summaryrefslogtreecommitdiff
path: root/net/mptcp/pm_netlink.c
blob: d66fbd558263279f9f1a66f18c8034019953eeb2 (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
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
// SPDX-License-Identifier: GPL-2.0
/* Multipath TCP
 *
 * Copyright (c) 2020, Red Hat, Inc.
 */

#define pr_fmt(fmt) "MPTCP: " fmt

#include <linux/inet.h>
#include <linux/kernel.h>
#include <net/tcp.h>
#include <net/netns/generic.h>
#include <net/mptcp.h>
#include <net/genetlink.h>
#include <uapi/linux/mptcp.h>

#include "protocol.h"
#include "mib.h"

/* forward declaration */
static struct genl_family mptcp_genl_family;

static int pm_nl_pernet_id;

struct mptcp_pm_add_entry {
	struct list_head	list;
	struct mptcp_addr_info	addr;
	struct timer_list	add_timer;
	struct mptcp_sock	*sock;
	u8			retrans_times;
};

struct pm_nl_pernet {
	/* protects pernet updates */
	spinlock_t		lock;
	struct list_head	local_addr_list;
	unsigned int		addrs;
	unsigned int		stale_loss_cnt;
	unsigned int		add_addr_signal_max;
	unsigned int		add_addr_accept_max;
	unsigned int		local_addr_max;
	unsigned int		subflows_max;
	unsigned int		next_id;
	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
};

#define MPTCP_PM_ADDR_MAX	8
#define ADD_ADDR_RETRANS_MAX	3

static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net)
{
	return net_generic(net, pm_nl_pernet_id);
}

static struct pm_nl_pernet *
pm_nl_get_pernet_from_msk(const struct mptcp_sock *msk)
{
	return pm_nl_get_pernet(sock_net((struct sock *)msk));
}

bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
			   const struct mptcp_addr_info *b, bool use_port)
{
	bool addr_equals = false;

	if (a->family == b->family) {
		if (a->family == AF_INET)
			addr_equals = a->addr.s_addr == b->addr.s_addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
		else
			addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6);
	} else if (a->family == AF_INET) {
		if (ipv6_addr_v4mapped(&b->addr6))
			addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3];
	} else if (b->family == AF_INET) {
		if (ipv6_addr_v4mapped(&a->addr6))
			addr_equals = a->addr6.s6_addr32[3] == b->addr.s_addr;
#endif
	}

	if (!addr_equals)
		return false;
	if (!use_port)
		return true;

	return a->port == b->port;
}

static void local_address(const struct sock_common *skc,
			  struct mptcp_addr_info *addr)
{
	addr->family = skc->skc_family;
	addr->port = htons(skc->skc_num);
	if (addr->family == AF_INET)
		addr->addr.s_addr = skc->skc_rcv_saddr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	else if (addr->family == AF_INET6)
		addr->addr6 = skc->skc_v6_rcv_saddr;
#endif
}

static void remote_address(const struct sock_common *skc,
			   struct mptcp_addr_info *addr)
{
	addr->family = skc->skc_family;
	addr->port = skc->skc_dport;
	if (addr->family == AF_INET)
		addr->addr.s_addr = skc->skc_daddr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	else if (addr->family == AF_INET6)
		addr->addr6 = skc->skc_v6_daddr;
#endif
}

static bool lookup_subflow_by_saddr(const struct list_head *list,
				    const struct mptcp_addr_info *saddr)
{
	struct mptcp_subflow_context *subflow;
	struct mptcp_addr_info cur;
	struct sock_common *skc;

	list_for_each_entry(subflow, list, node) {
		skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);

		local_address(skc, &cur);
		if (mptcp_addresses_equal(&cur, saddr, saddr->port))
			return true;
	}

	return false;
}

static bool lookup_subflow_by_daddr(const struct list_head *list,
				    const struct mptcp_addr_info *daddr)
{
	struct mptcp_subflow_context *subflow;
	struct mptcp_addr_info cur;
	struct sock_common *skc;

	list_for_each_entry(subflow, list, node) {
		skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);

		remote_address(skc, &cur);
		if (mptcp_addresses_equal(&cur, daddr, daddr->port))
			return true;
	}

	return false;
}

static struct mptcp_pm_addr_entry *
select_local_address(const struct pm_nl_pernet *pernet,
		     const struct mptcp_sock *msk)
{
	const struct sock *sk = (const struct sock *)msk;
	struct mptcp_pm_addr_entry *entry, *ret = NULL;

	msk_owned_by_me(msk);

	rcu_read_lock();
	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
			continue;

		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
			continue;

		if (entry->addr.family != sk->sk_family) {
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
			if ((entry->addr.family == AF_INET &&
			     !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ||
			    (sk->sk_family == AF_INET &&
			     !ipv6_addr_v4mapped(&entry->addr.addr6)))
#endif
				continue;
		}

		ret = entry;
		break;
	}
	rcu_read_unlock();
	return ret;
}

static struct mptcp_pm_addr_entry *
select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
{
	struct mptcp_pm_addr_entry *entry, *ret = NULL;

	rcu_read_lock();
	/* do not keep any additional per socket state, just signal
	 * the address list in order.
	 * Note: removal from the local address list during the msk life-cycle
	 * can lead to additional addresses not being announced.
	 */
	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
			continue;

		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
			continue;

		ret = entry;
		break;
	}
	rcu_read_unlock();
	return ret;
}

unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
{
	const struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->add_addr_signal_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max);

unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->add_addr_accept_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max);

unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->subflows_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max);

unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	return READ_ONCE(pernet->local_addr_max);
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max);

bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);

	if (msk->pm.subflows == mptcp_pm_get_subflows_max(msk) ||
	    (find_next_and_bit(pernet->id_bitmap, msk->pm.id_avail_bitmap,
			       MPTCP_PM_MAX_ADDR_ID + 1, 0) == MPTCP_PM_MAX_ADDR_ID + 1)) {
		WRITE_ONCE(msk->pm.work_pending, false);
		return false;
	}
	return true;
}

struct mptcp_pm_add_entry *
mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
				const struct mptcp_addr_info *addr)
{
	struct mptcp_pm_add_entry *entry;

	lockdep_assert_held(&msk->pm.lock);

	list_for_each_entry(entry, &msk->pm.anno_list, list) {
		if (mptcp_addresses_equal(&entry->addr, addr, true))
			return entry;
	}

	return NULL;
}

bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
{
	struct mptcp_pm_add_entry *entry;
	struct mptcp_addr_info saddr;
	bool ret = false;

	local_address((struct sock_common *)sk, &saddr);

	spin_lock_bh(&msk->pm.lock);
	list_for_each_entry(entry, &msk->pm.anno_list, list) {
		if (mptcp_addresses_equal(&entry->addr, &saddr, true)) {
			ret = true;
			goto out;
		}
	}

out:
	spin_unlock_bh(&msk->pm.lock);
	return ret;
}

static void mptcp_pm_add_timer(struct timer_list *timer)
{
	struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer);
	struct mptcp_sock *msk = entry->sock;
	struct sock *sk = (struct sock *)msk;

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

	if (!msk)
		return;

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

	if (!entry->addr.id)
		return;

	if (mptcp_pm_should_add_signal_addr(msk)) {
		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
		goto out;
	}

	spin_lock_bh(&msk->pm.lock);

	if (!mptcp_pm_should_add_signal_addr(msk)) {
		pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
		mptcp_pm_announce_addr(msk, &entry->addr, false);
		mptcp_pm_add_addr_send_ack(msk);
		entry->retrans_times++;
	}

