summaryrefslogtreecommitdiffstats
path: root/net/mptcp/sockopt.c
blob: dcd1c76d2a3ba1ccc31a3e9279f725cd6d433782 (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
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
// SPDX-License-Identifier: GPL-2.0
/* Multipath TCP
 *
 * Copyright (c) 2021, Red Hat.
 */

#define pr_fmt(fmt) "MPTCP: " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <net/sock.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <net/mptcp.h>
#include "protocol.h"

#define MIN_INFO_OPTLEN_SIZE		16
#define MIN_FULL_INFO_OPTLEN_SIZE	40

static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
{
	msk_owned_by_me(msk);

	if (likely(!__mptcp_check_fallback(msk)))
		return NULL;

	return msk->first;
}

static u32 sockopt_seq_reset(const struct sock *sk)
{
	sock_owned_by_me(sk);

	/* Highbits contain state.  Allows to distinguish sockopt_seq
	 * of listener and established:
	 * s0 = new_listener()
	 * sockopt(s0) - seq is 1
	 * s1 = accept(s0) - s1 inherits seq 1 if listener sk (s0)
	 * sockopt(s0) - seq increments to 2 on s0
	 * sockopt(s1) // seq increments to 2 on s1 (different option)
	 * new ssk completes join, inherits options from s0 // seq 2
	 * Needs sync from mptcp join logic, but ssk->seq == msk->seq
	 *
	 * Set High order bits to sk_state so ssk->seq == msk->seq test
	 * will fail.
	 */

	return (u32)sk->sk_state << 24u;
}

static void sockopt_seq_inc(struct mptcp_sock *msk)
{
	u32 seq = (msk->setsockopt_seq + 1) & 0x00ffffff;

	msk->setsockopt_seq = sockopt_seq_reset((struct sock *)msk) + seq;
}

static int mptcp_get_int_option(struct mptcp_sock *msk, sockptr_t optval,
				unsigned int optlen, int *val)
{
	if (optlen < sizeof(int))
		return -EINVAL;

	if (copy_from_sockptr(val, optval, sizeof(*val)))
		return -EFAULT;

	return 0;
}

static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, int val)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;

	lock_sock(sk);
	sockopt_seq_inc(msk);

	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		bool slow = lock_sock_fast(ssk);

		switch (optname) {
		case SO_DEBUG:
			sock_valbool_flag(ssk, SOCK_DBG, !!val);
			break;
		case SO_KEEPALIVE:
			if (ssk->sk_prot->keepalive)
				ssk->sk_prot->keepalive(ssk, !!val);
			sock_valbool_flag(ssk, SOCK_KEEPOPEN, !!val);
			break;
		case SO_PRIORITY:
			WRITE_ONCE(ssk->sk_priority, val);
			break;
		case SO_SNDBUF:
		case SO_SNDBUFFORCE:
			ssk->sk_userlocks |= SOCK_SNDBUF_LOCK;
			WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf);
			mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf;
			break;
		case SO_RCVBUF:
		case SO_RCVBUFFORCE:
			ssk->sk_userlocks |= SOCK_RCVBUF_LOCK;
			WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf);
			break;
		case SO_MARK:
			if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) {
				WRITE_ONCE(ssk->sk_mark, sk->sk_mark);
				sk_dst_reset(ssk);
			}
			break;
		case SO_INCOMING_CPU:
			WRITE_ONCE(ssk->sk_incoming_cpu, val);
			break;
		}

		subflow->setsockopt_seq = msk->setsockopt_seq;
		unlock_sock_fast(ssk, slow);
	}

	release_sock(sk);
}

static int mptcp_sol_socket_intval(struct mptcp_sock *msk, int optname, int val)
{
	sockptr_t optval = KERNEL_SOCKPTR(&val);
	struct sock *sk = (struct sock *)msk;
	int ret;

	ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
			      optval, sizeof(val));
	if (ret)
		return ret;

	mptcp_sol_socket_sync_intval(msk, optname, val);
	return 0;
}

static void mptcp_so_incoming_cpu(struct mptcp_sock *msk, int val)
{
	struct sock *sk = (struct sock *)msk;

	WRITE_ONCE(sk->sk_incoming_cpu, val);

	mptcp_sol_socket_sync_intval(msk, SO_INCOMING_CPU, val);
}

static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optname, int val)
{
	sockptr_t optval = KERNEL_SOCKPTR(&val);
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	int ret;

	ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
			      optval, sizeof(val));
	if (ret)
		return ret;

	lock_sock(sk);
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		bool slow = lock_sock_fast(ssk);

		sock_set_timestamp(sk, optname, !!val);
		unlock_sock_fast(ssk, slow);
	}

	release_sock(sk);
	return 0;
}

static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
					   sockptr_t optval,
					   unsigned int optlen)
{
	int val, ret;

	ret = mptcp_get_int_option(msk, optval, optlen, &val);
	if (ret)
		return ret;

	switch (optname) {
	case SO_KEEPALIVE:
		mptcp_sol_socket_sync_intval(msk, optname, val);
		return 0;
	case SO_DEBUG:
	case SO_MARK:
	case SO_PRIORITY:
	case SO_SNDBUF:
	case SO_SNDBUFFORCE:
	case SO_RCVBUF:
	case SO_RCVBUFFORCE:
		return mptcp_sol_socket_intval(msk, optname, val);
	case SO_INCOMING_CPU:
		mptcp_so_incoming_cpu(msk, val);
		return 0;
	case SO_TIMESTAMP_OLD:
	case SO_TIMESTAMP_NEW:
	case SO_TIMESTAMPNS_OLD:
	case SO_TIMESTAMPNS_NEW:
		return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val);
	}

	return -ENOPROTOOPT;
}

static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk,
						    int optname,
						    sockptr_t optval,
						    unsigned int optlen)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	struct so_timestamping timestamping;
	int ret;

	if (optlen == sizeof(timestamping)) {
		if (copy_from_sockptr(&timestamping, optval,
				      sizeof(timestamping)))
			return -EFAULT;
	} else if (optlen == sizeof(int)) {
		memset(&timestamping, 0, sizeof(timestamping));

		if (copy_from_sockptr(&timestamping.flags, optval, sizeof(int)))
			return -EFAULT;
	} else {
		return -EINVAL;
	}

	ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
			      KERNEL_SOCKPTR(&timestamping),
			      sizeof(timestamping));
	if (ret)
		return ret;

	lock_sock(sk);

	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		bool slow = lock_sock_fast(ssk);

		sock_set_timestamping(sk, optname, timestamping);
		unlock_sock_fast(ssk, slow);
	}

	release_sock(sk);

	return 0;
}

static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval,
					      unsigned int optlen)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	struct linger ling;
	sockptr_t kopt;
	int ret;

	if (optlen < sizeof(ling))
		return -EINVAL;

	if (copy_from_sockptr(&ling, optval, sizeof(ling)))
		return -EFAULT;

	kopt = KERNEL_SOCKPTR(&ling);
	ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, SO_LINGER, kopt, sizeof(ling));
	if (ret)
		return ret;

	lock_sock(sk);
	sockopt_seq_inc(msk);
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		bool slow = lock_sock_fast(ssk);

		if (!ling.l_onoff) {
			sock_reset_flag(ssk, SOCK_LINGER);
		} else {
			ssk->sk_lingertime = sk->sk_lingertime;
			sock_set_flag(ssk, SOCK_LINGER);
		}

		subflow->setsockopt_seq = msk->setsockopt_seq;
		unlock_sock_fast(ssk, slow);
	}

	release_sock(sk);
	return 0;
}

static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
				       sockptr_t optval, unsigned int optlen)
{
	struct sock *sk = (struct sock *)msk;
	struct sock *ssk;
	int ret;

	switch (optname) {
	case SO_REUSEPORT:
	case SO_REUSEADDR:
	case SO_BINDTODEVICE:
	case SO_BINDTOIFINDEX:
		lock_sock(sk);
		ssk = __mptcp_nmpc_sk(msk);
		if (IS_ERR(ssk)) {
			release_sock(sk);
			return PTR_ERR(ssk);
		}

		ret = sk_setsockopt(ssk, SOL_SOCKET, optname, optval, optlen);
		if (ret == 0) {
			if (optname == SO_REUSEPORT)
				sk->sk_reuseport = ssk->sk_reuseport;
			else if (optname == SO_REUSEADDR)
				sk->sk_reuse = ssk->sk_reuse;
			else if (optname == SO_BINDTODEVICE)
				sk->sk_bound_dev_if = ssk->sk_bound_dev_if;
			else if (optname == SO_BINDTOIFINDEX)
				sk->sk_bound_dev_if = ssk->sk_bound_dev_if;
		}
		release_sock(sk);
		return ret;
	case SO_KEEPALIVE:
	case SO_PRIORITY:
	case SO_SNDBUF:
	case SO_SNDBUFFORCE:
	case SO_RCVBUF:
	case SO_RCVBUFFORCE:
	case SO_MARK:
	case SO_INCOMING_CPU:
	case SO_DEBUG:
	case SO_TIMESTAMP_OLD:
	case SO_TIMESTAMP_NEW:
	case SO_TIMESTAMPNS_OLD:
	case SO_TIMESTAMPNS_NEW:
		return mptcp_setsockopt_sol_socket_int(msk, optname, optval,
						       optlen);
	case SO_TIMESTAMPING_OLD:
	case SO_TIMESTAMPING_NEW:
		return mptcp_setsockopt_sol_socket_timestamping(msk, optname,
								optval, optlen);
	case SO_LINGER:
		return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen);
	case SO_RCVLOWAT:
	case SO_RCVTIMEO_OLD:
	case SO_RCVTIMEO_NEW:
	case SO_SNDTIMEO_OLD:
	case SO_SNDTIMEO_NEW:
	case SO_BUSY_POLL:
	case SO_PREFER_BUSY_POLL:
	case SO_BUSY_POLL_BUDGET:
		/* No need to copy: only relevant for msk */
		return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);
	case SO_NO_CHECK:
	case SO_DONTROUTE:
	case SO_BROADCAST:
	case SO_BSDCOMPAT:
	case SO_PASSCRED:
	case SO_PASSPIDFD:
	case SO_PASSSEC:
	case SO_RXQ_OVFL:
	case SO_WIFI_STATUS:
	case SO_NOFCS:
	case SO_SELECT_ERR_QUEUE:
		return 0;
	}

