summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/sockmap.c
blob: 95a84b2f10cecf5c6bea495e3c07e3ffcefec82d (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
/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */

/* A BPF sock_map is used to store sock objects. This is primarly used
 * for doing socket redirect with BPF helper routines.
 *
 * A sock map may have BPF programs attached to it, currently a program
 * used to parse packets and a program to provide a verdict and redirect
 * decision on the packet are supported. Any programs attached to a sock
 * map are inherited by sock objects when they are added to the map. If
 * no BPF programs are attached the sock object may only be used for sock
 * redirect.
 *
 * A sock object may be in multiple maps, but can only inherit a single
 * parse or verdict program. If adding a sock object to a map would result
 * in having multiple parsing programs the update will return an EBUSY error.
 *
 * For reference this program is similar to devmap used in XDP context
 * reviewing these together may be useful. For an example please review
 * ./samples/bpf/sockmap/.
 */
#include <linux/bpf.h>
#include <net/sock.h>
#include <linux/filter.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/kernel.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/workqueue.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <net/strparser.h>
#include <net/tcp.h>
#include <linux/ptr_ring.h>
#include <net/inet_common.h>
#include <linux/sched/signal.h>

#define SOCK_CREATE_FLAG_MASK \
	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)

struct bpf_stab {
	struct bpf_map map;
	struct sock **sock_map;
	struct bpf_prog *bpf_tx_msg;
	struct bpf_prog *bpf_parse;
	struct bpf_prog *bpf_verdict;
};

enum smap_psock_state {
	SMAP_TX_RUNNING,
};

struct smap_psock_map_entry {
	struct list_head list;
	struct sock **entry;
};

struct smap_psock {
	struct rcu_head	rcu;
	refcount_t refcnt;

	/* datapath variables */
	struct sk_buff_head rxqueue;
	bool strp_enabled;

	/* datapath error path cache across tx work invocations */
	int save_rem;
	int save_off;
	struct sk_buff *save_skb;

	/* datapath variables for tx_msg ULP */
	struct sock *sk_redir;
	int apply_bytes;
	int cork_bytes;
	int sg_size;
	int eval;
	struct sk_msg_buff *cork;
	struct list_head ingress;

	struct strparser strp;
	struct bpf_prog *bpf_tx_msg;
	struct bpf_prog *bpf_parse;
	struct bpf_prog *bpf_verdict;
	struct list_head maps;

	/* Back reference used when sock callback trigger sockmap operations */
	struct sock *sock;
	unsigned long state;

	struct work_struct tx_work;
	struct work_struct gc_work;

	struct proto *sk_proto;
	void (*save_close)(struct sock *sk, long timeout);
	void (*save_data_ready)(struct sock *sk);
	void (*save_write_space)(struct sock *sk);
};

static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
			   int nonblock, int flags, int *addr_len);
static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
			    int offset, size_t size, int flags);

static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
{
	return rcu_dereference_sk_user_data(sk);
}

static bool bpf_tcp_stream_read(const struct sock *sk)
{
	struct smap_psock *psock;
	bool empty = true;

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (unlikely(!psock))
		goto out;
	empty = list_empty(&psock->ingress);
out:
	rcu_read_unlock();
	return !empty;
}

static struct proto tcp_bpf_proto;
static int bpf_tcp_init(struct sock *sk)
{
	struct smap_psock *psock;

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (unlikely(!psock)) {
		rcu_read_unlock();
		return -EINVAL;
	}

	if (unlikely(psock->sk_proto)) {
		rcu_read_unlock();
		return -EBUSY;
	}

	psock->save_close = sk->sk_prot->close;
	psock->sk_proto = sk->sk_prot;

	if (psock->bpf_tx_msg) {
		tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
		tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
		tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
		tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
	}

	sk->sk_prot = &tcp_bpf_proto;
	rcu_read_unlock();
	return 0;
}

static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
static int free_start_sg(struct sock *sk, struct sk_msg_buff *md);

static void bpf_tcp_release(struct sock *sk)
{
	struct smap_psock *psock;

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (unlikely(!psock))
		goto out;

	if (psock->cork) {
		free_start_sg(psock->sock, psock->cork);
		kfree(psock->cork);
		psock->cork = NULL;
	}

	if (psock->sk_proto) {
		sk->sk_prot = psock->sk_proto;
		psock->sk_proto = NULL;
	}
out:
	rcu_read_unlock();
}

static void bpf_tcp_close(struct sock *sk, long timeout)
{
	void (*close_fun)(struct sock *sk, long timeout);
	struct smap_psock_map_entry *e, *tmp;
	struct sk_msg_buff *md, *mtmp;
	struct smap_psock *psock;
	struct sock *osk;

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (unlikely(!psock)) {
		rcu_read_unlock();
		return sk->sk_prot->close(sk, timeout);
	}

	/* The psock may be destroyed anytime after exiting the RCU critial
	 * section so by the time we use close_fun the psock may no longer
	 * be valid. However, bpf_tcp_close is called with the sock lock
	 * held so the close hook and sk are still valid.
	 */
	close_fun = psock->save_close;

	write_lock_bh(&sk->sk_callback_lock);
	if (psock->cork) {
		free_start_sg(psock->sock, psock->cork);
		kfree(psock->cork);
		psock->cork = NULL;
	}

	list_for_each_entry_safe(md, mtmp, &psock->ingress, list) {
		list_del(&md->list);
		free_start_sg(psock->sock, md);
		kfree(md);
	}

	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
		osk = cmpxchg(e->entry, sk, NULL);
		if (osk == sk) {
			list_del(&e->list);
			smap_release_sock(psock, sk);
		}
	}
	write_unlock_bh(&sk->sk_callback_lock);
	rcu_read_unlock();
	close_fun(sk, timeout);
}

enum __sk_action {
	__SK_DROP = 0,
	__SK_PASS,
	__SK_REDIRECT,
	__SK_NONE,
};

static struct tcp_ulp_ops bpf_tcp_ulp_ops __read_mostly = {
	.name		= "bpf_tcp",
	.uid		= TCP_ULP_BPF,
	.user_visible	= false,
	.owner		= NULL,
	.init		= bpf_tcp_init,
	.release	= bpf_tcp_release,
};

static int memcopy_from_iter(struct sock *sk,
			     struct sk_msg_buff *md,
			     struct iov_iter *from, int bytes)
{
	struct scatterlist *sg = md->sg_data;
	int i = md->sg_curr, rc = -ENOSPC;

	do {
		int copy;
		char *to;