	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
		sk_reset_timer(sk, timer,
			       jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));

	spin_unlock_bh(&msk->pm.lock);

	if (entry->retrans_times == ADD_ADDR_RETRANS_MAX)
		mptcp_pm_subflow_established(msk);

out:
	__sock_put(sk);
}

struct mptcp_pm_add_entry *
mptcp_pm_del_add_timer(struct mptcp_sock *msk,
		       const struct mptcp_addr_info *addr, bool check_id)
{
	struct mptcp_pm_add_entry *entry;
	struct sock *sk = (struct sock *)msk;

	spin_lock_bh(&msk->pm.lock);
	entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
	if (entry && (!check_id || entry->addr.id == addr->id))
		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
	spin_unlock_bh(&msk->pm.lock);

	if (entry && (!check_id || entry->addr.id == addr->id))
		sk_stop_timer_sync(sk, &entry->add_timer);

	return entry;
}

bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
			      const struct mptcp_pm_addr_entry *entry)
{
	struct mptcp_pm_add_entry *add_entry = NULL;
	struct sock *sk = (struct sock *)msk;
	struct net *net = sock_net(sk);

	lockdep_assert_held(&msk->pm.lock);

	add_entry = mptcp_lookup_anno_list_by_saddr(msk, &entry->addr);

	if (add_entry) {
		if (mptcp_pm_is_kernel(msk))
			return false;

		sk_reset_timer(sk, &add_entry->add_timer,
			       jiffies + mptcp_get_add_addr_timeout(net));
		return true;
	}

	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
	if (!add_entry)
		return false;

	list_add(&add_entry->list, &msk->pm.anno_list);

	add_entry->addr = entry->addr;
	add_entry->sock = msk;
	add_entry->retrans_times = 0;

	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
	sk_reset_timer(sk, &add_entry->add_timer,
		       jiffies + mptcp_get_add_addr_timeout(net));

	return true;
}

void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
{
	struct mptcp_pm_add_entry *entry, *tmp;
	struct sock *sk = (struct sock *)msk;
	LIST_HEAD(free_list);

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

	spin_lock_bh(&msk->pm.lock);
	list_splice_init(&msk->pm.anno_list, &free_list);
	spin_unlock_bh(&msk->pm.lock);

	list_for_each_entry_safe(entry, tmp, &free_list, list) {
		sk_stop_timer_sync(sk, &entry->add_timer);
		kfree(entry);
	}
}

static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr,
				  const struct mptcp_addr_info *addr)
{
	int i;

	for (i = 0; i < nr; i++) {
		if (addrs[i].id == addr->id)
			return true;
	}

	return false;
}

/* Fill all the remote addresses into the array addrs[],
 * and return the array size.
 */
static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh,
					      struct mptcp_addr_info *addrs)
{
	bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
	struct sock *sk = (struct sock *)msk, *ssk;
	struct mptcp_subflow_context *subflow;
	struct mptcp_addr_info remote = { 0 };
	unsigned int subflows_max;
	int i = 0;

	subflows_max = mptcp_pm_get_subflows_max(msk);
	remote_address((struct sock_common *)sk, &remote);

	/* Non-fullmesh endpoint, fill in the single entry
	 * corresponding to the primary MPC subflow remote address
	 */
	if (!fullmesh) {
		if (deny_id0)
			return 0;

		msk->pm.subflows++;
		addrs[i++] = remote;
	} else {
		mptcp_for_each_subflow(msk, subflow) {
			ssk = mptcp_subflow_tcp_sock(subflow);
			remote_address((struct sock_common *)ssk, &addrs[i]);
			addrs[i].id = subflow->remote_id;
			if (deny_id0 && !addrs[i].id)
				continue;

			if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
			    msk->pm.subflows < subflows_max) {
				msk->pm.subflows++;
				i++;
			}
		}
	}

	return i;
}

static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
				bool prio, bool backup)
{
	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
	bool slow;

	pr_debug("send ack for %s",
		 prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"));

	slow = lock_sock_fast(ssk);
	if (prio) {
		if (subflow->backup != backup)
			msk->last_snd = NULL;

		subflow->send_mp_prio = 1;
		subflow->backup = backup;
		subflow->request_bkup = backup;
	}

	__mptcp_subflow_send_ack(ssk);
	unlock_sock_fast(ssk, slow);
}

static void mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
			      bool prio, bool backup)
{
	spin_unlock_bh(&msk->pm.lock);
	__mptcp_pm_send_ack(msk, subflow, prio, backup);
	spin_lock_bh(&msk->pm.lock);
}

static struct mptcp_pm_addr_entry *
__lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
{
	struct mptcp_pm_addr_entry *entry;

	list_for_each_entry(entry, &pernet->local_addr_list, list) {
		if (entry->addr.id == id)
			return entry;
	}
	return NULL;
}

static struct mptcp_pm_addr_entry *
__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info,
	      bool lookup_by_id)
{
	struct mptcp_pm_addr_entry *entry;

	list_for_each_entry(entry, &pernet->local_addr_list, list) {
		if ((!lookup_by_id &&
		     mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) ||
		    (lookup_by_id && entry->addr.id == info->id))
			return entry;
	}
	return NULL;
}

static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
{
	struct sock *sk = (struct sock *)msk;
	struct mptcp_pm_addr_entry *local;
	unsigned int add_addr_signal_max;
	unsigned int local_addr_max;
	struct pm_nl_pernet *pernet;
	unsigned int subflows_max;

	pernet = pm_nl_get_pernet(sock_net(sk));

	add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk);
	local_addr_max = mptcp_pm_get_local_addr_max(msk);
	subflows_max = mptcp_pm_get_subflows_max(msk);

	/* do lazy endpoint usage accounting for the MPC subflows */
	if (unlikely(!(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED))) && msk->first) {
		struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(msk->first);
		struct mptcp_pm_addr_entry *entry;
		struct mptcp_addr_info mpc_addr;
		bool backup = false;

		local_address((struct sock_common *)msk->first, &mpc_addr);
		rcu_read_lock();
		entry = __lookup_addr(pernet, &mpc_addr, false);
		if (entry) {
			__clear_bit(entry->addr.id, msk->pm.id_avail_bitmap);
			msk->mpc_endpoint_id = entry->addr.id;
			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
		}
		rcu_read_unlock();

		if (backup)
			mptcp_pm_send_ack(msk, subflow, true, backup);

		msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED);
	}

	pr_debug("local %d:%d signal %d:%d subflows %d:%d\n",
		 msk->pm.local_addr_used, local_addr_max,
		 msk->pm.add_addr_signaled, add_addr_signal_max,
		 msk->pm.subflows, subflows_max);

	/* check first for announce */
	if (msk->pm.add_addr_signaled < add_addr_signal_max) {
		local = select_signal_address(pernet, msk);

		/* due to racing events on both ends we can reach here while
		 * previous add address is still running: if we invoke now
		 * mptcp_pm_announce_addr(), that will fail and the
		 * corresponding id will be marked as used.
		 * Instead let the PM machinery reschedule us when the
		 * current address announce will be completed.
		 */
		if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
			return;

		if (local) {
			if (mptcp_pm_alloc_anno_list(msk, local)) {
				__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
				msk->pm.add_addr_signaled++;
				mptcp_pm_announce_addr(msk, &local->addr, false);
				mptcp_pm_nl_addr_send_ack(msk);
			}
		}
	}

