summaryrefslogtreecommitdiff
path: root/net/mptcp/protocol.h
blob: 3081294dca6c546eee3115d4694c1673dfde79dc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
/* SPDX-License-Identifier: GPL-2.0 */
/* Multipath TCP
 *
 * Copyright (c) 2017 - 2019, Intel Corporation.
 */

#ifndef __MPTCP_PROTOCOL_H
#define __MPTCP_PROTOCOL_H

#include <linux/random.h>
#include <net/tcp.h>
#include <net/inet_connection_sock.h>

#define MPTCP_SUPPORTED_VERSION	1

/* MPTCP option bits */
#define OPTION_MPTCP_MPC_SYN	BIT(0)
#define OPTION_MPTCP_MPC_SYNACK	BIT(1)
#define OPTION_MPTCP_MPC_ACK	BIT(2)
#define OPTION_MPTCP_MPJ_SYN	BIT(3)
#define OPTION_MPTCP_MPJ_SYNACK	BIT(4)
#define OPTION_MPTCP_MPJ_ACK	BIT(5)
#define OPTION_MPTCP_ADD_ADDR	BIT(6)
#define OPTION_MPTCP_ADD_ADDR6	BIT(7)
#define OPTION_MPTCP_RM_ADDR	BIT(8)
#define OPTION_MPTCP_FASTCLOSE	BIT(9)
#define OPTION_MPTCP_PRIO	BIT(10)

/* MPTCP option subtypes */
#define MPTCPOPT_MP_CAPABLE	0
#define MPTCPOPT_MP_JOIN	1
#define MPTCPOPT_DSS		2
#define MPTCPOPT_ADD_ADDR	3
#define MPTCPOPT_RM_ADDR	4
#define MPTCPOPT_MP_PRIO	5
#define MPTCPOPT_MP_FAIL	6
#define MPTCPOPT_MP_FASTCLOSE	7

/* MPTCP suboption lengths */
#define TCPOLEN_MPTCP_MPC_SYN		4
#define TCPOLEN_MPTCP_MPC_SYNACK	12
#define TCPOLEN_MPTCP_MPC_ACK		20
#define TCPOLEN_MPTCP_MPC_ACK_DATA	22
#define TCPOLEN_MPTCP_MPJ_SYN		12
#define TCPOLEN_MPTCP_MPJ_SYNACK	16
#define TCPOLEN_MPTCP_MPJ_ACK		24
#define TCPOLEN_MPTCP_DSS_BASE		4
#define TCPOLEN_MPTCP_DSS_ACK32		4
#define TCPOLEN_MPTCP_DSS_ACK64		8
#define TCPOLEN_MPTCP_DSS_MAP32		10
#define TCPOLEN_MPTCP_DSS_MAP64		14
#define TCPOLEN_MPTCP_DSS_CHECKSUM	2
#define TCPOLEN_MPTCP_ADD_ADDR		16
#define TCPOLEN_MPTCP_ADD_ADDR_PORT	20
#define TCPOLEN_MPTCP_ADD_ADDR_BASE	8
#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT	12
#define TCPOLEN_MPTCP_ADD_ADDR6		28
#define TCPOLEN_MPTCP_ADD_ADDR6_PORT	32
#define TCPOLEN_MPTCP_ADD_ADDR6_BASE	20
#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT	24
#define TCPOLEN_MPTCP_PORT_LEN		4
#define TCPOLEN_MPTCP_RM_ADDR_BASE	4
#define TCPOLEN_MPTCP_PRIO		3
#define TCPOLEN_MPTCP_PRIO_ALIGN	4
#define TCPOLEN_MPTCP_FASTCLOSE		12

/* MPTCP MP_JOIN flags */
#define MPTCPOPT_BACKUP		BIT(0)
#define MPTCPOPT_HMAC_LEN	20
#define MPTCPOPT_THMAC_LEN	8

