summaryrefslogtreecommitdiff
path: root/kernel/bpf/arraymap.c
blob: 6cdbb4c33d31d5d56dea634b1f062d6fe3caf0df (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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 * Copyright (c) 2016,2017 Facebook
 */
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/filter.h>
#include <linux/perf_event.h>
#include <uapi/linux/btf.h>
#include <linux/rcupdate_trace.h>
#include <linux/btf_ids.h>

#include "map_in_map.h"

#define ARRAY_CREATE_FLAG_MASK \
	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \
	 BPF_F_PRESERVE_ELEMS | BPF_F_INNER_MAP)

static void bpf_array_free_percpu(struct bpf_array *array)
{
	int i;

	for (i = 0; i < array->map.max_entries; i++) {
		free_percpu(array->pptrs[i]);
		cond_resched();
	}
}

static int bpf_array_alloc_percpu(struct bpf_array *array)
{
	void __percpu *ptr;
	int i;

	for (i = 0; i < array->map.max_entries; i++) {
		ptr = bpf_map_alloc_percpu(&array->map, array->elem_size, 8,
					   GFP_USER | __GFP_NOWARN);
		if (!ptr) {
			bpf_array_free_percpu(array);
			return -ENOMEM;
		}
		array->pptrs[i] = ptr;
		cond_resched();
	}

	return 0;
}

/* Called from syscall */
int array_map_alloc_check(union bpf_attr *attr)
{
	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
	int numa_node = bpf_map_attr_numa_node(attr);

	/* check sanity of attributes */
	if (attr->max_entries == 0 || attr->key_size != 4 ||
	    attr->value_size == 0 ||
	    attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
	    !bpf_map_flags_access_ok(attr->map_flags) ||
	    (percpu && numa_node != NUMA_NO_NODE))
		return -EINVAL;

	if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
	    attr->map_flags & (BPF_F_MMAPABLE | BPF_F_INNER_MAP))
		return -EINVAL;

	if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
	    attr->map_flags & BPF_F_PRESERVE_ELEMS)
		return -EINVAL;

	/* avoid overflow on round_up(map->value_size) */
	if (attr->value_size > INT_MAX)
		return -E2BIG;
	/* percpu map value size is bound by PCPU_MIN_UNIT_SIZE */
	if (percpu && round_up(attr->value_size, 8) > PCPU_MIN_UNIT_SIZE)
		return -E2BIG;

	return 0;
}

static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
	int numa_node = bpf_map_attr_numa_node(attr);
	u32 elem_size, index_mask, max_entries;
	bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL);
	u64 array_size, mask64;
	struct bpf_array *array;

	elem_size = round_up(attr->value_size, 8);

	max_entries = attr->max_entries;

	/* On 32 bit archs roundup_pow_of_two() with max_entries that has
	 * upper most bit set in u32 space is undefined behavior due to
	 * resulting 1U << 32, so do it manually here in u64 space.
	 */
	mask64 = fls_long(max_entries - 1);
	mask64 = 1ULL << mask64;
	mask64 -= 1;

	index_mask = mask64;
	if (!bypass_spec_v1) {
		/* round up array size to nearest power of 2,
		 * since cpu will speculate within index_mask limits
		 */
		max_entries = index_mask + 1;
		/* Check for overflows. */
		if (max_entries < attr->max_entries)
			return ERR_PTR(-E2BIG);
	}

	array_size = sizeof(*array);
	if (percpu) {
		array_size += (u64) max_entries * sizeof(void *);
	} else {
		/* rely on vmalloc() to return page-aligned memory and
		 * ensure array->value is exactly page-aligned
		 */
		if (attr->map_flags & BPF_F_MMAPABLE) {
			array_size = PAGE_ALIGN(array_size);
			array_size += PAGE_ALIGN((u64) max_entries * elem_size);
		} else {
			array_size += (u64) max_entries * elem_size;
		}
	}

	/* allocate all map elements and zero-initialize them */
	if (attr->map_flags & BPF_F_MMAPABLE) {
		void *data;

		/* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */
		data = bpf_map_area_mmapable_alloc(array_size, numa_node);
		if (!data)
			return ERR_PTR(-ENOMEM);
		array = data + PAGE_ALIGN(sizeof(struct bpf_array))
			- offsetof(struct bpf_array, value);
	} else {
		array = bpf_map_area_alloc(array_size, numa_node);
	}
	if (!array)
		return ERR_PTR(-ENOMEM);
	array->index_mask = index_mask;
	array->map.bypass_spec_v1 = bypass_spec_v1;

	/* copy mandatory map attributes */
	bpf_map_init_from_attr(&array->map, attr);
	array->elem_size = elem_size;

	if (percpu && bpf_array_alloc_percpu(array)) {
		bpf_map_area_free(array);
		return ERR_PTR(-ENOMEM);
	}

	return &array->map;
}

static void *array_map_elem_ptr(struct bpf_array* array, u32 index)
{
	return array->value + (u64)array->elem_size * index;
}