	/* SO_OOBINLINE is not supported, let's avoid the related mess
	 * SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF,
	 * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER,
	 * we must be careful with subflows
	 *
	 * SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks
	 * explicitly the sk_protocol field
	 *
	 * SO_PEEK_OFF is unsupported, as it is for plain TCP
	 * SO_MAX_PACING_RATE is unsupported, we must be careful with subflows
	 * SO_CNX_ADVICE is currently unsupported, could possibly be relevant,
	 * but likely needs careful design
	 *
	 * SO_ZEROCOPY is currently unsupported, TODO in sndmsg
	 * SO_TXTIME is currently unsupported
	 */

	return -EOPNOTSUPP;
}

static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
			       sockptr_t optval, unsigned int optlen)
{
	struct sock *sk = (struct sock *)msk;
	int ret = -EOPNOTSUPP;
	struct sock *ssk;

	switch (optname) {
	case IPV6_V6ONLY:
	case IPV6_TRANSPARENT:
	case IPV6_FREEBIND:
		lock_sock(sk);
		ssk = __mptcp_nmpc_sk(msk);
		if (IS_ERR(ssk)) {
			release_sock(sk);
			return PTR_ERR(ssk);
		}

		ret = tcp_setsockopt(ssk, SOL_IPV6, optname, optval, optlen);
		if (ret != 0) {
			release_sock(sk);
			return ret;
		}

		sockopt_seq_inc(msk);

		switch (optname) {
		case IPV6_V6ONLY:
			sk->sk_ipv6only = ssk->sk_ipv6only;
			break;
		case IPV6_TRANSPARENT:
			inet_assign_bit(TRANSPARENT, sk,
					inet_test_bit(TRANSPARENT, ssk));
			break;
		case IPV6_FREEBIND:
			inet_assign_bit(FREEBIND, sk,
					inet_test_bit(FREEBIND, ssk));
			break;
		}

		release_sock(sk);
		break;
	}

	return ret;
}

static bool mptcp_supported_sockopt(int level, int optname)
{
	if (level == SOL_IP) {
		switch (optname) {
		/* should work fine */
		case IP_FREEBIND:
		case IP_TRANSPARENT:
		case IP_BIND_ADDRESS_NO_PORT:
		case IP_LOCAL_PORT_RANGE:

		/* the following are control cmsg related */
		case IP_PKTINFO:
		case IP_RECVTTL:
		case IP_RECVTOS:
		case IP_RECVOPTS:
		case IP_RETOPTS:
		case IP_PASSSEC:
		case IP_RECVORIGDSTADDR:
		case IP_CHECKSUM:
		case IP_RECVFRAGSIZE:

		/* common stuff that need some love */
		case IP_TOS:
		case IP_TTL:
		case IP_MTU_DISCOVER:
		case IP_RECVERR:

		/* possibly less common may deserve some love */
		case IP_MINTTL:

		/* the following is apparently a no-op for plain TCP */
		case IP_RECVERR_RFC4884:
			return true;
		}

		/* IP_OPTIONS is not supported, needs subflow care */
		/* IP_HDRINCL, IP_NODEFRAG are not supported, RAW specific */
		/* IP_MULTICAST_TTL, IP_MULTICAST_LOOP, IP_UNICAST_IF,
		 * IP_ADD_MEMBERSHIP, IP_ADD_SOURCE_MEMBERSHIP, IP_DROP_MEMBERSHIP,
		 * IP_DROP_SOURCE_MEMBERSHIP, IP_BLOCK_SOURCE, IP_UNBLOCK_SOURCE,
		 * MCAST_JOIN_GROUP, MCAST_LEAVE_GROUP MCAST_JOIN_SOURCE_GROUP,
		 * MCAST_LEAVE_SOURCE_GROUP, MCAST_BLOCK_SOURCE, MCAST_UNBLOCK_SOURCE,
		 * MCAST_MSFILTER, IP_MULTICAST_ALL are not supported, better not deal
		 * with mcast stuff
		 */
		/* IP_IPSEC_POLICY, IP_XFRM_POLICY are nut supported, unrelated here */
		return false;
	}
	if (level == SOL_IPV6) {
		switch (optname) {
		case IPV6_V6ONLY:

		/* the following are control cmsg related */
		case IPV6_RECVPKTINFO:
		case IPV6_2292PKTINFO:
		case IPV6_RECVHOPLIMIT:
		case IPV6_2292HOPLIMIT:
		case IPV6_RECVRTHDR:
		case IPV6_2292RTHDR:
		case IPV6_RECVHOPOPTS:
		case IPV6_2292HOPOPTS:
		case IPV6_RECVDSTOPTS:
		case IPV6_2292DSTOPTS:
		case IPV6_RECVTCLASS:
		case IPV6_FLOWINFO:
		case IPV6_RECVPATHMTU:
		case IPV6_RECVORIGDSTADDR:
		case IPV6_RECVFRAGSIZE:

		/* the following ones need some love but are quite common */
		case IPV6_TCLASS:
		case IPV6_TRANSPARENT:
		case IPV6_FREEBIND:
		case IPV6_PKTINFO:
		case IPV6_2292PKTOPTIONS:
		case IPV6_UNICAST_HOPS:
		case IPV6_MTU_DISCOVER:
		case IPV6_MTU:
		case IPV6_RECVERR:
		case IPV6_FLOWINFO_SEND:
		case IPV6_FLOWLABEL_MGR:
		case IPV6_MINHOPCOUNT:
		case IPV6_DONTFRAG:
		case IPV6_AUTOFLOWLABEL:

		/* the following one is a no-op for plain TCP */
		case IPV6_RECVERR_RFC4884:
			return true;
		}

		/* IPV6_HOPOPTS, IPV6_RTHDRDSTOPTS, IPV6_RTHDR, IPV6_DSTOPTS are
		 * not supported
		 */
		/* IPV6_MULTICAST_HOPS, IPV6_MULTICAST_LOOP, IPV6_UNICAST_IF,
		 * IPV6_MULTICAST_IF, IPV6_ADDRFORM,
		 * IPV6_ADD_MEMBERSHIP, IPV6_DROP_MEMBERSHIP, IPV6_JOIN_ANYCAST,
		 * IPV6_LEAVE_ANYCAST, IPV6_MULTICAST_ALL, MCAST_JOIN_GROUP, MCAST_LEAVE_GROUP,
		 * MCAST_JOIN_SOURCE_GROUP, MCAST_LEAVE_SOURCE_GROUP,
		 * MCAST_BLOCK_SOURCE, MCAST_UNBLOCK_SOURCE, MCAST_MSFILTER
		 * are not supported better not deal with mcast
		 */
		/* IPV6_ROUTER_ALERT, IPV6_ROUTER_ALERT_ISOLATE are not supported, since are evil */