		if (md->sg_copybreak >= sg[i].length) {
			md->sg_copybreak = 0;

			if (++i == MAX_SKB_FRAGS)
				i = 0;

			if (i == md->sg_end)
				break;
		}

		copy = sg[i].length - md->sg_copybreak;
		to = sg_virt(&sg[i]) + md->sg_copybreak;
		md->sg_copybreak += copy;

		if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY)
			rc = copy_from_iter_nocache(to, copy, from);
		else
			rc = copy_from_iter(to, copy, from);

		if (rc != copy) {
			rc = -EFAULT;
			goto out;
		}

		bytes -= copy;
		if (!bytes)
			break;

		md->sg_copybreak = 0;
		if (++i == MAX_SKB_FRAGS)
			i = 0;
	} while (i != md->sg_end);
out:
	md->sg_curr = i;
	return rc;
}

static int bpf_tcp_push(struct sock *sk, int apply_bytes,
			struct sk_msg_buff *md,
			int flags, bool uncharge)
{
	bool apply = apply_bytes;
	struct scatterlist *sg;
	int offset, ret = 0;
	struct page *p;
	size_t size;

	while (1) {
		sg = md->sg_data + md->sg_start;
		size = (apply && apply_bytes < sg->length) ?
			apply_bytes : sg->length;
		offset = sg->offset;

		tcp_rate_check_app_limited(sk);
		p = sg_page(sg);
retry:
		ret = do_tcp_sendpages(sk, p, offset, size, flags);
		if (ret != size) {
			if (ret > 0) {
				if (apply)
					apply_bytes -= ret;

				sg->offset += ret;
				sg->length -= ret;
				size -= ret;
				offset += ret;
				if (uncharge)
					sk_mem_uncharge(sk, ret);
				goto retry;
			}

			return ret;
		}

		if (apply)
			apply_bytes -= ret;
		sg->offset += ret;
		sg->length -= ret;
		if (uncharge)
			sk_mem_uncharge(sk, ret);

		if (!sg->length) {
			put_page(p);
			md->sg_start++;
			if (md->sg_start == MAX_SKB_FRAGS)
				md->sg_start = 0;
			sg_init_table(sg, 1);

			if (md->sg_start == md->sg_end)
				break;
		}

		if (apply && !apply_bytes)
			break;
	}
	return 0;
}

static inline void bpf_compute_data_pointers_sg(struct sk_msg_buff *md)
{
	struct scatterlist *sg = md->sg_data + md->sg_start;

	if (md->sg_copy[md->sg_start]) {
		md->data = md->data_end = 0;
	} else {
		md->data = sg_virt(sg);
		md->data_end = md->data + sg->length;
	}
}

static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
{
	struct scatterlist *sg = md->sg_data;
	int i = md->sg_start;

	do {
		int uncharge = (bytes < sg[i].length) ? bytes : sg[i].length;

		sk_mem_uncharge(sk, uncharge);
		bytes -= uncharge;
		if (!bytes)
			break;
		i++;
		if (i == MAX_SKB_FRAGS)
			i = 0;
	} while (i != md->sg_end);
}

static void free_bytes_sg(struct sock *sk, int bytes,
			  struct sk_msg_buff *md, bool charge)
{
	struct scatterlist *sg = md->sg_data;
	int i = md->sg_start, free;

	while (bytes && sg[i].length) {
		free = sg[i].length;
		if (bytes < free) {
			sg[i].length -= bytes;
			sg[i].offset += bytes;
			if (charge)
				sk_mem_uncharge(sk, bytes);
			break;
		}

		if (charge)
			sk_mem_uncharge(sk, sg[i].length);
		put_page(sg_page(&sg[i]));
		bytes -= sg[i].length;
		sg[i].length = 0;
		sg[i].page_link = 0;
		sg[i].offset = 0;
		i++;

		if (i == MAX_SKB_FRAGS)
			i = 0;
	}
	md->sg_start = i;
}

static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
{
	struct scatterlist *sg = md->sg_data;
	int i = start, free = 0;

	while (sg[i].length) {
		free += sg[i].length;
		sk_mem_uncharge(sk, sg[i].length);
		put_page(sg_page(&sg[i]));
		sg[i].length = 0;
		sg[i].page_link = 0;
		sg[i].offset = 0;
		i++;

		if (i == MAX_SKB_FRAGS)
			i = 0;
	}

	return free;
}

static int free_start_sg(struct sock *sk, struct sk_msg_buff *md)
{
	int free = free_sg(sk, md->sg_start, md);

	md->sg_start = md->sg_end;
	return free;
}

static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md)
{
	return free_sg(sk, md->sg_curr, md);
}

static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md)
{
	return ((_rc == SK_PASS) ?
	       (md->map ? __SK_REDIRECT : __SK_PASS) :
	       __SK_DROP);
}

static unsigned int smap_do_tx_msg(struct sock *sk,
				   struct smap_psock *psock,
				   struct sk_msg_buff *md)
{
	struct bpf_prog *prog;
	unsigned int rc, _rc;

	preempt_disable();
	rcu_read_lock();

	/* If the policy was removed mid-send then default to 'accept' */
	prog = READ_ONCE(psock->bpf_tx_msg);
	if (unlikely(!prog)) {
		_rc = SK_PASS;
		goto verdict;
	}

	bpf_compute_data_pointers_sg(md);
	rc = (*prog->bpf_func)(md, prog->insnsi);
	psock->apply_bytes = md->apply_bytes;

	/* Moving return codes from UAPI namespace into internal namespace */
	_rc = bpf_map_msg_verdict(rc, md);

