summaryrefslogtreecommitdiff
path: root/net/mptcp/subflow.c
blob: e120e961645406551be353fd661cdb58dee299b3 (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
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
// 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 <crypto/algapi.h>
#include <crypto/sha2.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>
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
#include <uapi/linux/mptcp.h>
#include "protocol.h"
#include "mib.h"

#include <trace/events/mptcp.h>
#include <trace/events/sock.h>

static void mptcp_subflow_ops_undo_override(struct sock *ssk);

static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
				  enum linux_mptcp_mib_field field)
{
	MPTCP_INC_STATS(sock_net(req_to_sk(req)), field);
}

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->msk)
		sock_put((struct sock *)subflow_req->msk);

	mptcp_token_destroy_request(req);
}

static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2,
				  void *hmac)
{
	u8 msg[8];

	put_unaligned_be32(nonce1, &msg[0]);
	put_unaligned_be32(nonce2, &msg[4]);

	mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac);
}

static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk)
{
	return mptcp_is_fully_established((void *)msk) &&
		((mptcp_pm_is_userspace(msk) &&
		  mptcp_userspace_pm_active(msk)) ||
		 READ_ONCE(msk->pm.accept_subflow));
}

/* validate received token and create truncated hmac and nonce for SYN-ACK */
static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_req)
{
	struct mptcp_sock *msk = subflow_req->msk;
	u8 hmac[SHA256_DIGEST_SIZE];

	get_random_bytes(&subflow_req->local_nonce, sizeof(u32));

	subflow_generate_hmac(msk->local_key, msk->remote_key,
			      subflow_req->local_nonce,
			      subflow_req->remote_nonce, hmac);

	subflow_req->thmac = get_unaligned_be64(hmac);
}

static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
{
	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
	struct mptcp_sock *msk;
	int local_id;

	msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token);
	if (!msk) {
		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN);
		return NULL;
	}

	local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)req);
	if (local_id < 0) {
		sock_put((struct sock *)msk);
		return NULL;
	}
	subflow_req->local_id = local_id;

	return msk;
}

static void subflow_init_req(struct request_sock *req, const struct sock *sk_listener)
{
	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);

	subflow_req->mp_capable = 0;
	subflow_req->mp_join = 0;
	subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener));
	subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener));
	subflow_req->msk = NULL;
	mptcp_token_init_request(req);
}

static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk)
{
	return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport;
}

static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason)
{
	struct mptcp_ext *mpext = skb_ext_add(skb, SKB_EXT_MPTCP);

	if (mpext) {
		memset(mpext, 0, sizeof(*mpext));
		mpext->reset_reason = reason;
	}
}

/* Init mptcp request socket.
 *
 * Returns an error code if a JOIN has failed and a TCP reset
 * should be sent.
 */
static int subflow_check_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 mptcp_options_received mp_opt;
	bool opt_mp_capable, opt_mp_join;

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

#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 -EINVAL;
#endif

	mptcp_get_options(skb, &mp_opt);

	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
	if (opt_mp_capable) {
		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);

		if (opt_mp_join)
			return 0;
	} else if (opt_mp_join) {
		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
	}

	if (opt_mp_capable && listener->request_mptcp) {
		int err, retries = MPTCP_TOKEN_MAX_RETRIES;

		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
again:
		do {
			get_random_bytes(&subflow_req->local_key, sizeof(subflow_req->local_key));
		} while (subflow_req->local_key == 0);

		if (unlikely(req->syncookie)) {
			mptcp_crypto_key_sha(subflow_req->local_key,
					     &subflow_req->token,
					     &subflow_req->idsn);
			if (mptcp_token_exists(subflow_req->token)) {
				if (retries-- > 0)
					goto again;
				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT);
			} else {
				subflow_req->mp_capable = 1;
			}
			return 0;
		}

		err = mptcp_token_new_request(req);
		if (err == 0)
			subflow_req->mp_capable = 1;
		else if (retries-- > 0)
			goto again;
		else
			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT);

	} else if (opt_mp_join && listener->request_mptcp) {
		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
		subflow_req->mp_join = 1;
		subflow_req->backup = mp_opt.backup;
		subflow_req->remote_id = mp_opt.join_id;
		subflow_req->token = mp_opt.token;
		subflow_req->remote_nonce = mp_opt.nonce;
		subflow_req->msk = subflow_token_join_request(req);

		/* Can't fall back to TCP in this case. */
		if (!subflow_req->msk) {
			subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
			return -EPERM;
		}

		if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
			pr_debug("syn inet_sport=%d %d",
				 ntohs(inet_sk(sk_listener)->inet_sport),
				 ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
			if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
				return -EPERM;
			}
			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX);
		}

		subflow_req_create_thmac(subflow_req);

		if (unlikely(req->syncookie)) {
			if (mptcp_can_accept_new_subflow(subflow_req->msk))
				subflow_init_req_cookie_join_save(subflow_req, skb);
			else
				return -EPERM;
		}

		pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
			 subflow_req->remote_nonce, subflow_req->msk);
	}

	return 0;
}

int mptcp_subflow_init_cookie_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 mptcp_options_received mp_opt;
	bool opt_mp_capable, opt_mp_join;
	int err;

	subflow_init_req(req, sk_listener);
	mptcp_get_options(skb, &mp_opt);

