summaryrefslogtreecommitdiff
path: root/net/kcm/kcmsock.c
blob: d75d775e9462a8e0083ca3b60611dff8da3840d6 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel Connection Multiplexor
 *
 * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
 */

#include <linux/bpf.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/file.h>
#include <linux/filter.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <linux/poll.h>
#include <linux/rculist.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
#include <linux/uaccess.h>
#include <linux/workqueue.h>
#include <linux/syscalls.h>
#include <linux/sched/signal.h>

#include <net/kcm.h>
#include <net/netns/generic.h>
#include <net/sock.h>
#include <uapi/linux/kcm.h>
#include <trace/events/sock.h>

unsigned int kcm_net_id;

static struct kmem_cache *kcm_psockp __read_mostly;
static struct kmem_cache *kcm_muxp __read_mostly;
static struct workqueue_struct *kcm_wq;

static inline struct kcm_sock *kcm_sk(const struct sock *sk)
{
	return (struct kcm_sock *)sk;
}

static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb)
{
	return (struct kcm_tx_msg *)skb->cb;
}

static void report_csk_error(struct sock *csk, int err)
{
	csk->sk_err = EPIPE;
	sk_error_report(csk);
}

static void kcm_abort_tx_psock(struct kcm_psock *psock, int err,
			       bool wakeup_kcm)
{
	struct sock *csk = psock->sk;
	struct kcm_mux *mux = psock->mux;

	/* Unrecoverable error in transmit */

	spin_lock_bh(&mux->lock);

	if (psock->tx_stopped) {
		spin_unlock_bh(&mux->lock);
		return;
	}

	psock->tx_stopped = 1;
	KCM_STATS_INCR(psock->stats.tx_aborts);

	if (!psock->tx_kcm) {
		/* Take off psocks_avail list */
		list_del(&psock->psock_avail_list);
	} else if (wakeup_kcm) {
		/* In this case psock is being aborted while outside of
		 * write_msgs and psock is reserved. Schedule tx_work
		 * to handle the failure there. Need to commit tx_stopped
		 * before queuing work.
		 */
		smp_mb();

		queue_work(kcm_wq, &psock->tx_kcm->tx_work);
	}

	spin_unlock_bh(&mux->lock);

	/* Report error on lower socket */
	report_csk_error(csk, err);
}

/* RX mux lock held. */
static void kcm_update_rx_mux_stats(struct kcm_mux *mux,
				    struct kcm_psock *psock)
{
	STRP_STATS_ADD(mux->stats.rx_bytes,
		       psock->strp.stats.bytes -
		       psock->saved_rx_bytes);
	mux->stats.rx_msgs +=
		psock->strp.stats.msgs - psock->saved_rx_msgs;
	psock->saved_rx_msgs = psock->strp.stats.msgs;
	psock->saved_rx_bytes = psock->strp.stats.bytes;
}

static void kcm_update_tx_mux_stats(struct kcm_mux *mux,
				    struct kcm_psock *psock)
{
	KCM_STATS_ADD(mux->stats.tx_bytes,
		      psock->stats.tx_bytes - psock->saved_tx_bytes);
	mux->stats.tx_msgs +=
		psock->stats.tx_msgs - psock->saved_tx_msgs;
	psock->saved_tx_msgs = psock->stats.tx_msgs;
	psock->saved_tx_bytes = psock->stats.tx_bytes;
}

static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);

/* KCM is ready to receive messages on its queue-- either the KCM is new or
 * has become unblocked after being blocked on full socket buffer. Queue any
 * pending ready messages on a psock. RX mux lock held.
 */
static void kcm_rcv_ready(struct kcm_sock *kcm)
{
	struct kcm_mux *mux = kcm->mux;
	struct kcm_psock *psock;
	struct sk_buff *skb;

	if (unlikely(kcm->rx_wait || kcm->rx_psock || kcm->rx_disabled))
		return;

	while (unlikely((skb = __skb_dequeue(&mux->rx_hold_queue)))) {
		if (kcm_queue_rcv_skb(&kcm->sk, skb)) {
			/* Assuming buffer limit has been reached */
			skb_queue_head(&mux->rx_hold_queue, skb);
			WARN_ON(!sk_rmem_alloc_get(&kcm->sk));
			return;
		}
	}

	while (!list_empty(&mux->psocks_ready)) {
		psock = list_first_entry(&mux->psocks_ready, struct kcm_psock,
					 psock_ready_list);

		if (kcm_queue_rcv_skb(&kcm->sk, psock->ready_rx_msg)) {
			/* Assuming buffer limit has been reached */
			WARN_ON(!sk_rmem_alloc_get(&kcm->sk));
			return;
		}

		/* Consumed the ready message on the psock. Schedule rx_work to
		 * get more messages.
		 */
		list_del(&psock->psock_ready_list);
		psock->ready_rx_msg = NULL;
		/* Commit clearing of ready_rx_msg for queuing work */
		smp_mb();

		strp_unpause(&psock->strp);
		strp_check_rcv(&psock->strp);
	}

	/* Buffer limit is okay now, add to ready list */
	list_add_tail(&kcm->wait_rx_list,
		      &kcm->mux->kcm_rx_waiters);
	/* paired with lockless reads in kcm_rfree() */
	WRITE_ONCE(kcm->rx_wait, true);
}

static void kcm_rfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	struct kcm_sock *kcm = kcm_sk(sk);
	struct kcm_mux *mux = kcm->mux;
	unsigned int len = skb->truesize;

	sk_mem_uncharge(sk, len);
	atomic_sub(len, &sk->sk_rmem_alloc);

	/* For reading rx_wait and rx_psock without holding lock */
	smp_mb__after_atomic();

	if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) &&
	    sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) {
		spin_lock_bh(&mux->rx_lock);
		kcm_rcv_ready(kcm);
		spin_unlock_bh(&mux->rx_lock);
	}
}

static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	struct sk_buff_head *list = &sk->sk_receive_queue;

	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
		return -ENOMEM;

	if (!sk_rmem_schedule(sk, skb, skb->truesize))
		return -ENOBUFS;

	skb->dev = NULL;

	skb_orphan(skb);
	skb->sk = sk;
	skb->destructor = kcm_rfree;
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
	sk_mem_charge(sk, skb->truesize);

	skb_queue_tail(list, skb);