		/* IPV6_IPSEC_POLICY, IPV6_XFRM_POLICY are not supported */
		/* IPV6_ADDR_PREFERENCES is not supported, we must be careful with subflows */
		return false;
	}
	if (level == SOL_TCP) {
		switch (optname) {
		/* the following are no-op or should work just fine */
		case TCP_THIN_DUPACK:
		case TCP_DEFER_ACCEPT:

		/* the following need some love */
		case TCP_MAXSEG:
		case TCP_NODELAY:
		case TCP_THIN_LINEAR_TIMEOUTS:
		case TCP_CONGESTION:
		case TCP_CORK:
		case TCP_KEEPIDLE:
		case TCP_KEEPINTVL:
		case TCP_KEEPCNT:
		case TCP_SYNCNT:
		case TCP_SAVE_SYN:
		case TCP_LINGER2:
		case TCP_WINDOW_CLAMP:
		case TCP_QUICKACK:
		case TCP_USER_TIMEOUT:
		case TCP_TIMESTAMP:
		case TCP_NOTSENT_LOWAT:
		case TCP_TX_DELAY:
		case TCP_INQ:
		case TCP_FASTOPEN:
		case TCP_FASTOPEN_CONNECT:
		case TCP_FASTOPEN_KEY:
		case TCP_FASTOPEN_NO_COOKIE:
			return true;
		}

		/* TCP_MD5SIG, TCP_MD5SIG_EXT are not supported, MD5 is not compatible with MPTCP */

		/* TCP_REPAIR, TCP_REPAIR_QUEUE, TCP_QUEUE_SEQ, TCP_REPAIR_OPTIONS,
		 * TCP_REPAIR_WINDOW are not supported, better avoid this mess
		 */
	}
	return false;
}

static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t optval,
					       unsigned int optlen)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	char name[TCP_CA_NAME_MAX];
	bool cap_net_admin;
	int ret;

	if (optlen < 1)
		return -EINVAL;

	ret = strncpy_from_sockptr(name, optval,
				   min_t(long, TCP_CA_NAME_MAX - 1, optlen));
	if (ret < 0)
		return -EFAULT;

	name[ret] = 0;

	cap_net_admin = ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN);

	ret = 0;
	lock_sock(sk);
	sockopt_seq_inc(msk);
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		int err;

		lock_sock(ssk);
		err = tcp_set_congestion_control(ssk, name, true, cap_net_admin);
		if (err < 0 && ret == 0)
			ret = err;
		subflow->setsockopt_seq = msk->setsockopt_seq;
		release_sock(ssk);
	}

	if (ret == 0)
		strcpy(msk->ca_name, name);

	release_sock(sk);
	return ret;
}

static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;

	sockopt_seq_inc(msk);
	msk->cork = !!val;
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		lock_sock(ssk);
		__tcp_sock_set_cork(ssk, !!val);
		release_sock(ssk);
	}
	if (!val)
		mptcp_check_and_set_pending(sk);

	return 0;
}

static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;

	sockopt_seq_inc(msk);
	msk->nodelay = !!val;
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		lock_sock(ssk);
		__tcp_sock_set_nodelay(ssk, !!val);
		release_sock(ssk);
	}
	if (val)
		mptcp_check_and_set_pending(sk);
	return 0;
}

static int mptcp_setsockopt_sol_ip_set(struct mptcp_sock *msk, int optname,
				       sockptr_t optval, unsigned int optlen)
{
	struct sock *sk = (struct sock *)msk;
	struct sock *ssk;
	int err;

	err = ip_setsockopt(sk, SOL_IP, optname, optval, optlen);
	if (err != 0)
		return err;

	lock_sock(sk);

	ssk = __mptcp_nmpc_sk(msk);
	if (IS_ERR(ssk)) {
		release_sock(sk);
		return PTR_ERR(ssk);
	}

	switch (optname) {
	case IP_FREEBIND:
		inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
		break;
	case IP_TRANSPARENT:
		inet_assign_bit(TRANSPARENT, ssk,
				inet_test_bit(TRANSPARENT, sk));
		break;
	case IP_BIND_ADDRESS_NO_PORT:
		inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk,
				inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
		break;
	case IP_LOCAL_PORT_RANGE:
		WRITE_ONCE(inet_sk(ssk)->local_port_range,
			   READ_ONCE(inet_sk(sk)->local_port_range));
		break;
	default:
		release_sock(sk);
		WARN_ON_ONCE(1);
		return -EOPNOTSUPP;
	}

	sockopt_seq_inc(msk);
	release_sock(sk);
	return 0;
}

static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
				       sockptr_t optval, unsigned int optlen)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	int err, val;

	err = ip_setsockopt(sk, SOL_IP, optname, optval, optlen);

	if (err != 0)
		return err;

	lock_sock(sk);
	sockopt_seq_inc(msk);
	val = READ_ONCE(inet_sk(sk)->tos);
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		bool slow;

		slow = lock_sock_fast(ssk);
		__ip_sock_set_tos(ssk, val);
		unlock_sock_fast(ssk, slow);
	}
	release_sock(sk);

	return 0;
}

static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname,
			       sockptr_t optval, unsigned int optlen)
{
	switch (optname) {
	case IP_FREEBIND:
	case IP_TRANSPARENT:
	case IP_BIND_ADDRESS_NO_PORT:
	case IP_LOCAL_PORT_RANGE:
		return mptcp_setsockopt_sol_ip_set(msk, optname, optval, optlen);
	case IP_TOS:
		return mptcp_setsockopt_v4_set_tos(msk, optname, optval, optlen);
	}

	return -EOPNOTSUPP;
}

static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname,
					  sockptr_t optval, unsigned int optlen)
{
	struct sock *sk = (struct sock *)msk;
	struct sock *ssk;
	int ret;

