summaryrefslogtreecommitdiffstats
path: root/net/mptcp/subflow.c
blob: 0de2a44bdaa0aa82e84a800665c7d58e4e193040 (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
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
// SPDX-License-Identifier: GPL-2.0
/* Multipath TCP
 *
 * Copyright (c) 2017 - 2019, Intel Corporation.
 */

#define pr_fmt(fmt) "MPTCP: " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/protocol.h>
#include <net/tcp.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/ip6_route.h>
#endif
#include <net/mptcp.h>
#include "protocol.h"

static int subflow_rebuild_header(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	int err = 0;

	if (subflow->request_mptcp && !subflow->token) {
		pr_debug("subflow=%p", sk);
		err = mptcp_token_new_connect(sk);
	}

	if (err)
		return err;

	return subflow->icsk_af_ops->rebuild_header(sk);
}

static void subflow_req_destructor(struct request_sock *req)
{
	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);

	pr_debug("subflow_req=%p", subflow_req);

	if (subflow_req->mp_capable)
		mptcp_token_destroy_request(subflow_req->token);
	tcp_request_sock_ops.destructor(req);
}

static void subflow_init_req(struct request_sock *req,
			     const struct sock *sk_listener,
			     struct sk_buff *skb)
{
	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
	struct tcp_options_received rx_opt;

	pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);

	memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp));
	mptcp_get_options(skb, &rx_opt);

	subflow_req->mp_capable = 0;
	subflow_req->remote_key_valid = 0;

#ifdef CONFIG_TCP_MD5SIG
	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
	 * TCP option space.
	 */
	if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info))
		return;
#endif

	if (rx_opt.mptcp.mp_capable && listener->request_mptcp) {
		int err;

		err = mptcp_token_new_request(req);
		if (err == 0)
			subflow_req->mp_capable = 1;

		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
	}
}

static void subflow_v4_init_req(struct request_sock *req,
				const struct sock *sk_listener,
				struct sk_buff *skb)
{
	tcp_rsk(req)->is_mptcp = 1;

	tcp_request_sock_ipv4_ops.init_req(req, sk_listener, skb);

	subflow_init_req(req, sk_listener, skb);
}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static void subflow_v6_init_req(struct request_sock *req,
				const struct sock *sk_listener,
				struct sk_buff *skb)
{
	tcp_rsk(req)->is_mptcp = 1;

	tcp_request_sock_ipv6_ops.init_req(req, sk_listener, skb);

	subflow_init_req(req, sk_listener, skb);
}
#endif

static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);

	subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);

	if (subflow->conn && !subflow->conn_finished) {
		pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk),
			 subflow->remote_key);
		mptcp_finish_connect(sk);
		subflow->conn_finished = 1;

		if (skb) {
			pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq);
			subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
		}
	}
}

static struct request_sock_ops subflow_request_sock_ops;
static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops;

static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);

	pr_debug("subflow=%p", subflow);

	/* Never answer to SYNs sent to broadcast or multicast */
	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
		goto drop;

	return tcp_conn_request(&subflow_request_sock_ops,
				&subflow_request_sock_ipv4_ops,
				sk, skb);
drop:
	tcp_listendrop(sk);
	return 0;
}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops;
static struct inet_connection_sock_af_ops subflow_v6_specific;
static struct inet_connection_sock_af_ops subflow_v6m_specific;

static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);

	pr_debug("subflow=%p", subflow);

	if (skb->protocol == htons(ETH_P_IP))
		return subflow_v4_conn_request(sk, skb);

	if (!ipv6_unicast_destination(skb))
		goto drop;

	return tcp_conn_request(&subflow_request_sock_ops,
				&subflow_request_sock_ipv6_ops, sk, skb);

drop:
	tcp_listendrop(sk);
	return 0; /* don't send reset */
}
#endif

static struct sock *subflow_syn_recv_sock(const struct sock *sk,
					  struct sk_buff *skb,
					  struct request_sock *req,
					  struct dst_entry *dst,
					  struct request_sock *req_unhash,
					  bool *own_req)
{
	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
	struct mptcp_subflow_request_sock *subflow_req;
	struct tcp_options_received opt_rx;
	struct sock *child;