	/* The psock has a refcount on the sock but not on the map and because
	 * we need to drop rcu read lock here its possible the map could be
	 * removed between here and when we need it to execute the sock
	 * redirect. So do the map lookup now for future use.
	 */
	if (_rc == __SK_REDIRECT) {
		if (psock->sk_redir)
			sock_put(psock->sk_redir);
		psock->sk_redir = do_msg_redirect_map(md);
		if (!psock->sk_redir) {
			_rc = __SK_DROP;
			goto verdict;
		}
		sock_hold(psock->sk_redir);
	}
verdict:
	rcu_read_unlock();
	preempt_enable();

	return _rc;
}

static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
			   struct smap_psock *psock,
			   struct sk_msg_buff *md, int flags)
{
	bool apply = apply_bytes;
	size_t size, copied = 0;
	struct sk_msg_buff *r;
	int err = 0, i;

	r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_KERNEL);
	if (unlikely(!r))
		return -ENOMEM;

	lock_sock(sk);
	r->sg_start = md->sg_start;
	i = md->sg_start;

	do {
		size = (apply && apply_bytes < md->sg_data[i].length) ?
			apply_bytes : md->sg_data[i].length;

		if (!sk_wmem_schedule(sk, size)) {
			if (!copied)
				err = -ENOMEM;
			break;
		}

		sk_mem_charge(sk, size);
		r->sg_data[i] = md->sg_data[i];
		r->sg_data[i].length = size;
		md->sg_data[i].length -= size;
		md->sg_data[i].offset += size;
		copied += size;

		if (md->sg_data[i].length) {
			get_page(sg_page(&r->sg_data[i]));
			r->sg_end = (i + 1) == MAX_SKB_FRAGS ? 0 : i + 1;
		} else {
			i++;
			if (i == MAX_SKB_FRAGS)
				i = 0;
			r->sg_end = i;
		}

		if (apply) {
			apply_bytes -= size;
			if (!apply_bytes)
				break;
		}
	} while (i != md->sg_end);

	md->sg_start = i;

	if (!err) {
		list_add_tail(&r->list, &psock->ingress);
		sk->sk_data_ready(sk);
	} else {
		free_start_sg(sk, r);
		kfree(r);
	}

	release_sock(sk);
	return err;
}

static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
				       struct sk_msg_buff *md,
				       int flags)
{
	bool ingress = !!(md->flags & BPF_F_INGRESS);
	struct smap_psock *psock;
	struct scatterlist *sg;
	int err = 0;

	sg = md->sg_data;

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (unlikely(!psock))
		goto out_rcu;

	if (!refcount_inc_not_zero(&psock->refcnt))
		goto out_rcu;

	rcu_read_unlock();

	if (ingress) {
		err = bpf_tcp_ingress(sk, send, psock, md, flags);
	} else {
		lock_sock(sk);
		err = bpf_tcp_push(sk, send, md, flags, false);
		release_sock(sk);
	}
	smap_release_sock(psock, sk);
	if (unlikely(err))
		goto out;
	return 0;
out_rcu:
	rcu_read_unlock();
out:
	free_bytes_sg(NULL, send, md, false);
	return err;
}

static inline void bpf_md_init(struct smap_psock *psock)
{
	if (!psock->apply_bytes) {
		psock->eval =  __SK_NONE;
		if (psock->sk_redir) {
			sock_put(psock->sk_redir);
			psock->sk_redir = NULL;
		}
	}
}

static void apply_bytes_dec(struct smap_psock *psock, int i)
{
	if (psock->apply_bytes) {
		if (psock->apply_bytes < i)
			psock->apply_bytes = 0;
		else
			psock->apply_bytes -= i;
	}
}

static int bpf_exec_tx_verdict(struct smap_psock *psock,
			       struct sk_msg_buff *m,
			       struct sock *sk,
			       int *copied, int flags)
{
	bool cork = false, enospc = (m->sg_start == m->sg_end);
	struct sock *redir;
	int err = 0;
	int send;

more_data:
	if (psock->eval == __SK_NONE)
		psock->eval = smap_do_tx_msg(sk, psock, m);

	if (m->cork_bytes &&
	    m->cork_bytes > psock->sg_size && !enospc) {
		psock->cork_bytes = m->cork_bytes - psock->sg_size;
		if (!psock->cork) {
			psock->cork = kcalloc(1,
					sizeof(struct sk_msg_buff),
					GFP_ATOMIC | __GFP_NOWARN);

			if (!psock->cork) {
				err = -ENOMEM;
				goto out_err;
			}
		}
		memcpy(psock->cork, m, sizeof(*m));
		goto out_err;
	}

	send = psock->sg_size;
	if (psock->apply_bytes && psock->apply_bytes < send)
		send = psock->apply_bytes;

	switch (psock->eval) {
	case __SK_PASS:
		err = bpf_tcp_push(sk, send, m, flags, true);
		if (unlikely(err)) {
			*copied -= free_start_sg(sk, m);
			break;
		}

		apply_bytes_dec(psock, send);
		psock->sg_size -= send;
		break;
	case __SK_REDIRECT:
		redir = psock->sk_redir;
		apply_bytes_dec(psock, send);

		if (psock->cork) {
			cork = true;
			psock->cork = NULL;
		}

		return_mem_sg(sk, send, m);
		release_sock(sk);

		err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
		lock_sock(sk);

		if (unlikely(err < 0)) {
			free_start_sg(sk, m);
			psock->sg_size = 0;
			if (!cork)
				*copied -= send;
		} else {
			psock->sg_size -= send;
		}

		if (cork) {
			free_start_sg(sk, m);
			psock->sg_size = 0;
			kfree(m);
			m = NULL;
			err = 0;
		}
		break;
	case __SK_DROP:
	default:
		free_bytes_sg(sk, send, m, true);
		apply_bytes_dec(psock, send);
		*copied -= send;
		psock->sg_size -= send;
		err = -EACCES;
		break;
	}

	if (likely(!err)) {
		bpf_md_init(psock);
		if (m &&
		    m->sg_data[m->sg_start].page_link &&
		    m->sg_data[m->sg_start].length)
			goto more_data;
	}

out_err:
	return err;
}

static int bpf_wait_data(struct sock *sk,
			 struct smap_psock *psk, int flags,
			 long timeo, int *err)
{
	int rc;

	DEFINE_WAIT_FUNC(wait, woken_wake_function);

	add_wait_queue(sk_sleep(sk), &wait);
	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
	rc = sk_wait_event(sk, &timeo,
			   !list_empty(&psk->ingress) ||
			   !skb_queue_empty(&sk->sk_receive_queue),
			   &wait);
	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
	remove_wait_queue(sk_sleep(sk), &wait);

	return rc;
}

static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
			   int nonblock, int flags, int *addr_len)
{
	struct iov_iter *iter = &msg->msg_iter;
	struct smap_psock *psock;
	int copied = 0;

	if (unlikely(flags & MSG_ERRQUEUE))
		return inet_recv_error(sk, msg, len, addr_len);