/* MPTCP MP_CAPABLE flags */
#define MPTCP_VERSION_MASK	(0x0F)
#define MPTCP_CAP_CHECKSUM_REQD	BIT(7)
#define MPTCP_CAP_EXTENSIBILITY	BIT(6)
#define MPTCP_CAP_HMAC_SHA256	BIT(0)
#define MPTCP_CAP_FLAG_MASK	(0x3F)

/* MPTCP DSS flags */
#define MPTCP_DSS_DATA_FIN	BIT(4)
#define MPTCP_DSS_DSN64		BIT(3)
#define MPTCP_DSS_HAS_MAP	BIT(2)
#define MPTCP_DSS_ACK64		BIT(1)
#define MPTCP_DSS_HAS_ACK	BIT(0)
#define MPTCP_DSS_FLAG_MASK	(0x1F)

/* MPTCP ADD_ADDR flags */
#define MPTCP_ADDR_ECHO		BIT(0)
#define MPTCP_ADDR_IPVERSION_4	4
#define MPTCP_ADDR_IPVERSION_6	6

/* MPTCP MP_PRIO flags */
#define MPTCP_PRIO_BKUP		BIT(0)

/* MPTCP socket flags */
#define MPTCP_DATA_READY	0
#define MPTCP_NOSPACE		1
#define MPTCP_WORK_RTX		2
#define MPTCP_WORK_EOF		3
#define MPTCP_FALLBACK_DONE	4
#define MPTCP_WORK_CLOSE_SUBFLOW 5
#define MPTCP_PUSH_PENDING	6
#define MPTCP_CLEAN_UNA		7

static inline bool before64(__u64 seq1, __u64 seq2)
{
	return (__s64)(seq1 - seq2) < 0;
}

#define after64(seq2, seq1)	before64(seq1, seq2)

struct mptcp_options_received {
	u64	sndr_key;
	u64	rcvr_key;
	u64	data_ack;
	u64	data_seq;
	u32	subflow_seq;
	u16	data_len;
	u16	mp_capable : 1,
		mp_join : 1,
		fastclose : 1,
		dss : 1,
		add_addr : 1,
		rm_addr : 1,
		mp_prio : 1,
		family : 4,
		echo : 1,
		backup : 1;
	u32	token;
	u32	nonce;
	u64	thmac;
	u8	hmac[MPTCPOPT_HMAC_LEN];
	u8	join_id;
	u8	use_map:1,
		dsn64:1,
		data_fin:1,
		use_ack:1,
		ack64:1,
		mpc_map:1,
		__unused:2;
	u8	addr_id;
	u8	rm_id;
	union {
		struct in_addr	addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
		struct in6_addr	addr6;
#endif
	};
	u64	ahmac;
	u16	port;
};

static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
{
	return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
		     ((nib & 0xF) << 8) | field);
}

struct mptcp_addr_info {
	sa_family_t		family;
	__be16			port;
	u8			id;
	u8			flags;
	int			ifindex;
	union {
		struct in_addr addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
		struct in6_addr addr6;
#endif
	};
};

enum mptcp_pm_status {
	MPTCP_PM_ADD_ADDR_RECEIVED,
	MPTCP_PM_ADD_ADDR_SEND_ACK,
	MPTCP_PM_RM_ADDR_RECEIVED,
	MPTCP_PM_ESTABLISHED,
	MPTCP_PM_ALREADY_ESTABLISHED,	/* persistent status, set after ESTABLISHED event */
	MPTCP_PM_SUBFLOW_ESTABLISHED,
};

enum mptcp_addr_signal_status {
	MPTCP_ADD_ADDR_SIGNAL,
	MPTCP_ADD_ADDR_ECHO,
	MPTCP_ADD_ADDR_IPV6,
	MPTCP_ADD_ADDR_PORT,
	MPTCP_RM_ADDR_SIGNAL,
};

struct mptcp_pm_data {
	struct mptcp_addr_info local;
	struct mptcp_addr_info remote;
	struct list_head anno_list;

	spinlock_t	lock;		/*protects the whole PM data */

	u8		addr_signal;
	bool		server_side;
	bool		work_pending;
	bool		accept_addr;
	bool		accept_subflow;
	u8		add_addr_signaled;
	u8		add_addr_accepted;
	u8		local_addr_used;
	u8		subflows;
	u8		status;
	u8		rm_id;
};

struct mptcp_data_frag {
	struct list_head list;
	u64 data_seq;
	u16 data_len;
	u16 offset;
	u16 overhead;
	u16 already_sent;
	struct page *page;
};