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_data_ready(sk);

	return 0;
}

/* Requeue received messages for a kcm socket to other kcm sockets. This is
 * called with a kcm socket is receive disabled.
 * RX mux lock held.
 */
static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head)
{
	struct sk_buff *skb;
	struct kcm_sock *kcm;

	while ((skb = skb_dequeue(head))) {
		/* Reset destructor to avoid calling kcm_rcv_ready */
		skb->destructor = sock_rfree;
		skb_orphan(skb);
try_again:
		if (list_empty(&mux->kcm_rx_waiters)) {
			skb_queue_tail(&mux->rx_hold_queue, skb);
			continue;
		}

		kcm = list_first_entry(&mux->kcm_rx_waiters,
				       struct kcm_sock, wait_rx_list);

		if (kcm_queue_rcv_skb(&kcm->sk, skb)) {
			/* Should mean socket buffer full */
			list_del(&kcm->wait_rx_list);
			/* paired with lockless reads in kcm_rfree() */
			WRITE_ONCE(kcm->rx_wait, false);

			/* Commit rx_wait to read in kcm_free */
			smp_wmb();

			goto try_again;
		}
	}
}

/* Lower sock lock held */
static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock,
				       struct sk_buff *head)
{
	struct kcm_mux *mux = psock->mux;
	struct kcm_sock *kcm;

	WARN_ON(psock->ready_rx_msg);

	if (psock->rx_kcm)
		return psock->rx_kcm;

	spin_lock_bh(&mux->rx_lock);

	if (psock->rx_kcm) {
		spin_unlock_bh(&mux->rx_lock);
		return psock->rx_kcm;
	}

	kcm_update_rx_mux_stats(mux, psock);

	if (list_empty(&mux->kcm_rx_waiters)) {
		psock->ready_rx_msg = head;
		strp_pause(&psock->strp);
		list_add_tail(&psock->psock_ready_list,
			      &mux->psocks_ready);
		spin_unlock_bh(&mux->rx_lock);
		return NULL;
	}

	kcm = list_first_entry(&mux->kcm_rx_waiters,
			       struct kcm_sock, wait_rx_list);
	list_del(&kcm->wait_rx_list);
	/* paired with lockless reads in kcm_rfree() */
	WRITE_ONCE(kcm->rx_wait, false);

	psock->rx_kcm = kcm;
	/* paired with lockless reads in kcm_rfree() */
	WRITE_ONCE(kcm->rx_psock, psock);

	spin_unlock_bh(&mux->rx_lock);

	return kcm;
}

static void kcm_done(struct kcm_sock *kcm);

static void kcm_done_work(struct work_struct *w)
{
	kcm_done(container_of(w, struct kcm_sock, done_work));
}

/* Lower sock held */
static void unreserve_rx_kcm(struct kcm_psock *psock,
			     bool rcv_ready)
{
	struct kcm_sock *kcm = psock->rx_kcm;
	struct kcm_mux *mux = psock->mux;

	if (!kcm)
		return;

	spin_lock_bh(&mux->rx_lock);

	psock->rx_kcm = NULL;
	/* paired with lockless reads in kcm_rfree() */
	WRITE_ONCE(kcm->rx_psock, NULL);

	/* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with
	 * kcm_rfree
	 */
	smp_mb();

	if (unlikely(kcm->done)) {
		spin_unlock_bh(&mux->rx_lock);

		/* Need to run kcm_done in a task since we need to qcquire
		 * callback locks which may already be held here.
		 */
		INIT_WORK(&kcm->done_work, kcm_done_work);
		schedule_work(&kcm->done_work);
		return;
	}

	if (unlikely(kcm->rx_disabled)) {
		requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue);
	} else if (rcv_ready || unlikely(!sk_rmem_alloc_get(&kcm->sk))) {
		/* Check for degenerative race with rx_wait that all
		 * data was dequeued (accounted for in kcm_rfree).
		 */
		kcm_rcv_ready(kcm);
	}
	spin_unlock_bh(&mux->rx_lock);
}

/* Lower sock lock held */
static void psock_data_ready(struct sock *sk)
{
	struct kcm_psock *psock;

	trace_sk_data_ready(sk);

	read_lock_bh(&sk->sk_callback_lock);

	psock = (struct kcm_psock *)sk->sk_user_data;
	if (likely(psock))
		strp_data_ready(&psock->strp);

	read_unlock_bh(&sk->sk_callback_lock);
}

/* Called with lower sock held */
static void kcm_rcv_strparser(struct strparser *strp, struct sk_buff *skb)
{
	struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp);
	struct kcm_sock *kcm;

try_queue:
	kcm = reserve_rx_kcm(psock, skb);
	if (!kcm) {
		 /* Unable to reserve a KCM, message is held in psock and strp
		  * is paused.
		  */
		return;
	}

	if (kcm_queue_rcv_skb(&kcm->sk, skb)) {
		/* Should mean socket buffer full */
		unreserve_rx_kcm(psock, false);
		goto try_queue;
	}
}

static int kcm_parse_func_strparser(struct strparser *strp, struct sk_buff *skb)
{
	struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp);
	struct bpf_prog *prog = psock->bpf_prog;
	int res;

	res = bpf_prog_run_pin_on_cpu(prog, skb);
	return res;
}

static int kcm_read_sock_done(struct strparser *strp, int err)
{
	struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp);

	unreserve_rx_kcm(psock, true);

	return err;
}

static void psock_state_change(struct sock *sk)
{
	/* TCP only does a EPOLLIN for a half close. Do a EPOLLHUP here
	 * since application will normally not poll with EPOLLIN
	 * on the TCP sockets.
	 */

	report_csk_error(sk, EPIPE);
}

static void psock_write_space(struct sock *sk)
{
	struct kcm_psock *psock;
	struct kcm_mux *mux;
	struct kcm_sock *kcm;

	read_lock_bh(&sk->sk_callback_lock);

	psock = (struct kcm_psock *)sk->sk_user_data;
	if (unlikely(!psock))
		goto out;
	mux = psock->mux;

	spin_lock_bh(&mux->lock);

	/* Check if the socket is reserved so someone is waiting for sending. */
	kcm = psock->tx_kcm;
	if (kcm && !unlikely(kcm->tx_stopped))
		queue_work(kcm_wq, &kcm->tx_work);

	spin_unlock_bh(&mux->lock);
out:
	read_unlock_bh(&sk->sk_callback_lock);
}

static void unreserve_psock(struct kcm_sock *kcm);

/* kcm sock is locked. */
static struct kcm_psock *reserve_psock(struct kcm_sock *kcm)
{
	struct kcm_mux *mux = kcm->mux;
	struct kcm_psock *psock;

	psock = kcm->tx_psock;

	smp_rmb(); /* Must read tx_psock before tx_wait */

	if (psock) {
		WARN_ON(kcm->tx_wait);
		if (unlikely(psock->tx_stopped))
			unreserve_psock(kcm);
		else
			return kcm->tx_psock;
	}

	spin_lock_bh(&mux->lock);