/* Called from syscall or from eBPF program */
static void *array_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;

	if (unlikely(index >= array->map.max_entries))
		return NULL;

	return array->value + (u64)array->elem_size * (index & array->index_mask);
}

static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
				       u32 off)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);

	if (map->max_entries != 1)
		return -ENOTSUPP;
	if (off >= map->value_size)
		return -EINVAL;

	*imm = (unsigned long)array->value;
	return 0;
}

static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
				       u32 *off)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u64 base = (unsigned long)array->value;
	u64 range = array->elem_size;

	if (map->max_entries != 1)
		return -ENOTSUPP;
	if (imm < base || imm >= base + range)
		return -ENOENT;

	*off = imm - base;
	return 0;
}

/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
static int array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct bpf_insn *insn = insn_buf;
	u32 elem_size = array->elem_size;
	const int ret = BPF_REG_0;
	const int map_ptr = BPF_REG_1;
	const int index = BPF_REG_2;

	if (map->map_flags & BPF_F_INNER_MAP)
		return -EOPNOTSUPP;

	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
	if (!map->bypass_spec_v1) {
		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
	} else {
		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
	}

	if (is_power_of_2(elem_size)) {
		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
	} else {
		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
	}
	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
	*insn++ = BPF_MOV64_IMM(ret, 0);
	return insn - insn_buf;
}

/* Called from eBPF program */
static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;

	if (unlikely(index >= array->map.max_entries))
		return NULL;

	return this_cpu_ptr(array->pptrs[index & array->index_mask]);
}

/* emit BPF instructions equivalent to C code of percpu_array_map_lookup_elem() */
static int percpu_array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct bpf_insn *insn = insn_buf;

	if (!bpf_jit_supports_percpu_insn())
		return -EOPNOTSUPP;

	if (map->map_flags & BPF_F_INNER_MAP)
		return -EOPNOTSUPP;

	BUILD_BUG_ON(offsetof(struct bpf_array, map) != 0);
	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct bpf_array, pptrs));

	*insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0);
	if (!map->bypass_spec_v1) {
		*insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 6);
		*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_0, array->index_mask);
	} else {
		*insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 5);
	}

	*insn++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
	*insn++ = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1);
	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0);
	*insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
	*insn++ = BPF_MOV64_IMM(BPF_REG_0, 0);
	return insn - insn_buf;
}

static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;

	if (cpu >= nr_cpu_ids)
		return NULL;

	if (unlikely(index >= array->map.max_entries))
		return NULL;

	return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu);
}

int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;
	void __percpu *pptr;
	int cpu, off = 0;
	u32 size;

	if (unlikely(index >= array->map.max_entries))
		return -ENOENT;

	/* per_cpu areas are zero-filled and bpf programs can only
	 * access 'value_size' of them, so copying rounded areas
	 * will not leak any kernel data
	 */
	size = array->elem_size;
	rcu_read_lock();
	pptr = array->pptrs[index & array->index_mask];
	for_each_possible_cpu(cpu) {
		copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
		check_and_init_map_value(map, value + off);
		off += size;
	}
	rcu_read_unlock();
	return 0;
}

/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = key ? *(u32 *)key : U32_MAX;
	u32 *next = (u32 *)next_key;

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

	if (index == array->map.max_entries - 1)
		return -ENOENT;

	*next = index + 1;
	return 0;
}

/* Called from syscall or from eBPF program */
static long array_map_update_elem(struct bpf_map *map, void *key, void *value,
				  u64 map_flags)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;
	char *val;

	if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST))
		/* unknown flags */
		return -EINVAL;

	if (unlikely(index >= array->map.max_entries))
		/* all elements were pre-allocated, cannot insert a new one */
		return -E2BIG;

	if (unlikely(map_flags & BPF_NOEXIST))
		/* all elements already exist */
		return -EEXIST;

	if (unlikely((map_flags & BPF_F_LOCK) &&
		     !btf_record_has_field(map->record, BPF_SPIN_LOCK)))
		return -EINVAL;

	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
		val = this_cpu_ptr(array->pptrs[index & array->index_mask]);
		copy_map_value(map, val, value);
		bpf_obj_free_fields(array->map.record, val);
	} else {
		val = array->value +
			(u64)array->elem_size * (index & array->index_mask);
		if (map_flags & BPF_F_LOCK)
			copy_map_value_locked(map, val, value, false);
		else
			copy_map_value(map, val, value);
		bpf_obj_free_fields(array->map.record, val);
	}
	return 0;
}

int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
			    u64 map_flags)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;
	void __percpu *pptr;
	int cpu, off = 0;
	u32 size;

	if (unlikely(map_flags > BPF_EXIST))
		/* unknown flags */
		return -EINVAL;

	if (unlikely(index >= array->map.max_entries))
		/* all elements were pre-allocated, cannot insert a new one */
		return -E2BIG;

	if (unlikely(map_flags == BPF_NOEXIST))
		/* all elements already exist */
		return -EEXIST;