	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
	if (opt_mp_capable && opt_mp_join)
		return -EINVAL;

	if (opt_mp_capable && listener->request_mptcp) {
		if (mp_opt.sndr_key == 0)
			return -EINVAL;

		subflow_req->local_key = mp_opt.rcvr_key;
		err = mptcp_token_new_request(req);
		if (err)
			return err;

		subflow_req->mp_capable = 1;
		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
	} else if (opt_mp_join && listener->request_mptcp) {
		if (!mptcp_token_join_cookie_init_state(subflow_req, skb))
			return -EINVAL;

		subflow_req->mp_join = 1;
		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req);

static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
					      struct sk_buff *skb,
					      struct flowi *fl,
					      struct request_sock *req)
{
	struct dst_entry *dst;
	int err;

	tcp_rsk(req)->is_mptcp = 1;
	subflow_init_req(req, sk);

	dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req);
	if (!dst)
		return NULL;

	err = subflow_check_req(req, sk, skb);
	if (err == 0)
		return dst;

	dst_release(dst);
	if (!req->syncookie)
		tcp_request_sock_ops.send_reset(sk, skb);
	return NULL;
}

static void subflow_prep_synack(const struct sock *sk, struct request_sock *req,
				struct tcp_fastopen_cookie *foc,
				enum tcp_synack_type synack_type)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct inet_request_sock *ireq = inet_rsk(req);

	/* clear tstamp_ok, as needed depending on cookie */
	if (foc && foc->len > -1)
		ireq->tstamp_ok = 0;

	if (synack_type == TCP_SYNACK_FASTOPEN)
		mptcp_fastopen_subflow_synack_set_params(subflow, req);
}

static int subflow_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
				  struct flowi *fl,
				  struct request_sock *req,
				  struct tcp_fastopen_cookie *foc,
				  enum tcp_synack_type synack_type,
				  struct sk_buff *syn_skb)
{
	subflow_prep_synack(sk, req, foc, synack_type);

	return tcp_request_sock_ipv4_ops.send_synack(sk, dst, fl, req, foc,
						     synack_type, syn_skb);
}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static int subflow_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
				  struct flowi *fl,
				  struct request_sock *req,
				  struct tcp_fastopen_cookie *foc,
				  enum tcp_synack_type synack_type,
				  struct sk_buff *syn_skb)
{
	subflow_prep_synack(sk, req, foc, synack_type);

	return tcp_request_sock_ipv6_ops.send_synack(sk, dst, fl, req, foc,
						     synack_type, syn_skb);
}

static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
					      struct sk_buff *skb,
					      struct flowi *fl,
					      struct request_sock *req)
{
	struct dst_entry *dst;
	int err;

	tcp_rsk(req)->is_mptcp = 1;
	subflow_init_req(req, sk);

	dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req);
	if (!dst)
		return NULL;

	err = subflow_check_req(req, sk, skb);
	if (err == 0)
		return dst;

	dst_release(dst);
	if (!req->syncookie)
		tcp6_request_sock_ops.send_reset(sk, skb);
	return NULL;
}
#endif

/* validate received truncated hmac and create hmac for third ACK */
static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
{
	u8 hmac[SHA256_DIGEST_SIZE];
	u64 thmac;

	subflow_generate_hmac(subflow->remote_key, subflow->local_key,
			      subflow->remote_nonce, subflow->local_nonce,
			      hmac);

	thmac = get_unaligned_be64(hmac);
	pr_debug("subflow=%p, token=%u, thmac=%llu, subflow->thmac=%llu\n",
		 subflow, subflow->token, thmac, subflow->thmac);

	return thmac == subflow->thmac;
}

void mptcp_subflow_reset(struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	struct sock *sk = subflow->conn;

	/* mptcp_mp_fail_no_response() can reach here on an already closed
	 * socket
	 */
	if (ssk->sk_state == TCP_CLOSE)
		return;

	/* must hold: tcp_done() could drop last reference on parent */
	sock_hold(sk);

	tcp_send_active_reset(ssk, GFP_ATOMIC);
	tcp_done(ssk);
	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags))
		mptcp_schedule_work(sk);

	sock_put(sk);
}

static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct sock *sk)
{
	return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport;
}

void __mptcp_set_connected(struct sock *sk)
{
	__mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first);
	if (sk->sk_state == TCP_SYN_SENT) {
		inet_sk_state_store(sk, TCP_ESTABLISHED);
		sk->sk_state_change(sk);
	}
}

static void mptcp_set_connected(struct sock *sk)
{
	mptcp_data_lock(sk);
	if (!sock_owned_by_user(sk))
		__mptcp_set_connected(sk);
	else
		__set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->cb_flags);
	mptcp_data_unlock(sk);
}

static void subflow_set_remote_key(struct mptcp_sock *msk,
				   struct mptcp_subflow_context *subflow,
				   const struct mptcp_options_received *mp_opt)
{
	/* active MPC subflow will reach here multiple times:
	 * at subflow_finish_connect() time and at 4th ack time
	 */
	if (subflow->remote_key_valid)
		return;

	subflow->remote_key_valid = 1;
	subflow->remote_key = mp_opt->sndr_key;
	mptcp_crypto_key_sha(subflow->remote_key, NULL, &subflow->iasn);
	subflow->iasn++;

	WRITE_ONCE(msk->remote_key, subflow->remote_key);
	WRITE_ONCE(msk->ack_seq, subflow->iasn);
	WRITE_ONCE(msk->can_ack, true);
	atomic64_set(&msk->rcv_wnd_sent, subflow->iasn);
}

static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct mptcp_options_received mp_opt;
	struct sock *parent = subflow->conn;
	struct mptcp_sock *msk;

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

	/* be sure no special action on any packet other than syn-ack */
	if (subflow->conn_finished)
		return;

	msk = mptcp_sk(parent);
	subflow->rel_write_seq = 1;
	subflow->conn_finished = 1;
	subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
	pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);

	mptcp_get_options(skb, &mp_opt);
	if (subflow->request_mptcp) {
		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
			MPTCP_INC_STATS(sock_net(sk),
					MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
			mptcp_do_fallback(sk);
			pr_fallback(msk);
			goto fallback;
		}

		if (mp_opt.suboptions & OPTION_MPTCP_CSUMREQD)
			WRITE_ONCE(msk->csum_enabled, true);
		if (mp_opt.deny_join_id0)
			WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
		subflow->mp_capable = 1;
		subflow_set_remote_key(msk, subflow, &mp_opt);
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
		mptcp_finish_connect(sk);
		mptcp_set_connected(parent);
	} else if (subflow->request_join) {
		u8 hmac[SHA256_DIGEST_SIZE];