	/* Check again under lock to see if psock was reserved for this
	 * psock via psock_unreserve.
	 */
	psock = kcm->tx_psock;
	if (unlikely(psock)) {
		WARN_ON(kcm->tx_wait);
		spin_unlock_bh(&mux->lock);
		return kcm->tx_psock;
	}

	if (!list_empty(&mux->psocks_avail)) {
		psock = list_first_entry(&mux->psocks_avail,
					 struct kcm_psock,
					 psock_avail_list);
		list_del(&psock->psock_avail_list);
		if (kcm->tx_wait) {
			list_del(&kcm->wait_psock_list);
			kcm->tx_wait = false;
		}
		kcm->tx_psock = psock;
		psock->tx_kcm = kcm;
		KCM_STATS_INCR(psock->stats.reserved);
	} else if (!kcm->tx_wait) {
		list_add_tail(&kcm->wait_psock_list,
			      &mux->kcm_tx_waiters);
		kcm->tx_wait = true;
	}

	spin_unlock_bh(&mux->lock);

	return psock;
}

/* mux lock held */
static void psock_now_avail(struct kcm_psock *psock)
{
	struct kcm_mux *mux = psock->mux;
	struct kcm_sock *kcm;

	if (list_empty(&mux->kcm_tx_waiters)) {
		list_add_tail(&psock->psock_avail_list,
			      &mux->psocks_avail);
	} else {
		kcm = list_first_entry(&mux->kcm_tx_waiters,
				       struct kcm_sock,
				       wait_psock_list);
		list_del(&kcm->wait_psock_list);
		kcm->tx_wait = false;
		psock->tx_kcm = kcm;

		/* Commit before changing tx_psock since that is read in
		 * reserve_psock before queuing work.
		 */
		smp_mb();

		kcm->tx_psock = psock;
		KCM_STATS_INCR(psock->stats.reserved);
		queue_work(kcm_wq, &kcm->tx_work);
	}
}

/* kcm sock is locked. */
static void unreserve_psock(struct kcm_sock *kcm)
{
	struct kcm_psock *psock;
	struct kcm_mux *mux = kcm->mux;

	spin_lock_bh(&mux->lock);

	psock = kcm->tx_psock;

	if (WARN_ON(!psock)) {
		spin_unlock_bh(&mux->lock);
		return;
	}

	smp_rmb(); /* Read tx_psock before tx_wait */

	kcm_update_tx_mux_stats(mux, psock);

	WARN_ON(kcm->tx_wait);

	kcm->tx_psock = NULL;
	psock->tx_kcm = NULL;
	KCM_STATS_INCR(psock->stats.unreserved);

	if (unlikely(psock->tx_stopped)) {
		if (psock->done) {
			/* Deferred free */
			list_del(&psock->psock_list);
			mux->psocks_cnt--;
			sock_put(psock->sk);
			fput(psock->sk->sk_socket->file);
			kmem_cache_free(kcm_psockp, psock);
		}

		/* Don't put back on available list */

		spin_unlock_bh(&mux->lock);

		return;
	}

	psock_now_avail(psock);

	spin_unlock_bh(&mux->lock);
}

static void kcm_report_tx_retry(struct kcm_sock *kcm)
{
	struct kcm_mux *mux = kcm->mux;

	spin_lock_bh(&mux->lock);
	KCM_STATS_INCR(mux->stats.tx_retries);
	spin_unlock_bh(&mux->lock);
}

/* Write any messages ready on the kcm socket.  Called with kcm sock lock
 * held.  Return bytes actually sent or error.
 */
static int kcm_write_msgs(struct kcm_sock *kcm)
{
	unsigned int total_sent = 0;
	struct sock *sk = &kcm->sk;
	struct kcm_psock *psock;
	struct sk_buff *head;
	int ret = 0;

	kcm->tx_wait_more = false;
	psock = kcm->tx_psock;
	if (unlikely(psock && psock->tx_stopped)) {
		/* A reserved psock was aborted asynchronously. Unreserve
		 * it and we'll retry the message.
		 */
		unreserve_psock(kcm);
		kcm_report_tx_retry(kcm);
		if (skb_queue_empty(&sk->sk_write_queue))
			return 0;

		kcm_tx_msg(skb_peek(&sk->sk_write_queue))->started_tx = false;
	}

retry:
	while ((head = skb_peek(&sk->sk_write_queue))) {
		struct msghdr msg = {
			.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
		};
		struct kcm_tx_msg *txm = kcm_tx_msg(head);
		struct sk_buff *skb;
		unsigned int msize;
		int i;

		if (!txm->started_tx) {
			psock = reserve_psock(kcm);
			if (!psock)
				goto out;
			skb = head;
			txm->frag_offset = 0;
			txm->sent = 0;
			txm->started_tx = true;
		} else {
			if (WARN_ON(!psock)) {
				ret = -EINVAL;
				goto out;
			}
			skb = txm->frag_skb;
		}

		if (WARN_ON(!skb_shinfo(skb)->nr_frags)) {
			ret = -EINVAL;
			goto out;
		}

		msize = 0;
		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
			msize += skb_shinfo(skb)->frags[i].bv_len;

		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE,
			      skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags,
			      msize);
		iov_iter_advance(&msg.msg_iter, txm->frag_offset);

		do {
			ret = sock_sendmsg(psock->sk->sk_socket, &msg);
			if (ret <= 0) {
				if (ret == -EAGAIN) {
					/* Save state to try again when there's
					 * write space on the socket
					 */
					txm->frag_skb = skb;
					ret = 0;
					goto out;
				}

				/* Hard failure in sending message, abort this
				 * psock since it has lost framing
				 * synchronization and retry sending the
				 * message from the beginning.
				 */
				kcm_abort_tx_psock(psock, ret ? -ret : EPIPE,
						   true);
				unreserve_psock(kcm);

				txm->started_tx = false;
				kcm_report_tx_retry(kcm);
				ret = 0;
				goto retry;
			}

			txm->sent += ret;
			txm->frag_offset += ret;
			KCM_STATS_ADD(psock->stats.tx_bytes, ret);
		} while (msg.msg_iter.count > 0);

		if (skb == head) {
			if (skb_has_frag_list(skb)) {
				txm->frag_skb = skb_shinfo(skb)->frag_list;
				txm->frag_offset = 0;
				continue;
			}
		} else if (skb->next) {
			txm->frag_skb = skb->next;
			txm->frag_offset = 0;
			continue;
		}

		/* Successfully sent the whole packet, account for it. */
		sk->sk_wmem_queued -= txm->sent;
		total_sent += txm->sent;
		skb_dequeue(&sk->sk_write_queue);
		kfree_skb(head);
		KCM_STATS_INCR(psock->stats.tx_msgs);
	}
out:
	if (!head) {
		/* Done with all queued messages. */
		WARN_ON(!skb_queue_empty(&sk->sk_write_queue));
		unreserve_psock(kcm);
	}