	/* check if should create a new subflow */
	while (msk->pm.local_addr_used < local_addr_max &&
	       msk->pm.subflows < subflows_max) {
		struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
		bool fullmesh;
		int i, nr;

		local = select_local_address(pernet, msk);
		if (!local)
			break;

		fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);

		msk->pm.local_addr_used++;
		nr = fill_remote_addresses_vec(msk, fullmesh, addrs);
		if (nr)
			__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
		spin_unlock_bh(&msk->pm.lock);
		for (i = 0; i < nr; i++)
			__mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
		spin_lock_bh(&msk->pm.lock);
	}
	mptcp_pm_nl_check_work_pending(msk);
}

static void mptcp_pm_nl_fully_established(struct mptcp_sock *msk)
{
	mptcp_pm_create_subflow_or_signal_addr(msk);
}

static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
{
	mptcp_pm_create_subflow_or_signal_addr(msk);
}

/* Fill all the local addresses into the array addrs[],
 * and return the array size.
 */
static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
					     struct mptcp_addr_info *addrs)
{
	struct sock *sk = (struct sock *)msk;
	struct mptcp_pm_addr_entry *entry;
	struct mptcp_addr_info local;
	struct pm_nl_pernet *pernet;
	unsigned int subflows_max;
	int i = 0;

	pernet = pm_nl_get_pernet_from_msk(msk);
	subflows_max = mptcp_pm_get_subflows_max(msk);

	rcu_read_lock();
	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
			continue;

		if (entry->addr.family != sk->sk_family) {
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
			if ((entry->addr.family == AF_INET &&
			     !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ||
			    (sk->sk_family == AF_INET &&
			     !ipv6_addr_v4mapped(&entry->addr.addr6)))
#endif
				continue;
		}

		if (msk->pm.subflows < subflows_max) {
			msk->pm.subflows++;
			addrs[i++] = entry->addr;
		}
	}
	rcu_read_unlock();

	/* If the array is empty, fill in the single
	 * 'IPADDRANY' local address
	 */
	if (!i) {
		memset(&local, 0, sizeof(local));
		local.family = msk->pm.remote.family;

		msk->pm.subflows++;
		addrs[i++] = local;
	}

	return i;
}

static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
{
	struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
	struct sock *sk = (struct sock *)msk;
	unsigned int add_addr_accept_max;
	struct mptcp_addr_info remote;
	unsigned int subflows_max;
	int i, nr;

	add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
	subflows_max = mptcp_pm_get_subflows_max(msk);

	pr_debug("accepted %d:%d remote family %d",
		 msk->pm.add_addr_accepted, add_addr_accept_max,
		 msk->pm.remote.family);

	remote = msk->pm.remote;
	mptcp_pm_announce_addr(msk, &remote, true);
	mptcp_pm_nl_addr_send_ack(msk);

	if (lookup_subflow_by_daddr(&msk->conn_list, &remote))
		return;

	/* pick id 0 port, if none is provided the remote address */
	if (!remote.port)
		remote.port = sk->sk_dport;

	/* connect to the specified remote address, using whatever
	 * local address the routing configuration will pick.
	 */
	nr = fill_local_addresses_vec(msk, addrs);

	msk->pm.add_addr_accepted++;
	if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
	    msk->pm.subflows >= subflows_max)
		WRITE_ONCE(msk->pm.accept_addr, false);

	spin_unlock_bh(&msk->pm.lock);
	for (i = 0; i < nr; i++)
		__mptcp_subflow_connect(sk, &addrs[i], &remote);
	spin_lock_bh(&msk->pm.lock);
}

void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
{
	struct mptcp_subflow_context *subflow;

	msk_owned_by_me(msk);
	lockdep_assert_held(&msk->pm.lock);

	if (!mptcp_pm_should_add_signal(msk) &&
	    !mptcp_pm_should_rm_signal(msk))
		return;

	subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
	if (subflow)
		mptcp_pm_send_ack(msk, subflow, false, false);
}

int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
				 struct mptcp_addr_info *addr,
				 struct mptcp_addr_info *rem,
				 u8 bkup)
{
	struct mptcp_subflow_context *subflow;

	pr_debug("bkup=%d", bkup);

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

		local_address((struct sock_common *)ssk, &local);
		if (!mptcp_addresses_equal(&local, addr, addr->port))
			continue;

		if (rem && rem->family != AF_UNSPEC) {
			remote_address((struct sock_common *)ssk, &remote);
			if (!mptcp_addresses_equal(&remote, rem, rem->port))
				continue;
		}

		__mptcp_pm_send_ack(msk, subflow, true, bkup);
		return 0;
	}

	return -EINVAL;
}

static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id)
{
	return local_id == id || (!local_id && msk->mpc_endpoint_id == id);
}

static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
					   const struct mptcp_rm_list *rm_list,
					   enum linux_mptcp_mib_field rm_type)
{
	struct mptcp_subflow_context *subflow, *tmp;
	struct sock *sk = (struct sock *)msk;
	u8 i;

	pr_debug("%s rm_list_nr %d",
		 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr);

	msk_owned_by_me(msk);

	if (sk->sk_state == TCP_LISTEN)
		return;

	if (!rm_list->nr)
		return;

	if (list_empty(&msk->conn_list))
		return;

	for (i = 0; i < rm_list->nr; i++) {
		u8 rm_id = rm_list->ids[i];
		bool removed = false;

		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
			u8 id = subflow->local_id;

			if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
				continue;
			if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
				continue;

			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
				 i, rm_id, subflow->local_id, subflow->remote_id,
				 msk->mpc_endpoint_id);
			spin_unlock_bh(&msk->pm.lock);
			mptcp_subflow_shutdown(sk, ssk, how);

			/* the following takes care of updating the subflows counter */
			mptcp_close_ssk(sk, ssk, subflow);
			spin_lock_bh(&msk->pm.lock);

			removed = true;
			__MPTCP_INC_STATS(sock_net(sk), rm_type);
		}
		if (rm_type == MPTCP_MIB_RMSUBFLOW)
			__set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
		if (!removed)
			continue;

		if (!mptcp_pm_is_kernel(msk))
			continue;

		if (rm_type == MPTCP_MIB_RMADDR) {
			msk->pm.add_addr_accepted--;
			WRITE_ONCE(msk->pm.accept_addr, true);
		} else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
			msk->pm.local_addr_used--;
		}
	}
}

static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
{
	mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
}

void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
				     const struct mptcp_rm_list *rm_list)
{
	mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
}

void mptcp_pm_nl_work(struct mptcp_sock *msk)
{
	struct mptcp_pm_data *pm = &msk->pm;

	msk_owned_by_me(msk);

	if (!(pm->status & MPTCP_PM_WORK_MASK))
		return;

	spin_lock_bh(&msk->pm.lock);

	pr_debug("msk=%p status=%x", msk, pm->status);
	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
		mptcp_pm_nl_add_addr_received(msk);
	}
	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
		mptcp_pm_nl_addr_send_ack(msk);
	}
	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
		mptcp_pm_nl_rm_addr_received(msk);
	}
	if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
		pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
		mptcp_pm_nl_fully_established(msk);
	}
	if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) {
		pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED);
		mptcp_pm_nl_subflow_established(msk);
	}

	spin_unlock_bh(&msk->pm.lock);
}

static bool address_use_port(struct mptcp_pm_addr_entry *entry)
{
	return (entry->flags &
		(MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) ==
		MPTCP_PM_ADDR_FLAG_SIGNAL;
}

/* caller must ensure the RCU grace period is already elapsed */
static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
{
	if (entry->lsk)
		sock_release(entry->lsk);
	kfree(entry);
}

static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
					     struct mptcp_pm_addr_entry *entry)
{
	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
	unsigned int addr_max;
	int ret = -EINVAL;

	spin_lock_bh(&pernet->lock);
	/* to keep the code simple, don't do IDR-like allocation for address ID,
	 * just bail when we exceed limits
	 */
	if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID)
		pernet->next_id = 1;
	if (pernet->addrs >= MPTCP_PM_ADDR_MAX) {
		ret = -ERANGE;
		goto out;
	}
	if (test_bit(entry->addr.id, pernet->id_bitmap)) {
		ret = -EBUSY;
		goto out;
	}