	/* the user space will provide round_up(value_size, 8) bytes that
	 * will be copied into per-cpu area. bpf programs can only access
	 * value_size of it. During lookup the same extra bytes will be
	 * returned or zeros which were zero-filled by percpu_alloc,
	 * so no kernel data leaks possible
	 */
	size = array->elem_size;
	rcu_read_lock();
	pptr = array->pptrs[index & array->index_mask];
	for_each_possible_cpu(cpu) {
		copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off);
		bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu));
		off += size;
	}
	rcu_read_unlock();
	return 0;
}

/* Called from syscall or from eBPF program */
static long array_map_delete_elem(struct bpf_map *map, void *key)
{
	return -EINVAL;
}

static void *array_map_vmalloc_addr(struct bpf_array *array)
{
	return (void *)round_down((unsigned long)array, PAGE_SIZE);
}

static void array_map_free_timers_wq(struct bpf_map *map)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	int i;

	/* We don't reset or free fields other than timer and workqueue
	 * on uref dropping to zero.
	 */
	if (btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE)) {
		for (i = 0; i < array->map.max_entries; i++) {
			if (btf_record_has_field(map->record, BPF_TIMER))
				bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i));
			if (btf_record_has_field(map->record, BPF_WORKQUEUE))
				bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i));
		}
	}
}

/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void array_map_free(struct bpf_map *map)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	int i;

	if (!IS_ERR_OR_NULL(map->record)) {
		if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
			for (i = 0; i < array->map.max_entries; i++) {
				void __percpu *pptr = array->pptrs[i & array->index_mask];
				int cpu;

				for_each_possible_cpu(cpu) {
					bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu));
					cond_resched();
				}
			}
		} else {
			for (i = 0; i < array->map.max_entries; i++)
				bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i));
		}
	}

	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
		bpf_array_free_percpu(array);

	if (array->map.map_flags & BPF_F_MMAPABLE)
		bpf_map_area_free(array_map_vmalloc_addr(array));
	else
		bpf_map_area_free(array);
}

static void array_map_seq_show_elem(struct bpf_map *map, void *key,
				    struct seq_file *m)
{
	void *value;

	rcu_read_lock();

	value = array_map_lookup_elem(map, key);
	if (!value) {
		rcu_read_unlock();
		return;
	}

	if (map->btf_key_type_id)
		seq_printf(m, "%u: ", *(u32 *)key);
	btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
	seq_putc(m, '\n');

	rcu_read_unlock();
}

static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key,
					   struct seq_file *m)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 index = *(u32 *)key;
	void __percpu *pptr;
	int cpu;

	rcu_read_lock();

	seq_printf(m, "%u: {\n", *(u32 *)key);
	pptr = array->pptrs[index & array->index_mask];
	for_each_possible_cpu(cpu) {
		seq_printf(m, "\tcpu%d: ", cpu);
		btf_type_seq_show(map->btf, map->btf_value_type_id,
				  per_cpu_ptr(pptr, cpu), m);
		seq_putc(m, '\n');
	}
	seq_puts(m, "}\n");

	rcu_read_unlock();
}

static int array_map_check_btf(const struct bpf_map *map,
			       const struct btf *btf,
			       const struct btf_type *key_type,
			       const struct btf_type *value_type)
{
	u32 int_data;

	/* One exception for keyless BTF: .bss/.data/.rodata map */
	if (btf_type_is_void(key_type)) {
		if (map->map_type != BPF_MAP_TYPE_ARRAY ||
		    map->max_entries != 1)
			return -EINVAL;

		if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC)
			return -EINVAL;

		return 0;
	}

	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
		return -EINVAL;

	int_data = *(u32 *)(key_type + 1);
	/* bpf array can only take a u32 key. This check makes sure
	 * that the btf matches the attr used during map_create.
	 */
	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
		return -EINVAL;

	return 0;
}

static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT;

	if (!(map->map_flags & BPF_F_MMAPABLE))
		return -EINVAL;

	if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) >
	    PAGE_ALIGN((u64)array->map.max_entries * array->elem_size))
		return -EINVAL;

	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array),
				   vma->vm_pgoff + pgoff);
}

static bool array_map_meta_equal(const struct bpf_map *meta0,
				 const struct bpf_map *meta1)
{
	if (!bpf_map_meta_equal(meta0, meta1))
		return false;
	return meta0->map_flags & BPF_F_INNER_MAP ? true :
	       meta0->max_entries == meta1->max_entries;
}

struct bpf_iter_seq_array_map_info {
	struct bpf_map *map;
	void *percpu_value_buf;
	u32 index;
};

static void *bpf_array_map_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct bpf_iter_seq_array_map_info *info = seq->private;
	struct bpf_map *map = info->map;
	struct bpf_array *array;
	u32 index;

	if (info->index >= map->max_entries)
		return NULL;

	if (*pos == 0)
		++*pos;
	array = container_of(map, struct bpf_array, map);
	index = info->index & array->index_mask;
	if (info->percpu_value_buf)
		return (void *)(uintptr_t)array->pptrs[index];
	return array_map_elem_ptr(array, index);
}

static void *bpf_array_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct bpf_iter_seq_array_map_info *info = seq->private;
	struct bpf_map *map = info->map;
	struct bpf_array *array;
	u32 index;