	/* Check if write space is available */
	sk->sk_write_space(sk);

	return total_sent ? : ret;
}

static void kcm_tx_work(struct work_struct *w)
{
	struct kcm_sock *kcm = container_of(w, struct kcm_sock, tx_work);
	struct sock *sk = &kcm->sk;
	int err;

	lock_sock(sk);

	/* Primarily for SOCK_DGRAM sockets, also handle asynchronous tx
	 * aborts
	 */
	err = kcm_write_msgs(kcm);
	if (err < 0) {
		/* Hard failure in write, report error on KCM socket */
		pr_warn("KCM: Hard failure on kcm_write_msgs %d\n", err);
		report_csk_error(&kcm->sk, -err);
		goto out;
	}

	/* Primarily for SOCK_SEQPACKET sockets */
	if (likely(sk->sk_socket) &&
	    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
		clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		sk->sk_write_space(sk);
	}

out:
	release_sock(sk);
}

static void kcm_push(struct kcm_sock *kcm)
{
	if (kcm->tx_wait_more)
		kcm_write_msgs(kcm);
}

static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
{
	struct sock *sk = sock->sk;
	struct kcm_sock *kcm = kcm_sk(sk);
	struct sk_buff *skb = NULL, *head = NULL;
	size_t copy, copied = 0;
	long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
	int eor = (sock->type == SOCK_DGRAM) ?
		  !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR);
	int err = -EPIPE;

	lock_sock(sk);

	/* Per tcp_sendmsg this should be in poll */
	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);

	if (sk->sk_err)
		goto out_error;

	if (kcm->seq_skb) {
		/* Previously opened message */
		head = kcm->seq_skb;
		skb = kcm_tx_msg(head)->last_skb;
		goto start;
	}

	/* Call the sk_stream functions to manage the sndbuf mem. */
	if (!sk_stream_memory_free(sk)) {
		kcm_push(kcm);
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		err = sk_stream_wait_memory(sk, &timeo);
		if (err)
			goto out_error;
	}

	if (msg_data_left(msg)) {
		/* New message, alloc head skb */
		head = alloc_skb(0, sk->sk_allocation);
		while (!head) {
			kcm_push(kcm);
			err = sk_stream_wait_memory(sk, &timeo);
			if (err)
				goto out_error;

			head = alloc_skb(0, sk->sk_allocation);
		}

		skb = head;

		/* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling
		 * csum_and_copy_from_iter from skb_do_copy_data_nocache.
		 */
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	}

start:
	while (msg_data_left(msg)) {
		bool merge = true;
		int i = skb_shinfo(skb)->nr_frags;
		struct page_frag *pfrag = sk_page_frag(sk);

		if (!sk_page_frag_refill(sk, pfrag))
			goto wait_for_memory;

		if (!skb_can_coalesce(skb, i, pfrag->page,
				      pfrag->offset)) {
			if (i == MAX_SKB_FRAGS) {
				struct sk_buff *tskb;

				tskb = alloc_skb(0, sk->sk_allocation);
				if (!tskb)
					goto wait_for_memory;

				if (head == skb)
					skb_shinfo(head)->frag_list = tskb;
				else
					skb->next = tskb;

				skb = tskb;
				skb->ip_summed = CHECKSUM_UNNECESSARY;
				continue;
			}
			merge = false;
		}

		if (msg->msg_flags & MSG_SPLICE_PAGES) {
			copy = msg_data_left(msg);
			if (!sk_wmem_schedule(sk, copy))
				goto wait_for_memory;

			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
						   sk->sk_allocation);
			if (err < 0) {
				if (err == -EMSGSIZE)
					goto wait_for_memory;
				goto out_error;
			}

			copy = err;
			skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
			sk_wmem_queued_add(sk, copy);
			sk_mem_charge(sk, copy);

			if (head != skb)
				head->truesize += copy;
		} else {
			copy = min_t(int, msg_data_left(msg),
				     pfrag->size - pfrag->offset);
			if (!sk_wmem_schedule(sk, copy))
				goto wait_for_memory;

			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
						       pfrag->page,
						       pfrag->offset,
						       copy);
			if (err)
				goto out_error;

			/* Update the skb. */
			if (merge) {
				skb_frag_size_add(
					&skb_shinfo(skb)->frags[i - 1], copy);
			} else {
				skb_fill_page_desc(skb, i, pfrag->page,
						   pfrag->offset, copy);
				get_page(pfrag->page);
			}

			pfrag->offset += copy;
		}

		copied += copy;
		if (head != skb) {
			head->len += copy;
			head->data_len += copy;
		}

		continue;

wait_for_memory:
		kcm_push(kcm);
		err = sk_stream_wait_memory(sk, &timeo);
		if (err)
			goto out_error;
	}

	if (eor) {
		bool not_busy = skb_queue_empty(&sk->sk_write_queue);

		if (head) {
			/* Message complete, queue it on send buffer */
			__skb_queue_tail(&sk->sk_write_queue, head);
			kcm->seq_skb = NULL;
			KCM_STATS_INCR(kcm->stats.tx_msgs);
		}

		if (msg->msg_flags & MSG_BATCH) {
			kcm->tx_wait_more = true;
		} else if (kcm->tx_wait_more || not_busy) {
			err = kcm_write_msgs(kcm);
			if (err < 0) {
				/* We got a hard error in write_msgs but have
				 * already queued this message. Report an error
				 * in the socket, but don't affect return value
				 * from sendmsg
				 */
				pr_warn("KCM: Hard failure on kcm_write_msgs\n");
				report_csk_error(&kcm->sk, -err);
			}
		}
	} else {
		/* Message not complete, save state */
partial_message:
		if (head) {
			kcm->seq_skb = head;
			kcm_tx_msg(head)->last_skb = skb;
		}
	}

	KCM_STATS_ADD(kcm->stats.tx_bytes, copied);

	release_sock(sk);
	return copied;

out_error:
	kcm_push(kcm);

	if (copied && sock->type == SOCK_SEQPACKET) {
		/* Wrote some bytes before encountering an
		 * error, return partial success.
		 */
		goto partial_message;
	}

	if (head != kcm->seq_skb)
		kfree_skb(head);

	err = sk_stream_error(sk, msg->msg_flags, err);

	/* make sure we wake any epoll edge trigger waiter */
	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN))
		sk->sk_write_space(sk);

	release_sock(sk);
	return err;
}

static void kcm_splice_eof(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct kcm_sock *kcm = kcm_sk(sk);

	if (skb_queue_empty_lockless(&sk->sk_write_queue))
		return;

	lock_sock(sk);
	kcm_write_msgs(kcm);
	release_sock(sk);
}

static ssize_t kcm_sendpage(struct socket *sock, struct page *page,
			    int offset, size_t size, int flags)