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (unlikely(!psock))
		goto out;

	if (unlikely(!refcount_inc_not_zero(&psock->refcnt)))
		goto out;
	rcu_read_unlock();

	if (!skb_queue_empty(&sk->sk_receive_queue))
		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);

	lock_sock(sk);
bytes_ready:
	while (copied != len) {
		struct scatterlist *sg;
		struct sk_msg_buff *md;
		int i;

		md = list_first_entry_or_null(&psock->ingress,
					      struct sk_msg_buff, list);
		if (unlikely(!md))
			break;
		i = md->sg_start;
		do {
			struct page *page;
			int n, copy;

			sg = &md->sg_data[i];
			copy = sg->length;
			page = sg_page(sg);

			if (copied + copy > len)
				copy = len - copied;

			n = copy_page_to_iter(page, sg->offset, copy, iter);
			if (n != copy) {
				md->sg_start = i;
				release_sock(sk);
				smap_release_sock(psock, sk);
				return -EFAULT;
			}

			copied += copy;
			sg->offset += copy;
			sg->length -= copy;
			sk_mem_uncharge(sk, copy);

			if (!sg->length) {
				i++;
				if (i == MAX_SKB_FRAGS)
					i = 0;
				if (!md->skb)
					put_page(page);
			}
			if (copied == len)
				break;
		} while (i != md->sg_end);
		md->sg_start = i;

		if (!sg->length && md->sg_start == md->sg_end) {
			list_del(&md->list);
			if (md->skb)
				consume_skb(md->skb);
			kfree(md);
		}
	}

	if (!copied) {
		long timeo;
		int data;
		int err = 0;

		timeo = sock_rcvtimeo(sk, nonblock);
		data = bpf_wait_data(sk, psock, flags, timeo, &err);

		if (data) {
			if (!skb_queue_empty(&sk->sk_receive_queue)) {
				release_sock(sk);
				smap_release_sock(psock, sk);
				copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
				return copied;
			}
			goto bytes_ready;
		}

		if (err)
			copied = err;
	}

	release_sock(sk);
	smap_release_sock(psock, sk);
	return copied;
out:
	rcu_read_unlock();
	return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
}


static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
	int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS;
	struct sk_msg_buff md = {0};
	unsigned int sg_copy = 0;
	struct smap_psock *psock;
	int copied = 0, err = 0;
	struct scatterlist *sg;
	long timeo;

	/* Its possible a sock event or user removed the psock _but_ the ops
	 * have not been reprogrammed yet so we get here. In this case fallback
	 * to tcp_sendmsg. Note this only works because we _only_ ever allow
	 * a single ULP there is no hierarchy here.
	 */
	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (unlikely(!psock)) {
		rcu_read_unlock();
		return tcp_sendmsg(sk, msg, size);
	}

	/* Increment the psock refcnt to ensure its not released while sending a
	 * message. Required because sk lookup and bpf programs are used in
	 * separate rcu critical sections. Its OK if we lose the map entry
	 * but we can't lose the sock reference.
	 */
	if (!refcount_inc_not_zero(&psock->refcnt)) {
		rcu_read_unlock();
		return tcp_sendmsg(sk, msg, size);
	}

	sg = md.sg_data;
	sg_init_marker(sg, MAX_SKB_FRAGS);
	rcu_read_unlock();

	lock_sock(sk);
	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);

	while (msg_data_left(msg)) {
		struct sk_msg_buff *m;
		bool enospc = false;
		int copy;

		if (sk->sk_err) {
			err = sk->sk_err;
			goto out_err;
		}

		copy = msg_data_left(msg);
		if (!sk_stream_memory_free(sk))
			goto wait_for_sndbuf;

		m = psock->cork_bytes ? psock->cork : &md;
		m->sg_curr = m->sg_copybreak ? m->sg_curr : m->sg_end;
		err = sk_alloc_sg(sk, copy, m->sg_data,
				  m->sg_start, &m->sg_end, &sg_copy,
				  m->sg_end - 1);
		if (err) {
			if (err != -ENOSPC)
				goto wait_for_memory;
			enospc = true;
			copy = sg_copy;
		}

		err = memcopy_from_iter(sk, m, &msg->msg_iter, copy);
		if (err < 0) {
			free_curr_sg(sk, m);
			goto out_err;
		}

		psock->sg_size += copy;
		copied += copy;
		sg_copy = 0;

		/* When bytes are being corked skip running BPF program and
		 * applying verdict unless there is no more buffer space. In
		 * the ENOSPC case simply run BPF prorgram with currently
		 * accumulated data. We don't have much choice at this point
		 * we could try extending the page frags or chaining complex
		 * frags but even in these cases _eventually_ we will hit an
		 * OOM scenario. More complex recovery schemes may be
		 * implemented in the future, but BPF programs must handle
		 * the case where apply_cork requests are not honored. The
		 * canonical method to verify this is to check data length.
		 */
		if (psock->cork_bytes) {
			if (copy > psock->cork_bytes)
				psock->cork_bytes = 0;
			else
				psock->cork_bytes -= copy;

			if (psock->cork_bytes && !enospc)
				goto out_cork;

			/* All cork bytes accounted for re-run filter */
			psock->eval = __SK_NONE;
			psock->cork_bytes = 0;
		}

		err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags);
		if (unlikely(err < 0))
			goto out_err;
		continue;
wait_for_sndbuf:
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
		err = sk_stream_wait_memory(sk, &timeo);
		if (err)
			goto out_err;
	}
out_err:
	if (err < 0)
		err = sk_stream_error(sk, msg->msg_flags, err);
out_cork:
	release_sock(sk);
	smap_release_sock(psock, sk);
	return copied ? copied : err;
}

static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
			    int offset, size_t size, int flags)
{
	struct sk_msg_buff md = {0}, *m = NULL;
	int err = 0, copied = 0;
	struct smap_psock *psock;
	struct scatterlist *sg;
	bool enospc = false;

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (unlikely(!psock))
		goto accept;

	if (!refcount_inc_not_zero(&psock->refcnt))
		goto accept;
	rcu_read_unlock();

	lock_sock(sk);

	if (psock->cork_bytes) {
		m = psock->cork;
		sg = &m->sg_data[m->sg_end];
	} else {
		m = &md;
		sg = m->sg_data;
		sg_init_marker(sg, MAX_SKB_FRAGS);
	}

	/* Catch case where ring is full and sendpage is stalled. */
	if (unlikely(m->sg_end == m->sg_start &&
	    m->sg_data[m->sg_end].length))
		goto out_err;

	psock->sg_size += size;
	sg_set_page(sg, page, size, offset);
	get_page(page);
	m->sg_copy[m->sg_end] = true;
	sk_mem_charge(sk, size);
	m->sg_end++;
	copied = size;

	if (m->sg_end == MAX_SKB_FRAGS)
		m->sg_end = 0;

	if (m->sg_end == m->sg_start)
		enospc = true;

	if (psock->cork_bytes) {
		if (size > psock->cork_bytes)
			psock->cork_bytes = 0;
		else
			psock->cork_bytes -= size;

		if (psock->cork_bytes && !enospc)
			goto out_err;