	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);

	if (tcp_rsk(req)->is_mptcp == 0)
		goto create_child;

	/* if the sk is MP_CAPABLE, we try to fetch the client key */
	subflow_req = mptcp_subflow_rsk(req);
	if (subflow_req->mp_capable) {
		if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) {
			/* here we can receive and accept an in-window,
			 * out-of-order pkt, which will not carry the MP_CAPABLE
			 * opt even on mptcp enabled paths
			 */
			goto create_child;
		}

		opt_rx.mptcp.mp_capable = 0;
		mptcp_get_options(skb, &opt_rx);
		if (opt_rx.mptcp.mp_capable) {
			subflow_req->remote_key = opt_rx.mptcp.sndr_key;
			subflow_req->remote_key_valid = 1;
		} else {
			subflow_req->mp_capable = 0;
		}
	}

create_child:
	child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
						     req_unhash, own_req);

	if (child && *own_req) {
		struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);

		/* we have null ctx on TCP fallback, not fatal on MPC
		 * handshake
		 */
		if (!ctx)
			return child;

		if (ctx->mp_capable) {
			if (mptcp_token_new_accept(ctx->token))
				goto close_child;
		}
	}

	return child;

close_child:
	pr_debug("closing child socket");
	tcp_send_active_reset(child, GFP_ATOMIC);
	inet_csk_prepare_forced_close(child);
	tcp_done(child);
	return NULL;
}

static struct inet_connection_sock_af_ops subflow_specific;

enum mapping_status {
	MAPPING_OK,
	MAPPING_INVALID,
	MAPPING_EMPTY,
	MAPPING_DATA_FIN
};

static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq)
{
	if ((u32)seq == (u32)old_seq)
		return old_seq;

	/* Assume map covers data not mapped yet. */
	return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32));
}

static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
	WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
		  ssn, subflow->map_subflow_seq, subflow->map_data_len);
}

static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	unsigned int skb_consumed;

	skb_consumed = tcp_sk(ssk)->copied_seq - TCP_SKB_CB(skb)->seq;
	if (WARN_ON_ONCE(skb_consumed >= skb->len))
		return true;

	return skb->len - skb_consumed <= subflow->map_data_len -
					  mptcp_subflow_get_map_offset(subflow);
}

static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	u32 ssn = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;

	if (unlikely(before(ssn, subflow->map_subflow_seq))) {
		/* Mapping covers data later in the subflow stream,
		 * currently unsupported.
		 */
		warn_bad_map(subflow, ssn);
		return false;
	}
	if (unlikely(!before(ssn, subflow->map_subflow_seq +
				  subflow->map_data_len))) {
		/* Mapping does covers past subflow data, invalid */
		warn_bad_map(subflow, ssn + skb->len);
		return false;
	}
	return true;
}

static enum mapping_status get_mapping_status(struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	struct mptcp_ext *mpext;
	struct sk_buff *skb;
	u16 data_len;
	u64 map_seq;

	skb = skb_peek(&ssk->sk_receive_queue);
	if (!skb)
		return MAPPING_EMPTY;

	mpext = mptcp_get_ext(skb);
	if (!mpext || !mpext->use_map) {
		if (!subflow->map_valid && !skb->len) {
			/* the TCP stack deliver 0 len FIN pkt to the receive
			 * queue, that is the only 0len pkts ever expected here,
			 * and we can admit no mapping only for 0 len pkts
			 */
			if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
				WARN_ONCE(1, "0len seq %d:%d flags %x",
					  TCP_SKB_CB(skb)->seq,
					  TCP_SKB_CB(skb)->end_seq,
					  TCP_SKB_CB(skb)->tcp_flags);
			sk_eat_skb(ssk, skb);
			return MAPPING_EMPTY;
		}