	/* do not insert duplicate address, differentiate on port only
	 * singled addresses
	 */
	if (!address_use_port(entry))
		entry->addr.port = 0;
	list_for_each_entry(cur, &pernet->local_addr_list, list) {
		if (mptcp_addresses_equal(&cur->addr, &entry->addr,
					  cur->addr.port || entry->addr.port)) {
			/* allow replacing the exiting endpoint only if such
			 * endpoint is an implicit one and the user-space
			 * did not provide an endpoint id
			 */
			if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) {
				ret = -EEXIST;
				goto out;
			}
			if (entry->addr.id)
				goto out;

			pernet->addrs--;
			entry->addr.id = cur->addr.id;
			list_del_rcu(&cur->list);
			del_entry = cur;
			break;
		}
	}

	if (!entry->addr.id) {
find_next:
		entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
						    MPTCP_PM_MAX_ADDR_ID + 1,
						    pernet->next_id);
		if (!entry->addr.id && pernet->next_id != 1) {
			pernet->next_id = 1;
			goto find_next;
		}
	}

	if (!entry->addr.id)
		goto out;

	__set_bit(entry->addr.id, pernet->id_bitmap);
	if (entry->addr.id > pernet->next_id)
		pernet->next_id = entry->addr.id;

	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
		addr_max = pernet->add_addr_signal_max;
		WRITE_ONCE(pernet->add_addr_signal_max, addr_max + 1);
	}
	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
		addr_max = pernet->local_addr_max;
		WRITE_ONCE(pernet->local_addr_max, addr_max + 1);
	}

	pernet->addrs++;
	if (!entry->addr.port)
		list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
	else
		list_add_rcu(&entry->list, &pernet->local_addr_list);
	ret = entry->addr.id;

out:
	spin_unlock_bh(&pernet->lock);

	/* just replaced an existing entry, free it */
	if (del_entry) {
		synchronize_rcu();
		__mptcp_pm_release_addr_entry(del_entry);
	}
	return ret;
}

static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
					    struct mptcp_pm_addr_entry *entry)
{
	int addrlen = sizeof(struct sockaddr_in);
	struct sockaddr_storage addr;
	struct mptcp_sock *msk;
	struct socket *ssock;
	int backlog = 1024;
	int err;

	err = sock_create_kern(sock_net(sk), entry->addr.family,
			       SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk);
	if (err)
		return err;

	msk = mptcp_sk(entry->lsk->sk);
	if (!msk)
		return -EINVAL;

	ssock = __mptcp_nmpc_socket(msk);
	if (!ssock)
		return -EINVAL;

	mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family);
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	if (entry->addr.family == AF_INET6)
		addrlen = sizeof(struct sockaddr_in6);
#endif
	err = kernel_bind(ssock, (struct sockaddr *)&addr, addrlen);
	if (err)
		return err;

	err = kernel_listen(ssock, backlog);
	if (err)
		return err;

	return 0;
}

int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
{
	struct mptcp_pm_addr_entry *entry;
	struct mptcp_addr_info skc_local;
	struct mptcp_addr_info msk_local;
	struct pm_nl_pernet *pernet;
	int ret = -1;

	if (WARN_ON_ONCE(!msk))
		return -1;

	/* The 0 ID mapping is defined by the first subflow, copied into the msk
	 * addr
	 */
	local_address((struct sock_common *)msk, &msk_local);
	local_address((struct sock_common *)skc, &skc_local);
	if (mptcp_addresses_equal(&msk_local, &skc_local, false))
		return 0;

	if (mptcp_pm_is_userspace(msk))
		return mptcp_userspace_pm_get_local_id(msk, &skc_local);

	pernet = pm_nl_get_pernet_from_msk(msk);

	rcu_read_lock();
	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
		if (mptcp_addresses_equal(&entry->addr, &skc_local, entry->addr.port)) {
			ret = entry->addr.id;
			break;
		}
	}
	rcu_read_unlock();
	if (ret >= 0)
		return ret;

	/* address not found, add to local list */
	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
	if (!entry)
		return -ENOMEM;

	entry->addr = skc_local;
	entry->addr.id = 0;
	entry->addr.port = 0;
	entry->ifindex = 0;
	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
	entry->lsk = NULL;
	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
	if (ret < 0)
		kfree(entry);

	return ret;
}

#define MPTCP_PM_CMD_GRP_OFFSET       0
#define MPTCP_PM_EV_GRP_OFFSET        1

static const struct genl_multicast_group mptcp_pm_mcgrps[] = {
	[MPTCP_PM_CMD_GRP_OFFSET]	= { .name = MPTCP_PM_CMD_GRP_NAME, },
	[MPTCP_PM_EV_GRP_OFFSET]        = { .name = MPTCP_PM_EV_GRP_NAME,
					    .flags = GENL_UNS_ADMIN_PERM,
					  },
};

static const struct nla_policy
mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = {
	[MPTCP_PM_ADDR_ATTR_FAMILY]	= { .type	= NLA_U16,	},
	[MPTCP_PM_ADDR_ATTR_ID]		= { .type	= NLA_U8,	},
	[MPTCP_PM_ADDR_ATTR_ADDR4]	= { .type	= NLA_U32,	},
	[MPTCP_PM_ADDR_ATTR_ADDR6]	=
		NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
	[MPTCP_PM_ADDR_ATTR_PORT]	= { .type	= NLA_U16	},
	[MPTCP_PM_ADDR_ATTR_FLAGS]	= { .type	= NLA_U32	},
	[MPTCP_PM_ADDR_ATTR_IF_IDX]     = { .type	= NLA_S32	},
};

static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = {
	[MPTCP_PM_ATTR_ADDR]		=
					NLA_POLICY_NESTED(mptcp_pm_addr_policy),
	[MPTCP_PM_ATTR_RCV_ADD_ADDRS]	= { .type	= NLA_U32,	},
	[MPTCP_PM_ATTR_SUBFLOWS]	= { .type	= NLA_U32,	},
	[MPTCP_PM_ATTR_TOKEN]		= { .type	= NLA_U32,	},
	[MPTCP_PM_ATTR_LOC_ID]		= { .type	= NLA_U8,	},
	[MPTCP_PM_ATTR_ADDR_REMOTE]	=
					NLA_POLICY_NESTED(mptcp_pm_addr_policy),
};

void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
{
	struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk);
	struct sock *sk = (struct sock *)msk;
	unsigned int active_max_loss_cnt;
	struct net *net = sock_net(sk);
	unsigned int stale_loss_cnt;
	bool slow;

	stale_loss_cnt = mptcp_stale_loss_cnt(net);
	if (subflow->stale || !stale_loss_cnt || subflow->stale_count <= stale_loss_cnt)
		return;

	/* look for another available subflow not in loss state */
	active_max_loss_cnt = max_t(int, stale_loss_cnt - 1, 1);
	mptcp_for_each_subflow(msk, iter) {
		if (iter != subflow && mptcp_subflow_active(iter) &&
		    iter->stale_count < active_max_loss_cnt) {
			/* we have some alternatives, try to mark this subflow as idle ...*/
			slow = lock_sock_fast(ssk);
			if (!tcp_rtx_and_write_queues_empty(ssk)) {
				subflow->stale = 1;
				__mptcp_retransmit_pending_data(sk);
				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_SUBFLOWSTALE);
			}
			unlock_sock_fast(ssk, slow);