	++*pos;
	++info->index;
	if (info->index >= map->max_entries)
		return NULL;

	array = container_of(map, struct bpf_array, map);
	index = info->index & array->index_mask;
	if (info->percpu_value_buf)
		return (void *)(uintptr_t)array->pptrs[index];
	return array_map_elem_ptr(array, index);
}

static int __bpf_array_map_seq_show(struct seq_file *seq, void *v)
{
	struct bpf_iter_seq_array_map_info *info = seq->private;
	struct bpf_iter__bpf_map_elem ctx = {};
	struct bpf_map *map = info->map;
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct bpf_iter_meta meta;
	struct bpf_prog *prog;
	int off = 0, cpu = 0;
	void __percpu *pptr;
	u32 size;

	meta.seq = seq;
	prog = bpf_iter_get_info(&meta, v == NULL);
	if (!prog)
		return 0;

	ctx.meta = &meta;
	ctx.map = info->map;
	if (v) {
		ctx.key = &info->index;

		if (!info->percpu_value_buf) {
			ctx.value = v;
		} else {
			pptr = (void __percpu *)(uintptr_t)v;
			size = array->elem_size;
			for_each_possible_cpu(cpu) {
				copy_map_value_long(map, info->percpu_value_buf + off,
						    per_cpu_ptr(pptr, cpu));
				check_and_init_map_value(map, info->percpu_value_buf + off);
				off += size;
			}
			ctx.value = info->percpu_value_buf;
		}
	}

	return bpf_iter_run_prog(prog, &ctx);
}

static int bpf_array_map_seq_show(struct seq_file *seq, void *v)
{
	return __bpf_array_map_seq_show(seq, v);
}

static void bpf_array_map_seq_stop(struct seq_file *seq, void *v)
{
	if (!v)
		(void)__bpf_array_map_seq_show(seq, NULL);
}

static int bpf_iter_init_array_map(void *priv_data,
				   struct bpf_iter_aux_info *aux)
{
	struct bpf_iter_seq_array_map_info *seq_info = priv_data;
	struct bpf_map *map = aux->map;
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	void *value_buf;
	u32 buf_size;

	if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
		buf_size = array->elem_size * num_possible_cpus();
		value_buf = kmalloc(buf_size, GFP_USER | __GFP_NOWARN);
		if (!value_buf)
			return -ENOMEM;

		seq_info->percpu_value_buf = value_buf;
	}

	/* bpf_iter_attach_map() acquires a map uref, and the uref may be
	 * released before or in the middle of iterating map elements, so
	 * acquire an extra map uref for iterator.
	 */
	bpf_map_inc_with_uref(map);
	seq_info->map = map;
	return 0;
}

static void bpf_iter_fini_array_map(void *priv_data)
{
	struct bpf_iter_seq_array_map_info *seq_info = priv_data;

	bpf_map_put_with_uref(seq_info->map);
	kfree(seq_info->percpu_value_buf);
}

static const struct seq_operations bpf_array_map_seq_ops = {
	.start	= bpf_array_map_seq_start,
	.next	= bpf_array_map_seq_next,
	.stop	= bpf_array_map_seq_stop,
	.show	= bpf_array_map_seq_show,
};

static const struct bpf_iter_seq_info iter_seq_info = {
	.seq_ops		= &bpf_array_map_seq_ops,
	.init_seq_private	= bpf_iter_init_array_map,
	.fini_seq_private	= bpf_iter_fini_array_map,
	.seq_priv_size		= sizeof(struct bpf_iter_seq_array_map_info),
};

static long bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn,
				    void *callback_ctx, u64 flags)
{
	u32 i, key, num_elems = 0;
	struct bpf_array *array;
	bool is_percpu;
	u64 ret = 0;
	void *val;

	if (flags != 0)
		return -EINVAL;

	is_percpu = map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
	array = container_of(map, struct bpf_array, map);
	if (is_percpu)
		migrate_disable();
	for (i = 0; i < map->max_entries; i++) {
		if (is_percpu)
			val = this_cpu_ptr(array->pptrs[i]);
		else
			val = array_map_elem_ptr(array, i);
		num_elems++;
		key = i;
		ret = callback_fn((u64)(long)map, (u64)(long)&key,
				  (u64)(long)val, (u64)(long)callback_ctx, 0);
		/* return value: 0 - continue, 1 - stop and return */
		if (ret)
			break;
	}

	if (is_percpu)
		migrate_enable();
	return num_elems;
}

static u64 array_map_mem_usage(const struct bpf_map *map)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
	u32 elem_size = array->elem_size;
	u64 entries = map->max_entries;
	u64 usage = sizeof(*array);

	if (percpu) {
		usage += entries * sizeof(void *);
		usage += entries * elem_size * num_possible_cpus();
	} else {
		if (map->map_flags & BPF_F_MMAPABLE) {
			usage = PAGE_ALIGN(usage);
			usage += PAGE_ALIGN(entries * elem_size);
		} else {
			usage += entries * elem_size;
		}
	}
	return usage;
}

