTCP_RESET_SCHEDULER	7



struct mptcp_skb_cb {

	u64 map_seq;

	u64 end_seq;

	u32 offset;

	u8  has_rxtstamp:1;

};



#define MPTCP_SKB_CB(__skb)	((struct mptcp_skb_cb *)&((__skb)->cb[0]))



static inline bool before64(__u64 seq1, __u64 seq2)

{

	return (__s64)(seq1 - seq2) < 0;
@@ -467,17 +476,22 @@ struct mptcp_subflow_context { 
		send_fastclose : 1,

		send_infinite_map : 1,

		rx_eof : 1,

		can_ack : 1,        /* only after processing the remote a key */

		remote_key_valid : 1,        /* received the peer key from */

		disposable : 1,	    /* ctx can be free at ulp release time */

		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */

		local_id_valid : 1, /* local_id is correctly initialized */

		valid_csum_seen : 1;        /* at least one csum validated */

		valid_csum_seen : 1,        /* at least one csum validated */

		is_mptfo : 1,	    /* subflow is doing TFO */

		__unused : 8;

	enum mptcp_data_avail data_avail;

	u32	remote_nonce;

	u64	thmac;

	u32	local_nonce;

	u32	remote_token;

	u8	hmac[MPTCPOPT_HMAC_LEN];

	union {

		u8	hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */

		u64	iasn;	    /* initial ack sequence number, MPC subflows only */

	};

	u8	local_id;

	u8	remote_id;

	u8	reset_seen:1;
@@ -603,7 +617,7 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net); 
int mptcp_get_pm_type(const struct net *net);

void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk);

void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,

				     struct mptcp_options_received *mp_opt);

				     const struct mptcp_options_received *mp_opt);

bool __mptcp_retransmit_pending_data(struct sock *sk);

void mptcp_check_and_set_pending(struct sock *sk);

void __mptcp_push_pending(struct sock *sk, unsigned int flags);
@@ -619,6 +633,7 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent); 
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);

bool __mptcp_close(struct sock *sk, long timeout);

void mptcp_cancel_work(struct sock *sk);

void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk);



bool mptcp_addresses_equal(const struct mptcp_addr_info *a,

			   const struct mptcp_addr_info *b, bool use_port);
@@ -826,6 +841,11 @@ void mptcp_event_addr_announced(const struct sock *ssk, const struct mptcp_addr_ 
void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id);

bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);



void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,

				   const struct mptcp_options_received *mp_opt);

void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,

					      struct request_sock *req);



static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)

{

	return READ_ONCE(msk->pm.addr_signal) &