		if (!subflow->map_valid)
			return MAPPING_INVALID;

		goto validate_seq;
	}

	pr_debug("seq=%llu is64=%d ssn=%u data_len=%u data_fin=%d",
		 mpext->data_seq, mpext->dsn64, mpext->subflow_seq,
		 mpext->data_len, mpext->data_fin);

	data_len = mpext->data_len;
	if (data_len == 0) {
		pr_err("Infinite mapping not handled");
		return MAPPING_INVALID;
	}

	if (mpext->data_fin == 1) {
		if (data_len == 1) {
			pr_debug("DATA_FIN with no payload");
			if (subflow->map_valid) {
				/* A DATA_FIN might arrive in a DSS
				 * option before the previous mapping
				 * has been fully consumed. Continue
				 * handling the existing mapping.
				 */
				skb_ext_del(skb, SKB_EXT_MPTCP);
				return MAPPING_OK;
			} else {
				return MAPPING_DATA_FIN;
			}
		}

		/* Adjust for DATA_FIN using 1 byte of sequence space */
		data_len--;
	}

	if (!mpext->dsn64) {
		map_seq = expand_seq(subflow->map_seq, subflow->map_data_len,
				     mpext->data_seq);
		pr_debug("expanded seq=%llu", subflow->map_seq);
	} else {
		map_seq = mpext->data_seq;
	}

	if (subflow->map_valid) {
		/* Allow replacing only with an identical map */
		if (subflow->map_seq == map_seq &&
		    subflow->map_subflow_seq == mpext->subflow_seq &&
		    subflow->map_data_len == data_len) {
			skb_ext_del(skb, SKB_EXT_MPTCP);
			return MAPPING_OK;
		}

		/* If this skb data are fully covered by the current mapping,
		 * the new map would need caching, which is not supported
		 */
		if (skb_is_fully_mapped(ssk, skb))
			return MAPPING_INVALID;

		/* will validate the next map after consuming the current one */
		return MAPPING_OK;
	}

	subflow->map_seq = map_seq;
	subflow->map_subflow_seq = mpext->subflow_seq;
	subflow->map_data_len = data_len;
	subflow->map_valid = 1;
	subflow->mpc_map = mpext->mpc_map;
	pr_debug("new map seq=%llu subflow_seq=%u data_len=%u",
		 subflow->map_seq, subflow->map_subflow_seq,
		 subflow->map_data_len);

validate_seq:
	/* we revalidate valid mapping on new skb, because we must ensure
	 * the current skb is completely covered by the available mapping
	 */
	if (!validate_mapping(ssk, skb))
		return MAPPING_INVALID;

	skb_ext_del(skb, SKB_EXT_MPTCP);
	return MAPPING_OK;
}

static int subflow_read_actor(read_descriptor_t *desc,
			      struct sk_buff *skb,
			      unsigned int offset, size_t len)
{
	size_t copy_len = min(desc->count, len);

	desc->count -= copy_len;

	pr_debug("flushed %zu bytes, %zu left", copy_len, desc->count);
	return copy_len;
}

static bool subflow_check_data_avail(struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	enum mapping_status status;
	struct mptcp_sock *msk;
	struct sk_buff *skb;

	pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk,
		 subflow->data_avail, skb_peek(&ssk->sk_receive_queue));
	if (subflow->data_avail)
		return true;

	if (!subflow->conn)
		return false;

	msk = mptcp_sk(subflow->conn);
	for (;;) {
		u32 map_remaining;
		size_t delta;
		u64 ack_seq;
		u64 old_ack;

		status = get_mapping_status(ssk);
		pr_debug("msk=%p ssk=%p status=%d", msk, ssk, status);
		if (status == MAPPING_INVALID) {
			ssk->sk_err = EBADMSG;
			goto fatal;
		}

		if (status != MAPPING_OK)
			return false;

		skb = skb_peek(&ssk->sk_receive_queue);
		if (WARN_ON_ONCE(!skb))
			return false;