/* MPTCP connection sock */
struct mptcp_sock {
	/* inet_connection_sock must be the first member */
	struct inet_connection_sock sk;
	u64		local_key;
	u64		remote_key;
	u64		write_seq;
	u64		snd_nxt;
	u64		ack_seq;
	u64		rcv_wnd_sent;
	u64		rcv_data_fin_seq;
	int		wmem_reserved;
	struct sock	*last_snd;
	int		snd_burst;
	int		old_wspace;
	u64		snd_una;
	u64		wnd_end;
	unsigned long	timer_ival;
	u32		token;
	int		rmem_pending;
	int		rmem_released;
	unsigned long	flags;
	bool		can_ack;
	bool		fully_established;
	bool		rcv_data_fin;
	bool		snd_data_fin_enable;
	bool		rcv_fastclose;
	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
	spinlock_t	join_list_lock;
	struct sock	*ack_hint;
	struct work_struct work;
	struct sk_buff  *ooo_last_skb;
	struct rb_root  out_of_order_queue;
	struct sk_buff_head receive_queue;
	struct sk_buff_head skb_tx_cache;	/* this is wmem accounted */
	int		tx_pending_data;
	int		size_goal_cache;
	struct list_head conn_list;
	struct list_head rtx_queue;
	struct mptcp_data_frag *first_pending;
	struct list_head join_list;
	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
	struct sock	*first;
	struct mptcp_pm_data	pm;
	struct {
		u32	space;	/* bytes copied in last measurement window */
		u32	copied; /* bytes copied in this measurement window */
		u64	time;	/* start time of measurement window */
		u64	rtt_us; /* last maximum rtt of subflows */
	} rcvq_space;
};

#define mptcp_lock_sock(___sk, cb) do {					\
	struct sock *__sk = (___sk); /* silence macro reuse warning */	\
	might_sleep();							\
	spin_lock_bh(&__sk->sk_lock.slock);				\
	if (__sk->sk_lock.owned)					\
		__lock_sock(__sk);					\
	cb;								\
	__sk->sk_lock.owned = 1;					\
	spin_unlock(&__sk->sk_lock.slock);				\
	mutex_acquire(&__sk->sk_lock.dep_map, 0, 0, _RET_IP_);		\
	local_bh_enable();						\
} while (0)

#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
#define mptcp_data_unlock(sk) spin_unlock_bh(&(sk)->sk_lock.slock)

#define mptcp_for_each_subflow(__msk, __subflow)			\
	list_for_each_entry(__subflow, &((__msk)->conn_list), node)

static inline void msk_owned_by_me(const struct mptcp_sock *msk)
{
	sock_owned_by_me((const struct sock *)msk);
}

static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
{
	return (struct mptcp_sock *)sk;
}

static inline int __mptcp_space(const struct sock *sk)
{
	return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_pending);
}

static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
{
	const struct mptcp_sock *msk = mptcp_sk(sk);

	return READ_ONCE(msk->first_pending);
}

static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_data_frag *cur;

	cur = msk->first_pending;
	return list_is_last(&cur->list, &msk->rtx_queue) ? NULL :
						     list_next_entry(cur, list);
}

static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	if (!msk->first_pending)
		return NULL;

	if (WARN_ON_ONCE(list_empty(&msk->rtx_queue)))
		return NULL;