		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) {
			subflow->reset_reason = MPTCP_RST_EMPTCP;
			goto do_reset;
		}

		subflow->backup = mp_opt.backup;
		subflow->thmac = mp_opt.thmac;
		subflow->remote_nonce = mp_opt.nonce;
		subflow->remote_id = mp_opt.join_id;
		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
			 subflow, subflow->thmac, subflow->remote_nonce,
			 subflow->backup);

		if (!subflow_thmac_valid(subflow)) {
			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
			subflow->reset_reason = MPTCP_RST_EMPTCP;
			goto do_reset;
		}

		if (!mptcp_finish_join(sk))
			goto do_reset;

		subflow_generate_hmac(subflow->local_key, subflow->remote_key,
				      subflow->local_nonce,
				      subflow->remote_nonce,
				      hmac);
		memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);

		subflow->mp_join = 1;
		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);

		if (subflow_use_different_dport(msk, sk)) {
			pr_debug("synack inet_dport=%d %d",
				 ntohs(inet_sk(sk)->inet_dport),
				 ntohs(inet_sk(parent)->inet_dport));
			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX);
		}
	} else if (mptcp_check_fallback(sk)) {
fallback:
		mptcp_rcv_space_init(msk, sk);
		mptcp_set_connected(parent);
	}
	return;

do_reset:
	subflow->reset_transient = 0;
	mptcp_subflow_reset(sk);
}

static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
{
	subflow->local_id = local_id;
	subflow->local_id_valid = 1;
}

static int subflow_chk_local_id(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
	int err;

	if (likely(subflow->local_id_valid))
		return 0;

	err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
	if (err < 0)
		return err;

	subflow_set_local_id(subflow, err);
	return 0;
}

static int subflow_rebuild_header(struct sock *sk)
{
	int err = subflow_chk_local_id(sk);

	if (unlikely(err < 0))
		return err;

	return inet_sk_rebuild_header(sk);
}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static int subflow_v6_rebuild_header(struct sock *sk)
{
	int err = subflow_chk_local_id(sk);

	if (unlikely(err < 0))
		return err;

	return inet6_sk_rebuild_header(sk);
}
#endif

static struct request_sock_ops mptcp_subflow_v4_request_sock_ops __ro_after_init;
static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init;

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(&mptcp_subflow_v4_request_sock_ops,
				&subflow_request_sock_ipv4_ops,
				sk, skb);
drop:
	tcp_listendrop(sk);
	return 0;
}

static void subflow_v4_req_destructor(struct request_sock *req)
{
	subflow_req_destructor(req);
	tcp_request_sock_ops.destructor(req);
}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init;
static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init;
static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init;
static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init;
static struct proto tcpv6_prot_override __ro_after_init;

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;

	if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
		__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
		return 0;
	}

	return tcp_conn_request(&mptcp_subflow_v6_request_sock_ops,
				&subflow_request_sock_ipv6_ops, sk, skb);

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

static void subflow_v6_req_destructor(struct request_sock *req)
{
	subflow_req_destructor(req);
	tcp6_request_sock_ops.destructor(req);
}
#endif

struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops,
					       struct sock *sk_listener,
					       bool attach_listener)
{
	if (ops->family == AF_INET)
		ops = &mptcp_subflow_v4_request_sock_ops;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	else if (ops->family == AF_INET6)
		ops = &mptcp_subflow_v6_request_sock_ops;
#endif

	return inet_reqsk_alloc(ops, sk_listener, attach_listener);
}
EXPORT_SYMBOL(mptcp_subflow_reqsk_alloc);

/* validate hmac received in third ACK */
static bool subflow_hmac_valid(const struct request_sock *req,
			       const struct mptcp_options_received *mp_opt)
{
	const struct mptcp_subflow_request_sock *subflow_req;
	u8 hmac[SHA256_DIGEST_SIZE];
	struct mptcp_sock *msk;

	subflow_req = mptcp_subflow_rsk(req);
	msk = subflow_req->msk;
	if (!msk)
		return false;

	subflow_generate_hmac(msk->remote_key, msk->local_key,
			      subflow_req->remote_nonce,
			      subflow_req->local_nonce, hmac);

	return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN);
}

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;

	mptcp_subflow_ops_undo_override(sk);
}

void mptcp_subflow_drop_ctx(struct sock *ssk)
{
	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);

	if (!ctx)
		return;

	list_del(&mptcp_subflow_ctx(ssk)->node);
	if (inet_csk(ssk)->icsk_ulp_ops) {
		subflow_ulp_fallback(ssk, ctx);
		if (ctx->conn)
			sock_put(ctx->conn);
	}

	kfree_rcu(ctx, rcu);
}

void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
				     const struct mptcp_options_received *mp_opt)
{
	struct mptcp_sock *msk = mptcp_sk(subflow->conn);

	subflow_set_remote_key(msk, subflow, mp_opt);
	subflow->fully_established = 1;
	WRITE_ONCE(msk->fully_established, true);

	if (subflow->is_mptfo)
		mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
}

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 mptcp_options_received mp_opt;
	bool fallback, fallback_is_fatal;
	struct mptcp_sock *owner;
	struct sock *child;

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

	/* After child creation we must look for MPC even when options
	 * are not parsed
	 */
	mp_opt.suboptions = 0;

	/* hopefully temporary handling for MP_JOIN+syncookie */
	subflow_req = mptcp_subflow_rsk(req);
	fallback_is_fatal = tcp_rsk(req)->is_mptcp && subflow_req->mp_join;
	fallback = !tcp_rsk(req)->is_mptcp;
	if (fallback)
		goto create_child;