{
	struct bio_vec bvec;
	struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, };

	if (flags & MSG_SENDPAGE_NOTLAST)
		msg.msg_flags |= MSG_MORE;

	if (flags & MSG_OOB)
		return -EOPNOTSUPP;

	bvec_set_page(&bvec, page, size, offset);
	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
	return kcm_sendmsg(sock, &msg, size);
}

static int kcm_recvmsg(struct socket *sock, struct msghdr *msg,
		       size_t len, int flags)
{
	struct sock *sk = sock->sk;
	struct kcm_sock *kcm = kcm_sk(sk);
	int err = 0;
	struct strp_msg *stm;
	int copied = 0;
	struct sk_buff *skb;

	skb = skb_recv_datagram(sk, flags, &err);
	if (!skb)
		goto out;

	/* Okay, have a message on the receive queue */

	stm = strp_msg(skb);

	if (len > stm->full_len)
		len = stm->full_len;

	err = skb_copy_datagram_msg(skb, stm->offset, msg, len);
	if (err < 0)
		goto out;

	copied = len;
	if (likely(!(flags & MSG_PEEK))) {
		KCM_STATS_ADD(kcm->stats.rx_bytes, copied);
		if (copied < stm->full_len) {
			if (sock->type == SOCK_DGRAM) {
				/* Truncated message */
				msg->msg_flags |= MSG_TRUNC;
				goto msg_finished;
			}
			stm->offset += copied;
			stm->full_len -= copied;
		} else {
msg_finished:
			/* Finished with message */
			msg->msg_flags |= MSG_EOR;
			KCM_STATS_INCR(kcm->stats.rx_msgs);
		}
	}

out:
	skb_free_datagram(sk, skb);
	return copied ? : err;
}

static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
			       struct pipe_inode_info *pipe, size_t len,
			       unsigned int flags)
{
	struct sock *sk = sock->sk;
	struct kcm_sock *kcm = kcm_sk(sk);
	struct strp_msg *stm;
	int err = 0;
	ssize_t copied;
	struct sk_buff *skb;

	/* Only support splice for SOCKSEQPACKET */

	skb = skb_recv_datagram(sk, flags, &err);
	if (!skb)
		goto err_out;

	/* Okay, have a message on the receive queue */

	stm = strp_msg(skb);

	if (len > stm->full_len)
		len = stm->full_len;

	copied = skb_splice_bits(skb, sk, stm->offset, pipe, len, flags);
	if (copied < 0) {
		err = copied;
		goto err_out;
	}

	KCM_STATS_ADD(kcm->stats.rx_bytes, copied);

	stm->offset += copied;
	stm->full_len -= copied;

	/* We have no way to return MSG_EOR. If all the bytes have been
	 * read we still leave the message in the receive socket buffer.
	 * A subsequent recvmsg needs to be done to return MSG_EOR and
	 * finish reading the message.
	 */

	skb_free_datagram(sk, skb);
	return copied;

err_out:
	skb_free_datagram(sk, skb);
	return err;
}

/* kcm sock lock held */
static void kcm_recv_disable(struct kcm_sock *kcm)
{
	struct kcm_mux *mux = kcm->mux;

	if (kcm->rx_disabled)
		return;

	spin_lock_bh(&mux->rx_lock);

	kcm->rx_disabled = 1;

	/* If a psock is reserved we'll do cleanup in unreserve */
	if (!kcm->rx_psock) {
		if (kcm->rx_wait) {
			list_del(&kcm->wait_rx_list);
			/* paired with lockless reads in kcm_rfree() */
			WRITE_ONCE(kcm->rx_wait, false);
		}

		requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue);
	}

	spin_unlock_bh(&mux->rx_lock);
}

/* kcm sock lock held */
static void kcm_recv_enable(struct kcm_sock *kcm)
{
	struct kcm_mux *mux = kcm->mux;

	if (!kcm->rx_disabled)
		return;

	spin_lock_bh(&mux->rx_lock);

	kcm->rx_disabled = 0;
	kcm_rcv_ready(kcm);

	spin_unlock_bh(&mux->rx_lock);
}

static int kcm_setsockopt(struct socket *sock, int level, int optname,
			  sockptr_t optval, unsigned int optlen)
{
	struct kcm_sock *kcm = kcm_sk(sock->sk);
	int val, valbool;
	int err = 0;

	if (level != SOL_KCM)
		return -ENOPROTOOPT;

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

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

	valbool = val ? 1 : 0;

	switch (optname) {
	case KCM_RECV_DISABLE:
		lock_sock(&kcm->sk);
		if (valbool)
			kcm_recv_disable(kcm);
		else
			kcm_recv_enable(kcm);
		release_sock(&kcm->sk);
		break;
	default:
		err = -ENOPROTOOPT;
	}

	return err;
}

static int kcm_getsockopt(struct socket *sock, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	struct kcm_sock *kcm = kcm_sk(sock->sk);
	int val, len;

	if (level != SOL_KCM)
		return -ENOPROTOOPT;

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

	len = min_t(unsigned int, len, sizeof(int));
	if (len < 0)
		return -EINVAL;

	switch (optname) {
	case KCM_RECV_DISABLE:
		val = kcm->rx_disabled;
		break;
	default:
		return -ENOPROTOOPT;
	}

	if (put_user(len, optlen))
		return -EFAULT;
	if (copy_to_user(optval, &val, len))
		return -EFAULT;
	return 0;
}

static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
{
	struct kcm_sock *tkcm;
	struct list_head *head;
	int index = 0;

	/* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
	 * we set sk_state, otherwise epoll_wait always returns right away with
	 * EPOLLHUP
	 */
	kcm->sk.sk_state = TCP_ESTABLISHED;

	/* Add to mux's kcm sockets list */
	kcm->mux = mux;
	spin_lock_bh(&mux->lock);

	head = &mux->kcm_socks;
	list_for_each_entry(tkcm, &mux->kcm_socks, kcm_sock_list) {
		if (tkcm->index != index)
			break;
		head = &tkcm->kcm_sock_list;
		index++;
	}

	list_add(&kcm->kcm_sock_list, head);
	kcm->index = index;

	mux->kcm_socks_cnt++;
	spin_unlock_bh(&mux->lock);

	INIT_WORK(&kcm->tx_work, kcm_tx_work);

	spin_lock_bh(&mux->rx_lock);
	kcm_rcv_ready(kcm);
	spin_unlock_bh(&mux->rx_lock);
}

static int kcm_attach(struct socket *sock, struct socket *csock,
		      struct bpf_prog *prog)
{
	struct kcm_sock *kcm = kcm_sk(sock->sk);
	struct kcm_mux *mux = kcm->mux;
	struct sock *csk;
	struct kcm_psock *psock = NULL, *tpsock;
	struct list_head *head;
	int index = 0;
	static const struct strp_callbacks cb = {
		.rcv_msg = kcm_rcv_strparser,
		.parse_msg = kcm_parse_func_strparser,
		.read_sock_done = kcm_read_sock_done,
	};
	int err = 0;

	csk = csock->sk;
	if (!csk)
		return -EINVAL;

	lock_sock(csk);