		/* All cork bytes accounted for re-run filter */
		psock->eval = __SK_NONE;
		psock->cork_bytes = 0;
	}

	err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags);
out_err:
	release_sock(sk);
	smap_release_sock(psock, sk);
	return copied ? copied : err;
accept:
	rcu_read_unlock();
	return tcp_sendpage(sk, page, offset, size, flags);
}

static void bpf_tcp_msg_add(struct smap_psock *psock,
			    struct sock *sk,
			    struct bpf_prog *tx_msg)
{
	struct bpf_prog *orig_tx_msg;

	orig_tx_msg = xchg(&psock->bpf_tx_msg, tx_msg);
	if (orig_tx_msg)
		bpf_prog_put(orig_tx_msg);
}

static int bpf_tcp_ulp_register(void)
{
	tcp_bpf_proto = tcp_prot;
	tcp_bpf_proto.close = bpf_tcp_close;
	/* Once BPF TX ULP is registered it is never unregistered. It
	 * will be in the ULP list for the lifetime of the system. Doing
	 * duplicate registers is not a problem.
	 */
	return tcp_register_ulp(&bpf_tcp_ulp_ops);
}

static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
{
	struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict);
	int rc;

	if (unlikely(!prog))
		return __SK_DROP;

	skb_orphan(skb);
	/* We need to ensure that BPF metadata for maps is also cleared
	 * when we orphan the skb so that we don't have the possibility
	 * to reference a stale map.
	 */
	TCP_SKB_CB(skb)->bpf.map = NULL;
	skb->sk = psock->sock;
	bpf_compute_data_pointers(skb);
	preempt_disable();
	rc = (*prog->bpf_func)(skb, prog->insnsi);
	preempt_enable();
	skb->sk = NULL;

	/* Moving return codes from UAPI namespace into internal namespace */
	return rc == SK_PASS ?
		(TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) :
		__SK_DROP;
}

static int smap_do_ingress(struct smap_psock *psock, struct sk_buff *skb)
{
	struct sock *sk = psock->sock;
	int copied = 0, num_sg;
	struct sk_msg_buff *r;

	r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_ATOMIC);
	if (unlikely(!r))
		return -EAGAIN;

	if (!sk_rmem_schedule(sk, skb, skb->len)) {
		kfree(r);
		return -EAGAIN;
	}

	sg_init_table(r->sg_data, MAX_SKB_FRAGS);
	num_sg = skb_to_sgvec(skb, r->sg_data, 0, skb->len);
	if (unlikely(num_sg < 0)) {
		kfree(r);
		return num_sg;
	}
	sk_mem_charge(sk, skb->len);
	copied = skb->len;
	r->sg_start = 0;
	r->sg_end = num_sg == MAX_SKB_FRAGS ? 0 : num_sg;
	r->skb = skb;
	list_add_tail(&r->list, &psock->ingress);
	sk->sk_data_ready(sk);
	return copied;
}

static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
{
	struct smap_psock *peer;
	struct sock *sk;
	__u32 in;
	int rc;

	rc = smap_verdict_func(psock, skb);
	switch (rc) {
	case __SK_REDIRECT:
		sk = do_sk_redirect_map(skb);
		if (!sk) {
			kfree_skb(skb);
			break;
		}

		peer = smap_psock_sk(sk);
		in = (TCP_SKB_CB(skb)->bpf.flags) & BPF_F_INGRESS;

		if (unlikely(!peer || sock_flag(sk, SOCK_DEAD) ||
			     !test_bit(SMAP_TX_RUNNING, &peer->state))) {
			kfree_skb(skb);
			break;
		}

		if (!in && sock_writeable(sk)) {
			skb_set_owner_w(skb, sk);
			skb_queue_tail(&peer->rxqueue, skb);
			schedule_work(&peer->tx_work);
			break;
		} else if (in &&
			   atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
			skb_queue_tail(&peer->rxqueue, skb);
			schedule_work(&peer->tx_work);
			break;
		}
	/* Fall through and free skb otherwise */
	case __SK_DROP:
	default:
		kfree_skb(skb);
	}
}

static void smap_report_sk_error(struct smap_psock *psock, int err)
{
	struct sock *sk = psock->sock;

	sk->sk_err = err;
	sk->sk_error_report(sk);
}

static void smap_read_sock_strparser(struct strparser *strp,
				     struct sk_buff *skb)
{
	struct smap_psock *psock;

	rcu_read_lock();
	psock = container_of(strp, struct smap_psock, strp);
	smap_do_verdict(psock, skb);
	rcu_read_unlock();
}

/* Called with lock held on socket */
static void smap_data_ready(struct sock *sk)
{
	struct smap_psock *psock;

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (likely(psock)) {
		write_lock_bh(&sk->sk_callback_lock);
		strp_data_ready(&psock->strp);
		write_unlock_bh(&sk->sk_callback_lock);
	}
	rcu_read_unlock();
}

static void smap_tx_work(struct work_struct *w)
{
	struct smap_psock *psock;
	struct sk_buff *skb;
	int rem, off, n;

	psock = container_of(w, struct smap_psock, tx_work);

	/* lock sock to avoid losing sk_socket at some point during loop */
	lock_sock(psock->sock);
	if (psock->save_skb) {
		skb = psock->save_skb;
		rem = psock->save_rem;
		off = psock->save_off;
		psock->save_skb = NULL;
		goto start;
	}

	while ((skb = skb_dequeue(&psock->rxqueue))) {
		__u32 flags;

		rem = skb->len;
		off = 0;
start:
		flags = (TCP_SKB_CB(skb)->bpf.flags) & BPF_F_INGRESS;
		do {
			if (likely(psock->sock->sk_socket)) {
				if (flags)
					n = smap_do_ingress(psock, skb);
				else
					n = skb_send_sock_locked(psock->sock,
								 skb, off, rem);
			} else {
				n = -EINVAL;
			}

			if (n <= 0) {
				if (n == -EAGAIN) {
					/* Retry when space is available */
					psock->save_skb = skb;
					psock->save_rem = rem;
					psock->save_off = off;
					goto out;
				}
				/* Hard errors break pipe and stop xmit */
				smap_report_sk_error(psock, n ? -n : EPIPE);
				clear_bit(SMAP_TX_RUNNING, &psock->state);
				kfree_skb(skb);
				goto out;
			}
			rem -= n;
			off += n;
		} while (rem);