	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
}

static inline struct mptcp_data_frag *mptcp_rtx_tail(const struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	if (!before64(msk->snd_nxt, READ_ONCE(msk->snd_una)))
		return NULL;

	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
}

static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk)
{
	struct mptcp_sock *msk = mptcp_sk(sk);

	return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list);
}

struct mptcp_subflow_request_sock {
	struct	tcp_request_sock sk;
	u16	mp_capable : 1,
		mp_join : 1,
		backup : 1;
	u8	local_id;
	u8	remote_id;
	u64	local_key;
	u64	idsn;
	u32	token;
	u32	ssn_offset;
	u64	thmac;
	u32	local_nonce;
	u32	remote_nonce;
	struct mptcp_sock	*msk;
	struct hlist_nulls_node token_node;
};

static inline struct mptcp_subflow_request_sock *
mptcp_subflow_rsk(const struct request_sock *rsk)
{
	return (struct mptcp_subflow_request_sock *)rsk;
}

enum mptcp_data_avail {
	MPTCP_SUBFLOW_NODATA,
	MPTCP_SUBFLOW_DATA_AVAIL,
	MPTCP_SUBFLOW_OOO_DATA
};

struct mptcp_delegated_action {
	struct napi_struct napi;
	struct list_head head;
};

DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);

#define MPTCP_DELEGATE_SEND		0

/* MPTCP subflow context */
struct mptcp_subflow_context {
	struct	list_head node;/* conn_list of subflows */
	u64	local_key;
	u64	remote_key;
	u64	idsn;
	u64	map_seq;
	u32	snd_isn;
	u32	token;
	u32	rel_write_seq;
	u32	map_subflow_seq;
	u32	ssn_offset;
	u32	map_data_len;
	u32	request_mptcp : 1,  /* send MP_CAPABLE */
		request_join : 1,   /* send MP_JOIN */
		request_bkup : 1,
		mp_capable : 1,	    /* remote is MPTCP capable */
		mp_join : 1,	    /* remote is JOINing */
		fully_established : 1,	    /* path validated */
		pm_notified : 1,    /* PM hook called for established status */
		conn_finished : 1,
		map_valid : 1,
		mpc_map : 1,
		backup : 1,
		send_mp_prio : 1,
		rx_eof : 1,
		can_ack : 1,        /* only after processing the remote a key */
		disposable : 1;	    /* ctx can be free at ulp release time */
	enum mptcp_data_avail data_avail;
	u32	remote_nonce;
	u64	thmac;
	u32	local_nonce;
	u32	remote_token;
	u8	hmac[MPTCPOPT_HMAC_LEN];
	u8	local_id;
	u8	remote_id;

	long	delegated_status;
	struct	list_head delegated_node;   /* link into delegated_action, protected by local BH */

	struct	sock *tcp_sock;	    /* tcp sk backpointer */
	struct	sock *conn;	    /* parent mptcp_sock */
	const	struct inet_connection_sock_af_ops *icsk_af_ops;
	void	(*tcp_data_ready)(struct sock *sk);
	void	(*tcp_state_change)(struct sock *sk);
	void	(*tcp_write_space)(struct sock *sk);

	struct	rcu_head rcu;
};

static inline struct mptcp_subflow_context *
mptcp_subflow_ctx(const struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	/* Use RCU on icsk_ulp_data only for sock diag code */
	return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
}

static inline struct sock *
mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
{
	return subflow->tcp_sock;
}

static inline u64
mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow)
{
	return tcp_sk(mptcp_subflow_tcp_sock(subflow))->copied_seq -
		      subflow->ssn_offset -
		      subflow->map_subflow_seq;
}

static inline u64
mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
{
	return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
}

static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
					     struct mptcp_subflow_context *subflow)
{
	sock_hold(mptcp_subflow_tcp_sock(subflow));
	spin_lock_bh(&msk->join_list_lock);
	list_add_tail(&subflow->node, &msk->join_list);
	spin_unlock_bh(&msk->join_list_lock);
}

void mptcp_subflow_process_delegated(struct sock *ssk);

static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow)
{
	struct mptcp_delegated_action *delegated;
	bool schedule;