	/* Only allow TCP sockets to be attached for now */
	if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) ||
	    csk->sk_protocol != IPPROTO_TCP) {
		err = -EOPNOTSUPP;
		goto out;
	}

	/* Don't allow listeners or closed sockets */
	if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) {
		err = -EOPNOTSUPP;
		goto out;
	}

	psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
	if (!psock) {
		err = -ENOMEM;
		goto out;
	}

	psock->mux = mux;
	psock->sk = csk;
	psock->bpf_prog = prog;

	write_lock_bh(&csk->sk_callback_lock);

	/* Check if sk_user_data is already by KCM or someone else.
	 * Must be done under lock to prevent race conditions.
	 */
	if (csk->sk_user_data) {
		write_unlock_bh(&csk->sk_callback_lock);
		kmem_cache_free(kcm_psockp, psock);
		err = -EALREADY;
		goto out;
	}

	err = strp_init(&psock->strp, csk, &cb);
	if (err) {
		write_unlock_bh(&csk->sk_callback_lock);
		kmem_cache_free(kcm_psockp, psock);
		goto out;
	}

	psock->save_data_ready = csk->sk_data_ready;
	psock->save_write_space = csk->sk_write_space;
	psock->save_state_change = csk->sk_state_change;
	csk->sk_user_data = psock;
	csk->sk_data_ready = psock_data_ready;
	csk->sk_write_space = psock_write_space;
	csk->sk_state_change = psock_state_change;

	write_unlock_bh(&csk->sk_callback_lock);

	sock_hold(csk);

	/* Finished initialization, now add the psock to the MUX. */
	spin_lock_bh(&mux->lock);
	head = &mux->psocks;
	list_for_each_entry(tpsock, &mux->psocks, psock_list) {
		if (tpsock->index != index)
			break;
		head = &tpsock->psock_list;
		index++;
	}

	list_add(&psock->psock_list, head);
	psock->index = index;

	KCM_STATS_INCR(mux->stats.psock_attach);
	mux->psocks_cnt++;
	psock_now_avail(psock);
	spin_unlock_bh(&mux->lock);

	/* Schedule RX work in case there are already bytes queued */
	strp_check_rcv(&psock->strp);

out:
	release_sock(csk);

	return err;
}

static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info)
{
	struct socket *csock;
	struct bpf_prog *prog;
	int err;

	csock = sockfd_lookup(info->fd, &err);
	if (!csock)
		return -ENOENT;

	prog = bpf_prog_get_type(info->bpf_fd, BPF_PROG_TYPE_SOCKET_FILTER);
	if (IS_ERR(prog)) {
		err = PTR_ERR(prog);
		goto out;
	}

	err = kcm_attach(sock, csock, prog);
	if (err) {
		bpf_prog_put(prog);
		goto out;
	}

	/* Keep reference on file also */

	return 0;
out:
	sockfd_put(csock);
	return err;
}

static void kcm_unattach(struct kcm_psock *psock)
{
	struct sock *csk = psock->sk;
	struct kcm_mux *mux = psock->mux;

	lock_sock(csk);

	/* Stop getting callbacks from TCP socket. After this there should
	 * be no way to reserve a kcm for this psock.
	 */
	write_lock_bh(&csk->sk_callback_lock);
	csk->sk_user_data = NULL;
	csk->sk_data_ready = psock->save_data_ready;
	csk->sk_write_space = psock->save_write_space;
	csk->sk_state_change = psock->save_state_change;
	strp_stop(&psock->strp);

	if (WARN_ON(psock->rx_kcm)) {
		write_unlock_bh(&csk->sk_callback_lock);
		release_sock(csk);
		return;
	}

	spin_lock_bh(&mux->rx_lock);

	/* Stop receiver activities. After this point psock should not be
	 * able to get onto ready list either through callbacks or work.
	 */
	if (psock->ready_rx_msg) {
		list_del(&psock->psock_ready_list);
		kfree_skb(psock->ready_rx_msg);
		psock->ready_rx_msg = NULL;
		KCM_STATS_INCR(mux->stats.rx_ready_drops);
	}

	spin_unlock_bh(&mux->rx_lock);

	write_unlock_bh(&csk->sk_callback_lock);

	/* Call strp_done without sock lock */
	release_sock(csk);
	strp_done(&psock->strp);
	lock_sock(csk);

	bpf_prog_put(psock->bpf_prog);

	spin_lock_bh(&mux->lock);

	aggregate_psock_stats(&psock->stats, &mux->aggregate_psock_stats);
	save_strp_stats(&psock->strp, &mux->aggregate_strp_stats);

	KCM_STATS_INCR(mux->stats.psock_unattach);

	if (psock->tx_kcm) {
		/* psock was reserved.  Just mark it finished and we will clean
		 * up in the kcm paths, we need kcm lock which can not be
		 * acquired here.
		 */
		KCM_STATS_INCR(mux->stats.psock_unattach_rsvd);
		spin_unlock_bh(&mux->lock);

		/* We are unattaching a socket that is reserved. Abort the
		 * socket since we may be out of sync in sending on it. We need
		 * to do this without the mux lock.
		 */
		kcm_abort_tx_psock(psock, EPIPE, false);

		spin_lock_bh(&mux->lock);
		if (!psock->tx_kcm) {
			/* psock now unreserved in window mux was unlocked */
			goto no_reserved;
		}
		psock->done = 1;

		/* Commit done before queuing work to process it */
		smp_mb();

		/* Queue tx work to make sure psock->done is handled */
		queue_work(kcm_wq, &psock->tx_kcm->tx_work);
		spin_unlock_bh(&mux->lock);
	} else {
no_reserved:
		if (!psock->tx_stopped)
			list_del(&psock->psock_avail_list);
		list_del(&psock->psock_list);
		mux->psocks_cnt--;
		spin_unlock_bh(&mux->lock);

		sock_put(csk);
		fput(csk->sk_socket->file);
		kmem_cache_free(kcm_psockp, psock);
	}

	release_sock(csk);
}

static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info)
{
	struct kcm_sock *kcm = kcm_sk(sock->sk);
	struct kcm_mux *mux = kcm->mux;
	struct kcm_psock *psock;
	struct socket *csock;
	struct sock *csk;
	int err;

	csock = sockfd_lookup(info->fd, &err);
	if (!csock)
		return -ENOENT;

	csk = csock->sk;
	if (!csk) {
		err = -EINVAL;
		goto out;
	}

	err = -ENOENT;

	spin_lock_bh(&mux->lock);

	list_for_each_entry(psock, &mux->psocks, psock_list) {
		if (psock->sk != csk)
			continue;