			/* always try to push the pending data regardless of re-injections:
			 * we can possibly use backup subflows now, and subflow selection
			 * is cheap under the msk socket lock
			 */
			__mptcp_push_pending(sk, 0);
			return;
		}
	}
}

static int mptcp_pm_family_to_addr(int family)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	if (family == AF_INET6)
		return MPTCP_PM_ADDR_ATTR_ADDR6;
#endif
	return MPTCP_PM_ADDR_ATTR_ADDR4;
}

static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[],
				       const struct nlattr *attr,
				       struct genl_info *info,
				       struct mptcp_addr_info *addr,
				       bool require_family)
{
	int err, addr_addr;

	if (!attr) {
		GENL_SET_ERR_MSG(info, "missing address info");
		return -EINVAL;
	}

	/* no validation needed - was already done via nested policy */
	err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr,
					  mptcp_pm_addr_policy, info->extack);
	if (err)
		return err;

	if (tb[MPTCP_PM_ADDR_ATTR_ID])
		addr->id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]);

	if (!tb[MPTCP_PM_ADDR_ATTR_FAMILY]) {
		if (!require_family)
			return err;

		NL_SET_ERR_MSG_ATTR(info->extack, attr,
				    "missing family");
		return -EINVAL;
	}

	addr->family = nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_FAMILY]);
	if (addr->family != AF_INET
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	    && addr->family != AF_INET6
#endif
	    ) {
		NL_SET_ERR_MSG_ATTR(info->extack, attr,
				    "unknown address family");
		return -EINVAL;
	}
	addr_addr = mptcp_pm_family_to_addr(addr->family);
	if (!tb[addr_addr]) {
		NL_SET_ERR_MSG_ATTR(info->extack, attr,
				    "missing address data");
		return -EINVAL;
	}

#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	if (addr->family == AF_INET6)
		addr->addr6 = nla_get_in6_addr(tb[addr_addr]);
	else
#endif
		addr->addr.s_addr = nla_get_in_addr(tb[addr_addr]);

	if (tb[MPTCP_PM_ADDR_ATTR_PORT])
		addr->port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT]));

	return err;
}

int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
			struct mptcp_addr_info *addr)
{
	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];

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

	return mptcp_pm_parse_pm_addr_attr(tb, attr, info, addr, true);
}

int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
			 bool require_family,
			 struct mptcp_pm_addr_entry *entry)
{
	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
	int err;

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

	err = mptcp_pm_parse_pm_addr_attr(tb, attr, info, &entry->addr, require_family);
	if (err)
		return err;

	if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) {
		u32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]);

		entry->ifindex = val;
	}

	if (tb[MPTCP_PM_ADDR_ATTR_FLAGS])
		entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);

	if (tb[MPTCP_PM_ADDR_ATTR_PORT])
		entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT]));

	return 0;
}

static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
{
	return pm_nl_get_pernet(genl_info_net(info));
}

static int mptcp_nl_add_subflow_or_signal_addr(struct net *net)
{
	struct mptcp_sock *msk;
	long s_slot = 0, s_num = 0;

	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
		struct sock *sk = (struct sock *)msk;

		if (!READ_ONCE(msk->fully_established) ||
		    mptcp_pm_is_userspace(msk))
			goto next;

		lock_sock(sk);
		spin_lock_bh(&msk->pm.lock);
		mptcp_pm_create_subflow_or_signal_addr(msk);
		spin_unlock_bh(&msk->pm.lock);
		release_sock(sk);

next:
		sock_put(sk);
		cond_resched();
	}

	return 0;
}

static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info)
{
	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
	struct mptcp_pm_addr_entry addr, *entry;
	int ret;

	ret = mptcp_pm_parse_entry(attr, info, true, &addr);
	if (ret < 0)
		return ret;

	if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
		GENL_SET_ERR_MSG(info, "flags must have signal when using port");
		return -EINVAL;
	}

	if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL &&
	    addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) {
		GENL_SET_ERR_MSG(info, "flags mustn't have both signal and fullmesh");
		return -EINVAL;
	}

	if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) {
		GENL_SET_ERR_MSG(info, "can't create IMPLICIT endpoint");
		return -EINVAL;
	}

	entry = kzalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT);
	if (!entry) {
		GENL_SET_ERR_MSG(info, "can't allocate addr");
		return -ENOMEM;
	}

	*entry = addr;
	if (entry->addr.port) {
		ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry);
		if (ret) {
			GENL_SET_ERR_MSG_FMT(info, "create listen socket error: %d", ret);
			goto out_free;
		}
	}
	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
	if (ret < 0) {
		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
		goto out_free;
	}

	mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk));
	return 0;

out_free:
	__mptcp_pm_release_addr_entry(entry);
	return ret;
}

int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
					 u8 *flags, int *ifindex)
{
	struct mptcp_pm_addr_entry *entry;
	struct sock *sk = (struct sock *)msk;
	struct net *net = sock_net(sk);

	*flags = 0;
	*ifindex = 0;

	if (id) {
		if (mptcp_pm_is_userspace(msk))
			return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk,
									      id,
									      flags,
									      ifindex);

		rcu_read_lock();
		entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
		if (entry) {
			*flags = entry->flags;
			*ifindex = entry->ifindex;
		}
		rcu_read_unlock();
	}

	return 0;
}

static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
				      const struct mptcp_addr_info *addr)
{
	struct mptcp_pm_add_entry *entry;

	entry = mptcp_pm_del_add_timer(msk, addr, false);
	if (entry) {
		list_del(&entry->list);
		kfree(entry);
		return true;
	}

	return false;
}

static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
				      const struct mptcp_addr_info *addr,
				      bool force)
{
	struct mptcp_rm_list list = { .nr = 0 };
	bool ret;

	list.ids[list.nr++] = addr->id;

	ret = remove_anno_list_by_saddr(msk, addr);
	if (ret || force) {
		spin_lock_bh(&msk->pm.lock);
		mptcp_pm_remove_addr(msk, &list);
		spin_unlock_bh(&msk->pm.lock);
	}
	return ret;
}

static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
						   const struct mptcp_pm_addr_entry *entry)
{
	const struct mptcp_addr_info *addr = &entry->addr;
	struct mptcp_rm_list list = { .nr = 0 };
	long s_slot = 0, s_num = 0;
	struct mptcp_sock *msk;

	pr_debug("remove_id=%d", addr->id);

	list.ids[list.nr++] = addr->id;

	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
		struct sock *sk = (struct sock *)msk;
		bool remove_subflow;

		if (mptcp_pm_is_userspace(msk))
			goto next;

		if (list_empty(&msk->conn_list)) {
			mptcp_pm_remove_anno_addr(msk, addr, false);
			goto next;
		}

		lock_sock(sk);
		remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
					  !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
		if (remove_subflow)
			mptcp_pm_remove_subflow(msk, &list);
		release_sock(sk);

next:
		sock_put(sk);
		cond_resched();
	}

	return 0;
}

static int mptcp_nl_remove_id_zero_address(struct net *net,
					   struct mptcp_addr_info *addr)
{
	struct mptcp_rm_list list = { .nr = 0 };
	long s_slot = 0, s_num = 0;
	struct mptcp_sock *msk;

	list.ids[list.nr++] = 0;

	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
		struct sock *sk = (struct sock *)msk;
		struct mptcp_addr_info msk_local;

		if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
			goto next;

		local_address((struct sock_common *)msk, &msk_local);
		if (!mptcp_addresses_equal(&msk_local, addr, addr->port))
			goto next;

		lock_sock(sk);
		spin_lock_bh(&msk->pm.lock);
		mptcp_pm_remove_addr(msk, &list);
		mptcp_pm_nl_rm_subflow_received(msk, &list);
		spin_unlock_bh(&msk->pm.lock);
		release_sock(sk);

next:
		sock_put(sk);
		cond_resched();
	}

	return 0;
}

static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
{
	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
	struct mptcp_pm_addr_entry addr, *entry;
	unsigned int addr_max;
	int ret;