		/* if msk lacks the remote key, this subflow must provide an
		 * MP_CAPABLE-based mapping
		 */
		if (unlikely(!READ_ONCE(msk->can_ack))) {
			if (!subflow->mpc_map) {
				ssk->sk_err = EBADMSG;
				goto fatal;
			}
			WRITE_ONCE(msk->remote_key, subflow->remote_key);
			WRITE_ONCE(msk->ack_seq, subflow->map_seq);
			WRITE_ONCE(msk->can_ack, true);
		}

		old_ack = READ_ONCE(msk->ack_seq);
		ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
		pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
			 ack_seq);
		if (ack_seq == old_ack)
			break;

		/* only accept in-sequence mapping. Old values are spurious
		 * retransmission; we can hit "future" values on active backup
		 * subflow switch, we relay on retransmissions to get
		 * in-sequence data.
		 * Cuncurrent subflows support will require subflow data
		 * reordering
		 */
		map_remaining = subflow->map_data_len -
				mptcp_subflow_get_map_offset(subflow);
		if (before64(ack_seq, old_ack))
			delta = min_t(size_t, old_ack - ack_seq, map_remaining);
		else
			delta = min_t(size_t, ack_seq - old_ack, map_remaining);

		/* discard mapped data */
		pr_debug("discarding %zu bytes, current map len=%d", delta,
			 map_remaining);
		if (delta) {
			read_descriptor_t desc = {
				.count = delta,
			};
			int ret;

			ret = tcp_read_sock(ssk, &desc, subflow_read_actor);
			if (ret < 0) {
				ssk->sk_err = -ret;
				goto fatal;
			}
			if (ret < delta)
				return false;
			if (delta == map_remaining)
				subflow->map_valid = 0;
		}
	}
	return true;

fatal:
	/* fatal protocol error, close the socket */
	/* This barrier is coupled with smp_rmb() in tcp_poll() */
	smp_wmb();
	ssk->sk_error_report(ssk);
	tcp_set_state(ssk, TCP_CLOSE);
	tcp_send_active_reset(ssk, GFP_ATOMIC);
	return false;
}

bool mptcp_subflow_data_available(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct sk_buff *skb;

	/* check if current mapping is still valid */
	if (subflow->map_valid &&
	    mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) {
		subflow->map_valid = 0;
		subflow->data_avail = 0;

		pr_debug("Done with mapping: seq=%u data_len=%u",
			 subflow->map_subflow_seq,
			 subflow->map_data_len);
	}

	if (!subflow_check_data_avail(sk)) {
		subflow->data_avail = 0;
		return false;
	}

	skb = skb_peek(&sk->sk_receive_queue);
	subflow->data_avail = skb &&
		       before(tcp_sk(sk)->copied_seq, TCP_SKB_CB(skb)->end_seq);
	return subflow->data_avail;
}

static void subflow_data_ready(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct sock *parent = subflow->conn;

	if (!parent || !subflow->mp_capable) {
		subflow->tcp_data_ready(sk);

		if (parent)
			parent->sk_data_ready(parent);
		return;
	}

	if (mptcp_subflow_data_available(sk))
		mptcp_data_ready(parent, sk);
}

static void subflow_write_space(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct sock *parent = subflow->conn;

	sk_stream_write_space(sk);
	if (parent && sk_stream_is_writeable(sk)) {
		set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
		smp_mb__after_atomic();
		/* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
		sk_stream_write_space(parent);
	}
}

static struct inet_connection_sock_af_ops *
subflow_default_af_ops(struct sock *sk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	if (sk->sk_family == AF_INET6)
		return &subflow_v6_specific;
#endif
	return &subflow_specific;
}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_connection_sock_af_ops *target;

	target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk);

	pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d",
		 subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped);

	if (likely(icsk->icsk_af_ops == target))
		return;

	subflow->icsk_af_ops = icsk->icsk_af_ops;
	icsk->icsk_af_ops = target;
}
#endif

int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
{
	struct mptcp_subflow_context *subflow;
	struct net *net = sock_net(sk);
	struct socket *sf;
	int err;

	err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP,
			       &sf);
	if (err)
		return err;

	lock_sock(sf->sk);