		if (!flags)
			kfree_skb(skb);
	}
out:
	release_sock(psock->sock);
}

static void smap_write_space(struct sock *sk)
{
	struct smap_psock *psock;

	rcu_read_lock();
	psock = smap_psock_sk(sk);
	if (likely(psock && test_bit(SMAP_TX_RUNNING, &psock->state)))
		schedule_work(&psock->tx_work);
	rcu_read_unlock();
}

static void smap_stop_sock(struct smap_psock *psock, struct sock *sk)
{
	if (!psock->strp_enabled)
		return;
	sk->sk_data_ready = psock->save_data_ready;
	sk->sk_write_space = psock->save_write_space;
	psock->save_data_ready = NULL;
	psock->save_write_space = NULL;
	strp_stop(&psock->strp);
	psock->strp_enabled = false;
}

static void smap_destroy_psock(struct rcu_head *rcu)
{
	struct smap_psock *psock = container_of(rcu,
						  struct smap_psock, rcu);

	/* Now that a grace period has passed there is no longer
	 * any reference to this sock in the sockmap so we can
	 * destroy the psock, strparser, and bpf programs. But,
	 * because we use workqueue sync operations we can not
	 * do it in rcu context
	 */
	schedule_work(&psock->gc_work);
}

static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
{
	if (refcount_dec_and_test(&psock->refcnt)) {
		tcp_cleanup_ulp(sock);
		smap_stop_sock(psock, sock);
		clear_bit(SMAP_TX_RUNNING, &psock->state);
		rcu_assign_sk_user_data(sock, NULL);
		call_rcu_sched(&psock->rcu, smap_destroy_psock);
	}
}

static int smap_parse_func_strparser(struct strparser *strp,
				       struct sk_buff *skb)
{
	struct smap_psock *psock;
	struct bpf_prog *prog;
	int rc;

	rcu_read_lock();
	psock = container_of(strp, struct smap_psock, strp);
	prog = READ_ONCE(psock->bpf_parse);

	if (unlikely(!prog)) {
		rcu_read_unlock();
		return skb->len;
	}

	/* Attach socket for bpf program to use if needed we can do this
	 * because strparser clones the skb before handing it to a upper
	 * layer, meaning skb_orphan has been called. We NULL sk on the
	 * way out to ensure we don't trigger a BUG_ON in skb/sk operations
	 * later and because we are not charging the memory of this skb to
	 * any socket yet.
	 */
	skb->sk = psock->sock;
	bpf_compute_data_pointers(skb);
	rc = (*prog->bpf_func)(skb, prog->insnsi);
	skb->sk = NULL;
	rcu_read_unlock();
	return rc;
}

static int smap_read_sock_done(struct strparser *strp, int err)
{
	return err;
}

static int smap_init_sock(struct smap_psock *psock,
			  struct sock *sk)
{
	static const struct strp_callbacks cb = {
		.rcv_msg = smap_read_sock_strparser,
		.parse_msg = smap_parse_func_strparser,
		.read_sock_done = smap_read_sock_done,
	};

	return strp_init(&psock->strp, sk, &cb);
}

static void smap_init_progs(struct smap_psock *psock,
			    struct bpf_stab *stab,
			    struct bpf_prog *verdict,
			    struct bpf_prog *parse)
{
	struct bpf_prog *orig_parse, *orig_verdict;

	orig_parse = xchg(&psock->bpf_parse, parse);
	orig_verdict = xchg(&psock->bpf_verdict, verdict);

	if (orig_verdict)
		bpf_prog_put(orig_verdict);
	if (orig_parse)
		bpf_prog_put(orig_parse);
}

static void smap_start_sock(struct smap_psock *psock, struct sock *sk)
{
	if (sk->sk_data_ready == smap_data_ready)
		return;
	psock->save_data_ready = sk->sk_data_ready;
	psock->save_write_space = sk->sk_write_space;
	sk->sk_data_ready = smap_data_ready;
	sk->sk_write_space = smap_write_space;
	psock->strp_enabled = true;
}

static void sock_map_remove_complete(struct bpf_stab *stab)
{
	bpf_map_area_free(stab->sock_map);
	kfree(stab);
}

static void smap_gc_work(struct work_struct *w)
{
	struct smap_psock_map_entry *e, *tmp;
	struct sk_msg_buff *md, *mtmp;
	struct smap_psock *psock;

	psock = container_of(w, struct smap_psock, gc_work);

	/* no callback lock needed because we already detached sockmap ops */
	if (psock->strp_enabled)
		strp_done(&psock->strp);

	cancel_work_sync(&psock->tx_work);
	__skb_queue_purge(&psock->rxqueue);

	/* At this point all strparser and xmit work must be complete */
	if (psock->bpf_parse)
		bpf_prog_put(psock->bpf_parse);
	if (psock->bpf_verdict)
		bpf_prog_put(psock->bpf_verdict);
	if (psock->bpf_tx_msg)
		bpf_prog_put(psock->bpf_tx_msg);

	if (psock->cork) {
		free_start_sg(psock->sock, psock->cork);
		kfree(psock->cork);
	}

	list_for_each_entry_safe(md, mtmp, &psock->ingress, list) {
		list_del(&md->list);
		free_start_sg(psock->sock, md);
		kfree(md);
	}

	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
		list_del(&e->list);
		kfree(e);
	}

	if (psock->sk_redir)
		sock_put(psock->sk_redir);

	sock_put(psock->sock);
	kfree(psock);
}

static struct smap_psock *smap_init_psock(struct sock *sock,
					  struct bpf_stab *stab)
{
	struct smap_psock *psock;

	psock = kzalloc_node(sizeof(struct smap_psock),
			     GFP_ATOMIC | __GFP_NOWARN,
			     stab->map.numa_node);
	if (!psock)
		return ERR_PTR(-ENOMEM);

	psock->eval =  __SK_NONE;
	psock->sock = sock;
	skb_queue_head_init(&psock->rxqueue);
	INIT_WORK(&psock->tx_work, smap_tx_work);
	INIT_WORK(&psock->gc_work, smap_gc_work);
	INIT_LIST_HEAD(&psock->maps);
	INIT_LIST_HEAD(&psock->ingress);
	refcount_set(&psock->refcnt, 1);

	rcu_assign_sk_user_data(sock, psock);
	sock_hold(sock);
	return psock;
}

static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
{
	struct bpf_stab *stab;
	u64 cost;
	int err;

	if (!capable(CAP_NET_ADMIN))
		return ERR_PTR(-EPERM);