	/* Limit to first subflow, before the connection establishment */
	lock_sock(sk);
	ssk = __mptcp_nmpc_sk(msk);
	if (IS_ERR(ssk)) {
		ret = PTR_ERR(ssk);
		goto unlock;
	}

	ret = tcp_setsockopt(ssk, level, optname, optval, optlen);

unlock:
	release_sock(sk);
	return ret;
}

static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
				    sockptr_t optval, unsigned int optlen)
{
	struct sock *sk = (void *)msk;
	int ret, val;

	switch (optname) {
	case TCP_ULP:
		return -EOPNOTSUPP;
	case TCP_CONGESTION:
		return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen);
	case TCP_DEFER_ACCEPT:
		/* See tcp.c: TCP_DEFER_ACCEPT does not fail */
		mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen);
		return 0;
	case TCP_FASTOPEN:
	case TCP_FASTOPEN_CONNECT:
	case TCP_FASTOPEN_KEY:
	case TCP_FASTOPEN_NO_COOKIE:
		return mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname,
						      optval, optlen);
	}

	ret = mptcp_get_int_option(msk, optval, optlen, &val);
	if (ret)
		return ret;

	lock_sock(sk);
	switch (optname) {
	case TCP_INQ:
		if (val < 0 || val > 1)
			ret = -EINVAL;
		else
			msk->recvmsg_inq = !!val;
		break;
	case TCP_NOTSENT_LOWAT:
		WRITE_ONCE(msk->notsent_lowat, val);
		mptcp_write_space(sk);
		break;
	case TCP_CORK:
		ret = __mptcp_setsockopt_sol_tcp_cork(msk, val);
		break;
	case TCP_NODELAY:
		ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val);
		break;
	default:
		ret = -ENOPROTOOPT;
	}

	release_sock(sk);
	return ret;
}

int mptcp_setsockopt(struct sock *sk, int level, int optname,
		     sockptr_t optval, unsigned int optlen)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct sock *ssk;

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

	if (level == SOL_SOCKET)
		return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);

	if (!mptcp_supported_sockopt(level, optname))
		return -ENOPROTOOPT;

	/* @@ the meaning of setsockopt() when the socket is connected and
	 * there are multiple subflows is not yet defined. It is up to the
	 * MPTCP-level socket to configure the subflows until the subflow
	 * is in TCP fallback, when TCP socket options are passed through
	 * to the one remaining subflow.
	 */
	lock_sock(sk);
	ssk = __mptcp_tcp_fallback(msk);
	release_sock(sk);
	if (ssk)
		return tcp_setsockopt(ssk, level, optname, optval, optlen);

	if (level == SOL_IP)
		return mptcp_setsockopt_v4(msk, optname, optval, optlen);

	if (level == SOL_IPV6)
		return mptcp_setsockopt_v6(msk, optname, optval, optlen);

	if (level == SOL_TCP)
		return mptcp_setsockopt_sol_tcp(msk, optname, optval, optlen);

	return -EOPNOTSUPP;
}

static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname,
					  char __user *optval, int __user *optlen)
{
	struct sock *sk = (struct sock *)msk;
	struct sock *ssk;
	int ret;

	lock_sock(sk);
	ssk = msk->first;
	if (ssk) {
		ret = tcp_getsockopt(ssk, level, optname, optval, optlen);
		goto out;
	}

	ssk = __mptcp_nmpc_sk(msk);
	if (IS_ERR(ssk)) {
		ret = PTR_ERR(ssk);
		goto out;
	}

	ret = tcp_getsockopt(ssk, level, optname, optval, optlen);

out:
	release_sock(sk);
	return ret;
}

void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
{
	struct sock *sk = (struct sock *)msk;
	u32 flags = 0;
	bool slow;

	memset(info, 0, sizeof(*info));

	info->mptcpi_subflows = READ_ONCE(msk->pm.subflows);
	info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled);
	info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted);
	info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used);

	if (inet_sk_state_load(sk) == TCP_LISTEN)
		return;

	/* The following limits only make sense for the in-kernel PM */
	if (mptcp_pm_is_kernel(msk)) {
		info->mptcpi_subflows_max =
			mptcp_pm_get_subflows_max(msk);
		info->mptcpi_add_addr_signal_max =
			mptcp_pm_get_add_addr_signal_max(msk);
		info->mptcpi_add_addr_accepted_max =
			mptcp_pm_get_add_addr_accept_max(msk);
		info->mptcpi_local_addr_max =
			mptcp_pm_get_local_addr_max(msk);
	}

	if (__mptcp_check_fallback(msk))
		flags |= MPTCP_INFO_FLAG_FALLBACK;
	if (READ_ONCE(msk->can_ack))
		flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED;
	info->mptcpi_flags = flags;
	mptcp_data_lock(sk);
	info->mptcpi_snd_una = msk->snd_una;
	info->mptcpi_rcv_nxt = msk->ack_seq;
	info->mptcpi_bytes_acked = msk->bytes_acked;
	mptcp_data_unlock(sk);

