Commit cec37a6e authored by Peter Krystad's avatar Peter Krystad Committed by David S. Miller
Browse files

mptcp: Handle MP_CAPABLE options for outgoing connections 



Add hooks to tcp_output.c to add MP_CAPABLE to an outgoing SYN request,
to capture the MP_CAPABLE in the received SYN-ACK, to add MP_CAPABLE to
the final ACK of the three-way handshake.

Use the .sk_rx_dst_set() handler in the subflow proto to capture when the
responding SYN-ACK is received and notify the MPTCP connection layer.

Co-developed-by: default avatarPaolo Abeni <pabeni@redhat.com>
Signed-off-by: default avatarPaolo Abeni <pabeni@redhat.com>
Co-developed-by: default avatarFlorian Westphal <fw@strlen.de>
Signed-off-by: default avatarFlorian Westphal <fw@strlen.de>
Signed-off-by: default avatarPeter Krystad <peter.krystad@linux.intel.com>
Signed-off-by: default avatarChristoph Paasch <cpaasch@apple.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 2303f994

include/linux/tcp.h

+3 −0
Original line number Diff line number Diff line
@@ -137,6 +137,9 @@ struct tcp_request_sock { 
	const struct tcp_request_sock_ops *af_specific;

	u64				snt_synack; /* first SYNACK sent time */

	bool				tfo_listener;

#if IS_ENABLED(CONFIG_MPTCP)

	bool				is_mptcp;

#endif

	u32				txhash;

	u32				rcv_isn;

	u32				snt_isn;

include/net/mptcp.h

+57 −0
Original line number Diff line number Diff line
@@ -39,8 +39,27 @@ struct mptcp_out_options { 


void mptcp_init(void);



static inline bool sk_is_mptcp(const struct sock *sk)

{

	return tcp_sk(sk)->is_mptcp;

}



static inline bool rsk_is_mptcp(const struct request_sock *req)

{

	return tcp_rsk(req)->is_mptcp;

}



void mptcp_parse_option(const unsigned char *ptr, int opsize,

			struct tcp_options_received *opt_rx);

bool mptcp_syn_options(struct sock *sk, unsigned int *size,

		       struct mptcp_out_options *opts);

void mptcp_rcv_synsent(struct sock *sk);

bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,

			  struct mptcp_out_options *opts);

bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,

			       unsigned int *size, unsigned int remaining,

			       struct mptcp_out_options *opts);



void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);



/* move the skb extension owership, with the assumption that 'to' is
@@ -89,11 +108,47 @@ static inline void mptcp_init(void) 
{

}



static inline bool sk_is_mptcp(const struct sock *sk)

{

	return false;

}



static inline bool rsk_is_mptcp(const struct request_sock *req)

{

	return false;

}



static inline void mptcp_parse_option(const unsigned char *ptr, int opsize,

				      struct tcp_options_received *opt_rx)

{

}



static inline bool mptcp_syn_options(struct sock *sk, unsigned int *size,

				     struct mptcp_out_options *opts)

{

	return false;

}



static inline void mptcp_rcv_synsent(struct sock *sk)

{

}



static inline bool mptcp_synack_options(const struct request_sock *req,

					unsigned int *size,

					struct mptcp_out_options *opts)

{

	return false;

}



static inline bool mptcp_established_options(struct sock *sk,

					     struct sk_buff *skb,

					     unsigned int *size,

					     unsigned int remaining,

					     struct mptcp_out_options *opts)

{

	return false;

}



static inline void mptcp_skb_ext_move(struct sk_buff *to,

				      const struct sk_buff *from)

{
@@ -107,6 +162,8 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to, 


#endif /* CONFIG_MPTCP */



void mptcp_handle_ipv6_mapped(struct sock *sk, bool mapped);



#if IS_ENABLED(CONFIG_MPTCP_IPV6)

int mptcpv6_init(void);

#elif IS_ENABLED(CONFIG_IPV6)

net/ipv4/tcp_input.c

+6 −0
Original line number Diff line number Diff line
@@ -5978,6 +5978,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, 
		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);

		tcp_initialize_rcv_mss(sk);



		if (sk_is_mptcp(sk))

			mptcp_rcv_synsent(sk);



		/* Remember, tcp_poll() does not lock socket!