	/* check sanity of attributes */
	if (attr->max_entries == 0 || attr->key_size != 4 ||
	    attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
		return ERR_PTR(-EINVAL);

	err = bpf_tcp_ulp_register();
	if (err && err != -EEXIST)
		return ERR_PTR(err);

	stab = kzalloc(sizeof(*stab), GFP_USER);
	if (!stab)
		return ERR_PTR(-ENOMEM);

	bpf_map_init_from_attr(&stab->map, attr);

	/* make sure page count doesn't overflow */
	cost = (u64) stab->map.max_entries * sizeof(struct sock *);
	err = -EINVAL;
	if (cost >= U32_MAX - PAGE_SIZE)
		goto free_stab;

	stab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;

	/* if map size is larger than memlock limit, reject it early */
	err = bpf_map_precharge_memlock(stab->map.pages);
	if (err)
		goto free_stab;

	err = -ENOMEM;
	stab->sock_map = bpf_map_area_alloc(stab->map.max_entries *
					    sizeof(struct sock *),
					    stab->map.numa_node);
	if (!stab->sock_map)
		goto free_stab;

	return &stab->map;
free_stab:
	kfree(stab);
	return ERR_PTR(err);
}

static void smap_list_remove(struct smap_psock *psock, struct sock **entry)
{
	struct smap_psock_map_entry *e, *tmp;

	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
		if (e->entry == entry) {
			list_del(&e->list);
			break;
		}
	}
}

static void sock_map_free(struct bpf_map *map)
{
	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
	int i;

	synchronize_rcu();

	/* At this point no update, lookup or delete operations can happen.
	 * However, be aware we can still get a socket state event updates,
	 * and data ready callabacks that reference the psock from sk_user_data
	 * Also psock worker threads are still in-flight. So smap_release_sock
	 * will only free the psock after cancel_sync on the worker threads
	 * and a grace period expire to ensure psock is really safe to remove.
	 */
	rcu_read_lock();
	for (i = 0; i < stab->map.max_entries; i++) {
		struct smap_psock *psock;
		struct sock *sock;

		sock = xchg(&stab->sock_map[i], NULL);
		if (!sock)
			continue;

		write_lock_bh(&sock->sk_callback_lock);
		psock = smap_psock_sk(sock);
		/* This check handles a racing sock event that can get the
		 * sk_callback_lock before this case but after xchg happens
		 * causing the refcnt to hit zero and sock user data (psock)
		 * to be null and queued for garbage collection.
		 */
		if (likely(psock)) {
			smap_list_remove(psock, &stab->sock_map[i]);
			smap_release_sock(psock, sock);
		}
		write_unlock_bh(&sock->sk_callback_lock);
	}
	rcu_read_unlock();

	sock_map_remove_complete(stab);
}

static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
	u32 i = key ? *(u32 *)key : U32_MAX;
	u32 *next = (u32 *)next_key;

	if (i >= stab->map.max_entries) {
		*next = 0;
		return 0;
	}

	if (i == stab->map.max_entries - 1)
		return -ENOENT;

	*next = i + 1;
	return 0;
}

struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
{
	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);

	if (key >= map->max_entries)
		return NULL;

	return READ_ONCE(stab->sock_map[key]);
}

static int sock_map_delete_elem(struct bpf_map *map, void *key)
{
	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
	struct smap_psock *psock;
	int k = *(u32 *)key;
	struct sock *sock;

	if (k >= map->max_entries)
		return -EINVAL;

	sock = xchg(&stab->sock_map[k], NULL);
	if (!sock)
		return -EINVAL;

	write_lock_bh(&sock->sk_callback_lock);
	psock = smap_psock_sk(sock);
	if (!psock)
		goto out;

	if (psock->bpf_parse)
		smap_stop_sock(psock, sock);
	smap_list_remove(psock, &stab->sock_map[k]);
	smap_release_sock(psock, sock);
out:
	write_unlock_bh(&sock->sk_callback_lock);
	return 0;
}

/* Locking notes: Concurrent updates, deletes, and lookups are allowed and are
 * done inside rcu critical sections. This ensures on updates that the psock
 * will not be released via smap_release_sock() until concurrent updates/deletes
 * complete. All operations operate on sock_map using cmpxchg and xchg
 * operations to ensure we do not get stale references. Any reads into the
 * map must be done with READ_ONCE() because of this.
 *
 * A psock is destroyed via call_rcu and after any worker threads are cancelled
 * and syncd so we are certain all references from the update/lookup/delete
 * operations as well as references in the data path are no longer in use.
 *
 * Psocks may exist in multiple maps, but only a single set of parse/verdict
 * programs may be inherited from the maps it belongs to. A reference count
 * is kept with the total number of references to the psock from all maps. The
 * psock will not be released until this reaches zero. The psock and sock
 * user data data use the sk_callback_lock to protect critical data structures
 * from concurrent access. This allows us to avoid two updates from modifying
 * the user data in sock and the lock is required anyways for modifying
 * callbacks, we simply increase its scope slightly.
 *
 * Rules to follow,
 *  - psock must always be read inside RCU critical section
 *  - sk_user_data must only be modified inside sk_callback_lock and read
 *    inside RCU critical section.
 *  - psock->maps list must only be read & modified inside sk_callback_lock
 *  - sock_map must use READ_ONCE and (cmp)xchg operations
 *  - BPF verdict/parse programs must use READ_ONCE and xchg operations
 */
static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
				    struct bpf_map *map,
				    void *key, u64 flags)
{
	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
	struct smap_psock_map_entry *e = NULL;
	struct bpf_prog *verdict, *parse, *tx_msg;
	struct sock *osock, *sock;
	struct smap_psock *psock;
	u32 i = *(u32 *)key;
	bool new = false;
	int err;

	if (unlikely(flags > BPF_EXIST))
		return -EINVAL;

	if (unlikely(i >= stab->map.max_entries))
		return -E2BIG;

	sock = READ_ONCE(stab->sock_map[i]);
	if (flags == BPF_EXIST && !sock)
		return -ENOENT;
	else if (flags == BPF_NOEXIST && sock)
		return -EEXIST;

	sock = skops->sk;