	slow = lock_sock_fast(sk);
	info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
	info->mptcpi_token = msk->token;
	info->mptcpi_write_seq = msk->write_seq;
	info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits;
	info->mptcpi_bytes_sent = msk->bytes_sent;
	info->mptcpi_bytes_received = msk->bytes_received;
	info->mptcpi_bytes_retrans = msk->bytes_retrans;
	info->mptcpi_subflows_total = info->mptcpi_subflows +
		__mptcp_has_initial_subflow(msk);
	unlock_sock_fast(sk, slow);
}
EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);

static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, int __user *optlen)
{
	struct mptcp_info m_info;
	int len;

	if (get_user(len, optlen))
		return -EFAULT;

	len = min_t(unsigned int, len, sizeof(struct mptcp_info));

	mptcp_diag_fill_info(msk, &m_info);

	if (put_user(len, optlen))
		return -EFAULT;

	if (copy_to_user(optval, &m_info, len))
		return -EFAULT;

	return 0;
}

static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd,
				  char __user *optval,
				  u32 copied,
				  int __user *optlen)
{
	u32 copylen = min_t(u32, sfd->size_subflow_data, sizeof(*sfd));

	if (copied)
		copied += sfd->size_subflow_data;
	else
		copied = copylen;

	if (put_user(copied, optlen))
		return -EFAULT;

	if (copy_to_user(optval, sfd, copylen))
		return -EFAULT;

	return 0;
}

static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd,
				  char __user *optval,
				  int __user *optlen)
{
	int len, copylen;

	if (get_user(len, optlen))
		return -EFAULT;

	/* if mptcp_subflow_data size is changed, need to adjust
	 * this function to deal with programs using old version.
	 */
	BUILD_BUG_ON(sizeof(*sfd) != MIN_INFO_OPTLEN_SIZE);

	if (len < MIN_INFO_OPTLEN_SIZE)
		return -EINVAL;

	memset(sfd, 0, sizeof(*sfd));

	copylen = min_t(unsigned int, len, sizeof(*sfd));
	if (copy_from_user(sfd, optval, copylen))
		return -EFAULT;

	/* size_subflow_data is u32, but len is signed */
	if (sfd->size_subflow_data > INT_MAX ||
	    sfd->size_user > INT_MAX)
		return -EINVAL;

	if (sfd->size_subflow_data < MIN_INFO_OPTLEN_SIZE ||
	    sfd->size_subflow_data > len)
		return -EINVAL;

	if (sfd->num_subflows || sfd->size_kernel)
		return -EINVAL;

	return len - sfd->size_subflow_data;
}

static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval,
				    int __user *optlen)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	unsigned int sfcount = 0, copied = 0;
	struct mptcp_subflow_data sfd;
	char __user *infoptr;
	int len;

	len = mptcp_get_subflow_data(&sfd, optval, optlen);
	if (len < 0)
		return len;

	sfd.size_kernel = sizeof(struct tcp_info);
	sfd.size_user = min_t(unsigned int, sfd.size_user,
			      sizeof(struct tcp_info));

	infoptr = optval + sfd.size_subflow_data;

	lock_sock(sk);

	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		++sfcount;

		if (len && len >= sfd.size_user) {
			struct tcp_info info;

			tcp_get_info(ssk, &info);

			if (copy_to_user(infoptr, &info, sfd.size_user)) {
				release_sock(sk);
				return -EFAULT;
			}

			infoptr += sfd.size_user;
			copied += sfd.size_user;
			len -= sfd.size_user;
		}
	}

	release_sock(sk);

	sfd.num_subflows = sfcount;

	if (mptcp_put_subflow_data(&sfd, optval, copied, optlen))
		return -EFAULT;

	return 0;
}

static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addrs *a)
{
	const struct inet_sock *inet = inet_sk(sk);

	memset(a, 0, sizeof(*a));

	if (sk->sk_family == AF_INET) {
		a->sin_local.sin_family = AF_INET;
		a->sin_local.sin_port = inet->inet_sport;
		a->sin_local.sin_addr.s_addr = inet->inet_rcv_saddr;

		if (!a->sin_local.sin_addr.s_addr)
			a->sin_local.sin_addr.s_addr = inet->inet_saddr;

		a->sin_remote.sin_family = AF_INET;
		a->sin_remote.sin_port = inet->inet_dport;
		a->sin_remote.sin_addr.s_addr = inet->inet_daddr;
#if IS_ENABLED(CONFIG_IPV6)
	} else if (sk->sk_family == AF_INET6) {
		const struct ipv6_pinfo *np = inet6_sk(sk);

		if (WARN_ON_ONCE(!np))
			return;

		a->sin6_local.sin6_family = AF_INET6;
		a->sin6_local.sin6_port = inet->inet_sport;

		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
			a->sin6_local.sin6_addr = np->saddr;
		else
			a->sin6_local.sin6_addr = sk->sk_v6_rcv_saddr;

		a->sin6_remote.sin6_family = AF_INET6;
		a->sin6_remote.sin6_port = inet->inet_dport;
		a->sin6_remote.sin6_addr = sk->sk_v6_daddr;
#endif
	}
}

static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *optval,
					  int __user *optlen)
{
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	unsigned int sfcount = 0, copied = 0;
	struct mptcp_subflow_data sfd;
	char __user *addrptr;
	int len;

	len = mptcp_get_subflow_data(&sfd, optval, optlen);
	if (len < 0)
		return len;

	sfd.size_kernel = sizeof(struct mptcp_subflow_addrs);
	sfd.size_user = min_t(unsigned int, sfd.size_user,
			      sizeof(struct mptcp_subflow_addrs));

	addrptr = optval + sfd.size_subflow_data;

	lock_sock(sk);