	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
	if (ret < 0)
		return ret;

	/* the zero id address is special: the first address used by the msk
	 * always gets such an id, so different subflows can have different zero
	 * id addresses. Additionally zero id is not accounted for in id_bitmap.
	 * Let's use an 'mptcp_rm_list' instead of the common remove code.
	 */
	if (addr.addr.id == 0)
		return mptcp_nl_remove_id_zero_address(sock_net(skb->sk), &addr.addr);

	spin_lock_bh(&pernet->lock);
	entry = __lookup_addr_by_id(pernet, addr.addr.id);
	if (!entry) {
		GENL_SET_ERR_MSG(info, "address not found");
		spin_unlock_bh(&pernet->lock);
		return -EINVAL;
	}
	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
		addr_max = pernet->add_addr_signal_max;
		WRITE_ONCE(pernet->add_addr_signal_max, addr_max - 1);
	}
	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
		addr_max = pernet->local_addr_max;
		WRITE_ONCE(pernet->local_addr_max, addr_max - 1);
	}

	pernet->addrs--;
	list_del_rcu(&entry->list);
	__clear_bit(entry->addr.id, pernet->id_bitmap);
	spin_unlock_bh(&pernet->lock);

	mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry);
	synchronize_rcu();
	__mptcp_pm_release_addr_entry(entry);

	return ret;
}

void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
					struct list_head *rm_list)
{
	struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 };
	struct mptcp_pm_addr_entry *entry;

	list_for_each_entry(entry, rm_list, list) {
		if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
		    slist.nr < MPTCP_RM_IDS_MAX)
			slist.ids[slist.nr++] = entry->addr.id;

		if (remove_anno_list_by_saddr(msk, &entry->addr) &&
		    alist.nr < MPTCP_RM_IDS_MAX)
			alist.ids[alist.nr++] = entry->addr.id;
	}

	if (alist.nr) {
		spin_lock_bh(&msk->pm.lock);
		mptcp_pm_remove_addr(msk, &alist);
		spin_unlock_bh(&msk->pm.lock);
	}
	if (slist.nr)
		mptcp_pm_remove_subflow(msk, &slist);
}

static void mptcp_nl_remove_addrs_list(struct net *net,
				       struct list_head *rm_list)
{
	long s_slot = 0, s_num = 0;
	struct mptcp_sock *msk;

	if (list_empty(rm_list))
		return;

	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
		struct sock *sk = (struct sock *)msk;

		if (!mptcp_pm_is_userspace(msk)) {
			lock_sock(sk);
			mptcp_pm_remove_addrs_and_subflows(msk, rm_list);
			release_sock(sk);
		}

		sock_put(sk);
		cond_resched();
	}
}

/* caller must ensure the RCU grace period is already elapsed */
static void __flush_addrs(struct list_head *list)
{
	while (!list_empty(list)) {
		struct mptcp_pm_addr_entry *cur;

		cur = list_entry(list->next,
				 struct mptcp_pm_addr_entry, list);
		list_del_rcu(&cur->list);
		__mptcp_pm_release_addr_entry(cur);
	}
}

static void __reset_counters(struct pm_nl_pernet *pernet)
{
	WRITE_ONCE(pernet->add_addr_signal_max, 0);
	WRITE_ONCE(pernet->add_addr_accept_max, 0);
	WRITE_ONCE(pernet->local_addr_max, 0);
	pernet->addrs = 0;
}

static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info)
{
	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
	LIST_HEAD(free_list);

	spin_lock_bh(&pernet->lock);
	list_splice_init(&pernet->local_addr_list, &free_list);
	__reset_counters(pernet);
	pernet->next_id = 1;
	bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
	spin_unlock_bh(&pernet->lock);
	mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list);
	synchronize_rcu();
	__flush_addrs(&free_list);
	return 0;
}

static int mptcp_nl_fill_addr(struct sk_buff *skb,
			      struct mptcp_pm_addr_entry *entry)
{
	struct mptcp_addr_info *addr = &entry->addr;
	struct nlattr *attr;

	attr = nla_nest_start(skb, MPTCP_PM_ATTR_ADDR);
	if (!attr)
		return -EMSGSIZE;

	if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_FAMILY, addr->family))
		goto nla_put_failure;
	if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_PORT, ntohs(addr->port)))
		goto nla_put_failure;
	if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id))
		goto nla_put_failure;
	if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->flags))
		goto nla_put_failure;
	if (entry->ifindex &&
	    nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex))
		goto nla_put_failure;

	if (addr->family == AF_INET &&
	    nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4,
			    addr->addr.s_addr))
		goto nla_put_failure;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	else if (addr->family == AF_INET6 &&
		 nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6))
		goto nla_put_failure;
#endif
	nla_nest_end(skb, attr);
	return 0;

nla_put_failure:
	nla_nest_cancel(skb, attr);
	return -EMSGSIZE;
}

static int mptcp_nl_cmd_get_addr(struct sk_buff *skb, struct genl_info *info)
{
	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
	struct mptcp_pm_addr_entry addr, *entry;
	struct sk_buff *msg;
	void *reply;
	int ret;

	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
	if (ret < 0)
		return ret;

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
				  info->genlhdr->cmd);
	if (!reply) {
		GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
		ret = -EMSGSIZE;
		goto fail;
	}

	spin_lock_bh(&pernet->lock);
	entry = __lookup_addr_by_id(pernet, addr.addr.id);
	if (!entry) {
		GENL_SET_ERR_MSG(info, "address not found");
		ret = -EINVAL;
		goto unlock_fail;
	}

	ret = mptcp_nl_fill_addr(msg, entry);
	if (ret)
		goto unlock_fail;

	genlmsg_end(msg, reply);
	ret = genlmsg_reply(msg, info);
	spin_unlock_bh(&pernet->lock);
	return ret;

unlock_fail:
	spin_unlock_bh(&pernet->lock);

fail:
	nlmsg_free(msg);
	return ret;
}

static int mptcp_nl_cmd_dump_addrs(struct sk_buff *msg,
				   struct netlink_callback *cb)
{
	struct net *net = sock_net(msg->sk);
	struct mptcp_pm_addr_entry *entry;
	struct pm_nl_pernet *pernet;
	int id = cb->args[0];
	void *hdr;
	int i;

	pernet = pm_nl_get_pernet(net);

	spin_lock_bh(&pernet->lock);
	for (i = id; i < MPTCP_PM_MAX_ADDR_ID + 1; i++) {
		if (test_bit(i, pernet->id_bitmap)) {
			entry = __lookup_addr_by_id(pernet, i);
			if (!entry)
				break;

			if (entry->addr.id <= id)
				continue;

			hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
					  cb->nlh->nlmsg_seq, &mptcp_genl_family,
					  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
			if (!hdr)
				break;

			if (mptcp_nl_fill_addr(msg, entry) < 0) {
				genlmsg_cancel(msg, hdr);
				break;
			}

			id = entry->addr.id;
			genlmsg_end(msg, hdr);
		}
	}
	spin_unlock_bh(&pernet->lock);

	cb->args[0] = id;
	return msg->len;
}

static int parse_limit(struct genl_info *info, int id, unsigned int *limit)
{
	struct nlattr *attr = info->attrs[id];

	if (!attr)
		return 0;