	/* kernel sockets do not by default acquire net ref, but TCP timer
	 * needs it.
	 */
	sf->sk->sk_net_refcnt = 1;
	get_net(net);
#ifdef CONFIG_PROC_FS
	this_cpu_add(*net->core.sock_inuse, 1);
#endif
	err = tcp_set_ulp(sf->sk, "mptcp");
	release_sock(sf->sk);

	if (err)
		return err;

	subflow = mptcp_subflow_ctx(sf->sk);
	pr_debug("subflow=%p", subflow);

	*new_sock = sf;
	sock_hold(sk);
	subflow->conn = sk;

	return 0;
}

static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
							gfp_t priority)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct mptcp_subflow_context *ctx;

	ctx = kzalloc(sizeof(*ctx), priority);
	if (!ctx)
		return NULL;

	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
	INIT_LIST_HEAD(&ctx->node);

	pr_debug("subflow=%p", ctx);

	ctx->tcp_sock = sk;

	return ctx;
}

static void __subflow_state_change(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (skwq_has_sleeper(wq))
		wake_up_interruptible_all(&wq->wait);
	rcu_read_unlock();
}

static bool subflow_is_done(const struct sock *sk)
{
	return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
}

static void subflow_state_change(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct sock *parent = READ_ONCE(subflow->conn);

	__subflow_state_change(sk);

	/* as recvmsg() does not acquire the subflow socket for ssk selection
	 * a fin packet carrying a DSS can be unnoticed if we don't trigger
	 * the data available machinery here.
	 */
	if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk))
		mptcp_data_ready(parent, sk);

	if (parent && !(parent->sk_shutdown & RCV_SHUTDOWN) &&
	    !subflow->rx_eof && subflow_is_done(sk)) {
		subflow->rx_eof = 1;
		parent->sk_shutdown |= RCV_SHUTDOWN;
		__subflow_state_change(parent);
	}
}

static int subflow_ulp_init(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct mptcp_subflow_context *ctx;
	struct tcp_sock *tp = tcp_sk(sk);
	int err = 0;

	/* disallow attaching ULP to a socket unless it has been
	 * created with sock_create_kern()
	 */
	if (!sk->sk_kern_sock) {
		err = -EOPNOTSUPP;
		goto out;
	}

	ctx = subflow_create_ctx(sk, GFP_KERNEL);
	if (!ctx) {
		err = -ENOMEM;
		goto out;
	}

	pr_debug("subflow=%p, family=%d", ctx, sk->sk_family);

	tp->is_mptcp = 1;
	ctx->icsk_af_ops = icsk->icsk_af_ops;
	icsk->icsk_af_ops = subflow_default_af_ops(sk);
	ctx->tcp_data_ready = sk->sk_data_ready;
	ctx->tcp_state_change = sk->sk_state_change;
	ctx->tcp_write_space = sk->sk_write_space;
	sk->sk_data_ready = subflow_data_ready;
	sk->sk_write_space = subflow_write_space;
	sk->sk_state_change = subflow_state_change;
out:
	return err;
}

static void subflow_ulp_release(struct sock *sk)
{
	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(sk);

	if (!ctx)
		return;

	if (ctx->conn)
		sock_put(ctx->conn);

	kfree_rcu(ctx, rcu);
}

static void subflow_ulp_fallback(struct sock *sk,
				 struct mptcp_subflow_context *old_ctx)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	mptcp_subflow_tcp_fallback(sk, old_ctx);
	icsk->icsk_ulp_ops = NULL;
	rcu_assign_pointer(icsk->icsk_ulp_data, NULL);
	tcp_sk(sk)->is_mptcp = 0;
}