	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		++sfcount;

		if (len && len >= sfd.size_user) {
			struct mptcp_subflow_addrs a;

			mptcp_get_sub_addrs(ssk, &a);

			if (copy_to_user(addrptr, &a, sfd.size_user)) {
				release_sock(sk);
				return -EFAULT;
			}

			addrptr += sfd.size_user;
			copied += sfd.size_user;
			len -= sfd.size_user;
		}
	}

	release_sock(sk);

	sfd.num_subflows = sfcount;

	if (mptcp_put_subflow_data(&sfd, optval, copied, optlen))
		return -EFAULT;

	return 0;
}

static int mptcp_get_full_info(struct mptcp_full_info *mfi,
			       char __user *optval,
			       int __user *optlen)
{
	int len;

	BUILD_BUG_ON(offsetof(struct mptcp_full_info, mptcp_info) !=
		     MIN_FULL_INFO_OPTLEN_SIZE);

	if (get_user(len, optlen))
		return -EFAULT;

	if (len < MIN_FULL_INFO_OPTLEN_SIZE)
		return -EINVAL;

	memset(mfi, 0, sizeof(*mfi));
	if (copy_from_user(mfi, optval, MIN_FULL_INFO_OPTLEN_SIZE))
		return -EFAULT;

	if (mfi->size_tcpinfo_kernel ||
	    mfi->size_sfinfo_kernel ||
	    mfi->num_subflows)
		return -EINVAL;

	if (mfi->size_sfinfo_user > INT_MAX ||
	    mfi->size_tcpinfo_user > INT_MAX)
		return -EINVAL;

	return len - MIN_FULL_INFO_OPTLEN_SIZE;
}

static int mptcp_put_full_info(struct mptcp_full_info *mfi,
			       char __user *optval,
			       u32 copylen,
			       int __user *optlen)
{
	copylen += MIN_FULL_INFO_OPTLEN_SIZE;
	if (put_user(copylen, optlen))
		return -EFAULT;

	if (copy_to_user(optval, mfi, copylen))
		return -EFAULT;
	return 0;
}

static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optval,
				      int __user *optlen)
{
	unsigned int sfcount = 0, copylen = 0;
	struct mptcp_subflow_context *subflow;
	struct sock *sk = (struct sock *)msk;
	void __user *tcpinfoptr, *sfinfoptr;
	struct mptcp_full_info mfi;
	int len;

	len = mptcp_get_full_info(&mfi, optval, optlen);
	if (len < 0)
		return len;

	/* don't bother filling the mptcp info if there is not enough
	 * user-space-provided storage
	 */
	if (len > 0) {
		mptcp_diag_fill_info(msk, &mfi.mptcp_info);
		copylen += min_t(unsigned int, len, sizeof(struct mptcp_info));
	}

	mfi.size_tcpinfo_kernel = sizeof(struct tcp_info);
	mfi.size_tcpinfo_user = min_t(unsigned int, mfi.size_tcpinfo_user,
				      sizeof(struct tcp_info));
	sfinfoptr = u64_to_user_ptr(mfi.subflow_info);
	mfi.size_sfinfo_kernel = sizeof(struct mptcp_subflow_info);
	mfi.size_sfinfo_user = min_t(unsigned int, mfi.size_sfinfo_user,
				     sizeof(struct mptcp_subflow_info));
	tcpinfoptr = u64_to_user_ptr(mfi.tcp_info);

	lock_sock(sk);
	mptcp_for_each_subflow(msk, subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		struct mptcp_subflow_info sfinfo;
		struct tcp_info tcp_info;

		if (sfcount++ >= mfi.size_arrays_user)
			continue;

		/* fetch addr/tcp_info only if the user space buffers
		 * are wide enough
		 */
		memset(&sfinfo, 0, sizeof(sfinfo));
		sfinfo.id = subflow->subflow_id;
		if (mfi.size_sfinfo_user >
		    offsetof(struct mptcp_subflow_info, addrs))
			mptcp_get_sub_addrs(ssk, &sfinfo.addrs);
		if (copy_to_user(sfinfoptr, &sfinfo, mfi.size_sfinfo_user))
			goto fail_release;

		if (mfi.size_tcpinfo_user) {
			tcp_get_info(ssk, &tcp_info);
			if (copy_to_user(tcpinfoptr, &tcp_info,
					 mfi.size_tcpinfo_user))
				goto fail_release;
		}

		tcpinfoptr += mfi.size_tcpinfo_user;
		sfinfoptr += mfi.size_sfinfo_user;
	}
	release_sock(sk);

	mfi.num_subflows = sfcount;
	if (mptcp_put_full_info(&mfi, optval, copylen, optlen))
		return -EFAULT;

	return 0;

fail_release:
	release_sock(sk);
	return -EFAULT;
}

static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval,
				int __user *optlen, int val)
{
	int len;

	if (get_user(len, optlen))
		return -EFAULT;
	if (len < 0)
		return -EINVAL;

	if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) {
		unsigned char ucval = (unsigned char)val;

		len = 1;
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &ucval, 1))
			return -EFAULT;
	} else {
		len = min_t(unsigned int, len, sizeof(int));
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &val, len))
			return -EFAULT;
	}

	return 0;
}

static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
				    char __user *optval, int __user *optlen)
{
	switch (optname) {
	case TCP_ULP:
	case TCP_CONGESTION:
	case TCP_INFO:
	case TCP_CC_INFO:
	case TCP_DEFER_ACCEPT:
	case TCP_FASTOPEN:
	case TCP_FASTOPEN_CONNECT:
	case TCP_FASTOPEN_KEY:
	case TCP_FASTOPEN_NO_COOKIE:
		return mptcp_getsockopt_first_sf_only(msk, SOL_TCP, optname,
						      optval, optlen);
	case TCP_INQ:
		return mptcp_put_int_option(msk, optval, optlen, msk->recvmsg_inq);
	case TCP_CORK:
		return mptcp_put_int_option(msk, optval, optlen, msk->cork);
	case TCP_NODELAY:
		return mptcp_put_int_option(msk, optval, optlen, msk->nodelay);
	case TCP_NOTSENT_LOWAT:
		return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat);
	}
	return -EOPNOTSUPP;
}