	/* if the sk is MP_CAPABLE, we try to fetch the client key */
	if (subflow_req->mp_capable) {
		/* we can receive and accept an in-window, out-of-order pkt,
		 * which may not carry the MP_CAPABLE opt even on mptcp enabled
		 * paths: always try to extract the peer key, and fallback
		 * for packets missing it.
		 * Even OoO DSS packets coming legitly after dropped or
		 * reordered MPC will cause fallback, but we don't have other
		 * options.
		 */
		mptcp_get_options(skb, &mp_opt);
		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC))
			fallback = true;

	} else if (subflow_req->mp_join) {
		mptcp_get_options(skb, &mp_opt);
		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) ||
		    !subflow_hmac_valid(req, &mp_opt) ||
		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
			fallback = true;
		}
	}

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);

		tcp_rsk(req)->drop_req = false;

		/* we need to fallback on ctx allocation failure and on pre-reqs
		 * checking above. In the latter scenario we additionally need
		 * to reset the context to non MPTCP status.
		 */
		if (!ctx || fallback) {
			if (fallback_is_fatal) {
				subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
				goto dispose_child;
			}
			goto fallback;
		}

		/* ssk inherits options of listener sk */
		ctx->setsockopt_seq = listener->setsockopt_seq;

		if (ctx->mp_capable) {
			ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req);
			if (!ctx->conn)
				goto fallback;

			ctx->subflow_id = 1;
			owner = mptcp_sk(ctx->conn);
			mptcp_pm_new_connection(owner, child, 1);

			/* with OoO packets we can reach here without ingress
			 * mpc option
			 */
			if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) {
				mptcp_subflow_fully_established(ctx, &mp_opt);
				mptcp_pm_fully_established(owner, child);
				ctx->pm_notified = 1;
			}
		} else if (ctx->mp_join) {
			owner = subflow_req->msk;
			if (!owner) {
				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
				goto dispose_child;
			}

			/* move the msk reference ownership to the subflow */
			subflow_req->msk = NULL;
			ctx->conn = (struct sock *)owner;

			if (subflow_use_different_sport(owner, sk)) {
				pr_debug("ack inet_sport=%d %d",
					 ntohs(inet_sk(sk)->inet_sport),
					 ntohs(inet_sk((struct sock *)owner)->inet_sport));
				if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
					SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
					goto dispose_child;
				}
				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
			}

			if (!mptcp_finish_join(child))
				goto dispose_child;

			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
			tcp_rsk(req)->drop_req = true;
		}
	}

	/* check for expected invariant - should never trigger, just help
	 * catching eariler subtle bugs
	 */
	WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp &&
		     (!mptcp_subflow_ctx(child) ||
		      !mptcp_subflow_ctx(child)->conn));
	return child;

dispose_child:
	mptcp_subflow_drop_ctx(child);
	tcp_rsk(req)->drop_req = true;
	inet_csk_prepare_for_destroy_sock(child);
	tcp_done(child);
	req->rsk_ops->send_reset(sk, skb);

	/* The last child reference will be released by the caller */
	return child;

fallback:
	mptcp_subflow_drop_ctx(child);
	return child;
}

static struct inet_connection_sock_af_ops subflow_specific __ro_after_init;
static struct proto tcp_prot_override __ro_after_init;

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

static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
	pr_debug("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.
		 */
		dbg_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 */
		dbg_bad_map(subflow, ssn);
		return false;
	}
	return true;
}

static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb,
					      bool csum_reqd)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	u32 offset, seq, delta;
	__sum16 csum;
	int len;

	if (!csum_reqd)
		return MAPPING_OK;

	/* mapping already validated on previous traversal */
	if (subflow->map_csum_len == subflow->map_data_len)
		return MAPPING_OK;

	/* traverse the receive queue, ensuring it contains a full
	 * DSS mapping and accumulating the related csum.
	 * Preserve the accoumlate csum across multiple calls, to compute
	 * the csum only once
	 */
	delta = subflow->map_data_len - subflow->map_csum_len;
	for (;;) {
		seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len;
		offset = seq - TCP_SKB_CB(skb)->seq;

		/* if the current skb has not been accounted yet, csum its contents
		 * up to the amount covered by the current DSS
		 */
		if (offset < skb->len) {
			__wsum csum;

			len = min(skb->len - offset, delta);
			csum = skb_checksum(skb, offset, len, 0);
			subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum,
								subflow->map_csum_len);

			delta -= len;
			subflow->map_csum_len += len;
		}
		if (delta == 0)
			break;

		if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) {
			/* if this subflow is closed, the partial mapping
			 * will be never completed; flush the pending skbs, so
			 * that subflow_sched_work_if_closed() can kick in
			 */
			if (unlikely(ssk->sk_state == TCP_CLOSE))
				while ((skb = skb_peek(&ssk->sk_receive_queue)))
					sk_eat_skb(ssk, skb);

			/* not enough data to validate the csum */
			return MAPPING_EMPTY;
		}

		/* the DSS mapping for next skbs will be validated later,
		 * when a get_mapping_status call will process such skb
		 */
		skb = skb->next;
	}

	/* note that 'map_data_len' accounts only for the carried data, does
	 * not include the eventual seq increment due to the data fin,
	 * while the pseudo header requires the original DSS data len,
	 * including that
	 */
	csum = __mptcp_make_csum(subflow->map_seq,
				 subflow->map_subflow_seq,
				 subflow->map_data_len + subflow->map_data_fin,
				 subflow->map_data_csum);
	if (unlikely(csum)) {
		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
		return MAPPING_BAD_CSUM;
	}

	subflow->valid_csum_seen = 1;
	return MAPPING_OK;
}

static enum mapping_status get_mapping_status(struct sock *ssk,
					      struct mptcp_sock *msk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	bool csum_reqd = READ_ONCE(msk->csum_enabled);
	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;

	if (mptcp_check_fallback(ssk))
		return MAPPING_DUMMY;