		 * Change state from SYN-SENT only after copied_seq

		 * is initialized. */
@@ -6600,6 +6603,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, 


	tcp_rsk(req)->af_specific = af_ops;

	tcp_rsk(req)->ts_off = 0;

#if IS_ENABLED(CONFIG_MPTCP)

	tcp_rsk(req)->is_mptcp = 0;

#endif



	tcp_clear_options(&tmp_opt);

	tmp_opt.mss_clamp = af_ops->mss_clamp;

net/ipv4/tcp_output.c

+44 −0
Original line number Diff line number Diff line
@@ -597,6 +597,22 @@ static void smc_set_option_cond(const struct tcp_sock *tp, 
#endif

}



static void mptcp_set_option_cond(const struct request_sock *req,

				  struct tcp_out_options *opts,

				  unsigned int *remaining)

{

	if (rsk_is_mptcp(req)) {

		unsigned int size;



		if (mptcp_synack_options(req, &size, &opts->mptcp)) {

			if (*remaining >= size) {

				opts->options |= OPTION_MPTCP;

				*remaining -= size;

			}

		}

	}

}



/* Compute TCP options for SYN packets. This is not the final

 * network wire format yet.

 */
@@ -666,6 +682,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, 


	smc_set_option(tp, opts, &remaining);



	if (sk_is_mptcp(sk)) {

		unsigned int size;



		if (mptcp_syn_options(sk, &size, &opts->mptcp)) {

			opts->options |= OPTION_MPTCP;

			remaining -= size;

		}

	}



	return MAX_TCP_OPTION_SPACE - remaining;

}
@@ -727,6 +752,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, 
		}

	}



	mptcp_set_option_cond(req, opts, &remaining);



	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);



	return MAX_TCP_OPTION_SPACE - remaining;
@@ -764,6 +791,23 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb 
		size += TCPOLEN_TSTAMP_ALIGNED;

	}



	/* MPTCP options have precedence over SACK for the limited TCP

	 * option space because a MPTCP connection would be forced to

	 * fall back to regular TCP if a required multipath option is

	 * missing. SACK still gets a chance to use whatever space is

	 * left.

	 */

	if (sk_is_mptcp(sk)) {

		unsigned int remaining = MAX_TCP_OPTION_SPACE - size;

		unsigned int opt_size = 0;



		if (mptcp_established_options(sk, skb, &opt_size, remaining,

					      &opts->mptcp)) {

			opts->options |= OPTION_MPTCP;

			size += opt_size;

		}

	}



	eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;

	if (unlikely(eff_sacks)) {

		const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;

net/ipv6/tcp_ipv6.c

+6 −0
Original line number Diff line number Diff line
@@ -238,6 +238,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, 
		sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];



		icsk->icsk_af_ops = &ipv6_mapped;

		if (sk_is_mptcp(sk))

			mptcp_handle_ipv6_mapped(sk, true);

		sk->sk_backlog_rcv = tcp_v4_do_rcv;

#ifdef CONFIG_TCP_MD5SIG

		tp->af_specific = &tcp_sock_ipv6_mapped_specific;
@@ -248,6 +250,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, 
		if (err) {

			icsk->icsk_ext_hdr_len = exthdrlen;

			icsk->icsk_af_ops = &ipv6_specific;

			if (sk_is_mptcp(sk))

				mptcp_handle_ipv6_mapped(sk, false);

			sk->sk_backlog_rcv = tcp_v6_do_rcv;

#ifdef CONFIG_TCP_MD5SIG

			tp->af_specific = &tcp_sock_ipv6_specific;
@@ -1203,6 +1207,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * 
		newnp->saddr = newsk->sk_v6_rcv_saddr;



		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;

		if (sk_is_mptcp(newsk))

			mptcp_handle_ipv6_mapped(newsk, true);

		newsk->sk_backlog_rcv = tcp_v4_do_rcv;

#ifdef CONFIG_TCP_MD5SIG

		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;

CRA Git | Maintained and supported by SUSTech CRA and CCSE