	/* 1. If sock map has BPF programs those will be inherited by the
	 * sock being added. If the sock is already attached to BPF programs
	 * this results in an error.
	 */
	verdict = READ_ONCE(stab->bpf_verdict);
	parse = READ_ONCE(stab->bpf_parse);
	tx_msg = READ_ONCE(stab->bpf_tx_msg);

	if (parse && verdict) {
		/* bpf prog refcnt may be zero if a concurrent attach operation
		 * removes the program after the above READ_ONCE() but before
		 * we increment the refcnt. If this is the case abort with an
		 * error.
		 */
		verdict = bpf_prog_inc_not_zero(verdict);
		if (IS_ERR(verdict))
			return PTR_ERR(verdict);

		parse = bpf_prog_inc_not_zero(parse);
		if (IS_ERR(parse)) {
			bpf_prog_put(verdict);
			return PTR_ERR(parse);
		}
	}

	if (tx_msg) {
		tx_msg = bpf_prog_inc_not_zero(tx_msg);
		if (IS_ERR(tx_msg)) {
			if (parse && verdict) {
				bpf_prog_put(parse);
				bpf_prog_put(verdict);
			}
			return PTR_ERR(tx_msg);
		}
	}

	write_lock_bh(&sock->sk_callback_lock);
	psock = smap_psock_sk(sock);

	/* 2. Do not allow inheriting programs if psock exists and has
	 * already inherited programs. This would create confusion on
	 * which parser/verdict program is running. If no psock exists
	 * create one. Inside sk_callback_lock to ensure concurrent create
	 * doesn't update user data.
	 */
	if (psock) {
		if (READ_ONCE(psock->bpf_parse) && parse) {
			err = -EBUSY;
			goto out_progs;
		}
		if (READ_ONCE(psock->bpf_tx_msg) && tx_msg) {
			err = -EBUSY;
			goto out_progs;
		}
		if (!refcount_inc_not_zero(&psock->refcnt)) {
			err = -EAGAIN;
			goto out_progs;
		}
	} else {
		psock = smap_init_psock(sock, stab);
		if (IS_ERR(psock)) {
			err = PTR_ERR(psock);
			goto out_progs;
		}

		set_bit(SMAP_TX_RUNNING, &psock->state);
		new = true;
	}

	e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
	if (!e) {
		err = -ENOMEM;
		goto out_progs;
	}
	e->entry = &stab->sock_map[i];

	/* 3. At this point we have a reference to a valid psock that is
	 * running. Attach any BPF programs needed.
	 */
	if (tx_msg)
		bpf_tcp_msg_add(psock, sock, tx_msg);
	if (new) {
		err = tcp_set_ulp_id(sock, TCP_ULP_BPF);
		if (err)
			goto out_free;
	}

	if (parse && verdict && !psock->strp_enabled) {
		err = smap_init_sock(psock, sock);
		if (err)
			goto out_free;
		smap_init_progs(psock, stab, verdict, parse);
		smap_start_sock(psock, sock);
	}

	/* 4. Place psock in sockmap for use and stop any programs on
	 * the old sock assuming its not the same sock we are replacing
	 * it with. Because we can only have a single set of programs if
	 * old_sock has a strp we can stop it.
	 */
	list_add_tail(&e->list, &psock->maps);
	write_unlock_bh(&sock->sk_callback_lock);

	osock = xchg(&stab->sock_map[i], sock);
	if (osock) {
		struct smap_psock *opsock = smap_psock_sk(osock);

		write_lock_bh(&osock->sk_callback_lock);
		smap_list_remove(opsock, &stab->sock_map[i]);
		smap_release_sock(opsock, osock);
		write_unlock_bh(&osock->sk_callback_lock);
	}
	return 0;
out_free:
	smap_release_sock(psock, sock);
out_progs:
	if (parse && verdict) {
		bpf_prog_put(parse);
		bpf_prog_put(verdict);
	}
	if (tx_msg)
		bpf_prog_put(tx_msg);
	write_unlock_bh(&sock->sk_callback_lock);
	kfree(e);
	return err;
}

int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
{
	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
	struct bpf_prog *orig;

	if (unlikely(map->map_type != BPF_MAP_TYPE_SOCKMAP))
		return -EINVAL;

	switch (type) {
	case BPF_SK_MSG_VERDICT:
		orig = xchg(&stab->bpf_tx_msg, prog);
		break;
	case BPF_SK_SKB_STREAM_PARSER:
		orig = xchg(&stab->bpf_parse, prog);
		break;
	case BPF_SK_SKB_STREAM_VERDICT:
		orig = xchg(&stab->bpf_verdict, prog);
		break;
	default:
		return -EOPNOTSUPP;
	}

	if (orig)
		bpf_prog_put(orig);

	return 0;
}

static void *sock_map_lookup(struct bpf_map *map, void *key)
{
	return NULL;
}

static int sock_map_update_elem(struct bpf_map *map,
				void *key, void *value, u64 flags)
{
	struct bpf_sock_ops_kern skops;
	u32 fd = *(u32 *)value;
	struct socket *socket;
	int err;

	socket = sockfd_lookup(fd, &err);
	if (!socket)
		return err;

	skops.sk = socket->sk;
	if (!skops.sk) {
		fput(socket->file);
		return -EINVAL;
	}

	if (skops.sk->sk_type != SOCK_STREAM ||
	    skops.sk->sk_protocol != IPPROTO_TCP) {
		fput(socket->file);
		return -EOPNOTSUPP;
	}

	err = sock_map_ctx_update_elem(&skops, map, key, flags);
	fput(socket->file);
	return err;
}

static void sock_map_release(struct bpf_map *map)
{
	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
	struct bpf_prog *orig;

	orig = xchg(&stab->bpf_parse, NULL);
	if (orig)
		bpf_prog_put(orig);
	orig = xchg(&stab->bpf_verdict, NULL);
	if (orig)
		bpf_prog_put(orig);

	orig = xchg(&stab->bpf_tx_msg, NULL);
	if (orig)
		bpf_prog_put(orig);
}

const struct bpf_map_ops sock_map_ops = {
	.map_alloc = sock_map_alloc,
	.map_free = sock_map_free,
	.map_lookup_elem = sock_map_lookup,
	.map_get_next_key = sock_map_get_next_key,
	.map_update_elem = sock_map_update_elem,
	.map_delete_elem = sock_map_delete_elem,
	.map_release_uref = sock_map_release,
};

BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
	   struct bpf_map *, map, void *, key, u64, flags)
{
	WARN_ON_ONCE(!rcu_read_lock_held());
	return sock_map_ctx_update_elem(bpf_sock, map, key, flags);
}

const struct bpf_func_proto bpf_sock_map_update_proto = {
	.func		= bpf_sock_map_update,
	.gpl_only	= false,
	.pkt_access	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_PTR_TO_MAP_KEY,
	.arg4_type	= ARG_ANYTHING,
};