static void subflow_ulp_clone(const struct request_sock *req,
			      struct sock *newsk,
			      const gfp_t priority)
{
	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
	struct mptcp_subflow_context *old_ctx = mptcp_subflow_ctx(newsk);
	struct mptcp_subflow_context *new_ctx;

	if (!tcp_rsk(req)->is_mptcp || !subflow_req->mp_capable) {
		subflow_ulp_fallback(newsk, old_ctx);
		return;
	}

	new_ctx = subflow_create_ctx(newsk, priority);
	if (!new_ctx) {
		subflow_ulp_fallback(newsk, old_ctx);
		return;
	}

	/* see comments in subflow_syn_recv_sock(), MPTCP connection is fully
	 * established only after we receive the remote key
	 */
	new_ctx->conn_finished = 1;
	new_ctx->icsk_af_ops = old_ctx->icsk_af_ops;
	new_ctx->tcp_data_ready = old_ctx->tcp_data_ready;
	new_ctx->tcp_state_change = old_ctx->tcp_state_change;
	new_ctx->tcp_write_space = old_ctx->tcp_write_space;
	new_ctx->mp_capable = 1;
	new_ctx->fourth_ack = subflow_req->remote_key_valid;
	new_ctx->can_ack = subflow_req->remote_key_valid;
	new_ctx->remote_key = subflow_req->remote_key;
	new_ctx->local_key = subflow_req->local_key;
	new_ctx->token = subflow_req->token;
	new_ctx->ssn_offset = subflow_req->ssn_offset;
	new_ctx->idsn = subflow_req->idsn;
}

static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = {
	.name		= "mptcp",
	.owner		= THIS_MODULE,
	.init		= subflow_ulp_init,
	.release	= subflow_ulp_release,
	.clone		= subflow_ulp_clone,
};

static int subflow_ops_init(struct request_sock_ops *subflow_ops)
{
	subflow_ops->obj_size = sizeof(struct mptcp_subflow_request_sock);
	subflow_ops->slab_name = "request_sock_subflow";

	subflow_ops->slab = kmem_cache_create(subflow_ops->slab_name,
					      subflow_ops->obj_size, 0,
					      SLAB_ACCOUNT |
					      SLAB_TYPESAFE_BY_RCU,
					      NULL);
	if (!subflow_ops->slab)
		return -ENOMEM;

	subflow_ops->destructor = subflow_req_destructor;

	return 0;
}

void mptcp_subflow_init(void)
{
	subflow_request_sock_ops = tcp_request_sock_ops;
	if (subflow_ops_init(&subflow_request_sock_ops) != 0)
		panic("MPTCP: failed to init subflow request sock ops\n");

	subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops;
	subflow_request_sock_ipv4_ops.init_req = subflow_v4_init_req;

	subflow_specific = ipv4_specific;
	subflow_specific.conn_request = subflow_v4_conn_request;
	subflow_specific.syn_recv_sock = subflow_syn_recv_sock;
	subflow_specific.sk_rx_dst_set = subflow_finish_connect;
	subflow_specific.rebuild_header = subflow_rebuild_header;

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops;
	subflow_request_sock_ipv6_ops.init_req = subflow_v6_init_req;

	subflow_v6_specific = ipv6_specific;
	subflow_v6_specific.conn_request = subflow_v6_conn_request;
	subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock;
	subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect;
	subflow_v6_specific.rebuild_header = subflow_rebuild_header;

	subflow_v6m_specific = subflow_v6_specific;
	subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit;
	subflow_v6m_specific.send_check = ipv4_specific.send_check;
	subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len;
	subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced;
	subflow_v6m_specific.net_frag_header_len = 0;
#endif

	if (tcp_register_ulp(&subflow_ulp_ops) != 0)
		panic("MPTCP: failed to register subflows to ULP\n");
}