	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;
	}

	trace_get_mapping_status(mpext);

	data_len = mpext->data_len;
	if (data_len == 0) {
		pr_debug("infinite mapping received");
		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
		subflow->map_data_len = 0;
		return MAPPING_INVALID;
	}

	if (mpext->data_fin == 1) {
		if (data_len == 1) {
			bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
								 mpext->dsn64);
			pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq);
			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 {
				if (updated)
					mptcp_schedule_work((struct sock *)msk);

				return MAPPING_DATA_FIN;
			}
		} else {
			u64 data_fin_seq = mpext->data_seq + data_len - 1;

			/* If mpext->data_seq is a 32-bit value, data_fin_seq
			 * must also be limited to 32 bits.
			 */
			if (!mpext->dsn64)
				data_fin_seq &= GENMASK_ULL(31, 0);

			mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
			pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
				 data_fin_seq, mpext->dsn64);
		}

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

	map_seq = mptcp_expand_seq(READ_ONCE(msk->ack_seq), mpext->data_seq, mpext->dsn64);
	WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64);

	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 &&
		    subflow->map_csum_reqd == mpext->csum_reqd) {
			skb_ext_del(skb, SKB_EXT_MPTCP);
			goto validate_csum;
		}

		/* 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)) {
			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSNOMATCH);
			return MAPPING_INVALID;
		}

		/* will validate the next map after consuming the current one */
		goto validate_csum;
	}

	subflow->map_seq = map_seq;
	subflow->map_subflow_seq = mpext->subflow_seq;
	subflow->map_data_len = data_len;
	subflow->map_valid = 1;
	subflow->map_data_fin = mpext->data_fin;
	subflow->mpc_map = mpext->mpc_map;
	subflow->map_csum_reqd = mpext->csum_reqd;
	subflow->map_csum_len = 0;
	subflow->map_data_csum = csum_unfold(mpext->csum);

	/* Cfr RFC 8684 Section 3.3.0 */
	if (unlikely(subflow->map_csum_reqd != csum_reqd))
		return MAPPING_INVALID;

	pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
		 subflow->map_seq, subflow->map_subflow_seq,
		 subflow->map_data_len, subflow->map_csum_reqd,
		 subflow->map_data_csum);

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)) {
		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSTCPMISMATCH);
		return MAPPING_INVALID;
	}

	skb_ext_del(skb, SKB_EXT_MPTCP);

validate_csum:
	return validate_data_csum(ssk, skb, csum_reqd);
}

static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
				       u64 limit)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
	u32 incr;

	incr = limit >= skb->len ? skb->len + fin : limit;

	pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
		 subflow->map_subflow_seq);
	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
	tcp_sk(ssk)->copied_seq += incr;
	if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
		sk_eat_skb(ssk, skb);
	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
		subflow->map_valid = 0;
}

/* sched mptcp worker to remove the subflow if no more data is pending */
static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
{
	if (likely(ssk->sk_state != TCP_CLOSE))
		return;

	if (skb_queue_empty(&ssk->sk_receive_queue) &&
	    !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
		mptcp_schedule_work((struct sock *)msk);
}

static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
{
	struct mptcp_sock *msk = mptcp_sk(subflow->conn);

	if (subflow->mp_join)
		return false;
	else if (READ_ONCE(msk->csum_enabled))
		return !subflow->valid_csum_seen;
	else
		return !subflow->fully_established;
}

static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	unsigned long fail_tout;

	/* greceful failure can happen only on the MPC subflow */
	if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first)))
		return;

	/* since the close timeout take precedence on the fail one,
	 * no need to start the latter when the first is already set
	 */
	if (sock_flag((struct sock *)msk, SOCK_DEAD))
		return;

	/* we don't need extreme accuracy here, use a zero fail_tout as special
	 * value meaning no fail timeout at all;
	 */
	fail_tout = jiffies + TCP_RTO_MAX;
	if (!fail_tout)
		fail_tout = 1;
	WRITE_ONCE(subflow->fail_tout, fail_tout);
	tcp_send_ack(ssk);

	mptcp_reset_tout_timer(msk, subflow->fail_tout);
}

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;

	if (!skb_peek(&ssk->sk_receive_queue))
		WRITE_ONCE(subflow->data_avail, false);
	if (subflow->data_avail)
		return true;

	msk = mptcp_sk(subflow->conn);
	for (;;) {
		u64 ack_seq;
		u64 old_ack;

		status = get_mapping_status(ssk, msk);
		trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
		if (unlikely(status == MAPPING_INVALID || status == MAPPING_DUMMY ||
			     status == MAPPING_BAD_CSUM))
			goto fallback;

		if (status != MAPPING_OK)
			goto no_data;

		skb = skb_peek(&ssk->sk_receive_queue);
		if (WARN_ON_ONCE(!skb))
			goto no_data;

		if (unlikely(!READ_ONCE(msk->can_ack)))
			goto fallback;

		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 (unlikely(before64(ack_seq, old_ack))) {
			mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
			continue;
		}

		WRITE_ONCE(subflow->data_avail, true);
		break;
	}
	return true;

no_data:
	subflow_sched_work_if_closed(msk, ssk);
	return false;

fallback:
	if (!__mptcp_check_fallback(msk)) {
		/* RFC 8684 section 3.7. */
		if (status == MAPPING_BAD_CSUM &&
		    (subflow->mp_join || subflow->valid_csum_seen)) {
			subflow->send_mp_fail = 1;

			if (!READ_ONCE(msk->allow_infinite_fallback)) {
				subflow->reset_transient = 0;
				subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
				goto reset;
			}
			mptcp_subflow_fail(msk, ssk);
			WRITE_ONCE(subflow->data_avail, true);
			return true;
		}

		if (!subflow_can_fallback(subflow) && subflow->map_data_len) {
			/* fatal protocol error, close the socket.
			 * subflow_error_report() will introduce the appropriate barriers
			 */
			subflow->reset_transient = 0;
			subflow->reset_reason = MPTCP_RST_EMPTCP;

reset:
			WRITE_ONCE(ssk->sk_err, EBADMSG);
			tcp_set_state(ssk, TCP_CLOSE);
			while ((skb = skb_peek(&ssk->sk_receive_queue)))
				sk_eat_skb(ssk, skb);
			tcp_send_active_reset(ssk, GFP_ATOMIC);
			WRITE_ONCE(subflow->data_avail, false);
			return false;
		}

		mptcp_do_fallback(ssk);
	}

	skb = skb_peek(&ssk->sk_receive_queue);
	subflow->map_valid = 1;
	subflow->map_seq = READ_ONCE(msk->ack_seq);
	subflow->map_data_len = skb->len;
	subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
	WRITE_ONCE(subflow->data_avail, true);
	return true;
}

