Commit 60e2a778 authored by Ursula Braun's avatar Ursula Braun Committed by David S. Miller
Browse files

tcp: TCP experimental option for SMC 

The SMC protocol [1] relies on the use of a new TCP experimental
option [2, 3]. With this option, SMC capabilities are exchanged
between peers during the TCP three way handshake. This patch adds
support for this experimental option to TCP.

References:
[1] SMC-R Informational RFC: http://www.rfc-editor.org/info/rfc7609
[2] Shared Use of TCP Experimental Options RFC 6994:
    https://tools.ietf.org/rfc/rfc6994.txt
[3] IANA ExID SMCR:
http://www.iana.org/assignments/tcp-parameters/tcp-parameters.xhtml#tcp-exids



Signed-off-by: default avatarUrsula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 145686ba

include/linux/tcp.h

+7 −2
Original line number Diff line number Diff line
@@ -98,7 +98,8 @@ struct tcp_options_received { 
		tstamp_ok : 1,	/* TIMESTAMP seen on SYN packet		*/

		dsack : 1,	/* D-SACK is scheduled			*/

		wscale_ok : 1,	/* Wscale seen on SYN packet		*/

		sack_ok : 4,	/* SACK seen on SYN packet		*/

		sack_ok : 3,	/* SACK seen on SYN packet		*/

		smc_ok : 1,	/* SMC seen on SYN packet		*/

		snd_wscale : 4,	/* Window scaling received from sender	*/

		rcv_wscale : 4;	/* Window scaling to send to receiver	*/

	u8	num_sacks;	/* Number of SACK blocks		*/
@@ -110,6 +111,9 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) 
{

	rx_opt->tstamp_ok = rx_opt->sack_ok = 0;

	rx_opt->wscale_ok = rx_opt->snd_wscale = 0;

#if IS_ENABLED(CONFIG_SMC)

	rx_opt->smc_ok = 0;

#endif

}



/* This is the max number of SACKS that we'll generate and process. It's safe
@@ -229,7 +233,8 @@ struct tcp_sock { 
		syn_fastopen_ch:1, /* Active TFO re-enabling probe */

		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */

		save_syn:1,	/* Save headers of SYN packet */

		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */

		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */

		syn_smc:1;	/* SYN includes SMC */

	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */



/* RTT measurement */

include/net/inet_sock.h

+2 −1
Original line number Diff line number Diff line
@@ -92,7 +92,8 @@ struct inet_request_sock { 
				wscale_ok  : 1,

				ecn_ok	   : 1,

				acked	   : 1,

				no_srccheck: 1;

				no_srccheck: 1,

				smc_ok	   : 1;

	kmemcheck_bitfield_end(flags);

	u32                     ir_mark;

	union {

include/net/tcp.h

+7 −0
Original line number Diff line number Diff line
@@ -191,6 +191,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); 
 * experimental options. See draft-ietf-tcpm-experimental-options-00.txt

 */

#define TCPOPT_FASTOPEN_MAGIC	0xF989

#define TCPOPT_SMC_MAGIC	0xE2D4C3D9



/*

 *     TCP option lengths
@@ -203,6 +204,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); 
#define TCPOLEN_MD5SIG         18

#define TCPOLEN_FASTOPEN_BASE  2

#define TCPOLEN_EXP_FASTOPEN_BASE  4

#define TCPOLEN_EXP_SMC_BASE   6



/* But this is what stacks really send out. */

#define TCPOLEN_TSTAMP_ALIGNED		12
@@ -213,6 +215,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); 
#define TCPOLEN_SACK_PERBLOCK		8

#define TCPOLEN_MD5SIG_ALIGNED		20

#define TCPOLEN_MSS_ALIGNED		4

#define TCPOLEN_EXP_SMC_BASE_ALIGNED	8



/* Flags in tp->nonagle */

#define TCP_NAGLE_OFF		1	/* Nagle's algo is disabled */
@@ -2108,4 +2111,8 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) 
{

	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);

}



#if IS_ENABLED(CONFIG_SMC)

extern struct static_key_false tcp_have_smc;

#endif

#endif	/* _TCP_H */

net/ipv4/tcp.c

+6 −0
Original line number Diff line number Diff line
@@ -270,6 +270,7 @@ 
#include <linux/time.h>

#include <linux/slab.h>

#include <linux/errqueue.h>

#include <linux/static_key.h>



#include <net/icmp.h>

#include <net/inet_common.h>
@@ -302,6 +303,11 @@ EXPORT_SYMBOL(sysctl_tcp_wmem); 
atomic_long_t tcp_memory_allocated;	/* Current allocated memory. */

EXPORT_SYMBOL(tcp_memory_allocated);



#if IS_ENABLED(CONFIG_SMC)

DEFINE_STATIC_KEY_FALSE(tcp_have_smc);

EXPORT_SYMBOL(tcp_have_smc);

#endif



/*

 * Current number of TCP sockets.

 */

net/ipv4/tcp_input.c

+35 −0
Original line number Diff line number Diff line
@@ -76,6 +76,8 @@ 
#include <asm/unaligned.h>

#include <linux/errqueue.h>

#include <trace/events/tcp.h>

#include <linux/unaligned/access_ok.h>

#include <linux/static_key.h>



int sysctl_tcp_fack __read_mostly;

int sysctl_tcp_max_reordering __read_mostly = 300;
@@ -3737,6 +3739,21 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, 
	foc->exp = exp_opt;

}



static void smc_parse_options(const struct tcphdr *th,

			      struct tcp_options_received *opt_rx,

			      const unsigned char *ptr,

			      int opsize)

{

#if IS_ENABLED(CONFIG_SMC)

	if (static_branch_unlikely(&tcp_have_smc)) {

		if (th->syn && !(opsize & 1) &&

		    opsize >= TCPOLEN_EXP_SMC_BASE &&

		    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)

			opt_rx->smc_ok = 1;

	}

#endif

}



/* Look for tcp options. Normally only called on SYN and SYNACK packets.

 * But, this can also be called on packets in the established flow when

 * the fast version below fails.
@@ -3844,6 +3861,9 @@ void tcp_parse_options(const struct net *net, 
					tcp_parse_fastopen_option(opsize -

						TCPOLEN_EXP_FASTOPEN_BASE,

						ptr + 2, th->syn, foc, true);

				else

					smc_parse_options(th, opt_rx, ptr,

							  opsize);

				break;



			}
@@ -5598,6 +5618,16 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, 
	return false;

}



static void smc_check_reset_syn(struct tcp_sock *tp)

{

#if IS_ENABLED(CONFIG_SMC)

	if (static_branch_unlikely(&tcp_have_smc)) {

		if (tp->syn_smc && !tp->rx_opt.smc_ok)

			tp->syn_smc = 0;

	}

#endif

}



static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,

					 const struct tcphdr *th)

{
@@ -5704,6 +5734,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, 
		 * is initialized. */

		tp->copied_seq = tp->rcv_nxt;



		smc_check_reset_syn(tp);



		smp_mb();



		tcp_finish_connect(sk, skb);
@@ -6157,6 +6189,9 @@ static void tcp_openreq_init(struct request_sock *req, 
	ireq->ir_rmt_port = tcp_hdr(skb)->source;

	ireq->ir_num = ntohs(tcp_hdr(skb)->dest);

	ireq->ir_mark = inet_request_mark(sk, skb);

#if IS_ENABLED(CONFIG_SMC)

	ireq->smc_ok = rx_opt->smc_ok;

#endif

}



struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,

CRA Git | Maintained and supported by SUSTech CRA and CCSE