BTF_ID_LIST_SINGLE(array_map_btf_ids, struct, bpf_array)
const struct bpf_map_ops array_map_ops = {
	.map_meta_equal = array_map_meta_equal,
	.map_alloc_check = array_map_alloc_check,
	.map_alloc = array_map_alloc,
	.map_free = array_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_release_uref = array_map_free_timers_wq,
	.map_lookup_elem = array_map_lookup_elem,
	.map_update_elem = array_map_update_elem,
	.map_delete_elem = array_map_delete_elem,
	.map_gen_lookup = array_map_gen_lookup,
	.map_direct_value_addr = array_map_direct_value_addr,
	.map_direct_value_meta = array_map_direct_value_meta,
	.map_mmap = array_map_mmap,
	.map_seq_show_elem = array_map_seq_show_elem,
	.map_check_btf = array_map_check_btf,
	.map_lookup_batch = generic_map_lookup_batch,
	.map_update_batch = generic_map_update_batch,
	.map_set_for_each_callback_args = map_set_for_each_callback_args,
	.map_for_each_callback = bpf_for_each_array_elem,
	.map_mem_usage = array_map_mem_usage,
	.map_btf_id = &array_map_btf_ids[0],
	.iter_seq_info = &iter_seq_info,
};

const struct bpf_map_ops percpu_array_map_ops = {
	.map_meta_equal = bpf_map_meta_equal,
	.map_alloc_check = array_map_alloc_check,
	.map_alloc = array_map_alloc,
	.map_free = array_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = percpu_array_map_lookup_elem,
	.map_gen_lookup = percpu_array_map_gen_lookup,
	.map_update_elem = array_map_update_elem,
	.map_delete_elem = array_map_delete_elem,
	.map_lookup_percpu_elem = percpu_array_map_lookup_percpu_elem,
	.map_seq_show_elem = percpu_array_map_seq_show_elem,
	.map_check_btf = array_map_check_btf,
	.map_lookup_batch = generic_map_lookup_batch,
	.map_update_batch = generic_map_update_batch,
	.map_set_for_each_callback_args = map_set_for_each_callback_args,
	.map_for_each_callback = bpf_for_each_array_elem,
	.map_mem_usage = array_map_mem_usage,
	.map_btf_id = &array_map_btf_ids[0],
	.iter_seq_info = &iter_seq_info,
};

static int fd_array_map_alloc_check(union bpf_attr *attr)
{
	/* only file descriptors can be stored in this type of map */
	if (attr->value_size != sizeof(u32))
		return -EINVAL;
	/* Program read-only/write-only not supported for special maps yet. */
	if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG))
		return -EINVAL;
	return array_map_alloc_check(attr);
}

static void fd_array_map_free(struct bpf_map *map)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	int i;

	/* make sure it's empty */
	for (i = 0; i < array->map.max_entries; i++)
		BUG_ON(array->ptrs[i] != NULL);

	bpf_map_area_free(array);
}

static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
{
	return ERR_PTR(-EOPNOTSUPP);
}

/* only called from syscall */
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value)
{
	void **elem, *ptr;
	int ret =  0;

	if (!map->ops->map_fd_sys_lookup_elem)
		return -ENOTSUPP;

	rcu_read_lock();
	elem = array_map_lookup_elem(map, key);
	if (elem && (ptr = READ_ONCE(*elem)))
		*value = map->ops->map_fd_sys_lookup_elem(ptr);
	else
		ret = -ENOENT;
	rcu_read_unlock();

	return ret;
}

/* only called from syscall */
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
				 void *key, void *value, u64 map_flags)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	void *new_ptr, *old_ptr;
	u32 index = *(u32 *)key, ufd;

	if (map_flags != BPF_ANY)
		return -EINVAL;

	if (index >= array->map.max_entries)
		return -E2BIG;

	ufd = *(u32 *)value;
	new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
	if (IS_ERR(new_ptr))
		return PTR_ERR(new_ptr);

	if (map->ops->map_poke_run) {
		mutex_lock(&array->aux->poke_mutex);
		old_ptr = xchg(array->ptrs + index, new_ptr);
		map->ops->map_poke_run(map, index, old_ptr, new_ptr);
		mutex_unlock(&array->aux->poke_mutex);
	} else {
		old_ptr = xchg(array->ptrs + index, new_ptr);
	}

	if (old_ptr)
		map->ops->map_fd_put_ptr(map, old_ptr, true);
	return 0;
}

static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	void *old_ptr;
	u32 index = *(u32 *)key;

	if (index >= array->map.max_entries)
		return -E2BIG;