	/* The implied barrier pairs with mptcp_subflow_delegated_done(), and
	 * ensures the below list check sees list updates done prior to status
	 * bit changes
	 */
	if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
		/* still on delegated list from previous scheduling */
		if (!list_empty(&subflow->delegated_node))
			return;

		/* the caller held the subflow bh socket lock */
		lockdep_assert_in_softirq();

		delegated = this_cpu_ptr(&mptcp_delegated_actions);
		schedule = list_empty(&delegated->head);
		list_add_tail(&subflow->delegated_node, &delegated->head);
		sock_hold(mptcp_subflow_tcp_sock(subflow));
		if (schedule)
			napi_schedule(&delegated->napi);
	}
}

static inline struct mptcp_subflow_context *
mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)
{
	struct mptcp_subflow_context *ret;

	if (list_empty(&delegated->head))
		return NULL;

	ret = list_first_entry(&delegated->head, struct mptcp_subflow_context, delegated_node);
	list_del_init(&ret->delegated_node);
	return ret;
}

static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow)
{
	return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
}

static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow)
{
	/* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before
	 * touching the status bit
	 */
	smp_wmb();
	clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
}

int mptcp_is_enabled(struct net *net);
unsigned int mptcp_get_add_addr_timeout(struct net *net);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
				     struct mptcp_options_received *mp_opt);
bool mptcp_subflow_data_available(struct sock *sk);
void __init mptcp_subflow_init(void);
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
		     struct mptcp_subflow_context *subflow);
void mptcp_subflow_reset(struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);

/* called with sk socket lock held */
int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
			    const struct mptcp_addr_info *remote);
int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
			 struct sockaddr_storage *addr,
			 unsigned short family);

static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
					      struct mptcp_subflow_context *ctx)
{
	sk->sk_data_ready = ctx->tcp_data_ready;
	sk->sk_state_change = ctx->tcp_state_change;
	sk->sk_write_space = ctx->tcp_write_space;

	inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops;
}

void __init mptcp_proto_init(void);
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
int __init mptcp_proto_v6_init(void);
#endif

struct sock *mptcp_sk_clone(const struct sock *sk,
			    const struct mptcp_options_received *mp_opt,
			    struct request_sock *req);
void mptcp_get_options(const struct sk_buff *skb,
		       struct mptcp_options_received *mp_opt);

void mptcp_finish_connect(struct sock *sk);
static inline bool mptcp_is_fully_established(struct sock *sk)
{
	return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
	       READ_ONCE(mptcp_sk(sk)->fully_established);
}
void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
void mptcp_data_ready(struct sock *sk, struct sock *ssk);
bool mptcp_finish_join(struct sock *sk);
bool mptcp_schedule_work(struct sock *sk);
void __mptcp_check_push(struct sock *sk, struct sock *ssk);
void __mptcp_data_acked(struct sock *sk);
void mptcp_subflow_eof(struct sock *sk);
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
void __mptcp_flush_join_list(struct mptcp_sock *msk);
static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
{
	return READ_ONCE(msk->snd_data_fin_enable) &&
	       READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
}

static inline bool mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk)
{
	if ((sk->sk_userlocks & SOCK_SNDBUF_LOCK) || ssk->sk_sndbuf <= READ_ONCE(sk->sk_sndbuf))
		return false;

	WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf);
	return true;
}

static inline void mptcp_write_space(struct sock *sk)
{
	if (sk_stream_is_writeable(sk)) {
		/* pairs with memory barrier in mptcp_poll */
		smp_mb();
		if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags))
			sk_stream_write_space(sk);
	}
}

void mptcp_destroy_common(struct mptcp_sock *msk);

void __init mptcp_token_init(void);
static inline void mptcp_token_init_request(struct request_sock *req)
{
	mptcp_subflow_rsk(req)->token_node.pprev = NULL;
}

int mptcp_token_new_request(struct request_sock *req);
void mptcp_token_destroy_request(struct request_sock *req);
int mptcp_token_new_connect(struct sock *sk);
void mptcp_token_accept(struct mptcp_subflow_request_sock *r,
			struct mptcp_sock *msk);
bool mptcp_token_exists(u32 token);
struct mptcp_sock *mptcp_token_get_sock(u32 token);
struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot,
					 long *s_num);
void mptcp_token_destroy(struct mptcp_sock *msk);

void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn);

void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac);

void __init mptcp_pm_init(void);
void mptcp_pm_data_init(struct mptcp_sock *msk);
void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side);
void mptcp_pm_fully_established(struct mptcp_sock *msk);
bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
void mptcp_pm_connection_closed(struct mptcp_sock *msk);
void mptcp_pm_subflow_established(struct mptcp_sock *msk,
				  struct mptcp_subflow_context *subflow);
void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);
void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
				const struct mptcp_addr_info *addr);
void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id);
void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
				 struct mptcp_addr_info *addr,
				 u8 bkup);
void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
struct mptcp_pm_add_entry *
mptcp_pm_del_add_timer(struct mptcp_sock *msk,
		       struct mptcp_addr_info *addr);

int mptcp_pm_announce_addr(struct mptcp_sock *msk,
			   const struct mptcp_addr_info *addr,
			   bool echo, bool port);
int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id);
int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id);

static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
{
	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
}

static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk)
{
	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO);
}

static inline bool mptcp_pm_should_add_signal_ipv6(struct mptcp_sock *msk)
{
	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_IPV6);
}

static inline bool mptcp_pm_should_add_signal_port(struct mptcp_sock *msk)
{
	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_PORT);
}

static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
{
	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_RM_ADDR_SIGNAL);
}

static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
{
	u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;

	if (family == AF_INET6)
		len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
	if (!echo)
		len += MPTCPOPT_THMAC_LEN;
	if (port)
		len += TCPOLEN_MPTCP_PORT_LEN;

	return len;
}

bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
			      struct mptcp_addr_info *saddr, bool *echo, bool *port);
bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
			     u8 *rm_id);
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);

void __init mptcp_pm_nl_init(void);
void mptcp_pm_nl_data_init(struct mptcp_sock *msk);
void mptcp_pm_nl_work(struct mptcp_sock *msk);
void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk);
unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk);
unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk);

static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
{
	return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
}

void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);

static inline bool __mptcp_check_fallback(const struct mptcp_sock *msk)
{
	return test_bit(MPTCP_FALLBACK_DONE, &msk->flags);
}

static inline bool mptcp_check_fallback(const struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct mptcp_sock *msk = mptcp_sk(subflow->conn);

	return __mptcp_check_fallback(msk);
}

static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
{
	if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) {
		pr_debug("TCP fallback already done (msk=%p)", msk);
		return;
	}
	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
}

static inline void mptcp_do_fallback(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct mptcp_sock *msk = mptcp_sk(subflow->conn);

	__mptcp_do_fallback(msk);
}

#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)

static inline bool subflow_simultaneous_connect(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct sock *parent = subflow->conn;

	return sk->sk_state == TCP_ESTABLISHED &&
	       !mptcp_sk(parent)->pm.server_side &&
	       !subflow->conn_finished;
}

#ifdef CONFIG_SYN_COOKIES
void subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req,
				       struct sk_buff *skb);
bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req,
					struct sk_buff *skb);
void __init mptcp_join_cookie_init(void);
#else
static inline void
subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req,
				  struct sk_buff *skb) {}
static inline bool
mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req,
				   struct sk_buff *skb)
{
	return false;
}

static inline void mptcp_join_cookie_init(void) {}
#endif

#endif /* __MPTCP_PROTOCOL_H */