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

	/* 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;
		WRITE_ONCE(subflow->data_avail, false);

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

	return subflow_check_data_avail(sk);
}

/* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy,
 * not the ssk one.
 *
 * In mptcp, rwin is about the mptcp-level connection data.
 *
 * Data that is still on the ssk rx queue can thus be ignored,
 * as far as mptcp peer is concerned that data is still inflight.
 * DSS ACK is updated when skb is moved to the mptcp rx queue.
 */
void mptcp_space(const struct sock *ssk, int *space, int *full_space)
{
	const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	const struct sock *sk = subflow->conn;

	*space = __mptcp_space(sk);
	*full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
}

static void subflow_error_report(struct sock *ssk)
{
	struct sock *sk = mptcp_subflow_ctx(ssk)->conn;

	/* bail early if this is a no-op, so that we avoid introducing a
	 * problematic lockdep dependency between TCP accept queue lock
	 * and msk socket spinlock
	 */
	if (!sk->sk_socket)
		return;

	mptcp_data_lock(sk);
	if (!sock_owned_by_user(sk))
		__mptcp_error_report(sk);
	else
		__set_bit(MPTCP_ERROR_REPORT,  &mptcp_sk(sk)->cb_flags);
	mptcp_data_unlock(sk);
}

static void subflow_data_ready(struct sock *sk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
	u16 state = 1 << inet_sk_state_load(sk);
	struct sock *parent = subflow->conn;
	struct mptcp_sock *msk;

	trace_sk_data_ready(sk);

	msk = mptcp_sk(parent);
	if (state & TCPF_LISTEN) {
		/* MPJ subflow are removed from accept queue before reaching here,
		 * avoid stray wakeups
		 */
		if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue))
			return;

		parent->sk_data_ready(parent);
		return;
	}

	WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable &&
		     !subflow->mp_join && !(state & TCPF_CLOSE));

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

		/* subflow-level lowat test are not relevant.
		 * respect the msk-level threshold eventually mandating an immediate ack
		 */
		if (mptcp_data_avail(msk) < parent->sk_rcvlowat &&
		    (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss)
			inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
	} else if (unlikely(sk->sk_err)) {
		subflow_error_report(sk);
	}
}

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

	mptcp_propagate_sndbuf(sk, ssk);
	mptcp_write_space(sk);
}

static const 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);
	const 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

void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
			 struct sockaddr_storage *addr,
			 unsigned short family)
{
	memset(addr, 0, sizeof(*addr));
	addr->ss_family = family;
	if (addr->ss_family == AF_INET) {
		struct sockaddr_in *in_addr = (struct sockaddr_in *)addr;

		if (info->family == AF_INET)
			in_addr->sin_addr = info->addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
		else if (ipv6_addr_v4mapped(&info->addr6))
			in_addr->sin_addr.s_addr = info->addr6.s6_addr32[3];
#endif
		in_addr->sin_port = info->port;
	}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	else if (addr->ss_family == AF_INET6) {
		struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)addr;

		if (info->family == AF_INET)
			ipv6_addr_set_v4mapped(info->addr.s_addr,
					       &in6_addr->sin6_addr);
		else
			in6_addr->sin6_addr = info->addr6;
		in6_addr->sin6_port = info->port;
	}
#endif
}

int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
			    const struct mptcp_addr_info *remote)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_subflow_context *subflow;
	struct sockaddr_storage addr;
	int remote_id = remote->id;
	int local_id = loc->id;
	int err = -ENOTCONN;
	struct socket *sf;
	struct sock *ssk;
	u32 remote_token;
	int addrlen;
	int ifindex;
	u8 flags;

	if (!mptcp_is_fully_established(sk))
		goto err_out;

	err = mptcp_subflow_create_socket(sk, loc->family, &sf);
	if (err)
		goto err_out;

	ssk = sf->sk;
	subflow = mptcp_subflow_ctx(ssk);
	do {
		get_random_bytes(&subflow->local_nonce, sizeof(u32));
	} while (!subflow->local_nonce);

	if (local_id)
		subflow_set_local_id(subflow, local_id);

	mptcp_pm_get_flags_and_ifindex_by_id(msk, local_id,
					     &flags, &ifindex);
	subflow->remote_key_valid = 1;
	subflow->remote_key = msk->remote_key;
	subflow->local_key = msk->local_key;
	subflow->token = msk->token;
	mptcp_info2sockaddr(loc, &addr, ssk->sk_family);

	addrlen = sizeof(struct sockaddr_in);
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	if (addr.ss_family == AF_INET6)
		addrlen = sizeof(struct sockaddr_in6);
#endif
	ssk->sk_bound_dev_if = ifindex;
	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
	if (err)
		goto failed;

	mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
		 remote_token, local_id, remote_id);
	subflow->remote_token = remote_token;
	subflow->remote_id = remote_id;
	subflow->request_join = 1;
	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
	subflow->subflow_id = msk->subflow_id++;
	mptcp_info2sockaddr(remote, &addr, ssk->sk_family);

	sock_hold(ssk);
	list_add_tail(&subflow->node, &msk->conn_list);
	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
	if (err && err != -EINPROGRESS)
		goto failed_unlink;