	if (map->ops->map_poke_run) {
		mutex_lock(&array->aux->poke_mutex);
		old_ptr = xchg(array->ptrs + index, NULL);
		map->ops->map_poke_run(map, index, old_ptr, NULL);
		mutex_unlock(&array->aux->poke_mutex);
	} else {
		old_ptr = xchg(array->ptrs + index, NULL);
	}

	if (old_ptr) {
		map->ops->map_fd_put_ptr(map, old_ptr, need_defer);
		return 0;
	} else {
		return -ENOENT;
	}
}

static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
{
	return __fd_array_map_delete_elem(map, key, true);
}

static void *prog_fd_array_get_ptr(struct bpf_map *map,
				   struct file *map_file, int fd)
{
	struct bpf_prog *prog = bpf_prog_get(fd);
	bool is_extended;

	if (IS_ERR(prog))
		return prog;

	if (prog->type == BPF_PROG_TYPE_EXT ||
	    !bpf_prog_map_compatible(map, prog)) {
		bpf_prog_put(prog);
		return ERR_PTR(-EINVAL);
	}

	mutex_lock(&prog->aux->ext_mutex);
	is_extended = prog->aux->is_extended;
	if (!is_extended)
		prog->aux->prog_array_member_cnt++;
	mutex_unlock(&prog->aux->ext_mutex);
	if (is_extended) {
		/* Extended prog can not be tail callee. It's to prevent a
		 * potential infinite loop like:
		 * tail callee prog entry -> tail callee prog subprog ->
		 * freplace prog entry --tailcall-> tail callee prog entry.
		 */
		bpf_prog_put(prog);
		return ERR_PTR(-EBUSY);
	}

	return prog;
}

static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
{
	struct bpf_prog *prog = ptr;

	mutex_lock(&prog->aux->ext_mutex);
	prog->aux->prog_array_member_cnt--;
	mutex_unlock(&prog->aux->ext_mutex);
	/* bpf_prog is freed after one RCU or tasks trace grace period */
	bpf_prog_put(prog);
}

static u32 prog_fd_array_sys_lookup_elem(void *ptr)
{
	return ((struct bpf_prog *)ptr)->aux->id;
}

/* decrement refcnt of all bpf_progs that are stored in this map */
static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	int i;

	for (i = 0; i < array->map.max_entries; i++)
		__fd_array_map_delete_elem(map, &i, need_defer);
}

static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
					 struct seq_file *m)
{
	void **elem, *ptr;
	u32 prog_id;

	rcu_read_lock();

	elem = array_map_lookup_elem(map, key);
	if (elem) {
		ptr = READ_ONCE(*elem);
		if (ptr) {
			seq_printf(m, "%u: ", *(u32 *)key);
			prog_id = prog_fd_array_sys_lookup_elem(ptr);
			btf_type_seq_show(map->btf, map->btf_value_type_id,
					  &prog_id, m);
			seq_putc(m, '\n');
		}
	}

	rcu_read_unlock();
}

struct prog_poke_elem {
	struct list_head list;
	struct bpf_prog_aux *aux;
};

static int prog_array_map_poke_track(struct bpf_map *map,
				     struct bpf_prog_aux *prog_aux)
{
	struct prog_poke_elem *elem;
	struct bpf_array_aux *aux;
	int ret = 0;

	aux = container_of(map, struct bpf_array, map)->aux;
	mutex_lock(&aux->poke_mutex);
	list_for_each_entry(elem, &aux->poke_progs, list) {
		if (elem->aux == prog_aux)
			goto out;
	}

	elem = kmalloc(sizeof(*elem), GFP_KERNEL);
	if (!elem) {
		ret = -ENOMEM;
		goto out;
	}

	INIT_LIST_HEAD(&elem->list);
	/* We must track the program's aux info at this point in time
	 * since the program pointer itself may not be stable yet, see
	 * also comment in prog_array_map_poke_run().
	 */
	elem->aux = prog_aux;

	list_add_tail(&elem->list, &aux->poke_progs);
out:
	mutex_unlock(&aux->poke_mutex);
	return ret;
}

static void prog_array_map_poke_untrack(struct bpf_map *map,
					struct bpf_prog_aux *prog_aux)
{
	struct prog_poke_elem *elem, *tmp;
	struct bpf_array_aux *aux;

	aux = container_of(map, struct bpf_array, map)->aux;
	mutex_lock(&aux->poke_mutex);
	list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) {
		if (elem->aux == prog_aux) {
			list_del_init(&elem->list);
			kfree(elem);
			break;
		}
	}
	mutex_unlock(&aux->poke_mutex);
}

void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
				      struct bpf_prog *new, struct bpf_prog *old)
{
	WARN_ON_ONCE(1);
}

static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
				    struct bpf_prog *old,
				    struct bpf_prog *new)
{
	struct prog_poke_elem *elem;
	struct bpf_array_aux *aux;

	aux = container_of(map, struct bpf_array, map)->aux;
	WARN_ON_ONCE(!mutex_is_locked(&aux->poke_mutex));

	list_for_each_entry(elem, &aux->poke_progs, list) {
		struct bpf_jit_poke_descriptor *poke;
		int i;

		for (i = 0; i < elem->aux->size_poke_tab; i++) {
			poke = &elem->aux->poke_tab[i];