static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname,
			       char __user *optval, int __user *optlen)
{
	struct sock *sk = (void *)msk;

	switch (optname) {
	case IP_TOS:
		return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos));
	case IP_BIND_ADDRESS_NO_PORT:
		return mptcp_put_int_option(msk, optval, optlen,
				inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
	case IP_LOCAL_PORT_RANGE:
		return mptcp_put_int_option(msk, optval, optlen,
				READ_ONCE(inet_sk(sk)->local_port_range));
	}

	return -EOPNOTSUPP;
}

static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname,
				      char __user *optval, int __user *optlen)
{
	switch (optname) {
	case MPTCP_INFO:
		return mptcp_getsockopt_info(msk, optval, optlen);
	case MPTCP_FULL_INFO:
		return mptcp_getsockopt_full_info(msk, optval, optlen);
	case MPTCP_TCPINFO:
		return mptcp_getsockopt_tcpinfo(msk, optval, optlen);
	case MPTCP_SUBFLOW_ADDRS:
		return mptcp_getsockopt_subflow_addrs(msk, optval, optlen);
	}

	return -EOPNOTSUPP;
}

int mptcp_getsockopt(struct sock *sk, int level, int optname,
		     char __user *optval, int __user *option)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct sock *ssk;

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

	/* @@ the meaning of setsockopt() when the socket is connected and
	 * there are multiple subflows is not yet defined. It is up to the
	 * MPTCP-level socket to configure the subflows until the subflow
	 * is in TCP fallback, when socket options are passed through
	 * to the one remaining subflow.
	 */
	lock_sock(sk);
	ssk = __mptcp_tcp_fallback(msk);
	release_sock(sk);
	if (ssk)
		return tcp_getsockopt(ssk, level, optname, optval, option);

	if (level == SOL_IP)
		return mptcp_getsockopt_v4(msk, optname, optval, option);
	if (level == SOL_TCP)
		return mptcp_getsockopt_sol_tcp(msk, optname, optval, option);
	if (level == SOL_MPTCP)
		return mptcp_getsockopt_sol_mptcp(msk, optname, optval, option);
	return -EOPNOTSUPP;
}

static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
{
	static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK;
	struct sock *sk = (struct sock *)msk;

	if (ssk->sk_prot->keepalive) {
		if (sock_flag(sk, SOCK_KEEPOPEN))
			ssk->sk_prot->keepalive(ssk, 1);
		else
			ssk->sk_prot->keepalive(ssk, 0);
	}

	ssk->sk_priority = sk->sk_priority;
	ssk->sk_bound_dev_if = sk->sk_bound_dev_if;
	ssk->sk_incoming_cpu = sk->sk_incoming_cpu;
	ssk->sk_ipv6only = sk->sk_ipv6only;
	__ip_sock_set_tos(ssk, inet_sk(sk)->tos);

	if (sk->sk_userlocks & tx_rx_locks) {
		ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks;
		if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) {
			WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf);
			mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf;
		}
		if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
			WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf);
	}

	if (sock_flag(sk, SOCK_LINGER)) {
		ssk->sk_lingertime = sk->sk_lingertime;
		sock_set_flag(ssk, SOCK_LINGER);
	} else {
		sock_reset_flag(ssk, SOCK_LINGER);
	}

	if (sk->sk_mark != ssk->sk_mark) {
		ssk->sk_mark = sk->sk_mark;
		sk_dst_reset(ssk);
	}

	sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG));

	if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops)
		tcp_set_congestion_control(ssk, msk->ca_name, false, true);
	__tcp_sock_set_cork(ssk, !!msk->cork);
	__tcp_sock_set_nodelay(ssk, !!msk->nodelay);

	inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk));
	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
	inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk, inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
	WRITE_ONCE(inet_sk(ssk)->local_port_range, READ_ONCE(inet_sk(sk)->local_port_range));
}

void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);

	msk_owned_by_me(msk);

	ssk->sk_rcvlowat = 0;

	/* subflows must ignore any latency-related settings: will not affect
	 * the user-space - only the msk is relevant - but will foul the
	 * mptcp scheduler
	 */
	tcp_sk(ssk)->notsent_lowat = UINT_MAX;

	if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) {
		sync_socket_options(msk, ssk);

		subflow->setsockopt_seq = msk->setsockopt_seq;
	}
}

/* unfortunately this is different enough from the tcp version so
 * that we can't factor it out
 */
int mptcp_set_rcvlowat(struct sock *sk, int val)
{
	struct mptcp_subflow_context *subflow;
	int space, cap;

	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
		cap = sk->sk_rcvbuf >> 1;
	else
		cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
	val = min(val, cap);
	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);

	/* Check if we need to signal EPOLLIN right now */
	if (mptcp_epollin_ready(sk))
		sk->sk_data_ready(sk);

	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
		return 0;

	space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val);
	if (space <= sk->sk_rcvbuf)
		return 0;

	/* propagate the rcvbuf changes to all the subflows */
	WRITE_ONCE(sk->sk_rcvbuf, space);
	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
		bool slow;

		slow = lock_sock_fast(ssk);
		WRITE_ONCE(ssk->sk_rcvbuf, space);
		tcp_sk(ssk)->window_clamp = val;
		unlock_sock_fast(ssk, slow);
	}
	return 0;
}