	/* discard the subflow socket */
	mptcp_sock_graft(ssk, sk->sk_socket);
	iput(SOCK_INODE(sf));
	WRITE_ONCE(msk->allow_infinite_fallback, false);
	mptcp_stop_tout_timer(sk);
	return 0;

failed_unlink:
	list_del(&subflow->node);
	sock_put(mptcp_subflow_tcp_sock(subflow));

failed:
	subflow->disposable = 1;
	sock_release(sf);

err_out:
	/* we account subflows before the creation, and this failures will not
	 * be caught by sk_state_change()
	 */
	mptcp_pm_close_subflow(msk);
	return err;
}

static void mptcp_attach_cgroup(struct sock *parent, struct sock *child)
{
#ifdef CONFIG_SOCK_CGROUP_DATA
	struct sock_cgroup_data *parent_skcd = &parent->sk_cgrp_data,
				*child_skcd = &child->sk_cgrp_data;

	/* only the additional subflows created by kworkers have to be modified */
	if (cgroup_id(sock_cgroup_ptr(parent_skcd)) !=
	    cgroup_id(sock_cgroup_ptr(child_skcd))) {
#ifdef CONFIG_MEMCG
		struct mem_cgroup *memcg = parent->sk_memcg;

		mem_cgroup_sk_free(child);
		if (memcg && css_tryget(&memcg->css))
			child->sk_memcg = memcg;
#endif /* CONFIG_MEMCG */

		cgroup_sk_free(child_skcd);
		*child_skcd = *parent_skcd;
		cgroup_sk_clone(child_skcd);
	}
#endif /* CONFIG_SOCK_CGROUP_DATA */
}

static void mptcp_subflow_ops_override(struct sock *ssk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	if (ssk->sk_prot == &tcpv6_prot)
		ssk->sk_prot = &tcpv6_prot_override;
	else
#endif
		ssk->sk_prot = &tcp_prot_override;
}

static void mptcp_subflow_ops_undo_override(struct sock *ssk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	if (ssk->sk_prot == &tcpv6_prot_override)
		ssk->sk_prot = &tcpv6_prot;
	else
#endif
		ssk->sk_prot = &tcp_prot;
}

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

	/* un-accepted server sockets can reach here - on bad configuration
	 * bail early to avoid greater trouble later
	 */
	if (unlikely(!sk->sk_socket))
		return -EINVAL;

	err = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &sf);
	if (err)
		return err;

	lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING);

	err = security_mptcp_add_subflow(sk, sf->sk);
	if (err)
		goto err_free;

	/* the newly created socket has to be in the same cgroup as its parent */
	mptcp_attach_cgroup(sk, sf->sk);

	/* kernel sockets do not by default acquire net ref, but TCP timer
	 * needs it.
	 * Update ns_tracker to current stack trace and refcounted tracker.
	 */
	__netns_tracker_free(net, &sf->sk->ns_tracker, false);
	sf->sk->sk_net_refcnt = 1;
	get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL);
	sock_inuse_add(net, 1);
	err = tcp_set_ulp(sf->sk, "mptcp");
	if (err)
		goto err_free;

	mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk);
	release_sock(sf->sk);

	/* the newly created socket really belongs to the owning MPTCP master
	 * socket, even if for additional subflows the allocation is performed
	 * by a kernel workqueue. Adjust inode references, so that the
	 * procfs/diag interfaces really show this one belonging to the correct
	 * user.
	 */
	SOCK_INODE(sf)->i_ino = SOCK_INODE(sk->sk_socket)->i_ino;
	SOCK_INODE(sf)->i_uid = SOCK_INODE(sk->sk_socket)->i_uid;
	SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid;

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

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

	return 0;

err_free:
	release_sock(sf->sk);
	sock_release(sf);
	return err;
}

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);
	INIT_LIST_HEAD(&ctx->delegated_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 = subflow->conn;
	struct mptcp_sock *msk;

	__subflow_state_change(sk);

	msk = mptcp_sk(parent);
	if (subflow_simultaneous_connect(sk)) {
		mptcp_do_fallback(sk);
		mptcp_rcv_space_init(msk, sk);
		pr_fallback(msk);
		subflow->conn_finished = 1;
		mptcp_set_connected(parent);
	}

	/* 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 (mptcp_subflow_data_available(sk))
		mptcp_data_ready(parent, sk);
	else if (unlikely(sk->sk_err))
		subflow_error_report(sk);

	subflow_sched_work_if_closed(mptcp_sk(parent), sk);

	/* when the fallback subflow closes the rx side, trigger a 'dummy'
	 * ingress data fin, so that the msk state will follow along
	 */
	if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk &&
	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
		mptcp_schedule_work(parent);
}

void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
{
	struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
	struct request_sock *req, *head, *tail;
	struct mptcp_subflow_context *subflow;
	struct sock *sk, *ssk;

	/* Due to lock dependencies no relevant lock can be acquired under rskq_lock.
	 * Splice the req list, so that accept() can not reach the pending ssk after
	 * the listener socket is released below.
	 */
	spin_lock_bh(&queue->rskq_lock);
	head = queue->rskq_accept_head;
	tail = queue->rskq_accept_tail;
	queue->rskq_accept_head = NULL;
	queue->rskq_accept_tail = NULL;
	spin_unlock_bh(&queue->rskq_lock);

	if (!head)
		return;

	/* can't acquire the msk socket lock under the subflow one,
	 * or will cause ABBA deadlock
	 */
	release_sock(listener_ssk);

	for (req = head; req; req = req->dl_next) {
		ssk = req->sk;
		if (!sk_is_mptcp(ssk))
			continue;

		subflow = mptcp_subflow_ctx(ssk);
		if (!subflow || !subflow->conn)
			continue;

		sk = subflow->conn;
		sock_hold(sk);

		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
		__mptcp_unaccepted_force_close(sk);
		release_sock(sk);