			/* Few things to be aware of:
			 *
			 * 1) We can only ever access aux in this context, but
			 *    not aux->prog since it might not be stable yet and
			 *    there could be danger of use after free otherwise.
			 * 2) Initially when we start tracking aux, the program
			 *    is not JITed yet and also does not have a kallsyms
			 *    entry. We skip these as poke->tailcall_target_stable
			 *    is not active yet. The JIT will do the final fixup
			 *    before setting it stable. The various
			 *    poke->tailcall_target_stable are successively
			 *    activated, so tail call updates can arrive from here
			 *    while JIT is still finishing its final fixup for
			 *    non-activated poke entries.
			 * 3) Also programs reaching refcount of zero while patching
			 *    is in progress is okay since we're protected under
			 *    poke_mutex and untrack the programs before the JIT
			 *    buffer is freed.
			 */
			if (!READ_ONCE(poke->tailcall_target_stable))
				continue;
			if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
				continue;
			if (poke->tail_call.map != map ||
			    poke->tail_call.key != key)
				continue;

			bpf_arch_poke_desc_update(poke, new, old);
		}
	}
}

static void prog_array_map_clear_deferred(struct work_struct *work)
{
	struct bpf_map *map = container_of(work, struct bpf_array_aux,
					   work)->map;
	bpf_fd_array_map_clear(map, true);
	bpf_map_put(map);
}

static void prog_array_map_clear(struct bpf_map *map)
{
	struct bpf_array_aux *aux = container_of(map, struct bpf_array,
						 map)->aux;
	bpf_map_inc(map);
	schedule_work(&aux->work);
}

static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
{
	struct bpf_array_aux *aux;
	struct bpf_map *map;

	aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT);
	if (!aux)
		return ERR_PTR(-ENOMEM);

	INIT_WORK(&aux->work, prog_array_map_clear_deferred);
	INIT_LIST_HEAD(&aux->poke_progs);
	mutex_init(&aux->poke_mutex);

	map = array_map_alloc(attr);
	if (IS_ERR(map)) {
		kfree(aux);
		return map;
	}

	container_of(map, struct bpf_array, map)->aux = aux;
	aux->map = map;

	return map;
}

static void prog_array_map_free(struct bpf_map *map)
{
	struct prog_poke_elem *elem, *tmp;
	struct bpf_array_aux *aux;

	aux = container_of(map, struct bpf_array, map)->aux;
	list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) {
		list_del_init(&elem->list);
		kfree(elem);
	}
	kfree(aux);
	fd_array_map_free(map);
}

/* prog_array->aux->{type,jited} is a runtime binding.
 * Doing static check alone in the verifier is not enough.
 * Thus, prog_array_map cannot be used as an inner_map
 * and map_meta_equal is not implemented.
 */
const struct bpf_map_ops prog_array_map_ops = {
	.map_alloc_check = fd_array_map_alloc_check,
	.map_alloc = prog_array_map_alloc,
	.map_free = prog_array_map_free,
	.map_poke_track = prog_array_map_poke_track,
	.map_poke_untrack = prog_array_map_poke_untrack,
	.map_poke_run = prog_array_map_poke_run,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = fd_array_map_lookup_elem,
	.map_delete_elem = fd_array_map_delete_elem,
	.map_fd_get_ptr = prog_fd_array_get_ptr,
	.map_fd_put_ptr = prog_fd_array_put_ptr,
	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
	.map_release_uref = prog_array_map_clear,
	.map_seq_show_elem = prog_array_map_seq_show_elem,
	.map_mem_usage = array_map_mem_usage,
	.map_btf_id = &array_map_btf_ids[0],
};

static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
						   struct file *map_file)
{
	struct bpf_event_entry *ee;

	ee = kzalloc(sizeof(*ee), GFP_KERNEL);
	if (ee) {
		ee->event = perf_file->private_data;
		ee->perf_file = perf_file;
		ee->map_file = map_file;
	}

	return ee;
}

static void __bpf_event_entry_free(struct rcu_head *rcu)
{
	struct bpf_event_entry *ee;

	ee = container_of(rcu, struct bpf_event_entry, rcu);
	fput(ee->perf_file);
	kfree(ee);
}

static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee)
{
	call_rcu(&ee->rcu, __bpf_event_entry_free);
}

static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
					 struct file *map_file, int fd)
{
	struct bpf_event_entry *ee;
	struct perf_event *event;
	struct file *perf_file;
	u64 value;

	perf_file = perf_event_get(fd);
	if (IS_ERR(perf_file))
		return perf_file;

	ee = ERR_PTR(-EOPNOTSUPP);
	event = perf_file->private_data;
	if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP)
		goto err_out;

	ee = bpf_event_entry_gen(perf_file, map_file);
	if (ee)
		return ee;
	ee = ERR_PTR(-ENOMEM);
err_out:
	fput(perf_file);
	return ee;
}

static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
{
	/* bpf_perf_event is freed after one RCU grace period */
	bpf_event_entry_free_rcu(ptr);
}

static void perf_event_fd_array_release(struct bpf_map *map,
					struct file *map_file)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct bpf_event_entry *ee;
	int i;