		/* Found the matching psock */

		if (psock->unattaching || WARN_ON(psock->done)) {
			err = -EALREADY;
			break;
		}

		psock->unattaching = 1;

		spin_unlock_bh(&mux->lock);

		/* Lower socket lock should already be held */
		kcm_unattach(psock);

		err = 0;
		goto out;
	}

	spin_unlock_bh(&mux->lock);

out:
	sockfd_put(csock);
	return err;
}

static struct proto kcm_proto = {
	.name	= "KCM",
	.owner	= THIS_MODULE,
	.obj_size = sizeof(struct kcm_sock),
};

/* Clone a kcm socket. */
static struct file *kcm_clone(struct socket *osock)
{
	struct socket *newsock;
	struct sock *newsk;

	newsock = sock_alloc();
	if (!newsock)
		return ERR_PTR(-ENFILE);

	newsock->type = osock->type;
	newsock->ops = osock->ops;

	__module_get(newsock->ops->owner);

	newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL,
			 &kcm_proto, false);
	if (!newsk) {
		sock_release(newsock);
		return ERR_PTR(-ENOMEM);
	}
	sock_init_data(newsock, newsk);
	init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux);

	return sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name);
}

static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	int err;

	switch (cmd) {
	case SIOCKCMATTACH: {
		struct kcm_attach info;

		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
			return -EFAULT;

		err = kcm_attach_ioctl(sock, &info);

		break;
	}
	case SIOCKCMUNATTACH: {
		struct kcm_unattach info;

		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
			return -EFAULT;

		err = kcm_unattach_ioctl(sock, &info);

		break;
	}
	case SIOCKCMCLONE: {
		struct kcm_clone info;
		struct file *file;

		info.fd = get_unused_fd_flags(0);
		if (unlikely(info.fd < 0))
			return info.fd;

		file = kcm_clone(sock);
		if (IS_ERR(file)) {
			put_unused_fd(info.fd);
			return PTR_ERR(file);
		}
		if (copy_to_user((void __user *)arg, &info,
				 sizeof(info))) {
			put_unused_fd(info.fd);
			fput(file);
			return -EFAULT;
		}
		fd_install(info.fd, file);
		err = 0;
		break;
	}
	default:
		err = -ENOIOCTLCMD;
		break;
	}

	return err;
}

static void free_mux(struct rcu_head *rcu)
{
	struct kcm_mux *mux = container_of(rcu,
	    struct kcm_mux, rcu);

	kmem_cache_free(kcm_muxp, mux);
}

static void release_mux(struct kcm_mux *mux)
{
	struct kcm_net *knet = mux->knet;
	struct kcm_psock *psock, *tmp_psock;

	/* Release psocks */
	list_for_each_entry_safe(psock, tmp_psock,
				 &mux->psocks, psock_list) {
		if (!WARN_ON(psock->unattaching))
			kcm_unattach(psock);
	}

	if (WARN_ON(mux->psocks_cnt))
		return;

	__skb_queue_purge(&mux->rx_hold_queue);

	mutex_lock(&knet->mutex);
	aggregate_mux_stats(&mux->stats, &knet->aggregate_mux_stats);
	aggregate_psock_stats(&mux->aggregate_psock_stats,
			      &knet->aggregate_psock_stats);
	aggregate_strp_stats(&mux->aggregate_strp_stats,
			     &knet->aggregate_strp_stats);
	list_del_rcu(&mux->kcm_mux_list);
	knet->count--;
	mutex_unlock(&knet->mutex);

	call_rcu(&mux->rcu, free_mux);
}

static void kcm_done(struct kcm_sock *kcm)
{
	struct kcm_mux *mux = kcm->mux;
	struct sock *sk = &kcm->sk;
	int socks_cnt;

	spin_lock_bh(&mux->rx_lock);
	if (kcm->rx_psock) {
		/* Cleanup in unreserve_rx_kcm */
		WARN_ON(kcm->done);
		kcm->rx_disabled = 1;
		kcm->done = 1;
		spin_unlock_bh(&mux->rx_lock);
		return;
	}

	if (kcm->rx_wait) {
		list_del(&kcm->wait_rx_list);
		/* paired with lockless reads in kcm_rfree() */
		WRITE_ONCE(kcm->rx_wait, false);
	}
	/* Move any pending receive messages to other kcm sockets */
	requeue_rx_msgs(mux, &sk->sk_receive_queue);

	spin_unlock_bh(&mux->rx_lock);

	if (WARN_ON(sk_rmem_alloc_get(sk)))
		return;

	/* Detach from MUX */
	spin_lock_bh(&mux->lock);

	list_del(&kcm->kcm_sock_list);
	mux->kcm_socks_cnt--;
	socks_cnt = mux->kcm_socks_cnt;

	spin_unlock_bh(&mux->lock);

	if (!socks_cnt) {
		/* We are done with the mux now. */
		release_mux(mux);
	}

	WARN_ON(kcm->rx_wait);

	sock_put(&kcm->sk);
}

/* Called by kcm_release to close a KCM socket.
 * If this is the last KCM socket on the MUX, destroy the MUX.
 */
static int kcm_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct kcm_sock *kcm;
	struct kcm_mux *mux;
	struct kcm_psock *psock;

	if (!sk)
		return 0;

	kcm = kcm_sk(sk);
	mux = kcm->mux;

	lock_sock(sk);
	sock_orphan(sk);
	kfree_skb(kcm->seq_skb);

	/* Purge queue under lock to avoid race condition with tx_work trying
	 * to act when queue is nonempty. If tx_work runs after this point
	 * it will just return.
	 */
	__skb_queue_purge(&sk->sk_write_queue);

	/* Set tx_stopped. This is checked when psock is bound to a kcm and we
	 * get a writespace callback. This prevents further work being queued
	 * from the callback (unbinding the psock occurs after canceling work.
	 */
	kcm->tx_stopped = 1;

	release_sock(sk);

	spin_lock_bh(&mux->lock);
	if (kcm->tx_wait) {
		/* Take of tx_wait list, after this point there should be no way
		 * that a psock will be assigned to this kcm.
		 */
		list_del(&kcm->wait_psock_list);
		kcm->tx_wait = false;
	}
	spin_unlock_bh(&mux->lock);

	/* Cancel work. After this point there should be no outside references
	 * to the kcm socket.
	 */
	cancel_work_sync(&kcm->tx_work);

	lock_sock(sk);
	psock = kcm->tx_psock;
	if (psock) {
		/* A psock was reserved, so we need to kill it since it
		 * may already have some bytes queued from a message. We
		 * need to do this after removing kcm from tx_wait list.
		 */
		kcm_abort_tx_psock(psock, EPIPE, false);
		unreserve_psock(kcm);
	}
	release_sock(sk);