	*limit = nla_get_u32(attr);
	if (*limit > MPTCP_PM_ADDR_MAX) {
		GENL_SET_ERR_MSG(info, "limit greater than maximum");
		return -EINVAL;
	}
	return 0;
}

static int
mptcp_nl_cmd_set_limits(struct sk_buff *skb, struct genl_info *info)
{
	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
	unsigned int rcv_addrs, subflows;
	int ret;

	spin_lock_bh(&pernet->lock);
	rcv_addrs = pernet->add_addr_accept_max;
	ret = parse_limit(info, MPTCP_PM_ATTR_RCV_ADD_ADDRS, &rcv_addrs);
	if (ret)
		goto unlock;

	subflows = pernet->subflows_max;
	ret = parse_limit(info, MPTCP_PM_ATTR_SUBFLOWS, &subflows);
	if (ret)
		goto unlock;

	WRITE_ONCE(pernet->add_addr_accept_max, rcv_addrs);
	WRITE_ONCE(pernet->subflows_max, subflows);

unlock:
	spin_unlock_bh(&pernet->lock);
	return ret;
}

static int
mptcp_nl_cmd_get_limits(struct sk_buff *skb, struct genl_info *info)
{
	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
	struct sk_buff *msg;
	void *reply;

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
				  MPTCP_PM_CMD_GET_LIMITS);
	if (!reply)
		goto fail;

	if (nla_put_u32(msg, MPTCP_PM_ATTR_RCV_ADD_ADDRS,
			READ_ONCE(pernet->add_addr_accept_max)))
		goto fail;

	if (nla_put_u32(msg, MPTCP_PM_ATTR_SUBFLOWS,
			READ_ONCE(pernet->subflows_max)))
		goto fail;

	genlmsg_end(msg, reply);
	return genlmsg_reply(msg, info);

fail:
	GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
	nlmsg_free(msg);
	return -EMSGSIZE;
}

static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
				 struct mptcp_addr_info *addr)
{
	struct mptcp_rm_list list = { .nr = 0 };

	list.ids[list.nr++] = addr->id;

	spin_lock_bh(&msk->pm.lock);
	mptcp_pm_nl_rm_subflow_received(msk, &list);
	mptcp_pm_create_subflow_or_signal_addr(msk);
	spin_unlock_bh(&msk->pm.lock);
}

static int mptcp_nl_set_flags(struct net *net,
			      struct mptcp_addr_info *addr,
			      u8 bkup, u8 changed)
{
	long s_slot = 0, s_num = 0;
	struct mptcp_sock *msk;
	int ret = -EINVAL;

	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
		struct sock *sk = (struct sock *)msk;

		if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
			goto next;

		lock_sock(sk);
		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
			ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
		if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)
			mptcp_pm_nl_fullmesh(msk, addr);
		release_sock(sk);

next:
		sock_put(sk);
		cond_resched();
	}

	return ret;
}

static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
{
	struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry;
	struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, };
	struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
	u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
			   MPTCP_PM_ADDR_FLAG_FULLMESH;
	struct net *net = sock_net(skb->sk);
	u8 bkup = 0, lookup_by_id = 0;
	int ret;

	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
	if (ret < 0)
		return ret;

	if (attr_rem) {
		ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote);
		if (ret < 0)
			return ret;
	}

	if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
		bkup = 1;
	if (addr.addr.family == AF_UNSPEC) {
		lookup_by_id = 1;
		if (!addr.addr.id)
			return -EOPNOTSUPP;
	}

	if (token)
		return mptcp_userspace_pm_set_flags(sock_net(skb->sk),
						    token, &addr, &remote, bkup);

	spin_lock_bh(&pernet->lock);
	entry = __lookup_addr(pernet, &addr.addr, lookup_by_id);
	if (!entry) {
		spin_unlock_bh(&pernet->lock);
		return -EINVAL;
	}
	if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
	    (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
		spin_unlock_bh(&pernet->lock);
		return -EINVAL;
	}

	changed = (addr.flags ^ entry->flags) & mask;
	entry->flags = (entry->flags & ~mask) | (addr.flags & mask);
	addr = *entry;
	spin_unlock_bh(&pernet->lock);

	mptcp_nl_set_flags(net, &addr.addr, bkup, changed);
	return 0;
}

static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp)
{
	genlmsg_multicast_netns(&mptcp_genl_family, net,
				nlskb, 0, MPTCP_PM_EV_GRP_OFFSET, gfp);
}

bool mptcp_userspace_pm_active(const struct mptcp_sock *msk)
{
	return genl_has_listeners(&mptcp_genl_family,
				  sock_net((const struct sock *)msk),
				  MPTCP_PM_EV_GRP_OFFSET);
}

static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
{
	const struct inet_sock *issk = inet_sk(ssk);
	const struct mptcp_subflow_context *sf;

	if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family))
		return -EMSGSIZE;

	switch (ssk->sk_family) {
	case AF_INET:
		if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr))
			return -EMSGSIZE;
		if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, issk->inet_daddr))
			return -EMSGSIZE;
		break;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	case AF_INET6: {
		const struct ipv6_pinfo *np = inet6_sk(ssk);

		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr))
			return -EMSGSIZE;
		if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr))
			return -EMSGSIZE;
		break;
	}
#endif
	default:
		WARN_ON_ONCE(1);
		return -EMSGSIZE;
	}

	if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport))
		return -EMSGSIZE;
	if (nla_put_be16(skb, MPTCP_ATTR_DPORT, issk->inet_dport))
		return -EMSGSIZE;

	sf = mptcp_subflow_ctx(ssk);
	if (WARN_ON_ONCE(!sf))
		return -EINVAL;

	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id))
		return -EMSGSIZE;

	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id))
		return -EMSGSIZE;

	return 0;
}

static int mptcp_event_put_token_and_ssk(struct sk_buff *skb,
					 const struct mptcp_sock *msk,
					 const struct sock *ssk)
{
	const struct sock *sk = (const struct sock *)msk;
	const struct mptcp_subflow_context *sf;
	u8 sk_err;

	if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token))
		return -EMSGSIZE;

	if (mptcp_event_add_subflow(skb, ssk))
		return -EMSGSIZE;

	sf = mptcp_subflow_ctx(ssk);
	if (WARN_ON_ONCE(!sf))
		return -EINVAL;

	if (nla_put_u8(skb, MPTCP_ATTR_BACKUP, sf->backup))
		return -EMSGSIZE;

	if (ssk->sk_bound_dev_if &&
	    nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if))
		return -EMSGSIZE;

	sk_err = ssk->sk_err;
	if (sk_err && sk->sk_state == TCP_ESTABLISHED &&
	    nla_put_u8(skb, MPTCP_ATTR_ERROR, sk_err))
		return -EMSGSIZE;

	return 0;
}

static int mptcp_event_sub_established(struct sk_buff *skb,
				       const struct mptcp_sock *msk,
				       const struct sock *ssk)
{
	return mptcp_event_put_token_and_ssk(skb, msk, ssk);
}

static int mptcp_event_sub_closed(struct sk_buff *skb,
				  const struct mptcp_sock *msk,
				  const struct sock *ssk)
{
	const struct mptcp_subflow_context *sf;

	if (mptcp_event_put_token_and_ssk(skb, msk, ssk))
		return -EMSGSIZE;

	sf = mptcp_subflow_ctx(ssk);
	if (!sf->reset_seen)
		return 0;

	if (nla_put_u32(skb, MPTCP_ATTR_RESET_REASON, sf->reset_reason))
		return -EMSGSIZE;

	if (nla_put_u32(skb, MPTCP_ATTR_RESET_FLAGS, sf->reset_transient))
		return -EMSGSIZE;

	return 0;
}

static int mptcp_event_created(struct sk_buff *skb,
			       const struct mptcp_sock *msk,
			       const struct sock *ssk)
{
	int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token);

	if (err)
		return err;

	if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side)))
		return -EMSGSIZE;

	return mptcp_event_add_subflow(skb, ssk);
}

void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id)
{
	struct net *net = sock_net((const struct sock *)msk);
	struct nlmsghdr *nlh;
	struct sk_buff *skb;

	if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET))
		return;