	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
		return;

	rcu_read_lock();
	for (i = 0; i < array->map.max_entries; i++) {
		ee = READ_ONCE(array->ptrs[i]);
		if (ee && ee->map_file == map_file)
			__fd_array_map_delete_elem(map, &i, true);
	}
	rcu_read_unlock();
}

static void perf_event_fd_array_map_free(struct bpf_map *map)
{
	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
		bpf_fd_array_map_clear(map, false);
	fd_array_map_free(map);
}

const struct bpf_map_ops perf_event_array_map_ops = {
	.map_meta_equal = bpf_map_meta_equal,
	.map_alloc_check = fd_array_map_alloc_check,
	.map_alloc = array_map_alloc,
	.map_free = perf_event_fd_array_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = fd_array_map_lookup_elem,
	.map_delete_elem = fd_array_map_delete_elem,
	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
	.map_release = perf_event_fd_array_release,
	.map_check_btf = map_check_no_btf,
	.map_mem_usage = array_map_mem_usage,
	.map_btf_id = &array_map_btf_ids[0],
};

#ifdef CONFIG_CGROUPS
static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
				     struct file *map_file /* not used */,
				     int fd)
{
	return cgroup_get_from_fd(fd);
}

static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
{
	/* cgroup_put free cgrp after a rcu grace period */
	cgroup_put(ptr);
}

static void cgroup_fd_array_free(struct bpf_map *map)
{
	bpf_fd_array_map_clear(map, false);
	fd_array_map_free(map);
}

const struct bpf_map_ops cgroup_array_map_ops = {
	.map_meta_equal = bpf_map_meta_equal,
	.map_alloc_check = fd_array_map_alloc_check,
	.map_alloc = array_map_alloc,
	.map_free = cgroup_fd_array_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = fd_array_map_lookup_elem,
	.map_delete_elem = fd_array_map_delete_elem,
	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
	.map_check_btf = map_check_no_btf,
	.map_mem_usage = array_map_mem_usage,
	.map_btf_id = &array_map_btf_ids[0],
};
#endif

static struct bpf_map *array_of_map_alloc(union bpf_attr *attr)
{
	struct bpf_map *map, *inner_map_meta;

	inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
	if (IS_ERR(inner_map_meta))
		return inner_map_meta;

	map = array_map_alloc(attr);
	if (IS_ERR(map)) {
		bpf_map_meta_free(inner_map_meta);
		return map;
	}

	map->inner_map_meta = inner_map_meta;

	return map;
}

static void array_of_map_free(struct bpf_map *map)
{
	/* map->inner_map_meta is only accessed by syscall which
	 * is protected by fdget/fdput.
	 */
	bpf_map_meta_free(map->inner_map_meta);
	bpf_fd_array_map_clear(map, false);
	fd_array_map_free(map);
}

static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_map **inner_map = array_map_lookup_elem(map, key);

	if (!inner_map)
		return NULL;

	return READ_ONCE(*inner_map);
}

static int array_of_map_gen_lookup(struct bpf_map *map,
				   struct bpf_insn *insn_buf)
{
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u32 elem_size = array->elem_size;
	struct bpf_insn *insn = insn_buf;
	const int ret = BPF_REG_0;
	const int map_ptr = BPF_REG_1;
	const int index = BPF_REG_2;

	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
	if (!map->bypass_spec_v1) {
		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
	} else {
		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
	}
	if (is_power_of_2(elem_size))
		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
	else
		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
	*insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0);
	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
	*insn++ = BPF_MOV64_IMM(ret, 0);

	return insn - insn_buf;
}

const struct bpf_map_ops array_of_maps_map_ops = {
	.map_alloc_check = fd_array_map_alloc_check,
	.map_alloc = array_of_map_alloc,
	.map_free = array_of_map_free,
	.map_get_next_key = array_map_get_next_key,
	.map_lookup_elem = array_of_map_lookup_elem,
	.map_delete_elem = fd_array_map_delete_elem,
	.map_fd_get_ptr = bpf_map_fd_get_ptr,
	.map_fd_put_ptr = bpf_map_fd_put_ptr,
	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
	.map_gen_lookup = array_of_map_gen_lookup,
	.map_lookup_batch = generic_map_lookup_batch,
	.map_update_batch = generic_map_update_batch,
	.map_check_btf = map_check_no_btf,
	.map_mem_usage = array_map_mem_usage,
	.map_btf_id = &array_map_btf_ids[0],
};