		/* lockdep will report a false positive ABBA deadlock
		 * between cancel_work_sync and the listener socket.
		 * The involved locks belong to different sockets WRT
		 * the existing AB chain.
		 * Using a per socket key is problematic as key
		 * deregistration requires process context and must be
		 * performed at socket disposal time, in atomic
		 * context.
		 * Just tell lockdep to consider the listener socket
		 * released here.
		 */
		mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
		mptcp_cancel_work(sk);
		mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_);

		sock_put(sk);
	}

	/* we are still under the listener msk socket lock */
	lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING);

	/* restore the listener queue, to let the TCP code clean it up */
	spin_lock_bh(&queue->rskq_lock);
	WARN_ON_ONCE(queue->rskq_accept_head);
	queue->rskq_accept_head = head;
	queue->rskq_accept_tail = tail;
	spin_unlock_bh(&queue->rskq_lock);
}

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_state_change = sk->sk_state_change;
	ctx->tcp_error_report = sk->sk_error_report;

	WARN_ON_ONCE(sk->sk_data_ready != sock_def_readable);
	WARN_ON_ONCE(sk->sk_write_space != sk_stream_write_space);

	sk->sk_data_ready = subflow_data_ready;
	sk->sk_write_space = subflow_write_space;
	sk->sk_state_change = subflow_state_change;
	sk->sk_error_report = subflow_error_report;
out:
	return err;
}

static void subflow_ulp_release(struct sock *ssk)
{
	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
	bool release = true;
	struct sock *sk;

	if (!ctx)
		return;

	sk = ctx->conn;
	if (sk) {
		/* if the msk has been orphaned, keep the ctx
		 * alive, will be freed by __mptcp_close_ssk(),
		 * when the subflow is still unaccepted
		 */
		release = ctx->disposable || list_empty(&ctx->node);

		/* inet_child_forget() does not call sk_state_change(),
		 * explicitly trigger the socket close machinery
		 */
		if (!release && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW,
						  &mptcp_sk(sk)->flags))
			mptcp_schedule_work(sk);
		sock_put(sk);
	}

	mptcp_subflow_ops_undo_override(ssk);
	if (release)
		kfree_rcu(ctx, rcu);
}

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_req->mp_join)) {
		subflow_ulp_fallback(newsk, old_ctx);
		return;
	}

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

	new_ctx->conn_finished = 1;
	new_ctx->icsk_af_ops = old_ctx->icsk_af_ops;
	new_ctx->tcp_state_change = old_ctx->tcp_state_change;
	new_ctx->tcp_error_report = old_ctx->tcp_error_report;
	new_ctx->rel_write_seq = 1;
	new_ctx->tcp_sock = newsk;

	if (subflow_req->mp_capable) {
		/* see comments in subflow_syn_recv_sock(), MPTCP connection
		 * is fully established only after we receive the remote key
		 */
		new_ctx->mp_capable = 1;
		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;

		/* this is the first subflow, id is always 0 */
		new_ctx->local_id_valid = 1;
	} else if (subflow_req->mp_join) {
		new_ctx->ssn_offset = subflow_req->ssn_offset;
		new_ctx->mp_join = 1;
		new_ctx->fully_established = 1;
		new_ctx->remote_key_valid = 1;
		new_ctx->backup = subflow_req->backup;
		new_ctx->remote_id = subflow_req->remote_id;
		new_ctx->token = subflow_req->token;
		new_ctx->thmac = subflow_req->thmac;

		/* the subflow req id is valid, fetched via subflow_check_req()
		 * and subflow_token_join_request()
		 */
		subflow_set_local_id(new_ctx, subflow_req->local_id);
	}
}

static void tcp_release_cb_override(struct sock *ssk)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	long status;

	/* process and clear all the pending actions, but leave the subflow into
	 * the napi queue. To respect locking, only the same CPU that originated
	 * the action can touch the list. mptcp_napi_poll will take care of it.
	 */
	status = set_mask_bits(&subflow->delegated_status, MPTCP_DELEGATE_ACTIONS_MASK, 0);
	if (status)
		mptcp_subflow_process_delegated(ssk, status);

	tcp_release_cb(ssk);
}

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 = 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;

	return 0;
}

void __init mptcp_subflow_init(void)
{
	mptcp_subflow_v4_request_sock_ops = tcp_request_sock_ops;
	mptcp_subflow_v4_request_sock_ops.slab_name = "request_sock_subflow_v4";
	mptcp_subflow_v4_request_sock_ops.destructor = subflow_v4_req_destructor;

	if (subflow_ops_init(&mptcp_subflow_v4_request_sock_ops) != 0)
		panic("MPTCP: failed to init subflow v4 request sock ops\n");

	subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops;
	subflow_request_sock_ipv4_ops.route_req = subflow_v4_route_req;
	subflow_request_sock_ipv4_ops.send_synack = subflow_v4_send_synack;

	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;

	tcp_prot_override = tcp_prot;
	tcp_prot_override.release_cb = tcp_release_cb_override;

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	/* In struct mptcp_subflow_request_sock, we assume the TCP request sock
	 * structures for v4 and v6 have the same size. It should not changed in
	 * the future but better to make sure to be warned if it is no longer
	 * the case.
	 */
	BUILD_BUG_ON(sizeof(struct tcp_request_sock) != sizeof(struct tcp6_request_sock));

	mptcp_subflow_v6_request_sock_ops = tcp6_request_sock_ops;
	mptcp_subflow_v6_request_sock_ops.slab_name = "request_sock_subflow_v6";
	mptcp_subflow_v6_request_sock_ops.destructor = subflow_v6_req_destructor;

	if (subflow_ops_init(&mptcp_subflow_v6_request_sock_ops) != 0)
		panic("MPTCP: failed to init subflow v6 request sock ops\n");

	subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops;
	subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req;
	subflow_request_sock_ipv6_ops.send_synack = subflow_v6_send_synack;

	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_v6_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.rebuild_header = subflow_rebuild_header;

	tcpv6_prot_override = tcpv6_prot;
	tcpv6_prot_override.release_cb = tcp_release_cb_override;
#endif

	mptcp_diag_subflow_init(&subflow_ulp_ops);

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