	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
	if (!skb)
		return;

	nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_REMOVED);
	if (!nlh)
		goto nla_put_failure;

	if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token))
		goto nla_put_failure;

	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, id))
		goto nla_put_failure;

	genlmsg_end(skb, nlh);
	mptcp_nl_mcast_send(net, skb, GFP_ATOMIC);
	return;

nla_put_failure:
	kfree_skb(skb);
}

void mptcp_event_addr_announced(const struct sock *ssk,
				const struct mptcp_addr_info *info)
{
	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
	struct net *net = sock_net(ssk);
	struct nlmsghdr *nlh;
	struct sk_buff *skb;

	if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET))
		return;

	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
	if (!skb)
		return;

	nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0,
			  MPTCP_EVENT_ANNOUNCED);
	if (!nlh)
		goto nla_put_failure;

	if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token))
		goto nla_put_failure;

	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id))
		goto nla_put_failure;

	if (nla_put_be16(skb, MPTCP_ATTR_DPORT,
			 info->port == 0 ?
			 inet_sk(ssk)->inet_dport :
			 info->port))
		goto nla_put_failure;

	switch (info->family) {
	case AF_INET:
		if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, info->addr.s_addr))
			goto nla_put_failure;
		break;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
	case AF_INET6:
		if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &info->addr6))
			goto nla_put_failure;
		break;
#endif
	default:
		WARN_ON_ONCE(1);
		goto nla_put_failure;
	}

	genlmsg_end(skb, nlh);
	mptcp_nl_mcast_send(net, skb, GFP_ATOMIC);
	return;

nla_put_failure:
	kfree_skb(skb);
}

void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk,
		 const struct sock *ssk, gfp_t gfp)
{
	struct net *net = sock_net((const struct sock *)msk);
	struct nlmsghdr *nlh;
	struct sk_buff *skb;

	if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET))
		return;

	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
	if (!skb)
		return;

	nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, type);
	if (!nlh)
		goto nla_put_failure;

	switch (type) {
	case MPTCP_EVENT_UNSPEC:
		WARN_ON_ONCE(1);
		break;
	case MPTCP_EVENT_CREATED:
	case MPTCP_EVENT_ESTABLISHED:
		if (mptcp_event_created(skb, msk, ssk) < 0)
			goto nla_put_failure;
		break;
	case MPTCP_EVENT_CLOSED:
		if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token) < 0)
			goto nla_put_failure;
		break;
	case MPTCP_EVENT_ANNOUNCED:
	case MPTCP_EVENT_REMOVED:
		/* call mptcp_event_addr_announced()/removed instead */
		WARN_ON_ONCE(1);
		break;
	case MPTCP_EVENT_SUB_ESTABLISHED:
	case MPTCP_EVENT_SUB_PRIORITY:
		if (mptcp_event_sub_established(skb, msk, ssk) < 0)
			goto nla_put_failure;
		break;
	case MPTCP_EVENT_SUB_CLOSED:
		if (mptcp_event_sub_closed(skb, msk, ssk) < 0)
			goto nla_put_failure;
		break;
	}

	genlmsg_end(skb, nlh);
	mptcp_nl_mcast_send(net, skb, gfp);
	return;

nla_put_failure:
	kfree_skb(skb);
}

static const struct genl_small_ops mptcp_pm_ops[] = {
	{
		.cmd    = MPTCP_PM_CMD_ADD_ADDR,
		.doit   = mptcp_nl_cmd_add_addr,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
	{
		.cmd    = MPTCP_PM_CMD_DEL_ADDR,
		.doit   = mptcp_nl_cmd_del_addr,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
	{
		.cmd    = MPTCP_PM_CMD_FLUSH_ADDRS,
		.doit   = mptcp_nl_cmd_flush_addrs,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
	{
		.cmd    = MPTCP_PM_CMD_GET_ADDR,
		.doit   = mptcp_nl_cmd_get_addr,
		.dumpit   = mptcp_nl_cmd_dump_addrs,
	},
	{
		.cmd    = MPTCP_PM_CMD_SET_LIMITS,
		.doit   = mptcp_nl_cmd_set_limits,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
	{
		.cmd    = MPTCP_PM_CMD_GET_LIMITS,
		.doit   = mptcp_nl_cmd_get_limits,
	},
	{
		.cmd    = MPTCP_PM_CMD_SET_FLAGS,
		.doit   = mptcp_nl_cmd_set_flags,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
	{
		.cmd    = MPTCP_PM_CMD_ANNOUNCE,
		.doit   = mptcp_nl_cmd_announce,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
	{
		.cmd    = MPTCP_PM_CMD_REMOVE,
		.doit   = mptcp_nl_cmd_remove,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
	{
		.cmd    = MPTCP_PM_CMD_SUBFLOW_CREATE,
		.doit   = mptcp_nl_cmd_sf_create,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
	{
		.cmd    = MPTCP_PM_CMD_SUBFLOW_DESTROY,
		.doit   = mptcp_nl_cmd_sf_destroy,
		.flags  = GENL_UNS_ADMIN_PERM,
	},
};

static struct genl_family mptcp_genl_family __ro_after_init = {
	.name		= MPTCP_PM_NAME,
	.version	= MPTCP_PM_VER,
	.maxattr	= MPTCP_PM_ATTR_MAX,
	.policy		= mptcp_pm_policy,
	.netnsok	= true,
	.module		= THIS_MODULE,
	.small_ops	= mptcp_pm_ops,
	.n_small_ops	= ARRAY_SIZE(mptcp_pm_ops),
	.resv_start_op	= MPTCP_PM_CMD_SUBFLOW_DESTROY + 1,
	.mcgrps		= mptcp_pm_mcgrps,
	.n_mcgrps	= ARRAY_SIZE(mptcp_pm_mcgrps),
};

static int __net_init pm_nl_init_net(struct net *net)
{
	struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);

	INIT_LIST_HEAD_RCU(&pernet->local_addr_list);

	/* Cit. 2 subflows ought to be enough for anybody. */
	pernet->subflows_max = 2;
	pernet->next_id = 1;
	pernet->stale_loss_cnt = 4;
	spin_lock_init(&pernet->lock);

	/* No need to initialize other pernet fields, the struct is zeroed at
	 * allocation time.
	 */

	return 0;
}

static void __net_exit pm_nl_exit_net(struct list_head *net_list)
{
	struct net *net;

	list_for_each_entry(net, net_list, exit_list) {
		struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);

		/* net is removed from namespace list, can't race with
		 * other modifiers, also netns core already waited for a
		 * RCU grace period.
		 */
		__flush_addrs(&pernet->local_addr_list);
	}
}

static struct pernet_operations mptcp_pm_pernet_ops = {
	.init = pm_nl_init_net,
	.exit_batch = pm_nl_exit_net,
	.id = &pm_nl_pernet_id,
	.size = sizeof(struct pm_nl_pernet),
};

void __init mptcp_pm_nl_init(void)
{
	if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0)
		panic("Failed to register MPTCP PM pernet subsystem.\n");

	if (genl_register_family(&mptcp_genl_family))
		panic("Failed to register MPTCP PM netlink family\n");
}