	WARN_ON(kcm->tx_wait);
	WARN_ON(kcm->tx_psock);

	sock->sk = NULL;

	kcm_done(kcm);

	return 0;
}

static const struct proto_ops kcm_dgram_ops = {
	.family =	PF_KCM,
	.owner =	THIS_MODULE,
	.release =	kcm_release,
	.bind =		sock_no_bind,
	.connect =	sock_no_connect,
	.socketpair =	sock_no_socketpair,
	.accept =	sock_no_accept,
	.getname =	sock_no_getname,
	.poll =		datagram_poll,
	.ioctl =	kcm_ioctl,
	.listen =	sock_no_listen,
	.shutdown =	sock_no_shutdown,
	.setsockopt =	kcm_setsockopt,
	.getsockopt =	kcm_getsockopt,
	.sendmsg =	kcm_sendmsg,
	.recvmsg =	kcm_recvmsg,
	.mmap =		sock_no_mmap,
	.splice_eof =	kcm_splice_eof,
	.sendpage =	kcm_sendpage,
};

static const struct proto_ops kcm_seqpacket_ops = {
	.family =	PF_KCM,
	.owner =	THIS_MODULE,
	.release =	kcm_release,
	.bind =		sock_no_bind,
	.connect =	sock_no_connect,
	.socketpair =	sock_no_socketpair,
	.accept =	sock_no_accept,
	.getname =	sock_no_getname,
	.poll =		datagram_poll,
	.ioctl =	kcm_ioctl,
	.listen =	sock_no_listen,
	.shutdown =	sock_no_shutdown,
	.setsockopt =	kcm_setsockopt,
	.getsockopt =	kcm_getsockopt,
	.sendmsg =	kcm_sendmsg,
	.recvmsg =	kcm_recvmsg,
	.mmap =		sock_no_mmap,
	.splice_eof =	kcm_splice_eof,
	.sendpage =	kcm_sendpage,
	.splice_read =	kcm_splice_read,
};

/* Create proto operation for kcm sockets */
static int kcm_create(struct net *net, struct socket *sock,
		      int protocol, int kern)
{
	struct kcm_net *knet = net_generic(net, kcm_net_id);
	struct sock *sk;
	struct kcm_mux *mux;

	switch (sock->type) {
	case SOCK_DGRAM:
		sock->ops = &kcm_dgram_ops;
		break;
	case SOCK_SEQPACKET:
		sock->ops = &kcm_seqpacket_ops;
		break;
	default:
		return -ESOCKTNOSUPPORT;
	}

	if (protocol != KCMPROTO_CONNECTED)
		return -EPROTONOSUPPORT;

	sk = sk_alloc(net, PF_KCM, GFP_KERNEL, &kcm_proto, kern);
	if (!sk)
		return -ENOMEM;

	/* Allocate a kcm mux, shared between KCM sockets */
	mux = kmem_cache_zalloc(kcm_muxp, GFP_KERNEL);
	if (!mux) {
		sk_free(sk);
		return -ENOMEM;
	}

	spin_lock_init(&mux->lock);
	spin_lock_init(&mux->rx_lock);
	INIT_LIST_HEAD(&mux->kcm_socks);
	INIT_LIST_HEAD(&mux->kcm_rx_waiters);
	INIT_LIST_HEAD(&mux->kcm_tx_waiters);

	INIT_LIST_HEAD(&mux->psocks);
	INIT_LIST_HEAD(&mux->psocks_ready);
	INIT_LIST_HEAD(&mux->psocks_avail);

	mux->knet = knet;

	/* Add new MUX to list */
	mutex_lock(&knet->mutex);
	list_add_rcu(&mux->kcm_mux_list, &knet->mux_list);
	knet->count++;
	mutex_unlock(&knet->mutex);

	skb_queue_head_init(&mux->rx_hold_queue);

	/* Init KCM socket */
	sock_init_data(sock, sk);
	init_kcm_sock(kcm_sk(sk), mux);

	return 0;
}

static const struct net_proto_family kcm_family_ops = {
	.family = PF_KCM,
	.create = kcm_create,
	.owner  = THIS_MODULE,
};

static __net_init int kcm_init_net(struct net *net)
{
	struct kcm_net *knet = net_generic(net, kcm_net_id);

	INIT_LIST_HEAD_RCU(&knet->mux_list);
	mutex_init(&knet->mutex);

	return 0;
}

static __net_exit void kcm_exit_net(struct net *net)
{
	struct kcm_net *knet = net_generic(net, kcm_net_id);

	/* All KCM sockets should be closed at this point, which should mean
	 * that all multiplexors and psocks have been destroyed.
	 */
	WARN_ON(!list_empty(&knet->mux_list));
}

static struct pernet_operations kcm_net_ops = {
	.init = kcm_init_net,
	.exit = kcm_exit_net,
	.id   = &kcm_net_id,
	.size = sizeof(struct kcm_net),
};

static int __init kcm_init(void)
{
	int err = -ENOMEM;

	kcm_muxp = kmem_cache_create("kcm_mux_cache",
				     sizeof(struct kcm_mux), 0,
				     SLAB_HWCACHE_ALIGN, NULL);
	if (!kcm_muxp)
		goto fail;

	kcm_psockp = kmem_cache_create("kcm_psock_cache",
				       sizeof(struct kcm_psock), 0,
					SLAB_HWCACHE_ALIGN, NULL);
	if (!kcm_psockp)
		goto fail;

	kcm_wq = create_singlethread_workqueue("kkcmd");
	if (!kcm_wq)
		goto fail;

	err = proto_register(&kcm_proto, 1);
	if (err)
		goto fail;

	err = register_pernet_device(&kcm_net_ops);
	if (err)
		goto net_ops_fail;

	err = sock_register(&kcm_family_ops);
	if (err)
		goto sock_register_fail;

	err = kcm_proc_init();
	if (err)
		goto proc_init_fail;

	return 0;

proc_init_fail:
	sock_unregister(PF_KCM);

sock_register_fail:
	unregister_pernet_device(&kcm_net_ops);

net_ops_fail:
	proto_unregister(&kcm_proto);

fail:
	kmem_cache_destroy(kcm_muxp);
	kmem_cache_destroy(kcm_psockp);

	if (kcm_wq)
		destroy_workqueue(kcm_wq);

	return err;
}

static void __exit kcm_exit(void)
{
	kcm_proc_exit();
	sock_unregister(PF_KCM);
	unregister_pernet_device(&kcm_net_ops);
	proto_unregister(&kcm_proto);
	destroy_workqueue(kcm_wq);

	kmem_cache_destroy(kcm_muxp);
	kmem_cache_destroy(kcm_psockp);
}

module_init(kcm_init);
module_exit(kcm_exit);

MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(PF_KCM);